chore: bump version

Just a small thing now, as nodes are all still wip, but since
@psychedelicious was nice enough to add the progress image node for me,
what I noticed was missing now is the cancel button on nodes tab

.github/workflows/test-invoke-pip-skip.yml

@@ -1,10 +1,16 @@
 name: Test invoke.py pip
+
+# This is a dummy stand-in for the actual tests
+# we don't need to run python tests on non-Python changes
+# But PRs require passing tests to be mergeable
+
 on:
   pull_request:
     paths:
       - '**'
       - '!pyproject.toml'
       - '!invokeai/**'
+      - '!tests/**'
       - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
@@ -19,48 +25,26 @@ jobs:
     strategy:
       matrix:
         python-version:
-          # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
-            github-env: $GITHUB_ENV
           - pytorch: linux-rocm-5_2
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
           - pytorch: linux-cpu
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
           - pytorch: macos-default
             os: macOS-12
-            github-env: $GITHUB_ENV
           - pytorch: windows-cpu
             os: windows-2022
-            github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     steps:
-      - run: 'echo "No build required"'
+      - name: skip
+        run: echo "no build required"

.github/workflows/test-invoke-pip.yml

@@ -11,6 +11,7 @@ on:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
+      - 'tests/**'
       - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
@@ -32,19 +33,12 @@ jobs:
           # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
             github-env: $GITHUB_ENV
@@ -62,14 +56,6 @@ jobs:
           - pytorch: windows-cpu
             os: windows-2022
             github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     env:
@@ -100,40 +86,38 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: run invokeai-configure
-        id: run-preload-models
-        env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-        run: >
-          invokeai-configure
-          --yes
-          --default_only
-          --full-precision
-        # can't use fp16 weights without a GPU
+      # - name: run invokeai-configure
+      #   env:
+      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
+      #   run: >
+      #     invokeai-configure
+      #     --yes
+      #     --default_only
+      #     --full-precision
+      #   # can't use fp16 weights without a GPU
 
-      - name: run invokeai
-        id: run-invokeai
-        env:
-          # Set offline mode to make sure configure preloaded successfully.
-          HF_HUB_OFFLINE: 1
-          HF_DATASETS_OFFLINE: 1
-          TRANSFORMERS_OFFLINE: 1
-          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-        run: >
-          invokeai
-          --no-patchmatch
-          --no-nsfw_checker
-          --precision=float32
-          --always_use_cpu
-          --use_memory_db
-          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
-          --from_file ${{ env.TEST_PROMPTS }}
+      # - name: run invokeai
+      #   id: run-invokeai
+      #   env:
+      #     # Set offline mode to make sure configure preloaded successfully.
+      #     HF_HUB_OFFLINE: 1
+      #     HF_DATASETS_OFFLINE: 1
+      #     TRANSFORMERS_OFFLINE: 1
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   run: >
+      #     invokeai
+      #     --no-patchmatch
+      #     --no-nsfw_checker
+      #     --precision=float32
+      #     --always_use_cpu
+      #     --use_memory_db
+      #     --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+      #     --from_file ${{ env.TEST_PROMPTS }}
 
-      - name: Archive results
-        id: archive-results
-        env:
-          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-        uses: actions/upload-artifact@v3
-        with:
-          name: results
-          path: ${{ env.INVOKEAI_OUTDIR }}
+      # - name: Archive results
+      #   env:
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   uses: actions/upload-artifact@v3
+      #   with:
+      #     name: results
+      #     path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -34,7 +34,7 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-dist/
+# dist/
 downloads/
 eggs/
 .eggs/
@@ -79,6 +79,7 @@ cov.xml
 .pytest.ini
 cover/
 junit/
+notes/
 
 # Translations
 *.mo
@@ -201,7 +202,8 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
-invokeai/frontend/web/dist/*
+invokeai/frontend/yarn.lock
+invokeai/frontend/node_modules
 
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*

README.md

@@ -1,8 +1,11 @@
 <div align="center">
 
-![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
+![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
+
+# Invoke AI - Generative AI for Professional Creatives
+## Image Generation for Stable Diffusion, Custom-Trained Models, and more. 
+  Learn more about us and get started instantly at [invoke.ai](https://invoke.ai)
 
-# InvokeAI: A Stable Diffusion Toolkit
 
 [![discord badge]][discord link]
 
@@ -33,15 +36,32 @@
 
 </div>
 
-_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+_**Note: This is an alpha release. Bugs are expected and not all
+features are fully implemented. Please use the GitHub [Issues
+pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
+to report unexpected problems. Also note that InvokeAI root directory
+which contains models, outputs and configuration files, has changed
+between the 2.x and 3.x release. If you wish to use your v2.3 root
+directory with v3.0, please follow the directions in [Migrating a 2.3
+root directory to 3.0](#migrating-to-3).**_
 
-InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
+InvokeAI is a leading creative engine built to empower professionals
+and enthusiasts alike. Generate and create stunning visual media using
+the latest AI-driven technologies. InvokeAI offers an industry leading
+Web Interface, interactive Command Line Interface, and also serves as
+the foundation for multiple commercial products.
 
-**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
-
-_Note: InvokeAI is rapidly evolving. Please use the
-[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
-requests. Be sure to use the provided templates. They will help us diagnose issues faster._
+**Quick links**: [[How to
+  Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a
+  href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a
+  href="https://invoke-ai.github.io/InvokeAI/">Documentation and
+  Tutorials</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/">Code and
+  Downloads</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>]
+  [<a
+  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
+  Ideas & Q&A</a>]
 
 <div align="center">
 
@@ -51,22 +71,30 @@ requests. Be sure to use the provided templates. They will help us diagnose issu
 
 ## Table of Contents
 
-1. [Quick Start](#getting-started-with-invokeai)
-2. [Installation](#detailed-installation-instructions)
-3. [Hardware Requirements](#hardware-requirements)
-4. [Features](#features)
-5. [Latest Changes](#latest-changes)
-6. [Troubleshooting](#troubleshooting)
-7. [Contributing](#contributing)
-8. [Contributors](#contributors)
-9. [Support](#support)
-10. [Further Reading](#further-reading)
+Table of Contents 📝
 
-## Getting Started with InvokeAI
+**Getting Started**
+1. 🏁 [Quick Start](#quick-start) 
+3. 🖥️ [Hardware Requirements](#hardware-requirements) 
+
+**More About Invoke**
+1. 🌟 [Features](#features) 
+2. 📣 [Latest Changes](#latest-changes) 
+3. 🛠️ [Troubleshooting](#troubleshooting) 
+
+**Supporting the Project**
+1. 🤝 [Contributing](#contributing) 
+2. 👥 [Contributors](#contributors) 
+3. 💕 [Support](#support) 
+
+## Quick Start
 
 For full installation and upgrade instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
+If upgrading from version 2.3, please read [Migrating a 2.3 root
+directory to 3.0](#migrating-to-3) first.
+
 ### Automatic Installer (suggested for 1st time users)
 
 1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
@@ -75,9 +103,8 @@ For full installation and upgrade instructions, please see:
 
 3. Unzip the file.
 
-4. If you are on Windows, double-click on the `install.bat` script. On
-macOS, open a Terminal window, drag the file `install.sh` from Finder
-into the Terminal, and press return. On Linux, run `install.sh`.
+4. **Windows:** double-click on the `install.bat` script. **macOS:** Open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. **Linux:** run `install.sh`.
 
 5. You'll be asked to confirm the location of the folder in which
 to install InvokeAI and its image generation model files. Pick a
@@ -103,7 +130,7 @@ and go to http://localhost:9090.
 
 10. Type `banana sushi` in the box on the top left and click `Invoke`
 
-### Command-Line Installation (for users familiar with Terminals)
+### Command-Line Installation (for developers and users familiar with Terminals)
 
 You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
 not supported.
@@ -179,7 +206,7 @@ not supported.
 Be sure to activate the virtual environment each time before re-launching InvokeAI,
 using `source .venv/bin/activate` or `.venv\Scripts\activate`.
 
-### Detailed Installation Instructions
+## Detailed Installation Instructions
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
@@ -187,6 +214,87 @@ AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
 
+<a name="migrating-to-3"></a>
+### Migrating a v2.3 InvokeAI root directory
+
+The InvokeAI root directory is where the InvokeAI startup file,
+installed models, and generated images are stored. It is ordinarily
+named `invokeai` and located in your home directory. The contents and
+layout of this directory has changed between versions 2.3 and 3.0 and
+cannot be used directly.
+
+We currently recommend that you use the installer to create a new root
+directory named differently from the 2.3 one, e.g. `invokeai-3` and
+then use a migration script to copy your 2.3 models into the new
+location. However, if you choose, you can upgrade this directory in
+place.  This section gives both recipes.
+
+#### Creating a new root directory and migrating old models
+
+This is the safer recipe because it leaves your old root directory in
+place to fall back on.
+
+1. Follow the instructions above to create and install InvokeAI in a
+directory that has a different name from the 2.3 invokeai directory.
+In this example, we will use "invokeai-3"
+
+2. When you are prompted to select models to install, select a minimal
+set of models, such as stable-diffusion-v1.5 only.
+
+3. After installation is complete launch `invokeai.sh` (Linux/Mac) or
+`invokeai.bat` and select option 8 "Open the developers console". This
+will take you to the command line.
+
+4. Issue the command `invokeai-migrate3 --from /path/to/v2.3-root --to
+/path/to/invokeai-3-root`. Provide the correct `--from` and `--to`
+paths for your v2.3 and v3.0 root directories respectively.
+
+This will copy and convert your old models from 2.3 format to 3.0
+format and create a new `models` directory in the 3.0 directory. The
+old models directory (which contains the models selected at install
+time) will be renamed `models.orig` and can be deleted once you have
+confirmed that the migration was successful.
+
+#### Migrating in place
+
+For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
+without touching the command line. The recipe is as follows>
+
+1. Launch the InvokeAI launcher script in your current v2.3 root directory.
+
+2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
+
+3a. During the alpha release phase, select option [3] and manually
+enter the tag name `v3.0.0+a2`.
+
+3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
+
+4. Once the upgrade is finished you will be returned to the launcher
+menu. Select option [7] "Re-run the configure script to fix a broken
+install or to complete a major upgrade".
+
+This will run the configure script against the v2.3 directory and
+update it to the 3.0 format. The following files will be replaced:
+
+  - The invokeai.init file, replaced by invokeai.yaml
+  - The models directory
+  - The configs/models.yaml model index
+  
+The original versions of these files will be saved with the suffix
+".orig" appended to the end. Once you have confirmed that the upgrade
+worked, you can safely remove these files. Alternatively you can
+restore a working v2.3 directory by removing the new files and
+restoring the ".orig" files' original names.
+
+#### Migration Caveats
+
+The migration script will migrate your invokeai settings and models,
+including textual inversion models, LoRAs and merges that you may have
+installed previously. However it does **not** migrate the generated
+images stored in your 2.3-format outputs directory. The released
+version of 3.0 is expected to have an interface for importing an
+entire directory of image files as a batch.
+
 ## Hardware Requirements
 
 InvokeAI is supported across Linux, Windows and macOS. Linux
@@ -205,13 +313,9 @@ We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
 to render 512x512 images.
 
-### Memory
+**Memory** - At least 12 GB Main Memory RAM.
 
-- At least 12 GB Main Memory RAM.
-
-### Disk
-
-- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
+**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
 ## Features
 
@@ -227,7 +331,7 @@ The Unified Canvas is a fully integrated canvas implementation with support for
 
 ### *Advanced Prompt Syntax*
 
-InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
+Invoke AI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space. 
 
 ### *Command Line Interface*
 
@@ -237,16 +341,12 @@ For users utilizing a terminal-based environment, or who want to take advantage
 
 - *Support for both ckpt and diffusers models*
 - *SD 2.0, 2.1 support*
-- *Noise Control & Tresholding*
-- *Popular Sampler Support*
 - *Upscaling & Face Restoration Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-
-### Coming Soon
-
-- *Node-Based Architecture & UI*
-- And more...
+- *Node-Based Architecture*
+- *Node-Based Plug-&-Play UI (Beta)*
+- *Boards & Gallery Management
 
 ### Latest Changes
 
@@ -254,12 +354,12 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-## Troubleshooting
+### Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
 
-## Contributing
+## 🤝 Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
 cleanup, testing, or code reviews, is very much encouraged to do so.
@@ -278,14 +378,12 @@ to become part of our community.
 
 Welcome to InvokeAI!
 
-### Contributors
+### 👥 Contributors
 
 This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
-Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
-
 ### Support
 
 For support, please use this repository's GitHub Issues tracking service, or join the Discord.

docs/CHANGELOG.md

@@ -4,6 +4,236 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
+## v2.3.5 <small>(22 May 2023)</small>
+
+This release (along with the post1 and post2 follow-on releases) expands support for additional LoRA and LyCORIS models, upgrades diffusers versions, and fixes a few bugs.
+
+### LoRA and LyCORIS Support Improvement
+
+    A number of LoRA/LyCORIS fine-tune files (those which alter the text encoder as well as the unet model) were not having the desired effect in InvokeAI. This bug has now been fixed. Full documentation of LoRA support is available at InvokeAI LoRA Support.
+    Previously, InvokeAI did not distinguish between LoRA/LyCORIS models based on Stable Diffusion v1.5 vs those based on v2.0 and 2.1, leading to a crash when an incompatible model was loaded. This has now been fixed. In addition, the web pulldown menus for LoRA and Textual Inversion selection have been enhanced to show only those files that are compatible with the currently-selected Stable Diffusion model.
+    Support for the newer LoKR LyCORIS files has been added.
+
+### Library Updates and Speed/Reproducibility Advancements
+The major enhancement in this version is that NVIDIA users no longer need to decide between speed and reproducibility. Previously, if you activated the Xformers library, you would see improvements in speed and memory usage, but multiple images generated with the same seed and other parameters would be slightly different from each other. This is no longer the case. Relative to 2.3.5 you will see improved performance when running without Xformers, and even better performance when Xformers is activated. In both cases, images generated with the same settings will be identical.
+
+Here are the new library versions:
+Library 	Version
+Torch 	2.0.0
+Diffusers 	0.16.1
+Xformers 	0.0.19
+Compel 	1.1.5
+Other Improvements
+
+### Performance Improvements
+
+    When a model is loaded for the first time, InvokeAI calculates its checksum for incorporation into the PNG metadata. This process could take up to a minute on network-mounted disks and WSL mounts. This release noticeably speeds up the process.
+
+### Bug Fixes
+
+    The "import models from directory" and "import from URL" functionality in the console-based model installer has now been fixed.
+    When running the WebUI, we have reduced the number of times that InvokeAI reaches out to HuggingFace to fetch the list of embeddable Textual Inversion models. We have also caught and fixed a problem with the updater not correctly detecting when another instance of the updater is running 
+
+
+## v2.3.4 <small>(7 April 2023)</small>
+
+What's New in 2.3.4
+
+This features release adds support for LoRA (Low-Rank Adaptation) and LyCORIS (Lora beYond Conventional) models, as well as some minor bug fixes.
+### LoRA and LyCORIS Support
+
+LoRA files contain fine-tuning weights that enable particular styles, subjects or concepts to be applied to generated images. LyCORIS files are an extended variant of LoRA. InvokeAI supports the most common LoRA/LyCORIS format, which ends in the suffix .safetensors. You will find numerous LoRA and LyCORIS models for download at Civitai, and a small but growing number at Hugging Face. Full documentation of LoRA support is available at InvokeAI LoRA Support.( Pre-release note: this page will only be available after release)
+
+To use LoRA/LyCORIS models in InvokeAI:
+
+    Download the .safetensors files of your choice and place in /path/to/invokeai/loras. This directory was not present in earlier version of InvokeAI but will be created for you the first time you run the command-line or web client. You can also create the directory manually.
+
+    Add withLora(lora-file,weight) to your prompts. The weight is optional and will default to 1.0. A few examples, assuming that a LoRA file named loras/sushi.safetensors is present:
+
+family sitting at dinner table eating sushi withLora(sushi,0.9)
+family sitting at dinner table eating sushi withLora(sushi, 0.75)
+family sitting at dinner table eating sushi withLora(sushi)
+
+Multiple withLora() prompt fragments are allowed. The weight can be arbitrarily large, but the useful range is roughly 0.5 to 1.0. Higher weights make the LoRA's influence stronger. Negative weights are also allowed, which can lead to some interesting effects.
+
+    Generate as you usually would! If you find that the image is too "crisp" try reducing the overall CFG value or reducing individual LoRA weights. As is the case with all fine-tunes, you'll get the best results when running the LoRA on top of the model similar to, or identical with, the one that was used during the LoRA's training. Don't try to load a SD 1.x-trained LoRA into a SD 2.x model, and vice versa. This will trigger a non-fatal error message and generation will not proceed.
+
+    You can change the location of the loras directory by passing the --lora_directory option to `invokeai.
+
+### New WebUI LoRA and Textual Inversion Buttons
+
+This version adds two new web interface buttons for inserting LoRA and Textual Inversion triggers into the prompt as shown in the screenshot below.
+
+Clicking on one or the other of the buttons will bring up a menu of available LoRA/LyCORIS or Textual Inversion trigger terms. Select a menu item to insert the properly-formatted withLora() or <textual-inversion> prompt fragment into the positive prompt. The number in parentheses indicates the number of trigger terms currently in the prompt. You may click the button again and deselect the LoRA or trigger to remove it from the prompt, or simply edit the prompt directly.
+
+Currently terms are inserted into the positive prompt textbox only. However, some textual inversion embeddings are designed to be used with negative prompts. To move a textual inversion trigger into the negative prompt, simply cut and paste it.
+
+By default the Textual Inversion menu only shows locally installed models found at startup time in /path/to/invokeai/embeddings. However, InvokeAI has the ability to dynamically download and install additional Textual Inversion embeddings from the HuggingFace Concepts Library. You may choose to display the most popular of these (with five or more likes) in the Textual Inversion menu by going to Settings and turning on "Show Textual Inversions from HF Concepts Library." When this option is activated, the locally-installed TI embeddings will be shown first, followed by uninstalled terms from Hugging Face. See The Hugging Face Concepts Library and Importing Textual Inversion files for more information.
+### Minor features and fixes
+
+This release changes model switching behavior so that the command-line and Web UIs save the last model used and restore it the next time they are launched. It also improves the behavior of the installer so that the pip utility is kept up to date.
+  
+### Known Bugs in 2.3.4
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.3 <small>(28 March 2023)</small>
+
+This is a bugfix and minor feature release.
+### Bugfixes
+
+Since version 2.3.2 the following bugs have been fixed:
+Bugs
+
+    When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
+    Textual inversion will select an appropriate batchsize based on whether xformers is active, and will default to xformers enabled if the library is detected.
+    The batch script log file names have been fixed to be compatible with Windows.
+    Occasional corruption of the .next_prefix file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
+    Support loading of legacy config files that have no personalization (textual inversion) section.
+    An infinite loop when opening the developer's console from within the invoke.sh script has been corrected.
+    Documentation fixes, including a recipe for detecting and fixing problems with the AMD GPU ROCm driver.
+
+Enhancements
+
+    It is now possible to load and run several community-contributed SD-2.0 based models, including the often-requested "Illuminati" model.
+    The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI embeddings directory.
+    If no --model is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
+    On Linux systems, the invoke.sh launcher now uses a prettier console-based interface. To take advantage of it, install the dialog package using your package manager (e.g. sudo apt install dialog).
+    When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
+
+my-favorite-model.ckpt
+my-favorite-model.yaml
+my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
+
+### Known Bugs in 2.3.3
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.2 <small>(11 March 2023)</small>
+This is a bugfix and minor feature release.
+
+### Bugfixes
+
+Since version 2.3.1 the following bugs have been fixed:
+
+    Black images appearing for potential NSFW images when generating with legacy checkpoint models and both --no-nsfw_checker and --ckpt_convert turned on.
+    Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
+    The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
+    When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
+    Crashes that occurred during model merging.
+    Restore previous naming of Stable Diffusion base and 768 models.
+    Upgraded to latest versions of diffusers, transformers, safetensors and accelerate libraries upstream. We hope that this will fix the assertion NDArray > 2**32 issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
+
+As part of the upgrade to diffusers, the location of the diffusers-based models has changed from models/diffusers to models/hub. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your models/diffusers directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
+New "Invokeai-batch" script
+
+### Invoke AI Batch
+2.3.2 introduces a new command-line only script called invokeai-batch that can be used to generate hundreds of images from prompts and settings that vary systematically. This can be used to try the same prompt across multiple combinations of models, steps, CFG settings and so forth. It also allows you to template prompts and generate a combinatorial list like:
+
+a shack in the mountains, photograph
+a shack in the mountains, watercolor
+a shack in the mountains, oil painting
+a chalet in the mountains, photograph
+a chalet in the mountains, watercolor
+a chalet in the mountains, oil painting
+a shack in the desert, photograph
+...
+
+If you have a system with multiple GPUs, or a single GPU with lots of VRAM, you can parallelize generation across the combinatorial set, reducing wait times and using your system's resources efficiently (make sure you have good GPU cooling).
+
+To try invokeai-batch out. Launch the "developer's console" using the invoke launcher script, or activate the invokeai virtual environment manually. From the console, give the command invokeai-batch --help in order to learn how the script works and create your first template file for dynamic prompt generation.
+
+
+### Known Bugs in 2.3.2
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise a Trojan alert for the codeformer.pth face restoration model. As far as we have been able to determine, this is a false positive and can be safely whitelisted.
+
+
+## v2.3.1 <small>(22 February 2023)</small>
+This is primarily a bugfix release, but it does provide several new features that will improve the user experience.
+
+### Enhanced support for model management
+
+InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
+
+There are three ways of accessing the model management features:
+
+    From the WebUI, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
+
+    Using the Model Installer App
+
+Choose option (5) download and install models from the invoke launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
+
+Command-line users can start this app using the command invokeai-model-install.
+
+    Using the Command Line Client (CLI)
+
+The !install_model and !convert_model commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
+
+Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do not need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
+
+Please see INSTALLING MODELS for more information on model management.
+
+### An Improved Installer Experience
+
+The installer now launches a console-based UI for setting and changing commonly-used startup options:
+
+After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time, you can edit the startup options by launching invoke.sh/invoke.bat and entering option (6) change InvokeAI startup options
+
+Command-line users can launch the new configure app using invokeai-configure.
+
+This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch invoke.sh or invoke.bat and choose option (9) update InvokeAI . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
+
+Command-line users can run this interface by typing invokeai-configure
+
+### Image Symmetry Options
+
+There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting Symmetry from the image generation settings, or within the CLI by using the options --h_symmetry_time_pct and --v_symmetry_time_pct (these can be abbreviated to --h_sym and --v_sym like all other options).
+
+### A New Unified Canvas Look
+
+This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select Use Canvas Beta Layout:
+
+Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
+
+Model conversion and merging within the WebUI
+
+The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the invoke.sh/invoke.bat scripts.
+An easier way to contribute translations to the WebUI
+
+We have migrated our translation efforts to Weblate, a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief translation guide for more information on how to contribute.
+Numerous internal bugfixes and performance issues
+
+### Bug Fixes
+This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to diffusers 0.13.0, and using the compel library for prompt parsing. See Detailed Change Log for a detailed list of bugs caught and squished.
+Summary of InvokeAI command line scripts (all accessible via the launcher menu)
+Command 	Description
+invokeai 	Command line interface
+invokeai --web 	Web interface
+invokeai-model-install 	Model installer with console forms-based front end
+invokeai-ti --gui 	Textual inversion, with a console forms-based front end
+invokeai-merge --gui 	Model merging, with a console forms-based front end
+invokeai-configure 	Startup configuration; can also be used to reinstall support models
+invokeai-update 	InvokeAI software updater
+
+### Known Bugs in 2.3.1
+
+These are known bugs in the release.
+    MacOS users generating 768x768 pixel images or greater using diffusers models may experience a hard crash with assertion NDArray > 2**32 This appears to be an issu...
+
+
+
 ## v2.3.0 <small>(15 January 2023)</small>
 
 **Transition to diffusers
@@ -264,7 +494,7 @@ sections describe what's new for InvokeAI.
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
 - The ability to save frequently-used startup options (model to load, steps,
   sampler, etc) in a `.invokeai` file. See
-  [Client](features/CLI.md)
+  [Client](deprecated/CLI.md)
 - Support for AMD GPU cards (non-CUDA) on Linux machines.
 - Multiple bugs and edge cases squashed.
 
@@ -387,7 +617,7 @@ sections describe what's new for InvokeAI.
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
   backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for [inpainting](features/INPAINTING.md) and
+- Support for [inpainting](deprecated/INPAINTING.md) and
   [outpainting](features/OUTPAINTING.md)
 - img2img runs on all k\* samplers
 - Support for
@@ -399,7 +629,7 @@ sections describe what's new for InvokeAI.
   using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
   infinite canvas), and "embiggen" upscaling. See the `!fix` command.
 - New `--hires` option on `invoke>` line allows
-  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
+  [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
   at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control
   variation during image generation (see
@@ -408,7 +638,7 @@ sections describe what's new for InvokeAI.
   of images and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
   platforms.
-- Improved [command-line completion behavior](features/CLI.md) New commands
+- Improved [command-line completion behavior](deprecated/CLI.md) New commands
   added:
   - List command-line history with `!history`
   - Search command-line history with `!search`

docs/contributing/CONTRIBUTING.md

@@ -0,0 +1,54 @@
+## Welcome to Invoke AI
+
+We're thrilled to have you here and we're excited for you to contribute. 
+
+Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
+
+Here are some guidelines to help you get started:
+
+### Technical Prerequisites
+
+Front-end: You'll need a working knowledge of React and TypeScript.
+
+Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
+
+### How to Submit Contributions
+
+To start contributing, please follow these steps:
+
+1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
+2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
+3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
+
+### Types of Contributions We're Looking For
+
+We welcome all contributions that improve the project. Right now, we're especially looking for:
+
+1. Quality of life (QOL) enhancements on the front-end.
+2. New backend capabilities added through nodes.
+3. Incorporating additional optimizations from the broader open-source software community.
+
+### Communication and Decision-making Process
+
+Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
+
+For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
+
+### Code of Conduct and Contribution Expectations
+
+We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
+
+By making a contribution to this project, you certify that:
+
+1. The contribution was created in whole or in part by you and you have the right to submit it under the open-source license indicated in this project’s GitHub repository; or
+2. The contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open-source license and you have the right under that license to submit that work with modifications, whether created in whole or in part by you, under the same open-source license (unless you are permitted to submit under a different license); or
+3. The contribution was provided directly to you by some other person who certified (1) or (2) and you have not modified it; or
+4. You understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information you submit with it, including your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open-source license(s) involved.
+
+This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
+
+This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
+
+---
+
+Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/deprecated/CLI.md

@@ -205,14 +205,14 @@ Here are the invoke> command that apply to txt2img:
 | `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
 | `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
 | `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
-| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts)                                                                                                                                                  |
+| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/OTHER.md#weighted-prompts)                                                                                                                                                  |
 | `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
 | `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
 | `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
 | `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
 | `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this.                                                                                                                                                           |
+| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this.                                                                                                                                                           |
 | `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
 | `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
 | `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
@@ -257,7 +257,7 @@ additional options:
     by `-M`. You may also supply just a single initial image with the areas
     to overpaint made transparent, but you must be careful not to destroy
     the pixels underneath when you create the transparent areas. See
-    [Inpainting](./INPAINTING.md) for details.
+    [Inpainting](INPAINTING.md) for details.
 
 inpainting accepts all the arguments used for txt2img and img2img, as well as
 the --mask (-M) and --text_mask (-tm) arguments:
@@ -297,7 +297,7 @@ invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
 
 You can load and use hundreds of community-contributed Textual
 Inversion models just by typing the appropriate trigger phrase. Please
-see [Concepts Library](CONCEPTS.md) for more details.
+see [Concepts Library](../features/CONCEPTS.md) for more details.
 
 ## Other Commands
 

docs/features/CONCEPTS.md

@@ -65,39 +65,21 @@ find out what each concept is for, you can browse the
 [Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
 look at examples of what each concept produces.
 
-When you have an idea of a concept you wish to try, go to the command-line
-client (CLI) and type a `<` character and the beginning of the Hugging Face
-concept name you wish to load. Press ++tab++, and the CLI will show you all
-matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
-~800 concepts, but be prepared to scroll up to see them all! If there is more
-than one match you can continue to type and ++tab++ until the concept is
-completed.
+To load concepts, you will need to open the Web UI's configuration
+dialogue and activate "Show Textual Inversions from HF Concepts
+Library". This will then add a list of HF Concepts to the dropdown
+"Add Textual Inversion" menu. Select the concept(s) of your choice and
+they will be incorporated into the positive prompt. A few concepts are
+designed for the negative prompt, in which case you can add them to
+the negative prompt box by select the down arrow icon next to the
+textual inversion menu.
 
-!!! example
-
-    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
-
-    ```py
-    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
-    ```
-
-    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
-    because this is a unique match.
-
-    Finish your prompt and generate as usual. You may include multiple concept terms
-    in the prompt.
-
-If you have never used this concept before, you will see a message that the TI
-model is being downloaded and installed. After this, the concept will be saved
-locally (in the `models/sd-concepts-library` directory) for future use.
-
-Several steps happen during downloading and installation, including a scan of
-the file for malicious code. Should any errors occur, you will be warned and the
-concept will fail to load. Generation will then continue treating the trigger
-term as a normal string of characters (e.g. as literal `<ghibli-face>`).
-
-You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
-autocompletion at this time.
+There are nearly 1000 HF concepts, more than will fit into a menu. For
+this reason we only show the most popular concepts (those which have
+received 5 or more likes). If you wish to use a concept that is not on
+the list, you may simply type its name surrounded by brackets. For
+example, to load the concept named "xidiversity", add `<xidiversity>`
+to the positive or negative prompt text.
 
 ## Installing your Own TI Files
 
@@ -112,18 +94,11 @@ At startup time, InvokeAI will scan the `embeddings` directory and load any TI
 files it finds there. At startup you will see a message similar to this one:
 
 ```bash
->> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
+>> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
 ```
 
-Note the `*` trigger term. This is a placeholder term that many early TI
-tutorials taught people to use rather than a more descriptive term.
-Unfortunately, if you have multiple TI files that all use this term, only the
-first one loaded will be triggered by use of the term.
-
-To avoid this problem, you can use the `merge_embeddings.py` script to merge two
-or more TI files together. If it encounters a collision of terms, the script
-will prompt you to select new terms that do not collide. See
-[Textual Inversion](TEXTUAL_INVERSION.md) for details.
+The terms you can use will appear in the "Add Textual Inversion"
+dropdown menu above the HF Concepts.
 
 ## Further Reading
 

docs/features/CONTROLNET.md

@@ -0,0 +1,92 @@
+---
+title: ControlNet
+---
+
+# :material-loupe: ControlNet
+
+## ControlNet
+
+ControlNet
+
+ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
+
+With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
+
+
+### How it works
+
+ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
+
+
+### Models
+
+As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
+
+
+**Canny**:
+
+When the Canny model is used in ControlNet, Invoke will attempt to generate images that match the edges detected. 
+
+Canny edge detection works by detecting the edges in an image by looking for abrupt changes in intensity. It is known for its ability to detect edges accurately while reducing noise and false edges, and the preprocessor can identify more information by decreasing the thresholds.
+
+**M-LSD**: 
+
+M-LSD is another edge detection algorithm used in ControlNet. It stands for Multi-Scale Line Segment Detector. 
+
+It detects straight line segments in an image by analyzing the local structure of the image at multiple scales.  It can be useful for architectural imagery, or anything where straight-line structural information is needed for the resulting output. 
+
+**Lineart**: 
+
+The Lineart model in ControlNet generates line drawings from an input image. The resulting pre-processed image is a simplified version of the original, with only the outlines of objects visible.The Lineart model in ControlNet is known for its ability to accurately capture the contours of the objects in an input sketch. 
+
+**Lineart Anime**: 
+
+A variant of the Lineart model that generates line drawings with a distinct style inspired by anime and manga art styles.
+
+**Depth**: 
+A model that generates depth maps of images, allowing you to create more realistic 3D models or to simulate depth effects in post-processing.
+
+**Normal Map (BAE):** 
+A model that generates normal maps from input images, allowing for more realistic lighting effects in 3D rendering.
+		
+**Image Segmentation**: 
+A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
+
+
+**Openpose**: 
+The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
+
+**Mediapipe Face**:
+
+The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
+
+**Tile (experimental)**:
+
+The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
+
+- It can reinterpret specific details within an image and create fresh, new elements.
+- It has the ability to disregard global instructions if there's a discrepancy between them and the local context or specific parts of the image. In such cases, it uses the local context to guide the process.
+
+The Tile Model can be a powerful tool in your arsenal for enhancing image quality and details. If there are undesirable elements in your images, such as blurriness caused by resizing, this model can effectively eliminate these issues, resulting in cleaner, crisper images. Moreover, it can generate and add refined details to your images, improving their overall quality and appeal. 
+
+**Pix2Pix (experimental)**
+
+With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
+
+**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
+
+Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
+
+
+## Using ControlNet
+
+To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
+
+
+Each ControlNet has two settings that are applied to the ControlNet.
+
+Weight - Strength of the Controlnet model applied to the generation for the section, defined by start/end.
+
+Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
+
+Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.

docs/features/IMG2IMG.md

@@ -4,86 +4,13 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-Both the Web and command-line interfaces provide an "img2img" feature
-that lets you seed your creations with an initial drawing or
-photo. This is a really cool feature that tells stable diffusion to
-build the prompt on top of the image you provide, preserving the
-original's basic shape and layout.
+InvokeAI provides an "img2img" feature that lets you seed your
+creations with an initial drawing or photo. This is a really cool
+feature that tells stable diffusion to build the prompt on top of the
+image you provide, preserving the original's basic shape and layout.
 
-See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
-in the InvokeAI web server. This document describes how to use img2img
-in the command-line tool.
-
-## Basic Usage
-
-Launch the command-line client by launching `invoke.sh`/`invoke.bat`
-and choosing option (1). Alternative, activate the InvokeAI
-environment and issue the command `invokeai`.
-
-Once the `invoke> ` prompt appears, you can start an img2img render by
-pointing to a seed file with the `-I` option as shown here:
-
-!!! example ""
-
-    ```commandline
-    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
-    ```
-
-    <figure markdown>
-
-    | original image | generated image |
-    | :------------: | :-------------: |
-    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
-
-    </figure>
-
-The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
-(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
-the original intact), to `1.0` (ignore the original completely). The default is
-`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
-options include `-C` (classification free guidance scale), and `-s` (steps).
-Unlike `txt2img`, adding steps will continuously change the resulting image and
-it will not converge.
-
-You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
-count variants on the original image. This is done by passing the first
-generated image back into img2img the requested number of times. It generates
-interesting variants.
-
-Note that the prompt makes a big difference. For example, this slight variation
-on the prompt produces a very different image:
-
-<figure markdown>
-![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
-<caption markdown>photograph of a tree on a hill with a river</caption>
-</figure>
-
-!!! tip
-
-    When designing prompts, think about how the images scraped from the internet were
-    captioned. Very few photographs will be labeled "photograph" or "photorealistic."
-    They will, however, be captioned with the publication, photographer, camera model,
-    or film settings.
-
-If the initial image contains transparent regions, then Stable Diffusion will
-only draw within the transparent regions, a process called
-[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
-However, for this to work correctly, the color information underneath the
-transparent needs to be preserved, not erased.
-
-!!! warning "**IMPORTANT ISSUE** "
-
-    `img2img` does not work properly on initial images smaller
-    than 512x512. Please scale your image to at least 512x512 before using it.
-    Larger images are not a problem, but may run out of VRAM on your GPU card. To
-    fix this, use the --fit option, which downscales the initial image to fit within
-    the box specified by width x height:
-
-    ```
-    tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
-    ```
-
-## How does it actually work, though?
+For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
+Web Server](./WEB.md#image-to-image).
 
 The main difference between `img2img` and `prompt2img` is the starting point.
 While `prompt2img` always starts with pure gaussian noise and progressively
@@ -99,10 +26,6 @@ seed `1592514025` develops something like this:
 
 !!! example ""
 
-    ```bash
-    invoke> "fire" -s10 -W384 -H384 -S1592514025
-    ```
-
     <figure markdown>
     ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
     </figure>
@@ -157,17 +80,8 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
 the problems of my bad drawing.
 
 If you want to try this out yourself, all of these are using a seed of
-`1592514025` with a width/height of `384`, step count `10`, the default sampler
-(`k_lms`), and the single-word prompt `"fire"`:
-
-```bash
-invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
-```
-
-The code for rendering intermediates is on my (damian0815's) branch
-[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
-run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
-generating an image.
+`1592514025` with a width/height of `384`, step count `10`, the
+`k_lms` sampler, and the single-word prompt `"fire"`.
 
 ### Compensating for the reduced step count
 
@@ -180,10 +94,6 @@ give each generation 20 steps.
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
 does `20` steps from my image):
 
-```bash
-invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
-```
-
 <figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
 </figure>
@@ -191,10 +101,6 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
 make sure SD does `20` steps from my image):
 
-```commandline
-invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
-```
-
 <figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
 </figure>

docs/features/MODEL_MERGING.md

@@ -71,6 +71,3 @@ under the selected name and register it with InvokeAI.
   use InvokeAI conventions - only alphanumeric letters and the
   characters ".+-".
 
-## Caveats
-
-This is a new script and may contain bugs.

docs/features/NSFW.md

@@ -31,10 +31,22 @@ turned on and off on the command line using `--nsfw_checker` and
 
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file (usually
-`invokeai.init` in your home directory). You can change the default at any
-time by opening this file in a text editor and commenting or
-uncommenting the line `--nsfw_checker`.
+response is stored in the InvokeAI initialization file
+(`invokeai.yaml` in the InvokeAI root directory).  You can change the
+default at any time by opening this file in a text editor and
+changing the line `nsfw_checker:` from true to false or vice-versa:
+
+
+```
+...
+  Features:
+    esrgan: true
+    internet_available: true
+    log_tokenization: false
+    nsfw_checker: true
+    patchmatch: true
+    restore: true
+```
 
 ## Caveats
 
@@ -79,11 +91,3 @@ generates. However, it does write metadata into the PNG data area,
 including the prompt used to generate the image and relevant parameter
 settings. These fields can be examined using the `sd-metadata.py`
 script that comes with the InvokeAI package.
-
-Note that several other Stable Diffusion distributions offer
-wavelet-based "invisible" watermarking. We have experimented with the
-library used to generate these watermarks and have reached the
-conclusion that while the watermarking library may be adding
-watermarks to PNG images, the currently available version is unable to
-retrieve them successfully. If and when a functioning version of the
-library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -18,43 +18,16 @@ Output Example:
 
 ## **Seamless Tiling**
 
-The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
-`--seamless` option when starting the script which will result in all generated images to tile, or
-for each `invoke>` prompt as shown here:
+The seamless tiling mode causes generated images to seamlessly tile
+with itself creating repetitive wallpaper-like patterns. To use it,
+activate the Seamless Tiling option in the Web GUI and then select
+whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
+will then be active for the next set of generations.
+
+A nice prompt to test seamless tiling with is:
 
-```python
-invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
-
-By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
-Possible values are `x`, `y`, and `x,y`:
-```python
-invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
-```
-
----
-
-## **Shortcuts: Reusing Seeds**
-
-Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
-1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
-generated. If you produced multiple images with the `-n` switch, then you can go back further
-using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
-back further than one command.
-
-Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
-switch to turn on upscaling and face enhancement (see previous section):
-
-```bash
-invoke> a cute child playing hopscotch -G0.5
-[...]
-outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
-
-# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
-invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
-reusing previous seed 3498014304
-[...]
-outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304
+pond garden with lotus by claude monet"
 ```
 
 ---
@@ -73,66 +46,27 @@ This will tell the sampler to invest 25% of its effort on the tabby cat aspect o
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
----
-
-## **Filename Format**
-
-The argument `--fnformat` allows to specify the filename of the
- image. Supported wildcards are all arguments what can be set such as
- `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
- `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
- `prefix`.
-
-The following prompt
-```bash
-dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
-```
-
-generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
-
----
-
 ## **Thresholding and Perlin Noise Initialization Options**
 
-Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.
+Under the Noise section of the Web UI, you will find two options named
+Perlin Noise and Noise Threshold. [Perlin
+noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
+structured noise used to simulate terrain and other natural
+textures. The slider controls the percentage of perlin noise that will
+be mixed into the image at the beginning of generation. Adding a little
+perlin noise to a generation will alter the image substantially.
+
+The noise threshold limits the range of the latent values during
+sampling and helps combat the oversharpening seem with higher CFG
+scale values.
 
 For better intuition into what these options do in practice:
 
 ![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
 
-In generating this graphic, perlin noise at initialization was programmatically varied going across on the diagram by values 0.0, 0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied going down from
-0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are fixed, so the initial prompt is as follows (no thresholding or perlin noise):
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 0 --perlin 0
-```
-
-Here's an example of another prompt used when setting the threshold to 5 and perlin noise to 0.2:
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 5 --perlin 0.2
-```
-
-!!! note
-
-    currently the thresholding feature is only implemented for the k-diffusion style samplers, and empirically appears to work best with `k_euler_a` and `k_dpm_2_a`. Using 0 disables thresholding. Using 0 for perlin noise disables using perlin noise for initialization. Finally, using 1 for perlin noise uses only perlin noise for initialization.
-
----
-
-## **Simplified API**
-
-For programmers who wish to incorporate stable-diffusion into other products, this repository
-includes a simplified API for text to image generation, which lets you create images from a prompt
-in just three lines of code:
-
-```bash
-from ldm.generate import Generate
-g       = Generate()
-outputs = g.txt2img("a unicorn in manhattan")
-```
-
-Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
-
-Please see the documentation in ldm/generate.py for more information.
-
----
+In generating this graphic, perlin noise at initialization was
+programmatically varied going across on the diagram by values 0.0,
+0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
+going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
+fixed using the prompt "a portrait of a beautiful young lady" a CFG of
+20, 100 steps, and a seed of 1950357039.

docs/features/POSTPROCESS.md

@@ -8,12 +8,6 @@ title: Postprocessing
 
 This extension provides the ability to restore faces and upscale images.
 
-Face restoration and upscaling can be applied at the time you generate the
-images, or at any later time against a previously-generated PNG file, using the
-[!fix](#fixing-previously-generated-images) command.
-[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
-fact.
-
 ## Face Fixing
 
 The default face restoration module is GFPGAN. The default upscale is
@@ -23,8 +17,7 @@ Real-ESRGAN. For an alternative face restoration module, see
 As of version 1.14, environment.yaml will install the Real-ESRGAN package into
 the standard install location for python packages, and will put GFPGAN into a
 subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
-should "just work" without further intervention. Simply pass the `--upscale`
-(`-U`) option on the `invoke>` command line, or indicate the desired scale on
+should "just work" without further intervention. Simply indicate the desired scale on
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
@@ -41,48 +34,75 @@ reconstruction.
 
 ### Upscaling
 
-`-U : <upscaling_factor> <upscaling_strength>`
+Open the upscaling dialog by clicking on the "expand" icon located
+above the image display area in the Web UI:
 
-The upscaling prompt argument takes two values. The first value is a scaling
-factor and should be set to either `2` or `4` only. This will either scale the
-image 2x or 4x respectively using different models.
+<figure markdown>
+![upscale1](../assets/features/upscale-dialog.png)
+</figure>
 
-You can set the scaling stength between `0` and `1.0` to control intensity of
-the of the scaling. This is handy because AI upscalers generally tend to smooth
-out texture details. If you wish to retain some of those for natural looking
-results, we recommend using values between `0.5 to 0.8`.
+There are three different upscaling parameters that you can
+adjust. The first is the scale itself, either 2x or 4x.
 
-If you do not explicitly specify an upscaling_strength, it will default to 0.75.
+The second is the "Denoising Strength." Higher values will smooth out
+the image and remove digital chatter, but may lose fine detail at
+higher values.
+
+Third, "Upscale Strength" allows you to adjust how the You can set the
+scaling stength between `0` and `1.0` to control the intensity of the
+scaling. AI upscalers generally tend to smooth out texture details. If
+you wish to retain some of those for natural looking results, we
+recommend using values between `0.5 to 0.8`.
+
+[This figure](../assets/features/upscaling-montage.png) illustrates
+the effects of denoising and strength. The original image was 512x512,
+4x scaled to 2048x2048. The "original" version on the upper left was
+scaled using simple pixel averaging. The remainder use the ESRGAN
+upscaling algorithm at different levels of denoising and strength.
+
+<figure markdown>
+![upscaling](../assets/features/upscaling-montage.png){ width=720 }
+</figure>
+
+Both denoising and strength default to 0.75.
 
 ### Face Restoration
 
-`-G : <facetool_strength>`
+InvokeAI offers alternative two face restoration algorithms,
+[GFPGAN](https://github.com/TencentARC/GFPGAN) and
+[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
+algorithms improve the appearance of faces, particularly eyes and
+mouths. Issues with faces are less common with the latest set of
+Stable Diffusion models than with the original 1.4 release, but the
+restoration algorithms can still make a noticeable improvement in
+certain cases. You can also apply restoration to old photographs you
+upload.
 
-This prompt argument controls the strength of the face restoration that is being
-applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
+To access face restoration, click the "smiley face" icon in the
+toolbar above the InvokeAI image panel. You will be presented with a
+dialog that offers a choice between the two algorithm and sliders that
+allow you to adjust their parameters. Alternatively, you may open the
+left-hand accordion panel labeled "Face Restoration" and have the
+restoration algorithm of your choice applied to generated images
+automatically.
 
-You can use either one or both without any conflicts. In cases where you use
-both, the image will be first upscaled and then the face restoration process
-will be executed to ensure you get the highest quality facial features.
 
-`--save_orig`
+Like upscaling, there are a number of parameters that adjust the face
+restoration output. GFPGAN has a single parameter, `strength`, which
+controls how much the algorithm is allowed to adjust the
+image. CodeFormer has two parameters, `strength`, and `fidelity`,
+which together control the quality of the output image as described in
+the [CodeFormer project
+page](https://shangchenzhou.com/projects/CodeFormer/). Default values
+are 0.75 for both parameters, which achieves a reasonable balance
+between changing the image too much and not enough.
 
-When you use either `-U` or `-G`, the final result you get is upscaled or face
-modified. If you want to save the original Stable Diffusion generation, you can
-use the `-save_orig` prompt argument to save the original unaffected version
-too.
+[This figure](../assets/features/restoration-montage.png) illustrates
+the effects of adjusting GFPGAN and CodeFormer parameters.
 
-### Example Usage
-
-```bash
-invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
-```
-
-This also works with img2img:
-
-```bash
-invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
-```
+<figure markdown>
+![upscaling](../assets/features/restoration-montage.png){ width=720 }
+</figure>
 
 !!! note
 
@@ -95,69 +115,8 @@ invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
-If you wish to stop during the image generation but want to upscale or face
-restore a particular generated image, pass it again with the same prompt and
-generated seed along with the `-U` and `-G` prompt arguments to perform those
-actions.
-
-## CodeFormer Support
-
-This repo also allows you to perform face restoration using
-[CodeFormer](https://github.com/sczhou/CodeFormer).
-
-In order to setup CodeFormer to work, you need to download the models like with
-GFPGAN. You can do this either by running `invokeai-configure` or by manually
-downloading the
-[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
-and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
-
-You can use `-ft` prompt argument to swap between CodeFormer and the default
-GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
-strength of the restoration effect.
-
-### CodeFormer Usage
-
-The following command will perform face restoration with CodeFormer instead of
-the default gfpgan.
-
-`<prompt> -G 0.8 -ft codeformer`
-
-### Other Options
-
-- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
-  high quality results but low accuracy and 1 produces lower quality results but
-  higher accuacy to your original face.
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is closely matching to the input face.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.9`
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is the best restoration possible. This may deviate
-slightly from the original face. This is an excellent option to use in
-situations when there is very little facial data to work with.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.1`
-
-## Fixing Previously-Generated Images
-
-It is easy to apply face restoration and/or upscaling to any
-previously-generated file. Just use the syntax
-`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
-and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
-just run:
-
-```bash
-invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
-```
-
-A new file named `000044.2945021133.fixed.png` will be created in the output
-directory. Note that the `!fix` command does not replace the original file,
-unlike the behavior at generate time.
-
 ## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and
-`--no_upscale` options, respectively.
+`--no_esrgan` options, respectively.

docs/features/PROMPTS.md

@@ -4,77 +4,12 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
-## **Reading Prompts from a File**
-
-You can automate `invoke.py` by providing a text file with the prompts you want
-to run, one line per prompt. The text file must be composed with a text editor
-(e.g. Notepad) and not a word processor. Each line should look like what you
-would type at the invoke> prompt:
-
-```bash
-"a beautiful sunny day in the park, children playing" -n4 -C10
-"stormy weather on a mountain top, goats grazing" -s100
-"innovative packaging for a squid's dinner" -S137038382
-```
-
-Then pass this file's name to `invoke.py` when you invoke it:
-
-```bash
-python scripts/invoke.py --from_file "/path/to/prompts.txt"
-```
-
-You may also read a series of prompts from standard input by providing
-a filename of `-`. For example, here is a python script that creates a
-matrix of prompts, each one varying slightly:
-
-```bash
-#!/usr/bin/env python
-
-adjectives = ['sunny','rainy','overcast']
-samplers = ['k_lms','k_euler_a','k_heun']
-cfg = [7.5, 9, 11]
-
-for adj in adjectives:
-    for samp in samplers:
-        for cg in cfg:
-            print(f'a {adj} day -A{samp} -C{cg}')
-```
-
-Its output looks like this (abbreviated):
-
-```bash
-a sunny day -Aklms -C7.5
-a sunny day -Aklms -C9
-a sunny day -Aklms -C11
-a sunny day -Ak_euler_a -C7.5
-a sunny day -Ak_euler_a -C9
-...
-a overcast day -Ak_heun -C9
-a overcast day -Ak_heun -C11
-```
-
-To feed it to invoke.py, pass the filename of "-"
-
-```bash
-python matrix.py | python scripts/invoke.py --from_file -
-```
-
-When the script is finished, each of the 27 combinations
-of adjective, sampler and CFG will be executed.
-
-The command-line interface provides `!fetch` and `!replay` commands
-which allow you to read the prompts from a single previously-generated
-image or a whole directory of them, write the prompts to a file, and
-then replay them. Or you can create your own file of prompts and feed
-them to the command-line client from within an interactive session.
-See [Command-Line Interface](CLI.md) for details.
-
----
-
 ## **Negative and Unconditioned Prompts**
 
-Any words between a pair of square brackets will instruct Stable Diffusion to
-attempt to ban the concept from the generated image.
+Any words between a pair of square brackets will instruct Stable
+Diffusion to attempt to ban the concept from the generated image. The
+same effect is achieved by placing words in the "Negative Prompts"
+textbox in the Web UI.
 
 ```text
 this is a test prompt [not really] to make you understand [cool] how this works.
@@ -87,7 +22,9 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
+
+`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
 
 <figure markdown>
 
@@ -99,7 +36,8 @@ That image has a woman, so if we want the horse without a rider, we can
 influence the image not to have a woman by putting [woman] in the prompt, like
 this:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -110,7 +48,8 @@ this:
 That's nice - but say we also don't want the image to be quite so blue. We can
 add "blue" to the list of negative prompts, so it's now [woman blue]:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -121,7 +60,8 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 Getting close - but there's no sense in having a saddle when our horse doesn't
 have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -261,19 +201,6 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
-Note that `prompt2prompt` is not currently working with the runwayML inpainting
-model, and may never work due to the way this model is set up. If you attempt to
-use `prompt2prompt` you will get the original image back. However, since this
-model is so good at inpainting, a good substitute is to use the `clipseg` text
-masking option:
-
-```bash
-invoke> a fluffy cat eating a hotdog
-Outputs:
-[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
-invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
-```
-
 ### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
@@ -374,6 +301,5 @@ summoning up the concept of some sort of scifi creature? Let's find out.
 Indeed, removing the word "hybrid" produces an image that is more like what we'd
 expect.
 
-In conclusion, prompt blending is great for exploring creative space, but can be
-difficult to direct. A forthcoming release of InvokeAI will feature more
-deterministic prompt weighting.
+In conclusion, prompt blending is great for exploring creative space,
+but takes some trial and error to achieve the desired effect.

docs/features/TEXTUAL_INVERSION.md

@@ -46,11 +46,19 @@ start the front end by selecting choice (3):
 
 ```sh
 Do you want to generate images using the
-1. command-line
-2. browser-based UI
-3. textual inversion training
-4. open the developer console
-Please enter 1, 2, 3, or 4: [1] 3
+1: Browser-based UI
+2: Command-line interface
+3: Run textual inversion training
+4: Merge models (diffusers type only)
+5: Download and install models
+6: Change InvokeAI startup options
+7: Re-run the configure script to fix a broken install
+8: Open the developer console
+9: Update InvokeAI
+10: Command-line help
+Q: Quit
+
+Please enter 1-10, Q: [1] 
 ```
 
 From the command line, with the InvokeAI virtual environment active,

docs/features/VARIATIONS.md

@@ -6,9 +6,7 @@ title: Variations
 
 ## Intro
 
-Release 1.13 of SD-Dream adds support for image variations.
-
-You are able to do the following:
+InvokeAI's support for variations enables you to do the following:
 
 1. Generate a series of systematic variations of an image, given a prompt. The
    amount of variation from one image to the next can be controlled.
@@ -30,19 +28,7 @@ The prompt we will use throughout is:
 This will be indicated as `#!bash "prompt"` in the examples below.
 
 First we let SD create a series of images in the usual way, in this case
-requesting six iterations:
-
-```bash
-invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
-...
-Outputs:
-./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
-./outputs/Xena/000001.1880768722.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1880768722
-./outputs/Xena/000001.332057179.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S332057179
-./outputs/Xena/000001.2224800325.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S2224800325
-./outputs/Xena/000001.465250761.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S465250761
-./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
-```
+requesting six iterations.
 
 <figure markdown>
 ![var1](../assets/variation_walkthru/000001.3357757885.png)
@@ -53,22 +39,16 @@ Outputs:
 
 ## Step 2 - Generating Variations
 
-Let's try to generate some variations. Using the same seed, we pass the argument
-`-v0.1` (or --variant_amount), which generates a series of variations each
-differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
-with higher numbers being larger amounts of variation.
+Let's try to generate some variations on this image. We select the "*"
+symbol in the line of icons above the image in order to fix the prompt
+and seed. Then we open up the "Variations" section of the generation
+panel and use the slider to set the variation amount to 0.2. The
+higher this value, the more each generated image will differ from the
+previous one.
 
-```bash
-invoke> "prompt" -n6 -S3357757885 -v0.2
-...
-Outputs:
-./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
-./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
-./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
-./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
-./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
-./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
-```
+Now we run the prompt a second time, requesting six iterations. You
+will see six images that are thematically related to each other. Try
+increasing and decreasing the variation amount and see what happens.
 
 ### **Variation Sub Seeding**
 

docs/features/WEB.md

@@ -299,14 +299,6 @@ initial image" icons are located.
 
 See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
 
-## Parting remarks
-
-This concludes the walkthrough, but there are several more features that you can
-explore. Please check out the [Command Line Interface](CLI.md) documentation for
-further explanation of the advanced features that were not covered here.
-
-The WebUI is only rapid development. Check back regularly for updates!
-
 ## Reference
 
 ### Additional Options
@@ -349,11 +341,9 @@ the settings configured in the toolbar.
 
 See below for additional documentation related to each feature:
 
-- [Core Prompt Settings](./CLI.md)
 - [Variations](./VARIATIONS.md)
 - [Upscaling](./POSTPROCESS.md#upscaling)
 - [Image to Image](./IMG2IMG.md)
-- [Inpainting](./INPAINTING.md)
 - [Other](./OTHER.md)
 
 #### Invocation Gallery

docs/features/index.md

@@ -13,28 +13,16 @@ Build complex scenes by combine and modifying multiple images in a stepwise
 fashion. This feature combines img2img, inpainting and outpainting in
 a single convenient digital artist-optimized user interface.
 
-### * The [Command Line Interface (CLI)](CLI.md)
-Scriptable access to InvokeAI's features.
-
 ## Image Generation
 ### * [Prompt Engineering](PROMPTS.md)
 Get the images you want with the InvokeAI  prompt engineering language.
 
-## * [Post-Processing](POSTPROCESS.md)
-Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
-
 ## * The [Concepts Library](CONCEPTS.md)
 Add custom subjects and styles using HuggingFace's repository of embeddings.
 
-### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
+### * [Image-to-Image Guide](IMG2IMG.md)
 Use a seed image to build new creations in the CLI.
 
-### * [Inpainting Guide for the CLI](INPAINTING.md)
-Selectively erase and replace portions of an existing image in the CLI.
-
-### * [Outpainting Guide for the CLI](OUTPAINTING.md)
-Extend the borders of the image with an "outcrop" function within the CLI.
-
 ### * [Generating Variations](VARIATIONS.md)
 Have an image you like and want to generate many more like it? Variations
 are the ticket.

docs/index.md

@@ -13,6 +13,7 @@ title: Home
 
 <div align="center" markdown>
 
+
 [![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
@@ -67,7 +68,7 @@ title: Home
 implementation of Stable Diffusion, the open source text-to-image and
 image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
-Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
+Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 **Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>]
 [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a
@@ -131,17 +132,13 @@ This method is recommended for those familiar with running Docker containers
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
 - [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+
 <!-- separator -->
-### The InvokeAI Command Line Interface
-- [Command Line Interace Reference Guide](features/CLI.md)
-<!-- separator -->
+
 ### Image Management
 - [Image2Image](features/IMG2IMG.md)
-- [Inpainting](features/INPAINTING.md)
-- [Outpainting](features/OUTPAINTING.md)
 - [Adding custom styles and subjects](features/CONCEPTS.md)
 - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
-- [Embiggen upscaling](features/EMBIGGEN.md)
 - [Other Features](features/OTHER.md)
 
 <!-- separator -->
@@ -156,83 +153,60 @@ This method is recommended for those familiar with running Docker containers
 - [Prompt Syntax](features/PROMPTS.md)
 - [Generating Variations](features/VARIATIONS.md)
 
-## :octicons-log-16: Latest Changes
+## :octicons-log-16: Important Changes Since Version 2.3
 
-### v2.3.0 <small>(9 February 2023)</small>
+### Nodes
 
-#### Migration to Stable Diffusion `diffusers` models
+Behind the scenes, InvokeAI has been completely rewritten to support
+"nodes," small unitary operations that can be combined into graphs to
+form arbitrary workflows. For example, there is a prompt node that
+processes the prompt string and feeds it to a text2latent node that
+generates a latent image. The latents are then fed to a latent2image
+node that translates the latent image into a PNG.
 
-Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
+The WebGUI has a node editor that allows you to graphically design and
+execute custom node graphs. The ability to save and load graphs is
+still a work in progress, but coming soon.
 
-When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
+### Command-Line Interface Retired
 
-To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
+The original "invokeai" command-line interface has been retired. The
+`invokeai` command will now launch a new command-line client that can
+be used by developers to create and test nodes. It is not intended to
+be used for routine image generation or manipulation.
 
-* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
-* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
-* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
+To launch the Web GUI from the command-line, use the command
+`invokeai-web` rather than the traditional `invokeai --web`.
 
-The WebGUI offers similar functionality for model management.
+### ControlNet
 
-For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
+This version of InvokeAI features ControlNet, a system that allows you
+to achieve exact poses for human and animal figures by providing a
+model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
 
-Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
+### New Schedulers
 
-#### Support for the `XFormers` Memory-Efficient Crossattention Package
+The list of schedulers has been completely revamped and brought up to date:
 
-On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
+| **Short Name** | **Scheduler**                   | **Notes**                   |
+|----------------|---------------------------------|-----------------------------|
+| **ddim**       | DDIMScheduler                   |                             |
+| **ddpm**       | DDPMScheduler                   |                             |
+| **deis**       | DEISMultistepScheduler          |                             |
+| **lms**        | LMSDiscreteScheduler            |                             |
+| **pndm**       | PNDMScheduler                   |                             |
+| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
+| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
+| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
+| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
+| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
+| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
+| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
+| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
+| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
+| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
 
-The caveat with using `xformers` is that it introduces slightly non-deterministic behavior, and images generated using the same seed and other settings will be subtly different between invocations. Generally the changes are unnoticeable unless you rapidly shift back and forth between images, but to disable `xformers` and restore fully deterministic behavior, you may launch InvokeAI using the `--no-xformers` option. This is most conveniently done by opening the file `invokeai/invokeai.init` with a text editor, and adding the line `--no-xformers` at the bottom.
-
-#### A Negative Prompt Box in the WebUI
-
-There is now a separate text input box for negative prompts in the WebUI. This is convenient for stashing frequently-used negative prompts ("mangled limbs, bad anatomy"). The `[negative prompt]` syntax continues to work in the main prompt box as well.
-
-To see exactly how your prompts are being parsed, launch `invokeai` with the `--log_tokenization` option. The console window will then display the tokenization process for both positive and negative prompts.
-
-#### Model Merging
-
-Version 2.3.0 offers an intuitive user interface for merging up to three Stable Diffusion models using an intuitive user interface. Model merging allows you to mix the behavior of models to achieve very interesting effects. To use this, each of the models must already be imported into InvokeAI and saved in `diffusers` format, then launch the merger using a new menu item in the InvokeAI launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line with `invokeai-merge --gui`. You will be prompted to select the models to merge, the proportions in which to mix them, and the mixing algorithm. The script will create a new merged `diffusers` model and import it into InvokeAI for your use.
-
-See [MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/) for more details.
-
-#### Textual Inversion Training
-
-Textual Inversion (TI) is a technique for training a Stable Diffusion model to emit a particular subject or style when triggered by a keyword phrase. You can perform TI training by placing a small number of images of the subject or style in a directory, and choosing a distinctive trigger phrase, such as "pointillist-style". After successful training, The subject or style will be activated by including `<pointillist-style>` in your prompt.
-
-Previous versions of InvokeAI were able to perform TI, but it required using a command-line script with dozens of obscure command-line arguments. Version 2.3.0 features an intuitive TI frontend that will build a TI model on top of any `diffusers` model. To access training you can launch from a new item in the launcher script or from the command line using `invokeai-ti --gui`.
-
-See [TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/) for further details.
-
-#### A New Installer Experience
-
-The InvokeAI installer has been upgraded in order to provide a smoother and hopefully more glitch-free experience. In addition, InvokeAI is now packaged as a PyPi project, allowing developers and power-users to install InvokeAI with the command `pip install InvokeAI  --use-pep517`. Please see [Installation](#installation) for details.
-
-Developers should be aware that the `pip` installation procedure has been simplified and that the `conda` method is no longer supported at all. Accordingly, the `environments_and_requirements` directory has been deleted from the repository.
-
-#### Command-line name changes
-
-All of InvokeAI's functionality, including the WebUI, command-line interface, textual inversion training and model merging, can all be accessed from the `invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been expanded to add the new functionality. For the convenience of developers and power users, we have normalized the names of the InvokeAI command-line scripts:
-
-* `invokeai` -- Command-line client
-* `invokeai --web` -- Web GUI
-* `invokeai-merge --gui` -- Model merging script with graphical front end
-* `invokeai-ti --gui` -- Textual inversion script with graphical front end
-* `invokeai-configure` -- Configuration tool for initializing the `invokeai` directory and selecting popular starter models.
-
-For backward compatibility, the old command names are also recognized, including `invoke.py` and `configure-invokeai.py`. However, these are deprecated and will eventually be removed.
-
-Developers should be aware that the locations of the script's source code has been moved. The new locations are:
-* `invokeai` =>  `ldm/invoke/CLI.py`
-* `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
-* `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
-* `invokeai-merge` => `ldm/invoke/merge_diffusers`
-
-Developers are strongly encouraged to perform an "editable" install of InvokeAI using `pip install -e .  --use-pep517` in the Git repository, and then to call the scripts using their 2.3.0 names, rather than executing the scripts directly. Developers should also be aware that the several important data files have been relocated into a new directory named `invokeai`. This includes the WebGUI's `frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used by the installer to select starter models. Eventually all InvokeAI modules will be in subdirectories of `invokeai`.
-
-Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
-For older changelogs, please visit the
-**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
+Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
 
 ## :material-target: Troubleshooting
 
@@ -268,8 +242,3 @@ free to send me an email if you use and like the script.
 Original portions of the software are Copyright (c) 2022-23
 by [The InvokeAI Team](https://github.com/invoke-ai).
 
-## :octicons-book-24: Further Reading
-
-Please see the original README for more information on this software and
-underlying algorithm, located in the file
-[README-CompViz.md](other/README-CompViz.md).

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -87,18 +87,18 @@ Prior to installing PyPatchMatch, you need to take the following steps:
     sudo pacman -S --needed base-devel
     ```
 
-2. Install `opencv`:
+2. Install `opencv` and `blas`:
 
     ```sh
-    sudo pacman -S opencv
+    sudo pacman -S opencv blas
     ```
 
     or for CUDA support
 
     ```sh
-    sudo pacman -S opencv-cuda
+    sudo pacman -S opencv-cuda blas
     ```
-
+    
 3. Fix the naming of the `opencv` package configuration file:
 
     ```sh

installer/install.bat.in

@@ -38,6 +38,7 @@ echo    https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist
 echo.
 echo See %INSTRUCTIONS% for more details.
 echo.
+echo "For the best user experience we suggest enlarging or maximizing this window now."
 pause
 
 @rem ---------------------------- check Python version ---------------

installer/install.sh.in

@@ -25,7 +25,8 @@ done
 
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
-    echo "Please install Python 3.9 or higher before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "For the best user experience we suggest enlarging or maximizing this window now."
     read -p "Press any key to exit"
     exit -1
 fi

installer/lib/installer.py

@@ -149,7 +149,7 @@ class Installer:
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
         """
         Install the InvokeAI application into the given runtime path
 

installer/lib/messages.py

@@ -293,6 +293,8 @@ def introduction() -> None:
                 "3. Create initial configuration files.",
                 "",
                 "[i]At any point you may interrupt this program and resume later.",
+                "",
+                "[b]For the best user experience, please enlarge or maximize this window",
             ),
         )
     )

installer/templates/invoke.bat.in

@@ -14,7 +14,7 @@ echo 3. Run textual inversion training
 echo 4. Merge models (diffusers type only)
 echo 5. Download and install models
 echo 6. Change InvokeAI startup options
-echo 7. Re-run the configure script to fix a broken install
+echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 8. Open the developer console
 echo 9. Update InvokeAI
 echo 10. Command-line help

installer/templates/invoke.sh.in

@@ -81,7 +81,7 @@ do_choice() {
         ;;
     7)
         clear
-        printf "Re-run the configure script to fix a broken install\n"
+        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
         invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
         ;;
     8)
@@ -118,12 +118,12 @@ do_choice() {
 do_dialog() {
     options=(
         1 "Generate images with a browser-based interface"
-        2 "Generate images using a command-line interface"
+        2 "Explore InvokeAI nodes using a command-line interface"
         3 "Textual inversion training"
         4 "Merge models (diffusers type only)"
         5 "Download and install models"
         6 "Change InvokeAI startup options"
-        7 "Re-run the configure script to fix a broken install"
+        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         8 "Open the developer console"
         9 "Update InvokeAI")
 

invokeai/app/api/dependencies.py

@@ -2,8 +2,17 @@
 
 from logging import Logger
 import os
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
 from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
 from invokeai.app.services.metadata import CoreMetadataService
 from invokeai.app.services.resource_name import SimpleNameService
 from invokeai.app.services.urls import LocalUrlService
@@ -11,7 +20,6 @@ from invokeai.backend.util.logging import InvokeAILogger
 
 from ..services.default_graphs import create_system_graphs
 from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
 from ..services.graph import GraphExecutionState, LibraryGraph
 from ..services.image_file_storage import DiskImageFileStorage
@@ -20,6 +28,7 @@ from ..services.invocation_services import InvocationServices
 from ..services.invoker import Invoker
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
+from ..services.model_manager_service import ModelManagerService
 from .events import FastAPIEventService
 
 
@@ -57,7 +66,7 @@ class ApiDependencies:
 
         # TODO: build a file/path manager?
         db_location = config.db_path
-        db_location.parent.mkdir(parents=True,exist_ok=True)
+        db_location.parent.mkdir(parents=True, exist_ok=True)
 
         graph_execution_manager = SqliteItemStorage[GraphExecutionState](
             filename=db_location, table_name="graph_executions"
@@ -72,21 +81,49 @@ class ApiDependencies:
             DiskLatentsStorage(f"{output_folder}/latents")
         )
 
+        board_record_storage = SqliteBoardRecordStorage(db_location)
+        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+
+        boards = BoardService(
+            services=BoardServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                board_record_storage=board_record_storage,
+                image_record_storage=image_record_storage,
+                url=urls,
+                logger=logger,
+            )
+        )
+
+        board_images = BoardImagesService(
+            services=BoardImagesServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                board_record_storage=board_record_storage,
+                image_record_storage=image_record_storage,
+                url=urls,
+                logger=logger,
+            )
+        )
+
         images = ImageService(
-            image_record_storage=image_record_storage,
-            image_file_storage=image_file_storage,
-            metadata=metadata,
-            url=urls,
-            logger=logger,
-            names=names,
-            graph_execution_manager=graph_execution_manager,
+            services=ImageServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                image_record_storage=image_record_storage,
+                image_file_storage=image_file_storage,
+                metadata=metadata,
+                url=urls,
+                logger=logger,
+                names=names,
+                graph_execution_manager=graph_execution_manager,
+            )
         )
 
         services = InvocationServices(
-            model_manager=get_model_manager(config, logger),
+            model_manager=ModelManagerService(config,logger),
             events=events,
             latents=latents,
             images=images,
+            boards=boards,
+            board_images=board_images,
             queue=MemoryInvocationQueue(),
             graph_library=SqliteItemStorage[LibraryGraph](
                 filename=db_location, table_name="graphs"

invokeai/app/api/routers/app_info.py

@@ -0,0 +1,18 @@
+from fastapi.routing import APIRouter
+from pydantic import BaseModel
+
+from invokeai.version import __version__
+
+app_router = APIRouter(prefix="/v1/app", tags=['app'])
+
+
+class AppVersion(BaseModel):
+    """App Version Response"""
+    version: str
+
+
+@app_router.get('/version', operation_id="app_version",
+                status_code=200,
+                response_model=AppVersion)
+async def get_version() -> AppVersion:
+    return AppVersion(version=__version__)

invokeai/app/api/routers/board_images.py

@@ -0,0 +1,69 @@
+from fastapi import Body, HTTPException, Path, Query
+from fastapi.routing import APIRouter
+from invokeai.app.services.board_record_storage import BoardRecord, BoardChanges
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.board_record import BoardDTO
+from invokeai.app.services.models.image_record import ImageDTO
+
+from ..dependencies import ApiDependencies
+
+board_images_router = APIRouter(prefix="/v1/board_images", tags=["boards"])
+
+
+@board_images_router.post(
+    "/",
+    operation_id="create_board_image",
+    responses={
+        201: {"description": "The image was added to a board successfully"},
+    },
+    status_code=201,
+)
+async def create_board_image(
+    board_id: str = Body(description="The id of the board to add to"),
+    image_name: str = Body(description="The name of the image to add"),
+):
+    """Creates a board_image"""
+    try:
+        result = ApiDependencies.invoker.services.board_images.add_image_to_board(board_id=board_id, image_name=image_name)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to add to board")
+    
+@board_images_router.delete(
+    "/",
+    operation_id="remove_board_image",
+    responses={
+        201: {"description": "The image was removed from the board successfully"},
+    },
+    status_code=201,
+)
+async def remove_board_image(
+    board_id: str = Body(description="The id of the board"),
+    image_name: str = Body(description="The name of the image to remove"),
+):
+    """Deletes a board_image"""
+    try:
+        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(board_id=board_id, image_name=image_name)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to update board")
+
+
+
+@board_images_router.get(
+    "/{board_id}",
+    operation_id="list_board_images",
+    response_model=OffsetPaginatedResults[ImageDTO],
+)
+async def list_board_images(
+    board_id: str = Path(description="The id of the board"),
+    offset: int = Query(default=0, description="The page offset"),
+    limit: int = Query(default=10, description="The number of boards per page"),
+) -> OffsetPaginatedResults[ImageDTO]:
+    """Gets a list of images for a board"""
+
+    results = ApiDependencies.invoker.services.board_images.get_images_for_board(
+        board_id,
+    )
+    return results
+

invokeai/app/api/routers/boards.py

@@ -0,0 +1,117 @@
+from typing import Optional, Union
+from fastapi import Body, HTTPException, Path, Query
+from fastapi.routing import APIRouter
+from invokeai.app.services.board_record_storage import BoardChanges
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.board_record import BoardDTO
+
+
+from ..dependencies import ApiDependencies
+
+boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
+
+
+@boards_router.post(
+    "/",
+    operation_id="create_board",
+    responses={
+        201: {"description": "The board was created successfully"},
+    },
+    status_code=201,
+    response_model=BoardDTO,
+)
+async def create_board(
+    board_name: str = Query(description="The name of the board to create"),
+) -> BoardDTO:
+    """Creates a board"""
+    try:
+        result = ApiDependencies.invoker.services.boards.create(board_name=board_name)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to create board")
+
+
+@boards_router.get("/{board_id}", operation_id="get_board", response_model=BoardDTO)
+async def get_board(
+    board_id: str = Path(description="The id of board to get"),
+) -> BoardDTO:
+    """Gets a board"""
+
+    try:
+        result = ApiDependencies.invoker.services.boards.get_dto(board_id=board_id)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=404, detail="Board not found")
+
+
+@boards_router.patch(
+    "/{board_id}",
+    operation_id="update_board",
+    responses={
+        201: {
+            "description": "The board was updated successfully",
+        },
+    },
+    status_code=201,
+    response_model=BoardDTO,
+)
+async def update_board(
+    board_id: str = Path(description="The id of board to update"),
+    changes: BoardChanges = Body(description="The changes to apply to the board"),
+) -> BoardDTO:
+    """Updates a board"""
+    try:
+        result = ApiDependencies.invoker.services.boards.update(
+            board_id=board_id, changes=changes
+        )
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to update board")
+
+
+@boards_router.delete("/{board_id}", operation_id="delete_board")
+async def delete_board(
+    board_id: str = Path(description="The id of board to delete"),
+    include_images: Optional[bool] = Query(
+        description="Permanently delete all images on the board", default=False
+    ),
+) -> None:
+    """Deletes a board"""
+    try:
+        if include_images is True:
+            ApiDependencies.invoker.services.images.delete_images_on_board(
+                board_id=board_id
+            )
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+        else:
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+    except Exception as e:
+        # TODO: Does this need any exception handling at all?
+        pass
+
+
+@boards_router.get(
+    "/",
+    operation_id="list_boards",
+    response_model=Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]],
+)
+async def list_boards(
+    all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
+    offset: Optional[int] = Query(default=None, description="The page offset"),
+    limit: Optional[int] = Query(
+        default=None, description="The number of boards per page"
+    ),
+) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
+    """Gets a list of boards"""
+    if all:
+        return ApiDependencies.invoker.services.boards.get_all()
+    elif offset is not None and limit is not None:
+        return ApiDependencies.invoker.services.boards.get_many(
+            offset,
+            limit,
+        )
+    else:
+        raise HTTPException(
+            status_code=400,
+            detail="Invalid request: Must provide either 'all' or both 'offset' and 'limit'",
+        )

invokeai/app/api/routers/images.py

@@ -70,27 +70,25 @@ async def upload_image(
         raise HTTPException(status_code=500, detail="Failed to create image")
 
 
-@images_router.delete("/{image_origin}/{image_name}", operation_id="delete_image")
+@images_router.delete("/{image_name}", operation_id="delete_image")
 async def delete_image(
-    image_origin: ResourceOrigin = Path(description="The origin of image to delete"),
     image_name: str = Path(description="The name of the image to delete"),
 ) -> None:
     """Deletes an image"""
 
     try:
-        ApiDependencies.invoker.services.images.delete(image_origin, image_name)
+        ApiDependencies.invoker.services.images.delete(image_name)
     except Exception as e:
         # TODO: Does this need any exception handling at all?
         pass
 
 
 @images_router.patch(
-    "/{image_origin}/{image_name}",
+    "/{image_name}",
     operation_id="update_image",
     response_model=ImageDTO,
 )
 async def update_image(
-    image_origin: ResourceOrigin = Path(description="The origin of image to update"),
     image_name: str = Path(description="The name of the image to update"),
     image_changes: ImageRecordChanges = Body(
         description="The changes to apply to the image"
@@ -99,32 +97,29 @@ async def update_image(
     """Updates an image"""
 
     try:
-        return ApiDependencies.invoker.services.images.update(
-            image_origin, image_name, image_changes
-        )
+        return ApiDependencies.invoker.services.images.update(image_name, image_changes)
     except Exception as e:
         raise HTTPException(status_code=400, detail="Failed to update image")
 
 
 @images_router.get(
-    "/{image_origin}/{image_name}/metadata",
+    "/{image_name}/metadata",
     operation_id="get_image_metadata",
     response_model=ImageDTO,
 )
 async def get_image_metadata(
-    image_origin: ResourceOrigin = Path(description="The origin of image to get"),
     image_name: str = Path(description="The name of image to get"),
 ) -> ImageDTO:
     """Gets an image's metadata"""
 
     try:
-        return ApiDependencies.invoker.services.images.get_dto(image_origin, image_name)
+        return ApiDependencies.invoker.services.images.get_dto(image_name)
     except Exception as e:
         raise HTTPException(status_code=404)
 
 
 @images_router.get(
-    "/{image_origin}/{image_name}",
+    "/{image_name}",
     operation_id="get_image_full",
     response_class=Response,
     responses={
@@ -136,15 +131,12 @@ async def get_image_metadata(
     },
 )
 async def get_image_full(
-    image_origin: ResourceOrigin = Path(
-        description="The type of full-resolution image file to get"
-    ),
     image_name: str = Path(description="The name of full-resolution image file to get"),
 ) -> FileResponse:
     """Gets a full-resolution image file"""
 
     try:
-        path = ApiDependencies.invoker.services.images.get_path(image_origin, image_name)
+        path = ApiDependencies.invoker.services.images.get_path(image_name)
 
         if not ApiDependencies.invoker.services.images.validate_path(path):
             raise HTTPException(status_code=404)
@@ -160,7 +152,7 @@ async def get_image_full(
 
 
 @images_router.get(
-    "/{image_origin}/{image_name}/thumbnail",
+    "/{image_name}/thumbnail",
     operation_id="get_image_thumbnail",
     response_class=Response,
     responses={
@@ -172,14 +164,13 @@ async def get_image_full(
     },
 )
 async def get_image_thumbnail(
-    image_origin: ResourceOrigin = Path(description="The origin of thumbnail image file to get"),
     image_name: str = Path(description="The name of thumbnail image file to get"),
 ) -> FileResponse:
     """Gets a thumbnail image file"""
 
     try:
         path = ApiDependencies.invoker.services.images.get_path(
-            image_origin, image_name, thumbnail=True
+            image_name, thumbnail=True
         )
         if not ApiDependencies.invoker.services.images.validate_path(path):
             raise HTTPException(status_code=404)
@@ -192,25 +183,21 @@ async def get_image_thumbnail(
 
 
 @images_router.get(
-    "/{image_origin}/{image_name}/urls",
+    "/{image_name}/urls",
     operation_id="get_image_urls",
     response_model=ImageUrlsDTO,
 )
 async def get_image_urls(
-    image_origin: ResourceOrigin = Path(description="The origin of the image whose URL to get"),
     image_name: str = Path(description="The name of the image whose URL to get"),
 ) -> ImageUrlsDTO:
     """Gets an image and thumbnail URL"""
 
     try:
-        image_url = ApiDependencies.invoker.services.images.get_url(
-            image_origin, image_name
-        )
+        image_url = ApiDependencies.invoker.services.images.get_url(image_name)
         thumbnail_url = ApiDependencies.invoker.services.images.get_url(
-            image_origin, image_name, thumbnail=True
+            image_name, thumbnail=True
         )
         return ImageUrlsDTO(
-            image_origin=image_origin,
             image_name=image_name,
             image_url=image_url,
             thumbnail_url=thumbnail_url,
@@ -234,6 +221,9 @@ async def list_images_with_metadata(
     is_intermediate: Optional[bool] = Query(
         default=None, description="Whether to list intermediate images"
     ),
+    board_id: Optional[str] = Query(
+        default=None, description="The board id to filter by"
+    ),
     offset: int = Query(default=0, description="The page offset"),
     limit: int = Query(default=10, description="The number of images per page"),
 ) -> OffsetPaginatedResults[ImageDTO]:
@@ -245,6 +235,7 @@ async def list_images_with_metadata(
         image_origin,
         categories,
         is_intermediate,
+        board_id,
     )
 
     return image_dtos

invokeai/app/api/routers/models.py

@@ -1,100 +1,134 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2024 Lincoln Stein
 
-import shutil
-import asyncio
-from typing import Annotated, Any, List, Literal, Optional, Union
 
-from fastapi.routing import APIRouter, HTTPException
-from pydantic import BaseModel, Field, parse_obj_as
-from pathlib import Path
+from typing import Literal, List, Optional, Union
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, parse_obj_as
+from starlette.exceptions import HTTPException
+
+from invokeai.backend import BaseModelType, ModelType
+from invokeai.backend.model_management.models import (
+    OPENAPI_MODEL_CONFIGS,
+    SchedulerPredictionType,
+)
+from invokeai.backend.model_management import MergeInterpolationMethod
 from ..dependencies import ApiDependencies
 
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
-
-class VaeRepo(BaseModel):
-    repo_id: str = Field(description="The repo ID to use for this VAE")
-    path: Optional[str] = Field(description="The path to the VAE")
-    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
-
-class ModelInfo(BaseModel):
-    description: Optional[str] = Field(description="A description of the model")
-    
-class CkptModelInfo(ModelInfo):
-    format: Literal['ckpt'] = 'ckpt'
-
-    config: str = Field(description="The path to the model config")
-    weights: str = Field(description="The path to the model weights")
-    vae: str = Field(description="The path to the model VAE")
-    width: Optional[int] = Field(description="The width of the model")
-    height: Optional[int] = Field(description="The height of the model")
-
-class DiffusersModelInfo(ModelInfo):
-    format: Literal['diffusers'] = 'diffusers'
-
-    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
-    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
-    path: Optional[str] = Field(description="The path to the model")
-
-class CreateModelRequest(BaseModel):
-    name: str = Field(description="The name of the model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-
-class CreateModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-    status: str = Field(description="The status of the API response")
-
-class ConversionRequest(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: CkptModelInfo = Field(description="The converted model info")
-    save_location: str = Field(description="The path to save the converted model weights")
-    
-
-class ConvertedModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: DiffusersModelInfo = Field(description="The converted model info")
+UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 
 class ModelsList(BaseModel):
-    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
-
+    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
 
 @models_router.get(
     "/",
     operation_id="list_models",
     responses={200: {"model": ModelsList }},
 )
-async def list_models() -> ModelsList:
+async def list_models(
+    base_model: Optional[BaseModelType] = Query(default=None, description="Base model"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+) -> ModelsList:
     """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type)
     models = parse_obj_as(ModelsList, { "models": models_raw })
     return models
 
-
-@models_router.post(
-    "/",
+@models_router.patch(
+    "/{base_model}/{model_type}/{model_name}",
     operation_id="update_model",
-    responses={200: {"status": "success"}},
+    responses={200: {"description" : "The model was updated successfully"},
+               404: {"description" : "The model could not be found"},
+               400: {"description" : "Bad request"}
+               },
+    status_code = 200,
+    response_model = UpdateModelResponse,
 )
 async def update_model(
-    model_request: CreateModelRequest
-) -> CreateModelResponse:
+        base_model: BaseModelType = Path(description="Base model"),
+        model_type: ModelType = Path(description="The type of model"),
+        model_name: str = Path(description="model name"),
+        info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
+) -> UpdateModelResponse:
     """ Add Model """
-    model_request_info = model_request.info
-    info_dict = model_request_info.dict()
-    model_response = CreateModelResponse(name=model_request.name, info=model_request.info, status="success")
-
-    ApiDependencies.invoker.services.model_manager.add_model(
-        model_name=model_request.name,
-        model_attributes=info_dict,
-        clobber=True,
-    )
+    try:
+        ApiDependencies.invoker.services.model_manager.update_model(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+            model_attributes=info.dict()
+        )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        )
+        model_response = parse_obj_as(UpdateModelResponse, model_raw)
+    except KeyError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
 
     return model_response
 
+@models_router.post(
+    "/",
+    operation_id="import_model",
+    responses= {
+        201: {"description" : "The model imported successfully"},
+        404: {"description" : "The model could not be found"},
+        424: {"description" : "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description" : "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+    response_model=ImportModelResponse
+)
+async def import_model(
+        location: str = Body(description="A model path, repo_id or URL to import"),
+        prediction_type: Optional[Literal['v_prediction','epsilon','sample']] = \
+                Body(description='Prediction type for SDv2 checkpoint files', default="v_prediction"),
+) -> ImportModelResponse:
+    """ Add a model using its local path, repo_id, or remote URL """
+    
+    items_to_import = {location}
+    prediction_types = { x.value: x for x in SchedulerPredictionType }
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
+            items_to_import = items_to_import,
+            prediction_type_helper = lambda x: prediction_types.get(prediction_type)
+        )
+        info = installed_models.get(location)
+
+        if not info:
+            logger.error("Import failed")
+            raise HTTPException(status_code=424)
+        
+        logger.info(f'Successfully imported {location}, got {info}')
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name=info.name,
+            base_model=info.base_model,
+            model_type=info.model_type
+        )
+        return parse_obj_as(ImportModelResponse, model_raw)
+    
+    except KeyError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+        
 
 @models_router.delete(
-    "/{model_name}",
+    "/{base_model}/{model_type}/{model_name}",
     operation_id="del_model",
     responses={
         204: {
@@ -105,144 +139,95 @@ async def update_model(
         }
     },
 )
-async def delete_model(model_name: str) -> None:
+async def delete_model(
+        base_model: BaseModelType = Path(description="Base model"),
+        model_type: ModelType = Path(description="The type of model"),
+        model_name: str = Path(description="model name"),
+) -> Response:
     """Delete Model"""
-    model_names = ApiDependencies.invoker.services.model_manager.model_names()
     logger = ApiDependencies.invoker.services.logger
-    model_exists = model_name in model_names
-
-    # check if model exists
-    logger.info(f"Checking for model {model_name}...")
-           
-    if model_exists:
-        logger.info(f"Deleting Model: {model_name}")
-        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
-        logger.info(f"Model Deleted: {model_name}")
-        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
     
-    else:
-        logger.error(f"Model not found")
+    try:
+        ApiDependencies.invoker.services.model_manager.del_model(model_name,
+                                                                 base_model = base_model,
+                                                                 model_type = model_type
+                                                                 )
+        logger.info(f"Deleted model: {model_name}")
+        return Response(status_code=204)
+    except KeyError:
+        logger.error(f"Model not found: {model_name}")
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
-    
 
-            # @socketio.on("convertToDiffusers")
-        # def convert_to_diffusers(model_to_convert: dict):
-        #     try:
-        #         if model_info := self.generate.model_manager.model_info(
-        #             model_name=model_to_convert["model_name"]
-        #         ):
-        #             if "weights" in model_info:
-        #                 ckpt_path = Path(model_info["weights"])
-        #                 original_config_file = Path(model_info["config"])
-        #                 model_name = model_to_convert["model_name"]
-        #                 model_description = model_info["description"]
-        #             else:
-        #                 self.socketio.emit(
-        #                     "error", {"message": "Model is not a valid checkpoint file"}
-        #                 )
-        #         else:
-        #             self.socketio.emit(
-        #                 "error", {"message": "Could not retrieve model info."}
-        #             )
-
-        #         if not ckpt_path.is_absolute():
-        #             ckpt_path = Path(Globals.root, ckpt_path)
-
-        #         if original_config_file and not original_config_file.is_absolute():
-        #             original_config_file = Path(Globals.root, original_config_file)
-
-        #         diffusers_path = Path(
-        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
-        #         )
-
-        #         if model_to_convert["save_location"] == "root":
-        #             diffusers_path = Path(
-        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
-        #             )
-
-        #         if (
-        #             model_to_convert["save_location"] == "custom"
-        #             and model_to_convert["custom_location"] is not None
-        #         ):
-        #             diffusers_path = Path(
-        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
-        #             )
-
-        #         if diffusers_path.exists():
-        #             shutil.rmtree(diffusers_path)
-
-        #         self.generate.model_manager.convert_and_import(
-        #             ckpt_path,
-        #             diffusers_path,
-        #             model_name=model_name,
-        #             model_description=model_description,
-        #             vae=None,
-        #             original_config_file=original_config_file,
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         new_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "modelConverted",
-        #             {
-        #                 "new_model_name": model_name,
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Model Converted: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("mergeDiffusersModels")
-        # def merge_diffusers_models(model_merge_info: dict):
-        #     try:
-        #         models_to_merge = model_merge_info["models_to_merge"]
-        #         model_ids_or_paths = [
-        #             self.generate.model_manager.model_name_or_path(x)
-        #             for x in models_to_merge
-        #         ]
-        #         merged_pipe = merge_diffusion_models(
-        #             model_ids_or_paths,
-        #             model_merge_info["alpha"],
-        #             model_merge_info["interp"],
-        #             model_merge_info["force"],
-        #         )
-
-        #         dump_path = global_models_dir() / "merged_models"
-        #         if model_merge_info["model_merge_save_path"] is not None:
-        #             dump_path = Path(model_merge_info["model_merge_save_path"])
-
-        #         os.makedirs(dump_path, exist_ok=True)
-        #         dump_path = dump_path / model_merge_info["merged_model_name"]
-        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
-
-        #         merged_model_config = dict(
-        #             model_name=model_merge_info["merged_model_name"],
-        #             description=f'Merge of models {", ".join(models_to_merge)}',
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
-        #             "vae", None
-        #         ):
-        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
-        #             merged_model_config.update(vae=vae)
-
-        #         self.generate.model_manager.import_diffuser_model(
-        #             dump_path, **merged_model_config
-        #         )
-        #         new_model_list = self.generate.model_manager.list_models()
-
-        #         socketio.emit(
-        #             "modelsMerged",
-        #             {
-        #                 "merged_models": models_to_merge,
-        #                 "merged_model_name": model_merge_info["merged_model_name"],
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Models Merged: {models_to_merge}")
-        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as e:
+@models_router.put(
+    "/convert/{base_model}/{model_type}/{model_name}",
+    operation_id="convert_model",
+    responses={
+        200: { "description": "Model converted successfully" },
+        400: {"description" : "Bad request"  },
+        404: { "description": "Model not found"  },
+    },
+    status_code = 200,
+    response_model = ConvertModelResponse,
+)
+async def convert_model(
+        base_model: BaseModelType = Path(description="Base model"),
+        model_type: ModelType = Path(description="The type of model"),
+        model_name: str = Path(description="model name"),
+) -> ConvertModelResponse:
+    """Convert a checkpoint model into a diffusers model"""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Converting model: {model_name}")
+        ApiDependencies.invoker.services.model_manager.convert_model(model_name,
+                                                                     base_model = base_model,
+                                                                     model_type = model_type
+                                                                     )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(model_name,
+                                                                              base_model = base_model,
+                                                                              model_type = model_type)
+        response = parse_obj_as(ConvertModelResponse, model_raw)
+    except KeyError:
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response
+        
+@models_router.put(
+    "/merge/{base_model}",
+    operation_id="merge_models",
+    responses={
+        200: { "description": "Model converted successfully" },
+        400: { "description": "Incompatible models"  },
+        404: { "description": "One or more models not found"  },
+    },
+    status_code = 200,
+    response_model = MergeModelResponse,
+)
+async def merge_models(
+        base_model: BaseModelType                  = Path(description="Base model"),
+        model_names: List[str]                     = Body(description="model name", min_items=2, max_items=3),
+        merged_model_name: Optional[str]           = Body(description="Name of destination model"),
+        alpha: Optional[float]                     = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+        interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
+        force: Optional[bool]                      = Body(description="Force merging of models created with different versions of diffusers", default=False),
+) -> MergeModelResponse:
+    """Convert a checkpoint model into a diffusers model"""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Merging models: {model_names}")
+        result = ApiDependencies.invoker.services.model_manager.merge_models(model_names,
+                                                                             base_model,
+                                                                             merged_model_name or "+".join(model_names),
+                                                                             alpha,
+                                                                             interp,
+                                                                             force)
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(result.name,
+                                                                              base_model = base_model,
+                                                                              model_type = ModelType.Main,
+                                                                              )
+        response = parse_obj_as(ConvertModelResponse, model_raw)
+    except KeyError:
+        raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response

invokeai/app/api_app.py

@@ -22,12 +22,22 @@ app_config.parse_args()
 logger = InvokeAILogger.getLogger(config=app_config)
 
 import invokeai.frontend.web as web_dir
+import mimetypes
 
 from .api.dependencies import ApiDependencies
-from .api.routers import sessions, models, images
+from .api.routers import sessions, models, images, boards, board_images, app_info
 from .api.sockets import SocketIO
 from .invocations.baseinvocation import BaseInvocation
 
+import torch
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
+
+# fix for windows mimetypes registry entries being borked
+# see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
+mimetypes.add_type('application/javascript', '.js')
+mimetypes.add_type('text/css', '.css')
+
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
 app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)
@@ -78,6 +88,12 @@ app.include_router(models.models_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
 
+app.include_router(boards.boards_router, prefix="/api")
+
+app.include_router(board_images.board_images_router, prefix="/api")
+
+app.include_router(app_info.app_router, prefix='/api')
+
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
 def custom_openapi():
@@ -116,6 +132,22 @@ def custom_openapi():
 
         invoker_schema["output"] = outputs_ref
 
+    from invokeai.backend.model_management.models import get_model_config_enums
+    for model_config_format_enum in set(get_model_config_enums()):
+        name = model_config_format_enum.__qualname__
+
+        if name in openapi_schema["components"]["schemas"]:
+            # print(f"Config with name {name} already defined")
+            continue
+
+        # "BaseModelType":{"title":"BaseModelType","description":"An enumeration.","enum":["sd-1","sd-2"],"type":"string"}
+        openapi_schema["components"]["schemas"][name] = dict(
+            title=name,
+            description="An enumeration.",
+            type="string",
+            enum=list(v.value for v in model_config_format_enum),
+        )
+
     app.openapi_schema = openapi_schema
     return app.openapi_schema
 

invokeai/app/cli/commands.py

@@ -47,7 +47,7 @@ def add_parsers(
     commands: list[type],
     command_field: str = "type",
     exclude_fields: list[str] = ["id", "type"],
-    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None],None] = None
     ):
     """Adds parsers for each command to the subparsers"""
 
@@ -72,7 +72,7 @@ def add_parsers(
 def add_graph_parsers(
     subparsers,
     graphs: list[LibraryGraph],
-    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
 ):
     for graph in graphs:
         command_parser = subparsers.add_parser(graph.name, help=graph.description)

invokeai/app/cli_app.py

@@ -1,15 +1,11 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 import argparse
-import os
 import re
 import shlex
 import sys
 import time
-from typing import (
-    Union,
-    get_type_hints,
-)
+from typing import Union, get_type_hints, Optional
 
 from pydantic import BaseModel, ValidationError
 from pydantic.fields import Field
@@ -21,30 +17,45 @@ config = InvokeAIAppConfig.get_config()
 config.parse_args()
 logger = InvokeAILogger().getLogger(config=config)
 
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
 from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-from invokeai.app.services.images import ImageService
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
 from invokeai.app.services.metadata import CoreMetadataService
 from invokeai.app.services.resource_name import SimpleNameService
 from invokeai.app.services.urls import LocalUrlService
-
-from .services.default_graphs import create_system_graphs
+from .services.default_graphs import (default_text_to_image_graph_id,
+                                      create_system_graphs)
 from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
 
-from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, SortedHelpFormatter
+from .cli.commands import (BaseCommand, CliContext, ExitCli,
+                           SortedHelpFormatter, add_graph_parsers, add_parsers)
 from .cli.completer import set_autocompleter
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
-from .services.model_manager_initializer import get_model_manager
-from .services.restoration_services import RestorationServices
-from .services.graph import Edge, EdgeConnection, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
-from .services.default_graphs import default_text_to_image_graph_id
+from .services.graph import (Edge, EdgeConnection, GraphExecutionState,
+                             GraphInvocation, LibraryGraph,
+                             are_connection_types_compatible)
 from .services.image_file_storage import DiskImageFileStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
 from .services.invoker import Invoker
+from .services.model_manager_service import ModelManagerService
 from .services.processor import DefaultInvocationProcessor
+from .services.restoration_services import RestorationServices
 from .services.sqlite import SqliteItemStorage
 
+import torch
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
+
 
 class CliCommand(BaseModel):
     command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
@@ -197,7 +208,6 @@ def invoke_all(context: CliContext):
         raise SessionError()
 
 def invoke_cli():
-    
     # get the optional list of invocations to execute on the command line
     parser = config.get_parser()
     parser.add_argument('commands',nargs='*')
@@ -208,8 +218,8 @@ def invoke_cli():
     if infile := config.from_file:
         sys.stdin = open(infile,"r")
     
-    model_manager = get_model_manager(config,logger=logger)
-    
+    model_manager = ModelManagerService(config,logger)
+
     events = EventServiceBase()
     output_folder = config.output_path
 
@@ -232,21 +242,49 @@ def invoke_cli():
     image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
     names = SimpleNameService()
 
-    images = ImageService(
-        image_record_storage=image_record_storage,
-        image_file_storage=image_file_storage,
-        metadata=metadata,
-        url=urls,
-        logger=logger,
-        names=names,
-        graph_execution_manager=graph_execution_manager,
+    board_record_storage = SqliteBoardRecordStorage(db_location)
+    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+
+    boards = BoardService(
+        services=BoardServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
     )
 
+    board_images = BoardImagesService(
+        services=BoardImagesServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
+    )
+
+    images = ImageService(
+        services=ImageServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            image_record_storage=image_record_storage,
+            image_file_storage=image_file_storage,
+            metadata=metadata,
+            url=urls,
+            logger=logger,
+            names=names,
+            graph_execution_manager=graph_execution_manager,
+        )
+    )
+        
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
         images=images,
+        boards=boards,
+        board_images=board_images,
         queue=MemoryInvocationQueue(),
         graph_library=SqliteItemStorage[LibraryGraph](
             filename=db_location, table_name="graphs"
@@ -257,9 +295,11 @@ def invoke_cli():
         logger=logger,
         configuration=config,
     )
+    
 
     system_graphs = create_system_graphs(services.graph_library)
     system_graph_names = set([g.name for g in system_graphs])
+    set_autocompleter(services)
 
     invoker = Invoker(services)
     session: GraphExecutionState = invoker.create_execution_state()
@@ -311,7 +351,7 @@ def invoke_cli():
 
                 # Parse invocation
                 command: CliCommand = None # type:ignore
-                system_graph: LibraryGraph|None = None
+                system_graph: Optional[LibraryGraph] = None
                 if args['type'] in system_graph_names:
                     system_graph = next(filter(lambda g: g.name == args['type'], system_graphs))
                     invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))

invokeai/app/invocations/baseinvocation.py

@@ -4,9 +4,10 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict, TYPE_CHECKING
+from typing import (TYPE_CHECKING, Dict, List, Literal, TypedDict, get_args,
+                    get_type_hints)
 
-from pydantic import BaseModel, Field
+from pydantic import BaseConfig, BaseModel, Field
 
 if TYPE_CHECKING:
     from ..services.invocation_services import InvocationServices
@@ -65,8 +66,13 @@ class BaseInvocation(ABC, BaseModel):
     @classmethod
     def get_invocations_map(cls):
         # Get the type strings out of the literals and into a dictionary
-        return dict(map(lambda t: (get_args(get_type_hints(t)['type'])[0], t),BaseInvocation.get_all_subclasses()))
-    
+        return dict(
+            map(
+                lambda t: (get_args(get_type_hints(t)["type"])[0], t),
+                BaseInvocation.get_all_subclasses(),
+            )
+        )
+
     @classmethod
     def get_output_type(cls):
         return signature(cls.invoke).return_annotation
@@ -75,11 +81,11 @@ class BaseInvocation(ABC, BaseModel):
     def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
         """Invoke with provided context and return outputs."""
         pass
-    
-    #fmt: off
+
+    # fmt: off
     id: str = Field(description="The id of this node. Must be unique among all nodes.")
     is_intermediate: bool = Field(default=False, description="Whether or not this node is an intermediate node.")
-    #fmt: on
+    # fmt: on
 
 
 # TODO: figure out a better way to provide these hints
@@ -97,16 +103,20 @@ class UIConfig(TypedDict, total=False):
             "latents",
             "model",
             "control",
+            "image_collection",
+            "vae_model",
+            "lora_model",
         ],
     ]
     tags: List[str]
     title: str
 
+
 class CustomisedSchemaExtra(TypedDict):
     ui: UIConfig
 
 
-class InvocationConfig(BaseModel.Config):
+class InvocationConfig(BaseConfig):
     """Customizes pydantic's BaseModel.Config class for use by Invocations.
 
     Provide `schema_extra` a `ui` dict to add hints for generated UIs.

invokeai/app/invocations/collections.py

@@ -4,13 +4,16 @@ from typing import Literal
 
 import numpy as np
 from pydantic import Field, validator
+from invokeai.app.models.image import ImageField
 
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
 from .baseinvocation import (
     BaseInvocation,
+    InvocationConfig,
     InvocationContext,
     BaseInvocationOutput,
+    UIConfig,
 )
 
 
@@ -22,6 +25,7 @@ class IntCollectionOutput(BaseInvocationOutput):
     # Outputs
     collection: list[int] = Field(default=[], description="The int collection")
 
+
 class FloatCollectionOutput(BaseInvocationOutput):
     """A collection of floats"""
 
@@ -31,6 +35,18 @@ class FloatCollectionOutput(BaseInvocationOutput):
     collection: list[float] = Field(default=[], description="The float collection")
 
 
+class ImageCollectionOutput(BaseInvocationOutput):
+    """A collection of images"""
+
+    type: Literal["image_collection"] = "image_collection"
+
+    # Outputs
+    collection: list[ImageField] = Field(default=[], description="The output images")
+
+    class Config:
+        schema_extra = {"required": ["type", "collection"]}
+
+
 class RangeInvocation(BaseInvocation):
     """Creates a range of numbers from start to stop with step"""
 
@@ -92,3 +108,27 @@ class RandomRangeInvocation(BaseInvocation):
         return IntCollectionOutput(
             collection=list(rng.integers(low=self.low, high=self.high, size=self.size))
         )
+
+
+class ImageCollectionInvocation(BaseInvocation):
+    """Load a collection of images and provide it as output."""
+
+    # fmt: off
+    type: Literal["image_collection"] = "image_collection"
+
+    # Inputs
+    images: list[ImageField] = Field(
+        default=[], description="The image collection to load"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> ImageCollectionOutput:
+        return ImageCollectionOutput(collection=self.images)
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "type_hints": {
+                    "images": "image_collection",
+                }
+            },
+        }

invokeai/app/invocations/compel.py

@@ -1,25 +1,25 @@
-from typing import Literal, Optional, Union
+from typing import Literal, Optional, Union, List
 from pydantic import BaseModel, Field
-
-from invokeai.app.invocations.util.choose_model import choose_model
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-from ...backend.prompting.conditioning import try_parse_legacy_blend
-
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
-from ...backend.stable_diffusion.textual_inversion_manager import TextualInversionManager
-
+import re
+import torch
 from compel import Compel
-from compel.prompt_parser import (
-    Blend,
-    CrossAttentionControlSubstitute,
-    FlattenedPrompt,
-    Fragment, Conjunction,
-)
+from compel.prompt_parser import (Blend, Conjunction,
+                                  CrossAttentionControlSubstitute,
+                                  FlattenedPrompt, Fragment)
+from ...backend.util.devices import torch_dtype
+from ...backend.model_management import ModelType
+from ...backend.model_management.models import ModelNotFoundException
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+from .model import ClipField
 
 
 class ConditioningField(BaseModel):
-    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
+    conditioning_name: Optional[str] = Field(
+        default=None, description="The name of conditioning data")
+
     class Config:
         schema_extra = {"required": ["conditioning_name"]}
 
@@ -40,7 +40,7 @@ class CompelInvocation(BaseInvocation):
     type: Literal["compel"] = "compel"
 
     prompt: str = Field(default="", description="Prompt")
-    model: str = Field(default="", description="Model to use")
+    clip: ClipField = Field(None, description="Clip to use")
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -49,69 +49,77 @@ class CompelInvocation(BaseInvocation):
                 "title": "Prompt (Compel)",
                 "tags": ["prompt", "compel"],
                 "type_hints": {
-                  "model": "model"
+                    "model": "model"
                 }
             },
         }
 
+    @torch.no_grad()
     def invoke(self, context: InvocationContext) -> CompelOutput:
-
-        # TODO: load without model
-        model = choose_model(context.services.model_manager, self.model)
-        pipeline = model["model"]
-        tokenizer = pipeline.tokenizer
-        text_encoder = pipeline.text_encoder
-
-        # TODO: global? input?
-        #use_full_precision = precision == "float32" or precision == "autocast"
-        #use_full_precision = False
-
-        # TODO: redo TI when separate model loding implemented
-        #textual_inversion_manager = TextualInversionManager(
-        #    tokenizer=tokenizer,
-        #    text_encoder=text_encoder,
-        #    full_precision=use_full_precision,
-        #)
-
-        def load_huggingface_concepts(concepts: list[str]):
-            pipeline.textual_inversion_manager.load_huggingface_concepts(concepts)
-
-        # apply the concepts library to the prompt
-        prompt_str = pipeline.textual_inversion_manager.hf_concepts_library.replace_concepts_with_triggers(
-            self.prompt,
-            lambda concepts: load_huggingface_concepts(concepts),
-            pipeline.textual_inversion_manager.get_all_trigger_strings(),
+        tokenizer_info = context.services.model_manager.get_model(
+            **self.clip.tokenizer.dict(),
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **self.clip.text_encoder.dict(),
         )
 
-        # lazy-load any deferred textual inversions.
-        # this might take a couple of seconds the first time a textual inversion is used.
-        pipeline.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(
-            prompt_str
-        )
+        def _lora_loader():
+            for lora in self.clip.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
 
-        compel = Compel(
-            tokenizer=tokenizer,
-            text_encoder=text_encoder,
-            textual_inversion_manager=pipeline.textual_inversion_manager,
-            dtype_for_device_getter=torch_dtype,
-            truncate_long_prompts=False,
-        )
+        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        legacy_blend = try_parse_legacy_blend(prompt_str, skip_normalize=False)
-        if legacy_blend is not None:
-            conjunction = legacy_blend
-        else:
-            conjunction = Compel.parse_prompt_string(prompt_str)
+        ti_list = []
+        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    context.services.model_manager.get_model(
+                        model_name=name,
+                        base_model=self.clip.text_encoder.base_model,
+                        model_type=ModelType.TextualInversion,
+                    ).context.model
+                )
+            except ModelNotFoundException:
+                # print(e)
+                #import traceback
+                #print(traceback.format_exc())
+                print(f"Warn: trigger: \"{trigger}\" not found")
 
-        if context.services.configuration.log_tokenization:
-            log_tokenization_for_conjunction(conjunction, tokenizer)
+        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
+                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
+                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),\
+                text_encoder_info as text_encoder:
 
-        c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            compel = Compel(
+                tokenizer=tokenizer,
+                text_encoder=text_encoder,
+                textual_inversion_manager=ti_manager,
+                dtype_for_device_getter=torch_dtype,
+                truncate_long_prompts=True,  # TODO:
+            )
 
-        ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
-            tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-            cross_attention_control_args=options.get("cross_attention_control", None),
-        )
+            conjunction = Compel.parse_prompt_string(self.prompt)
+            prompt: Union[FlattenedPrompt, Blend] = conjunction.prompts[0]
+
+            if context.services.configuration.log_tokenization:
+                log_tokenization_for_prompt_object(prompt, tokenizer)
+
+            c, options = compel.build_conditioning_tensor_for_prompt_object(
+                prompt)
+
+            # TODO: long prompt support
+            # if not self.truncate_long_prompts:
+            #    [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
+            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+                tokens_count_including_eos_bos=get_max_token_count(
+                    tokenizer, conjunction),
+                cross_attention_control_args=options.get(
+                    "cross_attention_control", None),)
 
         conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
 
@@ -124,10 +132,28 @@ class CompelInvocation(BaseInvocation):
             ),
         )
 
+class ClipSkipInvocationOutput(BaseInvocationOutput):
+    """Clip skip node output"""
+    type: Literal["clip_skip_output"] = "clip_skip_output"
+    clip: ClipField = Field(None, description="Clip with skipped layers")
+
+class ClipSkipInvocation(BaseInvocation):
+    """Skip layers in clip text_encoder model."""
+    type: Literal["clip_skip"] = "clip_skip"
+
+    clip: ClipField = Field(None, description="Clip to use")
+    skipped_layers: int = Field(0, description="Number of layers to skip in text_encoder")
+
+    def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
+        self.clip.skipped_layers += self.skipped_layers
+        return ClipSkipInvocationOutput(
+            clip=self.clip,
+        )
+
 
 def get_max_token_count(
-    tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
-) -> int:
+        tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction],
+        truncate_if_too_long=False) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
         return max(
@@ -146,13 +172,13 @@ def get_max_token_count(
         )
     else:
         return len(
-            get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long)
-        )
+            get_tokens_for_prompt_object(
+                tokenizer, prompt, truncate_if_too_long))
 
 
 def get_tokens_for_prompt_object(
     tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True
-) -> [str]:
+) -> List[str]:
     if type(parsed_prompt) is Blend:
         raise ValueError(
             "Blend is not supported here - you need to get tokens for each of its .children"
@@ -181,7 +207,7 @@ def log_tokenization_for_conjunction(
 ):
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
-        if len(c.prompts)>1:
+        if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
             this_display_label_prefix = display_label_prefix
@@ -236,7 +262,8 @@ def log_tokenization_for_prompt_object(
             )
 
 
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(
+        text, tokenizer, display_label=None, truncate_if_too_long=False):
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/controlnet_image_processors.py

@@ -1,11 +1,12 @@
-# InvokeAI nodes for ControlNet image preprocessors
+# Invocations for ControlNet image preprocessors
 # initial implementation by Gregg Helt, 2023
 # heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
-from builtins import float
+from builtins import float, bool
 
+import cv2
 import numpy as np
-from typing import Literal, Optional, Union, List
-from PIL import Image, ImageFilter, ImageOps
+from typing import Literal, Optional, Union, List, Dict
+from PIL import Image
 from pydantic import BaseModel, Field, validator
 
 from ..models.image import ImageField, ImageCategory, ResourceOrigin
@@ -29,8 +30,13 @@ from controlnet_aux import (
     ContentShuffleDetector,
     ZoeDetector,
     MediapipeFaceDetector,
+    SamDetector,
+    LeresDetector,
 )
 
+from controlnet_aux.util import HWC3, ade_palette
+
+
 from .image import ImageOutput, PILInvocationConfig
 
 CONTROLNET_DEFAULT_MODELS = [
@@ -94,6 +100,10 @@ CONTROLNET_DEFAULT_MODELS = [
 ]
 
 CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
+CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
+# crop and fill options not ready yet
+# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
+
 
 class ControlField(BaseModel):
     image: ImageField = Field(default=None, description="The control image")
@@ -104,6 +114,9 @@ class ControlField(BaseModel):
                                       description="When the ControlNet is first applied (% of total steps)")
     end_step_percent: float = Field(default=1, ge=0, le=1,
                                     description="When the ControlNet is last applied (% of total steps)")
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
+    # resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
     @validator("control_weight")
     def abs_le_one(cls, v):
         """validate that all abs(values) are <=1"""
@@ -144,11 +157,11 @@ class ControlNetInvocation(BaseInvocation):
     control_model: CONTROLNET_NAME_VALUES = Field(default="lllyasviel/sd-controlnet-canny",
                                                   description="control model used")
     control_weight: Union[float, List[float]] = Field(default=1.0, description="The weight given to the ControlNet")
-    # TODO: add support in backend core for begin_step_percent, end_step_percent, guess_mode
     begin_step_percent: float = Field(default=0, ge=0, le=1,
                                       description="When the ControlNet is first applied (% of total steps)")
     end_step_percent: float = Field(default=1, ge=0, le=1,
                                     description="When the ControlNet is last applied (% of total steps)")
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode used")
     # fmt: on
 
     class Config(InvocationConfig):
@@ -166,7 +179,6 @@ class ControlNetInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ControlOutput:
-
         return ControlOutput(
             control=ControlField(
                 image=self.image,
@@ -174,10 +186,11 @@ class ControlNetInvocation(BaseInvocation):
                 control_weight=self.control_weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
+                control_mode=self.control_mode,
             ),
         )
 
-# TODO: move image processors to separate file (image_analysis.py
+
 class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
     """Base class for invocations that preprocess images for ControlNet"""
 
@@ -193,9 +206,7 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        raw_image = context.services.images.get_pil_image(self.image.image_name)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
@@ -216,10 +227,7 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         """Builds an ImageOutput and its ImageField"""
-        processed_image_field = ImageField(
-            image_name=image_dto.image_name,
-            image_origin=image_dto.image_origin,
-        )
+        processed_image_field = ImageField(image_name=image_dto.image_name)
         return ImageOutput(
             image=processed_image_field,
             # width=processed_image.width,
@@ -414,9 +422,9 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvoca
     # Inputs
     detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
     image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
-    h: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
-    w: Union[int, None] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
-    f: Union[int, None] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
+    h: Optional[int] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
+    w: Optional[int] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
+    f: Optional[int] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
     # fmt: on
 
     def run_processor(self, image):
@@ -454,6 +462,104 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
     # fmt: on
 
     def run_processor(self, image):
+        # MediaPipeFaceDetector throws an error if image has alpha channel
+        #     so convert to RGB if needed
+        if image.mode == 'RGBA':
+            image = image.convert('RGB')
         mediapipe_face_processor = MediapipeFaceDetector()
         processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
         return processed_image
+
+class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies leres processing to image"""
+    # fmt: off
+    type: Literal["leres_image_processor"] = "leres_image_processor"
+    # Inputs
+    thr_a: float = Field(default=0, description="Leres parameter `thr_a`")
+    thr_b: float = Field(default=0, description="Leres parameter `thr_b`")
+    boost: bool = Field(default=False, description="Whether to use boost mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = leres_processor(image,
+                                          thr_a=self.thr_a,
+                                          thr_b=self.thr_b,
+                                          boost=self.boost,
+                                          detect_resolution=self.detect_resolution,
+                                          image_resolution=self.image_resolution)
+        return processed_image
+
+
+class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+
+    # fmt: off
+    type: Literal["tile_image_processor"] = "tile_image_processor"
+    # Inputs
+    #res: int = Field(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
+    down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
+    # fmt: on
+
+    # tile_resample copied from sd-webui-controlnet/scripts/processor.py
+    def tile_resample(self,
+                      np_img: np.ndarray,
+                      res=512,   # never used?
+                      down_sampling_rate=1.0,
+                      ):
+        np_img = HWC3(np_img)
+        if down_sampling_rate < 1.1:
+            return np_img
+        H, W, C = np_img.shape
+        H = int(float(H) / float(down_sampling_rate))
+        W = int(float(W) / float(down_sampling_rate))
+        np_img = cv2.resize(np_img, (W, H), interpolation=cv2.INTER_AREA)
+        return np_img
+
+    def run_processor(self, img):
+        np_img = np.array(img, dtype=np.uint8)
+        processed_np_image = self.tile_resample(np_img,
+                                                #res=self.tile_size,
+                                                down_sampling_rate=self.down_sampling_rate
+                                                )
+        processed_image = Image.fromarray(processed_np_image)
+        return processed_image
+
+
+
+
+class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies segment anything processing to image"""
+    # fmt: off
+    type: Literal["segment_anything_processor"] = "segment_anything_processor"
+    # fmt: on
+
+    def run_processor(self, image):
+        # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        segment_anything_processor = SamDetectorReproducibleColors.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        np_img = np.array(image, dtype=np.uint8)
+        processed_image = segment_anything_processor(np_img)
+        return processed_image
+
+class SamDetectorReproducibleColors(SamDetector):
+
+    # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
+    #     base class show_anns() method randomizes colors,
+    #     which seems to also lead to non-reproducible image generation
+    # so using ADE20k color palette instead
+    def show_anns(self, anns: List[Dict]):
+        if len(anns) == 0:
+            return
+        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
+        h, w = anns[0]['segmentation'].shape
+        final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
+        palette = ade_palette()
+        for i, ann in enumerate(sorted_anns):
+            m = ann['segmentation']
+            img = np.empty((m.shape[0], m.shape[1], 3), dtype=np.uint8)
+            # doing modulo just in case number of annotated regions exceeds number of colors in palette
+            ann_color = palette[i % len(palette)]
+            img[:, :] = ann_color
+            final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
+        return np.array(final_img, dtype=np.uint8)

invokeai/app/invocations/cv.py

@@ -36,12 +36,8 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
-        mask = context.services.images.get_pil_image(
-            self.mask.image_origin, self.mask.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
+        mask = context.services.images.get_pil_image(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -65,10 +61,7 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/generate.py

@@ -1,25 +1,27 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from functools import partial
-from typing import Literal, Optional, Union, get_args
+from typing import Literal, Optional, get_args
 
-import numpy as np
-from diffusers import ControlNetModel
-from torch import Tensor
 import torch
+from pydantic import Field
 
-from pydantic import BaseModel, Field
-
-from invokeai.app.models.image import ColorField, ImageField, ResourceOrigin
-from invokeai.app.invocations.util.choose_model import choose_model
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
+from invokeai.app.models.image import (ColorField, ImageCategory, ImageField,
+                                       ResourceOrigin)
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 from invokeai.backend.generator.inpaint import infill_methods
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput
-from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+
+from ...backend.generator import Inpaint, InvokeAIGenerator
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ..util.step_callback import stable_diffusion_step_callback
+from .baseinvocation import BaseInvocation, InvocationConfig, InvocationContext
+from .image import ImageOutput
+
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
+from .model import UNetField, VaeField
+from .compel import ConditioningField
+from contextlib import contextmanager, ExitStack, ContextDecorator
 
 SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
 INFILL_METHODS = Literal[tuple(infill_methods())]
@@ -28,122 +30,51 @@ DEFAULT_INFILL_METHOD = (
 )
 
 
-class SDImageInvocation(BaseModel):
-    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
+from .latent import get_scheduler
 
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["stable-diffusion", "image"],
-                "type_hints": {
-                    "model": "model",
-                },
-            },
-        }
+class OldModelContext(ContextDecorator):
+    model: StableDiffusionGeneratorPipeline
+
+    def __init__(self, model):
+        self.model = model
+
+    def __enter__(self):
+        return self.model
+
+    def __exit__(self, *exc):
+        return False
+
+class OldModelInfo:
+    name: str
+    hash: str
+    context: OldModelContext
+
+    def __init__(self, name: str, hash: str, model: StableDiffusionGeneratorPipeline):
+        self.name = name
+        self.hash = hash
+        self.context = OldModelContext(
+            model=model,
+        )
 
 
-# Text to image
-class TextToImageInvocation(BaseInvocation, SDImageInvocation):
-    """Generates an image using text2img."""
+class InpaintInvocation(BaseInvocation):
+    """Generates an image using inpaint."""
 
-    type: Literal["txt2img"] = "txt2img"
+    type: Literal["inpaint"] = "inpaint"
 
-    # Inputs
-    # TODO: consider making prompt optional to enable providing prompt through a link
-    # fmt: off
-    prompt: Optional[str] = Field(description="The prompt to generate an image from")
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
     seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
     steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
     width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
     height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
     cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
     scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
-    control_model: Optional[str] = Field(default=None, description="The control model to use")
-    control_image: Optional[ImageField] = Field(default=None, description="The processed control image")
-    # fmt: on
-
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self,
-        context: InvocationContext,
-        source_node_id: str,
-        intermediate_state: PipelineIntermediateState,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.dict(),
-            source_node_id=source_node_id,
-        )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-
-        # loading controlnet image (currently requires pre-processed image)
-        control_image = (
-            None if self.control_image is None
-            else context.services.images.get_pil_image(
-                self.control_image.image_origin, self.control_image.image_name
-            )
-        )
-        # loading controlnet model
-        if (self.control_model is None or self.control_model==''):
-            control_model = None
-        else:
-            # FIXME: change this to dropdown menu?
-            # FIXME: generalize so don't have to hardcode torch_dtype and device
-            control_model = ControlNetModel.from_pretrained(self.control_model,
-                                                            torch_dtype=torch.float16).to("cuda")
-
-        # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(
-            context.graph_execution_state_id
-        )
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
-
-        txt2img = Txt2Img(model, control_model=control_model)
-        outputs = txt2img.generate(
-            prompt=self.prompt,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            control_image=control_image,
-            **self.dict(
-                exclude={"prompt", "control_image" }
-            ),  # Shorthand for passing all of the parameters above manually
-        )
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generate_output = next(outputs)
-
-        image_dto = context.services.images.create(
-            image=generate_output.image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class ImageToImageInvocation(TextToImageInvocation):
-    """Generates an image using img2img."""
-
-    type: Literal["img2img"] = "img2img"
+    unet: UNetField = Field(default=None, description="UNet model")
+    vae: VaeField = Field(default=None, description="Vae model")
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image")
+    image: Optional[ImageField] = Field(description="The input image")
     strength: float = Field(
         default=0.75, gt=0, le=1, description="The strength of the original image"
     )
@@ -152,79 +83,8 @@ class ImageToImageInvocation(TextToImageInvocation):
         description="Whether or not the result should be fit to the aspect ratio of the input image",
     )
 
-    def dispatch_progress(
-        self,
-        context: InvocationContext,
-        source_node_id: str,
-        intermediate_state: PipelineIntermediateState,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.dict(),
-            source_node_id=source_node_id,
-        )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = (
-            None
-            if self.image is None
-            else context.services.images.get_pil_image(
-                self.image.image_origin, self.image.image_name
-            )
-        )
-
-        if self.fit:
-            image = image.resize((self.width, self.height))
-
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-
-        # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(
-            context.graph_execution_state_id
-        )
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
-
-        outputs = Img2Img(model).generate(
-            prompt=self.prompt,
-            init_image=image,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            **self.dict(
-                exclude={"prompt", "image", "mask"}
-            ),  # Shorthand for passing all of the parameters above manually
-        )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
-
-        image_dto = context.services.images.create(
-            image=generator_output.image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-class InpaintInvocation(ImageToImageInvocation):
-    """Generates an image using inpaint."""
-
-    type: Literal["inpaint"] = "inpaint"
-
     # Inputs
-    mask: Union[ImageField, None] = Field(description="The mask")
+    mask: Optional[ImageField] = Field(description="The mask")
     seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
     seam_blur: int = Field(
         default=16, ge=0, description="The seam inpaint blur radius (px)"
@@ -265,6 +125,14 @@ class InpaintInvocation(ImageToImageInvocation):
         description="The amount by which to replace masked areas with latent noise",
     )
 
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+            },
+        }
+
     def dispatch_progress(
         self,
         context: InvocationContext,
@@ -278,39 +146,86 @@ class InpaintInvocation(ImageToImageInvocation):
             source_node_id=source_node_id,
         )
 
+    def get_conditioning(self, context):
+        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+
+        return (uc, c, extra_conditioning_info)
+
+    @contextmanager
+    def load_model_old_way(self, context, scheduler):
+        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
+        vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
+
+        #unet = unet_info.context.model
+        #vae = vae_info.context.model
+
+        with ExitStack() as stack:
+            loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
+
+            with vae_info as vae,\
+                 unet_info as unet,\
+                 ModelPatcher.apply_lora_unet(unet, loras):
+
+                device = context.services.model_manager.mgr.cache.execution_device
+                dtype = context.services.model_manager.mgr.cache.precision
+
+                pipeline = StableDiffusionGeneratorPipeline(
+                    vae=vae,
+                    text_encoder=None,
+                    tokenizer=None,
+                    unet=unet,
+                    scheduler=scheduler,
+                    safety_checker=None,
+                    feature_extractor=None,
+                    requires_safety_checker=False,
+                    precision="float16" if dtype == torch.float16 else "float32",
+                    execution_device=device,
+                )
+
+                yield OldModelInfo(
+                    name=self.unet.unet.model_name,
+                    hash="<NO-HASH>",
+                    model=pipeline,
+                )
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
             if self.image is None
-            else context.services.images.get_pil_image(
-                self.image.image_origin, self.image.image_name
-            )
+            else context.services.images.get_pil_image(self.image.image_name)
         )
         mask = (
             None
             if self.mask is None
-            else context.services.images.get_pil_image(self.mask.image_origin, self.mask.image_name)
+            else context.services.images.get_pil_image(self.mask.image_name)
         )
 
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-
         # Get the source node id (we are invoking the prepared node)
         graph_execution_state = context.services.graph_execution_manager.get(
             context.graph_execution_state_id
         )
         source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
-        outputs = Inpaint(model).generate(
-            prompt=self.prompt,
-            init_image=image,
-            mask_image=mask,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            **self.dict(
-                exclude={"prompt", "image", "mask"}
-            ),  # Shorthand for passing all of the parameters above manually
+        conditioning = self.get_conditioning(context)
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
         )
 
+        with self.load_model_old_way(context, scheduler) as model:
+            outputs = Inpaint(model).generate(
+                conditioning=conditioning,
+                scheduler=scheduler,
+                init_image=image,
+                mask_image=mask,
+                step_callback=partial(self.dispatch_progress, context, source_node_id),
+                **self.dict(
+                    exclude={"positive_conditioning", "negative_conditioning", "scheduler", "image", "mask"}
+                ),  # Shorthand for passing all of the parameters above manually
+            )
+
         # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
         # each time it is called. We only need the first one.
         generator_output = next(outputs)
@@ -325,10 +240,7 @@ class InpaintInvocation(ImageToImageInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/image.py

@@ -1,7 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import io
-from typing import Literal, Optional, Union
+from typing import Literal, Optional
 
 import numpy
 from PIL import Image, ImageFilter, ImageOps, ImageChops
@@ -67,18 +66,15 @@ class LoadImageInvocation(BaseInvocation):
     type: Literal["load_image"] = "load_image"
 
     # Inputs
-    image: Union[ImageField, None] = Field(
+    image: Optional[ImageField] = Field(
         default=None, description="The image to load"
     )
     # fmt: on
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         return ImageOutput(
-            image=ImageField(
-                image_name=self.image.image_name,
-                image_origin=self.image.image_origin,
-            ),
+            image=ImageField(image_name=self.image.image_name),
             width=image.width,
             height=image.height,
         )
@@ -90,24 +86,19 @@ class ShowImageInvocation(BaseInvocation):
     type: Literal["show_image"] = "show_image"
 
     # Inputs
-    image: Union[ImageField, None] = Field(
+    image: Optional[ImageField] = Field(
         default=None, description="The image to show"
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         if image:
             image.show()
 
         # TODO: how to handle failure?
 
         return ImageOutput(
-            image=ImageField(
-                image_name=self.image.image_name,
-                image_origin=self.image.image_origin,
-            ),
+            image=ImageField(image_name=self.image.image_name),
             width=image.width,
             height=image.height,
         )
@@ -120,7 +111,7 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_crop"] = "img_crop"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to crop")
+    image: Optional[ImageField]  = Field(default=None, description="The image to crop")
     x:      int = Field(default=0, description="The left x coordinate of the crop rectangle")
     y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
     width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
@@ -128,9 +119,7 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_crop = Image.new(
             mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
@@ -147,10 +136,7 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -163,27 +149,21 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_paste"] = "img_paste"
 
     # Inputs
-    base_image:     Union[ImageField, None]  = Field(default=None, description="The base image")
-    image:          Union[ImageField, None]  = Field(default=None, description="The image to paste")
+    base_image:     Optional[ImageField]  = Field(default=None, description="The base image")
+    image:          Optional[ImageField]  = Field(default=None, description="The image to paste")
     mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
     x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
     y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        base_image = context.services.images.get_pil_image(
-            self.base_image.image_origin, self.base_image.image_name
-        )
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        base_image = context.services.images.get_pil_image(self.base_image.image_name)
+        image = context.services.images.get_pil_image(self.image.image_name)
         mask = (
             None
             if self.mask is None
             else ImageOps.invert(
-                context.services.images.get_pil_image(
-                    self.mask.image_origin, self.mask.image_name
-                )
+                context.services.images.get_pil_image(self.mask.image_name)
             )
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
@@ -209,10 +189,7 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -225,14 +202,12 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["tomask"] = "tomask"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to create the mask from")
+    image: Optional[ImageField]  = Field(default=None, description="The image to create the mask from")
     invert:      bool = Field(default=False, description="Whether or not to invert the mask")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_mask = image.split()[-1]
         if self.invert:
@@ -248,9 +223,7 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return MaskOutput(
-            mask=ImageField(
-                image_origin=image_dto.image_origin, image_name=image_dto.image_name
-            ),
+            mask=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -263,17 +236,13 @@ class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_mul"] = "img_mul"
 
     # Inputs
-    image1: Union[ImageField, None]  = Field(default=None, description="The first image to multiply")
-    image2: Union[ImageField, None]  = Field(default=None, description="The second image to multiply")
+    image1: Optional[ImageField]  = Field(default=None, description="The first image to multiply")
+    image2: Optional[ImageField]  = Field(default=None, description="The second image to multiply")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image1 = context.services.images.get_pil_image(
-            self.image1.image_origin, self.image1.image_name
-        )
-        image2 = context.services.images.get_pil_image(
-            self.image2.image_origin, self.image2.image_name
-        )
+        image1 = context.services.images.get_pil_image(self.image1.image_name)
+        image2 = context.services.images.get_pil_image(self.image2.image_name)
 
         multiply_image = ImageChops.multiply(image1, image2)
 
@@ -287,9 +256,7 @@ class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_origin=image_dto.image_origin, image_name=image_dto.image_name
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -305,14 +272,12 @@ class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_chan"] = "img_chan"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to get the channel from")
+    image: Optional[ImageField]  = Field(default=None, description="The image to get the channel from")
     channel: IMAGE_CHANNELS  = Field(default="A", description="The channel to get")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         channel_image = image.getchannel(self.channel)
 
@@ -326,9 +291,7 @@ class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_origin=image_dto.image_origin, image_name=image_dto.image_name
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -344,14 +307,12 @@ class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_conv"] = "img_conv"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to convert")
+    image: Optional[ImageField]  = Field(default=None, description="The image to convert")
     mode: IMAGE_MODES  = Field(default="L", description="The mode to convert to")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         converted_image = image.convert(self.mode)
 
@@ -365,9 +326,7 @@ class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_origin=image_dto.image_origin, image_name=image_dto.image_name
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -380,15 +339,13 @@ class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_blur"] = "img_blur"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to blur")
+    image: Optional[ImageField]  = Field(default=None, description="The image to blur")
     radius:     float = Field(default=8.0, ge=0, description="The blur radius")
     blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         blur = (
             ImageFilter.GaussianBlur(self.radius)
@@ -407,10 +364,7 @@ class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -443,16 +397,14 @@ class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_resize"] = "img_resize"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to resize")
+    image: Optional[ImageField]  = Field(default=None, description="The image to resize")
     width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
     height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
     resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -471,10 +423,7 @@ class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -487,15 +436,13 @@ class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_scale"] = "img_scale"
 
     # Inputs
-    image:       Union[ImageField, None] = Field(default=None, description="The image to scale")
+    image:       Optional[ImageField] = Field(default=None, description="The image to scale")
     scale_factor:                  float = Field(gt=0, description="The factor by which to scale the image")
     resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
         width = int(image.width * self.scale_factor)
@@ -516,10 +463,7 @@ class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -532,15 +476,13 @@ class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_lerp"] = "img_lerp"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    image: Optional[ImageField]  = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32) / 255
         image_arr = image_arr * (self.max - self.min) + self.max
@@ -557,10 +499,7 @@ class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -573,15 +512,13 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["img_ilerp"] = "img_ilerp"
 
     # Inputs
-    image: Union[ImageField, None]  = Field(default=None, description="The image to lerp")
+    image: Optional[ImageField]  = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32)
         image_arr = (
@@ -603,10 +540,7 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/infill.py

@@ -1,6 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 
-from typing import Literal, Union, get_args
+from typing import Literal, Optional, get_args
 
 import numpy as np
 import math
@@ -68,7 +68,7 @@ def get_tile_images(image: np.ndarray, width=8, height=8):
 
 
 def tile_fill_missing(
-    im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
+    im: Image.Image, tile_size: int = 16, seed: Optional[int] = None
 ) -> Image.Image:
     # Only fill if there's an alpha layer
     if im.mode != "RGBA":
@@ -125,7 +125,7 @@ class InfillColorInvocation(BaseInvocation):
     """Infills transparent areas of an image with a solid color"""
 
     type: Literal["infill_rgba"] = "infill_rgba"
-    image: Union[ImageField, None] = Field(
+    image: Optional[ImageField] = Field(
         default=None, description="The image to infill"
     )
     color: ColorField = Field(
@@ -134,9 +134,7 @@ class InfillColorInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
@@ -153,10 +151,7 @@ class InfillColorInvocation(BaseInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -167,7 +162,7 @@ class InfillTileInvocation(BaseInvocation):
 
     type: Literal["infill_tile"] = "infill_tile"
 
-    image: Union[ImageField, None] = Field(
+    image: Optional[ImageField] = Field(
         default=None, description="The image to infill"
     )
     tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
@@ -179,9 +174,7 @@ class InfillTileInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         infilled = tile_fill_missing(
             image.copy(), seed=self.seed, tile_size=self.tile_size
@@ -198,10 +191,7 @@ class InfillTileInvocation(BaseInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
@@ -212,14 +202,12 @@ class InfillPatchMatchInvocation(BaseInvocation):
 
     type: Literal["infill_patchmatch"] = "infill_patchmatch"
 
-    image: Union[ImageField, None] = Field(
+    image: Optional[ImageField] = Field(
         default=None, description="The image to infill"
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         if PatchMatch.patchmatch_available():
             infilled = infill_patchmatch(image.copy())
@@ -236,10 +224,7 @@ class InfillPatchMatchInvocation(BaseInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/latent.py

@@ -1,52 +1,44 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-import random
+from typing import List, Literal, Optional, Union
+
 import einops
-from typing import Literal, Optional, Union, List
-
-from compel import Compel
-from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import MultiControlNetModel
-
-from pydantic import BaseModel, Field, validator
 import torch
-
-from invokeai.app.invocations.util.choose_model import choose_model
-from invokeai.app.models.image import ImageCategory
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from diffusers import ControlNetModel
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.schedulers import SchedulerMixin as Scheduler
+from pydantic import BaseModel, Field, validator
 
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from .controlnet_image_processors import ControlField
 
-from ...backend.model_management.model_manager import ModelManager
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
-from ...backend.image_util.seamless import configure_model_padding
-from ...backend.prompting.conditioning import get_uc_and_c_and_ec
-
-from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline, image_resized_to_grid_as_tensor
-from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
-from ...backend.stable_diffusion.diffusers_pipeline import ControlNetData
-
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-import numpy as np
-from ..services.image_file_storage import ResourceOrigin
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
-from .compel import ConditioningField
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from ...backend.model_management.lora import ModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
-from diffusers.schedulers import SchedulerMixin as Scheduler
-import diffusers
-from diffusers import DiffusionPipeline, ControlNetModel
+from ...backend.stable_diffusion.diffusers_pipeline import (
+    ConditioningData, ControlNetData, StableDiffusionGeneratorPipeline,
+    image_resized_to_grid_as_tensor)
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import \
+    PostprocessingSettings
+from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
+from ...backend.util.devices import torch_dtype
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+from .compel import ConditioningField
+from .controlnet_image_processors import ControlField
+from .image import ImageOutput
+from .model import ModelInfo, UNetField, VaeField
 
 
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
 
-    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
+    latents_name: Optional[str] = Field(
+        default=None, description="The name of the latents")
 
     class Config:
         schema_extra = {"required": ["latents_name"]}
 
+
 class LatentsOutput(BaseInvocationOutput):
     """Base class for invocations that output latents"""
     #fmt: off
@@ -60,29 +52,11 @@ class LatentsOutput(BaseInvocationOutput):
 
 
 def build_latents_output(latents_name: str, latents: torch.Tensor):
-      return LatentsOutput(
-          latents=LatentsField(latents_name=latents_name),
-          width=latents.size()[3] * 8,
-          height=latents.size()[2] * 8,
-      )
-
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-    #fmt: off
-    type:  Literal["noise_output"] = "noise_output"
-
-    # Inputs
-    noise: LatentsField            = Field(default=None, description="The output noise")
-    width:                     int = Field(description="The width of the noise in pixels")
-    height:                    int = Field(description="The height of the noise in pixels")
-    #fmt: on
-
-def build_noise_output(latents_name: str, latents: torch.Tensor):
-      return NoiseOutput(
-          noise=LatentsField(latents_name=latents_name),
-          width=latents.size()[3] * 8,
-          height=latents.size()[2] * 8,
-      )
+    return LatentsOutput(
+        latents=LatentsField(latents_name=latents_name),
+        width=latents.size()[3] * 8,
+        height=latents.size()[2] * 8,
+    )
 
 
 SAMPLER_NAME_VALUES = Literal[
@@ -90,13 +64,22 @@ SAMPLER_NAME_VALUES = Literal[
 ]
 
 
-def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
+def get_scheduler(
+    context: InvocationContext,
+    scheduler_info: ModelInfo,
+    scheduler_name: str,
+) -> Scheduler:
+    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(
+        scheduler_name, SCHEDULER_MAP['ddim'])
+    orig_scheduler_info = context.services.model_manager.get_model(
+        **scheduler_info.dict())
+    with orig_scheduler_info as orig_scheduler:
+        scheduler_config = orig_scheduler.config
 
-    scheduler_config = model.scheduler.config
     if "_backup" in scheduler_config:
         scheduler_config = scheduler_config["_backup"]
-    scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
+    scheduler_config = {**scheduler_config, **
+                        scheduler_extra_config, "_backup": scheduler_config}
     scheduler = scheduler_class.from_config(scheduler_config)
 
     # hack copied over from generate.py
@@ -105,63 +88,6 @@ def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->
     return scheduler
 
 
-def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
-    generator = torch.Generator(device=use_device).manual_seed(seed)
-    x = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width //  downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=use_device,
-        generator=generator,
-    ).to(device)
-    # if self.perlin > 0.0:
-    #     perlin_noise = self.get_perlin_noise(
-    #         width // self.downsampling_factor, height // self.downsampling_factor
-    #     )
-    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
-    return x
-
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed:       int = Field(ge=0, le=SEED_MAX, description="The seed to use", default_factory=get_random_seed)
-    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting noise", )
-    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting noise", )
-
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "noise"],
-            },
-        }
-
-    @validator("seed", pre=True)
-    def modulo_seed(cls, v):
-        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
-        return v % SEED_MAX
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        device = torch.device(choose_torch_device())
-        noise = get_noise(self.width, self.height, device, self.seed)
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise)
-
-
 # Text to image
 class TextToLatentsInvocation(BaseInvocation):
     """Generates latents from conditionings."""
@@ -176,10 +102,10 @@ class TextToLatentsInvocation(BaseInvocation):
     steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
     cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
     scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    control: Union[ControlField, List[ControlField]] = Field(default=None, description="The control to use")
-    # seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    # seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
+    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
     # fmt: on
 
     @validator("cfg_scale")
@@ -200,18 +126,18 @@ class TextToLatentsInvocation(BaseInvocation):
             "ui": {
                 "tags": ["latents"],
                 "type_hints": {
-                  "model": "model",
-                  "control": "control",
-                  # "cfg_scale": "float",
-                  "cfg_scale": "number"
+                    "model": "model",
+                    "control": "control",
+                    # "cfg_scale": "float",
+                    "cfg_scale": "number"
                 }
             },
         }
 
     # TODO: pass this an emitter method or something? or a session for dispatching?
     def dispatch_progress(
-        self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
-    ) -> None:
+            self, context: InvocationContext, source_node_id: str,
+            intermediate_state: PipelineIntermediateState) -> None:
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
@@ -219,43 +145,12 @@ class TextToLatentsInvocation(BaseInvocation):
             source_node_id=source_node_id,
         )
 
-    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
-        model_info = choose_model(model_manager, self.model)
-        model_name = model_info['model_name']
-        model_hash = model_info['hash']
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-        model.scheduler = get_scheduler(
-            model=model,
-            scheduler_name=self.scheduler
-        )
-
-        # if isinstance(model, DiffusionPipeline):
-        #     for component in [model.unet, model.vae]:
-        #         configure_model_padding(component,
-        #                                 self.seamless,
-        #                                 self.seamless_axes
-        #                                 )
-        # else:
-        #     configure_model_padding(model,
-        #                             self.seamless,
-        #                             self.seamless_axes
-        #                             )
-
-        return model
-
-
-    def get_conditioning_data(self, context: InvocationContext, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
-        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-
-        compel = Compel(
-            tokenizer=model.tokenizer,
-            text_encoder=model.text_encoder,
-            textual_inversion_manager=model.textual_inversion_manager,
-            dtype_for_device_getter=torch_dtype,
-            truncate_long_prompts=False,
-        )
-        [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
+    def get_conditioning_data(
+            self, context: InvocationContext, scheduler) -> ConditioningData:
+        c, extra_conditioning_info = context.services.latents.get(
+            self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(
+            self.negative_conditioning.conditioning_name)
 
         conditioning_data = ConditioningData(
             unconditioned_embeddings=uc,
@@ -263,38 +158,75 @@ class TextToLatentsInvocation(BaseInvocation):
             guidance_scale=self.cfg_scale,
             extra=extra_conditioning_info,
             postprocessing_settings=PostprocessingSettings(
-                threshold=0.0,#threshold,
-                warmup=0.2,#warmup,
-                h_symmetry_time_pct=None,#h_symmetry_time_pct,
-                v_symmetry_time_pct=None#v_symmetry_time_pct,
+                threshold=0.0,  # threshold,
+                warmup=0.2,  # warmup,
+                h_symmetry_time_pct=None,  # h_symmetry_time_pct,
+                v_symmetry_time_pct=None  # v_symmetry_time_pct,
             ),
-        ).add_scheduler_args_if_applicable(model.scheduler, eta=0.0)#ddim_eta)
+        )
+
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
+            scheduler,
+
+            # for ddim scheduler
+            eta=0.0,  # ddim_eta
+
+            # for ancestral and sde schedulers
+            generator=torch.Generator(device=uc.device).manual_seed(0),
+        )
         return conditioning_data
 
-    def prep_control_data(self,
-                          context: InvocationContext,
-                          model: StableDiffusionGeneratorPipeline, # really only need model for dtype and device
-                          control_input: List[ControlField],
-                          latents_shape: List[int],
-                          do_classifier_free_guidance: bool = True,
-                          ) -> List[ControlNetData]:
+    def create_pipeline(
+            self, unet, scheduler) -> StableDiffusionGeneratorPipeline:
+        # TODO:
+        # configure_model_padding(
+        #    unet,
+        #    self.seamless,
+        #    self.seamless_axes,
+        # )
+
+        class FakeVae:
+            class FakeVaeConfig:
+                def __init__(self):
+                    self.block_out_channels = [0]
+
+            def __init__(self):
+                self.config = FakeVae.FakeVaeConfig()
+
+        return StableDiffusionGeneratorPipeline(
+            vae=FakeVae(),  # TODO: oh...
+            text_encoder=None,
+            tokenizer=None,
+            unet=unet,
+            scheduler=scheduler,
+            safety_checker=None,
+            feature_extractor=None,
+            requires_safety_checker=False,
+            precision="float16" if unet.dtype == torch.float16 else "float32",
+        )
+
+    def prep_control_data(
+        self,
+        context: InvocationContext,
+        # really only need model for dtype and device
+        model: StableDiffusionGeneratorPipeline,
+        control_input: List[ControlField],
+        latents_shape: List[int],
+        do_classifier_free_guidance: bool = True,
+    ) -> List[ControlNetData]:
+
         # assuming fixed dimensional scaling of 8:1 for image:latents
         control_height_resize = latents_shape[2] * 8
         control_width_resize = latents_shape[3] * 8
         if control_input is None:
-            # print("control input is None")
             control_list = None
         elif isinstance(control_input, list) and len(control_input) == 0:
-            # print("control input is empty list")
             control_list = None
         elif isinstance(control_input, ControlField):
-            # print("control input is ControlField")
             control_list = [control_input]
         elif isinstance(control_input, list) and len(control_input) > 0 and isinstance(control_input[0], ControlField):
-            # print("control input is list[ControlField]")
             control_list = control_input
         else:
-            # print("input control is unrecognized:", type(self.control))
             control_list = None
         if (control_list is None):
             control_data = None
@@ -313,16 +245,17 @@ class TextToLatentsInvocation(BaseInvocation):
                     print("Using HF model subfolders")
                     print("    control_name: ", control_name)
                     print("    control_subfolder: ", control_subfolder)
-                    control_model = ControlNetModel.from_pretrained(control_name,
-                                                                    subfolder=control_subfolder,
-                                                                    torch_dtype=model.unet.dtype).to(model.device)
+                    control_model = ControlNetModel.from_pretrained(
+                        control_name, subfolder=control_subfolder,
+                        torch_dtype=model.unet.dtype).to(
+                        model.device)
                 else:
-                    control_model = ControlNetModel.from_pretrained(control_info.control_model,
-                                                                    torch_dtype=model.unet.dtype).to(model.device)
+                    control_model = ControlNetModel.from_pretrained(
+                        control_info.control_model, torch_dtype=model.unet.dtype).to(model.device)
                 control_models.append(control_model)
                 control_image_field = control_info.image
-                input_image = context.services.images.get_pil_image(control_image_field.image_origin,
-                                                                    control_image_field.image_name)
+                input_image = context.services.images.get_pil_image(
+                    control_image_field.image_name)
                 # self.image.image_type, self.image.image_name
                 # FIXME: still need to test with different widths, heights, devices, dtypes
                 #        and add in batch_size, num_images_per_prompt?
@@ -337,43 +270,68 @@ class TextToLatentsInvocation(BaseInvocation):
                     # num_images_per_prompt=num_images_per_prompt,
                     device=control_model.device,
                     dtype=control_model.dtype,
+                    control_mode=control_info.control_mode,
                 )
-                control_item = ControlNetData(model=control_model,
-                                              image_tensor=control_image,
-                                              weight=control_info.control_weight,
-                                              begin_step_percent=control_info.begin_step_percent,
-                                              end_step_percent=control_info.end_step_percent)
+                control_item = ControlNetData(
+                    model=control_model, image_tensor=control_image,
+                    weight=control_info.control_weight,
+                    begin_step_percent=control_info.begin_step_percent,
+                    end_step_percent=control_info.end_step_percent,
+                    control_mode=control_info.control_mode,)
                 control_data.append(control_item)
                 # MultiControlNetModel has been refactored out, just need list[ControlNetData]
         return control_data
 
+    @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
 
         # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id)
         source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
         def step_callback(state: PipelineIntermediateState):
             self.dispatch_progress(context, source_node_id, state)
 
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(context, model)
+        def _lora_loader():
+            for lora in self.unet.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
 
-        control_data = self.prep_control_data(model=model, context=context, control_input=self.control,
-                                              latents_shape=noise.shape,
-                                              # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                                              do_classifier_free_guidance=True,)
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict())
+        with ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
+                unet_info as unet:
 
-        # TODO: Verify the noise is the right size
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            control_data=control_data,  # list[ControlNetData]
-            callback=step_callback,
-        )
+            scheduler = get_scheduler(
+                context=context,
+                scheduler_info=self.unet.scheduler,
+                scheduler_name=self.scheduler,
+            )
+
+            pipeline = self.create_pipeline(unet, scheduler)
+            conditioning_data = self.get_conditioning_data(context, scheduler)
+
+            control_data = self.prep_control_data(
+                model=pipeline, context=context, control_input=self.control,
+                latents_shape=noise.shape,
+                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                do_classifier_free_guidance=True,
+            )
+
+            # TODO: Verify the noise is the right size
+            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
+                noise=noise,
+                num_inference_steps=self.steps,
+                conditioning_data=conditioning_data,
+                control_data=control_data,  # list[ControlNetData]
+                callback=step_callback,
+            )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
@@ -389,8 +347,11 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
     type: Literal["l2l"] = "l2l"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
-    strength: float = Field(default=0.7, ge=0, le=1, description="The strength of the latents to use")
+    latents: Optional[LatentsField] = Field(
+        description="The latents to use as a base image")
+    strength: float = Field(
+        default=0.7, ge=0, le=1,
+        description="The strength of the latents to use")
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -405,43 +366,67 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             },
         }
 
+    @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
         latent = context.services.latents.get(self.latents.latents_name)
 
         # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id)
         source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
         def step_callback(state: PipelineIntermediateState):
             self.dispatch_progress(context, source_node_id, state)
 
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(context, model)
+        def _lora_loader():
+            for lora in self.unet.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
 
-        control_data = self.prep_control_data(model=model, context=context, control_input=self.control,
-                                              latents_shape=noise.shape,
-                                              # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                                              do_classifier_free_guidance=True,
-                                              )
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict())
+        with ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
+                unet_info as unet:
 
-        # TODO: Verify the noise is the right size
+            scheduler = get_scheduler(
+                context=context,
+                scheduler_info=self.unet.scheduler,
+                scheduler_name=self.scheduler,
+            )
 
-        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-            latent, device=model.device, dtype=latent.dtype
-        )
+            pipeline = self.create_pipeline(unet, scheduler)
+            conditioning_data = self.get_conditioning_data(context, scheduler)
 
-        timesteps, _ = model.get_img2img_timesteps(self.steps, self.strength)
+            control_data = self.prep_control_data(
+                model=pipeline, context=context, control_input=self.control,
+                latents_shape=noise.shape,
+                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                do_classifier_free_guidance=True,
+            )
 
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=initial_latents,
-            timesteps=timesteps,
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            control_data=control_data,  # list[ControlNetData]
-            callback=step_callback
-        )
+            # TODO: Verify the noise is the right size
+            initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+                latent, device=unet.device, dtype=latent.dtype)
+
+            timesteps, _ = pipeline.get_img2img_timesteps(
+                self.steps,
+                self.strength,
+                device=unet.device,
+            )
+
+            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                latents=initial_latents,
+                timesteps=timesteps,
+                noise=noise,
+                num_inference_steps=self.steps,
+                conditioning_data=conditioning_data,
+                control_data=control_data,  # list[ControlNetData]
+                callback=step_callback
+            )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
@@ -458,17 +443,18 @@ class LatentsToImageInvocation(BaseInvocation):
     type: Literal["l2i"] = "l2i"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
-    model: str = Field(default="", description="The model to use")
+    latents: Optional[LatentsField] = Field(
+        description="The latents to generate an image from")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    tiled: bool = Field(
+        default=False,
+        description="Decode latents by overlaping tiles(less memory consumption)")
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "tags": ["latents", "image"],
-                "type_hints": {
-                  "model": "model"
-                }
             },
         }
 
@@ -476,44 +462,49 @@ class LatentsToImageInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
-        # TODO: this only really needs the vae
-        model_info = choose_model(context.services.model_manager, self.model)
-        model: StableDiffusionGeneratorPipeline = model_info['model']
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+        )
 
-        with torch.inference_mode():
-            np_image = model.decode_latents(latents)
-            image = model.numpy_to_pil(np_image)[0]
-
-            # what happened to metadata?
-            # metadata = context.services.metadata.build_metadata(
-            #     session_id=context.graph_execution_state_id, node=self
+        with vae_info as vae:
+            if self.tiled or context.services.configuration.tiled_decode:
+                vae.enable_tiling()
+            else:
+                vae.disable_tiling()
 
+            # clear memory as vae decode can request a lot
             torch.cuda.empty_cache()
 
-            # new (post Image service refactor) way of using services to save image
-            #     and gnenerate unique image_name
-            image_dto = context.services.images.create(
-                image=image,
-                image_origin=ResourceOrigin.INTERNAL,
-                image_category=ImageCategory.GENERAL,
-                session_id=context.graph_execution_state_id,
-                node_id=self.id,
-                is_intermediate=self.is_intermediate
-            )
+            with torch.inference_mode():
+                # copied from diffusers pipeline
+                latents = latents / vae.config.scaling_factor
+                image = vae.decode(latents, return_dict=False)[0]
+                image = (image / 2 + 0.5).clamp(0, 1)  # denormalize
+                # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
+                np_image = image.cpu().permute(0, 2, 3, 1).float().numpy()
 
-            return ImageOutput(
-                image=ImageField(
-                    image_name=image_dto.image_name,
-                    image_origin=image_dto.image_origin,
-                ),
-                width=image_dto.width,
-                height=image_dto.height,
-            )
+                image = VaeImageProcessor.numpy_to_pil(np_image)[0]
+
+        torch.cuda.empty_cache()
+
+        image_dto = context.services.images.create(
+            image=image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
 
 
-LATENTS_INTERPOLATION_MODE = Literal[
-    "nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"
-]
+LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear",
+                                     "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
 
 
 class ResizeLatentsInvocation(BaseInvocation):
@@ -522,21 +513,25 @@ class ResizeLatentsInvocation(BaseInvocation):
     type: Literal["lresize"] = "lresize"
 
     # Inputs
-    latents:    Optional[LatentsField] = Field(description="The latents to resize")
-    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
-    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
-    mode:   LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
-    antialias:                    bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+    latents: Optional[LatentsField] = Field(
+        description="The latents to resize")
+    width:                         int = Field(
+        ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(
+        ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode:   LATENTS_INTERPOLATION_MODE = Field(
+        default="bilinear", description="The interpolation mode")
+    antialias: bool = Field(
+        default=False,
+        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
         resized_latents = torch.nn.functional.interpolate(
-            latents,
-            size=(self.height // 8, self.width // 8),
-            mode=self.mode,
-            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
-        )
+            latents, size=(self.height // 8, self.width // 8),
+            mode=self.mode, antialias=self.antialias
+            if self.mode in ["bilinear", "bicubic"] else False,)
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
@@ -553,21 +548,24 @@ class ScaleLatentsInvocation(BaseInvocation):
     type: Literal["lscale"] = "lscale"
 
     # Inputs
-    latents:   Optional[LatentsField] = Field(description="The latents to scale")
-    scale_factor:               float = Field(gt=0, description="The factor by which to scale the latents")
-    mode:  LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
-    antialias:                   bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+    latents: Optional[LatentsField] = Field(
+        description="The latents to scale")
+    scale_factor:               float = Field(
+        gt=0, description="The factor by which to scale the latents")
+    mode:  LATENTS_INTERPOLATION_MODE = Field(
+        default="bilinear", description="The interpolation mode")
+    antialias: bool = Field(
+        default=False,
+        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
         # resizing
         resized_latents = torch.nn.functional.interpolate(
-            latents,
-            scale_factor=self.scale_factor,
-            mode=self.mode,
-            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
-        )
+            latents, scale_factor=self.scale_factor, mode=self.mode,
+            antialias=self.antialias
+            if self.mode in ["bilinear", "bicubic"] else False,)
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
@@ -584,15 +582,17 @@ class ImageToLatentsInvocation(BaseInvocation):
     type: Literal["i2l"] = "i2l"
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The image to encode")
-    model: str = Field(default="", description="The model to use")
+    image: Optional[ImageField] = Field(description="The image to encode")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    tiled: bool = Field(
+        default=False,
+        description="Encode latents by overlaping tiles(less memory consumption)")
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "tags": ["latents", "image"],
-                "type_hints": {"model": "model"},
             },
         }
 
@@ -601,24 +601,32 @@ class ImageToLatentsInvocation(BaseInvocation):
         # image = context.services.images.get(
         #     self.image.image_type, self.image.image_name
         # )
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        #vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
         )
 
-        # TODO: this only really needs the vae
-        model_info = choose_model(context.services.model_manager, self.model)
-        model: StableDiffusionGeneratorPipeline = model_info["model"]
-
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
-
         if image_tensor.dim() == 3:
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
-        latents = model.non_noised_latents_from_image(
-            image_tensor,
-            device=model._model_group.device_for(model.unet),
-            dtype=model.unet.dtype,
-        )
+        with vae_info as vae:
+            if self.tiled:
+                vae.enable_tiling()
+            else:
+                vae.disable_tiling()
+
+            # non_noised_latents_from_image
+            image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
+            with torch.inference_mode():
+                image_tensor_dist = vae.encode(image_tensor).latent_dist
+                latents = image_tensor_dist.sample().to(
+                    dtype=vae.dtype
+                )  # FIXME: uses torch.randn. make reproducible!
+
+            latents = 0.18215 * latents
 
         name = f"{context.graph_execution_state_id}__{self.id}"
         # context.services.latents.set(name, latents)

invokeai/app/invocations/model.py

@@ -0,0 +1,310 @@
+import copy
+from typing import List, Literal, Optional, Union
+
+from pydantic import BaseModel, Field
+
+from ...backend.model_management import BaseModelType, ModelType, SubModelType
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+
+
+class ModelInfo(BaseModel):
+    model_name: str = Field(description="Info to load submodel")
+    base_model: BaseModelType = Field(description="Base model")
+    model_type: ModelType = Field(description="Info to load submodel")
+    submodel: Optional[SubModelType] = Field(
+        default=None, description="Info to load submodel"
+    )
+
+
+class LoraInfo(ModelInfo):
+    weight: float = Field(description="Lora's weight which to use when apply to model")
+
+
+class UNetField(BaseModel):
+    unet: ModelInfo = Field(description="Info to load unet submodel")
+    scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
+    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
+
+
+class ClipField(BaseModel):
+    tokenizer: ModelInfo = Field(description="Info to load tokenizer submodel")
+    text_encoder: ModelInfo = Field(description="Info to load text_encoder submodel")
+    skipped_layers: int = Field(description="Number of skipped layers in text_encoder")
+    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
+
+
+class VaeField(BaseModel):
+    # TODO: better naming?
+    vae: ModelInfo = Field(description="Info to load vae submodel")
+
+
+class ModelLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["model_loader_output"] = "model_loader_output"
+
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
+
+
+class MainModelField(BaseModel):
+    """Main model field"""
+
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class LoRAModelField(BaseModel):
+    """LoRA model field"""
+
+    model_name: str = Field(description="Name of the LoRA model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class MainModelLoaderInvocation(BaseInvocation):
+    """Loads a main model, outputting its submodels."""
+
+    type: Literal["main_model_loader"] = "main_model_loader"
+
+    model: MainModelField = Field(description="The model to load")
+    # TODO: precision?
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Model Loader",
+                "tags": ["model", "loader"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
+
+        # TODO: not found exceptions
+        if not context.services.model_manager.model_exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+
+        """
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.Tokenizer,
+        ):
+            raise Exception(
+                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
+            )
+
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.TextEncoder,
+        ):
+            raise Exception(
+                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
+            )
+
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.UNet,
+        ):
+            raise Exception(
+                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
+            )
+        """
+
+        return ModelLoaderOutput(
+            unet=UNetField(
+                unet=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
+                ),
+                scheduler=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
+                ),
+                loras=[],
+            ),
+            clip=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
+                ),
+            ),
+        )
+
+
+class LoraLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["lora_loader_output"] = "lora_loader_output"
+
+    unet: Optional[UNetField] = Field(default=None, description="UNet submodel")
+    clip: Optional[ClipField] = Field(default=None, description="Tokenizer and text_encoder submodels")
+    # fmt: on
+
+
+class LoraLoaderInvocation(BaseInvocation):
+    """Apply selected lora to unet and text_encoder."""
+
+    type: Literal["lora_loader"] = "lora_loader"
+
+    lora: Union[LoRAModelField, None] = Field(
+        default=None, description="Lora model name"
+    )
+    weight: float = Field(default=0.75, description="With what weight to apply lora")
+
+    unet: Optional[UNetField] = Field(description="UNet model for applying lora")
+    clip: Optional[ClipField] = Field(description="Clip model for applying lora")
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Lora Loader",
+                "tags": ["lora", "loader"],
+                "type_hints": {"lora": "lora_model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
+        if self.lora is None:
+            raise Exception("No LoRA provided")
+
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
+
+        if not context.services.model_manager.model_exists(
+            base_model=base_model,
+            model_name=lora_name,
+            model_type=ModelType.Lora,
+        ):
+            raise Exception(f"Unkown lora name: {lora_name}!")
+
+        if self.unet is not None and any(
+            lora.model_name == lora_name for lora in self.unet.loras
+        ):
+            raise Exception(f'Lora "{lora_name}" already applied to unet')
+
+        if self.clip is not None and any(
+            lora.model_name == lora_name for lora in self.clip.loras
+        ):
+            raise Exception(f'Lora "{lora_name}" already applied to clip')
+
+        output = LoraLoaderOutput()
+
+        if self.unet is not None:
+            output.unet = copy.deepcopy(self.unet)
+            output.unet.loras.append(
+                LoraInfo(
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
+                    weight=self.weight,
+                )
+            )
+
+        if self.clip is not None:
+            output.clip = copy.deepcopy(self.clip)
+            output.clip.loras.append(
+                LoraInfo(
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
+                    weight=self.weight,
+                )
+            )
+
+        return output
+
+
+class VAEModelField(BaseModel):
+    """Vae model field"""
+
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class VaeLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["vae_loader_output"] = "vae_loader_output"
+
+    vae: VaeField = Field(default=None, description="Vae model")
+    # fmt: on
+
+
+class VaeLoaderInvocation(BaseInvocation):
+    """Loads a VAE model, outputting a VaeLoaderOutput"""
+
+    type: Literal["vae_loader"] = "vae_loader"
+
+    vae_model: VAEModelField = Field(description="The VAE to load")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "VAE Loader",
+                "tags": ["vae", "loader"],
+                "type_hints": {"vae_model": "vae_model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> VaeLoaderOutput:
+        base_model = self.vae_model.base_model
+        model_name = self.vae_model.model_name
+        model_type = ModelType.Vae
+
+        if not context.services.model_manager.model_exists(
+            base_model=base_model,
+            model_name=model_name,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unkown vae name: {model_name}!")
+        return VaeLoaderOutput(
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                )
+            )
+        )

invokeai/app/invocations/noise.py

@@ -0,0 +1,134 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
+
+import math
+from typing import Literal
+
+from pydantic import Field, validator
+import torch
+from invokeai.app.invocations.latent import LatentsField
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationConfig,
+    InvocationContext,
+)
+
+"""
+Utilities
+"""
+
+
+def get_noise(
+    width: int,
+    height: int,
+    device: torch.device,
+    seed: int = 0,
+    latent_channels: int = 4,
+    downsampling_factor: int = 8,
+    use_cpu: bool = True,
+    perlin: float = 0.0,
+):
+    """Generate noise for a given image size."""
+    noise_device_type = "cpu" if use_cpu else device.type
+
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    generator = torch.Generator(device=noise_device_type).manual_seed(seed)
+
+    noise_tensor = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width // downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=noise_device_type,
+        generator=generator,
+    ).to(device)
+
+    return noise_tensor
+
+
+"""
+Nodes
+"""
+
+
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+
+    # fmt: off
+    type:  Literal["noise_output"] = "noise_output"
+
+    # Inputs
+    noise: LatentsField            = Field(default=None, description="The output noise")
+    width:                     int = Field(description="The width of the noise in pixels")
+    height:                    int = Field(description="The height of the noise in pixels")
+    # fmt: on
+
+
+def build_noise_output(latents_name: str, latents: torch.Tensor):
+    return NoiseOutput(
+        noise=LatentsField(latents_name=latents_name),
+        width=latents.size()[3] * 8,
+        height=latents.size()[2] * 8,
+    )
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use",
+        default_factory=get_random_seed,
+    )
+    width: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The width of the resulting noise",
+    )
+    height: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The height of the resulting noise",
+    )
+    use_cpu: bool = Field(
+        default=True,
+        description="Use CPU for noise generation (for reproducible results across platforms)",
+    )
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    @validator("seed", pre=True)
+    def modulo_seed(cls, v):
+        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
+        return v % SEED_MAX
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        noise = get_noise(
+            width=self.width,
+            height=self.height,
+            device=choose_torch_device(),
+            seed=self.seed,
+            use_cpu=self.use_cpu,
+        )
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.save(name, noise)
+        return build_noise_output(latents_name=name, latents=noise)

invokeai/app/invocations/param_easing.py

@@ -133,20 +133,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            logger = InvokeAILogger.getLogger(name="StepParamEasing")
-            logger.debug("start_step: " + str(start_step))
-            logger.debug("end_step: " + str(end_step))
-            logger.debug("num_easing_steps: " + str(num_easing_steps))
-            logger.debug("num_presteps: " + str(num_presteps))
-            logger.debug("num_poststeps: " + str(num_poststeps))
-            logger.debug("prelist size: " + str(len(prelist)))
-            logger.debug("postlist size: " + str(len(postlist)))
-            logger.debug("prelist: " + str(prelist))
-            logger.debug("postlist: " + str(postlist))
+            context.services.logger.debug("start_step: " + str(start_step))
+            context.services.logger.debug("end_step: " + str(end_step))
+            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.services.logger.debug("num_presteps: " + str(num_presteps))
+            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.services.logger.debug("prelist size: " + str(len(prelist)))
+            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.services.logger.debug("prelist: " + str(prelist))
+            context.services.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            logger.debug("easing class: " + str(easing_class))
+            context.services.logger.debug("easing class: " + str(easing_class))
         easing_list = list()
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -156,7 +155,7 @@ class StepParamEasingInvocation(BaseInvocation):
             # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
 
             base_easing_duration = int(np.ceil(num_easing_steps/2.0))
-            if log_diagnostics: logger.debug("base easing duration: " + str(base_easing_duration))
+            if log_diagnostics: context.services.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
             easing_function = easing_class(start=self.start_value,
                                            end=self.end_value,
@@ -166,14 +165,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
             if even_num_steps:
                 mirror_easing_vals = list(reversed(base_easing_vals))
             else:
                 mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
             if log_diagnostics:
-                logger.debug("base easing vals: " + str(base_easing_vals))
-                logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
             easing_list = base_easing_vals + mirror_easing_vals
 
         # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
@@ -206,12 +205,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            logger.debug("prelist size: " + str(len(prelist)))
-            logger.debug("easing_list size: " + str(len(easing_list)))
-            logger.debug("postlist size: " + str(len(postlist)))
+            context.services.logger.debug("prelist size: " + str(len(prelist)))
+            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.services.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/invocations/prompt.py

@@ -2,8 +2,8 @@ from typing import Literal
 
 from pydantic.fields import Field
 
-from .baseinvocation import BaseInvocationOutput
-
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator
 
 class PromptOutput(BaseInvocationOutput):
     """Base class for invocations that output a prompt"""
@@ -20,3 +20,38 @@ class PromptOutput(BaseInvocationOutput):
                 'prompt',
             ]
         }
+
+
+class PromptCollectionOutput(BaseInvocationOutput):
+    """Base class for invocations that output a collection of prompts"""
+
+    # fmt: off
+    type: Literal["prompt_collection_output"] = "prompt_collection_output"
+
+    prompt_collection: list[str] = Field(description="The output prompt collection")
+    count: int = Field(description="The size of the prompt collection")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "prompt_collection", "count"]}
+
+
+class DynamicPromptInvocation(BaseInvocation):
+    """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
+
+    type: Literal["dynamic_prompt"] = "dynamic_prompt"
+    prompt: str = Field(description="The prompt to parse with dynamicprompts")
+    max_prompts: int = Field(default=1, description="The number of prompts to generate")
+    combinatorial: bool = Field(
+        default=False, description="Whether to use the combinatorial generator"
+    )
+
+    def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
+        if self.combinatorial:
+            generator = CombinatorialPromptGenerator()
+            prompts = generator.generate(self.prompt, max_prompts=self.max_prompts)
+        else:
+            generator = RandomPromptGenerator()
+            prompts = generator.generate(self.prompt, num_images=self.max_prompts)
+
+        return PromptCollectionOutput(prompt_collection=prompts, count=len(prompts))

invokeai/app/invocations/reconstruct.py

@@ -1,4 +1,4 @@
-from typing import Literal, Union
+from typing import Literal, Optional
 
 from pydantic import Field
 
@@ -15,7 +15,7 @@ class RestoreFaceInvocation(BaseInvocation):
     type:  Literal["restore_face"] = "restore_face"
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image")
+    image: Optional[ImageField] = Field(description="The input image")
     strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
     # fmt: on
 
@@ -28,9 +28,7 @@ class RestoreFaceInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=None,
@@ -51,10 +49,7 @@ class RestoreFaceInvocation(BaseInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/upscale.py

@@ -1,6 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Literal, Union
+from typing import Literal, Optional
 
 from pydantic import Field
 
@@ -16,7 +16,7 @@ class UpscaleInvocation(BaseInvocation):
     type: Literal["upscale"] = "upscale"
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    image: Optional[ImageField] = Field(description="The input image", default=None)
     strength: float = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2, 4] = Field(default=2, description="The upscale level")
     # fmt: on
@@ -30,9 +30,7 @@ class UpscaleInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(
-            self.image.image_origin, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=(self.level, self.strength),
@@ -53,10 +51,7 @@ class UpscaleInvocation(BaseInvocation):
         )
 
         return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-                image_origin=image_dto.image_origin,
-            ),
+            image=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )

invokeai/app/invocations/util/choose_model.py

@@ -1,14 +0,0 @@
-from invokeai.backend.model_management.model_manager import ModelManager
-
-
-def choose_model(model_manager: ModelManager, model_name: str):
-    """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
-    logger = model_manager.logger
-    if model_name and not model_manager.valid_model(model_name):
-        default_model_name = model_manager.default_model()
-        logger.warning(f"\'{model_name}\' is not a valid model name. Using default model \'{default_model_name}\' instead.")
-        model = model_manager.get_model()
-    else:
-        model = model_manager.get_model(model_name)
-
-    return model

invokeai/app/models/image.py

@@ -66,13 +66,10 @@ class InvalidImageCategoryException(ValueError):
 class ImageField(BaseModel):
     """An image field used for passing image objects between invocations"""
 
-    image_origin: ResourceOrigin = Field(
-        default=ResourceOrigin.INTERNAL, description="The type of the image"
-    )
     image_name: Optional[str] = Field(default=None, description="The name of the image")
 
     class Config:
-        schema_extra = {"required": ["image_origin", "image_name"]}
+        schema_extra = {"required": ["image_name"]}
 
 
 class ColorField(BaseModel):

invokeai/app/services/board_image_record_storage.py

@@ -0,0 +1,253 @@
+from abc import ABC, abstractmethod
+import sqlite3
+import threading
+from typing import Optional, cast
+
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.image_record import (
+    ImageRecord,
+    deserialize_image_record,
+)
+
+
+class BoardImageRecordStorageBase(ABC):
+    """Abstract base class for the one-to-many board-image relationship record storage."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Removes an image from a board."""
+        pass
+
+    @abstractmethod
+    def get_images_for_board(
+        self,
+        board_id: str,
+    ) -> OffsetPaginatedResults[ImageRecord]:
+        """Gets images for a board."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass
+
+    @abstractmethod
+    def get_image_count_for_board(
+        self,
+        board_id: str,
+    ) -> int:
+        """Gets the number of images for a board."""
+        pass
+
+
+class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
+    _filename: str
+    _conn: sqlite3.Connection
+    _cursor: sqlite3.Cursor
+    _lock: threading.Lock
+
+    def __init__(self, filename: str) -> None:
+        super().__init__()
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
+        self._conn.row_factory = sqlite3.Row
+        self._cursor = self._conn.cursor()
+        self._lock = threading.Lock()
+
+        try:
+            self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
+            self._create_tables()
+            self._conn.commit()
+        finally:
+            self._lock.release()
+
+    def _create_tables(self) -> None:
+        """Creates the `board_images` junction table."""
+
+        # Create the `board_images` junction table.
+        self._cursor.execute(
+            """--sql
+            CREATE TABLE IF NOT EXISTS board_images (
+                board_id TEXT NOT NULL,
+                image_name TEXT NOT NULL,
+                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- updated via trigger
+                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- Soft delete, currently unused
+                deleted_at DATETIME,
+                -- enforce one-to-many relationship between boards and images using PK
+                -- (we can extend this to many-to-many later)
+                PRIMARY KEY (image_name),
+                FOREIGN KEY (board_id) REFERENCES boards (board_id) ON DELETE CASCADE,
+                FOREIGN KEY (image_name) REFERENCES images (image_name) ON DELETE CASCADE
+            );
+            """
+        )
+
+        # Add index for board id
+        self._cursor.execute(
+            """--sql
+            CREATE INDEX IF NOT EXISTS idx_board_images_board_id ON board_images (board_id);
+            """
+        )
+
+        # Add index for board id, sorted by created_at
+        self._cursor.execute(
+            """--sql
+            CREATE INDEX IF NOT EXISTS idx_board_images_board_id_created_at ON board_images (board_id, created_at);
+            """
+        )
+
+        # Add trigger for `updated_at`.
+        self._cursor.execute(
+            """--sql
+            CREATE TRIGGER IF NOT EXISTS tg_board_images_updated_at
+            AFTER UPDATE
+            ON board_images FOR EACH ROW
+            BEGIN
+                UPDATE board_images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                    WHERE board_id = old.board_id AND image_name = old.image_name;
+            END;
+            """
+        )
+
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                INSERT INTO board_images (board_id, image_name)
+                VALUES (?, ?)
+                ON CONFLICT (image_name) DO UPDATE SET board_id = ?;
+                """,
+                (board_id, image_name, board_id),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def remove_image_from_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                DELETE FROM board_images
+                WHERE board_id = ? AND image_name = ?;
+                """,
+                (board_id, image_name),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def get_images_for_board(
+        self,
+        board_id: str,
+        offset: int = 0,
+        limit: int = 10,
+    ) -> OffsetPaginatedResults[ImageRecord]:
+        # TODO: this isn't paginated yet?
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT images.*
+                FROM board_images
+                INNER JOIN images ON board_images.image_name = images.image_name
+                WHERE board_images.board_id = ?
+                ORDER BY board_images.updated_at DESC;
+                """,
+                (board_id,),
+            )
+            result = cast(list[sqlite3.Row], self._cursor.fetchall())
+            images = list(map(lambda r: deserialize_image_record(dict(r)), result))
+
+            self._cursor.execute(
+                """--sql
+                SELECT COUNT(*) FROM images WHERE 1=1;
+                """
+            )
+            count = cast(int, self._cursor.fetchone()[0])
+
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+        return OffsetPaginatedResults(
+            items=images, offset=offset, limit=limit, total=count
+        )
+
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT board_id
+                FROM board_images
+                WHERE image_name = ?;
+                """,
+                (image_name,),
+            )
+            result = self._cursor.fetchone()
+            if result is None:
+                return None
+            return cast(str, result[0])
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def get_image_count_for_board(self, board_id: str) -> int:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT COUNT(*) FROM board_images WHERE board_id = ?;
+                """,
+                (board_id,),
+            )
+            count = cast(int, self._cursor.fetchone()[0])
+            return count
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()

invokeai/app/services/board_images.py

@@ -0,0 +1,142 @@
+from abc import ABC, abstractmethod
+from logging import Logger
+from typing import List, Union, Optional
+from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
+from invokeai.app.services.board_record_storage import (
+    BoardRecord,
+    BoardRecordStorageBase,
+)
+
+from invokeai.app.services.image_record_storage import (
+    ImageRecordStorageBase,
+    OffsetPaginatedResults,
+)
+from invokeai.app.services.models.board_record import BoardDTO
+from invokeai.app.services.models.image_record import ImageDTO, image_record_to_dto
+from invokeai.app.services.urls import UrlServiceBase
+
+
+class BoardImagesServiceABC(ABC):
+    """High-level service for board-image relationship management."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Removes an image from a board."""
+        pass
+
+    @abstractmethod
+    def get_images_for_board(
+        self,
+        board_id: str,
+    ) -> OffsetPaginatedResults[ImageDTO]:
+        """Gets images for a board."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass
+
+
+class BoardImagesServiceDependencies:
+    """Service dependencies for the BoardImagesService."""
+
+    board_image_records: BoardImageRecordStorageBase
+    board_records: BoardRecordStorageBase
+    image_records: ImageRecordStorageBase
+    urls: UrlServiceBase
+    logger: Logger
+
+    def __init__(
+        self,
+        board_image_record_storage: BoardImageRecordStorageBase,
+        image_record_storage: ImageRecordStorageBase,
+        board_record_storage: BoardRecordStorageBase,
+        url: UrlServiceBase,
+        logger: Logger,
+    ):
+        self.board_image_records = board_image_record_storage
+        self.image_records = image_record_storage
+        self.board_records = board_record_storage
+        self.urls = url
+        self.logger = logger
+
+
+class BoardImagesService(BoardImagesServiceABC):
+    _services: BoardImagesServiceDependencies
+
+    def __init__(self, services: BoardImagesServiceDependencies):
+        self._services = services
+
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        self._services.board_image_records.add_image_to_board(board_id, image_name)
+
+    def remove_image_from_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        self._services.board_image_records.remove_image_from_board(board_id, image_name)
+
+    def get_images_for_board(
+        self,
+        board_id: str,
+    ) -> OffsetPaginatedResults[ImageDTO]:
+        image_records = self._services.board_image_records.get_images_for_board(
+            board_id
+        )
+        image_dtos = list(
+            map(
+                lambda r: image_record_to_dto(
+                    r,
+                    self._services.urls.get_image_url(r.image_name),
+                    self._services.urls.get_image_url(r.image_name, True),
+                    board_id,
+                ),
+                image_records.items,
+            )
+        )
+        return OffsetPaginatedResults[ImageDTO](
+            items=image_dtos,
+            offset=image_records.offset,
+            limit=image_records.limit,
+            total=image_records.total,
+        )
+
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        board_id = self._services.board_image_records.get_board_for_image(image_name)
+        return board_id
+
+
+def board_record_to_dto(
+    board_record: BoardRecord, cover_image_name: Optional[str], image_count: int
+) -> BoardDTO:
+    """Converts a board record to a board DTO."""
+    return BoardDTO(
+        **board_record.dict(exclude={'cover_image_name'}),
+        cover_image_name=cover_image_name,
+        image_count=image_count,
+    )

invokeai/app/services/board_record_storage.py

@@ -0,0 +1,329 @@
+from abc import ABC, abstractmethod
+from typing import Optional, cast
+import sqlite3
+import threading
+from typing import Optional, Union
+import uuid
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.board_record import (
+    BoardRecord,
+    deserialize_board_record,
+)
+
+from pydantic import BaseModel, Field, Extra
+
+
+class BoardChanges(BaseModel, extra=Extra.forbid):
+    board_name: Optional[str] = Field(description="The board's new name.")
+    cover_image_name: Optional[str] = Field(
+        description="The name of the board's new cover image."
+    )
+
+
+class BoardRecordNotFoundException(Exception):
+    """Raised when an board record is not found."""
+
+    def __init__(self, message="Board record not found"):
+        super().__init__(message)
+
+
+class BoardRecordSaveException(Exception):
+    """Raised when an board record cannot be saved."""
+
+    def __init__(self, message="Board record not saved"):
+        super().__init__(message)
+
+
+class BoardRecordDeleteException(Exception):
+    """Raised when an board record cannot be deleted."""
+
+    def __init__(self, message="Board record not deleted"):
+        super().__init__(message)
+
+
+class BoardRecordStorageBase(ABC):
+    """Low-level service responsible for interfacing with the board record store."""
+
+    @abstractmethod
+    def delete(self, board_id: str) -> None:
+        """Deletes a board record."""
+        pass
+
+    @abstractmethod
+    def save(
+        self,
+        board_name: str,
+    ) -> BoardRecord:
+        """Saves a board record."""
+        pass
+
+    @abstractmethod
+    def get(
+        self,
+        board_id: str,
+    ) -> BoardRecord:
+        """Gets a board record."""
+        pass
+
+    @abstractmethod
+    def update(
+        self,
+        board_id: str,
+        changes: BoardChanges,
+    ) -> BoardRecord:
+        """Updates a board record."""
+        pass
+
+    @abstractmethod
+    def get_many(
+        self,
+        offset: int = 0,
+        limit: int = 10,
+    ) -> OffsetPaginatedResults[BoardRecord]:
+        """Gets many board records."""
+        pass
+
+    @abstractmethod
+    def get_all(
+        self,
+    ) -> list[BoardRecord]:
+        """Gets all board records."""
+        pass
+
+
+class SqliteBoardRecordStorage(BoardRecordStorageBase):
+    _filename: str
+    _conn: sqlite3.Connection
+    _cursor: sqlite3.Cursor
+    _lock: threading.Lock
+
+    def __init__(self, filename: str) -> None:
+        super().__init__()
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
+        self._conn.row_factory = sqlite3.Row
+        self._cursor = self._conn.cursor()
+        self._lock = threading.Lock()
+
+        try:
+            self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
+            self._create_tables()
+            self._conn.commit()
+        finally:
+            self._lock.release()
+
+    def _create_tables(self) -> None:
+        """Creates the `boards` table and `board_images` junction table."""
+
+        # Create the `boards` table.
+        self._cursor.execute(
+            """--sql
+            CREATE TABLE IF NOT EXISTS boards (
+                board_id TEXT NOT NULL PRIMARY KEY,
+                board_name TEXT NOT NULL,
+                cover_image_name TEXT,
+                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- Updated via trigger
+                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- Soft delete, currently unused
+                deleted_at DATETIME,
+                FOREIGN KEY (cover_image_name) REFERENCES images (image_name) ON DELETE SET NULL
+            );
+            """
+        )
+
+        self._cursor.execute(
+            """--sql
+            CREATE INDEX IF NOT EXISTS idx_boards_created_at ON boards (created_at);
+            """
+        )
+
+        # Add trigger for `updated_at`.
+        self._cursor.execute(
+            """--sql
+            CREATE TRIGGER IF NOT EXISTS tg_boards_updated_at
+            AFTER UPDATE
+            ON boards FOR EACH ROW
+            BEGIN
+                UPDATE boards SET updated_at = current_timestamp
+                    WHERE board_id = old.board_id;
+            END;
+            """
+        )
+
+    def delete(self, board_id: str) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                DELETE FROM boards
+                WHERE board_id = ?;
+                """,
+                (board_id,),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise BoardRecordDeleteException from e
+        except Exception as e:
+            self._conn.rollback()
+            raise BoardRecordDeleteException from e
+        finally:
+            self._lock.release()
+
+    def save(
+        self,
+        board_name: str,
+    ) -> BoardRecord:
+        try:
+            board_id = str(uuid.uuid4())
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                INSERT OR IGNORE INTO boards (board_id, board_name)
+                VALUES (?, ?);
+                """,
+                (board_id, board_name),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise BoardRecordSaveException from e
+        finally:
+            self._lock.release()
+        return self.get(board_id)
+
+    def get(
+        self,
+        board_id: str,
+    ) -> BoardRecord:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT *
+                FROM boards
+                WHERE board_id = ?;
+                """,
+                (board_id,),
+            )
+
+            result = cast(Union[sqlite3.Row, None], self._cursor.fetchone())
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise BoardRecordNotFoundException from e
+        finally:
+            self._lock.release()
+        if result is None:
+            raise BoardRecordNotFoundException
+        return BoardRecord(**dict(result))
+
+    def update(
+        self,
+        board_id: str,
+        changes: BoardChanges,
+    ) -> BoardRecord:
+        try:
+            self._lock.acquire()
+
+            # Change the name of a board
+            if changes.board_name is not None:
+                self._cursor.execute(
+                    f"""--sql
+                    UPDATE boards
+                    SET board_name = ?
+                    WHERE board_id = ?;
+                    """,
+                    (changes.board_name, board_id),
+                )
+
+            # Change the cover image of a board
+            if changes.cover_image_name is not None:
+                self._cursor.execute(
+                    f"""--sql
+                    UPDATE boards
+                    SET cover_image_name = ?
+                    WHERE board_id = ?;
+                    """,
+                    (changes.cover_image_name, board_id),
+                )
+
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise BoardRecordSaveException from e
+        finally:
+            self._lock.release()
+        return self.get(board_id)
+
+    def get_many(
+        self,
+        offset: int = 0,
+        limit: int = 10,
+    ) -> OffsetPaginatedResults[BoardRecord]:
+        try:
+            self._lock.acquire()
+
+            # Get all the boards
+            self._cursor.execute(
+                """--sql
+                SELECT *
+                FROM boards
+                ORDER BY created_at DESC
+                LIMIT ? OFFSET ?;
+                """,
+                (limit, offset),
+            )
+
+            result = cast(list[sqlite3.Row], self._cursor.fetchall())
+            boards = list(map(lambda r: deserialize_board_record(dict(r)), result))
+
+            # Get the total number of boards
+            self._cursor.execute(
+                """--sql
+                SELECT COUNT(*)
+                FROM boards
+                WHERE 1=1;
+                """
+            )
+
+            count = cast(int, self._cursor.fetchone()[0])
+
+            return OffsetPaginatedResults[BoardRecord](
+                items=boards, offset=offset, limit=limit, total=count
+            )
+
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def get_all(
+        self,
+    ) -> list[BoardRecord]:
+        try:
+            self._lock.acquire()
+
+            # Get all the boards
+            self._cursor.execute(
+                """--sql
+                SELECT *
+                FROM boards
+                ORDER BY created_at DESC
+                """
+            )
+
+            result = cast(list[sqlite3.Row], self._cursor.fetchall())
+            boards = list(map(lambda r: deserialize_board_record(dict(r)), result))
+
+            return boards
+
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()

invokeai/app/services/boards.py

@@ -0,0 +1,185 @@
+from abc import ABC, abstractmethod
+
+from logging import Logger
+from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
+from invokeai.app.services.board_images import board_record_to_dto
+
+from invokeai.app.services.board_record_storage import (
+    BoardChanges,
+    BoardRecordStorageBase,
+)
+from invokeai.app.services.image_record_storage import (
+    ImageRecordStorageBase,
+    OffsetPaginatedResults,
+)
+from invokeai.app.services.models.board_record import BoardDTO
+from invokeai.app.services.urls import UrlServiceBase
+
+
+class BoardServiceABC(ABC):
+    """High-level service for board management."""
+
+    @abstractmethod
+    def create(
+        self,
+        board_name: str,
+    ) -> BoardDTO:
+        """Creates a board."""
+        pass
+
+    @abstractmethod
+    def get_dto(
+        self,
+        board_id: str,
+    ) -> BoardDTO:
+        """Gets a board."""
+        pass
+
+    @abstractmethod
+    def update(
+        self,
+        board_id: str,
+        changes: BoardChanges,
+    ) -> BoardDTO:
+        """Updates a board."""
+        pass
+
+    @abstractmethod
+    def delete(
+        self,
+        board_id: str,
+    ) -> None:
+        """Deletes a board."""
+        pass
+
+    @abstractmethod
+    def get_many(
+        self,
+        offset: int = 0,
+        limit: int = 10,
+    ) -> OffsetPaginatedResults[BoardDTO]:
+        """Gets many boards."""
+        pass
+
+    @abstractmethod
+    def get_all(
+        self,
+    ) -> list[BoardDTO]:
+        """Gets all boards."""
+        pass
+
+
+class BoardServiceDependencies:
+    """Service dependencies for the BoardService."""
+
+    board_image_records: BoardImageRecordStorageBase
+    board_records: BoardRecordStorageBase
+    image_records: ImageRecordStorageBase
+    urls: UrlServiceBase
+    logger: Logger
+
+    def __init__(
+        self,
+        board_image_record_storage: BoardImageRecordStorageBase,
+        image_record_storage: ImageRecordStorageBase,
+        board_record_storage: BoardRecordStorageBase,
+        url: UrlServiceBase,
+        logger: Logger,
+    ):
+        self.board_image_records = board_image_record_storage
+        self.image_records = image_record_storage
+        self.board_records = board_record_storage
+        self.urls = url
+        self.logger = logger
+
+
+class BoardService(BoardServiceABC):
+    _services: BoardServiceDependencies
+
+    def __init__(self, services: BoardServiceDependencies):
+        self._services = services
+
+    def create(
+        self,
+        board_name: str,
+    ) -> BoardDTO:
+        board_record = self._services.board_records.save(board_name)
+        return board_record_to_dto(board_record, None, 0)
+
+    def get_dto(self, board_id: str) -> BoardDTO:
+        board_record = self._services.board_records.get(board_id)
+        cover_image = self._services.image_records.get_most_recent_image_for_board(
+            board_record.board_id
+        )
+        if cover_image:
+            cover_image_name = cover_image.image_name
+        else:
+            cover_image_name = None
+        image_count = self._services.board_image_records.get_image_count_for_board(
+            board_id
+        )
+        return board_record_to_dto(board_record, cover_image_name, image_count)
+
+    def update(
+        self,
+        board_id: str,
+        changes: BoardChanges,
+    ) -> BoardDTO:
+        board_record = self._services.board_records.update(board_id, changes)
+        cover_image = self._services.image_records.get_most_recent_image_for_board(
+            board_record.board_id
+        )
+        if cover_image:
+            cover_image_name = cover_image.image_name
+        else:
+            cover_image_name = None
+
+        image_count = self._services.board_image_records.get_image_count_for_board(
+            board_id
+        )
+        return board_record_to_dto(board_record, cover_image_name, image_count)
+
+    def delete(self, board_id: str) -> None:
+        self._services.board_records.delete(board_id)
+
+    def get_many(
+        self, offset: int = 0, limit: int = 10
+    ) -> OffsetPaginatedResults[BoardDTO]:
+        board_records = self._services.board_records.get_many(offset, limit)
+        board_dtos = []
+        for r in board_records.items:
+            cover_image = self._services.image_records.get_most_recent_image_for_board(
+                r.board_id
+            )
+            if cover_image:
+                cover_image_name = cover_image.image_name
+            else:
+                cover_image_name = None
+
+            image_count = self._services.board_image_records.get_image_count_for_board(
+                r.board_id
+            )
+            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
+
+        return OffsetPaginatedResults[BoardDTO](
+            items=board_dtos, offset=offset, limit=limit, total=len(board_dtos)
+        )
+
+    def get_all(self) -> list[BoardDTO]:
+        board_records = self._services.board_records.get_all()
+        board_dtos = []
+        for r in board_records:
+            cover_image = self._services.image_records.get_most_recent_image_for_board(
+                r.board_id
+            )
+            if cover_image:
+                cover_image_name = cover_image.image_name
+            else:
+                cover_image_name = None
+
+            image_count = self._services.board_image_records.get_image_count_for_board(
+                r.board_id
+            )
+            board_dtos.append(board_record_to_dto(r, cover_image_name, image_count))
+
+        return board_dtos

invokeai/app/services/config.py

@@ -15,10 +15,7 @@ InvokeAI:
     conf_path: configs/models.yaml
     legacy_conf_dir: configs/stable-diffusion
     outdir: outputs
-    embedding_dir: embeddings
-    lora_dir: loras
-    autoconvert_dir: null
-    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
+    autoimport_dir: null
   Models:
     model: stable-diffusion-1.5
     embeddings: true
@@ -171,9 +168,10 @@ from argparse import ArgumentParser
 from omegaconf import OmegaConf, DictConfig
 from pathlib import Path
 from pydantic import BaseSettings, Field, parse_obj_as
-from typing import ClassVar, Dict, List, Literal, Type, Union, get_origin, get_type_hints, get_args
+from typing import ClassVar, Dict, List, Literal, Union, get_origin, get_type_hints, get_args
 
 INIT_FILE = Path('invokeai.yaml')
+MODEL_CORE = Path('models/core')
 DB_FILE   = Path('invokeai.db')
 LEGACY_INIT_FILE = Path('invokeai.init')
 
@@ -231,10 +229,10 @@ class InvokeAISettings(BaseSettings):
         upcase_environ = dict()
         for key,value in os.environ.items():
             upcase_environ[key.upper()] = value
-        
+
         fields = cls.__fields__
         cls.argparse_groups = {}
-        
+
         for name, field in fields.items():
             if name not in cls._excluded():
                 current_default = field.default
@@ -327,16 +325,11 @@ class InvokeAISettings(BaseSettings):
                 help=field.field_info.description,
             )
 def _find_root()->Path:
+    venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
     if os.environ.get("INVOKEAI_ROOT"):
         root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
-    elif (
-            os.environ.get("VIRTUAL_ENV")
-            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
-                 or
-                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
-                 )
-    ):
-        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
+    elif any([(venv.parent/x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE, MODEL_CORE]]):
+        root = (venv.parent).resolve()
     else:
         root = Path("~/invokeai").expanduser().resolve()
     return root
@@ -351,7 +344,7 @@ setting environment variables INVOKEAI_<setting>.
      '''
     singleton_config: ClassVar[InvokeAIAppConfig] = None
     singleton_init: ClassVar[Dict] = None
-    
+
     #fmt: off
     type: Literal["InvokeAI"] = "InvokeAI"
     host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
@@ -370,27 +363,27 @@ setting environment variables INVOKEAI_<setting>.
 
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
     free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
-    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=3, gt=0, description="(DEPRECATED: use max_cache_size) Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    max_cache_size      : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
     precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
     xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
-
+    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
 
     root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
-    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    autoimport_dir      : Path = Field(default='autoimport/main', description='Path to a directory of models files to be imported on startup.', category='Paths')
+    lora_dir            : Path = Field(default='autoimport/lora', description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', category='Paths')
+    embedding_dir       : Path = Field(default='autoimport/embedding', description='Path to a directory of Textual Inversion embeddings to be imported on startup.', category='Paths')
+    controlnet_dir      : Path = Field(default='autoimport/controlnet', description='Path to a directory of ControlNet embeddings to be imported on startup.', category='Paths')
     conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
-    embedding_dir       : Path = Field(default='embeddings', description='Path to InvokeAI textual inversion aembeddings directory', category='Paths')
-    gfpgan_model_dir    : Path = Field(default="./models/gfpgan/GFPGANv1.4.pth", description='Path to GFPGAN models directory.', category='Paths')
-    controlnet_dir      : Path = Field(default="controlnets", description='Path to directory of ControlNet models.', category='Paths')
+    models_dir          : Path = Field(default='models', description='Path to the models directory', category='Paths')
     legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
-    lora_dir            : Path = Field(default='loras', description='Path to InvokeAI LoRA model directory', category='Paths')
     db_dir              : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
     outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
     from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
     use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
 
     model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
-    embeddings          : bool = Field(default=True, description='Load contents of embeddings directory', category='Models')
 
     log_handlers        : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
     # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
@@ -400,7 +393,7 @@ setting environment variables INVOKEAI_<setting>.
 
     def parse_args(self, argv: List[str]=None, conf: DictConfig = None, clobber=False):
         '''
-        Update settings with contents of init file, environment, and 
+        Update settings with contents of init file, environment, and
         command-line settings.
         :param conf: alternate Omegaconf dictionary object
         :param argv: aternate sys.argv list
@@ -415,7 +408,7 @@ setting environment variables INVOKEAI_<setting>.
             except:
                 pass
         InvokeAISettings.initconf = conf
-        
+
         # parse args again in order to pick up settings in configuration file
         super().parse_args(argv)
 
@@ -435,7 +428,7 @@ setting environment variables INVOKEAI_<setting>.
             cls.singleton_config = cls(**kwargs)
             cls.singleton_init = kwargs
         return cls.singleton_config
-        
+
     @property
     def root_path(self)->Path:
         '''
@@ -492,39 +485,11 @@ setting environment variables INVOKEAI_<setting>.
         return self._resolve(self.legacy_conf_dir)
 
     @property
-    def cache_dir(self)->Path:
-        '''
-        Path to the global cache directory for HuggingFace hub-managed models
-        '''
-        return self.models_dir / "hub"
-
-    @property
-    def models_dir(self)->Path:
+    def models_path(self)->Path:
         '''
         Path to the models directory
         '''
-        return self._resolve("models")
-
-    @property
-    def embedding_path(self)->Path:
-        '''
-        Path to the textual inversion embeddings directory.
-        '''
-        return self._resolve(self.embedding_dir) if self.embedding_dir else None
-
-    @property
-    def lora_path(self)->Path:
-        '''
-        Path to the LoRA models directory.
-        '''
-        return self._resolve(self.lora_dir) if self.lora_dir else None
-
-    @property
-    def controlnet_path(self)->Path:
-        '''
-        Path to the controlnet models directory.
-        '''
-        return self._resolve(self.controlnet_dir) if self.controlnet_dir else None
+        return self._resolve(self.models_dir)
 
     @property
     def autoconvert_path(self)->Path:
@@ -533,13 +498,6 @@ setting environment variables INVOKEAI_<setting>.
         '''
         return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
 
-    @property
-    def gfpgan_model_path(self)->Path:
-        '''
-        Path to the GFPGAN model.
-        '''
-        return self._resolve(self.gfpgan_model_dir) if self.gfpgan_model_dir else None
-
     # the following methods support legacy calls leftover from the Globals era
     @property
     def full_precision(self)->bool:

invokeai/app/services/default_graphs.py

@@ -1,4 +1,5 @@
-from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.latent import LatentsToImageInvocation, TextToLatentsInvocation
+from ..invocations.noise import NoiseInvocation
 from ..invocations.compel import CompelInvocation
 from ..invocations.params import ParamIntInvocation
 from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph

invokeai/app/services/events.py

@@ -1,9 +1,9 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Any
+from typing import Any, Optional
 from invokeai.app.models.image import ProgressImage
 from invokeai.app.util.misc import get_timestamp
-
+from invokeai.app.services.model_manager_service import BaseModelType, ModelType, SubModelType, ModelInfo
 
 class EventServiceBase:
     session_event: str = "session_event"
@@ -27,7 +27,7 @@ class EventServiceBase:
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
-        progress_image: ProgressImage | None,
+        progress_image: Optional[ProgressImage],
         step: int,
         total_steps: int,
     ) -> None:
@@ -101,3 +101,53 @@ class EventServiceBase:
                 graph_execution_state_id=graph_execution_state_id,
             ),
         )
+
+    def emit_model_load_started (
+            self,
+            graph_execution_state_id: str,
+            node: dict,
+            source_node_id: str,
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+            submodel: SubModelType,
+    ) -> None:
+        """Emitted when a model is requested"""
+        self.__emit_session_event(
+            event_name="model_load_started",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            ),
+        )
+
+    def emit_model_load_completed(
+            self,
+            graph_execution_state_id: str,
+            node: dict,
+            source_node_id: str,
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+            submodel: SubModelType,
+            model_info: ModelInfo,
+    ) -> None:
+        """Emitted when a model is correctly loaded (returns model info)"""
+        self.__emit_session_event(
+            event_name="model_load_completed",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                model_info=model_info,
+            ),
+        )

invokeai/app/services/graph.py

@@ -3,7 +3,6 @@
 import copy
 import itertools
 import uuid
-from types import NoneType
 from typing import (
     Annotated,
     Any,
@@ -26,6 +25,8 @@ from ..invocations.baseinvocation import (
     InvocationContext,
 )
 
+# in 3.10 this would be "from types import NoneType"
+NoneType = type(None)
 
 class EdgeConnection(BaseModel):
     node_id: str = Field(description="The id of the node for this edge connection")
@@ -60,8 +61,6 @@ def get_input_field(node: BaseInvocation, field: str) -> Any:
     node_input_field = node_inputs.get(field) or None
     return node_input_field
 
-from typing import Optional, Union, List, get_args
-
 def is_union_subtype(t1, t2):
     t1_args = get_args(t1)
     t2_args = get_args(t2)
@@ -846,7 +845,7 @@ class GraphExecutionState(BaseModel):
             ]
         }
 
-    def next(self) -> BaseInvocation | None:
+    def next(self) -> Optional[BaseInvocation]:
         """Gets the next node ready to execute."""
 
         # TODO: enable multiple nodes to execute simultaneously by tracking currently executing nodes

invokeai/app/services/image_file_storage.py

@@ -1,15 +1,13 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
-import os
 from abc import ABC, abstractmethod
 from pathlib import Path
 from queue import Queue
-from typing import Dict, Optional
+from typing import Dict, Optional, Union
 
 from PIL.Image import Image as PILImageType
 from PIL import Image, PngImagePlugin
 from send2trash import send2trash
 
-from invokeai.app.models.image import ResourceOrigin
 from invokeai.app.models.metadata import ImageMetadata
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
@@ -40,14 +38,12 @@ class ImageFileStorageBase(ABC):
     """Low-level service responsible for storing and retrieving image files."""
 
     @abstractmethod
-    def get(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+    def get(self, image_name: str) -> PILImageType:
         """Retrieves an image as PIL Image."""
         pass
 
     @abstractmethod
-    def get_path(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
         """Gets the internal path to an image or thumbnail."""
         pass
 
@@ -62,7 +58,6 @@ class ImageFileStorageBase(ABC):
     def save(
         self,
         image: PILImageType,
-        image_origin: ResourceOrigin,
         image_name: str,
         metadata: Optional[ImageMetadata] = None,
         thumbnail_size: int = 256,
@@ -71,7 +66,7 @@ class ImageFileStorageBase(ABC):
         pass
 
     @abstractmethod
-    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+    def delete(self, image_name: str) -> None:
         """Deletes an image and its thumbnail (if one exists)."""
         pass
 
@@ -79,31 +74,28 @@ class ImageFileStorageBase(ABC):
 class DiskImageFileStorage(ImageFileStorageBase):
     """Stores images on disk"""
 
-    __output_folder: str
+    __output_folder: Path
     __cache_ids: Queue  # TODO: this is an incredibly naive cache
-    __cache: Dict[str, PILImageType]
+    __cache: Dict[Path, PILImageType]
     __max_cache_size: int
 
-    def __init__(self, output_folder: str):
-        self.__output_folder = output_folder
+    def __init__(self, output_folder: Union[str, Path]):
         self.__cache = dict()
         self.__cache_ids = Queue()
         self.__max_cache_size = 10  # TODO: get this from config
 
-        Path(output_folder).mkdir(parents=True, exist_ok=True)
+        self.__output_folder: Path = (
+            output_folder if isinstance(output_folder, Path) else Path(output_folder)
+        )
+        self.__thumbnails_folder = self.__output_folder / "thumbnails"
 
-        # TODO: don't hard-code. get/save/delete should maybe take subpath?
-        for image_origin in ResourceOrigin:
-            Path(os.path.join(output_folder, image_origin)).mkdir(
-                parents=True, exist_ok=True
-            )
-            Path(os.path.join(output_folder, image_origin, "thumbnails")).mkdir(
-                parents=True, exist_ok=True
-            )
+        # Validate required output folders at launch
+        self.__validate_storage_folders()
 
-    def get(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+    def get(self, image_name: str) -> PILImageType:
         try:
-            image_path = self.get_path(image_origin, image_name)
+            image_path = self.get_path(image_name)
+
             cache_item = self.__get_cache(image_path)
             if cache_item:
                 return cache_item
@@ -117,13 +109,13 @@ class DiskImageFileStorage(ImageFileStorageBase):
     def save(
         self,
         image: PILImageType,
-        image_origin: ResourceOrigin,
         image_name: str,
         metadata: Optional[ImageMetadata] = None,
         thumbnail_size: int = 256,
     ) -> None:
         try:
-            image_path = self.get_path(image_origin, image_name)
+            self.__validate_storage_folders()
+            image_path = self.get_path(image_name)
 
             if metadata is not None:
                 pnginfo = PngImagePlugin.PngInfo()
@@ -133,7 +125,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
                 image.save(image_path, "PNG")
 
             thumbnail_name = get_thumbnail_name(image_name)
-            thumbnail_path = self.get_path(image_origin, thumbnail_name, thumbnail=True)
+            thumbnail_path = self.get_path(thumbnail_name, thumbnail=True)
             thumbnail_image = make_thumbnail(image, thumbnail_size)
             thumbnail_image.save(thumbnail_path)
 
@@ -142,20 +134,19 @@ class DiskImageFileStorage(ImageFileStorageBase):
         except Exception as e:
             raise ImageFileSaveException from e
 
-    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+    def delete(self, image_name: str) -> None:
         try:
-            basename = os.path.basename(image_name)
-            image_path = self.get_path(image_origin, basename)
+            image_path = self.get_path(image_name)
 
-            if os.path.exists(image_path):
+            if image_path.exists():
                 send2trash(image_path)
             if image_path in self.__cache:
                 del self.__cache[image_path]
 
             thumbnail_name = get_thumbnail_name(image_name)
-            thumbnail_path = self.get_path(image_origin, thumbnail_name, True)
+            thumbnail_path = self.get_path(thumbnail_name, True)
 
-            if os.path.exists(thumbnail_path):
+            if thumbnail_path.exists():
                 send2trash(thumbnail_path)
             if thumbnail_path in self.__cache:
                 del self.__cache[thumbnail_path]
@@ -163,36 +154,30 @@ class DiskImageFileStorage(ImageFileStorageBase):
             raise ImageFileDeleteException from e
 
     # TODO: make this a bit more flexible for e.g. cloud storage
-    def get_path(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
-        # strip out any relative path shenanigans
-        basename = os.path.basename(image_name)
+    def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
+        path = self.__output_folder / image_name
 
         if thumbnail:
-            thumbnail_name = get_thumbnail_name(basename)
-            path = os.path.join(
-                self.__output_folder, image_origin, "thumbnails", thumbnail_name
-            )
-        else:
-            path = os.path.join(self.__output_folder, image_origin, basename)
+            thumbnail_name = get_thumbnail_name(image_name)
+            path = self.__thumbnails_folder / thumbnail_name
 
-        abspath = os.path.abspath(path)
+        return path
 
-        return abspath
-
-    def validate_path(self, path: str) -> bool:
+    def validate_path(self, path: Union[str, Path]) -> bool:
         """Validates the path given for an image or thumbnail."""
-        try:
-            os.stat(path)
-            return True
-        except:
-            return False
+        path = path if isinstance(path, Path) else Path(path)
+        return path.exists()
 
-    def __get_cache(self, image_name: str) -> PILImageType | None:
+    def __validate_storage_folders(self) -> None:
+        """Checks if the required output folders exist and create them if they don't"""
+        folders: list[Path] = [self.__output_folder, self.__thumbnails_folder]
+        for folder in folders:
+            folder.mkdir(parents=True, exist_ok=True)
+
+    def __get_cache(self, image_name: Path) -> Optional[PILImageType]:
         return None if image_name not in self.__cache else self.__cache[image_name]
 
-    def __set_cache(self, image_name: str, image: PILImageType):
+    def __set_cache(self, image_name: Path, image: PILImageType):
         if not image_name in self.__cache:
             self.__cache[image_name] = image
             self.__cache_ids.put(

invokeai/app/services/image_record_storage.py

@@ -3,7 +3,6 @@ from datetime import datetime
 from typing import Generic, Optional, TypeVar, cast
 import sqlite3
 import threading
-from typing import Optional, Union
 
 from pydantic import BaseModel, Field
 from pydantic.generics import GenericModel
@@ -21,6 +20,7 @@ from invokeai.app.services.models.image_record import (
 
 T = TypeVar("T", bound=BaseModel)
 
+
 class OffsetPaginatedResults(GenericModel, Generic[T]):
     """Offset-paginated results"""
 
@@ -60,7 +60,7 @@ class ImageRecordStorageBase(ABC):
     # TODO: Implement an `update()` method
 
     @abstractmethod
-    def get(self, image_origin: ResourceOrigin, image_name: str) -> ImageRecord:
+    def get(self, image_name: str) -> ImageRecord:
         """Gets an image record."""
         pass
 
@@ -68,7 +68,6 @@ class ImageRecordStorageBase(ABC):
     def update(
         self,
         image_name: str,
-        image_origin: ResourceOrigin,
         changes: ImageRecordChanges,
     ) -> None:
         """Updates an image record."""
@@ -82,6 +81,7 @@ class ImageRecordStorageBase(ABC):
         image_origin: Optional[ResourceOrigin] = None,
         categories: Optional[list[ImageCategory]] = None,
         is_intermediate: Optional[bool] = None,
+        board_id: Optional[str] = None,
     ) -> OffsetPaginatedResults[ImageRecord]:
         """Gets a page of image records."""
         pass
@@ -89,10 +89,15 @@ class ImageRecordStorageBase(ABC):
     # TODO: The database has a nullable `deleted_at` column, currently unused.
     # Should we implement soft deletes? Would need coordination with ImageFileStorage.
     @abstractmethod
-    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+    def delete(self, image_name: str) -> None:
         """Deletes an image record."""
         pass
 
+    @abstractmethod
+    def delete_many(self, image_names: list[str]) -> None:
+        """Deletes many image records."""
+        pass
+
     @abstractmethod
     def save(
         self,
@@ -109,6 +114,11 @@ class ImageRecordStorageBase(ABC):
         """Saves an image record."""
         pass
 
+    @abstractmethod
+    def get_most_recent_image_for_board(self, board_id: str) -> Optional[ImageRecord]:
+        """Gets the most recent image for a board."""
+        pass
+
 
 class SqliteImageRecordStorage(ImageRecordStorageBase):
     _filename: str
@@ -135,7 +145,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             self._lock.release()
 
     def _create_tables(self) -> None:
-        """Creates the tables for the `images` database."""
+        """Creates the `images` table."""
 
         # Create the `images` table.
         self._cursor.execute(
@@ -152,6 +162,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
                 node_id TEXT,
                 metadata TEXT,
                 is_intermediate BOOLEAN DEFAULT FALSE,
+                board_id TEXT,
                 created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
                 -- Updated via trigger
                 updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
@@ -190,15 +201,13 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             AFTER UPDATE
             ON images FOR EACH ROW
             BEGIN
-                UPDATE images SET updated_at = current_timestamp
+                UPDATE images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
                     WHERE image_name = old.image_name;
             END;
             """
         )
 
-    def get(
-        self, image_origin: ResourceOrigin, image_name: str
-    ) -> Union[ImageRecord, None]:
+    def get(self, image_name: str) -> Optional[ImageRecord]:
         try:
             self._lock.acquire()
 
@@ -210,7 +219,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
                 (image_name,),
             )
 
-            result = cast(Union[sqlite3.Row, None], self._cursor.fetchone())
+            result = cast(Optional[sqlite3.Row], self._cursor.fetchone())
         except sqlite3.Error as e:
             self._conn.rollback()
             raise ImageRecordNotFoundException from e
@@ -225,7 +234,6 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
     def update(
         self,
         image_name: str,
-        image_origin: ResourceOrigin,
         changes: ImageRecordChanges,
     ) -> None:
         try:
@@ -262,6 +270,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
                     """,
                     (changes.is_intermediate, image_name),
                 )
+
             self._conn.commit()
         except sqlite3.Error as e:
             self._conn.rollback()
@@ -276,40 +285,66 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         image_origin: Optional[ResourceOrigin] = None,
         categories: Optional[list[ImageCategory]] = None,
         is_intermediate: Optional[bool] = None,
+        board_id: Optional[str] = None,
     ) -> OffsetPaginatedResults[ImageRecord]:
         try:
             self._lock.acquire()
 
             # Manually build two queries - one for the count, one for the records
+            count_query = """--sql
+            SELECT COUNT(*)
+            FROM images
+            LEFT JOIN board_images ON board_images.image_name = images.image_name
+            WHERE 1=1
+            """
 
-            count_query = f"""SELECT COUNT(*) FROM images WHERE 1=1\n"""
-            images_query = f"""SELECT * FROM images WHERE 1=1\n"""
+            images_query = """--sql
+            SELECT images.*
+            FROM images
+            LEFT JOIN board_images ON board_images.image_name = images.image_name
+            WHERE 1=1
+            """
 
             query_conditions = ""
             query_params = []
 
             if image_origin is not None:
-                query_conditions += f"""AND image_origin = ?\n"""
+                query_conditions += """--sql
+                AND images.image_origin = ?
+                """
                 query_params.append(image_origin.value)
 
             if categories is not None:
-                ## Convert the enum values to unique list of strings
-                category_strings = list(
-                    map(lambda c: c.value, set(categories))
-                )
+                # Convert the enum values to unique list of strings
+                category_strings = list(map(lambda c: c.value, set(categories)))
                 # Create the correct length of placeholders
                 placeholders = ",".join("?" * len(category_strings))
-                query_conditions += f"AND image_category IN ( {placeholders} )\n"
+
+                query_conditions += f"""--sql
+                AND images.image_category IN ( {placeholders} )
+                """
 
                 # Unpack the included categories into the query params
                 for c in category_strings:
                     query_params.append(c)
 
             if is_intermediate is not None:
-                query_conditions += f"""AND is_intermediate = ?\n"""
+                query_conditions += """--sql
+                AND images.is_intermediate = ?
+                """
+
                 query_params.append(is_intermediate)
 
-            query_pagination = f"""ORDER BY created_at DESC LIMIT ? OFFSET ?\n"""
+            if board_id is not None:
+                query_conditions += """--sql
+                AND board_images.board_id = ?
+                """
+
+                query_params.append(board_id)
+
+            query_pagination = """--sql
+            ORDER BY images.created_at DESC LIMIT ? OFFSET ?
+            """
 
             # Final images query with pagination
             images_query += query_conditions + query_pagination + ";"
@@ -326,7 +361,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             count_query += query_conditions + ";"
             count_params = query_params.copy()
             self._cursor.execute(count_query, count_params)
-            count = self._cursor.fetchone()[0]
+            count = cast(int, self._cursor.fetchone()[0])
         except sqlite3.Error as e:
             self._conn.rollback()
             raise e
@@ -337,7 +372,7 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             items=images, offset=offset, limit=limit, total=count
         )
 
-    def delete(self, image_origin: ResourceOrigin, image_name: str) -> None:
+    def delete(self, image_name: str) -> None:
         try:
             self._lock.acquire()
             self._cursor.execute(
@@ -354,6 +389,25 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
         finally:
             self._lock.release()
 
+    def delete_many(self, image_names: list[str]) -> None:
+        try:
+            placeholders = ",".join("?" for _ in image_names)
+
+            self._lock.acquire()
+
+            # Construct the SQLite query with the placeholders
+            query = f"DELETE FROM images WHERE image_name IN ({placeholders})"
+
+            # Execute the query with the list of IDs as parameters
+            self._cursor.execute(query, image_names)
+
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise ImageRecordDeleteException from e
+        finally:
+            self._lock.release()
+
     def save(
         self,
         image_name: str,
@@ -417,3 +471,28 @@ class SqliteImageRecordStorage(ImageRecordStorageBase):
             raise ImageRecordSaveException from e
         finally:
             self._lock.release()
+
+    def get_most_recent_image_for_board(
+        self, board_id: str
+    ) -> Optional[ImageRecord]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT images.*
+                FROM images
+                JOIN board_images ON images.image_name = board_images.image_name
+                WHERE board_images.board_id = ?
+                ORDER BY images.created_at DESC
+                LIMIT 1;
+                """,
+                (board_id,),
+            )
+
+            result = cast(Optional[sqlite3.Row], self._cursor.fetchone())
+        finally:
+            self._lock.release()
+        if result is None:
+            return None
+
+        return deserialize_image_record(dict(result))

invokeai/app/services/images.py

@@ -10,6 +10,7 @@ from invokeai.app.models.image import (
     InvalidOriginException,
 )
 from invokeai.app.models.metadata import ImageMetadata
+from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
 from invokeai.app.services.image_record_storage import (
     ImageRecordDeleteException,
     ImageRecordNotFoundException,
@@ -49,7 +50,7 @@ class ImageServiceABC(ABC):
         image_category: ImageCategory,
         node_id: Optional[str] = None,
         session_id: Optional[str] = None,
-        intermediate: bool = False,
+        is_intermediate: bool = False,
     ) -> ImageDTO:
         """Creates an image, storing the file and its metadata."""
         pass
@@ -57,7 +58,6 @@ class ImageServiceABC(ABC):
     @abstractmethod
     def update(
         self,
-        image_origin: ResourceOrigin,
         image_name: str,
         changes: ImageRecordChanges,
     ) -> ImageDTO:
@@ -65,22 +65,22 @@ class ImageServiceABC(ABC):
         pass
 
     @abstractmethod
-    def get_pil_image(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+    def get_pil_image(self, image_name: str) -> PILImageType:
         """Gets an image as a PIL image."""
         pass
 
     @abstractmethod
-    def get_record(self, image_origin: ResourceOrigin, image_name: str) -> ImageRecord:
+    def get_record(self, image_name: str) -> ImageRecord:
         """Gets an image record."""
         pass
 
     @abstractmethod
-    def get_dto(self, image_origin: ResourceOrigin, image_name: str) -> ImageDTO:
+    def get_dto(self, image_name: str) -> ImageDTO:
         """Gets an image DTO."""
         pass
 
     @abstractmethod
-    def get_path(self, image_origin: ResourceOrigin, image_name: str) -> str:
+    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
         """Gets an image's path."""
         pass
 
@@ -90,9 +90,7 @@ class ImageServiceABC(ABC):
         pass
 
     @abstractmethod
-    def get_url(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_url(self, image_name: str, thumbnail: bool = False) -> str:
         """Gets an image's or thumbnail's URL."""
         pass
 
@@ -104,21 +102,28 @@ class ImageServiceABC(ABC):
         image_origin: Optional[ResourceOrigin] = None,
         categories: Optional[list[ImageCategory]] = None,
         is_intermediate: Optional[bool] = None,
+        board_id: Optional[str] = None,
     ) -> OffsetPaginatedResults[ImageDTO]:
         """Gets a paginated list of image DTOs."""
         pass
 
     @abstractmethod
-    def delete(self, image_origin: ResourceOrigin, image_name: str):
+    def delete(self, image_name: str):
         """Deletes an image."""
         pass
 
+    @abstractmethod
+    def delete_images_on_board(self, board_id: str):
+        """Deletes all images on a board."""
+        pass
+
 
 class ImageServiceDependencies:
     """Service dependencies for the ImageService."""
 
-    records: ImageRecordStorageBase
-    files: ImageFileStorageBase
+    image_records: ImageRecordStorageBase
+    image_files: ImageFileStorageBase
+    board_image_records: BoardImageRecordStorageBase
     metadata: MetadataServiceBase
     urls: UrlServiceBase
     logger: Logger
@@ -129,14 +134,16 @@ class ImageServiceDependencies:
         self,
         image_record_storage: ImageRecordStorageBase,
         image_file_storage: ImageFileStorageBase,
+        board_image_record_storage: BoardImageRecordStorageBase,
         metadata: MetadataServiceBase,
         url: UrlServiceBase,
         logger: Logger,
         names: NameServiceBase,
         graph_execution_manager: ItemStorageABC["GraphExecutionState"],
     ):
-        self.records = image_record_storage
-        self.files = image_file_storage
+        self.image_records = image_record_storage
+        self.image_files = image_file_storage
+        self.board_image_records = board_image_record_storage
         self.metadata = metadata
         self.urls = url
         self.logger = logger
@@ -147,25 +154,8 @@ class ImageServiceDependencies:
 class ImageService(ImageServiceABC):
     _services: ImageServiceDependencies
 
-    def __init__(
-        self,
-        image_record_storage: ImageRecordStorageBase,
-        image_file_storage: ImageFileStorageBase,
-        metadata: MetadataServiceBase,
-        url: UrlServiceBase,
-        logger: Logger,
-        names: NameServiceBase,
-        graph_execution_manager: ItemStorageABC["GraphExecutionState"],
-    ):
-        self._services = ImageServiceDependencies(
-            image_record_storage=image_record_storage,
-            image_file_storage=image_file_storage,
-            metadata=metadata,
-            url=url,
-            logger=logger,
-            names=names,
-            graph_execution_manager=graph_execution_manager,
-        )
+    def __init__(self, services: ImageServiceDependencies):
+        self._services = services
 
     def create(
         self,
@@ -190,7 +180,7 @@ class ImageService(ImageServiceABC):
 
         try:
             # TODO: Consider using a transaction here to ensure consistency between storage and database
-            created_at = self._services.records.save(
+            self._services.image_records.save(
                 # Non-nullable fields
                 image_name=image_name,
                 image_origin=image_origin,
@@ -205,38 +195,15 @@ class ImageService(ImageServiceABC):
                 metadata=metadata,
             )
 
-            self._services.files.save(
-                image_origin=image_origin,
+            self._services.image_files.save(
                 image_name=image_name,
                 image=image,
                 metadata=metadata,
             )
 
-            image_url = self._services.urls.get_image_url(image_origin, image_name)
-            thumbnail_url = self._services.urls.get_image_url(
-                image_origin, image_name, True
-            )
+            image_dto = self.get_dto(image_name)
 
-            return ImageDTO(
-                # Non-nullable fields
-                image_name=image_name,
-                image_origin=image_origin,
-                image_category=image_category,
-                width=width,
-                height=height,
-                # Nullable fields
-                node_id=node_id,
-                session_id=session_id,
-                metadata=metadata,
-                # Meta fields
-                created_at=created_at,
-                updated_at=created_at,  # this is always the same as the created_at at this time
-                deleted_at=None,
-                is_intermediate=is_intermediate,
-                # Extra non-nullable fields for DTO
-                image_url=image_url,
-                thumbnail_url=thumbnail_url,
-            )
+            return image_dto
         except ImageRecordSaveException:
             self._services.logger.error("Failed to save image record")
             raise
@@ -249,13 +216,12 @@ class ImageService(ImageServiceABC):
 
     def update(
         self,
-        image_origin: ResourceOrigin,
         image_name: str,
         changes: ImageRecordChanges,
     ) -> ImageDTO:
         try:
-            self._services.records.update(image_name, image_origin, changes)
-            return self.get_dto(image_origin, image_name)
+            self._services.image_records.update(image_name, changes)
+            return self.get_dto(image_name)
         except ImageRecordSaveException:
             self._services.logger.error("Failed to update image record")
             raise
@@ -263,9 +229,9 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem updating image record")
             raise e
 
-    def get_pil_image(self, image_origin: ResourceOrigin, image_name: str) -> PILImageType:
+    def get_pil_image(self, image_name: str) -> PILImageType:
         try:
-            return self._services.files.get(image_origin, image_name)
+            return self._services.image_files.get(image_name)
         except ImageFileNotFoundException:
             self._services.logger.error("Failed to get image file")
             raise
@@ -273,9 +239,9 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem getting image file")
             raise e
 
-    def get_record(self, image_origin: ResourceOrigin, image_name: str) -> ImageRecord:
+    def get_record(self, image_name: str) -> ImageRecord:
         try:
-            return self._services.records.get(image_origin, image_name)
+            return self._services.image_records.get(image_name)
         except ImageRecordNotFoundException:
             self._services.logger.error("Image record not found")
             raise
@@ -283,14 +249,15 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem getting image record")
             raise e
 
-    def get_dto(self, image_origin: ResourceOrigin, image_name: str) -> ImageDTO:
+    def get_dto(self, image_name: str) -> ImageDTO:
         try:
-            image_record = self._services.records.get(image_origin, image_name)
+            image_record = self._services.image_records.get(image_name)
 
             image_dto = image_record_to_dto(
                 image_record,
-                self._services.urls.get_image_url(image_origin, image_name),
-                self._services.urls.get_image_url(image_origin, image_name, True),
+                self._services.urls.get_image_url(image_name),
+                self._services.urls.get_image_url(image_name, True),
+                self._services.board_image_records.get_board_for_image(image_name),
             )
 
             return image_dto
@@ -301,27 +268,23 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem getting image DTO")
             raise e
 
-    def get_path(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_path(self, image_name: str, thumbnail: bool = False) -> str:
         try:
-            return self._services.files.get_path(image_origin, image_name, thumbnail)
+            return self._services.image_files.get_path(image_name, thumbnail)
         except Exception as e:
             self._services.logger.error("Problem getting image path")
             raise e
 
     def validate_path(self, path: str) -> bool:
         try:
-            return self._services.files.validate_path(path)
+            return self._services.image_files.validate_path(path)
         except Exception as e:
             self._services.logger.error("Problem validating image path")
             raise e
 
-    def get_url(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_url(self, image_name: str, thumbnail: bool = False) -> str:
         try:
-            return self._services.urls.get_image_url(image_origin, image_name, thumbnail)
+            return self._services.urls.get_image_url(image_name, thumbnail)
         except Exception as e:
             self._services.logger.error("Problem getting image path")
             raise e
@@ -333,23 +296,26 @@ class ImageService(ImageServiceABC):
         image_origin: Optional[ResourceOrigin] = None,
         categories: Optional[list[ImageCategory]] = None,
         is_intermediate: Optional[bool] = None,
+        board_id: Optional[str] = None,
     ) -> OffsetPaginatedResults[ImageDTO]:
         try:
-            results = self._services.records.get_many(
+            results = self._services.image_records.get_many(
                 offset,
                 limit,
                 image_origin,
                 categories,
                 is_intermediate,
+                board_id,
             )
 
             image_dtos = list(
                 map(
                     lambda r: image_record_to_dto(
                         r,
-                        self._services.urls.get_image_url(r.image_origin, r.image_name),
-                        self._services.urls.get_image_url(
-                            r.image_origin, r.image_name, True
+                        self._services.urls.get_image_url(r.image_name),
+                        self._services.urls.get_image_url(r.image_name, True),
+                        self._services.board_image_records.get_board_for_image(
+                            r.image_name
                         ),
                     ),
                     results.items,
@@ -366,10 +332,10 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem getting paginated image DTOs")
             raise e
 
-    def delete(self, image_origin: ResourceOrigin, image_name: str):
+    def delete(self, image_name: str):
         try:
-            self._services.files.delete(image_origin, image_name)
-            self._services.records.delete(image_origin, image_name)
+            self._services.image_files.delete(image_name)
+            self._services.image_records.delete(image_name)
         except ImageRecordDeleteException:
             self._services.logger.error(f"Failed to delete image record")
             raise
@@ -380,9 +346,31 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Problem deleting image record and file")
             raise e
 
+    def delete_images_on_board(self, board_id: str):
+        try:
+            images = self._services.board_image_records.get_images_for_board(board_id)
+            image_name_list = list(
+                map(
+                    lambda r: r.image_name,
+                    images.items,
+                )
+            )
+            for image_name in image_name_list:
+                self._services.image_files.delete(image_name)
+            self._services.image_records.delete_many(image_name_list)
+        except ImageRecordDeleteException:
+            self._services.logger.error(f"Failed to delete image records")
+            raise
+        except ImageFileDeleteException:
+            self._services.logger.error(f"Failed to delete image files")
+            raise
+        except Exception as e:
+            self._services.logger.error("Problem deleting image records and files")
+            raise e
+
     def _get_metadata(
         self, session_id: Optional[str] = None, node_id: Optional[str] = None
-    ) -> Union[ImageMetadata, None]:
+    ) -> Optional[ImageMetadata]:
         """Get the metadata for a node."""
         metadata = None
 

invokeai/app/services/invocation_queue.py

@@ -5,7 +5,7 @@ from abc import ABC, abstractmethod
 from queue import Queue
 
 from pydantic import BaseModel, Field
-
+from typing import Optional
 
 class InvocationQueueItem(BaseModel):
     graph_execution_state_id: str = Field(description="The ID of the graph execution state")
@@ -22,7 +22,7 @@ class InvocationQueueABC(ABC):
         pass
 
     @abstractmethod
-    def put(self, item: InvocationQueueItem | None) -> None:
+    def put(self, item: Optional[InvocationQueueItem]) -> None:
         pass
 
     @abstractmethod
@@ -57,7 +57,7 @@ class MemoryInvocationQueue(InvocationQueueABC):
 
         return item
 
-    def put(self, item: InvocationQueueItem | None) -> None:
+    def put(self, item: Optional[InvocationQueueItem]) -> None:
         self.__queue.put(item)
 
     def cancel(self, graph_execution_state_id: str) -> None:

invokeai/app/services/invocation_services.py

@@ -4,8 +4,10 @@ from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from logging import Logger
-    from invokeai.app.services.images import ImageService
-    from invokeai.backend import ModelManager
+    from invokeai.app.services.board_images import BoardImagesServiceABC
+    from invokeai.app.services.boards import BoardServiceABC
+    from invokeai.app.services.images import ImageServiceABC
+    from invokeai.app.services.model_manager_service import ModelManagerServiceBase
     from invokeai.app.services.events import EventServiceBase
     from invokeai.app.services.latent_storage import LatentsStorageBase
     from invokeai.app.services.restoration_services import RestorationServices
@@ -20,41 +22,47 @@ class InvocationServices:
     """Services that can be used by invocations"""
 
     # TODO: Just forward-declared everything due to circular dependencies. Fix structure.
-    events: "EventServiceBase"
-    latents: "LatentsStorageBase"
-    queue: "InvocationQueueABC"
-    model_manager: "ModelManager"
-    restoration: "RestorationServices"
+    board_images: "BoardImagesServiceABC"
+    boards: "BoardServiceABC"
     configuration: "InvokeAISettings"
-    images: "ImageService"
-
-    # NOTE: we must forward-declare any types that include invocations, since invocations can use services
-    graph_library: "ItemStorageABC"["LibraryGraph"]
+    events: "EventServiceBase"
     graph_execution_manager: "ItemStorageABC"["GraphExecutionState"]
+    graph_library: "ItemStorageABC"["LibraryGraph"]
+    images: "ImageServiceABC"
+    latents: "LatentsStorageBase"
+    logger: "Logger"
+    model_manager: "ModelManagerServiceBase"
     processor: "InvocationProcessorABC"
+    queue: "InvocationQueueABC"
+    restoration: "RestorationServices"
 
     def __init__(
         self,
-        model_manager: "ModelManager",
-        events: "EventServiceBase",
-        logger: "Logger",
-        latents: "LatentsStorageBase",
-        images: "ImageService",
-        queue: "InvocationQueueABC",
-        graph_library: "ItemStorageABC"["LibraryGraph"],
-        graph_execution_manager: "ItemStorageABC"["GraphExecutionState"],
-        processor: "InvocationProcessorABC",
-        restoration: "RestorationServices",
+        board_images: "BoardImagesServiceABC",
+        boards: "BoardServiceABC",
         configuration: "InvokeAISettings",
+        events: "EventServiceBase",
+        graph_execution_manager: "ItemStorageABC"["GraphExecutionState"],
+        graph_library: "ItemStorageABC"["LibraryGraph"],
+        images: "ImageServiceABC",
+        latents: "LatentsStorageBase",
+        logger: "Logger",
+        model_manager: "ModelManagerServiceBase",
+        processor: "InvocationProcessorABC",
+        queue: "InvocationQueueABC",
+        restoration: "RestorationServices",
     ):
-        self.model_manager = model_manager
-        self.events = events
-        self.logger = logger
-        self.latents = latents
-        self.images = images
-        self.queue = queue
-        self.graph_library = graph_library
-        self.graph_execution_manager = graph_execution_manager
-        self.processor = processor
-        self.restoration = restoration
+        self.board_images = board_images
+        self.boards = boards
+        self.boards = boards
         self.configuration = configuration
+        self.events = events
+        self.graph_execution_manager = graph_execution_manager
+        self.graph_library = graph_library
+        self.images = images
+        self.latents = latents
+        self.logger = logger
+        self.model_manager = model_manager
+        self.processor = processor
+        self.queue = queue
+        self.restoration = restoration

invokeai/app/services/invoker.py

@@ -1,14 +1,11 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from abc import ABC
-from threading import Event, Thread
+from typing import Optional
 
-from ..invocations.baseinvocation import InvocationContext
 from .graph import Graph, GraphExecutionState
-from .invocation_queue import InvocationQueueABC, InvocationQueueItem
+from .invocation_queue import InvocationQueueItem
 from .invocation_services import InvocationServices
-from .item_storage import ItemStorageABC
-
 
 class Invoker:
     """The invoker, used to execute invocations"""
@@ -21,7 +18,7 @@ class Invoker:
 
     def invoke(
         self, graph_execution_state: GraphExecutionState, invoke_all: bool = False
-    ) -> str | None:
+    ) -> Optional[str]:
         """Determines the next node to invoke and enqueues it, preparing if needed.
         Returns the id of the queued node, or `None` if there are no nodes left to enqueue."""
 
@@ -45,7 +42,7 @@ class Invoker:
 
         return invocation.id
 
-    def create_execution_state(self, graph: Graph | None = None) -> GraphExecutionState:
+    def create_execution_state(self, graph: Optional[Graph] = None) -> GraphExecutionState:
         """Creates a new execution state for the given graph"""
         new_state = GraphExecutionState(graph=Graph() if graph is None else graph)
         self.services.graph_execution_manager.set(new_state)

invokeai/app/services/latent_storage.py

@@ -1,10 +1,9 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-import os
 from abc import ABC, abstractmethod
 from pathlib import Path
 from queue import Queue
-from typing import Dict
+from typing import Dict, Union, Optional
 
 import torch
 
@@ -56,7 +55,7 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
         if name in self.__cache:
             del self.__cache[name]
 
-    def __get_cache(self, name: str) -> torch.Tensor|None:
+    def __get_cache(self, name: str) -> Optional[torch.Tensor]:
         return None if name not in self.__cache else self.__cache[name]
 
     def __set_cache(self, name: str, data: torch.Tensor):
@@ -70,24 +69,26 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
 class DiskLatentsStorage(LatentsStorageBase):
     """Stores latents in a folder on disk without caching"""
 
-    __output_folder: str
+    __output_folder: Union[str, Path]
 
-    def __init__(self, output_folder: str):
-        self.__output_folder = output_folder
-        Path(output_folder).mkdir(parents=True, exist_ok=True)
+    def __init__(self, output_folder: Union[str, Path]):
+        self.__output_folder = output_folder if isinstance(output_folder, Path) else Path(output_folder)
+        self.__output_folder.mkdir(parents=True, exist_ok=True)
 
     def get(self, name: str) -> torch.Tensor:
         latent_path = self.get_path(name)
         return torch.load(latent_path)
 
     def save(self, name: str, data: torch.Tensor) -> None:
+        self.__output_folder.mkdir(parents=True, exist_ok=True)
         latent_path = self.get_path(name)
         torch.save(data, latent_path)
 
     def delete(self, name: str) -> None:
         latent_path = self.get_path(name)
-        os.remove(latent_path)
+        latent_path.unlink()
+        
 
-    def get_path(self, name: str) -> str:
-        return os.path.join(self.__output_folder, name)
-    
+    def get_path(self, name: str) -> Path:
+        return self.__output_folder / name
+    

invokeai/app/services/metadata.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Union
+from typing import Any, Optional
 import networkx as nx
 
 from invokeai.app.models.metadata import ImageMetadata
@@ -34,7 +34,7 @@ class CoreMetadataService(MetadataServiceBase):
 
         return metadata
 
-    def _find_nearest_ancestor(self, G: nx.DiGraph, node_id: str) -> Union[str, None]:
+    def _find_nearest_ancestor(self, G: nx.DiGraph, node_id: str) -> Optional[str]:
         """
         Finds the id of the nearest ancestor (of a valid type) of a given node.
 
@@ -65,7 +65,7 @@ class CoreMetadataService(MetadataServiceBase):
 
     def _get_additional_metadata(
         self, graph: Graph, node_id: str
-    ) -> Union[dict[str, Any], None]:
+    ) -> Optional[dict[str, Any]]:
         """
         Returns additional metadata for a given node.
 

invokeai/app/services/model_manager_initializer.py

@@ -1,104 +0,0 @@
-import os
-import sys
-import torch
-from argparse import Namespace
-from omegaconf import OmegaConf
-from pathlib import Path
-from typing import types
-
-import invokeai.version
-from .config import InvokeAISettings
-from ...backend import ModelManager
-from ...backend.util import choose_precision, choose_torch_device
-
-# TODO: Replace with an abstract class base ModelManagerBase
-def get_model_manager(config: InvokeAISettings, logger: types.ModuleType) -> ModelManager:
-    model_config = config.model_conf_path
-    if not model_config.exists():
-        report_model_error(
-            config, FileNotFoundError(f"The file {model_config} could not be found."), logger
-        )
-
-    logger.info(f"{invokeai.version.__app_name__}, version {invokeai.version.__version__}")
-    logger.info(f'InvokeAI runtime directory is "{config.root}"')
-
-    # these two lines prevent a horrible warning message from appearing
-    # when the frozen CLIP tokenizer is imported
-    import transformers  # type: ignore
-
-    transformers.logging.set_verbosity_error()
-    import diffusers
-
-    diffusers.logging.set_verbosity_error()
-    embedding_path = config.embedding_path
-
-    # migrate legacy models
-    ModelManager.migrate_models()
-
-    # creating the model manager
-    try:
-        device = torch.device(choose_torch_device())
-        precision = 'float16' if config.precision=='float16' \
-        else 'float32' if config.precision=='float32' \
-        else choose_precision(device)
-        
-        model_manager = ModelManager(
-            OmegaConf.load(config.model_conf_path),
-            precision=precision,
-            device_type=device,
-            max_loaded_models=config.max_loaded_models,
-            embedding_path = embedding_path,
-            logger = logger,
-        )
-    except (FileNotFoundError, TypeError, AssertionError) as e:
-        report_model_error(config, e, logger)
-    except (IOError, KeyError) as e:
-        logger.error(f"{e}. Aborting.")
-        sys.exit(-1)
-
-    # try to autoconvert new models
-    # autoimport new .ckpt files
-    if config.autoconvert_path:
-        model_manager.heuristic_import(
-            config.autoconvert_path,
-        )
-    return model_manager
-
-def report_model_error(opt: Namespace, e: Exception, logger: types.ModuleType):
-    logger.error(f'An error occurred while attempting to initialize the model: "{str(e)}"')
-    logger.error(
-        "This can be caused by a missing or corrupted models file, and can sometimes be fixed by (re)installing the models."
-    )
-    yes_to_all = os.environ.get("INVOKE_MODEL_RECONFIGURE")
-    if yes_to_all:
-        logger.warning(
-            "Reconfiguration is being forced by environment variable INVOKE_MODEL_RECONFIGURE"
-        )
-    else:
-        response = input(
-            "Do you want to run invokeai-configure script to select and/or reinstall models? [y] "
-        )
-        if response.startswith(("n", "N")):
-            return
-
-    logger.info("invokeai-configure is launching....\n")
-
-    # Match arguments that were set on the CLI
-    # only the arguments accepted by the configuration script are parsed
-    root_dir = ["--root", opt.root_dir] if opt.root_dir is not None else []
-    config = ["--config", opt.conf] if opt.conf is not None else []
-    sys.argv = ["invokeai-configure"]
-    sys.argv.extend(root_dir)
-    sys.argv.extend(config.to_dict())
-    if yes_to_all is not None:
-        for arg in yes_to_all.split():
-            sys.argv.append(arg)
-
-    from invokeai.frontend.install import invokeai_configure
-
-    invokeai_configure()
-    # TODO: Figure out how to restart
-    # print('** InvokeAI will now restart')
-    # sys.argv = previous_args
-    # main() # would rather do a os.exec(), but doesn't exist?
-    # sys.exit(0)

invokeai/app/services/model_manager_service.py

@@ -0,0 +1,562 @@
+# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from pathlib import Path
+from pydantic import Field
+from typing import Optional, Union, Callable, List, Tuple, TYPE_CHECKING
+from types import ModuleType
+
+from invokeai.backend.model_management import (
+    ModelManager,
+    BaseModelType,
+    ModelType,
+    SubModelType,
+    ModelInfo,
+    AddModelResult,
+    SchedulerPredictionType,
+    ModelMerger,
+    MergeInterpolationMethod,
+)
+
+
+import torch
+from invokeai.app.models.exceptions import CanceledException
+from ...backend.util import choose_precision, choose_torch_device
+from .config import InvokeAIAppConfig
+
+if TYPE_CHECKING:
+    from ..invocations.baseinvocation import BaseInvocation, InvocationContext
+
+
+class ModelManagerServiceBase(ABC):
+    """Responsible for managing models on disk and in memory"""
+
+    @abstractmethod
+    def __init__(
+        self,
+        config: InvokeAIAppConfig,
+        logger: ModuleType,
+    ):
+        """
+        Initialize with the path to the models.yaml config file.
+        Optional parameters are the torch device type, precision, max_models,
+        and sequential_offload boolean. Note that the default device
+        type and precision are set up for a CUDA system running at half precision.
+        """
+        pass
+
+    @abstractmethod
+    def get_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+        node: Optional[BaseInvocation] = None,
+        context: Optional[InvocationContext] = None,
+    ) -> ModelInfo:
+        """Retrieve the indicated model with name and type.
+        submodel can be used to get a part (such as the vae)
+        of a diffusers pipeline."""
+        pass
+
+    @property
+    @abstractmethod
+    def logger(self):
+        pass
+
+    @abstractmethod
+    def model_exists(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
+        pass
+
+    @abstractmethod
+    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Given a model name returns a dict-like (OmegaConf) object describing it.
+        Uses the exact format as the omegaconf stanza.
+        """
+        pass
+
+    @abstractmethod
+    def list_models(self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None) -> dict:
+        """
+        Return a dict of models in the format:
+        { model_type1:
+          { model_name1: {'status': 'active'|'cached'|'not loaded',
+                         'model_name' : name,
+                         'model_type' : SDModelType,
+                         'description': description,
+                         'format': 'folder'|'safetensors'|'ckpt'
+                         },
+            model_name2: { etc }
+          },
+          model_type2:
+            { model_name_n: etc
+        }
+        """
+        pass
+    
+    @abstractmethod
+    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Return information about the model using the same format as list_models()
+        """
+        pass
+
+    @abstractmethod
+    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
+        """
+        Returns a list of all the model names known.
+        """
+        pass
+
+    @abstractmethod
+    def add_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+        clobber: bool = False
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with an
+        assertion error if the name already exists. Pass clobber=True to overwrite.
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        pass
+
+    @abstractmethod
+    def update_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with a
+        KeyErrorException if the name does not already exist.
+
+        On a successful update, the config will be changed in memory. Will fail 
+        with an assertion error if provided attributes are incorrect or 
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        pass
+    
+    @abstractmethod
+    def del_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ):
+        """
+        Delete the named model from configuration. If delete_files is true,
+        then the underlying weight file or diffusers directory will be deleted
+        as well. Call commit() to write to disk.
+        """
+        pass
+
+    @abstractmethod
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Union[ModelType.Main,ModelType.Vae],
+    ) -> AddModelResult:
+        """
+        Convert a checkpoint file into a diffusers folder, deleting the cached
+        version and deleting the original checkpoint file if it is in the models
+        directory.
+        :param model_name: Name of the model to convert
+        :param base_model: Base model type
+        :param model_type: Type of model ['vae' or 'main']
+
+        This will raise a ValueError unless the model is not a checkpoint. It will
+        also raise a ValueError in the event that there is a similarly-named diffusers
+        directory already in place.
+        """
+        pass
+
+    @abstractmethod
+    def heuristic_import(self,
+                         items_to_import: set[str],
+                         prediction_type_helper: Optional[Callable[[Path],SchedulerPredictionType]]=None,
+                         )->dict[str, AddModelResult]:
+        '''Import a list of paths, repo_ids or URLs. Returns the set of
+        successfully imported items.
+        :param items_to_import: Set of strings corresponding to models to be imported.
+        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+
+        The prediction type helper is necessary to distinguish between
+        models based on Stable Diffusion 2 Base (requiring
+        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
+        (requiring SchedulerPredictionType.VPrediction). It is
+        generally impossible to do this programmatically, so the
+        prediction_type_helper usually asks the user to choose.
+
+        The result is a set of successfully installed models. Each element
+        of the set is a dict corresponding to the newly-created OmegaConf stanza for
+        that model.
+        '''
+        pass
+
+    @abstractmethod
+    def merge_models(
+            self,
+            model_names: List[str] = Field(default=None, min_items=2, max_items=3, description="List of model names to merge"),
+            base_model: Union[BaseModelType,str] = Field(default=None, description="Base model shared by all models to be merged"),
+            merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
+            alpha: Optional[float] = 0.5,
+            interp: Optional[MergeInterpolationMethod] = None,
+            force: Optional[bool] = False,
+    ) -> AddModelResult:
+        """
+        Merge two to three diffusrs pipeline models and save as a new model.
+        :param model_names: List of 2-3 models to merge
+        :param base_model: Base model to use for all models
+        :param merged_model_name: Name of destination merged model
+        :param alpha: Alpha strength to apply to 2d and 3d model
+        :param interp: Interpolation method. None (default) 
+        """
+        pass
+    
+    @abstractmethod
+    def commit(self, conf_file: Optional[Path] = None) -> None:
+        """
+        Write current configuration out to the indicated file.
+        If no conf_file is provided, then replaces the
+        original file/database used to initialize the object.
+        """
+        pass
+
+# simple implementation
+class ModelManagerService(ModelManagerServiceBase):
+    """Responsible for managing models on disk and in memory"""
+    def __init__(
+        self,
+        config: InvokeAIAppConfig,
+        logger: ModuleType,
+    ):
+        """
+        Initialize with the path to the models.yaml config file.
+        Optional parameters are the torch device type, precision, max_models,
+        and sequential_offload boolean. Note that the default device
+        type and precision are set up for a CUDA system running at half precision.
+        """
+        if config.model_conf_path and config.model_conf_path.exists():
+            config_file = config.model_conf_path
+        else:
+            config_file = config.root_dir / "configs/models.yaml"
+        if not config_file.exists():
+            raise IOError(f"The file {config_file} could not be found.")
+
+        logger.debug(f'config file={config_file}')
+
+        device = torch.device(choose_torch_device())
+        logger.debug(f'GPU device = {device}')
+
+        precision = config.precision
+        if precision == "auto":
+            precision = choose_precision(device)
+        dtype = torch.float32 if precision == 'float32' else torch.float16
+
+        # this is transitional backward compatibility
+        # support for the deprecated `max_loaded_models`
+        # configuration value. If present, then the
+        # cache size is set to 2.5 GB times
+        # the number of max_loaded_models. Otherwise
+        # use new `max_cache_size` config setting
+        max_cache_size = config.max_cache_size \
+            if hasattr(config,'max_cache_size') \
+               else config.max_loaded_models * 2.5
+
+        logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
+
+        sequential_offload = config.sequential_guidance
+
+        self.mgr = ModelManager(
+            config=config_file,
+            device_type=device,
+            precision=dtype,
+            max_cache_size=max_cache_size,
+            sequential_offload=sequential_offload,
+            logger=logger,
+        )
+        logger.info('Model manager service initialized')
+
+    def get_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+        node: Optional[BaseInvocation] = None,
+        context: Optional[InvocationContext] = None,
+    ) -> ModelInfo:
+        """
+        Retrieve the indicated model. submodel can be used to get a
+        part (such as the vae) of a diffusers mode.
+        """
+
+        # if we are called from within a node, then we get to emit
+        # load start and complete events
+        if node and context:
+            self._emit_load_event(
+                node=node,
+                context=context,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            )
+
+        model_info = self.mgr.get_model(
+            model_name,
+            base_model,
+            model_type,
+            submodel,
+        )
+
+        if node and context:
+            self._emit_load_event(
+                node=node,
+                context=context,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                model_info=model_info
+            )
+
+        return model_info
+
+    def model_exists(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
+        """
+        Given a model name, returns True if it is a valid
+        identifier.
+        """
+        return self.mgr.model_exists(
+            model_name,
+            base_model,
+            model_type,
+        )
+
+    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Given a model name returns a dict-like (OmegaConf) object describing it.
+        """
+        return self.mgr.model_info(model_name, base_model, model_type)
+
+    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
+        """
+        Returns a list of all the model names known.
+        """
+        return self.mgr.model_names()
+
+    def list_models(
+        self,
+        base_model: Optional[BaseModelType] = None,
+        model_type: Optional[ModelType] = None
+    ) -> list[dict]:
+        """
+        Return a list of models.
+        """
+        return self.mgr.list_models(base_model, model_type)
+
+    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
+        """
+        Return information about the model using the same format as list_models()
+        """
+        return self.mgr.list_model(model_name=model_name,
+                                   base_model=base_model,
+                                   model_type=model_type)
+
+    def add_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+        clobber: bool = False,
+    )->None:
+        """
+        Update the named model with a dictionary of attributes. Will fail with an
+        assertion error if the name already exists. Pass clobber=True to overwrite.
+        On a successful update, the config will be changed in memory. Will fail
+        with an assertion error if provided attributes are incorrect or
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        self.logger.debug(f'add/update model {model_name}')        
+        return self.mgr.add_model(model_name, base_model, model_type, model_attributes, clobber)
+
+    def update_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        model_attributes: dict,
+    ) -> AddModelResult:
+        """
+        Update the named model with a dictionary of attributes. Will fail with a
+        KeyError exception if the name does not already exist.
+        On a successful update, the config will be changed in memory. Will fail 
+        with an assertion error if provided attributes are incorrect or 
+        the model name is missing. Call commit() to write changes to disk.
+        """
+        self.logger.debug(f'update model {model_name}')
+        if not self.model_exists(model_name, base_model, model_type):
+            raise KeyError(f"Unknown model {model_name}")
+        return self.add_model(model_name, base_model, model_type, model_attributes, clobber=True)
+    
+    def del_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ):
+        """
+        Delete the named model from configuration. If delete_files is true,
+        then the underlying weight file or diffusers directory will be deleted
+        as well. Call commit() to write to disk.
+        """
+        self.logger.debug(f'delete model {model_name}')
+        self.mgr.del_model(model_name, base_model, model_type)
+
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Union[ModelType.Main,ModelType.Vae],
+    ) -> AddModelResult:
+        """
+        Convert a checkpoint file into a diffusers folder, deleting the cached
+        version and deleting the original checkpoint file if it is in the models
+        directory.
+        :param model_name: Name of the model to convert
+        :param base_model: Base model type
+        :param model_type: Type of model ['vae' or 'main']
+
+        This will raise a ValueError unless the model is not a checkpoint. It will
+        also raise a ValueError in the event that there is a similarly-named diffusers
+        directory already in place.
+        """
+        self.logger.debug(f'convert model {model_name}')        
+        return self.mgr.convert_model(model_name, base_model, model_type)
+
+    def commit(self, conf_file: Optional[Path]=None):
+        """
+        Write current configuration out to the indicated file.
+        If no conf_file is provided, then replaces the
+        original file/database used to initialize the object.
+        """
+        return self.mgr.commit(conf_file)
+
+    def _emit_load_event(
+        self,
+        node,
+        context,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: SubModelType,
+        model_info: Optional[ModelInfo] = None,
+    ):
+        if context.services.queue.is_canceled(context.graph_execution_state_id):
+            raise CanceledException()
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[node.id]
+        if model_info:
+            context.services.events.emit_model_load_completed(
+                graph_execution_state_id=context.graph_execution_state_id,
+                node=node.dict(),
+                source_node_id=source_node_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                model_info=model_info
+            )
+        else:
+            context.services.events.emit_model_load_started(
+                graph_execution_state_id=context.graph_execution_state_id,
+                node=node.dict(),
+                source_node_id=source_node_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            )
+
+
+    @property
+    def logger(self):
+        return self.mgr.logger
+
+    def heuristic_import(self,
+                         items_to_import: set[str],
+                         prediction_type_helper: Optional[Callable[[Path],SchedulerPredictionType]]=None,
+                         )->dict[str, AddModelResult]:
+        '''Import a list of paths, repo_ids or URLs. Returns the set of
+        successfully imported items.
+        :param items_to_import: Set of strings corresponding to models to be imported.
+        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+
+        The prediction type helper is necessary to distinguish between
+        models based on Stable Diffusion 2 Base (requiring
+        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
+        (requiring SchedulerPredictionType.VPrediction). It is
+        generally impossible to do this programmatically, so the
+        prediction_type_helper usually asks the user to choose.
+
+        The result is a set of successfully installed models. Each element
+        of the set is a dict corresponding to the newly-created OmegaConf stanza for
+        that model.
+        '''
+        return self.mgr.heuristic_import(items_to_import, prediction_type_helper)        
+
+    def merge_models(
+            self,
+            model_names: List[str] = Field(default=None, min_items=2, max_items=3, description="List of model names to merge"),
+            base_model: Union[BaseModelType,str] = Field(default=None, description="Base model shared by all models to be merged"),
+            merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
+            alpha: Optional[float] = 0.5,
+            interp: Optional[MergeInterpolationMethod] = None,
+            force: Optional[bool] = False,
+    ) -> AddModelResult:
+        """
+        Merge two to three diffusrs pipeline models and save as a new model.
+        :param model_names: List of 2-3 models to merge
+        :param base_model: Base model to use for all models
+        :param merged_model_name: Name of destination merged model
+        :param alpha: Alpha strength to apply to 2d and 3d model
+        :param interp: Interpolation method. None (default) 
+        """
+        merger = ModelMerger(self.mgr)
+        try:
+            result = merger.merge_diffusion_models_and_save(
+                model_names = model_names,
+                base_model = base_model,
+                merged_model_name = merged_model_name,
+                alpha = alpha,
+                interp = interp,
+                force = force,
+            )
+        except AssertionError as e:
+            raise ValueError(e)
+        return result

invokeai/app/services/models/board_record.py

@@ -0,0 +1,62 @@
+from typing import Optional, Union
+from datetime import datetime
+from pydantic import BaseModel, Extra, Field, StrictBool, StrictStr
+from invokeai.app.util.misc import get_iso_timestamp
+
+
+class BoardRecord(BaseModel):
+    """Deserialized board record."""
+
+    board_id: str = Field(description="The unique ID of the board.")
+    """The unique ID of the board."""
+    board_name: str = Field(description="The name of the board.")
+    """The name of the board."""
+    created_at: Union[datetime, str] = Field(
+        description="The created timestamp of the board."
+    )
+    """The created timestamp of the image."""
+    updated_at: Union[datetime, str] = Field(
+        description="The updated timestamp of the board."
+    )
+    """The updated timestamp of the image."""
+    deleted_at: Union[datetime, str, None] = Field(
+        description="The deleted timestamp of the board."
+    )
+    """The updated timestamp of the image."""
+    cover_image_name: Optional[str] = Field(
+        description="The name of the cover image of the board."
+    )
+    """The name of the cover image of the board."""
+
+
+class BoardDTO(BoardRecord):
+    """Deserialized board record with cover image URL and image count."""
+
+    cover_image_name: Optional[str] = Field(
+        description="The name of the board's cover image."
+    )
+    """The URL of the thumbnail of the most recent image in the board."""
+    image_count: int = Field(description="The number of images in the board.")
+    """The number of images in the board."""
+
+
+def deserialize_board_record(board_dict: dict) -> BoardRecord:
+    """Deserializes a board record."""
+
+    # Retrieve all the values, setting "reasonable" defaults if they are not present.
+
+    board_id = board_dict.get("board_id", "unknown")
+    board_name = board_dict.get("board_name", "unknown")
+    cover_image_name = board_dict.get("cover_image_name", "unknown")
+    created_at = board_dict.get("created_at", get_iso_timestamp())
+    updated_at = board_dict.get("updated_at", get_iso_timestamp())
+    deleted_at = board_dict.get("deleted_at", get_iso_timestamp())
+
+    return BoardRecord(
+        board_id=board_id,
+        board_name=board_name,
+        cover_image_name=cover_image_name,
+        created_at=created_at,
+        updated_at=updated_at,
+        deleted_at=deleted_at,
+    )

invokeai/app/services/models/image_record.py

@@ -79,8 +79,6 @@ class ImageUrlsDTO(BaseModel):
 
     image_name: str = Field(description="The unique name of the image.")
     """The unique name of the image."""
-    image_origin: ResourceOrigin = Field(description="The type of the image.")
-    """The origin of the image."""
     image_url: str = Field(description="The URL of the image.")
     """The URL of the image."""
     thumbnail_url: str = Field(description="The URL of the image's thumbnail.")
@@ -88,19 +86,24 @@ class ImageUrlsDTO(BaseModel):
 
 
 class ImageDTO(ImageRecord, ImageUrlsDTO):
-    """Deserialized image record, enriched for the frontend with URLs."""
+    """Deserialized image record, enriched for the frontend."""
 
+    board_id: Optional[str] = Field(
+        description="The id of the board the image belongs to, if one exists."
+    )
+    """The id of the board the image belongs to, if one exists."""
     pass
 
 
 def image_record_to_dto(
-    image_record: ImageRecord, image_url: str, thumbnail_url: str
+    image_record: ImageRecord, image_url: str, thumbnail_url: str, board_id: Optional[str]
 ) -> ImageDTO:
     """Converts an image record to an image DTO."""
     return ImageDTO(
         **image_record.dict(),
         image_url=image_url,
         thumbnail_url=thumbnail_url,
+        board_id=board_id,
     )
 
 

invokeai/app/services/restoration_services.py

@@ -16,13 +16,14 @@ class RestorationServices:
             gfpgan, codeformer, esrgan = None, None, None
             if args.restore or args.esrgan:
                 restoration = Restoration()
-                if args.restore:
+                # TODO: redo for new model structure
+                if False and args.restore:
                     gfpgan, codeformer = restoration.load_face_restore_models(
                         args.gfpgan_model_path
                     )
                 else:
                     logger.info("Face restoration disabled")
-                    if args.esrgan:
+                    if False and args.esrgan:
                         esrgan = restoration.load_esrgan(args.esrgan_bg_tile)
                     else:
                         logger.info("Upscaling disabled")

invokeai/app/services/sqlite.py

@@ -1,6 +1,6 @@
 import sqlite3
 from threading import Lock
-from typing import Generic, TypeVar, Union, get_args
+from typing import Generic, TypeVar, Optional, Union, get_args
 
 from pydantic import BaseModel, parse_raw_as
 
@@ -63,7 +63,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
             self._lock.release()
         self._on_changed(item)
 
-    def get(self, id: str) -> Union[T, None]:
+    def get(self, id: str) -> Optional[T]:
         try:
             self._lock.acquire()
             self._cursor.execute(

invokeai/app/services/urls.py

@@ -1,17 +1,12 @@
 import os
 from abc import ABC, abstractmethod
 
-from invokeai.app.models.image import ResourceOrigin
-from invokeai.app.util.thumbnails import get_thumbnail_name
-
 
 class UrlServiceBase(ABC):
     """Responsible for building URLs for resources."""
 
     @abstractmethod
-    def get_image_url(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_image_url(self, image_name: str, thumbnail: bool = False) -> str:
         """Gets the URL for an image or thumbnail."""
         pass
 
@@ -20,15 +15,11 @@ class LocalUrlService(UrlServiceBase):
     def __init__(self, base_url: str = "api/v1"):
         self._base_url = base_url
 
-    def get_image_url(
-        self, image_origin: ResourceOrigin, image_name: str, thumbnail: bool = False
-    ) -> str:
+    def get_image_url(self, image_name: str, thumbnail: bool = False) -> str:
         image_basename = os.path.basename(image_name)
 
         # These paths are determined by the routes in invokeai/app/api/routers/images.py
         if thumbnail:
-            return (
-                f"{self._base_url}/images/{image_origin.value}/{image_basename}/thumbnail"
-            )
+            return f"{self._base_url}/images/{image_basename}/thumbnail"
 
-        return f"{self._base_url}/images/{image_origin.value}/{image_basename}"
+        return f"{self._base_url}/images/{image_basename}"

invokeai/backend/__init__.py

@@ -5,9 +5,11 @@ from .generator import (
     InvokeAIGeneratorBasicParams,
     InvokeAIGenerator,
     InvokeAIGeneratorOutput,
-    Txt2Img,
     Img2Img,
     Inpaint
 )
-from .model_management import ModelManager, SDModelComponent
+from .model_management import (
+    ModelManager, ModelCache, BaseModelType,
+    ModelType, SubModelType, ModelInfo
+    )
 from .safety_checker import SafetyChecker

invokeai/backend/generator/__init__.py

@@ -5,7 +5,6 @@ from .base import (
     InvokeAIGenerator,
     InvokeAIGeneratorBasicParams,
     InvokeAIGeneratorOutput,
-    Txt2Img,
     Img2Img,
     Inpaint,
     Generator,

invokeai/backend/generator/base.py

@@ -21,7 +21,7 @@ from PIL import Image, ImageChops, ImageFilter
 from accelerate.utils import set_seed
 from diffusers import DiffusionPipeline
 from tqdm import trange
-from typing import Callable, List, Iterator, Optional, Type
+from typing import Callable, List, Iterator, Optional, Type, Union
 from dataclasses import dataclass, field
 from diffusers.schedulers import SchedulerMixin as Scheduler
 
@@ -29,7 +29,6 @@ import invokeai.backend.util.logging as logger
 from ..image_util import configure_model_padding
 from ..util.util import rand_perlin_2d
 from ..safety_checker import SafetyChecker
-from ..prompting.conditioning import get_uc_and_c_and_ec
 from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
 from ..stable_diffusion.schedulers import SCHEDULER_MAP
 
@@ -81,13 +80,15 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         self.params=params
         self.kwargs = kwargs
 
-    def generate(self,
-                 prompt: str='',
-                 callback: Optional[Callable]=None,
-                 step_callback: Optional[Callable]=None,
-                 iterations: int=1,
-                 **keyword_args,
-                 )->Iterator[InvokeAIGeneratorOutput]:
+    def generate(
+        self,
+        conditioning: tuple,
+        scheduler,
+        callback: Optional[Callable]=None,
+        step_callback: Optional[Callable]=None,
+        iterations: int=1,
+        **keyword_args,
+    )->Iterator[InvokeAIGeneratorOutput]:
         '''
         Return an iterator across the indicated number of generations.
         Each time the iterator is called it will return an InvokeAIGeneratorOutput
@@ -113,54 +114,46 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         generator_args.update(keyword_args)
 
         model_info = self.model_info
-        model_name = model_info['model_name']
-        model:StableDiffusionGeneratorPipeline = model_info['model']
-        model_hash = model_info['hash']
-        scheduler: Scheduler = self.get_scheduler(
-            model=model,
-            scheduler_name=generator_args.get('scheduler')
-        )
+        model_name = model_info.name
+        model_hash = model_info.hash
+        with model_info.context as model:
+            gen_class = self._generator_class()
+            generator = gen_class(model, self.params.precision, **self.kwargs)
+            if self.params.variation_amount > 0:
+                generator.set_variation(generator_args.get('seed'),
+                                        generator_args.get('variation_amount'),
+                                        generator_args.get('with_variations')
+                                        )
 
-        # get conditioning from prompt via Compel package
-        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(prompt, model=model)
-
-        gen_class = self._generator_class()
-        generator = gen_class(model, self.params.precision, **self.kwargs)
-        if self.params.variation_amount > 0:
-            generator.set_variation(generator_args.get('seed'),
-                                    generator_args.get('variation_amount'),
-                                    generator_args.get('with_variations')
-                                    )
-
-        if isinstance(model, DiffusionPipeline):
-            for component in [model.unet, model.vae]:
-                configure_model_padding(component,
+            if isinstance(model, DiffusionPipeline):
+                for component in [model.unet, model.vae]:
+                    configure_model_padding(component,
+                                            generator_args.get('seamless',False),
+                                            generator_args.get('seamless_axes')
+                                            )
+            else:
+                configure_model_padding(model,
                                         generator_args.get('seamless',False),
                                         generator_args.get('seamless_axes')
                                         )
-        else:
-            configure_model_padding(model,
-                                    generator_args.get('seamless',False),
-                                    generator_args.get('seamless_axes')
-                                    )
 
-        iteration_count = range(iterations) if iterations else itertools.count(start=0, step=1)
-        for i in iteration_count:
-            results = generator.generate(prompt,
-                                         conditioning=(uc, c, extra_conditioning_info),
-                                         step_callback=step_callback,
-                                         sampler=scheduler,
-                                         **generator_args,
-                                         )
-            output = InvokeAIGeneratorOutput(
-                image=results[0][0],
-                seed=results[0][1],
-                attention_maps_images=results[0][2],
-                model_hash = model_hash,
-                params=Namespace(model_name=model_name,**generator_args),
-            )
-            if callback:
-                callback(output)
+            iteration_count = range(iterations) if iterations else itertools.count(start=0, step=1)
+            for i in iteration_count:
+                results = generator.generate(
+                    conditioning=conditioning,
+                    step_callback=step_callback,
+                    sampler=scheduler,
+                    **generator_args,
+                )
+                output = InvokeAIGeneratorOutput(
+                    image=results[0][0],
+                    seed=results[0][1],
+                    attention_maps_images=results[0][2],
+                    model_hash = model_hash,
+                    params=Namespace(model_name=model_name,**generator_args),
+                )
+                if callback:
+                    callback(output)
             yield output
 
     @classmethod
@@ -173,20 +166,6 @@ class InvokeAIGenerator(metaclass=ABCMeta):
     def load_generator(self, model: StableDiffusionGeneratorPipeline, generator_class: Type[Generator]):
         return generator_class(model, self.params.precision)
 
-    def get_scheduler(self, scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-        scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
-        
-        scheduler_config = model.scheduler.config
-        if "_backup" in scheduler_config:
-            scheduler_config = scheduler_config["_backup"]
-        scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
-        scheduler = scheduler_class.from_config(scheduler_config)
-        
-        # hack copied over from generate.py
-        if not hasattr(scheduler, 'uses_inpainting_model'):
-            scheduler.uses_inpainting_model = lambda: False
-        return scheduler
-
     @classmethod
     def _generator_class(cls)->Type[Generator]:
         '''
@@ -196,17 +175,10 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         '''
         return Generator
 
-# ------------------------------------
-class Txt2Img(InvokeAIGenerator):
-    @classmethod
-    def _generator_class(cls):
-        from .txt2img import Txt2Img
-        return Txt2Img
-
 # ------------------------------------
 class Img2Img(InvokeAIGenerator):
     def generate(self,
-               init_image: Image.Image | torch.FloatTensor,
+               init_image: Union[Image.Image, torch.FloatTensor],
                strength: float=0.75,
                **keyword_args
                )->Iterator[InvokeAIGeneratorOutput]:
@@ -223,7 +195,7 @@ class Img2Img(InvokeAIGenerator):
 # Takes all the arguments of Img2Img and adds the mask image and the seam/infill stuff
 class Inpaint(Img2Img):
     def generate(self,
-                 mask_image: Image.Image | torch.FloatTensor,
+                 mask_image: Union[Image.Image, torch.FloatTensor],
                  # Seam settings - when 0, doesn't fill seam
                  seam_size: int = 96,
                  seam_blur: int = 16,
@@ -256,25 +228,6 @@ class Inpaint(Img2Img):
         from .inpaint import Inpaint
         return Inpaint
 
-# ------------------------------------
-class Embiggen(Txt2Img):
-    def generate(
-            self,
-            embiggen: list=None,
-            embiggen_tiles: list = None,
-            strength: float=0.75,
-            **kwargs)->Iterator[InvokeAIGeneratorOutput]:
-        return super().generate(embiggen=embiggen,
-                                embiggen_tiles=embiggen_tiles,
-                                strength=strength,
-                                **kwargs)
-
-    @classmethod
-    def _generator_class(cls):
-        from .embiggen import Embiggen
-        return Embiggen
-
-
 class Generator:
     downsampling_factor: int
     latent_channels: int
@@ -285,7 +238,7 @@ class Generator:
         self.model = model
         self.precision = precision
         self.seed = None
-        self.latent_channels = model.channels
+        self.latent_channels = model.unet.config.in_channels
         self.downsampling_factor = downsampling  # BUG: should come from model or config
         self.safety_checker = None
         self.perlin = 0.0
@@ -296,7 +249,7 @@ class Generator:
         self.free_gpu_mem = None
 
     # this is going to be overridden in img2img.py, txt2img.py and inpaint.py
-    def get_make_image(self, prompt, **kwargs):
+    def get_make_image(self, **kwargs):
         """
         Returns a function returning an image derived from the prompt and the initial image
         Return value depends on the seed at the time you call it
@@ -312,7 +265,6 @@ class Generator:
 
     def generate(
         self,
-        prompt,
         width,
         height,
         sampler,
@@ -337,7 +289,6 @@ class Generator:
             saver.get_stacked_maps_image()
         )
         make_image = self.get_make_image(
-            prompt,
             sampler=sampler,
             init_image=init_image,
             width=width,
@@ -619,28 +570,16 @@ class Generator:
         device = self.model.device
         # limit noise to only the diffusion image channels, not the mask channels
         input_channels = min(self.latent_channels, 4)
-        if self.use_mps_noise or device.type == "mps":
-            x = torch.randn(
-                [
-                    1,
-                    input_channels,
-                    height // self.downsampling_factor,
-                    width // self.downsampling_factor,
-                ],
-                dtype=self.torch_dtype(),
-                device="cpu",
-            ).to(device)
-        else:
-            x = torch.randn(
-                [
-                    1,
-                    input_channels,
-                    height // self.downsampling_factor,
-                    width // self.downsampling_factor,
-                ],
-                dtype=self.torch_dtype(),
-                device=device,
-            )
+        x = torch.randn(
+            [
+                1,
+                input_channels,
+                height // self.downsampling_factor,
+                width // self.downsampling_factor,
+            ],
+            dtype=self.torch_dtype(),
+            device=device,
+        )
         if self.perlin > 0.0:
             perlin_noise = self.get_perlin_noise(
                 width // self.downsampling_factor, height // self.downsampling_factor

invokeai/backend/generator/embiggen.py

@@ -1,559 +0,0 @@
-"""
-invokeai.backend.generator.embiggen descends from .generator
-and generates with .generator.img2img
-"""
-
-import numpy as np
-import torch
-from PIL import Image
-from tqdm import trange
-
-import invokeai.backend.util.logging as logger
-
-from .base import Generator
-from .img2img import Img2Img
-
-class Embiggen(Generator):
-    def __init__(self, model, precision):
-        super().__init__(model, precision)
-        self.init_latent = None
-
-    # Replace generate because Embiggen doesn't need/use most of what it does normallly
-    def generate(
-        self,
-        prompt,
-        iterations=1,
-        seed=None,
-        image_callback=None,
-        step_callback=None,
-        **kwargs,
-    ):
-        make_image = self.get_make_image(prompt, step_callback=step_callback, **kwargs)
-        results = []
-        seed = seed if seed else self.new_seed()
-
-        # Noise will be generated by the Img2Img generator when called
-        for _ in trange(iterations, desc="Generating"):
-            # make_image will call Img2Img which will do the equivalent of get_noise itself
-            image = make_image()
-            results.append([image, seed])
-            if image_callback is not None:
-                image_callback(image, seed, prompt_in=prompt)
-            seed = self.new_seed()
-        return results
-
-    @torch.no_grad()
-    def get_make_image(
-        self,
-        prompt,
-        sampler,
-        steps,
-        cfg_scale,
-        ddim_eta,
-        conditioning,
-        init_img,
-        strength,
-        width,
-        height,
-        embiggen,
-        embiggen_tiles,
-        step_callback=None,
-        **kwargs,
-    ):
-        """
-        Returns a function returning an image derived from the prompt and multi-stage twice-baked potato layering over the img2img on the initial image
-        Return value depends on the seed at the time you call it
-        """
-        assert (
-            not sampler.uses_inpainting_model()
-        ), "--embiggen is not supported by inpainting models"
-
-        # Construct embiggen arg array, and sanity check arguments
-        if embiggen == None:  # embiggen can also be called with just embiggen_tiles
-            embiggen = [1.0]  # If not specified, assume no scaling
-        elif embiggen[0] < 0:
-            embiggen[0] = 1.0
-            logger.warning(
-                "Embiggen scaling factor cannot be negative, fell back to the default of 1.0 !"
-            )
-        if len(embiggen) < 2:
-            embiggen.append(0.75)
-        elif embiggen[1] > 1.0 or embiggen[1] < 0:
-            embiggen[1] = 0.75
-            logger.warning(
-                "Embiggen upscaling strength for ESRGAN must be between 0 and 1, fell back to the default of 0.75 !"
-            )
-        if len(embiggen) < 3:
-            embiggen.append(0.25)
-        elif embiggen[2] < 0:
-            embiggen[2] = 0.25
-            logger.warning(
-                "Overlap size for Embiggen must be a positive ratio between 0 and 1 OR a number of pixels, fell back to the default of 0.25 !"
-            )
-
-        # Convert tiles from their user-freindly count-from-one to count-from-zero, because we need to do modulo math
-        # and then sort them, because... people.
-        if embiggen_tiles:
-            embiggen_tiles = list(map(lambda n: n - 1, embiggen_tiles))
-            embiggen_tiles.sort()
-
-        if strength >= 0.5:
-            logger.warning(
-                f"Embiggen may produce mirror motifs if the strength (-f) is too high (currently {strength}). Try values between 0.35-0.45."
-            )
-
-        # Prep img2img generator, since we wrap over it
-        gen_img2img = Img2Img(self.model, self.precision)
-
-        # Open original init image (not a tensor) to manipulate
-        initsuperimage = Image.open(init_img)
-
-        with Image.open(init_img) as img:
-            initsuperimage = img.convert("RGB")
-
-        # Size of the target super init image in pixels
-        initsuperwidth, initsuperheight = initsuperimage.size
-
-        # Increase by scaling factor if not already resized, using ESRGAN as able
-        if embiggen[0] != 1.0:
-            initsuperwidth = round(initsuperwidth * embiggen[0])
-            initsuperheight = round(initsuperheight * embiggen[0])
-            if embiggen[1] > 0:  # No point in ESRGAN upscaling if strength is set zero
-                from ..restoration.realesrgan import ESRGAN
-
-                esrgan = ESRGAN()
-                logger.info(
-                    f"ESRGAN upscaling init image prior to cutting with Embiggen with strength {embiggen[1]}"
-                )
-                if embiggen[0] > 2:
-                    initsuperimage = esrgan.process(
-                        initsuperimage,
-                        embiggen[1],  # upscale strength
-                        self.seed,
-                        4,  # upscale scale
-                    )
-                else:
-                    initsuperimage = esrgan.process(
-                        initsuperimage,
-                        embiggen[1],  # upscale strength
-                        self.seed,
-                        2,  # upscale scale
-                    )
-            # We could keep recursively re-running ESRGAN for a requested embiggen[0] larger than 4x
-            #   but from personal experiance it doesn't greatly improve anything after 4x
-            # Resize to target scaling factor resolution
-            initsuperimage = initsuperimage.resize(
-                (initsuperwidth, initsuperheight), Image.Resampling.LANCZOS
-            )
-
-        # Use width and height as tile widths and height
-        # Determine buffer size in pixels
-        if embiggen[2] < 1:
-            if embiggen[2] < 0:
-                embiggen[2] = 0
-            overlap_size_x = round(embiggen[2] * width)
-            overlap_size_y = round(embiggen[2] * height)
-        else:
-            overlap_size_x = round(embiggen[2])
-            overlap_size_y = round(embiggen[2])
-
-        # With overall image width and height known, determine how many tiles we need
-        def ceildiv(a, b):
-            return -1 * (-a // b)
-
-        # X and Y needs to be determined independantly (we may have savings on one based on the buffer pixel count)
-        # (initsuperwidth - width) is the area remaining to the right that we need to layers tiles to fill
-        # (width - overlap_size_x) is how much new we can fill with a single tile
-        emb_tiles_x = 1
-        emb_tiles_y = 1
-        if (initsuperwidth - width) > 0:
-            emb_tiles_x = ceildiv(initsuperwidth - width, width - overlap_size_x) + 1
-        if (initsuperheight - height) > 0:
-            emb_tiles_y = ceildiv(initsuperheight - height, height - overlap_size_y) + 1
-        # Sanity
-        assert (
-            emb_tiles_x > 1 or emb_tiles_y > 1
-        ), f"ERROR: Based on the requested dimensions of {initsuperwidth}x{initsuperheight} and tiles of {width}x{height} you don't need to Embiggen! Check your arguments."
-
-        # Prep alpha layers --------------
-        # https://stackoverflow.com/questions/69321734/how-to-create-different-transparency-like-gradient-with-python-pil
-        # agradientL is Left-side transparent
-        agradientL = (
-            Image.linear_gradient("L").rotate(90).resize((overlap_size_x, height))
-        )
-        # agradientT is Top-side transparent
-        agradientT = Image.linear_gradient("L").resize((width, overlap_size_y))
-        # radial corner is the left-top corner, made full circle then cut to just the left-top quadrant
-        agradientC = Image.new("L", (256, 256))
-        for y in range(256):
-            for x in range(256):
-                # Find distance to lower right corner (numpy takes arrays)
-                distanceToLR = np.sqrt([(255 - x) ** 2 + (255 - y) ** 2])[0]
-                # Clamp values to max 255
-                if distanceToLR > 255:
-                    distanceToLR = 255
-                # Place the pixel as invert of distance
-                agradientC.putpixel((x, y), round(255 - distanceToLR))
-
-        # Create alternative asymmetric diagonal corner to use on "tailing" intersections to prevent hard edges
-        # Fits for a left-fading gradient on the bottom side and full opacity on the right side.
-        agradientAsymC = Image.new("L", (256, 256))
-        for y in range(256):
-            for x in range(256):
-                value = round(max(0, x - (255 - y)) * (255 / max(1, y)))
-                # Clamp values
-                value = max(0, value)
-                value = min(255, value)
-                agradientAsymC.putpixel((x, y), value)
-
-        # Create alpha layers default fully white
-        alphaLayerL = Image.new("L", (width, height), 255)
-        alphaLayerT = Image.new("L", (width, height), 255)
-        alphaLayerLTC = Image.new("L", (width, height), 255)
-        # Paste gradients into alpha layers
-        alphaLayerL.paste(agradientL, (0, 0))
-        alphaLayerT.paste(agradientT, (0, 0))
-        alphaLayerLTC.paste(agradientL, (0, 0))
-        alphaLayerLTC.paste(agradientT, (0, 0))
-        alphaLayerLTC.paste(agradientC.resize((overlap_size_x, overlap_size_y)), (0, 0))
-        # make masks with an asymmetric upper-right corner so when the curved transparent corner of the next tile
-        # to its right is placed it doesn't reveal a hard trailing semi-transparent edge in the overlapping space
-        alphaLayerTaC = alphaLayerT.copy()
-        alphaLayerTaC.paste(
-            agradientAsymC.rotate(270).resize((overlap_size_x, overlap_size_y)),
-            (width - overlap_size_x, 0),
-        )
-        alphaLayerLTaC = alphaLayerLTC.copy()
-        alphaLayerLTaC.paste(
-            agradientAsymC.rotate(270).resize((overlap_size_x, overlap_size_y)),
-            (width - overlap_size_x, 0),
-        )
-
-        if embiggen_tiles:
-            # Individual unconnected sides
-            alphaLayerR = Image.new("L", (width, height), 255)
-            alphaLayerR.paste(agradientL.rotate(180), (width - overlap_size_x, 0))
-            alphaLayerB = Image.new("L", (width, height), 255)
-            alphaLayerB.paste(agradientT.rotate(180), (0, height - overlap_size_y))
-            alphaLayerTB = Image.new("L", (width, height), 255)
-            alphaLayerTB.paste(agradientT, (0, 0))
-            alphaLayerTB.paste(agradientT.rotate(180), (0, height - overlap_size_y))
-            alphaLayerLR = Image.new("L", (width, height), 255)
-            alphaLayerLR.paste(agradientL, (0, 0))
-            alphaLayerLR.paste(agradientL.rotate(180), (width - overlap_size_x, 0))
-
-            # Sides and corner Layers
-            alphaLayerRBC = Image.new("L", (width, height), 255)
-            alphaLayerRBC.paste(agradientL.rotate(180), (width - overlap_size_x, 0))
-            alphaLayerRBC.paste(agradientT.rotate(180), (0, height - overlap_size_y))
-            alphaLayerRBC.paste(
-                agradientC.rotate(180).resize((overlap_size_x, overlap_size_y)),
-                (width - overlap_size_x, height - overlap_size_y),
-            )
-            alphaLayerLBC = Image.new("L", (width, height), 255)
-            alphaLayerLBC.paste(agradientL, (0, 0))
-            alphaLayerLBC.paste(agradientT.rotate(180), (0, height - overlap_size_y))
-            alphaLayerLBC.paste(
-                agradientC.rotate(90).resize((overlap_size_x, overlap_size_y)),
-                (0, height - overlap_size_y),
-            )
-            alphaLayerRTC = Image.new("L", (width, height), 255)
-            alphaLayerRTC.paste(agradientL.rotate(180), (width - overlap_size_x, 0))
-            alphaLayerRTC.paste(agradientT, (0, 0))
-            alphaLayerRTC.paste(
-                agradientC.rotate(270).resize((overlap_size_x, overlap_size_y)),
-                (width - overlap_size_x, 0),
-            )
-
-            # All but X layers
-            alphaLayerABT = Image.new("L", (width, height), 255)
-            alphaLayerABT.paste(alphaLayerLBC, (0, 0))
-            alphaLayerABT.paste(agradientL.rotate(180), (width - overlap_size_x, 0))
-            alphaLayerABT.paste(
-                agradientC.rotate(180).resize((overlap_size_x, overlap_size_y)),
-                (width - overlap_size_x, height - overlap_size_y),
-            )
-            alphaLayerABL = Image.new("L", (width, height), 255)
-            alphaLayerABL.paste(alphaLayerRTC, (0, 0))
-            alphaLayerABL.paste(agradientT.rotate(180), (0, height - overlap_size_y))
-            alphaLayerABL.paste(
-                agradientC.rotate(180).resize((overlap_size_x, overlap_size_y)),
-                (width - overlap_size_x, height - overlap_size_y),
-            )
-            alphaLayerABR = Image.new("L", (width, height), 255)
-            alphaLayerABR.paste(alphaLayerLBC, (0, 0))
-            alphaLayerABR.paste(agradientT, (0, 0))
-            alphaLayerABR.paste(
-                agradientC.resize((overlap_size_x, overlap_size_y)), (0, 0)
-            )
-            alphaLayerABB = Image.new("L", (width, height), 255)
-            alphaLayerABB.paste(alphaLayerRTC, (0, 0))
-            alphaLayerABB.paste(agradientL, (0, 0))
-            alphaLayerABB.paste(
-                agradientC.resize((overlap_size_x, overlap_size_y)), (0, 0)
-            )
-
-            # All-around layer
-            alphaLayerAA = Image.new("L", (width, height), 255)
-            alphaLayerAA.paste(alphaLayerABT, (0, 0))
-            alphaLayerAA.paste(agradientT, (0, 0))
-            alphaLayerAA.paste(
-                agradientC.resize((overlap_size_x, overlap_size_y)), (0, 0)
-            )
-            alphaLayerAA.paste(
-                agradientC.rotate(270).resize((overlap_size_x, overlap_size_y)),
-                (width - overlap_size_x, 0),
-            )
-
-        # Clean up temporary gradients
-        del agradientL
-        del agradientT
-        del agradientC
-
-        def make_image():
-            # Make main tiles -------------------------------------------------
-            if embiggen_tiles:
-                logger.info(f"Making {len(embiggen_tiles)} Embiggen tiles...")
-            else:
-                logger.info(
-                    f"Making {(emb_tiles_x * emb_tiles_y)} Embiggen tiles ({emb_tiles_x}x{emb_tiles_y})..."
-                )
-
-            emb_tile_store = []
-            # Although we could use the same seed for every tile for determinism, at higher strengths this may
-            # produce duplicated structures for each tile and make the tiling effect more obvious
-            # instead track and iterate a local seed we pass to Img2Img
-            seed = self.seed
-            seedintlimit = (
-                np.iinfo(np.uint32).max - 1
-            )  # only retreive this one from numpy
-
-            for tile in range(emb_tiles_x * emb_tiles_y):
-                # Don't iterate on first tile
-                if tile != 0:
-                    if seed < seedintlimit:
-                        seed += 1
-                    else:
-                        seed = 0
-
-                # Determine if this is a re-run and replace
-                if embiggen_tiles and not tile in embiggen_tiles:
-                    continue
-                # Get row and column entries
-                emb_row_i = tile // emb_tiles_x
-                emb_column_i = tile % emb_tiles_x
-                # Determine bounds to cut up the init image
-                # Determine upper-left point
-                if emb_column_i + 1 == emb_tiles_x:
-                    left = initsuperwidth - width
-                else:
-                    left = round(emb_column_i * (width - overlap_size_x))
-                if emb_row_i + 1 == emb_tiles_y:
-                    top = initsuperheight - height
-                else:
-                    top = round(emb_row_i * (height - overlap_size_y))
-                right = left + width
-                bottom = top + height
-
-                # Cropped image of above dimension (does not modify the original)
-                newinitimage = initsuperimage.crop((left, top, right, bottom))
-                # DEBUG:
-                # newinitimagepath = init_img[0:-4] + f'_emb_Ti{tile}.png'
-                # newinitimage.save(newinitimagepath)
-
-                if embiggen_tiles:
-                    logger.debug(
-                        f"Making tile #{tile + 1} ({embiggen_tiles.index(tile) + 1} of {len(embiggen_tiles)} requested)"
-                    )
-                else:
-                    logger.debug(f"Starting {tile + 1} of {(emb_tiles_x * emb_tiles_y)} tiles")
-
-                # create a torch tensor from an Image
-                newinitimage = np.array(newinitimage).astype(np.float32) / 255.0
-                newinitimage = newinitimage[None].transpose(0, 3, 1, 2)
-                newinitimage = torch.from_numpy(newinitimage)
-                newinitimage = 2.0 * newinitimage - 1.0
-                newinitimage = newinitimage.to(self.model.device)
-                clear_cuda_cache = (
-                    kwargs["clear_cuda_cache"] if "clear_cuda_cache" in kwargs else None
-                )
-
-                tile_results = gen_img2img.generate(
-                    prompt,
-                    iterations=1,
-                    seed=seed,
-                    sampler=sampler,
-                    steps=steps,
-                    cfg_scale=cfg_scale,
-                    conditioning=conditioning,
-                    ddim_eta=ddim_eta,
-                    image_callback=None,  # called only after the final image is generated
-                    step_callback=step_callback,  # called after each intermediate image is generated
-                    width=width,
-                    height=height,
-                    init_image=newinitimage,  # notice that init_image is different from init_img
-                    mask_image=None,
-                    strength=strength,
-                    clear_cuda_cache=clear_cuda_cache,
-                )
-
-                emb_tile_store.append(tile_results[0][0])
-                # DEBUG (but, also has other uses), worth saving if you want tiles without a transparency overlap to manually composite
-                # emb_tile_store[-1].save(init_img[0:-4] + f'_emb_To{tile}.png')
-                del newinitimage
-
-            # Sanity check we have them all
-            if len(emb_tile_store) == (emb_tiles_x * emb_tiles_y) or (
-                embiggen_tiles != [] and len(emb_tile_store) == len(embiggen_tiles)
-            ):
-                outputsuperimage = Image.new("RGBA", (initsuperwidth, initsuperheight))
-                if embiggen_tiles:
-                    outputsuperimage.alpha_composite(
-                        initsuperimage.convert("RGBA"), (0, 0)
-                    )
-                for tile in range(emb_tiles_x * emb_tiles_y):
-                    if embiggen_tiles:
-                        if tile in embiggen_tiles:
-                            intileimage = emb_tile_store.pop(0)
-                        else:
-                            continue
-                    else:
-                        intileimage = emb_tile_store[tile]
-                    intileimage = intileimage.convert("RGBA")
-                    # Get row and column entries
-                    emb_row_i = tile // emb_tiles_x
-                    emb_column_i = tile % emb_tiles_x
-                    if emb_row_i == 0 and emb_column_i == 0 and not embiggen_tiles:
-                        left = 0
-                        top = 0
-                    else:
-                        # Determine upper-left point
-                        if emb_column_i + 1 == emb_tiles_x:
-                            left = initsuperwidth - width
-                        else:
-                            left = round(emb_column_i * (width - overlap_size_x))
-                        if emb_row_i + 1 == emb_tiles_y:
-                            top = initsuperheight - height
-                        else:
-                            top = round(emb_row_i * (height - overlap_size_y))
-                        # Handle gradients for various conditions
-                        # Handle emb_rerun case
-                        if embiggen_tiles:
-                            # top of image
-                            if emb_row_i == 0:
-                                if emb_column_i == 0:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        if (
-                                            tile + emb_tiles_x
-                                        ) not in embiggen_tiles:  # Look-ahead down
-                                            intileimage.putalpha(alphaLayerB)
-                                        # Otherwise do nothing on this tile
-                                    elif (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down only
-                                        intileimage.putalpha(alphaLayerR)
-                                    else:
-                                        intileimage.putalpha(alphaLayerRBC)
-                                elif emb_column_i == emb_tiles_x - 1:
-                                    if (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down
-                                        intileimage.putalpha(alphaLayerL)
-                                    else:
-                                        intileimage.putalpha(alphaLayerLBC)
-                                else:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        if (
-                                            tile + emb_tiles_x
-                                        ) in embiggen_tiles:  # Look-ahead down
-                                            intileimage.putalpha(alphaLayerL)
-                                        else:
-                                            intileimage.putalpha(alphaLayerLBC)
-                                    elif (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down only
-                                        intileimage.putalpha(alphaLayerLR)
-                                    else:
-                                        intileimage.putalpha(alphaLayerABT)
-                            # bottom of image
-                            elif emb_row_i == emb_tiles_y - 1:
-                                if emb_column_i == 0:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        intileimage.putalpha(alphaLayerTaC)
-                                    else:
-                                        intileimage.putalpha(alphaLayerRTC)
-                                elif emb_column_i == emb_tiles_x - 1:
-                                    # No tiles to look ahead to
-                                    intileimage.putalpha(alphaLayerLTC)
-                                else:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        intileimage.putalpha(alphaLayerLTaC)
-                                    else:
-                                        intileimage.putalpha(alphaLayerABB)
-                            # vertical middle of image
-                            else:
-                                if emb_column_i == 0:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        if (
-                                            tile + emb_tiles_x
-                                        ) in embiggen_tiles:  # Look-ahead down
-                                            intileimage.putalpha(alphaLayerTaC)
-                                        else:
-                                            intileimage.putalpha(alphaLayerTB)
-                                    elif (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down only
-                                        intileimage.putalpha(alphaLayerRTC)
-                                    else:
-                                        intileimage.putalpha(alphaLayerABL)
-                                elif emb_column_i == emb_tiles_x - 1:
-                                    if (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down
-                                        intileimage.putalpha(alphaLayerLTC)
-                                    else:
-                                        intileimage.putalpha(alphaLayerABR)
-                                else:
-                                    if (tile + 1) in embiggen_tiles:  # Look-ahead right
-                                        if (
-                                            tile + emb_tiles_x
-                                        ) in embiggen_tiles:  # Look-ahead down
-                                            intileimage.putalpha(alphaLayerLTaC)
-                                        else:
-                                            intileimage.putalpha(alphaLayerABR)
-                                    elif (
-                                        tile + emb_tiles_x
-                                    ) in embiggen_tiles:  # Look-ahead down only
-                                        intileimage.putalpha(alphaLayerABB)
-                                    else:
-                                        intileimage.putalpha(alphaLayerAA)
-                        # Handle normal tiling case (much simpler - since we tile left to right, top to bottom)
-                        else:
-                            if emb_row_i == 0 and emb_column_i >= 1:
-                                intileimage.putalpha(alphaLayerL)
-                            elif emb_row_i >= 1 and emb_column_i == 0:
-                                if (
-                                    emb_column_i + 1 == emb_tiles_x
-                                ):  # If we don't have anything that can be placed to the right
-                                    intileimage.putalpha(alphaLayerT)
-                                else:
-                                    intileimage.putalpha(alphaLayerTaC)
-                            else:
-                                if (
-                                    emb_column_i + 1 == emb_tiles_x
-                                ):  # If we don't have anything that can be placed to the right
-                                    intileimage.putalpha(alphaLayerLTC)
-                                else:
-                                    intileimage.putalpha(alphaLayerLTaC)
-                    # Layer tile onto final image
-                    outputsuperimage.alpha_composite(intileimage, (left, top))
-            else:
-                logger.error(
-                    "Could not find all Embiggen output tiles in memory? Something must have gone wrong with img2img generation."
-                )
-
-            # after internal loops and patching up return Embiggen image
-            return outputsuperimage
-
-        # end of function declaration
-        return make_image

invokeai/backend/generator/img2img.py

@@ -22,7 +22,6 @@ class Img2Img(Generator):
 
     def get_make_image(
         self,
-        prompt,
         sampler,
         steps,
         cfg_scale,
@@ -89,10 +88,7 @@ class Img2Img(Generator):
 
     def get_noise_like(self, like: torch.Tensor):
         device = like.device
-        if device.type == "mps":
-            x = torch.randn_like(like, device="cpu").to(device)
-        else:
-            x = torch.randn_like(like, device=device)
+        x = torch.randn_like(like, device=device)
         if self.perlin > 0.0:
             shape = like.shape
             x = (1 - self.perlin) * x + self.perlin * self.get_perlin_noise(

invokeai/backend/generator/inpaint.py

@@ -4,11 +4,10 @@ invokeai.backend.generator.inpaint descends from .generator
 from __future__ import annotations
 
 import math
-from typing import Tuple, Union
+from typing import Tuple, Union, Optional
 
 import cv2
 import numpy as np
-import PIL
 import torch
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
@@ -76,7 +75,7 @@ class Inpaint(Img2Img):
         return im_patched
 
     def tile_fill_missing(
-        self, im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
+        self, im: Image.Image, tile_size: int = 16, seed: Optional[int] = None
     ) -> Image.Image:
         # Only fill if there's an alpha layer
         if im.mode != "RGBA":
@@ -161,9 +160,7 @@ class Inpaint(Img2Img):
         im: Image.Image,
         seam_size: int,
         seam_blur: int,
-        prompt,
         seed,
-        sampler,
         steps,
         cfg_scale,
         ddim_eta,
@@ -177,8 +174,6 @@ class Inpaint(Img2Img):
         mask = self.mask_edge(hard_mask, seam_size, seam_blur)
 
         make_image = self.get_make_image(
-            prompt,
-            sampler,
             steps,
             cfg_scale,
             ddim_eta,
@@ -203,14 +198,12 @@ class Inpaint(Img2Img):
     @torch.no_grad()
     def get_make_image(
         self,
-        prompt,
-        sampler,
         steps,
         cfg_scale,
         ddim_eta,
         conditioning,
-        init_image: Image.Image | torch.FloatTensor,
-        mask_image: Image.Image | torch.FloatTensor,
+        init_image: Union[Image.Image, torch.FloatTensor],
+        mask_image: Union[Image.Image, torch.FloatTensor],
         strength: float,
         mask_blur_radius: int = 8,
         # Seam settings - when 0, doesn't fill seam
@@ -306,7 +299,6 @@ class Inpaint(Img2Img):
 
         # noinspection PyTypeChecker
         pipeline: StableDiffusionGeneratorPipeline = self.model
-        pipeline.scheduler = sampler
 
         # todo: support cross-attention control
         uc, c, _ = conditioning
@@ -345,9 +337,7 @@ class Inpaint(Img2Img):
                     result,
                     seam_size,
                     seam_blur,
-                    prompt,
                     seed,
-                    sampler,
                     seam_steps,
                     cfg_scale,
                     ddim_eta,
@@ -360,8 +350,6 @@ class Inpaint(Img2Img):
 
                 # Restore original settings
                 self.get_make_image(
-                    prompt,
-                    sampler,
                     steps,
                     cfg_scale,
                     ddim_eta,

invokeai/backend/generator/txt2img.py

@@ -1,125 +0,0 @@
-"""
-invokeai.backend.generator.txt2img inherits from invokeai.backend.generator
-"""
-import PIL.Image
-import torch
-
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-from diffusers.models.controlnet import ControlNetModel, ControlNetOutput
-from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import MultiControlNetModel
-
-from ..stable_diffusion import (
-    ConditioningData,
-    PostprocessingSettings,
-    StableDiffusionGeneratorPipeline,
-)
-from .base import Generator
-
-
-class Txt2Img(Generator):
-    def __init__(self, model, precision,
-                 control_model: Optional[Union[ControlNetModel, List[ControlNetModel]]] = None,
-                 **kwargs):
-        self.control_model = control_model
-        if isinstance(self.control_model, list):
-            self.control_model = MultiControlNetModel(self.control_model)
-        super().__init__(model, precision, **kwargs)
-
-    @torch.no_grad()
-    def get_make_image(
-        self,
-        prompt,
-        sampler,
-        steps,
-        cfg_scale,
-        ddim_eta,
-        conditioning,
-        width,
-        height,
-        step_callback=None,
-        threshold=0.0,
-        warmup=0.2,
-        perlin=0.0,
-        h_symmetry_time_pct=None,
-        v_symmetry_time_pct=None,
-        attention_maps_callback=None,
-        **kwargs,
-    ):
-        """
-        Returns a function returning an image derived from the prompt and the initial image
-        Return value depends on the seed at the time you call it
-        kwargs are 'width' and 'height'
-        """
-        self.perlin = perlin
-        control_image = kwargs.get("control_image", None)
-        do_classifier_free_guidance = cfg_scale > 1.0
-
-        # noinspection PyTypeChecker
-        pipeline: StableDiffusionGeneratorPipeline = self.model
-        pipeline.control_model = self.control_model
-        pipeline.scheduler = sampler
-
-        uc, c, extra_conditioning_info = conditioning
-        conditioning_data = ConditioningData(
-            uc,
-            c,
-            cfg_scale,
-            extra_conditioning_info,
-            postprocessing_settings=PostprocessingSettings(
-                threshold=threshold,
-                warmup=warmup,
-                h_symmetry_time_pct=h_symmetry_time_pct,
-                v_symmetry_time_pct=v_symmetry_time_pct,
-            ),
-        ).add_scheduler_args_if_applicable(pipeline.scheduler, eta=ddim_eta)
-
-        # FIXME: still need to test with different widths, heights, devices, dtypes
-        #        and add in batch_size, num_images_per_prompt?
-        if control_image is not None:
-            if isinstance(self.control_model, ControlNetModel):
-                control_image = pipeline.prepare_control_image(
-                    image=control_image,
-                    do_classifier_free_guidance=do_classifier_free_guidance,
-                    width=width,
-                    height=height,
-                    # batch_size=batch_size * num_images_per_prompt,
-                    # num_images_per_prompt=num_images_per_prompt,
-                    device=self.control_model.device,
-                    dtype=self.control_model.dtype,
-                )
-            elif isinstance(self.control_model, MultiControlNetModel):
-                images = []
-                for image_ in control_image:
-                    image_ = self.model.prepare_control_image(
-                        image=image_,
-                        do_classifier_free_guidance=do_classifier_free_guidance,
-                        width=width,
-                        height=height,
-                        # batch_size=batch_size * num_images_per_prompt,
-                        # num_images_per_prompt=num_images_per_prompt,
-                        device=self.control_model.device,
-                        dtype=self.control_model.dtype,
-                    )
-                    images.append(image_)
-                control_image = images
-            kwargs["control_image"] = control_image
-
-        def make_image(x_T: torch.Tensor, _: int) -> PIL.Image.Image:
-            pipeline_output = pipeline.image_from_embeddings(
-                latents=torch.zeros_like(x_T, dtype=self.torch_dtype()),
-                noise=x_T,
-                num_inference_steps=steps,
-                conditioning_data=conditioning_data,
-                callback=step_callback,
-                **kwargs,
-            )
-
-            if (
-                pipeline_output.attention_map_saver is not None
-                and attention_maps_callback is not None
-            ):
-                attention_maps_callback(pipeline_output.attention_map_saver)
-
-            return pipeline.numpy_to_pil(pipeline_output.images)[0]
-
-        return make_image

invokeai/backend/generator/txt2img2img.py

@@ -1,209 +0,0 @@
-"""
-invokeai.backend.generator.txt2img inherits from invokeai.backend.generator
-"""
-
-import math
-from typing import Callable, Optional
-
-import torch
-from diffusers.utils.logging import get_verbosity, set_verbosity, set_verbosity_error
-
-from ..stable_diffusion import PostprocessingSettings
-from .base import Generator
-from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
-from ..stable_diffusion.diffusers_pipeline import ConditioningData
-from ..stable_diffusion.diffusers_pipeline import trim_to_multiple_of
-
-import invokeai.backend.util.logging as logger
-
-class Txt2Img2Img(Generator):
-    def __init__(self, model, precision):
-        super().__init__(model, precision)
-        self.init_latent = None  # for get_noise()
-
-    def get_make_image(
-        self,
-        prompt: str,
-        sampler,
-        steps: int,
-        cfg_scale: float,
-        ddim_eta,
-        conditioning,
-        width: int,
-        height: int,
-        strength: float,
-        step_callback: Optional[Callable] = None,
-        threshold=0.0,
-        warmup=0.2,
-        perlin=0.0,
-        h_symmetry_time_pct=None,
-        v_symmetry_time_pct=None,
-        attention_maps_callback=None,
-        **kwargs,
-    ):
-        """
-        Returns a function returning an image derived from the prompt and the initial image
-        Return value depends on the seed at the time you call it
-        kwargs are 'width' and 'height'
-        """
-        self.perlin = perlin
-
-        # noinspection PyTypeChecker
-        pipeline: StableDiffusionGeneratorPipeline = self.model
-        pipeline.scheduler = sampler
-
-        uc, c, extra_conditioning_info = conditioning
-        conditioning_data = ConditioningData(
-            uc,
-            c,
-            cfg_scale,
-            extra_conditioning_info,
-            postprocessing_settings=PostprocessingSettings(
-                threshold=threshold,
-                warmup=0.2,
-                h_symmetry_time_pct=h_symmetry_time_pct,
-                v_symmetry_time_pct=v_symmetry_time_pct,
-            ),
-        ).add_scheduler_args_if_applicable(pipeline.scheduler, eta=ddim_eta)
-
-        def make_image(x_T: torch.Tensor, _: int):
-            first_pass_latent_output, _ = pipeline.latents_from_embeddings(
-                latents=torch.zeros_like(x_T),
-                num_inference_steps=steps,
-                conditioning_data=conditioning_data,
-                noise=x_T,
-                callback=step_callback,
-            )
-
-            # Get our initial generation width and height directly from the latent output so
-            # the message below is accurate.
-            init_width = first_pass_latent_output.size()[3] * self.downsampling_factor
-            init_height = first_pass_latent_output.size()[2] * self.downsampling_factor
-            logger.info(
-                f"Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling"
-            )
-
-            # resizing
-            resized_latents = torch.nn.functional.interpolate(
-                first_pass_latent_output,
-                size=(
-                    height // self.downsampling_factor,
-                    width // self.downsampling_factor,
-                ),
-                mode="bilinear",
-            )
-
-            # Free up memory from the last generation.
-            clear_cuda_cache = kwargs["clear_cuda_cache"] or None
-            if clear_cuda_cache is not None:
-                clear_cuda_cache()
-
-            second_pass_noise = self.get_noise_like(
-                resized_latents, override_perlin=True
-            )
-
-            # Clear symmetry for the second pass
-            from dataclasses import replace
-
-            new_postprocessing_settings = replace(
-                conditioning_data.postprocessing_settings, h_symmetry_time_pct=None
-            )
-            new_postprocessing_settings = replace(
-                new_postprocessing_settings, v_symmetry_time_pct=None
-            )
-            new_conditioning_data = replace(
-                conditioning_data, postprocessing_settings=new_postprocessing_settings
-            )
-
-            verbosity = get_verbosity()
-            set_verbosity_error()
-            pipeline_output = pipeline.img2img_from_latents_and_embeddings(
-                resized_latents,
-                num_inference_steps=steps,
-                conditioning_data=new_conditioning_data,
-                strength=strength,
-                noise=second_pass_noise,
-                callback=step_callback,
-            )
-            set_verbosity(verbosity)
-
-            if (
-                pipeline_output.attention_map_saver is not None
-                and attention_maps_callback is not None
-            ):
-                attention_maps_callback(pipeline_output.attention_map_saver)
-
-            return pipeline.numpy_to_pil(pipeline_output.images)[0]
-
-        # FIXME: do we really need something entirely different for the inpainting model?
-
-        # in the case of the inpainting model being loaded, the trick of
-        # providing an interpolated latent doesn't work, so we transiently
-        # create a 512x512 PIL image, upscale it, and run the inpainting
-        # over it in img2img mode. Because the inpaing model is so conservative
-        # it doesn't change the image (much)
-
-        return make_image
-
-    def get_noise_like(self, like: torch.Tensor, override_perlin: bool = False):
-        device = like.device
-        if device.type == "mps":
-            x = torch.randn_like(like, device="cpu", dtype=self.torch_dtype()).to(
-                device
-            )
-        else:
-            x = torch.randn_like(like, device=device, dtype=self.torch_dtype())
-        if self.perlin > 0.0 and override_perlin == False:
-            shape = like.shape
-            x = (1 - self.perlin) * x + self.perlin * self.get_perlin_noise(
-                shape[3], shape[2]
-            )
-        return x
-
-    # returns a tensor filled with random numbers from a normal distribution
-    def get_noise(self, width, height, scale=True):
-        # print(f"Get noise: {width}x{height}")
-        if scale:
-            # Scale the input width and height for the initial generation
-            # Make their area equivalent to the model's resolution area (e.g. 512*512 = 262144),
-            # while keeping the minimum dimension at least 0.5 * resolution (e.g. 512*0.5 = 256)
-
-            aspect = width / height
-            dimension = self.model.unet.config.sample_size * self.model.vae_scale_factor
-            min_dimension = math.floor(dimension * 0.5)
-            model_area = (
-                dimension * dimension
-            )  # hardcoded for now since all models are trained on square images
-
-            if aspect > 1.0:
-                init_height = max(min_dimension, math.sqrt(model_area / aspect))
-                init_width = init_height * aspect
-            else:
-                init_width = max(min_dimension, math.sqrt(model_area * aspect))
-                init_height = init_width / aspect
-
-            scaled_width, scaled_height = trim_to_multiple_of(
-                math.floor(init_width), math.floor(init_height)
-            )
-
-        else:
-            scaled_width = width
-            scaled_height = height
-
-        device = self.model.device
-        channels = self.latent_channels
-        if channels == 9:
-            channels = 4  # we don't really want noise for all the mask channels
-        shape = (
-            1,
-            channels,
-            scaled_height // self.downsampling_factor,
-            scaled_width // self.downsampling_factor,
-        )
-        if self.use_mps_noise or device.type == "mps":
-            tensor = torch.empty(size=shape, device="cpu")
-            tensor = self.get_noise_like(like=tensor).to(device)
-        else:
-            tensor = torch.empty(size=shape, device=device)
-            tensor = self.get_noise_like(like=tensor)
-        return tensor

invokeai/backend/install/invokeai_configure.py

@@ -7,8 +7,6 @@
 # Coauthor: Kevin Turner http://github.com/keturn
 #
 import sys
-print("Loading Python libraries...\n",file=sys.stderr)
-
 import argparse
 import io
 import os
@@ -16,6 +14,7 @@ import shutil
 import textwrap
 import traceback
 import warnings
+import yaml
 from argparse import Namespace
 from pathlib import Path
 from shutil import get_terminal_size
@@ -25,6 +24,7 @@ from urllib import request
 import npyscreen
 import transformers
 from diffusers import AutoencoderKL
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from huggingface_hub import HfFolder
 from huggingface_hub import login as hf_hub_login
 from omegaconf import OmegaConf
@@ -34,6 +34,8 @@ from transformers import (
     CLIPSegForImageSegmentation,
     CLIPTextModel,
     CLIPTokenizer,
+    AutoFeatureExtractor,
+    BertTokenizerFast,
 )
 import invokeai.configs as configs
 
@@ -43,6 +45,7 @@ from invokeai.app.services.config import (
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.frontend.install.model_install import addModelsForm, process_and_execute
 from invokeai.frontend.install.widgets import (
+    SingleSelectColumns,
     CenteredButtonPress,
     IntTitleSlider,
     set_min_terminal_size,
@@ -52,12 +55,13 @@ from invokeai.frontend.install.widgets import (
 )
 from invokeai.backend.install.legacy_arg_parsing import legacy_parser
 from invokeai.backend.install.model_install_backend import (
-    default_dataset,
-    download_from_hf,
-    hf_download_with_resume,
-    recommended_datasets,
-    UserSelections,
+    hf_download_from_pretrained,
+    InstallSelections,
+    ModelInstall,
 )
+from invokeai.backend.model_management.model_probe import (
+    ModelType, BaseModelType
+    )
 
 warnings.filterwarnings("ignore")
 transformers.logging.set_verbosity_error()
@@ -73,7 +77,7 @@ Weights_dir = "ldm/stable-diffusion-v1/"
 Default_config_file = config.model_conf_path
 SD_Configs = config.legacy_conf_path
 
-PRECISION_CHOICES = ['auto','float16','float32','autocast']
+PRECISION_CHOICES = ['auto','float16','float32']
 
 INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # This is the InvokeAI initialization file, which contains command-line default values.
@@ -81,7 +85,7 @@ INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # or renaming it and then running invokeai-configure again.
 """
 
-logger=None
+logger=InvokeAILogger.getLogger()
 
 # --------------------------------------------
 def postscript(errors: None):
@@ -162,75 +166,91 @@ class ProgressBar:
 # ---------------------------------------------
 def download_with_progress_bar(model_url: str, model_dest: str, label: str = "the"):
     try:
-        print(f"Installing {label} model file {model_url}...", end="", file=sys.stderr)
+        logger.info(f"Installing {label} model file {model_url}...")
         if not os.path.exists(model_dest):
             os.makedirs(os.path.dirname(model_dest), exist_ok=True)
             request.urlretrieve(
                 model_url, model_dest, ProgressBar(os.path.basename(model_dest))
             )
-            print("...downloaded successfully", file=sys.stderr)
+            logger.info("...downloaded successfully")
         else:
-            print("...exists", file=sys.stderr)
+            logger.info("...exists")
     except Exception:
-        print("...download failed", file=sys.stderr)
-        print(f"Error downloading {label} model", file=sys.stderr)
+        logger.info("...download failed")
+        logger.info(f"Error downloading {label} model")
         print(traceback.format_exc(), file=sys.stderr)
 
 
-# ---------------------------------------------
-# this will preload the Bert tokenizer fles
-def download_bert():
-    print("Installing bert tokenizer...", file=sys.stderr)
-    with warnings.catch_warnings():
-        warnings.filterwarnings("ignore", category=DeprecationWarning)
-        from transformers import BertTokenizerFast
+def download_conversion_models():
+    target_dir = config.root_path / 'models/core/convert'
+    kwargs = dict()  # for future use
+    try:
+        logger.info('Downloading core tokenizers and text encoders')
 
-        download_from_hf(BertTokenizerFast, "bert-base-uncased")
+        # bert
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", category=DeprecationWarning)
+            bert = BertTokenizerFast.from_pretrained("bert-base-uncased", **kwargs)
+            bert.save_pretrained(target_dir / 'bert-base-uncased', safe_serialization=True)
+        
+        # sd-1
+        repo_id = 'openai/clip-vit-large-patch14'
+        hf_download_from_pretrained(CLIPTokenizer, repo_id, target_dir / 'clip-vit-large-patch14')
+        hf_download_from_pretrained(CLIPTextModel, repo_id, target_dir / 'clip-vit-large-patch14')
 
+        # sd-2
+        repo_id = "stabilityai/stable-diffusion-2"
+        pipeline = CLIPTokenizer.from_pretrained(repo_id, subfolder="tokenizer", **kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-2-clip' / 'tokenizer', safe_serialization=True)
 
-# ---------------------------------------------
-def download_sd1_clip():
-    print("Installing SD1 clip model...", file=sys.stderr)
-    version = "openai/clip-vit-large-patch14"
-    download_from_hf(CLIPTokenizer, version)
-    download_from_hf(CLIPTextModel, version)
+        pipeline = CLIPTextModel.from_pretrained(repo_id, subfolder="text_encoder", **kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-2-clip' / 'text_encoder', safe_serialization=True)
 
+        # VAE
+        logger.info('Downloading stable diffusion VAE')
+        vae = AutoencoderKL.from_pretrained('stabilityai/sd-vae-ft-mse', **kwargs)
+        vae.save_pretrained(target_dir / 'sd-vae-ft-mse', safe_serialization=True)
 
-# ---------------------------------------------
-def download_sd2_clip():
-    version = "stabilityai/stable-diffusion-2"
-    print("Installing SD2 clip model...", file=sys.stderr)
-    download_from_hf(CLIPTokenizer, version, subfolder="tokenizer")
-    download_from_hf(CLIPTextModel, version, subfolder="text_encoder")
+        # safety checking
+        logger.info('Downloading safety checker')
+        repo_id = "CompVis/stable-diffusion-safety-checker"
+        pipeline = AutoFeatureExtractor.from_pretrained(repo_id,**kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-safety-checker', safe_serialization=True)
 
+        pipeline = StableDiffusionSafetyChecker.from_pretrained(repo_id,**kwargs)
+        pipeline.save_pretrained(target_dir / 'stable-diffusion-safety-checker', safe_serialization=True)
+    except KeyboardInterrupt:
+        raise
+    except Exception as e:
+        logger.error(str(e))
 
 # ---------------------------------------------
 def download_realesrgan():
-    print("Installing models from RealESRGAN...", file=sys.stderr)
+    logger.info("Installing models from RealESRGAN...")
     model_url = "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth"
     wdn_model_url = "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth"
 
-    model_dest = config.root_path / "models/realesrgan/realesr-general-x4v3.pth"
-    wdn_model_dest = config.root_path / "models/realesrgan/realesr-general-wdn-x4v3.pth"
+    model_dest = config.root_path / "models/core/upscaling/realesrgan/realesr-general-x4v3.pth"
+    wdn_model_dest = config.root_path / "models/core/upscaling/realesrgan/realesr-general-wdn-x4v3.pth"
 
     download_with_progress_bar(model_url, str(model_dest), "RealESRGAN")
     download_with_progress_bar(wdn_model_url, str(wdn_model_dest), "RealESRGANwdn")
 
 
 def download_gfpgan():
-    print("Installing GFPGAN models...", file=sys.stderr)
+    logger.info("Installing GFPGAN models...")
     for model in (
         [
             "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth",
-            "./models/gfpgan/GFPGANv1.4.pth",
+            "./models/core/face_restoration/gfpgan/GFPGANv1.4.pth",
         ],
         [
             "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth",
-            "./models/gfpgan/weights/detection_Resnet50_Final.pth",
+            "./models/core/face_restoration/gfpgan/weights/detection_Resnet50_Final.pth",
         ],
         [
             "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth",
-            "./models/gfpgan/weights/parsing_parsenet.pth",
+            "./models/core/face_restoration/gfpgan/weights/parsing_parsenet.pth",
         ],
     ):
         model_url, model_dest = model[0], config.root_path / model[1]
@@ -239,70 +259,32 @@ def download_gfpgan():
 
 # ---------------------------------------------
 def download_codeformer():
-    print("Installing CodeFormer model file...", file=sys.stderr)
+    logger.info("Installing CodeFormer model file...")
     model_url = (
         "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth"
     )
-    model_dest = config.root_path / "models/codeformer/codeformer.pth"
+    model_dest = config.root_path / "models/core/face_restoration/codeformer/codeformer.pth"
     download_with_progress_bar(model_url, str(model_dest), "CodeFormer")
 
 
 # ---------------------------------------------
 def download_clipseg():
-    print("Installing clipseg model for text-based masking...", file=sys.stderr)
+    logger.info("Installing clipseg model for text-based masking...")
     CLIPSEG_MODEL = "CIDAS/clipseg-rd64-refined"
     try:
-        download_from_hf(AutoProcessor, CLIPSEG_MODEL)
-        download_from_hf(CLIPSegForImageSegmentation, CLIPSEG_MODEL)
+        hf_download_from_pretrained(AutoProcessor, CLIPSEG_MODEL, config.root_path / 'models/core/misc/clipseg')
+        hf_download_from_pretrained(CLIPSegForImageSegmentation, CLIPSEG_MODEL, config.root_path / 'models/core/misc/clipseg')
     except Exception:
-        print("Error installing clipseg model:")
-        print(traceback.format_exc())
+        logger.info("Error installing clipseg model:")
+        logger.info(traceback.format_exc())
 
 
-# -------------------------------------
-def download_safety_checker():
-    print("Installing model for NSFW content detection...", file=sys.stderr)
-    try:
-        from diffusers.pipelines.stable_diffusion.safety_checker import (
-            StableDiffusionSafetyChecker,
-        )
-        from transformers import AutoFeatureExtractor
-    except ModuleNotFoundError:
-        print("Error installing NSFW checker model:")
-        print(traceback.format_exc())
-        return
-    safety_model_id = "CompVis/stable-diffusion-safety-checker"
-    print("AutoFeatureExtractor...", file=sys.stderr)
-    download_from_hf(AutoFeatureExtractor, safety_model_id)
-    print("StableDiffusionSafetyChecker...", file=sys.stderr)
-    download_from_hf(StableDiffusionSafetyChecker, safety_model_id)
-
-
-# -------------------------------------
-def download_vaes():
-    print("Installing stabilityai VAE...", file=sys.stderr)
-    try:
-        # first the diffusers version
-        repo_id = "stabilityai/sd-vae-ft-mse"
-        args = dict(
-            cache_dir=config.cache_dir,
-        )
-        if not AutoencoderKL.from_pretrained(repo_id, **args):
-            raise Exception(f"download of {repo_id} failed")
-
-        repo_id = "stabilityai/sd-vae-ft-mse-original"
-        model_name = "vae-ft-mse-840000-ema-pruned.ckpt"
-        # next the legacy checkpoint version
-        if not hf_download_with_resume(
-            repo_id=repo_id,
-            model_name=model_name,
-            model_dir=str(config.root_path / Model_dir / Weights_dir),
-        ):
-            raise Exception(f"download of {model_name} failed")
-    except Exception as e:
-        print(f"Error downloading StabilityAI standard VAE: {str(e)}", file=sys.stderr)
-        print(traceback.format_exc(), file=sys.stderr)
-
+def download_support_models():
+    download_realesrgan()
+    download_gfpgan()
+    download_codeformer()
+    download_clipseg()
+    download_conversion_models()
 
 # -------------------------------------
 def get_root(root: str = None) -> str:
@@ -378,9 +360,7 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
             scroll_exit=True,
         )
         self.nextrely += 1
-        label = """If you have an account at HuggingFace you may optionally paste your access token here
-to allow InvokeAI to download restricted styles & subjects from the "Concept Library". See https://huggingface.co/settings/tokens.
-"""
+        label = """HuggingFace access token (OPTIONAL) for automatic model downloads. See https://huggingface.co/settings/tokens."""
         for line in textwrap.wrap(label,width=window_width-6):
             self.add_widget_intelligent(
                 npyscreen.FixedText,
@@ -442,6 +422,7 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
         )
         self.precision = self.add_widget_intelligent(
             npyscreen.TitleSelectOne,
+            columns = 2,
             name="Precision",
             values=PRECISION_CHOICES,
             value=PRECISION_CHOICES.index(precision),
@@ -449,13 +430,13 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
             max_height=len(PRECISION_CHOICES) + 1,
             scroll_exit=True,
         )
-        self.max_loaded_models = self.add_widget_intelligent(
+        self.max_cache_size = self.add_widget_intelligent(
             IntTitleSlider,
-            name="Number of models to cache in CPU memory (each will use 2-4 GB!)",
-            value=old_opts.max_loaded_models,
-            out_of=10,
-            lowest=1,
-            begin_entry_at=4,
+            name="Size of the RAM cache used for fast model switching (GB)",
+            value=old_opts.max_cache_size,
+            out_of=20,
+            lowest=3,
+            begin_entry_at=6,
             scroll_exit=True,
         )
         self.nextrely += 1
@@ -465,39 +446,19 @@ to allow InvokeAI to download restricted styles & subjects from the "Concept Lib
             editable=False,
             color="CONTROL",
         )
-        self.embedding_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name=" Textual Inversion Embeddings:",
-            value=str(default_embedding_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
-        self.lora_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name="             LoRA and LyCORIS:",
-            value=str(default_lora_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
-        self.controlnet_dir = self.add_widget_intelligent(
-            npyscreen.TitleFilename,
-            name="             ControlNets:",
-            value=str(default_controlnet_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=32,
-            scroll_exit=True,
-        )
+        self.autoimport_dirs = {}
+        for description, config_name, path in autoimport_paths(old_opts):
+            self.autoimport_dirs[config_name] = self.add_widget_intelligent(
+                npyscreen.TitleFilename,
+                name=description+':',
+                value=str(path),
+                select_dir=True,
+                must_exist=False,
+                use_two_lines=False,
+                labelColor="GOOD",
+                begin_entry_at=32,
+                scroll_exit=True
+            )
         self.nextrely += 1
         self.add_widget_intelligent(
             npyscreen.TitleFixedText,
@@ -562,10 +523,6 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
             bad_fields.append(
                 f"The output directory does not seem to be valid. Please check that {str(Path(opt.outdir).parent)} is an existing directory."
             )
-        if not Path(opt.embedding_dir).parent.exists():
-            bad_fields.append(
-                f"The embedding directory does not seem to be valid. Please check that {str(Path(opt.embedding_dir).parent)} is an existing directory."
-            )
         if len(bad_fields) > 0:
             message = "The following problems were detected and must be corrected:\n"
             for problem in bad_fields:
@@ -582,22 +539,22 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
                 "outdir",
                 "nsfw_checker",
                 "free_gpu_mem",
-                "max_loaded_models",
+                "max_cache_size",
                 "xformers_enabled",
                 "always_use_cpu",
-                "embedding_dir",
-                "lora_dir",
-                "controlnet_dir",
         ]:
             setattr(new_opts, attr, getattr(self, attr).value)
 
+        for attr in self.autoimport_dirs:
+            directory = Path(self.autoimport_dirs[attr].value)
+            if directory.is_relative_to(config.root_path):
+                directory = directory.relative_to(config.root_path)
+            setattr(new_opts, attr, directory)
+
         new_opts.hf_token = self.hf_token.value
         new_opts.license_acceptance = self.license_acceptance.value
         new_opts.precision = PRECISION_CHOICES[self.precision.value[0]]
         
-        # widget library workaround to make max_loaded_models an int rather than a float
-        new_opts.max_loaded_models = int(new_opts.max_loaded_models)
-
         return new_opts
 
 
@@ -607,7 +564,8 @@ class EditOptApplication(npyscreen.NPSAppManaged):
         self.program_opts = program_opts
         self.invokeai_opts = invokeai_opts
         self.user_cancelled = False
-        self.user_selections = default_user_selections(program_opts)
+        self.autoload_pending = True
+        self.install_selections = default_user_selections(program_opts)
 
     def onStart(self):
         npyscreen.setTheme(npyscreen.Themes.DefaultTheme)
@@ -642,41 +600,62 @@ def default_startup_options(init_file: Path) -> Namespace:
         opts.nsfw_checker = True
     return opts
 
-def default_user_selections(program_opts: Namespace) -> UserSelections:
-    return UserSelections(
-        install_models=default_dataset()
+def default_user_selections(program_opts: Namespace) -> InstallSelections:
+    installer = ModelInstall(config)
+    models = installer.all_models()
+    return InstallSelections(
+        install_models=[models[installer.default_model()].path or models[installer.default_model()].repo_id]
         if program_opts.default_only
-        else recommended_datasets()
+        else [models[x].path or models[x].repo_id for x in installer.recommended_models()]
         if program_opts.yes_to_all
-        else dict(),
-        purge_deleted_models=False,
-        scan_directory=None,
-        autoscan_on_startup=None,
+        else list(),
+#        scan_directory=None,
+#        autoscan_on_startup=None,
     )
 
-
+# -------------------------------------
+def autoimport_paths(config: InvokeAIAppConfig):
+    return [
+        ('Checkpoints & diffusers models', 'autoimport_dir', config.root_path / config.autoimport_dir),
+        ('LoRA/LyCORIS models',            'lora_dir',       config.root_path / config.lora_dir),
+        ('Controlnet models',              'controlnet_dir', config.root_path / config.controlnet_dir),
+        ('Textual Inversion Embeddings',   'embedding_dir',  config.root_path / config.embedding_dir),
+    ]
+    
 # -------------------------------------
 def initialize_rootdir(root: Path, yes_to_all: bool = False):
-    print("** INITIALIZING INVOKEAI RUNTIME DIRECTORY **")
-
+    logger.info("** INITIALIZING INVOKEAI RUNTIME DIRECTORY **")
     for name in (
             "models",
-            "configs",
-            "embeddings",
             "databases",
-            "loras",
-            "controlnets",
             "text-inversion-output",
             "text-inversion-training-data",
+            "configs"
     ):
         os.makedirs(os.path.join(root, name), exist_ok=True)
+    for model_type in ModelType:
+        Path(root, 'autoimport', model_type.value).mkdir(parents=True, exist_ok=True)
 
     configs_src = Path(configs.__path__[0])
     configs_dest = root / "configs"
     if not os.path.samefile(configs_src, configs_dest):
         shutil.copytree(configs_src, configs_dest, dirs_exist_ok=True)
 
+    dest = root / 'models'
+    for model_base in BaseModelType:
+        for model_type in ModelType:
+            path = dest / model_base.value / model_type.value
+            path.mkdir(parents=True, exist_ok=True)
+    path = dest / 'core'
+    path.mkdir(parents=True, exist_ok=True)
 
+    with open(root / 'configs' / 'models.yaml','w') as yaml_file:
+        yaml_file.write(yaml.dump({'__metadata__':
+                                   {'version':'3.0.0'}
+                                   }
+                                  )
+                        )
+        
 # -------------------------------------
 def run_console_ui(
     program_opts: Namespace, initfile: Path = None
@@ -699,7 +678,7 @@ def run_console_ui(
     if editApp.user_cancelled:
         return (None, None)
     else:
-        return (editApp.new_opts, editApp.user_selections)
+        return (editApp.new_opts, editApp.install_selections)
 
 
 # -------------------------------------
@@ -722,18 +701,6 @@ def write_opts(opts: Namespace, init_file: Path):
 def default_output_dir() -> Path:
     return config.root_path / "outputs"
 
-# -------------------------------------
-def default_embedding_dir() -> Path:
-    return config.root_path / "embeddings"
-
-# -------------------------------------
-def default_lora_dir() -> Path:
-    return config.root_path / "loras"
-
-# -------------------------------------
-def default_controlnet_dir() -> Path:
-    return config.root_path / "controlnets"
-
 # -------------------------------------
 def write_default_options(program_opts: Namespace, initfile: Path):
     opt = default_startup_options(initfile)
@@ -758,14 +725,42 @@ def migrate_init_file(legacy_format:Path):
     new.nsfw_checker = old.safety_checker
     new.xformers_enabled = old.xformers
     new.conf_path = old.conf
-    new.embedding_dir = old.embedding_path
+    new.root = legacy_format.parent.resolve()
 
     invokeai_yaml = legacy_format.parent / 'invokeai.yaml'
     with open(invokeai_yaml,"w", encoding="utf-8") as outfile:
         outfile.write(new.to_yaml())
 
-    legacy_format.replace(legacy_format.parent / 'invokeai.init.old')
+    legacy_format.replace(legacy_format.parent / 'invokeai.init.orig')
 
+# -------------------------------------
+def migrate_models(root: Path):
+    from invokeai.backend.install.migrate_to_3 import do_migrate
+    do_migrate(root, root)
+
+def migrate_if_needed(opt: Namespace, root: Path)->bool:
+    # We check for to see if the runtime directory is correctly initialized.
+    old_init_file = root / 'invokeai.init'
+    new_init_file = root / 'invokeai.yaml'
+    old_hub = root / 'models/hub'
+    migration_needed =  old_init_file.exists() and not new_init_file.exists() or old_hub.exists()
+    
+    if migration_needed:
+        if opt.yes_to_all or \
+            yes_or_no(f'{str(config.root_path)} appears to be a 2.3 format root directory. Convert to version 3.0?'):
+
+            logger.info('** Migrating invokeai.init to invokeai.yaml')
+            migrate_init_file(old_init_file)
+            config.parse_args(argv=[],conf=OmegaConf.load(new_init_file))
+
+            if old_hub.exists():
+                migrate_models(config.root_path)
+        else:
+            print('Cannot continue without conversion. Aborting.')
+    
+    return migration_needed
+
+    
 # -------------------------------------
 def main():
     parser = argparse.ArgumentParser(description="InvokeAI model downloader")
@@ -831,20 +826,16 @@ def main():
     errors = set()
 
     try:
-        models_to_download = default_user_selections(opt)
-
-        # We check for to see if the runtime directory is correctly initialized.
-        old_init_file = config.root_path / 'invokeai.init'
-        new_init_file = config.root_path / 'invokeai.yaml'
-        if old_init_file.exists() and not new_init_file.exists():
-            print('** Migrating invokeai.init to invokeai.yaml')
-            migrate_init_file(old_init_file)
-            # Load new init file into config
-            config.parse_args(argv=[],conf=OmegaConf.load(new_init_file))
+        # if we do a root migration/upgrade, then we are keeping previous
+        # configuration and we are done.
+        if migrate_if_needed(opt, config.root_path):
+            sys.exit(0)
 
         if not config.model_conf_path.exists():
             initialize_rootdir(config.root_path, opt.yes_to_all)
 
+        models_to_download = default_user_selections(opt)
+        new_init_file = config.root_path / 'invokeai.yaml'
         if opt.yes_to_all:
             write_default_options(opt, new_init_file)
             init_options = Namespace(
@@ -855,29 +846,21 @@ def main():
             if init_options:
                 write_opts(init_options, new_init_file)
             else:
-                print(
+                logger.info(
                     '\n** CANCELLED AT USER\'S REQUEST. USE THE "invoke.sh" LAUNCHER TO RUN LATER **\n'
                 )
                 sys.exit(0)
-
+                
         if opt.skip_support_models:
-            print("\n** SKIPPING SUPPORT MODEL DOWNLOADS PER USER REQUEST **")
+            logger.info("SKIPPING SUPPORT MODEL DOWNLOADS PER USER REQUEST")
         else:
-            print("\n** CHECKING/UPDATING SUPPORT MODELS **")
-            download_bert()
-            download_sd1_clip()
-            download_sd2_clip()
-            download_realesrgan()
-            download_gfpgan()
-            download_codeformer()
-            download_clipseg()
-            download_safety_checker()
-            download_vaes()
+            logger.info("CHECKING/UPDATING SUPPORT MODELS")
+            download_support_models()
 
         if opt.skip_sd_weights:
-            print("\n** SKIPPING DIFFUSION WEIGHTS DOWNLOAD PER USER REQUEST **")
+            logger.info("\n** SKIPPING DIFFUSION WEIGHTS DOWNLOAD PER USER REQUEST **")
         elif models_to_download:
-            print("\n** DOWNLOADING DIFFUSION WEIGHTS **")
+            logger.info("\n** DOWNLOADING DIFFUSION WEIGHTS **")
             process_and_execute(opt, models_to_download)
 
         postscript(errors=errors)

invokeai/backend/install/legacy_arg_parsing.py

@@ -4,11 +4,14 @@ import argparse
 import shlex
 from argparse import ArgumentParser
 
+# note that this includes both old sampler names and new scheduler names
+# in order to be able to parse both 2.0 and 3.0-pre-nodes versions of invokeai.init
 SAMPLER_CHOICES = [
     "ddim",
     "ddpm",
     "deis",
     "lms",
+    "lms_k",
     "pndm",
     "heun",
     "heun_k",
@@ -18,9 +21,23 @@ SAMPLER_CHOICES = [
     "kdpm_2",
     "kdpm_2_a",
     "dpmpp_2s",
+    "dpmpp_2s_k",
     "dpmpp_2m",
     "dpmpp_2m_k",
+    "dpmpp_2m_sde",
+    "dpmpp_2m_sde_k",
+    "dpmpp_sde",
+    "dpmpp_sde_k",
     "unipc",
+    "k_dpm_2_a",
+    "k_dpm_2",
+    "k_dpmpp_2_a",
+    "k_dpmpp_2",
+    "k_euler_a",
+    "k_euler",
+    "k_heun",
+    "k_lms",
+    "plms",
 ]
 
 PRECISION_CHOICES = [

invokeai/backend/install/migrate_to_3.py

@@ -0,0 +1,606 @@
+'''
+Migrate the models directory and models.yaml file from an existing
+InvokeAI 2.3 installation to 3.0.0.
+'''
+
+import os
+import argparse
+import shutil
+import yaml
+
+import transformers
+import diffusers
+import warnings
+
+from dataclasses import dataclass
+from pathlib import Path
+from omegaconf import OmegaConf, DictConfig
+from typing import Union
+
+from diffusers import StableDiffusionPipeline, AutoencoderKL
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from transformers import (
+    CLIPTextModel,
+    CLIPTokenizer,
+    AutoFeatureExtractor,
+    BertTokenizerFast,
+)
+
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import InvokeAIAppConfig
+from invokeai.backend.model_management import ModelManager
+from invokeai.backend.model_management.model_probe import (
+    ModelProbe, ModelType, BaseModelType, ModelProbeInfo
+    )
+
+warnings.filterwarnings("ignore")
+transformers.logging.set_verbosity_error()
+diffusers.logging.set_verbosity_error()
+
+# holder for paths that we will migrate
+@dataclass
+class ModelPaths:
+    models: Path
+    embeddings: Path
+    loras: Path
+    controlnets: Path
+
+class MigrateTo3(object):
+    def __init__(self,
+                 from_root: Path,
+                 to_models: Path,
+                 model_manager: ModelManager,
+                 src_paths: ModelPaths,
+                 ):
+        self.root_directory = from_root
+        self.dest_models = to_models
+        self.mgr = model_manager
+        self.src_paths = src_paths
+        
+    @classmethod
+    def initialize_yaml(cls, yaml_file: Path):
+        with open(yaml_file, 'w') as file:
+            file.write(
+                yaml.dump(
+                    {
+                        '__metadata__': {'version':'3.0.0'}
+                    }
+                )
+            )
+    
+    def create_directory_structure(self):
+        '''
+        Create the basic directory structure for the models folder.
+        '''
+        for model_base in [BaseModelType.StableDiffusion1,BaseModelType.StableDiffusion2]:
+            for model_type in [ModelType.Main, ModelType.Vae, ModelType.Lora,
+                               ModelType.ControlNet,ModelType.TextualInversion]:
+                path = self.dest_models / model_base.value / model_type.value
+                path.mkdir(parents=True, exist_ok=True)
+        path = self.dest_models / 'core'
+        path.mkdir(parents=True, exist_ok=True)
+
+    @staticmethod
+    def copy_file(src:Path,dest:Path):
+        '''
+        copy a single file with logging
+        '''
+        if dest.exists():
+            logger.info(f'Skipping existing {str(dest)}')
+            return
+        logger.info(f'Copying {str(src)} to {str(dest)}')
+        try:
+            shutil.copy(src, dest)
+        except Exception as e:
+            logger.error(f'COPY FAILED: {str(e)}')
+
+    @staticmethod
+    def copy_dir(src:Path,dest:Path):
+        '''
+        Recursively copy a directory with logging
+        '''
+        if dest.exists():
+            logger.info(f'Skipping existing {str(dest)}')
+            return
+        
+        logger.info(f'Copying {str(src)} to {str(dest)}')
+        try:
+            shutil.copytree(src, dest)
+        except Exception as e:
+            logger.error(f'COPY FAILED: {str(e)}')
+
+    def migrate_models(self, src_dir: Path):
+        '''
+        Recursively walk through src directory, probe anything
+        that looks like a model, and copy the model into the
+        appropriate location within the destination models directory.
+        '''
+        directories_scanned = set()
+        for root, dirs, files in os.walk(src_dir):
+            for d in dirs:
+                try:
+                    model = Path(root,d)
+                    info = ModelProbe().heuristic_probe(model)
+                    if not info:
+                        continue
+                    dest = self._model_probe_to_path(info) / model.name
+                    self.copy_dir(model, dest)
+                    directories_scanned.add(model)
+                except Exception as e:
+                    logger.error(str(e))
+                except KeyboardInterrupt:
+                    raise
+                except Exception as e:
+                    logger.error(str(e))
+            for f in files:
+                # don't copy raw learned_embeds.bin or pytorch_lora_weights.bin
+                # let them be copied as part of a tree copy operation
+                try:
+                    if f in {'learned_embeds.bin','pytorch_lora_weights.bin'}:
+                        continue
+                    model = Path(root,f)
+                    if model.parent in directories_scanned:
+                        continue
+                    info = ModelProbe().heuristic_probe(model)
+                    if not info:
+                        continue
+                    dest = self._model_probe_to_path(info) / f
+                    self.copy_file(model, dest)
+                except Exception as e:
+                    logger.error(str(e))
+                except KeyboardInterrupt:
+                    raise
+                except Exception as e:
+                    logger.error(str(e))
+
+    def migrate_support_models(self):
+        '''
+        Copy the clipseg, upscaler, and restoration models to their new
+        locations.
+        '''
+        dest_directory = self.dest_models
+        if (self.root_directory / 'models/clipseg').exists():
+            self.copy_dir(self.root_directory / 'models/clipseg', dest_directory / 'core/misc/clipseg')
+        if (self.root_directory / 'models/realesrgan').exists():
+            self.copy_dir(self.root_directory / 'models/realesrgan', dest_directory / 'core/upscaling/realesrgan')
+        for d in ['codeformer','gfpgan']:
+            path = self.root_directory / 'models' / d
+            if path.exists():
+                self.copy_dir(path,dest_directory / f'core/face_restoration/{d}')
+
+    def migrate_tuning_models(self):
+        '''
+        Migrate the embeddings, loras and controlnets directories to their new homes.
+        '''
+        for src in [self.src_paths.embeddings, self.src_paths.loras, self.src_paths.controlnets]:
+            if not src:
+                continue
+            if src.is_dir():
+                logger.info(f'Scanning {src}')
+                self.migrate_models(src)
+            else:
+                logger.info(f'{src} directory not found; skipping')
+                continue
+
+    def migrate_conversion_models(self):
+        '''
+        Migrate all the models that are needed by the ckpt_to_diffusers conversion
+        script.
+        '''
+
+        dest_directory = self.dest_models
+        kwargs = dict(
+            cache_dir = self.root_directory / 'models/hub',
+            #local_files_only = True
+        )
+        try:
+            logger.info('Migrating core tokenizers and text encoders')
+            target_dir = dest_directory / 'core' / 'convert'
+
+            self._migrate_pretrained(BertTokenizerFast,
+                                     repo_id='bert-base-uncased',
+                                     dest = target_dir / 'bert-base-uncased',
+                                     **kwargs)
+
+            # sd-1
+            repo_id = 'openai/clip-vit-large-patch14'
+            self._migrate_pretrained(CLIPTokenizer,
+                                     repo_id= repo_id,
+                                     dest= target_dir / 'clip-vit-large-patch14',
+                                     **kwargs)
+            self._migrate_pretrained(CLIPTextModel,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'clip-vit-large-patch14',
+                                     force = True,
+                                     **kwargs)
+
+            # sd-2
+            repo_id = "stabilityai/stable-diffusion-2"
+            self._migrate_pretrained(CLIPTokenizer,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-2-clip' / 'tokenizer',
+                                     **{'subfolder':'tokenizer',**kwargs}
+                                     )
+            self._migrate_pretrained(CLIPTextModel,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-2-clip' / 'text_encoder',
+                                     **{'subfolder':'text_encoder',**kwargs}
+                                     )
+
+            # VAE
+            logger.info('Migrating stable diffusion VAE')
+            self._migrate_pretrained(AutoencoderKL,
+                                     repo_id = 'stabilityai/sd-vae-ft-mse',
+                                     dest = target_dir / 'sd-vae-ft-mse',
+                                     **kwargs)
+            
+            # safety checking
+            logger.info('Migrating safety checker')
+            repo_id = "CompVis/stable-diffusion-safety-checker"
+            self._migrate_pretrained(AutoFeatureExtractor,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-safety-checker',
+                                     **kwargs)
+            self._migrate_pretrained(StableDiffusionSafetyChecker,
+                                     repo_id = repo_id,
+                                     dest = target_dir / 'stable-diffusion-safety-checker',
+                                     **kwargs)
+        except KeyboardInterrupt:
+            raise
+        except Exception as e:
+            logger.error(str(e))
+
+    def _model_probe_to_path(self, info: ModelProbeInfo)->Path:
+        return Path(self.dest_models, info.base_type.value, info.model_type.value)
+
+    def _migrate_pretrained(self, model_class, repo_id: str, dest: Path, force:bool=False, **kwargs):
+        if dest.exists() and not force:
+            logger.info(f'Skipping existing {dest}')
+            return
+        model = model_class.from_pretrained(repo_id, **kwargs)
+        self._save_pretrained(model, dest, overwrite=force)
+
+    def _save_pretrained(self, model, dest: Path, overwrite: bool=False):
+        model_name = dest.name
+        if overwrite:
+            model.save_pretrained(dest, safe_serialization=True)
+        else:
+            download_path = dest.with_name(f'{model_name}.downloading')
+            model.save_pretrained(download_path, safe_serialization=True)
+            download_path.replace(dest)
+
+    def _download_vae(self, repo_id: str, subfolder:str=None)->Path:
+        vae = AutoencoderKL.from_pretrained(repo_id, cache_dir=self.root_directory / 'models/hub', subfolder=subfolder)
+        info = ModelProbe().heuristic_probe(vae)
+        _, model_name = repo_id.split('/')
+        dest = self._model_probe_to_path(info) / self.unique_name(model_name, info)
+        vae.save_pretrained(dest, safe_serialization=True)
+        return dest
+
+    def _vae_path(self, vae: Union[str,dict])->Path:
+        '''
+        Convert 2.3 VAE stanza to a straight path.
+        '''
+        vae_path = None
+        
+        # First get a path
+        if isinstance(vae,str):
+            vae_path = vae
+
+        elif isinstance(vae,DictConfig):
+            if p := vae.get('path'):
+                vae_path = p
+            elif repo_id := vae.get('repo_id'):
+                if repo_id=='stabilityai/sd-vae-ft-mse':  # this guy is already downloaded
+                    vae_path = 'models/core/convert/sd-vae-ft-mse'
+                    return vae_path
+                else:
+                    vae_path = self._download_vae(repo_id, vae.get('subfolder'))
+
+        assert vae_path is not None, "Couldn't find VAE for this model"
+
+        # if the VAE is in the old models directory, then we must move it into the new
+        # one. VAEs outside of this directory can stay where they are.
+        vae_path = Path(vae_path)
+        if vae_path.is_relative_to(self.src_paths.models):
+            info = ModelProbe().heuristic_probe(vae_path)
+            dest = self._model_probe_to_path(info) / vae_path.name
+            if not dest.exists():
+                if vae_path.is_dir():
+                    self.copy_dir(vae_path,dest)
+                else:
+                    self.copy_file(vae_path,dest)
+            vae_path = dest
+
+        if vae_path.is_relative_to(self.dest_models):
+            rel_path = vae_path.relative_to(self.dest_models)
+            return Path('models',rel_path)
+        else:
+            return vae_path
+
+    def migrate_repo_id(self, repo_id: str, model_name: str=None, **extra_config):
+        '''
+        Migrate a locally-cached diffusers pipeline identified with a repo_id
+        '''
+        dest_dir = self.dest_models
+        
+        cache = self.root_directory / 'models/hub'
+        kwargs = dict(
+            cache_dir = cache,
+            safety_checker = None,
+            # local_files_only = True,
+        )
+
+        owner,repo_name = repo_id.split('/')
+        model_name = model_name or repo_name
+        model = cache / '--'.join(['models',owner,repo_name])
+        
+        if len(list(model.glob('snapshots/**/model_index.json')))==0:
+            return
+        revisions = [x.name for x in model.glob('refs/*')]
+
+        # if an fp16 is available we use that
+        revision = 'fp16' if len(revisions) > 1 and 'fp16' in revisions else revisions[0]
+        pipeline = StableDiffusionPipeline.from_pretrained(
+            repo_id,
+            revision=revision,
+            **kwargs)
+
+        info = ModelProbe().heuristic_probe(pipeline)
+        if not info:
+            return
+
+        if self.mgr.model_exists(model_name, info.base_type, info.model_type):
+            logger.warning(f'A model named {model_name} already exists at the destination. Skipping migration.')
+            return
+
+        dest = self._model_probe_to_path(info) / model_name
+        self._save_pretrained(pipeline, dest)
+            
+        rel_path = Path('models',dest.relative_to(dest_dir))
+        self._add_model(model_name, info, rel_path, **extra_config)
+
+    def migrate_path(self, location: Path, model_name: str=None, **extra_config):
+        '''
+        Migrate a model referred to using 'weights' or 'path'
+        '''
+
+        # handle relative paths
+        dest_dir = self.dest_models
+        location = self.root_directory / location
+        model_name = model_name or location.stem
+        
+        info = ModelProbe().heuristic_probe(location)
+        if not info:
+            return
+        
+        if self.mgr.model_exists(model_name, info.base_type, info.model_type):
+            logger.warning(f'A model named {model_name} already exists at the destination. Skipping migration.')
+            return
+
+        # uh oh, weights is in the old models directory - move it into the new one
+        if Path(location).is_relative_to(self.src_paths.models):
+            dest = Path(dest_dir, info.base_type.value, info.model_type.value, location.name)
+            if location.is_dir():
+                self.copy_dir(location,dest)
+            else:
+                self.copy_file(location,dest)
+            location = Path('models', info.base_type.value, info.model_type.value, location.name)
+
+        self._add_model(model_name, info, location, **extra_config)
+
+    def _add_model(self,
+                   model_name: str,
+                   info: ModelProbeInfo,
+                   location: Path,
+                   **extra_config):
+        if info.model_type != ModelType.Main:
+            return
+        
+        self.mgr.add_model(
+            model_name = model_name,
+            base_model = info.base_type,
+            model_type = info.model_type,
+            clobber = True,
+            model_attributes = {
+                'path': str(location),
+                'description': f'A {info.base_type.value} {info.model_type.value} model',
+                'model_format': info.format,
+                'variant': info.variant_type.value,
+                **extra_config,
+            }
+        )
+        
+    def migrate_defined_models(self):
+        '''
+        Migrate models defined in models.yaml
+        '''
+        # find any models referred to in old models.yaml
+        conf = OmegaConf.load(self.root_directory / 'configs/models.yaml')
+        
+        for model_name, stanza in conf.items():
+
+            try:
+                passthru_args = {}
+                
+                if vae := stanza.get('vae'):
+                    try:
+                        passthru_args['vae'] = str(self._vae_path(vae))
+                    except Exception as e:
+                        logger.warning(f'Could not find a VAE matching "{vae}" for model "{model_name}"')
+                        logger.warning(str(e))
+
+                if config := stanza.get('config'):
+                    passthru_args['config'] = config
+
+                if description:= stanza.get('description'):
+                    passthru_args['description'] = description
+                
+                if repo_id := stanza.get('repo_id'):
+                    logger.info(f'Migrating diffusers model {model_name}')
+                    self.migrate_repo_id(repo_id, model_name, **passthru_args)
+
+                elif location := stanza.get('weights'):
+                    logger.info(f'Migrating checkpoint model {model_name}')
+                    self.migrate_path(Path(location), model_name, **passthru_args)
+                    
+                elif location := stanza.get('path'):
+                    logger.info(f'Migrating diffusers model {model_name}')
+                    self.migrate_path(Path(location), model_name, **passthru_args)
+                    
+            except KeyboardInterrupt:
+                raise
+            except Exception as e:
+                logger.error(str(e))
+                    
+    def migrate(self):
+        self.create_directory_structure()
+        # the configure script is doing this
+        self.migrate_support_models()
+        self.migrate_conversion_models()
+        self.migrate_tuning_models()
+        self.migrate_defined_models()
+
+def _parse_legacy_initfile(root: Path, initfile: Path)->ModelPaths:
+    '''
+    Returns tuple of (embedding_path, lora_path, controlnet_path)
+    '''
+    parser = argparse.ArgumentParser(fromfile_prefix_chars='@')
+    parser.add_argument(
+        '--embedding_directory',
+        '--embedding_path',
+        type=Path,
+        dest='embedding_path',
+        default=Path('embeddings'),
+    )
+    parser.add_argument(
+        '--lora_directory',
+        dest='lora_path',
+        type=Path,
+        default=Path('loras'),
+    )
+    opt,_ = parser.parse_known_args([f'@{str(initfile)}'])
+    return ModelPaths(
+        models = root / 'models',
+        embeddings = root / str(opt.embedding_path).strip('"'),
+        loras = root / str(opt.lora_path).strip('"'),
+        controlnets = root / 'controlnets',
+    )
+
+def _parse_legacy_yamlfile(root: Path, initfile: Path)->ModelPaths:
+    '''
+    Returns tuple of (embedding_path, lora_path, controlnet_path)
+    '''
+    # Don't use the config object because it is unforgiving of version updates
+    # Just use omegaconf directly
+    opt = OmegaConf.load(initfile)
+    paths = opt.InvokeAI.Paths
+    models = paths.get('models_dir','models')
+    embeddings = paths.get('embedding_dir','embeddings')
+    loras = paths.get('lora_dir','loras')
+    controlnets = paths.get('controlnet_dir','controlnets')
+    return ModelPaths(
+        models = root / models,
+        embeddings = root / embeddings,
+        loras = root /loras,
+        controlnets = root / controlnets,
+    )
+    
+def get_legacy_embeddings(root: Path) -> ModelPaths:
+    path = root / 'invokeai.init'
+    if path.exists():
+        return _parse_legacy_initfile(root, path)
+    path = root / 'invokeai.yaml'
+    if path.exists():
+        return _parse_legacy_yamlfile(root, path)
+
+def do_migrate(src_directory: Path, dest_directory: Path):
+    """
+    Migrate models from src to dest InvokeAI root directories
+    """
+    config_file = dest_directory / 'configs' / 'models.yaml.3'
+    dest_models = dest_directory / 'models.3'
+    
+    version_3 = (dest_directory / 'models' / 'core').exists()
+
+    # Here we create the destination models.yaml file.
+    # If we are writing into a version 3 directory and the
+    # file already exists, then we write into a copy of it to
+    # avoid deleting its previous customizations. Otherwise we
+    # create a new empty one.
+    if version_3:  # write into the dest directory
+        try:
+            shutil.copy(dest_directory / 'configs' / 'models.yaml', config_file)
+        except:
+            MigrateTo3.initialize_yaml(config_file)
+        mgr = ModelManager(config_file) # important to initialize BEFORE moving the models directory
+        (dest_directory / 'models').replace(dest_models)
+    else:
+        MigrateTo3.initialize_yaml(config_file)
+        mgr = ModelManager(config_file)
+    
+    paths = get_legacy_embeddings(src_directory)
+    migrator = MigrateTo3(
+        from_root = src_directory,
+        to_models = dest_models,
+        model_manager = mgr,
+        src_paths = paths
+    )
+    migrator.migrate()
+    print("Migration successful.")
+
+    if not version_3:
+        (dest_directory / 'models').replace(src_directory / 'models.orig')
+        print(f'Original models directory moved to {dest_directory}/models.orig')
+        
+    (dest_directory / 'configs' / 'models.yaml').replace(src_directory / 'configs' / 'models.yaml.orig')
+    print(f'Original models.yaml file moved to {dest_directory}/configs/models.yaml.orig')
+    
+    config_file.replace(config_file.with_suffix(''))
+    dest_models.replace(dest_models.with_suffix(''))
+    
+def main():
+    parser = argparse.ArgumentParser(prog="invokeai-migrate3",
+                                     description="""
+This will copy and convert the models directory and the configs/models.yaml from the InvokeAI 2.3 format 
+'--from-directory' root to the InvokeAI 3.0 '--to-directory' root. These may be abbreviated '--from' and '--to'.a
+
+The old models directory and config file will be renamed 'models.orig' and 'models.yaml.orig' respectively.
+It is safe to provide the same directory for both arguments, but it is better to use the invokeai_configure
+script, which will perform a full upgrade in place."""
+                                     )
+    parser.add_argument('--from-directory',
+                        dest='src_root',
+                        type=Path,
+                        required=True,
+                        help='Source InvokeAI 2.3 root directory (containing "invokeai.init" or "invokeai.yaml")'
+                        )
+    parser.add_argument('--to-directory',
+                        dest='dest_root',
+                        type=Path,
+                        required=True,
+                        help='Destination InvokeAI 3.0 directory (containing "invokeai.yaml")'
+                        )
+    args = parser.parse_args()
+    src_root = args.src_root
+    assert src_root.is_dir(), f"{src_root} is not a valid directory"
+    assert (src_root / 'models').is_dir(), f"{src_root} does not contain a 'models' subdirectory"
+    assert (src_root / 'models' / 'hub').exists(), f"{src_root} does not contain a version 2.3 models directory"
+    assert (src_root / 'invokeai.init').exists() or (src_root / 'invokeai.yaml').exists(), f"{src_root} does not contain an InvokeAI init file."
+
+    dest_root = args.dest_root
+    assert dest_root.is_dir(), f"{dest_root} is not a valid directory"
+    config = InvokeAIAppConfig.get_config()
+    config.parse_args(['--root',str(dest_root)])
+
+    # TODO: revisit
+    # assert (dest_root / 'models').is_dir(), f"{dest_root} does not contain a 'models' subdirectory"
+    # assert (dest_root / 'invokeai.yaml').exists(), f"{dest_root} does not contain an InvokeAI init file."
+
+    do_migrate(src_root,dest_root)
+
+if __name__ == '__main__':
+    main()
+
+
+

invokeai/backend/install/model_install_backend.py

@@ -2,46 +2,37 @@
 Utility (backend) functions used by model_install.py
 """
 import os
-import re
 import shutil
-import sys
 import warnings
 from dataclasses import dataclass,field
 from pathlib import Path
-from tempfile import TemporaryFile
-from typing import List, Dict, Callable
+from tempfile import TemporaryDirectory
+from typing import List, Dict, Callable, Union, Set
 
 import requests
-from diffusers import AutoencoderKL
-from huggingface_hub import hf_hub_url, HfFolder
+from diffusers import StableDiffusionPipeline
+from diffusers import logging as dlogging
+from huggingface_hub import hf_hub_url, HfFolder, HfApi
 from omegaconf import OmegaConf
-from omegaconf.dictconfig import DictConfig
 from tqdm import tqdm
 
 import invokeai.configs as configs
 
-
 from invokeai.app.services.config import InvokeAIAppConfig
-from ..stable_diffusion import StableDiffusionGeneratorPipeline
+from invokeai.backend.model_management import ModelManager, ModelType, BaseModelType, ModelVariantType, AddModelResult
+from invokeai.backend.model_management.model_probe import ModelProbe, SchedulerPredictionType, ModelProbeInfo
+from invokeai.backend.util import download_with_resume
 from ..util.logging import InvokeAILogger
 
 warnings.filterwarnings("ignore")
 
 # --------------------------globals-----------------------
 config = InvokeAIAppConfig.get_config()
-
-Model_dir = "models"
-Weights_dir = "ldm/stable-diffusion-v1/"
+logger = InvokeAILogger.getLogger(name='InvokeAI')
 
 # the initial "configs" dir is now bundled in the `invokeai.configs` package
 Dataset_path = Path(configs.__path__[0]) / "INITIAL_MODELS.yaml"
 
-# initial models omegaconf
-Datasets = None
-
-# logger
-logger = InvokeAILogger.getLogger(name='InvokeAI')
-
 Config_preamble = """
 # This file describes the alternative machine learning models
 # available to InvokeAI script.
@@ -52,6 +43,24 @@ Config_preamble = """
 # was trained on.
 """
 
+LEGACY_CONFIGS = {
+    BaseModelType.StableDiffusion1: {
+        ModelVariantType.Normal: 'v1-inference.yaml',
+        ModelVariantType.Inpaint: 'v1-inpainting-inference.yaml',
+    },
+
+    BaseModelType.StableDiffusion2: {
+        ModelVariantType.Normal: {
+            SchedulerPredictionType.Epsilon: 'v2-inference.yaml',
+            SchedulerPredictionType.VPrediction: 'v2-inference-v.yaml',
+        },
+        ModelVariantType.Inpaint: {
+            SchedulerPredictionType.Epsilon: 'v2-inpainting-inference.yaml',
+            SchedulerPredictionType.VPrediction: 'v2-inpainting-inference-v.yaml',
+        }
+    }
+}
+
 @dataclass
 class ModelInstallList:
     '''Class for listing models to be installed/removed'''
@@ -59,133 +68,332 @@ class ModelInstallList:
     remove_models: List[str] = field(default_factory=list)
 
 @dataclass
-class UserSelections():
+class InstallSelections():
     install_models: List[str]= field(default_factory=list)
     remove_models: List[str]=field(default_factory=list)
-    purge_deleted_models: bool=field(default_factory=list)
-    install_cn_models: List[str] = field(default_factory=list)
-    remove_cn_models: List[str] = field(default_factory=list)
-    install_lora_models: List[str] = field(default_factory=list)
-    remove_lora_models: List[str] = field(default_factory=list)
-    install_ti_models: List[str] = field(default_factory=list)
-    remove_ti_models: List[str] = field(default_factory=list)
-    scan_directory: Path = None
-    autoscan_on_startup: bool=False
-    import_model_paths: str=None
+#    scan_directory: Path = None
+#    autoscan_on_startup: bool=False
+
+@dataclass
+class ModelLoadInfo():
+    name: str
+    model_type: ModelType
+    base_type: BaseModelType
+    path: Path = None
+    repo_id: str = None
+    description: str = ''
+    installed: bool = False
+    recommended: bool = False
+    default: bool = False
+
+class ModelInstall(object):
+    def __init__(self,
+                 config:InvokeAIAppConfig,
+                 prediction_type_helper: Callable[[Path],SchedulerPredictionType]=None,
+                 model_manager: ModelManager = None,
+                 access_token:str = None):
+        self.config = config
+        self.mgr = model_manager or ModelManager(config.model_conf_path)
+        self.datasets = OmegaConf.load(Dataset_path)
+        self.prediction_helper = prediction_type_helper
+        self.access_token = access_token or HfFolder.get_token()
+        self.reverse_paths = self._reverse_paths(self.datasets)
+
+    def all_models(self)->Dict[str,ModelLoadInfo]:
+        '''
+        Return dict of model_key=>ModelLoadInfo objects.
+        This method consolidates and simplifies the entries in both
+        models.yaml and INITIAL_MODELS.yaml so that they can
+        be treated uniformly. It also sorts the models alphabetically
+        by their name, to improve the display somewhat.
+        '''
+        model_dict = dict()
         
-def default_config_file():
-    return config.model_conf_path
+        # first populate with the entries in INITIAL_MODELS.yaml
+        for key, value in self.datasets.items():
+            name,base,model_type = ModelManager.parse_key(key)
+            value['name'] = name
+            value['base_type'] = base
+            value['model_type'] = model_type
+            model_dict[key] = ModelLoadInfo(**value)
 
-def sd_configs():
-    return config.legacy_conf_path
-
-def initial_models():
-    global Datasets
-    if Datasets:
-        return Datasets
-    return (Datasets := OmegaConf.load(Dataset_path)['diffusers'])
-
-def install_requested_models(
-        diffusers: ModelInstallList = None,
-        controlnet: ModelInstallList = None,
-        lora: ModelInstallList = None,
-        ti: ModelInstallList = None,
-        cn_model_map: Dict[str,str] = None, # temporary - move to model manager
-        scan_directory: Path = None,
-        external_models: List[str] = None,
-        scan_at_startup: bool = False,
-        precision: str = "float16",
-        purge_deleted: bool = False,
-        config_file_path: Path = None,
-        model_config_file_callback:  Callable[[Path],Path] = None
-):
-    """
-    Entry point for installing/deleting starter models, or installing external models.
-    """
-    access_token = HfFolder.get_token()
-    config_file_path = config_file_path or default_config_file()
-    if not config_file_path.exists():
-        open(config_file_path, "w")
-
-    # prevent circular import here
-    from ..model_management import ModelManager
-    model_manager = ModelManager(OmegaConf.load(config_file_path), precision=precision)
-    if controlnet:
-        model_manager.install_controlnet_models(controlnet.install_models, access_token=access_token)
-        model_manager.delete_controlnet_models(controlnet.remove_models)
-
-    if lora:
-        model_manager.install_lora_models(lora.install_models, access_token=access_token)
-        model_manager.delete_lora_models(lora.remove_models)
-
-    if ti:
-        model_manager.install_ti_models(ti.install_models, access_token=access_token)
-        model_manager.delete_ti_models(ti.remove_models)
-
-    if diffusers:
-        # TODO: Replace next three paragraphs with calls into new model manager
-        if diffusers.remove_models and len(diffusers.remove_models) > 0:
-            logger.info("Processing requested deletions")
-            for model in diffusers.remove_models:
-                logger.info(f"{model}...")
-                model_manager.del_model(model, delete_files=purge_deleted)
-            model_manager.commit(config_file_path)
-
-        if diffusers.install_models and len(diffusers.install_models) > 0:
-            logger.info("Installing requested models")
-            downloaded_paths = download_weight_datasets(
-                models=diffusers.install_models,
-                access_token=None,
-                precision=precision,
-            )
-            successful = {x:v for x,v in downloaded_paths.items() if v is not None}
-            if len(successful) > 0:
-                update_config_file(successful, config_file_path)
-            if len(successful) < len(diffusers.install_models):
-                unsuccessful = [x for x in downloaded_paths if downloaded_paths[x] is None]
-                logger.warning(f"Some of the model downloads were not successful: {unsuccessful}")
-
-    # due to above, we have to reload the model manager because conf file
-    # was changed behind its back
-    model_manager = ModelManager(OmegaConf.load(config_file_path), precision=precision)
-
-    external_models = external_models or list()
-    if scan_directory:
-        external_models.append(str(scan_directory))
-
-    if len(external_models) > 0:
-        logger.info("INSTALLING EXTERNAL MODELS")
-        for path_url_or_repo in external_models:
-            try:
-                logger.debug(f'In install_requested_models; callback = {model_config_file_callback}')
-                model_manager.heuristic_import(
-                    path_url_or_repo,
-                    commit_to_conf=config_file_path,
-                    config_file_callback = model_config_file_callback,
+        # supplement with entries in models.yaml
+        installed_models = self.mgr.list_models()
+        for md in installed_models:
+            base = md['base_model']
+            model_type = md['type']
+            name = md['name']
+            key = ModelManager.create_key(name, base, model_type)
+            if key in model_dict:
+                model_dict[key].installed = True
+            else:
+                model_dict[key] = ModelLoadInfo(
+                    name = name,
+                    base_type = base,
+                    model_type = model_type,
+                    path = value.get('path'),
+                    installed = True,
                 )
-            except KeyboardInterrupt:
-                sys.exit(-1)
-            except Exception:
+        return {x : model_dict[x] for x in sorted(model_dict.keys(),key=lambda y: model_dict[y].name.lower())}
+
+    def starter_models(self)->Set[str]:
+        models = set()
+        for key, value in self.datasets.items():
+            name,base,model_type = ModelManager.parse_key(key)
+            if model_type==ModelType.Main:
+                models.add(key)
+        return models
+
+    def recommended_models(self)->Set[str]:
+        starters = self.starter_models()
+        return set([x for x in starters if self.datasets[x].get('recommended',False)])
+    
+    def default_model(self)->str:
+        starters = self.starter_models()
+        defaults = [x for x in starters if self.datasets[x].get('default',False)]
+        return defaults[0]
+
+    def install(self, selections: InstallSelections):
+        verbosity = dlogging.get_verbosity()  # quench NSFW nags
+        dlogging.set_verbosity_error()
+
+        job = 1
+        jobs = len(selections.remove_models) + len(selections.install_models)
+        
+        # remove requested models
+        for key in selections.remove_models:
+            name,base,mtype = self.mgr.parse_key(key)
+            logger.info(f'Deleting {mtype} model {name} [{job}/{jobs}]')
+            try:
+                self.mgr.del_model(name,base,mtype)
+            except FileNotFoundError as e:
+                logger.warning(e)
+            job += 1
+            
+        # add requested models
+        for path in selections.install_models:
+            logger.info(f'Installing {path} [{job}/{jobs}]')
+            try:
+                self.heuristic_import(path)
+            except (ValueError, KeyError) as e:
+                logger.error(str(e))
+            job += 1
+            
+        dlogging.set_verbosity(verbosity)
+        self.mgr.commit()
+
+    def heuristic_import(self,
+                         model_path_id_or_url: Union[str,Path],
+                         models_installed: Set[Path]=None,
+                         )->Dict[str, AddModelResult]:
+        '''
+        :param model_path_id_or_url: A Path to a local model to import, or a string representing its repo_id or URL
+        :param models_installed: Set of installed models, used for recursive invocation
+        Returns a set of dict objects corresponding to newly-created stanzas in models.yaml.
+        '''
+
+        if not models_installed:
+            models_installed = dict()
+            
+        # A little hack to allow nested routines to retrieve info on the requested ID
+        self.current_id = model_path_id_or_url
+        path = Path(model_path_id_or_url)
+        # checkpoint file, or similar
+        if path.is_file():
+            models_installed.update({str(path):self._install_path(path)})
+
+        # folders style or similar
+        elif path.is_dir() and any([(path/x).exists() for x in \
+                                    {'config.json','model_index.json','learned_embeds.bin','pytorch_lora_weights.bin'}
+                                    ]
+                                   ):
+            models_installed.update(self._install_path(path))
+
+        # recursive scan
+        elif path.is_dir():
+            for child in path.iterdir():
+                self.heuristic_import(child, models_installed=models_installed)
+
+        # huggingface repo
+        elif len(str(model_path_id_or_url).split('/')) == 2:
+            models_installed.update({str(model_path_id_or_url): self._install_repo(str(model_path_id_or_url))})
+
+        # a URL
+        elif str(model_path_id_or_url).startswith(("http:", "https:", "ftp:")):
+            models_installed.update({str(model_path_id_or_url): self._install_url(model_path_id_or_url)})
+
+        else:
+            raise KeyError(f'{str(model_path_id_or_url)} is not recognized as a local path, repo ID or URL. Skipping')
+
+        return models_installed
+
+    # install a model from a local path. The optional info parameter is there to prevent
+    # the model from being probed twice in the event that it has already been probed.
+    def _install_path(self, path: Path, info: ModelProbeInfo=None)->AddModelResult:
+        info = info or ModelProbe().heuristic_probe(path,self.prediction_helper)
+        if not info:
+            logger.warning(f'Unable to parse format of {path}')
+            return None
+        model_name = path.stem if path.is_file() else path.name
+        if self.mgr.model_exists(model_name, info.base_type, info.model_type):
+            raise ValueError(f'A model named "{model_name}" is already installed.')
+        attributes = self._make_attributes(path,info)
+        return self.mgr.add_model(model_name = model_name,
+                                  base_model = info.base_type,
+                                  model_type = info.model_type,
+                                  model_attributes = attributes,
+                                  )
+
+    def _install_url(self, url: str)->AddModelResult:
+        with TemporaryDirectory(dir=self.config.models_path) as staging:
+            location = download_with_resume(url,Path(staging))
+            if not location:
+                logger.error(f'Unable to download {url}. Skipping.')
+            info = ModelProbe().heuristic_probe(location)
+            dest = self.config.models_path / info.base_type.value / info.model_type.value / location.name
+            models_path = shutil.move(location,dest)
+
+        # staged version will be garbage-collected at this time
+        return self._install_path(Path(models_path), info)
+
+    def _install_repo(self, repo_id: str)->AddModelResult:
+        hinfo = HfApi().model_info(repo_id)
+        
+        # we try to figure out how to download this most economically
+        # list all the files in the repo
+        files = [x.rfilename for x in hinfo.siblings]
+        location = None
+
+        with TemporaryDirectory(dir=self.config.models_path) as staging:
+            staging = Path(staging)
+            if 'model_index.json' in files:
+                location = self._download_hf_pipeline(repo_id, staging)   # pipeline
+            else:
+                for suffix in ['safetensors','bin']:
+                    if f'pytorch_lora_weights.{suffix}' in files:
+                        location = self._download_hf_model(repo_id, ['pytorch_lora_weights.bin'], staging)  # LoRA
+                        break
+                    elif self.config.precision=='float16' and f'diffusion_pytorch_model.fp16.{suffix}' in files: # vae, controlnet or some other standalone
+                        files = ['config.json', f'diffusion_pytorch_model.fp16.{suffix}']
+                        location = self._download_hf_model(repo_id, files, staging)
+                        break
+                    elif f'diffusion_pytorch_model.{suffix}' in files:
+                        files = ['config.json', f'diffusion_pytorch_model.{suffix}']
+                        location = self._download_hf_model(repo_id, files, staging)
+                        break
+                    elif f'learned_embeds.{suffix}' in files:
+                        location = self._download_hf_model(repo_id, [f'learned_embeds.{suffix}'], staging)
+                        break
+            if not location:
+                logger.warning(f'Could not determine type of repo {repo_id}. Skipping install.')
+                return {}
+
+            info = ModelProbe().heuristic_probe(location, self.prediction_helper)
+            if not info:
+                logger.warning(f'Could not probe {location}. Skipping install.')
+                return {}
+            dest = self.config.models_path / info.base_type.value / info.model_type.value / self._get_model_name(repo_id,location)
+            if dest.exists():
+                shutil.rmtree(dest)
+            shutil.copytree(location,dest)
+            return self._install_path(dest, info)
+
+    def _get_model_name(self,path_name: str, location: Path)->str:
+        '''
+        Calculate a name for the model - primitive implementation.
+        '''
+        if key := self.reverse_paths.get(path_name):
+            (name, base, mtype) = ModelManager.parse_key(key)
+            return name
+        else:
+            return location.stem
+
+    def _make_attributes(self, path: Path, info: ModelProbeInfo)->dict:
+        model_name = path.name if path.is_dir() else path.stem
+        description = f'{info.base_type.value} {info.model_type.value} model {model_name}'
+        if key := self.reverse_paths.get(self.current_id):
+            if key in self.datasets:
+                description = self.datasets[key].get('description') or description
+
+        rel_path = self.relative_to_root(path)
+
+        attributes = dict(
+            path = str(rel_path),
+            description = str(description),
+            model_format = info.format,
+            )
+        if info.model_type == ModelType.Main:
+            attributes.update(dict(variant = info.variant_type,))
+            if info.format=="checkpoint":
+                try:
+                    possible_conf = path.with_suffix('.yaml')
+                    if possible_conf.exists():
+                        legacy_conf = str(self.relative_to_root(possible_conf))
+                    elif info.base_type == BaseModelType.StableDiffusion2:
+                        legacy_conf = Path(self.config.legacy_conf_dir, LEGACY_CONFIGS[info.base_type][info.variant_type][info.prediction_type])
+                    else:
+                        legacy_conf = Path(self.config.legacy_conf_dir, LEGACY_CONFIGS[info.base_type][info.variant_type])
+                except KeyError:
+                    legacy_conf = Path(self.config.legacy_conf_dir, 'v1-inference.yaml')  # best guess
+                    
+                attributes.update(
+                    dict(
+                        config = str(legacy_conf)
+                    )
+                )
+        return attributes
+
+    def relative_to_root(self, path: Path)->Path:
+        root = self.config.root_path
+        if path.is_relative_to(root):
+            return path.relative_to(root)
+        else:
+            return path
+
+    def _download_hf_pipeline(self, repo_id: str, staging: Path)->Path:
+        '''
+        This retrieves a StableDiffusion model from cache or remote and then
+        does a save_pretrained() to the indicated staging area.
+        '''
+        _,name = repo_id.split("/")
+        revisions = ['fp16','main'] if self.config.precision=='float16' else ['main']
+        model = None
+        for revision in revisions:
+            try:
+                model = StableDiffusionPipeline.from_pretrained(repo_id,revision=revision,safety_checker=None)
+            except:  # most errors are due to fp16 not being present. Fix this to catch other errors
                 pass
+            if model:
+                break
+        if not model:
+            logger.error(f'Diffusers model {repo_id} could not be downloaded. Skipping.')
+            return None
+        model.save_pretrained(staging / name, safe_serialization=True)
+        return staging / name
 
-    if scan_at_startup and scan_directory.is_dir():
-        update_autoconvert_dir(scan_directory)
-    else:
-        update_autoconvert_dir(None)
-
-def update_autoconvert_dir(autodir: Path):
-    '''
-    Update the "autoconvert_dir" option in invokeai.yaml
-    '''
-    invokeai_config_path = config.init_file_path
-    conf = OmegaConf.load(invokeai_config_path)
-    conf.InvokeAI.Paths.autoconvert_dir = str(autodir) if autodir else None
-    yaml = OmegaConf.to_yaml(conf)
-    tmpfile = invokeai_config_path.parent / "new_config.tmp"
-    with open(tmpfile, "w", encoding="utf-8") as outfile:
-        outfile.write(yaml)
-    tmpfile.replace(invokeai_config_path)
+    def _download_hf_model(self, repo_id: str, files: List[str], staging: Path)->Path:
+        _,name = repo_id.split("/")
+        location = staging / name
+        paths = list()
+        for filename in files:
+            p = hf_download_with_resume(repo_id,
+                                        model_dir=location,
+                                        model_name=filename,
+                                        access_token = self.access_token
+                                        )
+            if p:
+                paths.append(p)
+            else:
+                logger.warning(f'Could not download {filename} from {repo_id}.')
+            
+        return location if len(paths)>0 else None
 
+    @classmethod
+    def _reverse_paths(cls,datasets)->dict:
+        '''
+        Reverse mapping from repo_id/path to destination name.
+        '''
+        return {v.get('path') or v.get('repo_id') : k for k, v in datasets.items()}
 
 # -------------------------------------
 def yes_or_no(prompt: str, default_yes=True):
@@ -197,133 +405,19 @@ def yes_or_no(prompt: str, default_yes=True):
         return response[0] in ("y", "Y")
 
 # ---------------------------------------------
-def recommended_datasets() -> List['str']:
-    datasets = set()
-    for ds in initial_models().keys():
-        if initial_models()[ds].get("recommended", False):
-            datasets.add(ds)
-    return list(datasets)
-
-# ---------------------------------------------
-def default_dataset() -> dict:
-    datasets = set()
-    for ds in initial_models().keys():
-        if initial_models()[ds].get("default", False):
-            datasets.add(ds)
-    return list(datasets)
-
-
-# ---------------------------------------------
-def all_datasets() -> dict:
-    datasets = dict()
-    for ds in initial_models().keys():
-        datasets[ds] = True
-    return datasets
-
-
-# ---------------------------------------------
-# look for legacy model.ckpt in models directory and offer to
-# normalize its name
-def migrate_models_ckpt():
-    model_path = os.path.join(config.root_dir, Model_dir, Weights_dir)
-    if not os.path.exists(os.path.join(model_path, "model.ckpt")):
-        return
-    new_name = initial_models()["stable-diffusion-1.4"]["file"]
-    logger.warning(
-        'The Stable Diffusion v4.1 "model.ckpt" is already installed. The name will be changed to {new_name} to avoid confusion.'
-    )
-    logger.warning(f"model.ckpt => {new_name}")
-    os.replace(
-        os.path.join(model_path, "model.ckpt"), os.path.join(model_path, new_name)
-    )
-
-
-# ---------------------------------------------
-def download_weight_datasets(
-    models: List[str], access_token: str, precision: str = "float32"
-):
-    migrate_models_ckpt()
-    successful = dict()
-    for mod in models:
-        logger.info(f"Downloading {mod}:")
-        successful[mod] = _download_repo_or_file(
-            initial_models()[mod], access_token, precision=precision
-        )
-    return successful
-
-
-def _download_repo_or_file(
-    mconfig: DictConfig, access_token: str, precision: str = "float32"
-) -> Path:
-    path = None
-    if mconfig["format"] == "ckpt":
-        path = _download_ckpt_weights(mconfig, access_token)
-    else:
-        path = _download_diffusion_weights(mconfig, access_token, precision=precision)
-        if "vae" in mconfig and "repo_id" in mconfig["vae"]:
-            _download_diffusion_weights(
-                mconfig["vae"], access_token, precision=precision
-            )
-    return path
-
-def _download_ckpt_weights(mconfig: DictConfig, access_token: str) -> Path:
-    repo_id = mconfig["repo_id"]
-    filename = mconfig["file"]
-    cache_dir = os.path.join(config.root_dir, Model_dir, Weights_dir)
-    return hf_download_with_resume(
-        repo_id=repo_id,
-        model_dir=cache_dir,
-        model_name=filename,
-        access_token=access_token,
-    )
-
-
-# ---------------------------------------------
-def download_from_hf(
-    model_class: object, model_name: str, **kwargs
+def hf_download_from_pretrained(
+        model_class: object, model_name: str, destination: Path, **kwargs
 ):
     logger = InvokeAILogger.getLogger('InvokeAI')
     logger.addFilter(lambda x: 'fp16 is not a valid' not in x.getMessage())
     
-    path = config.cache_dir
     model = model_class.from_pretrained(
         model_name,
-        cache_dir=path,
         resume_download=True,
         **kwargs,
     )
-    model_name = "--".join(("models", *model_name.split("/")))
-    return path / model_name if model else None
-
-
-def _download_diffusion_weights(
-    mconfig: DictConfig, access_token: str, precision: str = "float32"
-):
-    repo_id = mconfig["repo_id"]
-    model_class = (
-        StableDiffusionGeneratorPipeline
-        if mconfig.get("format", None) == "diffusers"
-        else AutoencoderKL
-    )
-    extra_arg_list = [{"revision": "fp16"}, {}] if precision == "float16" else [{}]
-    path = None
-    for extra_args in extra_arg_list:
-        try:
-            path = download_from_hf(
-                model_class,
-                repo_id,
-                safety_checker=None,
-                **extra_args,
-            )
-        except OSError as e:
-            if 'Revision Not Found' in str(e):
-                pass
-            else:
-                logger.error(str(e))
-        if path:
-            break
-    return path
-
+    model.save_pretrained(destination, safe_serialization=True)
+    return destination
 
 # ---------------------------------------------
 def hf_download_with_resume(
@@ -383,128 +477,3 @@ def hf_download_with_resume(
     return model_dest
 
 
-# ---------------------------------------------
-def update_config_file(successfully_downloaded: dict, config_file: Path):
-    config_file = (
-        Path(config_file) if config_file is not None else default_config_file()
-    )
-
-    # In some cases (incomplete setup, etc), the default configs directory might be missing.
-    # Create it if it doesn't exist.
-    # this check is ignored if opt.config_file is specified - user is assumed to know what they
-    # are doing if they are passing a custom config file from elsewhere.
-    if config_file is default_config_file() and not config_file.parent.exists():
-        configs_src = Dataset_path.parent
-        configs_dest = default_config_file().parent
-        shutil.copytree(configs_src, configs_dest, dirs_exist_ok=True)
-
-    yaml = new_config_file_contents(successfully_downloaded, config_file)
-
-    try:
-        backup = None
-        if os.path.exists(config_file):
-            logger.warning(
-                f"{config_file.name} exists. Renaming to {config_file.stem}.yaml.orig"
-            )
-            backup = config_file.with_suffix(".yaml.orig")
-            ## Ugh. Windows is unable to overwrite an existing backup file, raises a WinError 183
-            if sys.platform == "win32" and backup.is_file():
-                backup.unlink()
-            config_file.rename(backup)
-
-        with TemporaryFile() as tmp:
-            tmp.write(Config_preamble.encode())
-            tmp.write(yaml.encode())
-
-            with open(str(config_file.expanduser().resolve()), "wb") as new_config:
-                tmp.seek(0)
-                new_config.write(tmp.read())
-
-    except Exception as e:
-        logger.error(f"Error creating config file {config_file}: {str(e)}")
-        if backup is not None:
-            logger.info("restoring previous config file")
-            ## workaround, for WinError 183, see above
-            if sys.platform == "win32" and config_file.is_file():
-                config_file.unlink()
-            backup.rename(config_file)
-        return
-    
-    logger.info(f"Successfully created new configuration file {config_file}")
-
-
-# ---------------------------------------------
-def new_config_file_contents(
-    successfully_downloaded: dict,
-    config_file: Path,
-) -> str:
-    if config_file.exists():
-        conf = OmegaConf.load(str(config_file.expanduser().resolve()))
-    else:
-        conf = OmegaConf.create()
-
-    default_selected = None
-    for model in successfully_downloaded:
-        # a bit hacky - what we are doing here is seeing whether a checkpoint
-        # version of the model was previously defined, and whether the current
-        # model is a diffusers (indicated with a path)
-        if conf.get(model) and Path(successfully_downloaded[model]).is_dir():
-            delete_weights(model, conf[model])
-
-        stanza = {}
-        mod = initial_models()[model]
-        stanza["description"] = mod["description"]
-        stanza["repo_id"] = mod["repo_id"]
-        stanza["format"] = mod["format"]
-        # diffusers don't need width and height (probably .ckpt doesn't either)
-        # so we no longer require these in INITIAL_MODELS.yaml
-        if "width" in mod:
-            stanza["width"] = mod["width"]
-        if "height" in mod:
-            stanza["height"] = mod["height"]
-        if "file" in mod:
-            stanza["weights"] = os.path.relpath(
-                successfully_downloaded[model], start=config.root_dir
-            )
-            stanza["config"] = os.path.normpath(
-                os.path.join(sd_configs(), mod["config"])
-            )
-        if "vae" in mod:
-            if "file" in mod["vae"]:
-                stanza["vae"] = os.path.normpath(
-                    os.path.join(Model_dir, Weights_dir, mod["vae"]["file"])
-                )
-            else:
-                stanza["vae"] = mod["vae"]
-        if mod.get("default", False):
-            stanza["default"] = True
-            default_selected = True
-
-        conf[model] = stanza
-
-    # if no default model was chosen, then we select the first
-    # one in the list
-    if not default_selected:
-        conf[list(successfully_downloaded.keys())[0]]["default"] = True
-
-    return OmegaConf.to_yaml(conf)
-
-
-# ---------------------------------------------
-def delete_weights(model_name: str, conf_stanza: dict):
-    if not (weights := conf_stanza.get("weights")):
-        return
-    if re.match("/VAE/", conf_stanza.get("config")):
-        return
-
-    logger.warning(
-        f"\nThe checkpoint version of {model_name} is superseded by the diffusers version. Deleting the original file {weights}?"
-    )
-
-    weights = Path(weights)
-    if not weights.is_absolute():
-        weights = config.root_dir / weights
-        try:
-            weights.unlink()
-        except OSError as e:
-            logger.error(str(e))

invokeai/backend/model_management/__init__.py

@@ -1,11 +1,8 @@
 """
 Initialization file for invokeai.backend.model_management
 """
-from .convert_ckpt_to_diffusers import (
-    convert_ckpt_to_diffusers,
-    load_pipeline_from_original_stable_diffusion_ckpt,
-)
-from .model_manager import ModelManager,SDModelComponent
-
-
+from .model_manager import ModelManager, ModelInfo, AddModelResult, SchedulerPredictionType
+from .model_cache import ModelCache
+from .models import BaseModelType, ModelType, SubModelType, ModelVariantType
+from .model_merge import ModelMerger, MergeInterpolationMethod
 

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -28,10 +28,13 @@ from safetensors.torch import load_file
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config import InvokeAIAppConfig
 
-from .model_manager import ModelManager, SDLegacyType
+from .model_manager import ModelManager
+from picklescan.scanner import scan_file_path
+from .models import BaseModelType, ModelVariantType
 
 try:
     from omegaconf import OmegaConf
+    from omegaconf.dictconfig import DictConfig
 except ImportError:
     raise ImportError(
         "OmegaConf is required to convert the LDM checkpoints. Please install it with `pip install OmegaConf`."
@@ -56,10 +59,6 @@ from diffusers.pipelines.latent_diffusion.pipeline_latent_diffusion import (
     LDMBertConfig,
     LDMBertModel,
 )
-from diffusers.pipelines.paint_by_example import (
-    PaintByExampleImageEncoder,
-    PaintByExamplePipeline,
-)
 from diffusers.pipelines.stable_diffusion.safety_checker import (
     StableDiffusionSafetyChecker,
 )
@@ -74,6 +73,10 @@ from transformers import (
 
 from ..stable_diffusion import StableDiffusionGeneratorPipeline
 
+# TODO: redo in future
+#CONVERT_MODEL_ROOT = InvokeAIAppConfig.get_config().models_path / "core" / "convert"
+CONVERT_MODEL_ROOT = InvokeAIAppConfig.get_config().root_path / "models" / "core" / "convert"
+
 def shave_segments(path, n_shave_prefix_segments=1):
     """
     Removes segments. Positive values shave the first segments, negative shave the last segments.
@@ -158,17 +161,17 @@ def renew_vae_attention_paths(old_list, n_shave_prefix_segments=0):
         new_item = new_item.replace("norm.weight", "group_norm.weight")
         new_item = new_item.replace("norm.bias", "group_norm.bias")
 
-        new_item = new_item.replace("q.weight", "query.weight")
-        new_item = new_item.replace("q.bias", "query.bias")
+        new_item = new_item.replace("q.weight", "to_q.weight")
+        new_item = new_item.replace("q.bias", "to_q.bias")
 
-        new_item = new_item.replace("k.weight", "key.weight")
-        new_item = new_item.replace("k.bias", "key.bias")
+        new_item = new_item.replace("k.weight", "to_k.weight")
+        new_item = new_item.replace("k.bias", "to_k.bias")
 
-        new_item = new_item.replace("v.weight", "value.weight")
-        new_item = new_item.replace("v.bias", "value.bias")
+        new_item = new_item.replace("v.weight", "to_v.weight")
+        new_item = new_item.replace("v.bias", "to_v.bias")
 
-        new_item = new_item.replace("proj_out.weight", "proj_attn.weight")
-        new_item = new_item.replace("proj_out.bias", "proj_attn.bias")
+        new_item = new_item.replace("proj_out.weight", "to_out.0.weight")
+        new_item = new_item.replace("proj_out.bias", "to_out.0.bias")
 
         new_item = shave_segments(
             new_item, n_shave_prefix_segments=n_shave_prefix_segments
@@ -183,7 +186,6 @@ def assign_to_checkpoint(
     paths,
     checkpoint,
     old_checkpoint,
-    attention_paths_to_split=None,
     additional_replacements=None,
     config=None,
 ):
@@ -198,35 +200,9 @@ def assign_to_checkpoint(
         paths, list
     ), "Paths should be a list of dicts containing 'old' and 'new' keys."
 
-    # Splits the attention layers into three variables.
-    if attention_paths_to_split is not None:
-        for path, path_map in attention_paths_to_split.items():
-            old_tensor = old_checkpoint[path]
-            channels = old_tensor.shape[0] // 3
-
-            target_shape = (-1, channels) if len(old_tensor.shape) == 3 else (-1)
-
-            num_heads = old_tensor.shape[0] // config["num_head_channels"] // 3
-
-            old_tensor = old_tensor.reshape(
-                (num_heads, 3 * channels // num_heads) + old_tensor.shape[1:]
-            )
-            query, key, value = old_tensor.split(channels // num_heads, dim=1)
-
-            checkpoint[path_map["query"]] = query.reshape(target_shape)
-            checkpoint[path_map["key"]] = key.reshape(target_shape)
-            checkpoint[path_map["value"]] = value.reshape(target_shape)
-
     for path in paths:
         new_path = path["new"]
 
-        # These have already been assigned
-        if (
-            attention_paths_to_split is not None
-            and new_path in attention_paths_to_split
-        ):
-            continue
-
         # Global renaming happens here
         new_path = new_path.replace("middle_block.0", "mid_block.resnets.0")
         new_path = new_path.replace("middle_block.1", "mid_block.attentions.0")
@@ -245,14 +221,14 @@ def assign_to_checkpoint(
 
 def conv_attn_to_linear(checkpoint):
     keys = list(checkpoint.keys())
-    attn_keys = ["query.weight", "key.weight", "value.weight"]
+    attn_keys = ["to_q.weight", "to_k.weight", "to_v.weight"]
     for key in keys:
         if ".".join(key.split(".")[-2:]) in attn_keys:
             if checkpoint[key].ndim > 2:
                 checkpoint[key] = checkpoint[key][:, :, 0, 0]
-        elif "proj_attn.weight" in key:
+        elif "to_out.0.weight" in key:
             if checkpoint[key].ndim > 2:
-                checkpoint[key] = checkpoint[key][:, :, 0]
+                checkpoint[key] = checkpoint[key][:, :, 0, 0]
 
 
 def create_unet_diffusers_config(original_config, image_size: int):
@@ -612,16 +588,29 @@ def convert_ldm_unet_checkpoint(checkpoint, config, path=None, extract_ema=False
 
     return new_checkpoint
 
-
 def convert_ldm_vae_checkpoint(checkpoint, config):
-    # extract state dict for VAE
-    vae_state_dict = {}
-    vae_key = "first_stage_model."
-    keys = list(checkpoint.keys())
-    for key in keys:
-        if key.startswith(vae_key):
-            vae_state_dict[key.replace(vae_key, "")] = checkpoint.get(key)
+    # Extract state dict for VAE. Works both with burnt-in
+    # VAEs, and with standalone VAEs.
 
+    # checkpoint can either be a all-in-one stable diffusion
+    # model, or an isolated vae .ckpt. This tests for
+    # a key that will be present in the all-in-one model
+    # that isn't present in the isolated ckpt.
+    probe_key = "first_stage_model.encoder.conv_in.weight"
+    if probe_key in checkpoint:
+        vae_state_dict = {}
+        vae_key = "first_stage_model."
+        keys = list(checkpoint.keys())
+        for key in keys:
+            if key.startswith(vae_key):
+                vae_state_dict[key.replace(vae_key, "")] = checkpoint.get(key)
+    else:
+        vae_state_dict = checkpoint
+        
+    new_checkpoint = convert_ldm_vae_state_dict(vae_state_dict, config)
+    return new_checkpoint
+
+def convert_ldm_vae_state_dict(vae_state_dict, config):
     new_checkpoint = {}
 
     new_checkpoint["encoder.conv_in.weight"] = vae_state_dict["encoder.conv_in.weight"]
@@ -841,10 +830,7 @@ def convert_ldm_bert_checkpoint(checkpoint, config):
 
 
 def convert_ldm_clip_checkpoint(checkpoint):
-    text_model = CLIPTextModel.from_pretrained(
-        "openai/clip-vit-large-patch14", cache_dir=InvokeAIAppConfig.get_config().cache_dir
-    )
-
+    text_model = CLIPTextModel.from_pretrained(CONVERT_MODEL_ROOT / 'clip-vit-large-patch14')
     keys = list(checkpoint.keys())
 
     text_model_dict = {}
@@ -896,82 +882,10 @@ protected = {re.escape(x[0]): x[1] for x in textenc_transformer_conversion_lst}
 textenc_pattern = re.compile("|".join(protected.keys()))
 
 
-def convert_paint_by_example_checkpoint(checkpoint):
-    cache_dir = InvokeAIAppConfig.get_config().cache_dir
-    config = CLIPVisionConfig.from_pretrained(
-        "openai/clip-vit-large-patch14", cache_dir=cache_dir
-    )
-    model = PaintByExampleImageEncoder(config)
-
-    keys = list(checkpoint.keys())
-
-    text_model_dict = {}
-
-    for key in keys:
-        if key.startswith("cond_stage_model.transformer"):
-            text_model_dict[key[len("cond_stage_model.transformer.") :]] = checkpoint[
-                key
-            ]
-
-    # load clip vision
-    model.model.load_state_dict(text_model_dict)
-
-    # load mapper
-    keys_mapper = {
-        k[len("cond_stage_model.mapper.res") :]: v
-        for k, v in checkpoint.items()
-        if k.startswith("cond_stage_model.mapper")
-    }
-
-    MAPPING = {
-        "attn.c_qkv": ["attn1.to_q", "attn1.to_k", "attn1.to_v"],
-        "attn.c_proj": ["attn1.to_out.0"],
-        "ln_1": ["norm1"],
-        "ln_2": ["norm3"],
-        "mlp.c_fc": ["ff.net.0.proj"],
-        "mlp.c_proj": ["ff.net.2"],
-    }
-
-    mapped_weights = {}
-    for key, value in keys_mapper.items():
-        prefix = key[: len("blocks.i")]
-        suffix = key.split(prefix)[-1].split(".")[-1]
-        name = key.split(prefix)[-1].split(suffix)[0][1:-1]
-        mapped_names = MAPPING[name]
-
-        num_splits = len(mapped_names)
-        for i, mapped_name in enumerate(mapped_names):
-            new_name = ".".join([prefix, mapped_name, suffix])
-            shape = value.shape[0] // num_splits
-            mapped_weights[new_name] = value[i * shape : (i + 1) * shape]
-
-    model.mapper.load_state_dict(mapped_weights)
-
-    # load final layer norm
-    model.final_layer_norm.load_state_dict(
-        {
-            "bias": checkpoint["cond_stage_model.final_ln.bias"],
-            "weight": checkpoint["cond_stage_model.final_ln.weight"],
-        }
-    )
-
-    # load final proj
-    model.proj_out.load_state_dict(
-        {
-            "bias": checkpoint["proj_out.bias"],
-            "weight": checkpoint["proj_out.weight"],
-        }
-    )
-
-    # load uncond vector
-    model.uncond_vector.data = torch.nn.Parameter(checkpoint["learnable_vector"])
-    return model
-
-
 def convert_open_clip_checkpoint(checkpoint):
-    cache_dir = InvokeAIAppConfig.get_config().cache_dir
     text_model = CLIPTextModel.from_pretrained(
-        "stabilityai/stable-diffusion-2", subfolder="text_encoder", cache_dir=cache_dir
+        CONVERT_MODEL_ROOT / 'stable-diffusion-2-clip',
+        subfolder='text_encoder',
     )
 
     keys = list(checkpoint.keys())
@@ -1037,7 +951,7 @@ def convert_open_clip_checkpoint(checkpoint):
 
     return text_model
 
-def replace_checkpoint_vae(checkpoint, vae_path:str):
+def replace_checkpoint_vae(checkpoint, vae_path: str):
     if vae_path.endswith(".safetensors"):
         vae_ckpt = load_file(vae_path)
     else:
@@ -1047,22 +961,28 @@ def replace_checkpoint_vae(checkpoint, vae_path:str):
         new_key = f'first_stage_model.{vae_key}'
         checkpoint[new_key] = state_dict[vae_key]
 
+def convert_ldm_vae_to_diffusers(checkpoint, vae_config: DictConfig, image_size: int) -> AutoencoderKL:
+    vae_config = create_vae_diffusers_config(
+        vae_config, image_size=image_size
+    )
+
+    converted_vae_checkpoint = convert_ldm_vae_checkpoint(
+        checkpoint, vae_config
+    )
+
+    vae = AutoencoderKL(**vae_config)
+    vae.load_state_dict(converted_vae_checkpoint)
+    return vae
+
 def load_pipeline_from_original_stable_diffusion_ckpt(
     checkpoint_path: str,
-    original_config_file: str = None,
-    num_in_channels: int = None,
-    scheduler_type: str = "pndm",
-    pipeline_type: str = None,
-    image_size: int = None,
-    prediction_type: str = None,
+    model_version: BaseModelType,
+    model_variant: ModelVariantType,
+    original_config_file: str,
     extract_ema: bool = True,
-    upcast_attn: bool = False,
-    vae: AutoencoderKL = None,
-    vae_path: str = None,
     precision: torch.dtype = torch.float32,
-    return_generator_pipeline: bool = False,
-    scan_needed:bool=True,
-) -> Union[StableDiffusionPipeline, StableDiffusionGeneratorPipeline]:
+    scan_needed: bool = True,
+) -> StableDiffusionPipeline:
     """
     Load a Stable Diffusion pipeline object from a CompVis-style `.ckpt`/`.safetensors` file and (ideally) a `.yaml`
     config file.
@@ -1074,148 +994,72 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     :param checkpoint_path: Path to `.ckpt` file.
     :param original_config_file: Path to `.yaml` config file corresponding to the original architecture.
       If `None`, will be automatically inferred by looking for a key that only exists in SD2.0 models.
-    :param image_size: The image size that the model was trained on. Use 512 for Stable Diffusion v1.X and Stable Diffusion v2
-      Base. Use 768 for Stable Diffusion v2.
-    :param prediction_type: The prediction type that the model was trained on. Use `'epsilon'` for Stable Diffusion
-     v1.X and Stable Diffusion v2 Base. Use `'v-prediction'` for Stable Diffusion v2.
-    :param num_in_channels: The number of input channels. If `None` number of input channels will be automatically
-    inferred.
     :param scheduler_type: Type of scheduler to use. Should be one of `["pndm", "lms", "heun", "euler",
      "euler-ancestral", "dpm", "ddim"]`. :param model_type: The pipeline type. `None` to automatically infer, or one of
-     `["FrozenOpenCLIPEmbedder", "FrozenCLIPEmbedder", "PaintByExample"]`. :param extract_ema: Only relevant for
+     `["FrozenOpenCLIPEmbedder", "FrozenCLIPEmbedder"]`. :param extract_ema: Only relevant for
      checkpoints that have both EMA and non-EMA weights. Whether to extract the EMA weights
      or not. Defaults to `False`. Pass `True` to extract the EMA weights. EMA weights usually yield higher
      quality images for inference. Non-EMA weights are usually better to continue fine-tuning.
     :param precision: precision to use - torch.float16, torch.float32 or torch.autocast
-    :param upcast_attention: Whether the attention computation should always be upcasted. This is necessary when
-    running stable diffusion 2.1.
-    :param vae: A diffusers VAE to load into the pipeline.
-    :param vae_path: Path to a checkpoint VAE that will be converted into diffusers and loaded into the pipeline.
     """
-    config = InvokeAIAppConfig.get_config()
-    cache_dir = config.cache_dir
+    if not isinstance(checkpoint_path, Path):
+        checkpoint_path = Path(checkpoint_path)
 
     with warnings.catch_warnings():
         warnings.simplefilter("ignore")
         verbosity = dlogging.get_verbosity()
         dlogging.set_verbosity_error()
 
-        if Path(checkpoint_path).suffix == '.ckpt':
-            if scan_needed:
-                ModelManager.scan_model(checkpoint_path,checkpoint_path)
-            checkpoint = torch.load(checkpoint_path)
-        else:
+        if checkpoint_path.suffix == ".safetensors":
             checkpoint = load_file(checkpoint_path)
-
-        pipeline_class = (
-            StableDiffusionGeneratorPipeline
-            if return_generator_pipeline
-            else StableDiffusionPipeline
-        )
-
-        # Sometimes models don't have the global_step item
-        if "global_step" in checkpoint:
-            global_step = checkpoint["global_step"]
         else:
-            logger.debug("global_step key not found in model")
-            global_step = None
+            if scan_needed:
+                # scan model
+                scan_result = scan_file_path(checkpoint_path)
+                if scan_result.infected_files != 0:
+                    raise "The model {checkpoint_path} is potentially infected by malware. Aborting import."
+            checkpoint = torch.load(checkpoint_path)
 
         # sometimes there is a state_dict key and sometimes not
         if "state_dict" in checkpoint:
             checkpoint = checkpoint["state_dict"]
 
-        upcast_attention = False
-        if original_config_file is None:
-            model_type = ModelManager.probe_model_type(checkpoint)
-
-            if model_type == SDLegacyType.V2_v:
-                original_config_file = (
-                    config.legacy_conf_path / "v2-inference-v.yaml"
-                )
-                if global_step == 110000:
-                    # v2.1 needs to upcast attention
-                    upcast_attention = True
-            elif model_type == SDLegacyType.V2_e:
-                original_config_file = (
-                    config.legacy_conf_path / "v2-inference.yaml"
-                )
-            elif model_type == SDLegacyType.V1_INPAINT:
-                original_config_file = (
-                    config.legacy_conf_path / "v1-inpainting-inference.yaml"
-                )
-
-            elif model_type == SDLegacyType.V1:
-                original_config_file = (
-                    config.legacy_conf_path / "v1-inference.yaml"
-                )
-
-            else:
-                raise Exception("Unknown checkpoint type")
-
         original_config = OmegaConf.load(original_config_file)
 
-        if num_in_channels is not None:
-            original_config["model"]["params"]["unet_config"]["params"][
-                "in_channels"
-            ] = num_in_channels
-
-        if (
-            "parameterization" in original_config["model"]["params"]
-            and original_config["model"]["params"]["parameterization"] == "v"
-        ):
-            if prediction_type is None:
-                # NOTE: For stable diffusion 2 base it is recommended to pass `prediction_type=="epsilon"`
-                # as it relies on a brittle global step parameter here
-                prediction_type = "epsilon" if global_step == 875000 else "v_prediction"
-            if image_size is None:
-                # NOTE: For stable diffusion 2 base one has to pass `image_size==512`
-                # as it relies on a brittle global step parameter here
-                image_size = 512 if global_step == 875000 else 768
+        if model_version == BaseModelType.StableDiffusion2 and original_config["model"]["params"]["parameterization"] == "v":
+            prediction_type = "v_prediction"
+            upcast_attention = True
+            image_size = 768
         else:
-            if prediction_type is None:
-                prediction_type = "epsilon"
-            if image_size is None:
-                image_size = 512
+            prediction_type = "epsilon"
+            upcast_attention = False
+            image_size = 512
+
+        #
+        # convert scheduler
+        #
 
         num_train_timesteps = original_config.model.params.timesteps
         beta_start = original_config.model.params.linear_start
         beta_end = original_config.model.params.linear_end
 
-        scheduler = DDIMScheduler(
+        scheduler = PNDMScheduler(
             beta_end=beta_end,
             beta_schedule="scaled_linear",
             beta_start=beta_start,
             num_train_timesteps=num_train_timesteps,
             steps_offset=1,
-            clip_sample=False,
             set_alpha_to_one=False,
             prediction_type=prediction_type,
+            skip_prk_steps=True
         )
         # make sure scheduler works correctly with DDIM
         scheduler.register_to_config(clip_sample=False)
 
-        if scheduler_type == "pndm":
-            config = dict(scheduler.config)
-            config["skip_prk_steps"] = True
-            scheduler = PNDMScheduler.from_config(config)
-        elif scheduler_type == "lms":
-            scheduler = LMSDiscreteScheduler.from_config(scheduler.config)
-        elif scheduler_type == "heun":
-            scheduler = HeunDiscreteScheduler.from_config(scheduler.config)
-        elif scheduler_type == "euler":
-            scheduler = EulerDiscreteScheduler.from_config(scheduler.config)
-        elif scheduler_type == "euler-ancestral":
-            scheduler = EulerAncestralDiscreteScheduler.from_config(scheduler.config)
-        elif scheduler_type == "dpm":
-            scheduler = DPMSolverMultistepScheduler.from_config(scheduler.config)
-        elif scheduler_type == 'unipc':
-            scheduler = UniPCMultistepScheduler.from_config(scheduler.config)
-        elif scheduler_type == "ddim":
-            scheduler = scheduler
-        else:
-            raise ValueError(f"Scheduler of type {scheduler_type} doesn't exist!")
+        #
+        # convert unet
+        #
 
-        # Convert the UNet2DConditionModel model.
         unet_config = create_unet_diffusers_config(
             original_config, image_size=image_size
         )
@@ -1228,44 +1072,25 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         unet.load_state_dict(converted_unet_checkpoint)
 
-        # If a replacement VAE path was specified, we'll incorporate that into
-        # the checkpoint model and then convert it
-        if vae_path:
-            logger.debug(f"Converting VAE {vae_path}")
-            replace_checkpoint_vae(checkpoint,vae_path)
-        # otherwise we use the original VAE, provided that
-        # an externally loaded diffusers VAE was not passed
-        elif not vae:
-            logger.debug("Using checkpoint model's original VAE")
+        #
+        # convert vae
+        #
 
-        if vae:
-            logger.debug("Using replacement diffusers VAE")
-        else:  # convert the original or replacement VAE
-            vae_config = create_vae_diffusers_config(
-                original_config, image_size=image_size
-            )
-            converted_vae_checkpoint = convert_ldm_vae_checkpoint(
-                checkpoint, vae_config
-            )
-
-            vae = AutoencoderKL(**vae_config)
-            vae.load_state_dict(converted_vae_checkpoint)
+        vae = convert_ldm_vae_to_diffusers(
+            checkpoint,
+            original_config,
+            image_size,
+        )
 
         # Convert the text model.
-        model_type = pipeline_type
-        if model_type is None:
-            model_type = original_config.model.params.cond_stage_config.target.split(
-                "."
-            )[-1]
-
+        model_type = original_config.model.params.cond_stage_config.target.split(".")[-1]
         if model_type == "FrozenOpenCLIPEmbedder":
             text_model = convert_open_clip_checkpoint(checkpoint)
             tokenizer = CLIPTokenizer.from_pretrained(
-                "stabilityai/stable-diffusion-2",
-                subfolder="tokenizer",
-                cache_dir=cache_dir,
+                CONVERT_MODEL_ROOT / 'stable-diffusion-2-clip',
+                subfolder='tokenizer',
             )
-            pipe = pipeline_class(
+            pipe = StableDiffusionPipeline(
                 vae=vae.to(precision),
                 text_encoder=text_model.to(precision),
                 tokenizer=tokenizer,
@@ -1275,49 +1100,26 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
                 feature_extractor=None,
                 requires_safety_checker=False,
             )
-        elif model_type == "PaintByExample":
-            vision_model = convert_paint_by_example_checkpoint(checkpoint)
-            tokenizer = CLIPTokenizer.from_pretrained(
-                "openai/clip-vit-large-patch14", cache_dir=cache_dir
-            )
-            feature_extractor = AutoFeatureExtractor.from_pretrained(
-                "CompVis/stable-diffusion-safety-checker", cache_dir=cache_dir
-            )
-            pipe = PaintByExamplePipeline(
-                vae=vae,
-                image_encoder=vision_model,
-                unet=unet,
-                scheduler=scheduler,
-                safety_checker=None,
-                feature_extractor=feature_extractor,
-            )
+
         elif model_type in ["FrozenCLIPEmbedder", "WeightedFrozenCLIPEmbedder"]:
             text_model = convert_ldm_clip_checkpoint(checkpoint)
-            tokenizer = CLIPTokenizer.from_pretrained(
-                "openai/clip-vit-large-patch14", cache_dir=cache_dir
-            )
-            safety_checker = StableDiffusionSafetyChecker.from_pretrained(
-                "CompVis/stable-diffusion-safety-checker",
-                cache_dir=cache_dir,
-            )
-            feature_extractor = AutoFeatureExtractor.from_pretrained(
-                "CompVis/stable-diffusion-safety-checker", cache_dir=cache_dir
-            )
-            pipe = pipeline_class(
+            tokenizer = CLIPTokenizer.from_pretrained(CONVERT_MODEL_ROOT / 'clip-vit-large-patch14')
+            safety_checker = StableDiffusionSafetyChecker.from_pretrained(CONVERT_MODEL_ROOT / 'stable-diffusion-safety-checker')
+            feature_extractor = AutoFeatureExtractor.from_pretrained(CONVERT_MODEL_ROOT / 'stable-diffusion-safety-checker')
+            pipe = StableDiffusionPipeline(
                 vae=vae.to(precision),
                 text_encoder=text_model.to(precision),
                 tokenizer=tokenizer,
                 unet=unet.to(precision),
                 scheduler=scheduler,
-                safety_checker=None if return_generator_pipeline else safety_checker.to(precision),
+                safety_checker=safety_checker.to(precision),
                 feature_extractor=feature_extractor,
             )
+
         else:
             text_config = create_ldm_bert_config(original_config)
             text_model = convert_ldm_bert_checkpoint(checkpoint, text_config)
-            tokenizer = BertTokenizerFast.from_pretrained(
-                "bert-base-uncased", cache_dir=cache_dir
-            )
+            tokenizer = BertTokenizerFast.from_pretrained(CONVERT_MODEL_ROOT / "bert-base-uncased")
             pipe = LDMTextToImagePipeline(
                 vqvae=vae,
                 bert=text_model,
@@ -1331,9 +1133,9 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
 
 def convert_ckpt_to_diffusers(
-    checkpoint_path: Union[str, Path],
-    dump_path: Union[str, Path],
-    **kwargs,
+        checkpoint_path: Union[str, Path],
+        dump_path: Union[str, Path],
+        **kwargs,
 ):
     """
     Takes all the arguments of load_pipeline_from_original_stable_diffusion_ckpt(),

invokeai/backend/model_management/lora.py

@@ -0,0 +1,710 @@
+from __future__ import annotations
+
+import copy
+from contextlib import contextmanager
+from typing import Optional, Dict, Tuple, Any, Union, List
+from pathlib import Path
+
+import torch
+from compel.embeddings_provider import BaseTextualInversionManager
+from diffusers.models import UNet2DConditionModel
+from safetensors.torch import load_file
+from transformers import CLIPTextModel, CLIPTokenizer
+
+class LoRALayerBase:
+    #rank: Optional[int]
+    #alpha: Optional[float]
+    #bias: Optional[torch.Tensor]
+    #layer_key: str
+
+    #@property
+    #def scale(self):
+    #    return self.alpha / self.rank if (self.alpha and self.rank) else 1.0
+
+    def __init__(
+        self,
+        layer_key: str,
+        values: dict,
+    ):
+        if "alpha" in values:
+            self.alpha = values["alpha"].item()
+        else:
+            self.alpha = None
+
+        if (
+            "bias_indices" in values
+            and "bias_values" in values
+            and "bias_size" in values
+        ):
+            self.bias = torch.sparse_coo_tensor(
+                values["bias_indices"],
+                values["bias_values"],
+                tuple(values["bias_size"]),
+            )
+
+        else:
+            self.bias = None
+
+        self.rank = None # set in layer implementation
+        self.layer_key = layer_key
+
+    def forward(
+        self,
+        module: torch.nn.Module,
+        input_h: Any, # for real looks like Tuple[torch.nn.Tensor] but not sure
+        multiplier: float,
+    ):
+        if type(module) == torch.nn.Conv2d:
+            op = torch.nn.functional.conv2d
+            extra_args = dict(
+                stride=module.stride,
+                padding=module.padding,
+                dilation=module.dilation,
+                groups=module.groups,
+            )
+
+        else:
+            op = torch.nn.functional.linear
+            extra_args = {}
+
+        weight = self.get_weight()
+
+        bias = self.bias if self.bias is not None else 0
+        scale = self.alpha / self.rank if (self.alpha and self.rank) else 1.0
+        return op(
+            *input_h,
+            (weight + bias).view(module.weight.shape),
+            None,
+            **extra_args,
+        ) * multiplier * scale
+
+    def get_weight(self):
+        raise NotImplementedError()
+
+    def calc_size(self) -> int:
+        model_size = 0
+        for val in [self.bias]:
+            if val is not None:
+                model_size += val.nelement() * val.element_size()
+        return model_size
+
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        if self.bias is not None:
+            self.bias = self.bias.to(device=device, dtype=dtype)
+
+
+# TODO: find and debug lora/locon with bias
+class LoRALayer(LoRALayerBase):
+    #up: torch.Tensor
+    #mid: Optional[torch.Tensor]
+    #down: torch.Tensor
+
+    def __init__(
+        self,
+        layer_key: str,
+        values: dict,
+    ):
+        super().__init__(layer_key, values)
+
+        self.up = values["lora_up.weight"]
+        self.down = values["lora_down.weight"]
+        if "lora_mid.weight" in values:
+            self.mid = values["lora_mid.weight"]
+        else:
+            self.mid = None
+
+        self.rank = self.down.shape[0]
+
+    def get_weight(self):
+        if self.mid is not None:
+            up = self.up.reshape(self.up.shape[0], self.up.shape[1])
+            down = self.down.reshape(self.down.shape[0], self.down.shape[1])
+            weight = torch.einsum("m n w h, i m, n j -> i j w h", self.mid, up, down)
+        else:
+            weight = self.up.reshape(self.up.shape[0], -1) @ self.down.reshape(self.down.shape[0], -1)
+
+        return weight
+
+    def calc_size(self) -> int:
+        model_size = super().calc_size()
+        for val in [self.up, self.mid, self.down]:
+            if val is not None:
+                model_size += val.nelement() * val.element_size()
+        return model_size
+
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        super().to(device=device, dtype=dtype)
+
+        self.up = self.up.to(device=device, dtype=dtype)
+        self.down = self.down.to(device=device, dtype=dtype)
+
+        if self.mid is not None:
+            self.mid = self.mid.to(device=device, dtype=dtype)
+
+
+class LoHALayer(LoRALayerBase):
+    #w1_a: torch.Tensor
+    #w1_b: torch.Tensor
+    #w2_a: torch.Tensor
+    #w2_b: torch.Tensor
+    #t1: Optional[torch.Tensor] = None
+    #t2: Optional[torch.Tensor] = None
+
+    def __init__(
+        self,
+        layer_key: str,
+        values: dict,
+    ):
+        super().__init__(layer_key, values)
+
+        self.w1_a = values["hada_w1_a"]
+        self.w1_b = values["hada_w1_b"]
+        self.w2_a = values["hada_w2_a"]
+        self.w2_b = values["hada_w2_b"]
+
+        if "hada_t1" in values:
+            self.t1 = values["hada_t1"]
+        else:
+            self.t1 = None
+
+        if "hada_t2" in values:
+            self.t2 = values["hada_t2"]
+        else:
+            self.t2 = None
+
+        self.rank = self.w1_b.shape[0]
+
+    def get_weight(self):
+        if self.t1 is None:
+            weight = (self.w1_a @ self.w1_b) * (self.w2_a @ self.w2_b)
+
+        else:
+            rebuild1 = torch.einsum(
+                "i j k l, j r, i p -> p r k l", self.t1, self.w1_b, self.w1_a
+            )
+            rebuild2 = torch.einsum(
+                "i j k l, j r, i p -> p r k l", self.t2, self.w2_b, self.w2_a
+            )
+            weight = rebuild1 * rebuild2
+
+        return weight
+
+    def calc_size(self) -> int:
+        model_size = super().calc_size()
+        for val in [self.w1_a, self.w1_b, self.w2_a, self.w2_b, self.t1, self.t2]:
+            if val is not None:
+                model_size += val.nelement() * val.element_size()
+        return model_size
+
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        super().to(device=device, dtype=dtype)
+
+        self.w1_a = self.w1_a.to(device=device, dtype=dtype)
+        self.w1_b = self.w1_b.to(device=device, dtype=dtype)
+        if self.t1 is not None:
+            self.t1 = self.t1.to(device=device, dtype=dtype)
+
+        self.w2_a = self.w2_a.to(device=device, dtype=dtype)
+        self.w2_b = self.w2_b.to(device=device, dtype=dtype)
+        if self.t2 is not None:
+            self.t2 = self.t2.to(device=device, dtype=dtype)
+
+
+class LoKRLayer(LoRALayerBase):
+    #w1: Optional[torch.Tensor] = None
+    #w1_a: Optional[torch.Tensor] = None
+    #w1_b: Optional[torch.Tensor] = None
+    #w2: Optional[torch.Tensor] = None
+    #w2_a: Optional[torch.Tensor] = None
+    #w2_b: Optional[torch.Tensor] = None
+    #t2: Optional[torch.Tensor] = None
+
+    def __init__(
+        self,
+        layer_key: str,
+        values: dict,
+    ):
+        super().__init__(layer_key, values)        
+
+        if "lokr_w1" in values:
+            self.w1 = values["lokr_w1"]
+            self.w1_a = None
+            self.w1_b = None
+        else:
+            self.w1 = None
+            self.w1_a = values["lokr_w1_a"]
+            self.w1_b = values["lokr_w1_b"]
+
+        if "lokr_w2" in values:
+            self.w2 = values["lokr_w2"]
+            self.w2_a = None
+            self.w2_b = None
+        else:
+            self.w2 = None
+            self.w2_a = values["lokr_w2_a"]
+            self.w2_b = values["lokr_w2_b"]
+
+        if "lokr_t2" in values:
+            self.t2 = values["lokr_t2"]
+        else:
+            self.t2 = None
+
+        if "lokr_w1_b" in values:
+            self.rank = values["lokr_w1_b"].shape[0]
+        elif "lokr_w2_b" in values:
+            self.rank = values["lokr_w2_b"].shape[0]
+        else:
+            self.rank = None # unscaled
+
+    def get_weight(self):
+        w1 = self.w1
+        if w1 is None:
+            w1 = self.w1_a @ self.w1_b
+
+        w2 = self.w2
+        if w2 is None:
+            if self.t2 is None:
+                w2 = self.w2_a @ self.w2_b
+            else:
+                w2 = torch.einsum('i j k l, i p, j r -> p r k l', self.t2, self.w2_a, self.w2_b)
+
+        if len(w2.shape) == 4:
+            w1 = w1.unsqueeze(2).unsqueeze(2)
+        w2 = w2.contiguous()
+        weight = torch.kron(w1, w2)
+
+        return weight
+
+    def calc_size(self) -> int:
+        model_size = super().calc_size()
+        for val in [self.w1, self.w1_a, self.w1_b, self.w2, self.w2_a, self.w2_b, self.t2]:
+            if val is not None:
+                model_size += val.nelement() * val.element_size()
+        return model_size
+
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        super().to(device=device, dtype=dtype)
+
+        if self.w1 is not None:
+            self.w1 = self.w1.to(device=device, dtype=dtype)
+        else:
+            self.w1_a = self.w1_a.to(device=device, dtype=dtype)
+            self.w1_b = self.w1_b.to(device=device, dtype=dtype)
+
+        if self.w2 is not None:
+            self.w2 = self.w2.to(device=device, dtype=dtype)
+        else:
+            self.w2_a = self.w2_a.to(device=device, dtype=dtype)
+            self.w2_b = self.w2_b.to(device=device, dtype=dtype)
+
+        if self.t2 is not None:
+            self.t2 = self.t2.to(device=device, dtype=dtype)
+
+
+class LoRAModel: #(torch.nn.Module):
+    _name: str
+    layers: Dict[str, LoRALayer]
+    _device: torch.device
+    _dtype: torch.dtype
+
+    def __init__(
+        self,
+        name: str,
+        layers: Dict[str, LoRALayer],
+        device: torch.device,
+        dtype: torch.dtype,
+    ):
+        self._name = name
+        self._device = device or torch.cpu
+        self._dtype = dtype or torch.float32
+        self.layers = layers
+
+    @property
+    def name(self):
+        return self._name
+
+    @property
+    def device(self):
+        return self._device
+
+    @property
+    def dtype(self):
+        return self._dtype    
+
+    def to(
+        self,
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ) -> LoRAModel:
+        # TODO: try revert if exception?
+        for key, layer in self.layers.items():
+            layer.to(device=device, dtype=dtype)
+        self._device = device
+        self._dtype = dtype
+
+    def calc_size(self) -> int:
+        model_size = 0
+        for _, layer in self.layers.items():
+            model_size += layer.calc_size()
+        return model_size
+
+    @classmethod
+    def from_checkpoint(
+        cls,
+        file_path: Union[str, Path],
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        device = device or torch.device("cpu")
+        dtype = dtype or torch.float32
+
+        if isinstance(file_path, str):
+            file_path = Path(file_path)
+
+        model = cls(
+            device=device,
+            dtype=dtype,
+            name=file_path.stem, # TODO:
+            layers=dict(),
+        )
+
+        if file_path.suffix == ".safetensors":
+            state_dict = load_file(file_path.absolute().as_posix(), device="cpu")
+        else:
+            state_dict = torch.load(file_path, map_location="cpu")
+
+        state_dict = cls._group_state(state_dict)
+
+        for layer_key, values in state_dict.items():
+
+            # lora and locon
+            if "lora_down.weight" in values:
+                layer = LoRALayer(layer_key, values)
+
+            # loha
+            elif "hada_w1_b" in values:
+                layer = LoHALayer(layer_key, values)
+
+            # lokr
+            elif "lokr_w1_b" in values or "lokr_w1" in values:
+                layer = LoKRLayer(layer_key, values)
+
+            else:
+                # TODO: diff/ia3/... format
+                print(
+                    f">> Encountered unknown lora layer module in {model.name}: {layer_key}"
+                )
+                return
+
+            # lower memory consumption by removing already parsed layer values
+            state_dict[layer_key].clear()
+
+            layer.to(device=device, dtype=dtype)
+            model.layers[layer_key] = layer
+
+        return model
+
+    @staticmethod
+    def _group_state(state_dict: dict):
+        state_dict_groupped = dict()
+
+        for key, value in state_dict.items():
+            stem, leaf = key.split(".", 1)
+            if stem not in state_dict_groupped:
+                state_dict_groupped[stem] = dict()
+            state_dict_groupped[stem][leaf] = value
+
+        return state_dict_groupped
+
+
+"""
+loras = [
+    (lora_model1, 0.7),
+    (lora_model2, 0.4),
+]
+with LoRAHelper.apply_lora_unet(unet, loras):
+    # unet with applied loras
+# unmodified unet
+
+"""
+# TODO: rename smth like ModelPatcher and add TI method?
+class ModelPatcher:
+
+    @staticmethod
+    def _resolve_lora_key(model: torch.nn.Module, lora_key: str, prefix: str) -> Tuple[str, torch.nn.Module]:
+        assert "." not in lora_key
+
+        if not lora_key.startswith(prefix):
+            raise Exception(f"lora_key with invalid prefix: {lora_key}, {prefix}")
+
+        module = model
+        module_key = ""
+        key_parts = lora_key[len(prefix):].split('_')
+
+        submodule_name = key_parts.pop(0)
+        
+        while len(key_parts) > 0:
+            try:
+                module = module.get_submodule(submodule_name)
+                module_key += "." + submodule_name
+                submodule_name = key_parts.pop(0)
+            except:
+                submodule_name += "_" + key_parts.pop(0)
+
+        module = module.get_submodule(submodule_name)
+        module_key = (module_key + "." + submodule_name).lstrip(".")
+
+        return (module_key, module)
+
+    @staticmethod
+    def _lora_forward_hook(
+        applied_loras: List[Tuple[LoraModel, float]],
+        layer_name: str,
+    ):
+
+        def lora_forward(module, input_h, output):
+            if len(applied_loras) == 0:
+                return output
+
+            for lora, weight in applied_loras:
+                layer = lora.layers.get(layer_name, None)
+                if layer is None:
+                    continue
+                output += layer.forward(module, input_h, weight)
+            return output
+
+        return lora_forward
+
+
+    @classmethod
+    @contextmanager
+    def apply_lora_unet(
+        cls,
+        unet: UNet2DConditionModel,
+        loras: List[Tuple[LoRAModel, float]],
+    ):
+        with cls.apply_lora(unet, loras, "lora_unet_"):
+            yield
+
+
+    @classmethod
+    @contextmanager
+    def apply_lora_text_encoder(
+        cls,
+        text_encoder: CLIPTextModel,
+        loras: List[Tuple[LoRAModel, float]],
+    ):
+        with cls.apply_lora(text_encoder, loras, "lora_te_"):
+            yield
+
+
+    @classmethod
+    @contextmanager
+    def apply_lora(
+        cls,
+        model: torch.nn.Module,
+        loras: List[Tuple[LoraModel, float]],
+        prefix: str,
+    ):
+        original_weights = dict()
+        try:
+            with torch.no_grad():
+                for lora, lora_weight in loras:
+                    #assert lora.device.type == "cpu"
+                    for layer_key, layer in lora.layers.items():
+                        if not layer_key.startswith(prefix):
+                            continue
+
+                        module_key, module = cls._resolve_lora_key(model, layer_key, prefix)
+                        if module_key not in original_weights:
+                            original_weights[module_key] = module.weight.detach().to(device="cpu", copy=True)
+
+                        # enable autocast to calc fp16 loras on cpu
+                        #with torch.autocast(device_type="cpu"):
+                        layer.to(dtype=torch.float32)
+                        layer_scale = layer.alpha / layer.rank if (layer.alpha and layer.rank) else 1.0
+                        layer_weight = layer.get_weight() * lora_weight * layer_scale
+
+                        if module.weight.shape != layer_weight.shape:
+                            # TODO: debug on lycoris
+                            layer_weight = layer_weight.reshape(module.weight.shape)
+
+                        module.weight += layer_weight.to(device=module.weight.device, dtype=module.weight.dtype)
+
+            yield # wait for context manager exit
+
+        finally:
+            with torch.no_grad():
+                for module_key, weight in original_weights.items():
+                    model.get_submodule(module_key).weight.copy_(weight)
+
+
+    @classmethod
+    @contextmanager
+    def apply_ti(
+        cls,
+        tokenizer: CLIPTokenizer,
+        text_encoder: CLIPTextModel,
+        ti_list: List[Any],
+    ) -> Tuple[CLIPTokenizer, TextualInversionManager]:
+        init_tokens_count = None
+        new_tokens_added = None
+
+        try:
+            ti_tokenizer = copy.deepcopy(tokenizer)
+            ti_manager = TextualInversionManager(ti_tokenizer)
+            init_tokens_count = text_encoder.resize_token_embeddings(None).num_embeddings
+
+            def _get_trigger(ti, index):
+                trigger = ti.name
+                if index > 0:
+                    trigger += f"-!pad-{i}"
+                return f"<{trigger}>"
+
+            # modify tokenizer
+            new_tokens_added = 0
+            for ti in ti_list:
+                for i in range(ti.embedding.shape[0]):
+                    new_tokens_added += ti_tokenizer.add_tokens(_get_trigger(ti, i))
+
+            # modify text_encoder
+            text_encoder.resize_token_embeddings(init_tokens_count + new_tokens_added)
+            model_embeddings = text_encoder.get_input_embeddings()
+
+            for ti in ti_list:
+                ti_tokens = []
+                for i in range(ti.embedding.shape[0]):
+                    embedding = ti.embedding[i]
+                    trigger = _get_trigger(ti, i)
+
+                    token_id = ti_tokenizer.convert_tokens_to_ids(trigger)
+                    if token_id == ti_tokenizer.unk_token_id:
+                        raise RuntimeError(f"Unable to find token id for token '{trigger}'")
+
+                    if model_embeddings.weight.data[token_id].shape != embedding.shape:
+                        raise ValueError(
+                            f"Cannot load embedding for {trigger}. It was trained on a model with token dimension {embedding.shape[0]}, but the current model has token dimension {model_embeddings.weight.data[token_id].shape[0]}."
+                        )
+
+                    model_embeddings.weight.data[token_id] = embedding.to(device=text_encoder.device, dtype=text_encoder.dtype)
+                    ti_tokens.append(token_id)
+
+                if len(ti_tokens) > 1:
+                    ti_manager.pad_tokens[ti_tokens[0]] = ti_tokens[1:]
+
+            yield ti_tokenizer, ti_manager
+
+        finally:
+            if init_tokens_count and new_tokens_added:
+                text_encoder.resize_token_embeddings(init_tokens_count)
+
+
+    @classmethod
+    @contextmanager
+    def apply_clip_skip(
+        cls,
+        text_encoder: CLIPTextModel,
+        clip_skip: int,
+    ):
+        skipped_layers = []
+        try:
+            for i in range(clip_skip):
+                skipped_layers.append(text_encoder.text_model.encoder.layers.pop(-1))
+
+            yield
+
+        finally:
+            while len(skipped_layers) > 0:
+                text_encoder.text_model.encoder.layers.append(skipped_layers.pop())
+
+class TextualInversionModel:
+    name: str
+    embedding: torch.Tensor # [n, 768]|[n, 1280]
+
+    @classmethod
+    def from_checkpoint(
+        cls,
+        file_path: Union[str, Path],
+        device: Optional[torch.device] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        if not isinstance(file_path, Path):
+            file_path = Path(file_path)
+
+        result = cls() # TODO:
+        result.name = file_path.stem # TODO:
+
+        if file_path.suffix == ".safetensors":
+            state_dict = load_file(file_path.absolute().as_posix(), device="cpu")
+        else:
+            state_dict = torch.load(file_path, map_location="cpu")
+
+        # both v1 and v2 format embeddings
+        # difference mostly in metadata
+        if "string_to_param" in state_dict:
+            if len(state_dict["string_to_param"]) > 1:
+                print(f"Warn: Embedding \"{file_path.name}\" contains multiple tokens, which is not supported. The first token will be used.")
+
+            result.embedding = next(iter(state_dict["string_to_param"].values()))
+
+        # v3 (easynegative)
+        elif "emb_params" in state_dict:
+            result.embedding = state_dict["emb_params"]
+
+        # v4(diffusers bin files)
+        else:
+            result.embedding = next(iter(state_dict.values()))
+
+            if len(result.embedding.shape) == 1:
+                result.embedding = result.embedding.unsqueeze(0)
+
+            if not isinstance(result.embedding, torch.Tensor):
+                raise ValueError(f"Invalid embeddings file: {file_path.name}")
+
+        return result
+
+
+class TextualInversionManager(BaseTextualInversionManager):
+    pad_tokens: Dict[int, List[int]]
+    tokenizer: CLIPTokenizer
+
+    def __init__(self, tokenizer: CLIPTokenizer):
+        self.pad_tokens = dict()
+        self.tokenizer = tokenizer
+
+    def expand_textual_inversion_token_ids_if_necessary(
+        self, token_ids: list[int]
+    ) -> list[int]:
+
+        if len(self.pad_tokens) == 0:
+            return token_ids
+
+        if token_ids[0] == self.tokenizer.bos_token_id:
+            raise ValueError("token_ids must not start with bos_token_id")
+        if token_ids[-1] == self.tokenizer.eos_token_id:
+            raise ValueError("token_ids must not end with eos_token_id")
+
+        new_token_ids = []
+        for token_id in token_ids:
+            new_token_ids.append(token_id)
+            if token_id in self.pad_tokens:
+                new_token_ids.extend(self.pad_tokens[token_id])
+
+        return new_token_ids
+

invokeai/backend/model_management/model_cache.py

@@ -0,0 +1,381 @@
+"""
+Manage a RAM cache of diffusion/transformer models for fast switching.
+They are moved between GPU VRAM and CPU RAM as necessary. If the cache
+grows larger than a preset maximum, then the least recently used
+model will be cleared and (re)loaded from disk when next needed.
+
+The cache returns context manager generators designed to load the
+model into the GPU within the context, and unload outside the
+context. Use like this:
+
+   cache = ModelCache(max_cache_size=7.5)
+   with cache.get_model('runwayml/stable-diffusion-1-5') as SD1,
+          cache.get_model('stabilityai/stable-diffusion-2') as SD2:
+       do_something_in_GPU(SD1,SD2)
+
+
+"""
+
+import gc
+import os
+import sys
+import hashlib
+from contextlib import suppress
+from pathlib import Path
+from typing import Dict, Union, types, Optional, Type, Any
+
+import torch
+
+import logging
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
+from .lora import LoRAModel, TextualInversionModel
+from .models import BaseModelType, ModelType, SubModelType, ModelBase
+
+# Maximum size of the cache, in gigs
+# Default is roughly enough to hold three fp16 diffusers models in RAM simultaneously
+DEFAULT_MAX_CACHE_SIZE = 6.0
+
+# actual size of a gig
+GIG = 1073741824
+
+class ModelLocker(object):
+    "Forward declaration"
+    pass
+
+class ModelCache(object):
+    "Forward declaration"
+    pass
+
+class _CacheRecord:
+    size: int
+    model: Any
+    cache: ModelCache
+    _locks: int
+
+    def __init__(self, cache, model: Any, size: int):
+        self.size = size
+        self.model = model
+        self.cache = cache
+        self._locks = 0
+
+    def lock(self):
+        self._locks += 1
+
+    def unlock(self):
+        self._locks -= 1
+        assert self._locks >= 0
+
+    @property
+    def locked(self):
+        return self._locks > 0
+
+    @property
+    def loaded(self):
+        if self.model is not None and hasattr(self.model, "device"):
+            return self.model.device != self.cache.storage_device
+        else:
+            return False
+    
+
+class ModelCache(object):
+    def __init__(
+        self,
+        max_cache_size: float=DEFAULT_MAX_CACHE_SIZE,
+        execution_device: torch.device=torch.device('cuda'),
+        storage_device: torch.device=torch.device('cpu'),
+        precision: torch.dtype=torch.float16,
+        sequential_offload: bool=False,
+        lazy_offloading: bool=True,
+        sha_chunksize: int = 16777216,
+        logger: types.ModuleType = logger
+    ):
+        '''
+        :param max_cache_size: Maximum size of the RAM cache [6.0 GB]
+        :param execution_device: Torch device to load active model into [torch.device('cuda')]
+        :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
+        :param precision: Precision for loaded models [torch.float16]
+        :param lazy_offloading: Keep model in VRAM until another model needs to be loaded
+        :param sequential_offload: Conserve VRAM by loading and unloading each stage of the pipeline sequentially
+        :param sha_chunksize: Chunksize to use when calculating sha256 model hash
+        '''
+        #max_cache_size = 9999
+        self.model_infos: Dict[str, ModelBase] = dict()
+        self.lazy_offloading = lazy_offloading
+        #self.sequential_offload: bool=sequential_offload
+        self.precision: torch.dtype=precision
+        self.max_cache_size: int=max_cache_size
+        self.execution_device: torch.device=execution_device
+        self.storage_device: torch.device=storage_device
+        self.sha_chunksize=sha_chunksize
+        self.logger = logger
+
+        self._cached_models = dict()
+        self._cache_stack = list()
+
+    def get_key(
+        self,
+        model_path: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel_type: Optional[SubModelType] = None,
+    ):
+
+        key = f"{model_path}:{base_model}:{model_type}"
+        if submodel_type:
+            key += f":{submodel_type}"
+        return key
+
+    def _get_model_info(
+        self,
+        model_path: str,
+        model_class: Type[ModelBase],
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ):
+        model_info_key = self.get_key(
+            model_path=model_path,
+            base_model=base_model,
+            model_type=model_type,
+            submodel_type=None,
+        )
+
+        if model_info_key not in self.model_infos:
+            self.model_infos[model_info_key] = model_class(
+                model_path,
+                base_model,
+                model_type,
+            )
+
+        return self.model_infos[model_info_key]
+
+    # TODO: args
+    def get_model(
+        self,
+        model_path: Union[str, Path],
+        model_class: Type[ModelBase],
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+        gpu_load: bool = True,
+    ) -> Any:
+
+        if not isinstance(model_path, Path):
+            model_path = Path(model_path)
+
+        if not os.path.exists(model_path):
+            raise Exception(f"Model not found: {model_path}")
+
+        model_info = self._get_model_info(
+            model_path=model_path,
+            model_class=model_class,
+            base_model=base_model,
+            model_type=model_type,
+        )
+        key = self.get_key(
+            model_path=model_path,
+            base_model=base_model,
+            model_type=model_type,
+            submodel_type=submodel,
+        )
+
+        # TODO: lock for no copies on simultaneous calls?
+        cache_entry = self._cached_models.get(key, None)
+        if cache_entry is None:
+            self.logger.info(f'Loading model {model_path}, type {base_model}:{model_type}:{submodel}')
+
+            # this will remove older cached models until
+            # there is sufficient room to load the requested model
+            self._make_cache_room(model_info.get_size(submodel))
+
+            # clean memory to make MemoryUsage() more accurate
+            gc.collect()
+            model = model_info.get_model(child_type=submodel, torch_dtype=self.precision)
+            if mem_used := model_info.get_size(submodel):
+                self.logger.debug(f'CPU RAM used for load: {(mem_used/GIG):.2f} GB')
+
+            cache_entry = _CacheRecord(self, model, mem_used)
+            self._cached_models[key] = cache_entry
+
+        with suppress(Exception):
+            self._cache_stack.remove(key)
+        self._cache_stack.append(key)
+
+        return self.ModelLocker(self, key, cache_entry.model, gpu_load)
+
+    class ModelLocker(object):
+        def __init__(self, cache, key, model, gpu_load):
+            self.gpu_load = gpu_load
+            self.cache = cache
+            self.key = key
+            self.model = model
+            self.cache_entry = self.cache._cached_models[self.key]
+
+        def __enter__(self) -> Any:
+            if not hasattr(self.model, 'to'):
+                return self.model
+
+            # NOTE that the model has to have the to() method in order for this
+            # code to move it into GPU!
+            if self.gpu_load:
+                self.cache_entry.lock()
+
+                try:
+                    if self.cache.lazy_offloading:
+                       self.cache._offload_unlocked_models()
+                       
+                    if self.model.device != self.cache.execution_device:
+                        self.cache.logger.debug(f'Moving {self.key} into {self.cache.execution_device}')
+                        with VRAMUsage() as mem:
+                            self.model.to(self.cache.execution_device)  # move into GPU
+                        self.cache.logger.debug(f'GPU VRAM used for load: {(mem.vram_used/GIG):.2f} GB')
+                        
+                    self.cache.logger.debug(f'Locking {self.key} in {self.cache.execution_device}')                
+                    self.cache._print_cuda_stats()
+
+                except:
+                    self.cache_entry.unlock()
+                    raise
+
+            
+            # TODO: not fully understand
+            # in the event that the caller wants the model in RAM, we
+            # move it into CPU if it is in GPU and not locked
+            elif self.cache_entry.loaded and not self.cache_entry.locked:
+                self.model.to(self.cache.storage_device)
+
+            return self.model
+
+        def __exit__(self, type, value, traceback):
+            if not hasattr(self.model, 'to'):
+                return
+
+            self.cache_entry.unlock()
+            if not self.cache.lazy_offloading:
+                self.cache._offload_unlocked_models()
+                self.cache._print_cuda_stats()
+
+    # TODO: should it be called untrack_model?
+    def uncache_model(self, cache_id: str):
+        with suppress(ValueError):
+            self._cache_stack.remove(cache_id)
+        self._cached_models.pop(cache_id, None)
+
+    def model_hash(
+        self,
+        model_path: Union[str, Path],
+    ) -> str:
+        '''
+        Given the HF repo id or path to a model on disk, returns a unique
+        hash. Works for legacy checkpoint files, HF models on disk, and HF repo IDs
+        :param model_path: Path to model file/directory on disk.
+        '''
+        return self._local_model_hash(model_path)
+
+    def cache_size(self) -> float:
+        "Return the current size of the cache, in GB"
+        current_cache_size = sum([m.size for m in self._cached_models.values()])
+        return current_cache_size / GIG
+
+    def _has_cuda(self) -> bool:
+        return self.execution_device.type == 'cuda'
+
+    def _print_cuda_stats(self):
+        vram = "%4.2fG" % (torch.cuda.memory_allocated() / GIG)
+        ram = "%4.2fG" % self.cache_size()
+
+        cached_models = 0
+        loaded_models = 0
+        locked_models = 0
+        for model_info in self._cached_models.values():
+            cached_models += 1
+            if model_info.loaded:
+                loaded_models += 1
+            if model_info.locked:
+                locked_models += 1
+
+        self.logger.debug(f"Current VRAM/RAM usage: {vram}/{ram}; cached_models/loaded_models/locked_models/ = {cached_models}/{loaded_models}/{locked_models}")
+
+
+    def _make_cache_room(self, model_size):
+        # calculate how much memory this model will require
+        #multiplier = 2 if self.precision==torch.float32 else 1
+        bytes_needed = model_size
+        maximum_size = self.max_cache_size * GIG  # stored in GB, convert to bytes
+        current_size = sum([m.size for m in self._cached_models.values()])
+
+        if current_size + bytes_needed > maximum_size:
+            self.logger.debug(f'Max cache size exceeded: {(current_size/GIG):.2f}/{self.max_cache_size:.2f} GB, need an additional {(bytes_needed/GIG):.2f} GB')
+
+        self.logger.debug(f"Before unloading: cached_models={len(self._cached_models)}")
+
+        pos = 0
+        while current_size + bytes_needed > maximum_size and pos < len(self._cache_stack):
+            model_key = self._cache_stack[pos]
+            cache_entry = self._cached_models[model_key]
+
+            refs = sys.getrefcount(cache_entry.model)
+
+            device = cache_entry.model.device if hasattr(cache_entry.model, "device") else None
+            self.logger.debug(f"Model: {model_key}, locks: {cache_entry._locks}, device: {device}, loaded: {cache_entry.loaded}, refs: {refs}")
+
+            # 2 refs:
+            # 1 from cache_entry
+            # 1 from getrefcount function
+            if not cache_entry.locked and refs <= 2:
+                self.logger.debug(f'Unloading model {model_key} to free {(model_size/GIG):.2f} GB (-{(cache_entry.size/GIG):.2f} GB)')
+                current_size -= cache_entry.size
+                del self._cache_stack[pos]
+                del self._cached_models[model_key]
+                del cache_entry
+
+            else:
+                pos += 1
+
+        gc.collect()
+        torch.cuda.empty_cache()
+
+        self.logger.debug(f"After unloading: cached_models={len(self._cached_models)}")
+
+
+    def _offload_unlocked_models(self):
+        for model_key, cache_entry in self._cached_models.items():
+            if not cache_entry.locked and cache_entry.loaded:
+                self.logger.debug(f'Offloading {model_key} from {self.execution_device} into {self.storage_device}')
+                with VRAMUsage() as mem:
+                    cache_entry.model.to(self.storage_device)
+                self.logger.debug(f'GPU VRAM freed: {(mem.vram_used/GIG):.2f} GB')
+        
+    def _local_model_hash(self, model_path: Union[str, Path]) -> str:
+        sha = hashlib.sha256()
+        path = Path(model_path)
+        
+        hashpath = path / "checksum.sha256"
+        if hashpath.exists() and path.stat().st_mtime <= hashpath.stat().st_mtime:
+            with open(hashpath) as f:
+                hash = f.read()
+            return hash
+        
+        self.logger.debug(f'computing hash of model {path.name}')
+        for file in list(path.rglob("*.ckpt")) \
+            + list(path.rglob("*.safetensors")) \
+            + list(path.rglob("*.pth")):
+            with open(file, "rb") as f:
+                while chunk := f.read(self.sha_chunksize):
+                    sha.update(chunk)
+        hash = sha.hexdigest()
+        with open(hashpath, "w") as f:
+            f.write(hash)
+        return hash
+
+class VRAMUsage(object):
+    def __init__(self):
+        self.vram = None
+        self.vram_used = 0
+        
+    def __enter__(self):
+        self.vram = torch.cuda.memory_allocated()
+        return self
+
+    def __exit__(self, *args):
+        self.vram_used = torch.cuda.memory_allocated() - self.vram

invokeai/backend/model_management/model_merge.py

@@ -0,0 +1,131 @@
+"""
+invokeai.backend.model_management.model_merge exports:
+merge_diffusion_models() -- combine multiple models by location and return a pipeline object
+merge_diffusion_models_and_commit() -- combine multiple models by ModelManager ID and write to models.yaml
+
+Copyright (c) 2023 Lincoln Stein and the InvokeAI Development Team
+"""
+
+import warnings
+from enum import Enum
+from pathlib import Path
+from diffusers import DiffusionPipeline
+from diffusers import logging as dlogging
+from typing import List, Union
+
+import invokeai.backend.util.logging as logger
+
+from ...backend.model_management import ModelManager, ModelType, BaseModelType, ModelVariantType, AddModelResult
+
+class MergeInterpolationMethod(str, Enum):
+    WeightedSum = "weighted_sum"
+    Sigmoid = "sigmoid"
+    InvSigmoid = "inv_sigmoid"
+    AddDifference = "add_difference"
+
+class ModelMerger(object):
+    def __init__(self, manager: ModelManager):
+        self.manager = manager
+
+    def merge_diffusion_models(
+            self,
+            model_paths: List[Path],
+            alpha: float = 0.5,
+            interp: MergeInterpolationMethod = None,
+            force: bool = False,
+            **kwargs,
+    ) -> DiffusionPipeline:
+        """
+        :param model_paths:  up to three models, designated by their local paths or HuggingFace repo_ids
+        :param alpha: The interpolation parameter. Ranges from 0 to 1.  It affects the ratio in which the checkpoints are merged. A 0.8 alpha
+                   would mean that the first model checkpoints would affect the final result far less than an alpha of 0.2
+        :param interp: The interpolation method to use for the merging. Supports "sigmoid", "inv_sigmoid", "add_difference" and None.
+                   Passing None uses the default interpolation which is weighted sum interpolation. For merging three checkpoints, only "add_difference" is supported.
+        :param force:  Whether to ignore mismatch in model_config.json for the current models. Defaults to False.
+
+        **kwargs - the default DiffusionPipeline.get_config_dict kwargs:
+             cache_dir, resume_download, force_download, proxies, local_files_only, use_auth_token, revision, torch_dtype, device_map
+        """
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore")
+            verbosity = dlogging.get_verbosity()
+            dlogging.set_verbosity_error()
+
+            pipe = DiffusionPipeline.from_pretrained(
+                model_paths[0],
+                custom_pipeline="checkpoint_merger",
+            )
+            merged_pipe = pipe.merge(
+                pretrained_model_name_or_path_list=model_paths,
+                alpha=alpha,
+                interp=interp.value if interp else None, #diffusers API treats None as "weighted sum"
+                force=force,
+                **kwargs,
+            )
+            dlogging.set_verbosity(verbosity)
+        return merged_pipe
+
+
+    def merge_diffusion_models_and_save (
+            self,
+            model_names: List[str],
+            base_model: Union[BaseModelType,str],
+            merged_model_name: str,
+            alpha: float = 0.5,
+            interp: MergeInterpolationMethod = None,
+            force: bool = False,
+            **kwargs,
+    ) -> AddModelResult:
+        """
+        :param models: up to three models, designated by their InvokeAI models.yaml model name
+        :param base_model: base model (must be the same for all merged models!)
+        :param merged_model_name: name for new model
+        :param alpha: The interpolation parameter. Ranges from 0 to 1.  It affects the ratio in which the checkpoints are merged. A 0.8 alpha
+                   would mean that the first model checkpoints would affect the final result far less than an alpha of 0.2
+        :param interp: The interpolation method to use for the merging. Supports "weighted_average", "sigmoid", "inv_sigmoid", "add_difference" and None.
+                   Passing None uses the default interpolation which is weighted sum interpolation. For merging three checkpoints, only "add_difference" is supported. Add_difference is A+(B-C).
+        :param force:  Whether to ignore mismatch in model_config.json for the current models. Defaults to False.
+
+        **kwargs - the default DiffusionPipeline.get_config_dict kwargs:
+             cache_dir, resume_download, force_download, proxies, local_files_only, use_auth_token, revision, torch_dtype, device_map
+        """
+        model_paths = list()
+        config = self.manager.app_config
+        base_model = BaseModelType(base_model)
+        vae = None
+        
+        for mod in model_names:
+            info = self.manager.list_model(mod, base_model=base_model, model_type=ModelType.Main)
+            assert info,                                f"model {mod}, base_model {base_model}, is unknown"
+            assert info["model_format"] == "diffusers", f"{mod} is not a diffusers model. It must be optimized before merging"
+            assert info["variant"] == "normal",         f"{mod} is a {info['variant']} model, which cannot currently be merged"
+            assert len(model_names) <= 2 or \
+                interp==MergeInterpolationMethod.AddDifference, "When merging three models, only the 'add_difference' merge method is supported"
+            # pick up the first model's vae
+            if mod == model_names[0]:
+                vae = info.get("vae")
+            model_paths.extend([config.root_path / info["path"]])
+
+        merge_method = None if interp == 'weighted_sum' else MergeInterpolationMethod(interp)
+        logger.debug(f'interp = {interp}, merge_method={merge_method}')
+        merged_pipe = self.merge_diffusion_models(
+           model_paths, alpha, merge_method, force, **kwargs
+        )
+        dump_path = config.models_path / base_model.value / ModelType.Main.value
+        dump_path.mkdir(parents=True, exist_ok=True)
+        dump_path = dump_path / merged_model_name
+
+        merged_pipe.save_pretrained(dump_path, safe_serialization=1)
+        attributes = dict(
+            path = str(dump_path),
+            description = f"Merge of models {', '.join(model_names)}",
+            model_format = "diffusers",
+            variant = ModelVariantType.Normal.value,
+            vae = vae,
+        )
+        return self.manager.add_model(merged_model_name,
+                                      base_model = base_model,
+                                      model_type = ModelType.Main,
+                                      model_attributes = attributes,
+                                      clobber = True
+                                      )