Add cProfile for profiling graph execution.

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -6,6 +6,10 @@ title: '[bug]: '
 
 labels: ['bug']
 
+# assignees:
+#   - moderator_bot
+#   - lstein
+
 body:
   - type: markdown
     attributes:
@@ -14,9 +18,10 @@ body:
 
   - type: checkboxes
     attributes:
-      label: Is there an existing issue for this problem?
+      label: Is there an existing issue for this?
       description: |
-        Please [search](https://github.com/invoke-ai/InvokeAI/issues) first to see if an issue already exists for the problem.
+        Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
+        irst to see if an issue already exists for the bug you encountered.
       options:
         - label: I have searched the existing issues
           required: true
@@ -28,119 +33,80 @@ body:
   - type: dropdown
     id: os_dropdown
     attributes:
-      label: Operating system
-      description: Your computer's operating system.
+      label: OS
+      description: Which operating System did you use when the bug occured
       multiple: false
       options:
         - 'Linux'
         - 'Windows'
         - 'macOS'
-        - 'other'
     validations:
       required: true
 
   - type: dropdown
     id: gpu_dropdown
     attributes:
-      label: GPU vendor
-      description: Your GPU's vendor.
+      label: GPU
+      description: Which kind of Graphic-Adapter is your System using
       multiple: false
       options:
-        - 'Nvidia (CUDA)'
-        - 'AMD (ROCm)'
-        - 'Apple Silicon (MPS)'
-        - 'None (CPU)'
+        - 'cuda'
+        - 'amd'
+        - 'mps'
+        - 'cpu'
     validations:
       required: true
 
-  - type: input
-    id: gpu_model
-    attributes:
-      label: GPU model
-      description: Your GPU's model. If on Apple Silicon, this is your Mac's chip. Leave blank if on CPU.
-      placeholder: ex. RTX 2080 Ti, Mac M1 Pro
-    validations:
-      required: false
-
   - type: input
     id: vram
     attributes:
-      label: GPU VRAM
-      description: Your GPU's VRAM. If on Apple Silicon, this is your Mac's unified memory. Leave blank if on CPU.
+      label: VRAM
+      description: Size of the VRAM if known
       placeholder: 8GB
     validations:
       required: false
-
+      
   - type: input
     id: version-number
     attributes:
-      label: Version number
+      label: What version did you experience this issue on?
       description: |
-        The version of Invoke you have installed. If it is not the latest version, please update and try again to confirm the issue still exists. If you are testing main, please include the commit hash instead.
-      placeholder: ex. 3.6.1
+        Please share the version of Invoke AI that you experienced the issue on. If this is not the latest version, please update first to confirm the issue still exists. If you are testing main, please include the commit hash instead.
+      placeholder: X.X.X
     validations:
       required: true
 
-  - type: input
-    id: browser-version
-    attributes:
-      label: Browser
-      description: Your web browser and version.
-      placeholder: ex. Firefox 123.0b3
-    validations:
-      required: true
-
-  - type: textarea
-    id: python-deps
-    attributes:
-      label: Python dependencies
-      description: |
-        If the problem occurred during image generation, click the gear icon at the bottom left corner, click "About", click the copy button and then paste here.
-    validations:
-      required: false
-
   - type: textarea
     id: what-happened
     attributes:
-      label: What happened
+      label: What happened?
       description: |
-        Describe what happened. Include any relevant error messages, stack traces and screenshots here.
-      placeholder: I clicked button X and then Y happened.
+        Briefly describe what happened, what you expected to happen and how to reproduce this bug.
+      placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
     validations:
       required: true
 
   - type: textarea
-    id: what-you-expected
     attributes:
-      label: What you expected to happen
-      description: Describe what you expected to happen.
-      placeholder: I expected Z to happen.
-    validations:
-      required: true
-
-  - type: textarea
-    id: how-to-repro
-    attributes:
-      label: How to reproduce the problem
-      description: List steps to reproduce the problem.
-      placeholder: Start the app, generate an image with these settings, then click button X.
+      label: Screenshots
+      description: If applicable, add screenshots to help explain your problem
+      placeholder: this is what the result looked like <screenshot>
     validations:
       required: false
 
   - type: textarea
-    id: additional-context
     attributes:
       label: Additional context
-      description: Any other context that might help us to understand the problem.
+      description: Add any other context about the problem here
       placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
     validations:
       required: false
 
   - type: input
-    id: discord-username
+    id: contact
     attributes:
-      label: Discord username
-      description: If you are on the Invoke discord and would prefer to be contacted there, please provide your username.
-      placeholder: supercoolusername123
+      label: Contact Details
+      description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
+      placeholder: ex. email@example.com, discordname, twitter, ...
     validations:
       required: false

.github/pr_labels.yml

@@ -1,59 +0,0 @@
-Root:
-- changed-files:
-  - any-glob-to-any-file: '*'
-
-PythonDeps:
-- changed-files:
-  - any-glob-to-any-file: 'pyproject.toml'
-
-Python:
-- changed-files:
-  - all-globs-to-any-file: 
-    - 'invokeai/**'
-    - '!invokeai/frontend/web/**'
-
-PythonTests:
-- changed-files:
-  - any-glob-to-any-file: 'tests/**'
-
-CICD:
-- changed-files:
-  - any-glob-to-any-file: .github/**
-
-Docker:
-- changed-files:
-  - any-glob-to-any-file: docker/**
-
-Installer:
-- changed-files:
-  - any-glob-to-any-file: installer/**
-
-Documentation:
-- changed-files:
-  - any-glob-to-any-file: docs/**
-
-Invocations:
-- changed-files:
-  - any-glob-to-any-file: 'invokeai/app/invocations/**'
-
-Backend:
-- changed-files:
-  - any-glob-to-any-file: 'invokeai/backend/**'
-
-Api:
-- changed-files:
-  - any-glob-to-any-file: 'invokeai/app/api/**'
-
-Services:
-- changed-files:
-  - any-glob-to-any-file: 'invokeai/app/services/**'
-
-FrontendDeps:
-- changed-files:
-  - any-glob-to-any-file:
-    - '**/*/package.json'
-    - '**/*/pnpm-lock.yaml'
-
-Frontend:
-- changed-files:
-  - any-glob-to-any-file: 'invokeai/frontend/web/**'

.github/workflows/label-pr.yml

@@ -1,16 +0,0 @@
-name: "Pull Request Labeler"
-on:
-- pull_request_target
-
-jobs:
-  labeler:
-    permissions:
-      contents: read
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - uses: actions/labeler@v5
-        with:
-          configuration-path: .github/pr_labels.yml

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

@@ -58,7 +58,7 @@ jobs:
 
       - name: Check for changed python files
         id: changed-files
-        uses: tj-actions/changed-files@v41
+        uses: tj-actions/changed-files@v37
         with:
           files_yaml: |
             python:

README.md

@@ -169,7 +169,7 @@ the command `npm install -g pnpm` if needed)
     _For Linux with an AMD GPU:_
 
     ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
     _For non-GPU systems:_

docs/contributing/contribution_guides/contributingToFrontend.md

@@ -0,0 +1,76 @@
+# Contributing to the Frontend
+
+# InvokeAI Web UI
+
+- [InvokeAI Web UI](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#invokeai-web-ui)
+    - [Stack](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#stack)
+    - [Contributing](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#contributing)
+        - [Dev Environment](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#dev-environment)
+        - [Production builds](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#production-builds)
+
+The UI is a fairly straightforward Typescript React app, with the Unified Canvas being more complex.
+
+Code is located in `invokeai/frontend/web/` for review.
+
+## Stack
+
+State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). We lean heavily on RTK:
+
+- `createAsyncThunk` for HTTP requests
+- `createEntityAdapter` for fetching images and models
+- `createListenerMiddleware` for workflows
+
+The API client and associated types are generated from the OpenAPI schema. See API_CLIENT.md.
+
+Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a simple socket.io redux middleware to help).
+
+[Chakra-UI](https://github.com/chakra-ui/chakra-ui) & [Mantine](https://github.com/mantinedev/mantine) for components and styling.
+
+[Konva](https://github.com/konvajs/react-konva) for the canvas, but we are pushing the limits of what is feasible with it (and HTML canvas in general). We plan to rebuild it with [PixiJS](https://github.com/pixijs/pixijs) to take advantage of WebGL's improved raster handling.
+
+[Vite](https://vitejs.dev/) for bundling.
+
+Localisation is via [i18next](https://github.com/i18next/react-i18next), but translation happens on our [Weblate](https://hosted.weblate.org/engage/invokeai/) project. Only the English source strings should be changed on this repo.
+
+## Contributing
+
+Thanks for your interest in contributing to the InvokeAI Web UI!
+
+We encourage you to ping @psychedelicious and @blessedcoolant on [Discord](https://discord.gg/ZmtBAhwWhy) if you want to contribute, just to touch base and ensure your work doesn't conflict with anything else going on. The project is very active.
+
+### Dev Environment
+
+**Setup** 
+
+1. Install [node](https://nodejs.org/en/download/). You can confirm node is installed with:
+```bash
+node --version
+```
+
+2. Install [pnpm](https://pnpm.io/) and confirm it is installed by running this:
+```bash
+npm install --global pnpm
+pnpm --version
+```
+
+From `invokeai/frontend/web/` run `pnpm install` to get everything set up.
+
+Start everything in dev mode:
+1. Ensure your virtual environment is running
+2. Start the dev server: `pnpm dev`
+3. Start the InvokeAI Nodes backend: `python scripts/invokeai-web.py # run from the repo root`
+4. Point your browser to the dev server address e.g. [http://localhost:5173/](http://localhost:5173/)
+
+### VSCode Remote Dev
+
+We've noticed an intermittent issue with the VSCode Remote Dev port forwarding. If you use this feature of VSCode, you may intermittently click the Invoke button and then get nothing until the request times out. Suggest disabling the IDE's port forwarding feature and doing it manually via SSH:
+
+`ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host`
+
+### Production builds
+
+For a number of technical and logistical reasons, we need to commit UI build artefacts to the repo.
+
+If you submit a PR, there is a good chance we will ask you to include a separate commit with a build of the app.
+
+To build for production, run `pnpm build`.

docs/contributing/contribution_guides/development.md

@@ -12,7 +12,7 @@ To get started, take a look at our [new contributors checklist](newContributorCh
 Once you're setup, for more information, you can review the documentation specific to your area of interest:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web)
+* #### [Frontend Documentation](./contributingToFrontend.md)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 

docs/index.md

@@ -117,11 +117,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 ## :octicons-gift-24: InvokeAI Features
 
-### Installation
-  - [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
-  - [Manual Installation](installation/020_INSTALL_MANUAL.md)
-  - [Docker Installation](installation/040_INSTALL_DOCKER.md)
-
 ### The InvokeAI Web Interface
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)

docs/installation/010_INSTALL_AUTOMATED.md

@@ -477,7 +477,7 @@ Then type the following commands:
 
 === "AMD System"
     ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.6
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
 ### Corrupted configuration file

docs/installation/020_INSTALL_MANUAL.md

@@ -154,7 +154,7 @@ manager, please follow these steps:
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -313,7 +313,7 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md).
+You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
 
 If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
 
@@ -345,7 +345,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.6
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -361,7 +361,7 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/README.md) and do a production build of the UI as described.
+5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
 
 6.  You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -134,7 +134,7 @@ recipes are available
 
 When installing torch and torchvision manually with `pip`, remember to provide
 the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.6` as described in the [Manual
+https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
 Installation Guide](020_INSTALL_MANUAL.md).
 
 This will be done automatically for you if you use the installer

docs/installation/INSTALLATION.md

@@ -18,18 +18,13 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 
-## **[Automated Installer (Recommended)](010_INSTALL_AUTOMATED.md)**
- ✅ This is the recommended installation method for first-time users. 
+## **[Automated Installer](010_INSTALL_AUTOMATED.md)**
+✅ This is the recommended installation method for first-time users. 
 
   This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself.
-
-🖥️ **Download the latest installer .zip file here** : https://github.com/invoke-ai/InvokeAI/releases/latest
-  
-- *Look for the file labelled "InvokeAI-installer-v3.X.X.zip" at the bottom of the page*
-- If you experience issues, read through the full [installation instructions](010_INSTALL_AUTOMATED.md) to make sure you have met all of the installation requirements. If you need more help, join the [Discord](discord.gg/invoke-ai) or create an issue on [Github](https://github.com/invoke-ai/InvokeAI).
-
-
+  third party libraries and InvokeAI itself. It includes access to a
+  "developer console" which will help us debug problems with you and
+  give you to access experimental features.
 
 ## **[Manual Installation](020_INSTALL_MANUAL.md)**
 This method is recommended for experienced users and developers.

docs/nodes/communityNodes.md

@@ -14,7 +14,6 @@ To use a community workflow, download the the `.json` node graph file and load i
 
 - Community Nodes
     + [Adapters-Linked](#adapters-linked-nodes)
-    + [Autostereogram](#autostereogram-nodes)
     + [Average Images](#average-images)
     + [Clean Image Artifacts After Cut](#clean-image-artifacts-after-cut)
     + [Close Color Mask](#close-color-mask) 
@@ -26,7 +25,7 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [GPT2RandomPromptMaker](#gpt2randompromptmaker)
     + [Grid to Gif](#grid-to-gif)
     + [Halftone](#halftone)
-    + [Hand Refiner with MeshGraphormer](#hand-refiner-with-meshgraphormer)
+    + [Ideal Size](#ideal-size)
     + [Image and Mask Composition Pack](#image-and-mask-composition-pack)
     + [Image Dominant Color](#image-dominant-color)
     + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
@@ -42,7 +41,6 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [Oobabooga](#oobabooga)
     + [Prompt Tools](#prompt-tools)
     + [Remote Image](#remote-image)
-    + [BriaAI Background Remove](#briaai-remove-background)
     + [Remove Background](#remove-background)    
     + [Retroize](#retroize)
     + [Size Stepper Nodes](#size-stepper-nodes)
@@ -69,17 +67,6 @@ Note: These are inherited from the core nodes so any update to the core nodes sh
 
 **Node Link:** https://github.com/skunkworxdark/adapters-linked-nodes
 
---------------------------------
-### Autostereogram Nodes
-
-**Description:** Generate autostereogram images from a depth map. This is not a very practically useful node but more a 90s nostalgic indulgence as I used to love these images as a kid.
-
-**Node Link:** https://github.com/skunkworxdark/autostereogram_nodes
-
-**Example Usage:**
-</br>
-<img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/blob/main/images/spider-depth.png" width="200" /> -> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-dots.png" width="200" /> <img src="https://github.com/skunkworxdark/autostereogram_nodes/raw/main/images/spider-pattern.png" width="200" />
-
 --------------------------------
 ### Average Images
 
@@ -210,18 +197,13 @@ CMYK Halftone Output:
 <img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
 
 --------------------------------
+### Ideal Size
 
-### Hand Refiner with MeshGraphormer
+**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
 
-**Description**: Hand Refiner takes in your image and automatically generates a fixed depth map for the hands along with a mask of the hands region that will conveniently allow you to use them along with ControlNet to fix the wonky hands generated by Stable Diffusion
-
-**Node Link:** https://github.com/blessedcoolant/invoke_meshgraphormer
-
-**View**
-<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_meshgraphormer/main/assets/preview.jpg" />
+**Node Link:** https://github.com/JPPhoto/ideal-size-node
 
 --------------------------------
-
 ### Image and Mask Composition Pack
 
 **Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
@@ -435,17 +417,6 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Node Link:** https://github.com/fieldOfView/InvokeAI-remote_image
 
---------------------------------
-
-### BriaAI Remove Background
-
-**Description**: Implements one click background removal with BriaAI's new version 1.4 model which seems to be be producing better results than any other previous background removal tool.
-
-**Node Link:** https://github.com/blessedcoolant/invoke_bria_rmbg
-
-**View**
-<img src="https://raw.githubusercontent.com/blessedcoolant/invoke_bria_rmbg/main/assets/preview.jpg" />
-
 --------------------------------
 ### Remove Background
 

docs/nodes/defaultNodes.md

@@ -36,7 +36,6 @@ their descriptions.
 | Integer Math                                                  | Perform basic math operations on two integers                                                                                                        |
 | Convert Image Mode                                            | Converts an image to a different mode.                                                                                                               |
 | Crop Image                                                    | Crops an image to a specified box. The box can be outside of the image.                                                                              |
-| Ideal Size                                                    | Calculates an ideal image size for latents for a first pass of a multi-pass upscaling to avoid duplication and other artifacts                       |
 | Image Hue Adjustment                                          | Adjusts the Hue of an image.                                                                                                                         |
 | Inverse Lerp Image                                            | Inverse linear interpolation of all pixels of an image                                                                                               |
 | Image Primitive                                               | An image primitive value                                                                                                                             |

docs/other/CONTRIBUTORS.md

@@ -13,69 +13,46 @@ We thank them for all of their time and hard work.
 
 - [Lincoln D. Stein](mailto:lincoln.stein@gmail.com)
 
-## **Current Core Team**
+## **Current core team**
 
 * @lstein (Lincoln Stein) - Co-maintainer
 * @blessedcoolant - Co-maintainer
 * @hipsterusername (Kent Keirsey) - Co-maintainer, CEO, Positive Vibes
 * @psychedelicious (Spencer Mabrito) - Web Team Leader
-* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
-* @josh is toast (Josh Corbett) - Web Development
-* @cheerio (Mary Rogers) - Lead Engineer & Web App Development
+* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
+* @damian0815 - Attention Systems and Compel Maintainer
 * @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
-* @sunija - Standalone version
 * @genomancer (Gregg Helt) - Controlnet support
+* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @cheerio (Mary Rogers) - Lead Engineer & Web App Development
 * @brandon (Brandon Rising) - Platform, Infrastructure, Backend Systems
 * @ryanjdick (Ryan Dick) - Machine Learning & Training
-* @JPPhoto - Core image generation nodes
-* @dunkeroni - Image generation backend
-* @SkunkWorxDark - Image generation backend
+* @millu (Millun Atluri) - Community Manager, Documentation, Node-wrangler
+* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
 * @keturn (Kevin Turner) - Diffusers
-* @millu (Millun Atluri) - Community Wizard, Documentation, Node-wrangler, 
-* @glimmerleaf (Devon Hopkins) - Community Wizard
 * @gogurt enjoyer - Discord moderator and end user support
 * @whosawhatsis - Discord moderator and end user support
 * @dwinrger - Discord moderator and end user support
 * @526christian - Discord moderator and end user support
-* @harvester62 -  Discord moderator and end user support
-
-
-## **Honored Team Alumni**
-
-* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
-* @damian0815 - Attention Systems and Compel Maintainer
-* @netsvetaev (Artur) - Localization support
-* @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
-* @tildebyte - Installation and configuration
-* @mauwii (Matthias Wilde) - Installation, release, continuous integration
-
 
 ## **Full List of Contributors by Commit Name**
 
-- 이승석
 - AbdBarho
 - ablattmann
 - AdamOStark
 - Adam Rice
 - Airton Silva
-- Aldo Hoeben
 - Alexander Eichhorn
 - Alexandre D. Roberge
-- Alexandre Macabies
-- Alfie John
 - Andreas Rozek
 - Andre LaBranche
 - Andy Bearman
 - Andy Luhrs
 - Andy Pilate
-- Anonymous
-- Anthony Monthe
 - Any-Winter-4079
 - apolinario
-- Ar7ific1al
 - ArDiouscuros
 - Armando C. Santisbon
-- Arnold Cordewiner
 - Arthur Holstvoogd
 - artmen1516
 - Artur
@@ -87,16 +64,13 @@ We thank them for all of their time and hard work.
 - blhook
 - BlueAmulet
 - Bouncyknighter
-- Brandon
 - Brandon Rising
 - Brent Ozar
 - Brian Racer
 - bsilvereagle
 - c67e708d
-- camenduru
 - CapableWeb
 - Carson Katri
-- chainchompa
 - Chloe
 - Chris Dawson
 - Chris Hayes
@@ -112,45 +86,30 @@ We thank them for all of their time and hard work.
 - cpacker
 - Cragin Godley
 - creachec
-- CrypticWit
-- d8ahazard
-- damian
-- damian0815
-- Damian at mba
 - Damian Stewart
 - Daniel Manzke
 - Danny Beer
 - Dan Sully
-- Darren Ringer
 - David Burnett
 - David Ford
 - David Regla
-- David Sisco
 - David Wager
 - Daya Adianto
 - db3000
-- DekitaRPG
 - Denis Olshin
 - Dennis
-- dependabot[bot]
-- Dmitry Parnas
-- Dobrynia100
 - Dominic Letz
 - DrGunnarMallon
-- Drun555
-- dunkeroni
 - Edward Johan
 - elliotsayes
 - Elrik
 - ElrikUnderlake
 - Eric Khun
 - Eric Wolf
-- Eugene
 - Eugene Brodsky
 - ExperimentalCyborg
 - Fabian Bahl
 - Fabio 'MrWHO' Torchetti
-- Fattire
 - fattire
 - Felipe Nogueira
 - Félix Sanz
@@ -159,12 +118,8 @@ We thank them for all of their time and hard work.
 - gabrielrotbart
 - gallegonovato
 - Gérald LONLAS
-- Gille
 - GitHub Actions Bot
-- glibesyck
 - gogurtenjoyer
-- Gohsuke Shimada
-- greatwolf
 - greentext2
 - Gregg Helt
 - H4rk
@@ -176,7 +131,6 @@ We thank them for all of their time and hard work.
 - Hosted Weblate
 - Iman Karim
 - ismail ihsan bülbül
-- ItzAttila
 - Ivan Efimov
 - jakehl
 - Jakub Kolčář
@@ -187,7 +141,6 @@ We thank them for all of their time and hard work.
 - Jason Toffaletti
 - Jaulustus
 - Jeff Mahoney
-- Jennifer Player
 - jeremy
 - Jeremy Clark
 - JigenD
@@ -195,26 +148,19 @@ We thank them for all of their time and hard work.
 - Johan Roxendal
 - Johnathon Selstad
 - Jonathan
-- Jordan Hewitt
 - Joseph Dries III
-- Josh Corbett
 - JPPhoto
 - jspraul
-- junzi
 - Justin Wong
 - Juuso V
 - Kaspar Emanuel
 - Katsuyuki-Karasawa
-- Keerigan45
 - Kent Keirsey
-- Kevin Brack
 - Kevin Coakley
 - Kevin Gibbons
 - Kevin Schaul
 - Kevin Turner
-- Kieran Klaassen
 - krummrey
-- Kyle
 - Kyle Lacy
 - Kyle Schouviller
 - Lawrence Norton
@@ -225,15 +171,10 @@ We thank them for all of their time and hard work.
 - Lynne Whitehorn
 - majick
 - Marco Labarile
-- Marta Nahorniuk
 - Martin Kristiansen
-- Mary Hipp
-- maryhipp
 - Mary Hipp Rogers
-- mastercaster
 - mastercaster9000
 - Matthias Wild
-- mauwii
 - michaelk71
 - mickr777
 - Mihai
@@ -241,15 +182,11 @@ We thank them for all of their time and hard work.
 - Mikhail Tishin
 - Millun Atluri
 - Minjune Song
-- Mitchell Allain
 - mitien
 - mofuzz
 - Muhammad Usama
 - Name
 - _nderscore
-- Neil Wang
-- nekowaiz
-- nemuruibai
 - Netzer R
 - Nicholas Koh
 - Nicholas Körfer
@@ -260,11 +197,9 @@ We thank them for all of their time and hard work.
 - ofirkris
 - Olivier Louvignes
 - owenvincent
-- pand4z31
 - Patrick Esser
 - Patrick Tien
 - Patrick von Platen
-- Paul Curry
 - Paul Sajna
 - pejotr
 - Peter Baylies
@@ -272,7 +207,6 @@ We thank them for all of their time and hard work.
 - plucked
 - prixt
 - psychedelicious
-- psychedelicious@windows
 - Rainer Bernhardt
 - Riccardo Giovanetti
 - Rich Jones
@@ -281,22 +215,17 @@ We thank them for all of their time and hard work.
 - Robert Bolender
 - Robin Rombach
 - Rohan Barar
-- Rohinish
+- rohinish404
 - rpagliuca
 - rromb
 - Rupesh Sreeraman
-- Ryan
 - Ryan Cao
-- Ryan Dick
 - Saifeddine
 - Saifeddine ALOUI
-- Sam
 - SammCheese
-- Sam McLeod
 - Sammy
 - sammyf
 - Samuel Husso
-- Saurav Maheshkar
 - Scott Lahteine
 - Sean McLellan
 - Sebastian Aigner
@@ -304,21 +233,16 @@ We thank them for all of their time and hard work.
 - Sergey Krashevich
 - Shapor Naghibzadeh
 - Shawn Zhong
-- Simona Liliac
 - Simon Vans-Colina
 - skunkworxdark
 - slashtechno
-- SoheilRezaei
-- Song, Pengcheng
 - spezialspezial
 - ssantos
 - StAlKeR7779
-- Stefan Tobler
 - Stephan Koglin-Fischer
 - SteveCaruso
 - Steve Martinelli
 - Steven Frank
-- Surisen
 - System X - Files
 - Taylor Kems
 - techicode
@@ -337,34 +261,26 @@ We thank them for all of their time and hard work.
 - tyler
 - unknown
 - user1
-- vedant-3010
 - Vedant Madane
 - veprogames
 - wa.code
 - wfng92
-- whjms
 - whosawhatsis
 - Will
 - William Becher
 - William Chong
-- Wilson E. Alvarez
-- woweenie
-- Wubbbi
 - xra
 - Yeung Yiu Hung
 - ymgenesis
 - Yorzaren
 - Yosuke Shinya
 - yun saki
-- ZachNagengast
 - Zadagu
 - zeptofine
-- Zerdoumi
-- Васянатор
 - 冯不游
 - 唐澤 克幸
 
-## **Original CompVis (Stable Diffusion) Authors**
+## **Original CompVis Authors**
 
 - [Robin Rombach](https://github.com/rromb)
 - [Patrick von Platen](https://github.com/patrickvonplaten)

installer/create_installer.sh

@@ -14,19 +14,11 @@ function is_bin_in_path {
 }
 
 function git_show {
-    git show -s --format=oneline --abbrev-commit "$1" | cat
+    git show -s --format='%h %s' $1
 }
 
-if [[ -v "VIRTUAL_ENV" ]]; then
-    # we can't just call 'deactivate' because this function is not exported
-    # to the environment of this script from the bash process that runs the script
-    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
-    exit -1
-fi
-
 cd "$(dirname "$0")"
 
-echo
 echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
 echo "The current working directory is $(pwd)"
 read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
@@ -40,6 +32,13 @@ if ! is_bin_in_path python && is_bin_in_path python3; then
     }
 fi
 
+if [[ -v "VIRTUAL_ENV" ]]; then
+    # we can't just call 'deactivate' because this function is not exported
+    # to the environment of this script from the bash process that runs the script
+    echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
+    exit -1
+fi
+
 VERSION=$(
     cd ..
     python -c "from invokeai.version import __version__ as version; print(version)"
@@ -48,9 +47,38 @@ PATCH=""
 VERSION="v${VERSION}${PATCH}"
 
 echo -e "${BGREEN}HEAD${RESET}:"
-git_show HEAD
+git_show
 echo
 
+# ---------------------- FRONTEND ----------------------
+
+pushd ../invokeai/frontend/web >/dev/null
+echo
+echo "Installing frontend dependencies..."
+echo
+pnpm i --frozen-lockfile
+echo
+echo "Building frontend..."
+echo
+pnpm build
+popd
+
+# ---------------------- BACKEND ----------------------
+
+echo
+echo "Building wheel..."
+echo
+
+# install the 'build' package in the user site packages, if needed
+# could be improved by using a temporary venv, but it's tiny and harmless
+if [[ $(python -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
+    pip install --user build
+fi
+
+rm -rf ../build
+
+python -m build --wheel --outdir dist/ ../.
+
 # ----------------------
 
 echo
@@ -69,13 +97,16 @@ done
 mkdir InvokeAI-Installer/lib
 cp lib/*.py InvokeAI-Installer/lib
 
+# Move the wheel
+mv dist/*.whl InvokeAI-Installer/lib/
+
 # Install scripts
 # Mac/Linux
 cp install.sh.in InvokeAI-Installer/install.sh
 chmod a+x InvokeAI-Installer/install.sh
 
 # Windows
-cp install.bat.in InvokeAI-Installer/install.bat
+perl -p -e "s/^set INVOKEAI_VERSION=.*/set INVOKEAI_VERSION=$VERSION/" install.bat.in >InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
 # Zip everything up

installer/install.bat.in

@@ -15,6 +15,7 @@ if "%1" == "use-cache" (
 @rem Config
 @rem The version in the next line is replaced by an up to date release number
 @rem when create_installer.sh is run. Change the release number there.
+set INVOKEAI_VERSION=latest
 set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
 set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
 set PYTHON_URL=https://www.python.org/downloads/windows/

installer/lib/installer.py

@@ -11,7 +11,7 @@ import sys
 import venv
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import Optional, Tuple
+from typing import Union
 
 SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
@@ -21,20 +21,40 @@ OS = platform.uname().system
 ARCH = platform.uname().machine
 VERSION = "latest"
 
+### Feature flags
+# Install the virtualenv into the runtime dir
+FF_VENV_IN_RUNTIME = True
+
+# Install the wheel packaged with the installer
+FF_USE_LOCAL_WHEEL = True
+
 
 class Installer:
     """
     Deploys an InvokeAI installation into a given path
     """
 
-    reqs: list[str] = INSTALLER_REQS
-
     def __init__(self) -> None:
+        self.reqs = INSTALLER_REQS
+        self.preflight()
         if os.getenv("VIRTUAL_ENV") is not None:
             print("A virtual environment is already activated. Please 'deactivate' before installation.")
             sys.exit(-1)
         self.bootstrap()
-        self.available_releases = get_github_releases()
+
+    def preflight(self) -> None:
+        """
+        Preflight checks
+        """
+
+        # TODO
+        # verify python version
+        # on macOS verify XCode tools are present
+        # verify libmesa, libglx on linux
+        # check that the system arch is not i386 (?)
+        # check that the system has a GPU, and the type of GPU
+
+        pass
 
     def mktemp_venv(self) -> TemporaryDirectory:
         """
@@ -58,9 +78,12 @@ class Installer:
 
         return venv_dir
 
-    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory | None:
+    def bootstrap(self, verbose: bool = False) -> TemporaryDirectory:
         """
         Bootstrap the installer venv with packages required at install time
+
+        :return: path to the virtual environment directory that was bootstrapped
+        :rtype: TemporaryDirectory
         """
 
         print("Initializing the installer. This may take a minute - please wait...")
@@ -72,27 +95,39 @@ class Installer:
         cmd.extend(self.reqs)
 
         try:
-            # upgrade pip to the latest version to avoid a confusing message
-            res = upgrade_pip(Path(venv_dir.name))
-            if verbose:
-                print(res)
-
-            # run the install prerequisites installation
             res = subprocess.check_output(cmd).decode()
-
             if verbose:
                 print(res)
-
             return venv_dir
         except subprocess.CalledProcessError as e:
             print(e)
 
-    def app_venv(self, venv_parent) -> Path:
+    def app_venv(self, path: str = None):
         """
         Create a virtualenv for the InvokeAI installation
         """
 
-        venv_dir = venv_parent / ".venv"
+        # explicit venv location
+        # currently unused in normal operation
+        # useful for testing or special cases
+        if path is not None:
+            venv_dir = Path(path)
+
+        # experimental / testing
+        elif not FF_VENV_IN_RUNTIME:
+            if OS == "Windows":
+                venv_dir_parent = os.getenv("APPDATA", "~/AppData/Roaming")
+            elif OS == "Darwin":
+                # there is no environment variable on macOS to find this
+                # TODO: confirm this is working as expected
+                venv_dir_parent = "~/Library/Application Support"
+            elif OS == "Linux":
+                venv_dir_parent = os.getenv("XDG_DATA_DIR", "~/.local/share")
+            venv_dir = Path(venv_dir_parent).expanduser().resolve() / f"InvokeAI/{VERSION}/venv"
+
+        # stable / current
+        else:
+            venv_dir = self.dest / ".venv"
 
         # Prefer to copy python executables
         # so that updates to system python don't break InvokeAI
@@ -106,7 +141,7 @@ class Installer:
         return venv_dir
 
     def install(
-        self, version=None, root: str = "~/invokeai", yes_to_all=False, find_links: Optional[Path] = None
+        self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None
     ) -> None:
         """
         Install the InvokeAI application into the given runtime path
@@ -123,20 +158,15 @@ class Installer:
 
         import messages
 
-        messages.welcome(self.available_releases)
+        messages.welcome()
 
-        version = messages.choose_version(self.available_releases)
-
-        auto_dest = Path(os.environ.get("INVOKEAI_ROOT", root)).expanduser().resolve()
-        destination = auto_dest if yes_to_all else messages.dest_path(root)
-        if destination is None:
-            print("Could not find or create the destination directory. Installation cancelled.")
-            sys.exit(0)
+        default_path = os.environ.get("INVOKEAI_ROOT") or Path(root).expanduser().resolve()
+        self.dest = default_path if yes_to_all else messages.dest_path(root)
 
         # create the venv for the app
-        self.venv = self.app_venv(venv_parent=destination)
+        self.venv = self.app_venv()
 
-        self.instance = InvokeAiInstance(runtime=destination, venv=self.venv, version=version)
+        self.instance = InvokeAiInstance(runtime=self.dest, venv=self.venv, version=version)
 
         # install dependencies and the InvokeAI application
         (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
@@ -160,7 +190,7 @@ class InvokeAiInstance:
     A single runtime directory *may* be shared by multiple virtual environments, though this isn't currently tested or supported.
     """
 
-    def __init__(self, runtime: Path, venv: Path, version: str = "stable") -> None:
+    def __init__(self, runtime: Path, venv: Path, version: str) -> None:
         self.runtime = runtime
         self.venv = venv
         self.pip = get_pip_from_venv(venv)
@@ -169,7 +199,6 @@ class InvokeAiInstance:
         set_sys_path(venv)
         os.environ["INVOKEAI_ROOT"] = str(self.runtime.expanduser().resolve())
         os.environ["VIRTUAL_ENV"] = str(self.venv.expanduser().resolve())
-        upgrade_pip(venv)
 
     def get(self) -> tuple[Path, Path]:
         """
@@ -183,7 +212,54 @@ class InvokeAiInstance:
 
     def install(self, extra_index_url=None, optional_modules=None, find_links=None):
         """
-        Install the package from PyPi.
+        Install this instance, including dependencies and the app itself
+
+        :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
+        :type extra_index_url: str
+        """
+
+        import messages
+
+        # install torch first to ensure the correct version gets installed.
+        # works with either source or wheel install with negligible impact on installation times.
+        messages.simple_banner("Installing PyTorch :fire:")
+        self.install_torch(extra_index_url, find_links)
+
+        messages.simple_banner("Installing the InvokeAI Application :art:")
+        self.install_app(extra_index_url, optional_modules, find_links)
+
+    def install_torch(self, extra_index_url=None, find_links=None):
+        """
+        Install PyTorch
+        """
+
+        from plumbum import FG, local
+
+        pip = local[self.pip]
+
+        (
+            pip[
+                "install",
+                "--require-virtualenv",
+                "numpy==1.26.3",  # choose versions that won't be uninstalled during phase 2
+                "urllib3~=1.26.0",
+                "requests~=2.28.0",
+                "torch==2.1.2",
+                "torchmetrics==0.11.4",
+                "torchvision==0.16.2",
+                "--force-reinstall",
+                "--find-links" if find_links is not None else None,
+                find_links,
+                "--extra-index-url" if extra_index_url is not None else None,
+                extra_index_url,
+            ]
+            & FG
+        )
+
+    def install_app(self, extra_index_url=None, optional_modules=None, find_links=None):
+        """
+        Install the application with pip.
+        Supports installation from PyPi or from a local source directory.
 
         :param extra_index_url: the "--extra-index-url ..." line for pip to look in extra indexes.
         :type extra_index_url: str
@@ -195,52 +271,53 @@ class InvokeAiInstance:
         :type find_links: Path
         """
 
-        import messages
-
-        # not currently used, but may be useful for "install most recent version" option
-        if self.version == "prerelease":
+        ## this only applies to pypi installs; TODO actually use this
+        if self.version == "pre":
             version = None
-            pre_flag = "--pre"
-        elif self.version == "stable":
-            version = None
-            pre_flag = None
+            pre = "--pre"
         else:
             version = self.version
-            pre_flag = None
+            pre = None
 
-        src = "invokeai"
-        if optional_modules:
-            src += optional_modules
-        if version:
-            src += f"=={version}"
+        ## TODO: only local wheel will be installed as of now; support for --version arg is TODO
+        if FF_USE_LOCAL_WHEEL:
+            # if no wheel, try to do a source install before giving up
+            try:
+                src = str(next(Path(__file__).parent.glob("InvokeAI-*.whl")))
+            except StopIteration:
+                try:
+                    src = Path(__file__).parents[1].expanduser().resolve()
+                    # if the above directory contains one of these files, we'll do a source install
+                    next(src.glob("pyproject.toml"))
+                    next(src.glob("invokeai"))
+                except StopIteration:
+                    print("Unable to find a wheel or perform a source install. Giving up.")
 
-        messages.simple_banner("Installing the InvokeAI Application :art:")
+        elif version == "source":
+            # this makes an assumption about the location of the installer package in the source tree
+            src = Path(__file__).parents[1].expanduser().resolve()
+        else:
+            # will install from PyPi
+            src = f"invokeai=={version}" if version is not None else "invokeai"
 
-        from plumbum import FG, ProcessExecutionError, local  # type: ignore
+        from plumbum import FG, local
 
         pip = local[self.pip]
 
-        pipeline = pip[
-            "install",
-            "--require-virtualenv",
-            "--force-reinstall",
-            "--use-pep517",
-            str(src),
-            "--find-links" if find_links is not None else None,
-            find_links,
-            "--extra-index-url" if extra_index_url is not None else None,
-            extra_index_url,
-            pre_flag,
-        ]
-
-        try:
-            _ = pipeline & FG
-        except ProcessExecutionError as e:
-            print(f"Error: {e}")
-            print(
-                "Could not install InvokeAI. Please try downloading the latest version of the installer and install again."
-            )
-            sys.exit(1)
+        (
+            pip[
+                "install",
+                "--require-virtualenv",
+                "--use-pep517",
+                str(src) + (optional_modules if optional_modules else ""),
+                "--find-links" if find_links is not None else None,
+                find_links,
+                "--extra-index-url" if extra_index_url is not None else None,
+                extra_index_url,
+                pre,
+            ]
+            & FG
+        )
 
     def configure(self):
         """
@@ -296,6 +373,7 @@ class InvokeAiInstance:
 
         ext = "bat" if OS == "Windows" else "sh"
 
+        # scripts = ['invoke', 'update']
         scripts = ["invoke"]
 
         for script in scripts:
@@ -330,23 +408,6 @@ def get_pip_from_venv(venv_path: Path) -> str:
     return str(venv_path.expanduser().resolve() / pip)
 
 
-def upgrade_pip(venv_path: Path) -> str | None:
-    """
-    Upgrade the pip executable in the given virtual environment
-    """
-
-    python = "Scripts\\python.exe" if OS == "Windows" else "bin/python"
-    python = str(venv_path.expanduser().resolve() / python)
-
-    try:
-        result = subprocess.check_output([python, "-m", "pip", "install", "--upgrade", "pip"]).decode()
-    except subprocess.CalledProcessError as e:
-        print(e)
-        result = None
-
-    return result
-
-
 def set_sys_path(venv_path: Path) -> None:
     """
     Given a path to a virtual environment, set the sys.path, in a cross-platform fashion,
@@ -370,43 +431,7 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_github_releases() -> tuple[list, list] | None:
-    """
-    Query Github for published (pre-)release versions.
-    Return a tuple where the first element is a list of stable releases and the second element is a list of pre-releases.
-    Return None if the query fails for any reason.
-    """
-
-    import requests
-
-    ## get latest releases using github api
-    url = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
-    releases, pre_releases = [], []
-    try:
-        res = requests.get(url)
-        res.raise_for_status()
-        tag_info = res.json()
-        for tag in tag_info:
-            if not tag["prerelease"]:
-                releases.append(tag["tag_name"].lstrip("v"))
-            else:
-                pre_releases.append(tag["tag_name"].lstrip("v"))
-    except requests.HTTPError as e:
-        print(f"Error: {e}")
-        print("Could not fetch version information from GitHub. Please check your network connection and try again.")
-        return
-    except Exception as e:
-        print(f"Error: {e}")
-        print("An unexpected error occurred while trying to fetch version information from GitHub. Please try again.")
-        return
-
-    releases.sort(reverse=True)
-    pre_releases.sort(reverse=True)
-
-    return releases, pre_releases
-
-
-def get_torch_source() -> Tuple[str | None, str | None]:
+def get_torch_source() -> (Union[str, None], str):
     """
     Determine the extra index URL for pip to use for torch installation.
     This depends on the OS and the graphics accelerator in use.
@@ -421,26 +446,25 @@ def get_torch_source() -> Tuple[str | None, str | None]:
     :rtype: list
     """
 
-    from messages import select_gpu
+    from messages import graphical_accelerator
 
-    # device can be one of: "cuda", "rocm", "cpu", "cuda_and_dml, autodetect"
-    device = select_gpu()
+    # device can be one of: "cuda", "rocm", "cpu", "idk"
+    device = graphical_accelerator()
 
     url = None
     optional_modules = "[onnx]"
     if OS == "Linux":
-        if device.value == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.6"
-        elif device.value == "cpu":
+        if device == "rocm":
+            url = "https://download.pytorch.org/whl/rocm5.4.2"
+        elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
-    elif OS == "Windows":
-        if device.value == "cuda":
-            url = "https://download.pytorch.org/whl/cu121"
-            optional_modules = "[xformers,onnx-cuda]"
-        if device.value == "cuda_and_dml":
-            url = "https://download.pytorch.org/whl/cu121"
-            optional_modules = "[xformers,onnx-directml]"
+    if device == "cuda":
+        url = "https://download.pytorch.org/whl/cu121"
+        optional_modules = "[xformers,onnx-cuda]"
+    if device == "cuda_and_dml":
+        url = "https://download.pytorch.org/whl/cu121"
+        optional_modules = "[xformers,onnx-directml]"
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/lib/messages.py

@@ -5,11 +5,10 @@ Installer user interaction
 
 import os
 import platform
-from enum import Enum
 from pathlib import Path
 
 from prompt_toolkit import HTML, prompt
-from prompt_toolkit.completion import FuzzyWordCompleter, PathCompleter
+from prompt_toolkit.completion import PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
 from rich.console import Console, Group, group
@@ -36,26 +35,16 @@ else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
 
-def welcome(available_releases: tuple | None = None) -> None:
+def welcome():
     @group()
     def text():
-        if (platform_specific := _platform_specific_help()) is not None:
+        if (platform_specific := _platform_specific_help()) != "":
             yield platform_specific
             yield ""
         yield Text.from_markup(
             "Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.",
             justify="center",
         )
-        if available_releases is not None:
-            latest_stable = available_releases[0][0]
-            last_pre = available_releases[1][0]
-            yield ""
-            yield Text.from_markup(
-                f"[red3]🠶[/] Latest stable release (recommended): [b bright_white]{latest_stable}", justify="center"
-            )
-            yield Text.from_markup(
-                f"[red3]🠶[/] Last published pre-release version: [b bright_white]{last_pre}", justify="center"
-            )
 
     console.rule()
     print(
@@ -72,31 +61,19 @@ def welcome(available_releases: tuple | None = None) -> None:
     console.line()
 
 
-def choose_version(available_releases: tuple | None = None) -> str:
-    """
-    Prompt the user to choose an Invoke version to install
-    """
-
-    # short circuit if we couldn't get a version list
-    # still try to install the latest stable version
-    if available_releases is None:
-        return "stable"
-
-    console.print(":grey_question: [orange3]Please choose an Invoke version to install.")
-
-    choices = available_releases[0] + available_releases[1]
-
-    response = prompt(
-        message=f"   <Enter> to install the recommended release ({choices[0]}). <Tab> or type to pick a version: ",
-        complete_while_typing=True,
-        completer=FuzzyWordCompleter(choices),
-    )
-
-    console.print(f"   Version {choices[0] if response == "" else response} will be installed.")
-
+def confirm_install(dest: Path) -> bool:
+    if dest.exists():
+        print(f":exclamation: Directory {dest} already exists :exclamation:")
+        dest_confirmed = Confirm.ask(
+            ":stop_sign: (re)install in this location?",
+            default=False,
+        )
+    else:
+        print(f"InvokeAI will be installed in {dest}")
+        dest_confirmed = Confirm.ask("Use this location?", default=True)
     console.line()
 
-    return "stable" if response == "" else response
+    return dest_confirmed
 
 
 def user_wants_auto_configuration() -> bool:
@@ -132,23 +109,7 @@ def user_wants_auto_configuration() -> bool:
     return choice.lower().startswith("a")
 
 
-def confirm_install(dest: Path) -> bool:
-    if dest.exists():
-        print(f":stop_sign: Directory {dest} already exists!")
-        print("   Is this location correct?")
-        default = False
-    else:
-        print(f":file_folder: InvokeAI will be installed in {dest}")
-        default = True
-
-    dest_confirmed = Confirm.ask("   Please confirm:", default=default)
-
-    console.line()
-
-    return dest_confirmed
-
-
-def dest_path(dest=None) -> Path | None:
+def dest_path(dest=None) -> Path:
     """
     Prompt the user for the destination path and create the path
 
@@ -163,21 +124,25 @@ def dest_path(dest=None) -> Path | None:
     else:
         dest = Path.cwd().expanduser().resolve()
     prev_dest = init_path = dest
-    dest_confirmed = False
+
+    dest_confirmed = confirm_install(dest)
 
     while not dest_confirmed:
-        browse_start = (dest or Path.cwd()).expanduser().resolve()
+        # if the given destination already exists, the starting point for browsing is its parent directory.
+        # the user may have made a typo, or otherwise wants to place the root dir next to an existing one.
+        # if the destination dir does NOT exist, then the user must have changed their mind about the selection.
+        # since we can't read their mind, start browsing at Path.cwd().
+        browse_start = (prev_dest.parent if prev_dest.exists() else Path.cwd()).expanduser().resolve()
 
         path_completer = PathCompleter(
             only_directories=True,
             expanduser=True,
-            get_paths=lambda: [str(browse_start)],  # noqa: B023
+            get_paths=lambda: [browse_start],  # noqa: B023
             # get_paths=lambda: [".."].extend(list(browse_start.iterdir()))
         )
 
         console.line()
-
-        console.print(f":grey_question: [orange3]Please select the install destination:[/] \\[{browse_start}]: ")
+        console.print(f"[orange3]Please select the destination directory for the installation:[/] \\[{browse_start}]: ")
         selected = prompt(
             ">>> ",
             complete_in_thread=True,
@@ -190,7 +155,6 @@ def dest_path(dest=None) -> Path | None:
         )
         prev_dest = dest
         dest = Path(selected)
-
         console.line()
 
         dest_confirmed = confirm_install(dest.expanduser().resolve())
@@ -218,45 +182,41 @@ def dest_path(dest=None) -> Path | None:
         console.rule("Goodbye!")
 
 
-class GpuType(Enum):
-    CUDA = "cuda"
-    CUDA_AND_DML = "cuda_and_dml"
-    ROCM = "rocm"
-    CPU = "cpu"
-    AUTODETECT = "autodetect"
-
-
-def select_gpu() -> GpuType:
+def graphical_accelerator():
     """
-    Prompt the user to select the GPU driver
+    Prompt the user to select the graphical accelerator in their system
+    This does not validate user's choices (yet), but only offers choices
+    valid for the platform.
+    CUDA is the fallback.
+    We may be able to detect the GPU driver by shelling out to `modprobe` or `lspci`,
+    but this is not yet supported or reliable. Also, some users may have exotic preferences.
     """
 
     if ARCH == "arm64" and OS != "Darwin":
         print(f"Only CPU acceleration is available on {ARCH} architecture. Proceeding with that.")
-        return GpuType.CPU
+        return "cpu"
 
     nvidia = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
-        GpuType.CUDA,
+        "cuda",
     )
     nvidia_with_dml = (
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
-        GpuType.CUDA_AND_DML,
+        "cuda_and_dml",
     )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
-        GpuType.ROCM,
+        "rocm",
     )
     cpu = (
-        "Do not install any GPU support, use CPU for generation (slow)",
-        GpuType.CPU,
+        "no compatible GPU, or specifically prefer to use the CPU",
+        "cpu",
     )
-    autodetect = (
+    idk = (
         "I'm not sure what to choose",
-        GpuType.AUTODETECT,
+        "idk",
     )
 
-    options = []
     if OS == "Windows":
         options = [nvidia, nvidia_with_dml, cpu]
     if OS == "Linux":
@@ -270,7 +230,7 @@ def select_gpu() -> GpuType:
         return options[0][1]
 
     # "I don't know" is always added the last option
-    options.append(autodetect)  # type: ignore
+    options.append(idk)
 
     options = {str(i): opt for i, opt in enumerate(options, 1)}
 
@@ -305,9 +265,9 @@ def select_gpu() -> GpuType:
         ),
     )
 
-    if options[choice][1] is GpuType.AUTODETECT:
+    if options[choice][1] == "idk":
         console.print(
-            "No problem. We will install CUDA support first :crossed_fingers: If Invoke does not detect a GPU, please re-run the installer and select one of the other GPU types."
+            "No problem. We will try to install a version that [i]should[/i] be compatible. :crossed_fingers:"
         )
 
     return options[choice][1]
@@ -331,7 +291,7 @@ def windows_long_paths_registry() -> None:
     """
 
     with open(str(Path(__file__).parent / "WinLongPathsEnabled.reg"), "r", encoding="utf-16le") as code:
-        syntax = Syntax(code.read(), line_numbers=True, lexer="regedit")
+        syntax = Syntax(code.read(), line_numbers=True)
 
     console.print(
         Panel(
@@ -341,7 +301,7 @@ def windows_long_paths_registry() -> None:
                         "We will now apply a registry fix to enable long paths on Windows. InvokeAI needs this to function correctly. We are asking your permission to modify the Windows Registry on your behalf.",
                         "",
                         "This is the change that will be applied:",
-                        str(syntax),
+                        syntax,
                     ]
                 )
             ),
@@ -380,7 +340,7 @@ def introduction() -> None:
     console.line(2)
 
 
-def _platform_specific_help() -> Text | None:
+def _platform_specific_help() -> str:
     if OS == "Darwin":
         text = Text.from_markup(
             """[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/]."""
@@ -394,5 +354,5 @@ def _platform_specific_help() -> Text | None:
      [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]"""
         )
     else:
-        return
+        text = ""
     return text

installer/templates/invoke.bat.in

@@ -15,7 +15,7 @@ echo 4. Download and install models
 echo 5. Change InvokeAI startup options
 echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 7. Open the developer console
-echo 8. Update InvokeAI (DEPRECATED - please use the installer)
+echo 8. Update InvokeAI
 echo 9. Run the InvokeAI image database maintenance script
 echo 10. Command-line help
 echo Q - Quit
@@ -52,10 +52,8 @@ IF /I "%choice%" == "1" (
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
 ) ELSE IF /I "%choice%" == "8" (
-    echo UPDATING FROM WITHIN THE APP IS BEING DEPRECATED.
-    echo Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.
-    timeout 4
-    python -m invokeai.frontend.install.invokeai_update
+   echo Running invokeai-update...
+   python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "9" (
    echo Running the db maintenance script...
    python .venv\Scripts\invokeai-db-maintenance.exe
@@ -79,3 +77,4 @@ pause
 
 :ending
 exit /b
+

installer/templates/invoke.sh.in

@@ -90,9 +90,7 @@ do_choice() {
         ;;
     8)
         clear
-        printf "UPDATING FROM WITHIN THE APP IS BEING DEPRECATED\n"
-        printf "Please download the installer from https://github.com/invoke-ai/InvokeAI/releases/latest and run it to update your installation.\n"
-        sleep 4
+        printf "Update InvokeAI\n"
         python -m invokeai.frontend.install.invokeai_update
         ;;
     9)
@@ -124,7 +122,7 @@ do_dialog() {
         5 "Change InvokeAI startup options"
         6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         7 "Open the developer console"
-        8 "Update InvokeAI (DEPRECATED - please use the installer)"
+        8 "Update InvokeAI"
 	9 "Run the InvokeAI image database maintenance script"
 	10 "Command-line help"
     )

installer/templates/update.bat.in

@@ -0,0 +1,72 @@
+@echo off
+setlocal EnableExtensions EnableDelayedExpansion
+
+PUSHD "%~dp0"
+
+set INVOKE_AI_VERSION=latest
+set arg=%1
+if "%arg%" neq "" (
+   if "%arg:~0,2%" equ "/?" (
+       echo Usage: update.bat ^<release name or branch^>
+       echo Updates InvokeAI to use the indicated version of the code base.
+       echo Find the version or branch for the release you want, and pass it as the argument.
+       echo For example '.\update.bat v2.2.5' for release 2.2.5.
+       echo             '.\update.bat main' for the latest development version
+       echo.
+       echo If no argument provided then will install the most recent release, equivalent to
+       echo '.\update.bat latest'
+       exit /b
+   ) else (
+       set INVOKE_AI_VERSION=%arg%
+   )
+)
+
+set INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/!INVOKE_AI_VERSION!.zip"
+set INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/!INVOKE_AI_VERSION!/environments-and-requirements/requirements-base.txt
+set INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
+
+call curl -I "%INVOKE_AI_DEP%" -fs >.tmp.out
+if %errorlevel% neq 0 (
+    echo '!INVOKE_AI_VERSION!' is not a known branch name or tag. Please check the version and try again.
+    echo "Press any key to continue"
+    pause
+    exit /b
+)
+del .tmp.out
+
+echo This script will update InvokeAI and all its dependencies to !INVOKE_AI_SRC!.
+echo If you do not want to do this, press control-C now!
+pause
+
+call curl -L "%INVOKE_AI_DEP%" > environments-and-requirements/requirements-base.txt
+call curl -L "%INVOKE_AI_MODELS%" > configs/INITIAL_MODELS.yaml
+
+
+call .venv\Scripts\activate.bat
+call .venv\Scripts\python -mpip install -r requirements.txt
+if %errorlevel% neq 0 (
+   echo Installation of requirements failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
+   pause
+   exit /b
+)
+
+call .venv\Scripts\python -mpip install !INVOKE_AI_SRC!
+if %errorlevel% neq 0 (
+   echo Installation of InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
+   pause
+   exit /b
+)
+
+@rem call .venv\Scripts\invokeai-configure --root=.
+
+@rem if %errorlevel% neq 0 (
+@rem    echo Configuration InvokeAI failed. See https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting for suggestions.
+@rem    pause
+@rem    exit /b
+@rem )
+
+echo InvokeAI has been updated to '%INVOKE_AI_VERSION%'
+
+echo "Press any key to continue"
+pause
+endlocal

installer/templates/update.sh.in

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+
+set -eu
+
+if [ $# -ge 1 ] && [ "${1:0:2}" == "-h" ]; then
+    echo "Usage: update.sh <release>"
+    echo "Updates InvokeAI to use the indicated version of the code base."
+    echo "Find the version or branch for the release you want, and pass it as the argument."
+    echo "For example: update.sh v2.2.5 for release 2.2.5."
+    echo "             update.sh main for the current development version."
+    echo ""
+    echo "If no argument provided then will install the version tagged with 'latest', equivalent to"
+    echo "update.sh latest"
+    exit -1
+fi
+
+INVOKE_AI_VERSION=${1:-latest}
+
+INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive/$INVOKE_AI_VERSION.zip"
+INVOKE_AI_DEP=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/environments-and-requirements/requirements-base.txt
+INVOKE_AI_MODELS=https://raw.githubusercontent.com/invoke-ai/InvokeAI/$INVOKE_AI_VERSION/configs/INITIAL_MODELS.yaml
+
+# ensure we're in the correct folder in case user's CWD is somewhere else
+scriptdir=$(dirname "$0")
+cd "$scriptdir"
+
+function _err_exit {
+    if test "$1" -ne 0
+    then
+	echo "Something went wrong while installing InvokeAI and/or its requirements."
+	echo "Update cannot continue. Please report this error to https://github.com/invoke-ai/InvokeAI/issues"
+        echo -e "Error code $1; Error caught was '$2'"
+        read -p "Press any key to exit..."
+        exit
+    fi
+}
+
+if ! curl -I "$INVOKE_AI_DEP" -fs >/dev/null; then
+    echo \'$INVOKE_AI_VERSION\' is not a known branch name or tag. Please check the version and try again.
+    exit
+fi
+
+echo This script will update InvokeAI and all its dependencies to version \'$INVOKE_AI_VERSION\'.
+echo If you do not want to do this, press control-C now!
+read -p "Press any key to continue, or CTRL-C to exit..."
+
+curl -L "$INVOKE_AI_DEP" > environments-and-requirements/requirements-base.txt
+curl -L "$INVOKE_AI_MODELS" > configs/INITIAL_MODELS.yaml
+
+. .venv/bin/activate
+
+./.venv/bin/python -mpip install -r requirements.txt
+_err_exit $? "The pip program failed to install InvokeAI's requirements."
+
+./.venv/bin/python -mpip install $INVOKE_AI_SRC
+_err_exit $? "The pip program failed to install InvokeAI."
+
+echo InvokeAI updated to \'$INVOKE_AI_VERSION\'

invokeai/app/api/dependencies.py

@@ -2,7 +2,6 @@
 
 from logging import Logger
 
-from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
@@ -22,10 +21,11 @@ from ..services.invocation_queue.invocation_queue_memory import MemoryInvocation
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
+from ..services.item_storage.item_storage_sqlite import SqliteItemStorage
 from ..services.latents_storage.latents_storage_disk import DiskLatentsStorage
 from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
+from ..services.model_install import ModelInstallService
 from ..services.model_manager.model_manager_default import ModelManagerService
-from ..services.model_metadata import ModelMetadataStoreSQL
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
 from ..services.session_processor.session_processor_default import DefaultSessionProcessor
@@ -61,7 +61,7 @@ class ApiDependencies:
     invoker: Invoker
 
     @staticmethod
-    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger) -> None:
+    def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger):
         logger.info(f"InvokeAI version {__version__}")
         logger.info(f"Root directory = {str(config.root_path)}")
         logger.debug(f"Internet connectivity is {config.internet_available}")
@@ -79,18 +79,16 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        graph_execution_manager = ItemStorageMemory[GraphExecutionState]()
+        graph_execution_manager = SqliteItemStorage[GraphExecutionState](db=db, table_name="graph_executions")
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
+        model_manager = ModelManagerService(config, logger)
+        model_record_service = ModelRecordServiceSQL(db=db)
         download_queue_service = DownloadQueueService(event_bus=events)
-        model_metadata_service = ModelMetadataStoreSQL(db=db)
-        model_manager = ModelManagerService.build_model_manager(
-            app_config=configuration,
-            model_record_service=ModelRecordServiceSQL(db=db, metadata_store=model_metadata_service),
-            download_queue=download_queue_service,
-            events=events,
+        model_install_service = ModelInstallService(
+            app_config=config, record_store=model_record_service, event_bus=events
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
@@ -116,7 +114,9 @@ class ApiDependencies:
             latents=latents,
             logger=logger,
             model_manager=model_manager,
+            model_records=model_record_service,
             download_queue=download_queue_service,
+            model_install=model_install_service,
             names=names,
             performance_statistics=performance_statistics,
             processor=processor,
@@ -131,6 +131,6 @@ class ApiDependencies:
         db.clean()
 
     @staticmethod
-    def shutdown() -> None:
+    def shutdown():
         if ApiDependencies.invoker:
             ApiDependencies.invoker.stop()

invokeai/app/api/no_cache_staticfiles.py

@@ -1,28 +0,0 @@
-from typing import Any
-
-from starlette.responses import Response
-from starlette.staticfiles import StaticFiles
-
-
-class NoCacheStaticFiles(StaticFiles):
-    """
-    This class is used to override the default caching behavior of starlette for static files,
-    ensuring we *never* cache static files. It modifies the file response headers to strictly
-    never cache the files.
-
-    Static files include the javascript bundles, fonts, locales, and some images. Generated
-    images are not included, as they are served by a router.
-    """
-
-    def __init__(self, *args: Any, **kwargs: Any):
-        self.cachecontrol = "max-age=0, no-cache, no-store, , must-revalidate"
-        self.pragma = "no-cache"
-        self.expires = "0"
-        super().__init__(*args, **kwargs)
-
-    def file_response(self, *args: Any, **kwargs: Any) -> Response:
-        resp = super().file_response(*args, **kwargs)
-        resp.headers.setdefault("Cache-Control", self.cachecontrol)
-        resp.headers.setdefault("Pragma", self.pragma)
-        resp.headers.setdefault("Expires", self.expires)
-        return resp

invokeai/app/api/routers/download_queue.py

@@ -36,7 +36,7 @@ async def list_downloads() -> List[DownloadJob]:
         400: {"description": "Bad request"},
     },
 )
-async def prune_downloads() -> Response:
+async def prune_downloads():
     """Prune completed and errored jobs."""
     queue = ApiDependencies.invoker.services.download_queue
     queue.prune_jobs()
@@ -55,7 +55,7 @@ async def download(
 ) -> DownloadJob:
     """Download the source URL to the file or directory indicted in dest."""
     queue = ApiDependencies.invoker.services.download_queue
-    return queue.download(source, Path(dest), priority, access_token)
+    return queue.download(source, dest, priority, access_token)
 
 
 @download_queue_router.get(
@@ -87,7 +87,7 @@ async def get_download_job(
 )
 async def cancel_download_job(
     id: int = Path(description="ID of the download job to cancel."),
-) -> Response:
+):
     """Cancel a download job using its ID."""
     try:
         queue = ApiDependencies.invoker.services.download_queue
@@ -105,7 +105,7 @@ async def cancel_download_job(
         204: {"description": "Download jobs have been cancelled"},
     },
 )
-async def cancel_all_download_jobs() -> Response:
+async def cancel_all_download_jobs():
     """Cancel all download jobs."""
     ApiDependencies.invoker.services.download_queue.cancel_all_jobs()
     return Response(status_code=204)

invokeai/app/api/routers/model_manager.py

@@ -1,759 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein
-"""FastAPI route for model configuration records."""
-
-import pathlib
-import shutil
-from hashlib import sha1
-from random import randbytes
-from typing import Any, Dict, List, Optional, Set
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict
-from starlette.exceptions import HTTPException
-from typing_extensions import Annotated
-
-from invokeai.app.services.model_install import ModelInstallJob, ModelSource
-from invokeai.app.services.model_records import (
-    DuplicateModelException,
-    InvalidModelException,
-    ModelRecordOrderBy,
-    ModelSummary,
-    UnknownModelException,
-)
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager.config import (
-    AnyModelConfig,
-    BaseModelType,
-    MainCheckpointConfig,
-    ModelFormat,
-    ModelType,
-    SubModelType,
-)
-from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..dependencies import ApiDependencies
-
-model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
-
-
-class ModelsList(BaseModel):
-    """Return list of configs."""
-
-    models: List[AnyModelConfig]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-class ModelTagSet(BaseModel):
-    """Return tags for a set of models."""
-
-    key: str
-    name: str
-    author: str
-    tags: Set[str]
-
-
-##############################################################################
-# These are example inputs and outputs that are used in places where Swagger
-# is unable to generate a correct example.
-##############################################################################
-example_model_config = {
-    "path": "string",
-    "name": "string",
-    "base": "sd-1",
-    "type": "main",
-    "format": "checkpoint",
-    "config": "string",
-    "key": "string",
-    "original_hash": "string",
-    "current_hash": "string",
-    "description": "string",
-    "source": "string",
-    "last_modified": 0,
-    "vae": "string",
-    "variant": "normal",
-    "prediction_type": "epsilon",
-    "repo_variant": "fp16",
-    "upcast_attention": False,
-    "ztsnr_training": False,
-}
-
-example_model_input = {
-    "path": "/path/to/model",
-    "name": "model_name",
-    "base": "sd-1",
-    "type": "main",
-    "format": "checkpoint",
-    "config": "configs/stable-diffusion/v1-inference.yaml",
-    "description": "Model description",
-    "vae": None,
-    "variant": "normal",
-}
-
-example_model_metadata = {
-    "name": "ip_adapter_sd_image_encoder",
-    "author": "InvokeAI",
-    "tags": [
-        "transformers",
-        "safetensors",
-        "clip_vision_model",
-        "endpoints_compatible",
-        "region:us",
-        "has_space",
-        "license:apache-2.0",
-    ],
-    "files": [
-        {
-            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/README.md",
-            "path": "ip_adapter_sd_image_encoder/README.md",
-            "size": 628,
-            "sha256": None,
-        },
-        {
-            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/config.json",
-            "path": "ip_adapter_sd_image_encoder/config.json",
-            "size": 560,
-            "sha256": None,
-        },
-        {
-            "url": "https://huggingface.co/InvokeAI/ip_adapter_sd_image_encoder/resolve/main/model.safetensors",
-            "path": "ip_adapter_sd_image_encoder/model.safetensors",
-            "size": 2528373448,
-            "sha256": "6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030",
-        },
-    ],
-    "type": "huggingface",
-    "id": "InvokeAI/ip_adapter_sd_image_encoder",
-    "tag_dict": {"license": "apache-2.0"},
-    "last_modified": "2023-09-23T17:33:25Z",
-}
-
-##############################################################################
-# ROUTES
-##############################################################################
-
-
-@model_manager_router.get(
-    "/",
-    operation_id="list_model_records",
-)
-async def list_model_records(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
-    model_format: Optional[ModelFormat] = Query(
-        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
-    ),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    found_models: list[AnyModelConfig] = []
-    if base_models:
-        for base_model in base_models:
-            found_models.extend(
-                record_store.search_by_attr(
-                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
-                )
-            )
-    else:
-        found_models.extend(
-            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
-        )
-    return ModelsList(models=found_models)
-
-
-@model_manager_router.get(
-    "/i/{key}",
-    operation_id="get_model_record",
-    responses={
-        200: {
-            "description": "The model configuration was retrieved successfully",
-            "content": {"application/json": {"example": example_model_config}},
-        },
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-    },
-)
-async def get_model_record(
-    key: str = Path(description="Key of the model record to fetch."),
-) -> AnyModelConfig:
-    """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    try:
-        config: AnyModelConfig = record_store.get_model(key)
-        return config
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_manager_router.get("/summary", operation_id="list_model_summary")
-async def list_model_summary(
-    page: int = Query(default=0, description="The page to get"),
-    per_page: int = Query(default=10, description="The number of models per page"),
-    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-) -> PaginatedResults[ModelSummary]:
-    """Gets a page of model summary data."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
-    return results
-
-
-@model_manager_router.get(
-    "/meta/i/{key}",
-    operation_id="get_model_metadata",
-    responses={
-        200: {
-            "description": "The model metadata was retrieved successfully",
-            "content": {"application/json": {"example": example_model_metadata}},
-        },
-        400: {"description": "Bad request"},
-        404: {"description": "No metadata available"},
-    },
-)
-async def get_model_metadata(
-    key: str = Path(description="Key of the model repo metadata to fetch."),
-) -> Optional[AnyModelRepoMetadata]:
-    """Get a model metadata object."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    result: Optional[AnyModelRepoMetadata] = record_store.get_metadata(key)
-    if not result:
-        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
-    return result
-
-
-@model_manager_router.get(
-    "/tags",
-    operation_id="list_tags",
-)
-async def list_tags() -> Set[str]:
-    """Get a unique set of all the model tags."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    result: Set[str] = record_store.list_tags()
-    return result
-
-
-@model_manager_router.get(
-    "/tags/search",
-    operation_id="search_by_metadata_tags",
-)
-async def search_by_metadata_tags(
-    tags: Set[str] = Query(default=None, description="Tags to search for"),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    results = record_store.search_by_metadata_tag(tags)
-    return ModelsList(models=results)
-
-
-@model_manager_router.patch(
-    "/i/{key}",
-    operation_id="update_model_record",
-    responses={
-        200: {
-            "description": "The model was updated successfully",
-            "content": {"application/json": {"example": example_model_config}},
-        },
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-)
-async def update_model_record(
-    key: Annotated[str, Path(description="Unique key of model")],
-    info: Annotated[
-        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
-    ],
-) -> AnyModelConfig:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    try:
-        model_response: AnyModelConfig = record_store.update_model(key, config=info)
-        logger.info(f"Updated model: {key}")
-    except UnknownModelException as 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))
-    return model_response
-
-
-@model_manager_router.delete(
-    "/i/{key}",
-    operation_id="del_model_record",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-)
-async def del_model_record(
-    key: str = Path(description="Unique key of model to remove from model registry."),
-) -> Response:
-    """
-    Delete model record from database.
-
-    The configuration record will be removed. The corresponding weights files will be
-    deleted as well if they reside within the InvokeAI "models" directory.
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_manager.install
-        installer.delete(key)
-        logger.info(f"Deleted model: {key}")
-        return Response(status_code=204)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_manager_router.post(
-    "/i/",
-    operation_id="add_model_record",
-    responses={
-        201: {
-            "description": "The model added successfully",
-            "content": {"application/json": {"example": example_model_config}},
-        },
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-        415: {"description": "Unrecognized file/folder format"},
-    },
-    status_code=201,
-)
-async def add_model_record(
-    config: Annotated[
-        AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
-    ],
-) -> AnyModelConfig:
-    """Add a model using the configuration information appropriate for its type."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_manager.store
-    if config.key == "<NOKEY>":
-        config.key = sha1(randbytes(100)).hexdigest()
-        logger.info(f"Created model {config.key} for {config.name}")
-    try:
-        record_store.add_model(config.key, config)
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-
-    # now fetch it out
-    result: AnyModelConfig = record_store.get_model(config.key)
-    return result
-
-
-@model_manager_router.post(
-    "/heuristic_import",
-    operation_id="heuristic_import_model",
-    responses={
-        201: {"description": "The model imported successfully"},
-        415: {"description": "Unrecognized file/folder format"},
-        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,
-)
-async def heuristic_import(
-    source: str,
-    config: Optional[Dict[str, Any]] = Body(
-        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
-        default=None,
-        example={"name": "modelT", "description": "antique cars"},
-    ),
-    access_token: Optional[str] = None,
-) -> ModelInstallJob:
-    """Install a model using a string identifier.
-
-    `source` can be any of the following.
-
-    1. A path on the local filesystem ('C:\\users\\fred\\model.safetensors')
-    2. A Url pointing to a single downloadable model file
-    3. A HuggingFace repo_id with any of the following formats:
-       - model/name
-       - model/name:fp16:vae
-       - model/name::vae          -- use default precision
-       - model/name:fp16:path/to/model.safetensors
-       - model/name::path/to/model.safetensors
-
-    `config` is an optional dict containing model configuration values that will override
-    the ones that are probed automatically.
-
-    `access_token` is an optional access token for use with Urls that require
-    authentication.
-
-    Models will be downloaded, probed, configured and installed in a
-    series of background threads. The return object has `status` attribute
-    that can be used to monitor progress.
-
-    See the documentation for `import_model_record` for more information on
-    interpreting the job information returned by this route.
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_manager.install
-        result: ModelInstallJob = installer.heuristic_import(
-            source=source,
-            config=config,
-        )
-        logger.info(f"Started installation of {source}")
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return result
-
-
-@model_manager_router.post(
-    "/install",
-    operation_id="import_model",
-    responses={
-        201: {"description": "The model imported successfully"},
-        415: {"description": "Unrecognized file/folder format"},
-        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,
-)
-async def import_model(
-    source: ModelSource,
-    config: Optional[Dict[str, Any]] = Body(
-        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
-        default=None,
-    ),
-) -> ModelInstallJob:
-    """Install a model using its local path, repo_id, or remote URL.
-
-    Models will be downloaded, probed, configured and installed in a
-    series of background threads. The return object has `status` attribute
-    that can be used to monitor progress.
-
-    The source object is a discriminated Union of LocalModelSource,
-    HFModelSource and URLModelSource. Set the "type" field to the
-    appropriate value:
-
-    * To install a local path using LocalModelSource, pass a source of form:
-      ```
-      {
-        "type": "local",
-        "path": "/path/to/model",
-        "inplace": false
-      }
-      ```
-      The "inplace" flag, if true, will register the model in place in its
-      current filesystem location. Otherwise, the model will be copied
-      into the InvokeAI models directory.
-
-    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
-      ```
-      {
-        "type": "hf",
-        "repo_id": "stabilityai/stable-diffusion-2.0",
-        "variant": "fp16",
-        "subfolder": "vae",
-        "access_token": "f5820a918aaf01"
-      }
-      ```
-      The `variant`, `subfolder` and `access_token` fields are optional.
-
-    * To install a remote model using an arbitrary URL, pass:
-      ```
-      {
-        "type": "url",
-        "url": "http://www.civitai.com/models/123456",
-        "access_token": "f5820a918aaf01"
-      }
-      ```
-      The `access_token` field is optonal
-
-    The model's configuration record will be probed and filled in
-    automatically.  To override the default guesses, pass "metadata"
-    with a Dict containing the attributes you wish to override.
-
-    Installation occurs in the background. Either use list_model_install_jobs()
-    to poll for completion, or listen on the event bus for the following events:
-
-      * "model_install_running"
-      * "model_install_completed"
-      * "model_install_error"
-
-    On successful completion, the event's payload will contain the field "key"
-    containing the installed ID of the model. On an error, the event's payload
-    will contain the fields "error_type" and "error" describing the nature of the
-    error and its traceback, respectively.
-
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_manager.install
-        result: ModelInstallJob = installer.import_model(
-            source=source,
-            config=config,
-        )
-        logger.info(f"Started installation of {source}")
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return result
-
-
-@model_manager_router.get(
-    "/import",
-    operation_id="list_model_install_jobs",
-)
-async def list_model_install_jobs() -> List[ModelInstallJob]:
-    """Return the list of model install jobs.
-
-    Install jobs have a numeric `id`, a `status`, and other fields that provide information on
-    the nature of the job and its progress. The `status` is one of:
-
-    * "waiting" -- Job is waiting in the queue to run
-    * "downloading" -- Model file(s) are downloading
-    * "running" -- Model has downloaded and the model probing and registration process is running
-    * "completed" -- Installation completed successfully
-    * "error" -- An error occurred. Details will be in the "error_type" and "error" fields.
-    * "cancelled" -- Job was cancelled before completion.
-
-    Once completed, information about the model such as its size, base
-    model, type, and metadata can be retrieved from the `config_out`
-    field. For multi-file models such as diffusers, information on individual files
-    can be retrieved from `download_parts`.
-
-    See the example and schema below for more information.
-    """
-    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_manager.install.list_jobs()
-    return jobs
-
-
-@model_manager_router.get(
-    "/import/{id}",
-    operation_id="get_model_install_job",
-    responses={
-        200: {"description": "Success"},
-        404: {"description": "No such job"},
-    },
-)
-async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
-    """
-    Return model install job corresponding to the given source. See the documentation for 'List Model Install Jobs'
-    for information on the format of the return value.
-    """
-    try:
-        result: ModelInstallJob = ApiDependencies.invoker.services.model_manager.install.get_job_by_id(id)
-        return result
-    except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_manager_router.delete(
-    "/import/{id}",
-    operation_id="cancel_model_install_job",
-    responses={
-        201: {"description": "The job was cancelled successfully"},
-        415: {"description": "No such job"},
-    },
-    status_code=201,
-)
-async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
-    """Cancel the model install job(s) corresponding to the given job ID."""
-    installer = ApiDependencies.invoker.services.model_manager.install
-    try:
-        job = installer.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=415, detail=str(e))
-    installer.cancel_job(job)
-
-
-@model_manager_router.patch(
-    "/import",
-    operation_id="prune_model_install_jobs",
-    responses={
-        204: {"description": "All completed and errored jobs have been pruned"},
-        400: {"description": "Bad request"},
-    },
-)
-async def prune_model_install_jobs() -> Response:
-    """Prune all completed and errored jobs from the install job list."""
-    ApiDependencies.invoker.services.model_manager.install.prune_jobs()
-    return Response(status_code=204)
-
-
-@model_manager_router.patch(
-    "/sync",
-    operation_id="sync_models_to_config",
-    responses={
-        204: {"description": "Model config record database resynced with files on disk"},
-        400: {"description": "Bad request"},
-    },
-)
-async def sync_models_to_config() -> Response:
-    """
-    Traverse the models and autoimport directories.
-
-    Model files without a corresponding
-    record in the database are added. Orphan records without a models file are deleted.
-    """
-    ApiDependencies.invoker.services.model_manager.install.sync_to_config()
-    return Response(status_code=204)
-
-
-@model_manager_router.put(
-    "/convert/{key}",
-    operation_id="convert_model",
-    responses={
-        200: {
-            "description": "Model converted successfully",
-            "content": {"application/json": {"example": example_model_config}},
-        },
-        400: {"description": "Bad request"},
-        404: {"description": "Model not found"},
-        409: {"description": "There is already a model registered at this location"},
-    },
-)
-async def convert_model(
-    key: str = Path(description="Unique key of the safetensors main model to convert to diffusers format."),
-) -> AnyModelConfig:
-    """
-    Permanently convert a model into diffusers format, replacing the safetensors version.
-    Note that during the conversion process the key and model hash will change.
-    The return value is the model configuration for the converted model.
-    """
-    logger = ApiDependencies.invoker.services.logger
-    loader = ApiDependencies.invoker.services.model_manager.load
-    store = ApiDependencies.invoker.services.model_manager.store
-    installer = ApiDependencies.invoker.services.model_manager.install
-
-    try:
-        model_config = store.get_model(key)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-
-    if not isinstance(model_config, MainCheckpointConfig):
-        logger.error(f"The model with key {key} is not a main checkpoint model.")
-        raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
-
-    # loading the model will convert it into a cached diffusers file
-    loader.load_model_by_config(model_config, submodel_type=SubModelType.Scheduler)
-
-    # Get the path of the converted model from the loader
-    cache_path = loader.convert_cache.cache_path(key)
-    assert cache_path.exists()
-
-    # temporarily rename the original safetensors file so that there is no naming conflict
-    original_name = model_config.name
-    model_config.name = f"{original_name}.DELETE"
-    store.update_model(key, config=model_config)
-
-    # install the diffusers
-    try:
-        new_key = installer.install_path(
-            cache_path,
-            config={
-                "name": original_name,
-                "description": model_config.description,
-                "original_hash": model_config.original_hash,
-                "source": model_config.source,
-            },
-        )
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-    # get the original metadata
-    if orig_metadata := store.get_metadata(key):
-        store.metadata_store.add_metadata(new_key, orig_metadata)
-
-    # delete the original safetensors file
-    installer.delete(key)
-
-    # delete the cached version
-    shutil.rmtree(cache_path)
-
-    # return the config record for the new diffusers directory
-    new_config: AnyModelConfig = store.get_model(new_key)
-    return new_config
-
-
-@model_manager_router.put(
-    "/merge",
-    operation_id="merge",
-    responses={
-        200: {
-            "description": "Model converted successfully",
-            "content": {"application/json": {"example": example_model_config}},
-        },
-        400: {"description": "Bad request"},
-        404: {"description": "Model not found"},
-        409: {"description": "There is already a model registered at this location"},
-    },
-)
-async def merge(
-    keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
-    merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
-    alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-    force: bool = Body(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    ),
-    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
-    merge_dest_directory: Optional[str] = Body(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    ),
-) -> AnyModelConfig:
-    """
-    Merge diffusers models. The process is controlled by a set parameters provided in the body of the request.
-    ```
-    Argument                Description [default]
-    --------               ----------------------
-    keys                   List of 2-3 model keys to merge together. All models must use the same base type.
-    merged_model_name      Name for the merged model [Concat model names]
-    alpha                  Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
-    force                  If true, force the merge even if the models were generated by different versions of the diffusers library [False]
-    interp                 Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
-    merge_dest_directory   Specify a directory to store the merged model in [models directory]
-    ```
-    """
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-        installer = ApiDependencies.invoker.services.model_manager.install
-        merger = ModelMerger(installer)
-        model_names = [installer.record_store.get_model(x).name for x in keys]
-        response = merger.merge_diffusion_models_and_save(
-            model_keys=keys,
-            merged_model_name=merged_model_name or "+".join(model_names),
-            alpha=alpha,
-            interp=interp,
-            force=force,
-            merge_dest_directory=dest,
-        )
-    except UnknownModelException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{keys}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/routers/model_records.py

@@ -0,0 +1,322 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+
+from hashlib import sha1
+from random import randbytes
+from typing import Any, Dict, List, Optional
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, ConfigDict
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob, ModelSource
+from invokeai.app.services.model_records import (
+    DuplicateModelException,
+    InvalidModelException,
+    UnknownModelException,
+)
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    ModelType,
+)
+
+from ..dependencies import ApiDependencies
+
+model_records_router = APIRouter(prefix="/v1/model/record", tags=["model_manager_v2_unstable"])
+
+
+class ModelsList(BaseModel):
+    """Return list of configs."""
+
+    models: list[AnyModelConfig]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+@model_records_router.get(
+    "/",
+    operation_id="list_model_records",
+)
+async def list_model_records(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
+    model_format: Optional[str] = Query(
+        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
+    ),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_records
+    found_models: list[AnyModelConfig] = []
+    if base_models:
+        for base_model in base_models:
+            found_models.extend(
+                record_store.search_by_attr(
+                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
+                )
+            )
+    else:
+        found_models.extend(
+            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
+        )
+    return ModelsList(models=found_models)
+
+
+@model_records_router.get(
+    "/i/{key}",
+    operation_id="get_model_record",
+    responses={
+        200: {"description": "Success"},
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+    },
+)
+async def get_model_record(
+    key: str = Path(description="Key of the model record to fetch."),
+) -> AnyModelConfig:
+    """Get a model record"""
+    record_store = ApiDependencies.invoker.services.model_records
+    try:
+        return record_store.get_model(key)
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_records_router.patch(
+    "/i/{key}",
+    operation_id="update_model_record",
+    responses={
+        200: {"description": "The model was updated successfully"},
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+    response_model=AnyModelConfig,
+)
+async def update_model_record(
+    key: Annotated[str, Path(description="Unique key of model")],
+    info: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
+) -> AnyModelConfig:
+    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_records
+    try:
+        model_response = record_store.update_model(key, config=info)
+        logger.info(f"Updated model: {key}")
+    except UnknownModelException as 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))
+    return model_response
+
+
+@model_records_router.delete(
+    "/i/{key}",
+    operation_id="del_model_record",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+)
+async def del_model_record(
+    key: str = Path(description="Unique key of model to remove from model registry."),
+) -> Response:
+    """
+    Delete model record from database.
+
+    The configuration record will be removed. The corresponding weights files will be
+    deleted as well if they reside within the InvokeAI "models" directory.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_install
+        installer.delete(key)
+        logger.info(f"Deleted model: {key}")
+        return Response(status_code=204)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_records_router.post(
+    "/i/",
+    operation_id="add_model_record",
+    responses={
+        201: {"description": "The model added successfully"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+        415: {"description": "Unrecognized file/folder format"},
+    },
+    status_code=201,
+)
+async def add_model_record(
+    config: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
+) -> AnyModelConfig:
+    """
+    Add a model using the configuration information appropriate for its type.
+    """
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_records
+    if config.key == "<NOKEY>":
+        config.key = sha1(randbytes(100)).hexdigest()
+        logger.info(f"Created model {config.key} for {config.name}")
+    try:
+        record_store.add_model(config.key, config)
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+
+    # now fetch it out
+    return record_store.get_model(config.key)
+
+
+@model_records_router.post(
+    "/import",
+    operation_id="import_model_record",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        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,
+)
+async def import_model(
+    source: ModelSource,
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+    ),
+) -> ModelInstallJob:
+    """Add a model using its local path, repo_id, or remote URL.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    The source object is a discriminated Union of LocalModelSource,
+    HFModelSource and URLModelSource. Set the "type" field to the
+    appropriate value:
+
+    * To install a local path using LocalModelSource, pass a source of form:
+      `{
+        "type": "local",
+        "path": "/path/to/model",
+        "inplace": false
+      }`
+       The "inplace" flag, if true, will register the model in place in its
+       current filesystem location. Otherwise, the model will be copied
+       into the InvokeAI models directory.
+
+    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
+      `{
+        "type": "hf",
+        "repo_id": "stabilityai/stable-diffusion-2.0",
+        "variant": "fp16",
+        "subfolder": "vae",
+        "access_token": "f5820a918aaf01"
+      }`
+     The `variant`, `subfolder` and `access_token` fields are optional.
+
+    * To install a remote model using an arbitrary URL, pass:
+      `{
+        "type": "url",
+        "url": "http://www.civitai.com/models/123456",
+        "access_token": "f5820a918aaf01"
+      }`
+    The `access_token` field is optonal
+
+    The model's configuration record will be probed and filled in
+    automatically.  To override the default guesses, pass "metadata"
+    with a Dict containing the attributes you wish to override.
+
+    Installation occurs in the background. Either use list_model_install_jobs()
+    to poll for completion, or listen on the event bus for the following events:
+
+      "model_install_started"
+      "model_install_completed"
+      "model_install_error"
+
+    On successful completion, the event's payload will contain the field "key"
+    containing the installed ID of the model. On an error, the event's payload
+    will contain the fields "error_type" and "error" describing the nature of the
+    error and its traceback, respectively.
+
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_install
+        result: ModelInstallJob = installer.import_model(
+            source=source,
+            config=config,
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_records_router.get(
+    "/import",
+    operation_id="list_model_install_jobs",
+)
+async def list_model_install_jobs() -> List[ModelInstallJob]:
+    """
+    Return list of model install jobs.
+
+    If the optional 'source' argument is provided, then the list will be filtered
+    for partial string matches against the install source.
+    """
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_install.list_jobs()
+    return jobs
+
+
+@model_records_router.patch(
+    "/import",
+    operation_id="prune_model_install_jobs",
+    responses={
+        204: {"description": "All completed and errored jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_model_install_jobs() -> Response:
+    """
+    Prune all completed and errored jobs from the install job list.
+    """
+    ApiDependencies.invoker.services.model_install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_records_router.patch(
+    "/sync",
+    operation_id="sync_models_to_config",
+    responses={
+        204: {"description": "Model config record database resynced with files on disk"},
+        400: {"description": "Bad request"},
+    },
+)
+async def sync_models_to_config() -> Response:
+    """
+    Traverse the models and autoimport directories. Model files without a corresponding
+    record in the database are added. Orphan records without a models file are deleted.
+    """
+    ApiDependencies.invoker.services.model_install.sync_to_config()
+    return Response(status_code=204)

invokeai/app/api/routers/models.py

@@ -0,0 +1,427 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2023 Lincoln D. Stein
+
+import pathlib
+from typing import Annotated, List, Literal, Optional, Union
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
+from starlette.exceptions import HTTPException
+
+from invokeai.backend import BaseModelType, ModelType
+from invokeai.backend.model_management import MergeInterpolationMethod
+from invokeai.backend.model_management.models import (
+    OPENAPI_MODEL_CONFIGS,
+    InvalidModelException,
+    ModelNotFoundException,
+    SchedulerPredictionType,
+)
+
+from ..dependencies import ApiDependencies
+
+models_router = APIRouter(prefix="/v1/models", tags=["models"])
+
+UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
+
+ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
+
+ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
+
+MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+
+
+class ModelsList(BaseModel):
+    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+ModelsListValidator = TypeAdapter(ModelsList)
+
+
+@models_router.get(
+    "/",
+    operation_id="list_models",
+    responses={200: {"model": ModelsList}},
+)
+async def list_models(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+) -> ModelsList:
+    """Gets a list of models"""
+    if base_models and len(base_models) > 0:
+        models_raw = []
+        for base_model in base_models:
+            models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
+    else:
+        models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
+    models = ModelsListValidator.validate_python({"models": models_raw})
+    return models
+
+
+@models_router.patch(
+    "/{base_model}/{model_type}/{model_name}",
+    operation_id="update_model",
+    responses={
+        200: {"description": "The model was updated successfully"},
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+    response_model=UpdateModelResponse,
+)
+async def update_model(
+    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:
+    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        previous_info = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        )
+
+        # rename operation requested
+        if info.model_name != model_name or info.base_model != base_model:
+            ApiDependencies.invoker.services.model_manager.rename_model(
+                base_model=base_model,
+                model_type=model_type,
+                model_name=model_name,
+                new_name=info.model_name,
+                new_base=info.base_model,
+            )
+            logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
+            # update information to support an update of attributes
+            model_name = info.model_name
+            base_model = info.base_model
+            new_info = ApiDependencies.invoker.services.model_manager.list_model(
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+            )
+            if new_info.get("path") != previous_info.get(
+                "path"
+            ):  # model manager moved model path during rename - don't overwrite it
+                info.path = new_info.get("path")
+
+        # replace empty string values with None/null to avoid phenomenon of vae: ''
+        info_dict = info.model_dump()
+        info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
+
+        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 = UpdateModelResponseValidator.validate_python(model_raw)
+    except ModelNotFoundException as 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))
+    except Exception as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=400, detail=str(e))
+
+    return model_response
+
+
+@models_router.post(
+    "/import",
+    operation_id="import_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        404: {"description": "The model could not be found"},
+        415: {"description": "Unrecognized file/folder format"},
+        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 checkpoints and rare SDv1 checkpoints",
+        default=None,
+    ),
+) -> ImportModelResponse:
+    """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
+
+    location = location.strip("\"' ")
+    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=415)
+
+        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 ImportModelResponseValidator.validate_python(model_raw)
+
+    except ModelNotFoundException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+
+
+@models_router.post(
+    "/add",
+    operation_id="add_model",
+    responses={
+        201: {"description": "The model added successfully"},
+        404: {"description": "The model could not be found"},
+        424: {"description": "The model appeared to add 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 add_model(
+    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
+) -> ImportModelResponse:
+    """Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
+
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        ApiDependencies.invoker.services.model_manager.add_model(
+            info.model_name,
+            info.base_model,
+            info.model_type,
+            model_attributes=info.model_dump(),
+        )
+        logger.info(f"Successfully added {info.model_name}")
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name=info.model_name,
+            base_model=info.base_model,
+            model_type=info.model_type,
+        )
+        return ImportModelResponseValidator.validate_python(model_raw)
+    except ModelNotFoundException 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(
+    "/{base_model}/{model_type}/{model_name}",
+    operation_id="del_model",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+    response_model=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"""
+    logger = ApiDependencies.invoker.services.logger
+
+    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 ModelNotFoundException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(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"),
+    convert_dest_directory: Optional[str] = Query(
+        default=None, description="Save the converted model to the designated directory"
+    ),
+) -> ConvertModelResponse:
+    """Convert a checkpoint model into a diffusers model, optionally saving to the indicated destination directory, or `models` if none."""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Converting model: {model_name}")
+        dest = pathlib.Path(convert_dest_directory) if convert_dest_directory else None
+        ApiDependencies.invoker.services.model_manager.convert_model(
+            model_name,
+            base_model=base_model,
+            model_type=model_type,
+            convert_dest_directory=dest,
+        )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name, base_model=base_model, model_type=model_type
+        )
+        response = ConvertModelResponseValidator.validate_python(model_raw)
+    except ModelNotFoundException as e:
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response
+
+
+@models_router.get(
+    "/search",
+    operation_id="search_for_models",
+    responses={
+        200: {"description": "Directory searched successfully"},
+        404: {"description": "Invalid directory path"},
+    },
+    status_code=200,
+    response_model=List[pathlib.Path],
+)
+async def search_for_models(
+    search_path: pathlib.Path = Query(description="Directory path to search for models"),
+) -> List[pathlib.Path]:
+    if not search_path.is_dir():
+        raise HTTPException(
+            status_code=404,
+            detail=f"The search path '{search_path}' does not exist or is not directory",
+        )
+    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
+
+
+@models_router.get(
+    "/ckpt_confs",
+    operation_id="list_ckpt_configs",
+    responses={
+        200: {"description": "paths retrieved successfully"},
+    },
+    status_code=200,
+    response_model=List[pathlib.Path],
+)
+async def list_ckpt_configs() -> List[pathlib.Path]:
+    """Return a list of the legacy checkpoint configuration files stored in `ROOT/configs/stable-diffusion`, relative to ROOT."""
+    return ApiDependencies.invoker.services.model_manager.list_checkpoint_configs()
+
+
+@models_router.post(
+    "/sync",
+    operation_id="sync_to_config",
+    responses={
+        201: {"description": "synchronization successful"},
+    },
+    status_code=201,
+    response_model=bool,
+)
+async def sync_to_config() -> bool:
+    """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
+    in-memory data structures with disk data structures."""
+    ApiDependencies.invoker.services.model_manager.sync_to_config()
+    return True
+
+
+# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
+# TODO: After a few updates, see if it works inside the route operation handler?
+class MergeModelsBody(BaseModel):
+    model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
+    merged_model_name: Optional[str] = Field(description="Name of destination model")
+    alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
+    interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
+    force: Optional[bool] = Field(
+        description="Force merging of models created with different versions of diffusers",
+        default=False,
+    )
+
+    merge_dest_directory: Optional[str] = Field(
+        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+        default=None,
+    )
+
+    model_config = ConfigDict(protected_namespaces=())
+
+
+@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(
+    body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
+    base_model: BaseModelType = Path(description="Base model"),
+) -> MergeModelResponse:
+    """Convert a checkpoint model into a diffusers model"""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(
+            f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
+        )
+        dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
+        result = ApiDependencies.invoker.services.model_manager.merge_models(
+            model_names=body.model_names,
+            base_model=base_model,
+            merged_model_name=body.merged_model_name or "+".join(body.model_names),
+            alpha=body.alpha,
+            interp=body.interp,
+            force=body.force,
+            merge_dest_directory=dest,
+        )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            result.name,
+            base_model=base_model,
+            model_type=ModelType.Main,
+        )
+        response = ConvertModelResponseValidator.validate_python(model_raw)
+    except ModelNotFoundException:
+        raise HTTPException(
+            status_code=404,
+            detail=f"One or more of the models '{body.model_names}' not found",
+        )
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response

invokeai/app/api/sockets.py

@@ -14,7 +14,7 @@ class SocketIO:
 
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
+        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
         app.mount("/ws", self.__app)
 
         self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)

invokeai/app/api_app.py

@@ -3,7 +3,6 @@
 # values from the command line or config file.
 import sys
 
-from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.version.invokeai_version import __version__
 
 from .services.config import InvokeAIAppConfig
@@ -28,7 +27,8 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     from fastapi.middleware.gzip import GZipMiddleware
     from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
     from fastapi.openapi.utils import get_openapi
-    from fastapi.responses import HTMLResponse
+    from fastapi.responses import FileResponse, HTMLResponse
+    from fastapi.staticfiles import StaticFiles
     from fastapi_events.handlers.local import local_handler
     from fastapi_events.middleware import EventHandlerASGIMiddleware
     from pydantic.json_schema import models_json_schema
@@ -47,7 +47,8 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         boards,
         download_queue,
         images,
-        model_manager,
+        model_records,
+        models,
         session_queue,
         sessions,
         utilities,
@@ -114,7 +115,8 @@ async def shutdown_event() -> None:
 app.include_router(sessions.session_router, prefix="/api")
 
 app.include_router(utilities.utilities_router, prefix="/api")
-app.include_router(model_manager.model_manager_router, prefix="/api")
+app.include_router(models.models_router, prefix="/api")
+app.include_router(model_records.model_records_router, prefix="/api")
 app.include_router(download_queue.download_queue_router, prefix="/api")
 app.include_router(images.images_router, prefix="/api")
 app.include_router(boards.boards_router, prefix="/api")
@@ -176,23 +178,21 @@ def custom_openapi() -> dict[str, Any]:
         invoker_schema["class"] = "invocation"
         openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
-    # This code no longer seems to be necessary?
-    # Leave it here just in case
-    #
-    # from invokeai.backend.model_manager import get_model_config_formats
-    # formats = get_model_config_formats()
-    # for model_config_name, enum_set in formats.items():
+    from invokeai.backend.model_management.models import get_model_config_enums
 
-    #     if model_config_name in openapi_schema["components"]["schemas"]:
-    #         # print(f"Config with name {name} already defined")
-    #         continue
+    for model_config_format_enum in set(get_model_config_enums()):
+        name = model_config_format_enum.__qualname__
 
-    #     openapi_schema["components"]["schemas"][model_config_name] = {
-    #         "title": model_config_name,
-    #         "description": "An enumeration.",
-    #         "type": "string",
-    #         "enum": [v.value for v in enum_set],
-    #     }
+        if name in openapi_schema["components"]["schemas"]:
+            # print(f"Config with name {name} already defined")
+            continue
+
+        openapi_schema["components"]["schemas"][name] = {
+            "title": name,
+            "description": "An enumeration.",
+            "type": "string",
+            "enum": [v.value for v in model_config_format_enum],
+        }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema
@@ -221,13 +221,19 @@ def overridden_redoc() -> HTMLResponse:
 
 web_root_path = Path(list(web_dir.__path__)[0])
 
-try:
-    app.mount("/", NoCacheStaticFiles(directory=Path(web_root_path, "dist"), html=True), name="ui")
-except RuntimeError:
-    logger.warn(f"No UI found at {web_root_path}/dist, skipping UI mount")
-app.mount(
-    "/static", NoCacheStaticFiles(directory=Path(web_root_path, "static/")), name="static"
-)  # docs favicon is in here
+# Only serve the UI if we it has a build
+if (web_root_path / "dist").exists():
+    # Cannot add headers to StaticFiles, so we must serve index.html with a custom route
+    # Add cache-control: no-store header to prevent caching of index.html, which leads to broken UIs at release
+    @app.get("/", include_in_schema=False, name="ui_root")
+    def get_index() -> FileResponse:
+        return FileResponse(Path(web_root_path, "dist/index.html"), headers={"Cache-Control": "no-store"})
+
+    # Must mount *after* the other routes else it borks em
+    app.mount("/assets", StaticFiles(directory=Path(web_root_path, "dist/assets/")), name="assets")
+    app.mount("/locales", StaticFiles(directory=Path(web_root_path, "dist/locales/")), name="locales")
+
+app.mount("/static", StaticFiles(directory=Path(web_root_path, "static/")), name="static")  # docs favicon is in here
 
 
 def invoke_api() -> None:

invokeai/app/invocations/compel.py

@@ -1,27 +1,22 @@
 from dataclasses import dataclass
-from typing import Iterator, List, Optional, Tuple, Union
+from typing import List, Optional, Union
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
-from transformers import CLIPTokenizer
 
-import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.services.model_records import UnknownModelException
 from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.app.util.ti_utils import extract_ti_triggers_from_prompt
-from invokeai.backend.lora import LoRAModelRaw
-from invokeai.backend.model_manager import ModelType
-from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
-from invokeai.backend.textual_inversion import TextualInversionModelRaw
-from invokeai.backend.util.devices import torch_dtype
 
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.model_management.models import ModelNotFoundException, ModelType
+from ...backend.util.devices import torch_dtype
+from ..util.ti_utils import extract_ti_triggers_from_prompt
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -71,22 +66,21 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.load_model_by_key(
+        tokenizer_info = context.services.model_manager.get_model(
             **self.clip.tokenizer.model_dump(),
             context=context,
         )
-        text_encoder_info = context.services.model_manager.load_model_by_key(
+        text_encoder_info = context.services.model_manager.get_model(
             **self.clip.text_encoder.model_dump(),
             context=context,
         )
 
-        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
+        def _lora_loader():
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.load_model_by_key(
+                lora_info = context.services.model_manager.get_model(
                     **lora.model_dump(exclude={"weight"}), context=context
                 )
-                assert isinstance(lora_info.model, LoRAModelRaw)
-                yield (lora_info.model, lora.weight)
+                yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
@@ -96,20 +90,25 @@ class CompelInvocation(BaseInvocation):
         for trigger in extract_ti_triggers_from_prompt(self.prompt):
             name = trigger[1:-1]
             try:
-                loaded_model = context.services.model_manager.load_model_by_key(
-                    **self.clip.text_encoder.model_dump(),
-                    context=context,
-                ).model
-                assert isinstance(loaded_model, TextualInversionModelRaw)
-                ti_list.append((name, loaded_model))
-            except UnknownModelException:
+                ti_list.append(
+                    (
+                        name,
+                        context.services.model_manager.get_model(
+                            model_name=name,
+                            base_model=self.clip.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                            context=context,
+                        ).context.model,
+                    )
+                )
+            except ModelNotFoundException:
                 # print(e)
                 # import traceback
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.model, text_encoder_info.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -117,7 +116,7 @@ class CompelInvocation(BaseInvocation):
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
         ):
             compel = Compel(
                 tokenizer=tokenizer,
@@ -151,7 +150,7 @@ class CompelInvocation(BaseInvocation):
         )
 
         conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)  # TODO: fix type mismatch here
+        context.services.latents.save(conditioning_name, conditioning_data)
 
         return ConditioningOutput(
             conditioning=ConditioningField(
@@ -161,8 +160,6 @@ class CompelInvocation(BaseInvocation):
 
 
 class SDXLPromptInvocationBase:
-    """Prompt processor for SDXL models."""
-
     def run_clip_compel(
         self,
         context: InvocationContext,
@@ -171,27 +168,26 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
-        tokenizer_info = context.services.model_manager.load_model_by_key(
+    ):
+        tokenizer_info = context.services.model_manager.get_model(
             **clip_field.tokenizer.model_dump(),
             context=context,
         )
-        text_encoder_info = context.services.model_manager.load_model_by_key(
+        text_encoder_info = context.services.model_manager.get_model(
             **clip_field.text_encoder.model_dump(),
             context=context,
         )
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.model
-            assert isinstance(cpu_text_encoder, torch.nn.Module)
+            cpu_text_encoder = text_encoder_info.context.model
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=cpu_text_encoder.dtype,
+                dtype=text_encoder_info.context.cache.precision,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -202,14 +198,12 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
+        def _lora_loader():
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.load_model_by_key(
+                lora_info = context.services.model_manager.get_model(
                     **lora.model_dump(exclude={"weight"}), context=context
                 )
-                lora_model = lora_info.model
-                assert isinstance(lora_model, LoRAModelRaw)
-                yield (lora_model, lora.weight)
+                yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
@@ -219,24 +213,25 @@ class SDXLPromptInvocationBase:
         for trigger in extract_ti_triggers_from_prompt(prompt):
             name = trigger[1:-1]
             try:
-                ti_model = context.services.model_manager.load_model_by_attr(
-                    model_name=name,
-                    base_model=text_encoder_info.config.base,
-                    model_type=ModelType.TextualInversion,
-                    context=context,
-                ).model
-                assert isinstance(ti_model, TextualInversionModelRaw)
-                ti_list.append((name, ti_model))
-            except UnknownModelException:
+                ti_list.append(
+                    (
+                        name,
+                        context.services.model_manager.get_model(
+                            model_name=name,
+                            base_model=clip_field.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                            context=context,
+                        ).context.model,
+                    )
+                )
+            except ModelNotFoundException:
                 # print(e)
                 # import traceback
                 # print(traceback.format_exc())
-                logger.warning(f'trigger: "{trigger}" not found')
-            except ValueError:
-                logger.warning(f'trigger: "{trigger}" more than one similarly-named textual inversion models')
+                print(f'Warn: trigger: "{trigger}" not found')
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.model, text_encoder_info.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -244,7 +239,7 @@ class SDXLPromptInvocationBase:
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
         ):
             compel = Compel(
                 tokenizer=tokenizer,
@@ -362,7 +357,6 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
-        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -416,7 +410,6 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
-        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -466,9 +459,9 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-    tokenizer: CLIPTokenizer,
+    tokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long: bool = False,
+    truncate_if_too_long=False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -480,9 +473,7 @@ def get_max_token_count(
         return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(
-    tokenizer: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
-) -> List[str]:
+def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> 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")
 
@@ -495,29 +486,24 @@ def get_tokens_for_prompt_object(
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens: List[str] = tokenizer.tokenize(text)
+    tokens = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(
-    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
-) -> None:
+def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
-            assert display_label_prefix is not None
             this_display_label_prefix = display_label_prefix
         log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(
-    p: Union[Blend, FlattenedPrompt], tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
-) -> None:
+def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -557,12 +543,7 @@ def log_tokenization_for_prompt_object(
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(
-    text: str,
-    tokenizer: CLIPTokenizer,
-    display_label: Optional[str] = None,
-    truncate_if_too_long: Optional[bool] = False,
-) -> None:
+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

@@ -24,14 +24,14 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, Field, field_validator, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
 
+from ...backend.model_management import BaseModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -56,7 +56,10 @@ CONTROLNET_RESIZE_VALUES = Literal[
 class ControlNetModelField(BaseModel):
     """ControlNet model field"""
 
-    key: str = Field(description="Model config record key for the ControlNet model")
+    model_name: str = Field(description="Name of the ControlNet model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class ControlField(BaseModel):
@@ -599,33 +602,3 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
         color_map = cv2.resize(color_map, (width, height), interpolation=cv2.INTER_NEAREST)
         color_map = Image.fromarray(color_map)
         return color_map
-
-
-DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
-
-
-@invocation(
-    "depth_anything_image_processor",
-    title="Depth Anything Processor",
-    tags=["controlnet", "depth", "depth anything"],
-    category="controlnet",
-    version="1.0.0",
-)
-class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
-    """Generates a depth map based on the Depth Anything algorithm"""
-
-    model_size: DEPTH_ANYTHING_MODEL_SIZES = InputField(
-        default="small", description="The size of the depth model to use"
-    )
-    resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
-    offload: bool = InputField(default=False)
-
-    def run_processor(self, image):
-        depth_anything_detector = DepthAnythingDetector()
-        depth_anything_detector.load_model(model_size=self.model_size)
-
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
-
-        processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
-        return processed_image

invokeai/app/invocations/ip_adapter.py

@@ -1,8 +1,8 @@
+import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, Field, field_validator, model_validator
-from typing_extensions import Self
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -17,16 +17,22 @@ from invokeai.app.invocations.baseinvocation import (
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_manager import BaseModelType, ModelType
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType
+from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
 
 
-# LS: Consider moving these two classes into model.py
 class IPAdapterModelField(BaseModel):
-    key: str = Field(description="Key to the IP-Adapter model")
+    model_name: str = Field(description="Name of the IP-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class CLIPVisionModelField(BaseModel):
-    key: str = Field(description="Key to the CLIP Vision image encoder model")
+    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
+    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class IPAdapterField(BaseModel):
@@ -43,12 +49,12 @@ class IPAdapterField(BaseModel):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v: float) -> float:
+    def validate_ip_adapter_weight(cls, v):
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self) -> Self:
+    def validate_begin_end_step_percent(self):
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
@@ -81,25 +87,33 @@ class IPAdapterInvocation(BaseInvocation):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v: float) -> float:
+    def validate_ip_adapter_weight(cls, v):
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self) -> Self:
+    def validate_begin_end_step_percent(self):
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.store.get_model(self.ip_adapter_model.key)
-        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
-        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_models = context.services.model_manager.store.search_by_attr(
-            model_name=image_encoder_model_name, base_model=BaseModelType.Any, model_type=ModelType.CLIPVision
+        ip_adapter_info = context.services.model_manager.model_info(
+            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
+        )
+        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
+        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
+        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
+        # is currently messy due to differences between how the model info is generated when installing a model from
+        # disk vs. downloading the model.
+        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
+            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
+        )
+        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
+        image_encoder_model = CLIPVisionModelField(
+            model_name=image_encoder_model_name,
+            base_model=BaseModelType.Any,
         )
-        assert len(image_encoder_models) == 1
-        image_encoder_model = CLIPVisionModelField(key=image_encoder_models[0].key)
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,

invokeai/app/invocations/latent.py

@@ -1,17 +1,14 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
+from typing import List, Literal, Optional, Union
 
 import einops
 import numpy as np
-import numpy.typing as npt
 import torch
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
-from diffusers.configuration_utils import ConfigMixin
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.models.adapter import T2IAdapter
 from diffusers.models.attention_processor import (
@@ -20,10 +17,8 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
-from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 from diffusers.schedulers import DPMSolverSDEScheduler
 from diffusers.schedulers import SchedulerMixin as Scheduler
-from PIL import Image
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
 
@@ -43,13 +38,13 @@ from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-from invokeai.backend.lora import LoRAModelRaw
-from invokeai.backend.model_manager import BaseModelType, LoadedModel
-from invokeai.backend.model_patcher import ModelPatcher
-from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
+from invokeai.backend.model_management.models import ModelType, SilenceWarnings
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
-from invokeai.backend.util.silence_warnings import SilenceWarnings
 
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.model_management.models import BaseModelType
+from ...backend.model_management.seamless import set_seamless
+from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     IPAdapterData,
@@ -81,9 +76,7 @@ if choose_torch_device() == torch.device("mps"):
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-SAMPLER_NAME_VALUES = Literal[
-    tuple(SCHEDULER_MAP.keys())
-]  # FIXME: "Invalid type alias". This defeats static type checking.
+SAMPLER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
 
 # HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
 # be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
@@ -137,10 +130,10 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         ui_order=4,
     )
 
-    def prep_mask_tensor(self, mask_image: Image) -> torch.Tensor:
+    def prep_mask_tensor(self, mask_image):
         if mask_image.mode != "L":
             mask_image = mask_image.convert("L")
-        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
         if mask_tensor.dim() == 3:
             mask_tensor = mask_tensor.unsqueeze(0)
         # if shape is not None:
@@ -151,24 +144,24 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
             image = context.services.images.get_pil_image(self.image.image_name)
-            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image_tensor.dim() == 3:
-                image_tensor = image_tensor.unsqueeze(0)
+            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image.dim() == 3:
+                image = image.unsqueeze(0)
         else:
-            image_tensor = None
+            image = None
 
         mask = self.prep_mask_tensor(
             context.services.images.get_pil_image(self.mask.image_name),
         )
 
-        if image_tensor is not None:
-            vae_info = context.services.model_manager.load_model_by_key(
+        if image is not None:
+            vae_info = context.services.model_manager.get_model(
                 **self.vae.vae.model_dump(),
                 context=context,
             )
 
-            img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-            masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+            img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+            masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
@@ -195,7 +188,7 @@ def get_scheduler(
     seed: int,
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.services.model_manager.load_model_by_key(
+    orig_scheduler_info = context.services.model_manager.get_model(
         **scheduler_info.model_dump(),
         context=context,
     )
@@ -206,7 +199,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,  # FIXME
+        **scheduler_extra_config,
         "_backup": scheduler_config,
     }
 
@@ -219,7 +212,6 @@ def get_scheduler(
     # hack copied over from generate.py
     if not hasattr(scheduler, "uses_inpainting_model"):
         scheduler.uses_inpainting_model = lambda: False
-    assert isinstance(scheduler, Scheduler)
     return scheduler
 
 
@@ -303,7 +295,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
 
     @field_validator("cfg_scale")
-    def ge_one(cls, v: Union[List[float], float]) -> Union[List[float], float]:
+    def ge_one(cls, v):
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
             for i in v:
@@ -333,9 +325,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler: Scheduler,
-        unet: UNet2DConditionModel,
-        seed: int,
+        scheduler,
+        unet,
+        seed,
     ) -> ConditioningData:
         positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
         c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
@@ -358,7 +350,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             ),
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
             scheduler,
             # for ddim scheduler
             eta=0.0,  # ddim_eta
@@ -370,8 +362,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     def create_pipeline(
         self,
-        unet: UNet2DConditionModel,
-        scheduler: Scheduler,
+        unet,
+        scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -382,10 +374,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         class FakeVae:
             class FakeVaeConfig:
-                def __init__(self) -> None:
+                def __init__(self):
                     self.block_out_channels = [0]
 
-            def __init__(self) -> None:
+            def __init__(self):
                 self.config = FakeVae.FakeVaeConfig()
 
         return StableDiffusionGeneratorPipeline(
@@ -402,11 +394,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        control_input: Optional[Union[ControlField, List[ControlField]]],
+        control_input: Union[ControlField, List[ControlField]],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
-    ) -> Optional[List[ControlNetData]]:
+    ) -> List[ControlNetData]:
         # Assuming fixed dimensional scaling of LATENT_SCALE_FACTOR.
         control_height_resize = latents_shape[2] * LATENT_SCALE_FACTOR
         control_width_resize = latents_shape[3] * LATENT_SCALE_FACTOR
@@ -429,8 +421,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
         controlnet_data = []
         for control_info in control_list:
             control_model = exit_stack.enter_context(
-                context.services.model_manager.load_model_by_key(
-                    key=control_info.control_model.key,
+                context.services.model_manager.get_model(
+                    model_name=control_info.control_model.model_name,
+                    model_type=ModelType.ControlNet,
+                    base_model=control_info.control_model.base_model,
                     context=context,
                 )
             )
@@ -495,25 +489,27 @@ class DenoiseLatentsInvocation(BaseInvocation):
         conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-                context.services.model_manager.load_model_by_key(
-                    key=single_ip_adapter.ip_adapter_model.key,
+                context.services.model_manager.get_model(
+                    model_name=single_ip_adapter.ip_adapter_model.model_name,
+                    model_type=ModelType.IPAdapter,
+                    base_model=single_ip_adapter.ip_adapter_model.base_model,
                     context=context,
                 )
             )
 
-            image_encoder_model_info = context.services.model_manager.load_model_by_key(
-                key=single_ip_adapter.image_encoder_model.key,
+            image_encoder_model_info = context.services.model_manager.get_model(
+                model_name=single_ip_adapter.image_encoder_model.model_name,
+                model_type=ModelType.CLIPVision,
+                base_model=single_ip_adapter.image_encoder_model.base_model,
                 context=context,
             )
 
             # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
-            single_ipa_image_fields = single_ip_adapter.image
-            if not isinstance(single_ipa_image_fields, list):
-                single_ipa_image_fields = [single_ipa_image_fields]
+            single_ipa_images = single_ip_adapter.image
+            if not isinstance(single_ipa_images, list):
+                single_ipa_images = [single_ipa_images]
 
-            single_ipa_images = [
-                context.services.images.get_pil_image(image.image_name) for image in single_ipa_image_fields
-            ]
+            single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
 
             # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
             # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
@@ -557,19 +553,23 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.load_model_by_key(
-                key=t2i_adapter_field.t2i_adapter_model.key,
+            t2i_adapter_model_info = context.services.model_manager.get_model(
+                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
+                model_type=ModelType.T2IAdapter,
+                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
                 context=context,
             )
             image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
-            if t2i_adapter_model_info.base == BaseModelType.StableDiffusion1:
+            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
-            elif t2i_adapter_model_info.base == BaseModelType.StableDiffusionXL:
+            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
             else:
-                raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_info.base}'.")
+                raise ValueError(
+                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
+                )
 
             t2i_adapter_model: T2IAdapter
             with t2i_adapter_model_info as t2i_adapter_model:
@@ -592,7 +592,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     do_classifier_free_guidance=False,
                     width=t2i_input_width,
                     height=t2i_input_height,
-                    num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
+                    num_channels=t2i_adapter_model.config.in_channels,
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
@@ -617,15 +617,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
-    def init_scheduler(
-        self,
-        scheduler: Union[Scheduler, ConfigMixin],
-        device: torch.device,
-        steps: int,
-        denoising_start: float,
-        denoising_end: float,
-    ) -> Tuple[int, List[int], int]:
-        assert isinstance(scheduler, ConfigMixin)
+    def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
@@ -637,11 +629,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         _timesteps = timesteps[:: scheduler.order]
 
         # get start timestep index
-        t_start_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_start)))
+        t_start_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_start)))
         t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, _timesteps)))
 
         # get end timestep index
-        t_end_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_end)))
+        t_end_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_end)))
         t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, _timesteps[t_start_idx:])))
 
         # apply order to indexes
@@ -654,9 +646,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(
-        self, context: InvocationContext, latents: torch.Tensor
-    ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor]]:
+    def prep_inpaint_mask(self, context, latents):
         if self.denoise_mask is None:
             return None, None
 
@@ -709,36 +699,31 @@ class DenoiseLatentsInvocation(BaseInvocation):
             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]
 
-            # get the unet's config so that we can pass the base to dispatch_progress()
-            unet_config = context.services.model_manager.store.get_model(self.unet.unet.key)
+            def step_callback(state: PipelineIntermediateState):
+                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
 
-            def step_callback(state: PipelineIntermediateState) -> None:
-                self.dispatch_progress(context, source_node_id, state, unet_config.base)
-
-            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
+            def _lora_loader():
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.load_model_by_key(
+                    lora_info = context.services.model_manager.get_model(
                         **lora.model_dump(exclude={"weight"}),
                         context=context,
                     )
-                    yield (lora_info.model, lora.weight)
+                    yield (lora_info.context.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.services.model_manager.load_model_by_key(
+            unet_info = context.services.model_manager.get_model(
                 **self.unet.unet.model_dump(),
                 context=context,
             )
-            assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 ExitStack() as exit_stack,
-                ModelPatcher.apply_freeu(unet_info.model, self.unet.freeu_config),
-                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
+                ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
+                set_seamless(unet_info.context.model, self.unet.seamless_axes),
                 unet_info as unet,
                 # Apply the LoRA after unet has been moved to its target device for faster patching.
                 ModelPatcher.apply_lora_unet(unet, _lora_loader()),
             ):
-                assert isinstance(unet, UNet2DConditionModel)
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
@@ -836,13 +821,12 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.load_model_by_key(
+        vae_info = context.services.model_manager.get_model(
             **self.vae.vae.model_dump(),
             context=context,
         )
 
-        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
-            assert isinstance(vae, torch.nn.Module)
+        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
@@ -1031,9 +1015,8 @@ class ImageToLatentsInvocation(BaseInvocation):
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
     @staticmethod
-    def vae_encode(vae_info: LoadedModel, upcast: bool, tiled: bool, image_tensor: torch.Tensor) -> torch.Tensor:
+    def vae_encode(vae_info, upcast, tiled, image_tensor):
         with vae_info as vae:
-            assert isinstance(vae, torch.nn.Module)
             orig_dtype = vae.dtype
             if upcast:
                 vae.to(dtype=torch.float32)
@@ -1079,7 +1062,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
-        vae_info = context.services.model_manager.load_model_by_key(
+        vae_info = context.services.model_manager.get_model(
             **self.vae.vae.model_dump(),
             context=context,
         )
@@ -1098,19 +1081,14 @@ class ImageToLatentsInvocation(BaseInvocation):
     @singledispatchmethod
     @staticmethod
     def _encode_to_tensor(vae: AutoencoderKL, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
-        assert isinstance(vae, torch.nn.Module)
         image_tensor_dist = vae.encode(image_tensor).latent_dist
-        latents: torch.Tensor = image_tensor_dist.sample().to(
-            dtype=vae.dtype
-        )  # FIXME: uses torch.randn. make reproducible!
+        latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
         return latents
 
     @_encode_to_tensor.register
     @staticmethod
     def _(vae: AutoencoderTiny, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
-        assert isinstance(vae, torch.nn.Module)
-        latents: torch.FloatTensor = vae.encode(image_tensor).latents
-        return latents
+        return vae.encode(image_tensor).latents
 
 
 @invocation(
@@ -1143,12 +1121,7 @@ class BlendLatentsInvocation(BaseInvocation):
         # TODO:
         device = choose_torch_device()
 
-        def slerp(
-            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
-            v0: Union[torch.Tensor, npt.NDArray[Any]],
-            v1: Union[torch.Tensor, npt.NDArray[Any]],
-            DOT_THRESHOLD: float = 0.9995,
-        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
+        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
             """
             Spherical linear interpolation
             Args:
@@ -1181,16 +1154,12 @@ class BlendLatentsInvocation(BaseInvocation):
                 v2 = s0 * v0 + s1 * v1
 
             if inputs_are_torch:
-                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
-                return v2_torch
-            else:
-                assert isinstance(v2, np.ndarray)
-                return v2
+                v2 = torch.from_numpy(v2).to(device)
+
+            return v2
 
         # blend
-        bl = slerp(self.alpha, latents_a, latents_b)
-        assert isinstance(bl, torch.Tensor)
-        blended_latents: torch.Tensor = bl  # for type checking convenience
+        blended_latents = slerp(self.alpha, latents_a, latents_b)
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
@@ -1259,61 +1228,3 @@ class CropLatentsCoreInvocation(BaseInvocation):
         context.services.latents.save(name, cropped_latents)
 
         return build_latents_output(latents_name=name, latents=cropped_latents)
-
-
-@invocation_output("ideal_size_output")
-class IdealSizeOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    width: int = OutputField(description="The ideal width of the image (in pixels)")
-    height: int = OutputField(description="The ideal height of the image (in pixels)")
-
-
-@invocation(
-    "ideal_size",
-    title="Ideal Size",
-    tags=["latents", "math", "ideal_size"],
-    version="1.0.2",
-)
-class IdealSizeInvocation(BaseInvocation):
-    """Calculates the ideal size for generation to avoid duplication"""
-
-    width: int = InputField(default=1024, description="Final image width")
-    height: int = InputField(default=576, description="Final image height")
-    unet: UNetField = InputField(default=None, description=FieldDescriptions.unet)
-    multiplier: float = InputField(
-        default=1.0,
-        description="Amount to multiply the model's dimensions by when calculating the ideal size (may result in initial generation artifacts if too large)",
-    )
-
-    def trim_to_multiple_of(self, *args: int, multiple_of: int = LATENT_SCALE_FACTOR) -> Tuple[int, ...]:
-        return tuple((x - x % multiple_of) for x in args)
-
-    def invoke(self, context: InvocationContext) -> IdealSizeOutput:
-        unet_config = context.services.model_manager.load_model_by_key(
-            **self.unet.unet.model_dump(),
-            context=context,
-        )
-        aspect = self.width / self.height
-        dimension: float = 512
-        if unet_config.base == BaseModelType.StableDiffusion2:
-            dimension = 768
-        elif unet_config.base == BaseModelType.StableDiffusionXL:
-            dimension = 1024
-        dimension = dimension * self.multiplier
-        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 = self.trim_to_multiple_of(
-            math.floor(init_width),
-            math.floor(init_height),
-        )
-
-        return IdealSizeOutput(width=scaled_width, height=scaled_height)

invokeai/app/invocations/model.py

@@ -1,12 +1,12 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.app.shared.models import FreeUConfig
 
-from ...backend.model_manager import SubModelType
+from ...backend.model_management import BaseModelType, ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -20,8 +20,12 @@ from .baseinvocation import (
 
 
 class ModelInfo(BaseModel):
-    key: str = Field(description="Key of model as returned by ModelRecordServiceBase.get_model()")
-    submodel_type: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
+    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")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class LoraInfo(ModelInfo):
@@ -51,7 +55,7 @@ class VaeField(BaseModel):
 
 @invocation_output("unet_output")
 class UNetOutput(BaseInvocationOutput):
-    """Base class for invocations that output a UNet field."""
+    """Base class for invocations that output a UNet field"""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
 
@@ -80,13 +84,20 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
 class MainModelField(BaseModel):
     """Main model field"""
 
-    key: str = Field(description="Model key")
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+    model_type: ModelType = Field(description="Model Type")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class LoRAModelField(BaseModel):
     """LoRA model field"""
 
-    key: str = Field(description="LoRA model key")
+    model_name: str = Field(description="Name of the LoRA model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 @invocation(
@@ -103,40 +114,85 @@ class MainModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-        key = self.model.key
+        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.store.exists(key):
-            raise Exception(f"Unknown model {key}")
+        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(
-                    key=key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Tokenizer,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.TextEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )
@@ -173,16 +229,21 @@ class LoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        lora_key = self.lora.key
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
 
-        if not context.services.model_manager.store.exists(lora_key):
-            raise Exception(f"Unkown lora: {lora_key}!")
+        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.key == lora_key for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_key}" already applied to unet')
+        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.key == lora_key for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_key}" already applied to clip')
+        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()
 
@@ -190,8 +251,10 @@ class LoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -200,8 +263,10 @@ class LoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -253,19 +318,24 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         if self.lora is None:
             raise Exception("No LoRA provided")
 
-        lora_key = self.lora.key
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
 
-        if not context.services.model_manager.store.exists(lora_key):
-            raise Exception(f"Unknown lora: {lora_key}!")
+        if not context.services.model_manager.model_exists(
+            base_model=base_model,
+            model_name=lora_name,
+            model_type=ModelType.Lora,
+        ):
+            raise Exception(f"Unknown lora name: {lora_name}!")
 
-        if self.unet is not None and any(lora.key == lora_key for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_key}" already applied to unet')
+        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.key == lora_key for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_key}" already applied to clip')
+        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')
 
-        if self.clip2 is not None and any(lora.key == lora_key for lora in self.clip2.loras):
-            raise Exception(f'Lora "{lora_key}" already applied to clip2')
+        if self.clip2 is not None and any(lora.model_name == lora_name for lora in self.clip2.loras):
+            raise Exception(f'Lora "{lora_name}" already applied to clip2')
 
         output = SDXLLoraLoaderOutput()
 
@@ -273,8 +343,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.unet = copy.deepcopy(self.unet)
             output.unet.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -283,8 +355,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip = copy.deepcopy(self.clip)
             output.clip.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -293,8 +367,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
             output.clip2 = copy.deepcopy(self.clip2)
             output.clip2.loras.append(
                 LoraInfo(
-                    key=lora_key,
-                    submodel_type=None,
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
                     weight=self.weight,
                 )
             )
@@ -305,7 +381,10 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
 class VAEModelField(BaseModel):
     """Vae model field"""
 
-    key: str = Field(description="Model's key")
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 @invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
@@ -319,12 +398,25 @@ class VaeLoaderInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:
-        key = self.vae_model.key
+        base_model = self.vae_model.base_model
+        model_name = self.vae_model.model_name
+        model_type = ModelType.Vae
 
-        if not context.services.model_manager.store.exists(key):
-            raise Exception(f"Unkown vae: {key}!")
-
-        return VAEOutput(vae=VaeField(vae=ModelInfo(key=key)))
+        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 VAEOutput(
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                )
+            )
+        )
 
 
 @invocation_output("seamless_output")

invokeai/app/invocations/onnx.py

@@ -8,16 +8,16 @@ from typing import List, Literal, Union
 import numpy as np
 import torch
 from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator
 from tqdm import tqdm
 
 from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
 from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend.model_manager import ModelType, SubModelType
-from invokeai.backend.model_patcher import ONNXModelPatcher
+from invokeai.backend import BaseModelType, ModelType, SubModelType
 
+from ...backend.model_management import ONNXModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.util import choose_torch_device
 from ..util.ti_utils import extract_ti_triggers_from_prompt
@@ -62,16 +62,16 @@ class ONNXPromptInvocation(BaseInvocation):
     clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.load_model_by_key(
+        tokenizer_info = context.services.model_manager.get_model(
             **self.clip.tokenizer.model_dump(),
         )
-        text_encoder_info = context.services.model_manager.load_model_by_key(
+        text_encoder_info = context.services.model_manager.get_model(
             **self.clip.text_encoder.model_dump(),
         )
         with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
             loras = [
                 (
-                    context.services.model_manager.load_model_by_key(**lora.model_dump(exclude={"weight"})).model,
+                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
                     lora.weight,
                 )
                 for lora in self.clip.loras
@@ -84,11 +84,11 @@ class ONNXPromptInvocation(BaseInvocation):
                     ti_list.append(
                         (
                             name,
-                            context.services.model_manager.load_model_by_attr(
+                            context.services.model_manager.get_model(
                                 model_name=name,
-                                base_model=text_encoder_info.config.base,
+                                base_model=self.clip.text_encoder.base_model,
                                 model_type=ModelType.TextualInversion,
-                            ).model,
+                            ).context.model,
                         )
                     )
                 except Exception:
@@ -257,13 +257,13 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
                 eta=0.0,
             )
 
-        unet_info = context.services.model_manager.load_model_by_key(**self.unet.unet.model_dump())
+        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
 
         with unet_info as unet:  # , 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]
             loras = [
                 (
-                    context.services.model_manager.load_model_by_key(**lora.model_dump(exclude={"weight"})).model,
+                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
                     lora.weight,
                 )
                 for lora in self.unet.loras
@@ -344,9 +344,9 @@ class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata):
         latents = context.services.latents.get(self.latents.latents_name)
 
         if self.vae.vae.submodel != SubModelType.VaeDecoder:
-            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.submodel}")
+            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
 
-        vae_info = context.services.model_manager.load_model_by_key(
+        vae_info = context.services.model_manager.get_model(
             **self.vae.vae.model_dump(),
         )
 
@@ -400,7 +400,11 @@ class ONNXModelLoaderOutput(BaseInvocationOutput):
 class OnnxModelField(BaseModel):
     """Onnx model field"""
 
-    key: str = Field(description="Model ID")
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+    model_type: ModelType = Field(description="Model Type")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 @invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
@@ -412,46 +416,93 @@ class OnnxModelLoaderInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
-        model_key = self.model.key
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.ONNX
 
         # TODO: not found exceptions
-        if not context.services.model_manager.store.exists(model_key):
-            raise Exception(f"Unknown model: {model_key}")
+        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 ONNXModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae_decoder=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.VaeDecoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.VaeDecoder,
                 ),
             ),
             vae_encoder=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.VaeEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.VaeEncoder,
                 ),
             ),
         )

invokeai/app/invocations/primitives.py

@@ -368,7 +368,7 @@ class LatentsCollectionInvocation(BaseInvocation):
         return LatentsCollectionOutput(collection=self.collection)
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None) -> LatentsOutput:
+def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None):
     return LatentsOutput(
         latents=LatentsField(latents_name=latents_name, seed=seed),
         width=latents.size()[3] * 8,

invokeai/app/invocations/sdxl.py

@@ -1,6 +1,6 @@
 from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.model_manager import SubModelType
 
+from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -44,52 +44,72 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLModelLoaderOutput:
-        model_key = self.model.key
+        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.store.exists(model_key):
-            raise Exception(f"Unknown model: {model_key}")
+        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}")
 
         return SDXLModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )
@@ -113,40 +133,56 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLRefinerModelLoaderOutput:
-        model_key = self.model.key
+        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.store.exists(model_key):
-            raise Exception(f"Unknown model: {model_key}")
+        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}")
 
         return SDXLRefinerModelLoaderOutput(
             unet=UNetField(
                 unet=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.UNet,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
                 ),
                 scheduler=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Scheduler,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
                 ),
                 loras=[],
             ),
             clip2=ClipField(
                 tokenizer=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Tokenizer2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
                 ),
                 text_encoder=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.TextEncoder2,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
                 ),
                 loras=[],
                 skipped_layers=0,
             ),
             vae=VaeField(
                 vae=ModelInfo(
-                    key=model_key,
-                    submodel_type=SubModelType.Vae,
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
                 ),
             ),
         )

invokeai/app/invocations/t2i_adapter.py

@@ -1,6 +1,6 @@
 from typing import Union
 
-from pydantic import BaseModel, Field, field_validator, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -16,10 +16,14 @@ from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESI
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.backend.model_management.models.base import BaseModelType
 
 
 class T2IAdapterModelField(BaseModel):
-    key: str = Field(description="Model record key for the T2I-Adapter model")
+    model_name: str = Field(description="Name of the T2I-Adapter model")
+    base_model: BaseModelType = Field(description="Base model")
+
+    model_config = ConfigDict(protected_namespaces=())
 
 
 class T2IAdapterField(BaseModel):

invokeai/app/invocations/upscale.py

@@ -5,12 +5,12 @@ from typing import Literal
 import cv2
 import numpy as np
 import torch
+from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
 from pydantic import ConfigDict
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.image_util.realesrgan.realesrgan import RealESRGAN
 from invokeai.backend.util.devices import choose_torch_device
 

invokeai/app/services/config/config_base.py

@@ -27,11 +27,11 @@ class InvokeAISettings(BaseSettings):
     """Runtime configuration settings in which default values are read from an omegaconf .yaml file."""
 
     initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict[str, Any]] = {}
+    argparse_groups: ClassVar[Dict] = {}
 
     model_config = SettingsConfigDict(env_file_encoding="utf-8", arbitrary_types_allowed=True, case_sensitive=True)
 
-    def parse_args(self, argv: Optional[List[str]] = sys.argv[1:]) -> None:
+    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
         """Call to parse command-line arguments."""
         parser = self.get_parser()
         opt, unknown_opts = parser.parse_known_args(argv)
@@ -68,7 +68,7 @@ class InvokeAISettings(BaseSettings):
         return OmegaConf.to_yaml(conf)
 
     @classmethod
-    def add_parser_arguments(cls, parser: ArgumentParser) -> None:
+    def add_parser_arguments(cls, parser):
         """Dynamically create arguments for a settings parser."""
         if "type" in get_type_hints(cls):
             settings_stanza = get_args(get_type_hints(cls)["type"])[0]
@@ -117,8 +117,7 @@ class InvokeAISettings(BaseSettings):
         """Return the category of a setting."""
         hints = get_type_hints(cls)
         if command_field in hints:
-            result: str = get_args(hints[command_field])[0]
-            return result
+            return get_args(hints[command_field])[0]
         else:
             return "Uncategorized"
 
@@ -159,7 +158,7 @@ class InvokeAISettings(BaseSettings):
         ]
 
     @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None) -> None:
+    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
         """Add the argparse arguments for a setting parser."""
         field_type = get_type_hints(cls).get(name)
         default = (

invokeai/app/services/config/config_common.py

@@ -21,7 +21,7 @@ class PagingArgumentParser(argparse.ArgumentParser):
     It also supports reading defaults from an init file.
     """
 
-    def print_help(self, file=None) -> None:
+    def print_help(self, file=None):
         text = self.format_help()
         pydoc.pager(text)
 

invokeai/app/services/config/config_default.py

@@ -173,10 +173,10 @@ from __future__ import annotations
 
 import os
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional
+from typing import Any, ClassVar, Dict, List, Literal, Optional, Union, get_type_hints
 
 from omegaconf import DictConfig, OmegaConf
-from pydantic import Field
+from pydantic import Field, TypeAdapter
 from pydantic.config import JsonDict
 from pydantic_settings import SettingsConfigDict
 
@@ -185,9 +185,7 @@ from .config_base import InvokeAISettings
 INIT_FILE = Path("invokeai.yaml")
 DB_FILE = Path("invokeai.db")
 LEGACY_INIT_FILE = Path("invokeai.init")
-DEFAULT_RAM_CACHE = 10.0
-DEFAULT_VRAM_CACHE = 0.25
-DEFAULT_CONVERT_CACHE = 20.0
+DEFAULT_MAX_VRAM = 0.5
 
 
 class Categories(object):
@@ -211,7 +209,7 @@ class InvokeAIAppConfig(InvokeAISettings):
     """Configuration object for InvokeAI App."""
 
     singleton_config: ClassVar[Optional[InvokeAIAppConfig]] = None
-    singleton_init: ClassVar[Optional[Dict[str, Any]]] = None
+    singleton_init: ClassVar[Optional[Dict]] = None
 
     # fmt: off
     type: Literal["InvokeAI"] = "InvokeAI"
@@ -239,7 +237,6 @@ class InvokeAIAppConfig(InvokeAISettings):
     autoimport_dir      : Path = Field(default=Path('autoimport'), description='Path to a directory of models files to be imported on startup.', json_schema_extra=Categories.Paths)
     conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
     models_dir          : Path = Field(default=Path('models'), description='Path to the models directory', json_schema_extra=Categories.Paths)
-    convert_cache_dir   : Path = Field(default=Path('models/.cache'), description='Path to the converted models cache directory', json_schema_extra=Categories.Paths)
     legacy_conf_dir     : Path = Field(default=Path('configs/stable-diffusion'), description='Path to directory of legacy checkpoint config files', json_schema_extra=Categories.Paths)
     db_dir              : Path = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
     outdir              : Path = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
@@ -254,32 +251,26 @@ class InvokeAIAppConfig(InvokeAISettings):
     log_level           : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or  higher", json_schema_extra=Categories.Logging)
     log_sql             : bool = Field(default=False, description="Log SQL queries", json_schema_extra=Categories.Logging)
 
-    # Development
     dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", json_schema_extra=Categories.Development)
-    profile_graphs      : bool = Field(default=False, description="Enable graph profiling", json_schema_extra=Categories.Development)
-    profile_prefix      : Optional[str] = Field(default=None, description="An optional prefix for profile output files.", json_schema_extra=Categories.Development)
-    profiles_dir        : Path = Field(default=Path('profiles'), description="Directory for graph profiles", json_schema_extra=Categories.Development)
 
     version             : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
 
     # CACHE
-    ram                 : float = Field(default=DEFAULT_RAM_CACHE, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    vram                : float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    convert_cache       : float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB)", json_schema_extra=Categories.ModelCache)
-
+    ram                 : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
+    vram                : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
     lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", json_schema_extra=Categories.ModelCache, )
     log_memory_usage    : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
 
     # DEVICE
     device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", json_schema_extra=Categories.Device)
-    precision           : Literal["auto", "float16", "bfloat16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
+    precision           : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
 
     # GENERATION
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", json_schema_extra=Categories.Generation)
     attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", json_schema_extra=Categories.Generation)
     attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', json_schema_extra=Categories.Generation)
     force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Generation)
-    png_compress_level  : int = Field(default=1, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
+    png_compress_level  : int = Field(default=6, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
 
     # QUEUE
     max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", json_schema_extra=Categories.Queue)
@@ -289,9 +280,6 @@ class InvokeAIAppConfig(InvokeAISettings):
     deny_nodes          : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", json_schema_extra=Categories.Nodes)
     node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory", json_schema_extra=Categories.Nodes)
 
-    # MODEL IMPORT
-    civitai_api_key       : Optional[str] = Field(default=os.environ.get("CIVITAI_API_KEY"), description="API key for CivitAI", json_schema_extra=Categories.Other)
-
     # DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", json_schema_extra=Categories.MemoryPerformance)
     max_cache_size      : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", json_schema_extra=Categories.MemoryPerformance)
@@ -301,7 +289,6 @@ class InvokeAIAppConfig(InvokeAISettings):
     lora_dir            : Optional[Path] = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', json_schema_extra=Categories.Paths)
     embedding_dir       : Optional[Path] = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
     controlnet_dir      : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
-
     # this is not referred to in the source code and can be removed entirely
     #free_gpu_mem        : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", json_schema_extra=Categories.MemoryPerformance)
 
@@ -314,8 +301,8 @@ class InvokeAIAppConfig(InvokeAISettings):
         self,
         argv: Optional[list[str]] = None,
         conf: Optional[DictConfig] = None,
-        clobber: Optional[bool] = False,
-    ) -> None:
+        clobber=False,
+    ):
         """
         Update settings with contents of init file, environment, and command-line settings.
 
@@ -341,12 +328,16 @@ class InvokeAIAppConfig(InvokeAISettings):
         super().parse_args(argv)
 
         if self.singleton_init and not clobber:
-            # When setting values in this way, set validate_assignment to true if you want to validate the value.
-            for k, v in self.singleton_init.items():
-                setattr(self, k, v)
+            hints = get_type_hints(self.__class__)
+            for k in self.singleton_init:
+                setattr(
+                    self,
+                    k,
+                    TypeAdapter(hints[k]).validate_python(self.singleton_init[k]),
+                )
 
     @classmethod
-    def get_config(cls, **kwargs: Any) -> InvokeAIAppConfig:
+    def get_config(cls, **kwargs: Dict[str, Any]) -> InvokeAIAppConfig:
         """Return a singleton InvokeAIAppConfig configuration object."""
         if (
             cls.singleton_config is None
@@ -409,11 +400,6 @@ class InvokeAIAppConfig(InvokeAISettings):
         """Path to the models directory."""
         return self._resolve(self.models_dir)
 
-    @property
-    def models_convert_cache_path(self) -> Path:
-        """Path to the converted cache models directory."""
-        return self._resolve(self.convert_cache_dir)
-
     @property
     def custom_nodes_path(self) -> Path:
         """Path to the custom nodes directory."""
@@ -443,20 +429,15 @@ class InvokeAIAppConfig(InvokeAISettings):
         return True
 
     @property
-    def ram_cache_size(self) -> float:
-        """Return the ram cache size using the legacy or modern setting (GB)."""
+    def ram_cache_size(self) -> Union[Literal["auto"], float]:
+        """Return the ram cache size using the legacy or modern setting."""
         return self.max_cache_size or self.ram
 
     @property
-    def vram_cache_size(self) -> float:
-        """Return the vram cache size using the legacy or modern setting (GB)."""
+    def vram_cache_size(self) -> Union[Literal["auto"], float]:
+        """Return the vram cache size using the legacy or modern setting."""
         return self.max_vram_cache_size or self.vram
 
-    @property
-    def convert_cache_size(self) -> float:
-        """Return the convert cache size on disk (GB)."""
-        return self.convert_cache
-
     @property
     def use_cpu(self) -> bool:
         """Return true if the device is set to CPU or the always_use_cpu flag is set."""
@@ -468,18 +449,13 @@ class InvokeAIAppConfig(InvokeAISettings):
         disabled_in_config = not self.xformers_enabled
         return disabled_in_config and self.attention_type != "xformers"
 
-    @property
-    def profiles_path(self) -> Path:
-        """Path to the graph profiles directory."""
-        return self._resolve(self.profiles_dir)
-
     @staticmethod
     def find_root() -> Path:
         """Choose the runtime root directory when not specified on command line or init file."""
         return _find_root()
 
 
-def get_invokeai_config(**kwargs: Any) -> InvokeAIAppConfig:
+def get_invokeai_config(**kwargs) -> InvokeAIAppConfig:
     """Legacy function which returns InvokeAIAppConfig.get_config()."""
     return InvokeAIAppConfig.get_config(**kwargs)
 

invokeai/app/services/download/download_base.py

@@ -34,7 +34,6 @@ class ServiceInactiveException(Exception):
 
 
 DownloadEventHandler = Callable[["DownloadJob"], None]
-DownloadExceptionHandler = Callable[["DownloadJob", Optional[Exception]], None]
 
 
 @total_ordering
@@ -56,7 +55,6 @@ class DownloadJob(BaseModel):
     job_ended: Optional[str] = Field(
         default=None, description="Timestamp for when the download job ende1d (completed or errored)"
     )
-    content_type: Optional[str] = Field(default=None, description="Content type of downloaded file")
     bytes: int = Field(default=0, description="Bytes downloaded so far")
     total_bytes: int = Field(default=0, description="Total file size (bytes)")
 
@@ -72,11 +70,7 @@ class DownloadJob(BaseModel):
     _on_progress: Optional[DownloadEventHandler] = PrivateAttr(default=None)
     _on_complete: Optional[DownloadEventHandler] = PrivateAttr(default=None)
     _on_cancelled: Optional[DownloadEventHandler] = PrivateAttr(default=None)
-    _on_error: Optional[DownloadExceptionHandler] = PrivateAttr(default=None)
-
-    def __hash__(self) -> int:
-        """Return hash of the string representation of this object, for indexing."""
-        return hash(str(self))
+    _on_error: Optional[DownloadEventHandler] = PrivateAttr(default=None)
 
     def __le__(self, other: "DownloadJob") -> bool:
         """Return True if this job's priority is less than another's."""
@@ -93,26 +87,6 @@ class DownloadJob(BaseModel):
         """Call to cancel the job."""
         return self._cancelled
 
-    @property
-    def complete(self) -> bool:
-        """Return true if job completed without errors."""
-        return self.status == DownloadJobStatus.COMPLETED
-
-    @property
-    def running(self) -> bool:
-        """Return true if the job is running."""
-        return self.status == DownloadJobStatus.RUNNING
-
-    @property
-    def errored(self) -> bool:
-        """Return true if the job is errored."""
-        return self.status == DownloadJobStatus.ERROR
-
-    @property
-    def in_terminal_state(self) -> bool:
-        """Return true if job has finished, one way or another."""
-        return self.status not in [DownloadJobStatus.WAITING, DownloadJobStatus.RUNNING]
-
     @property
     def on_start(self) -> Optional[DownloadEventHandler]:
         """Return the on_start event handler."""
@@ -129,7 +103,7 @@ class DownloadJob(BaseModel):
         return self._on_complete
 
     @property
-    def on_error(self) -> Optional[DownloadExceptionHandler]:
+    def on_error(self) -> Optional[DownloadEventHandler]:
         """Return the on_error event handler."""
         return self._on_error
 
@@ -144,7 +118,7 @@ class DownloadJob(BaseModel):
         on_progress: Optional[DownloadEventHandler] = None,
         on_complete: Optional[DownloadEventHandler] = None,
         on_cancelled: Optional[DownloadEventHandler] = None,
-        on_error: Optional[DownloadExceptionHandler] = None,
+        on_error: Optional[DownloadEventHandler] = None,
     ) -> None:
         """Set the callbacks for download events."""
         self._on_start = on_start
@@ -176,10 +150,10 @@ class DownloadQueueServiceBase(ABC):
         on_progress: Optional[DownloadEventHandler] = None,
         on_complete: Optional[DownloadEventHandler] = None,
         on_cancelled: Optional[DownloadEventHandler] = None,
-        on_error: Optional[DownloadExceptionHandler] = None,
+        on_error: Optional[DownloadEventHandler] = None,
     ) -> DownloadJob:
         """
-        Create and enqueue download job.
+        Create a download job.
 
         :param source: Source of the download as a URL.
         :param dest: Path to download to. See below.
@@ -201,25 +175,6 @@ class DownloadQueueServiceBase(ABC):
         """
         pass
 
-    @abstractmethod
-    def submit_download_job(
-        self,
-        job: DownloadJob,
-        on_start: Optional[DownloadEventHandler] = None,
-        on_progress: Optional[DownloadEventHandler] = None,
-        on_complete: Optional[DownloadEventHandler] = None,
-        on_cancelled: Optional[DownloadEventHandler] = None,
-        on_error: Optional[DownloadExceptionHandler] = None,
-    ) -> None:
-        """
-        Enqueue a download job.
-
-        :param job: The DownloadJob
-        :param on_start, on_progress, on_complete, on_error: Callbacks for the indicated
-         events.
-        """
-        pass
-
     @abstractmethod
     def list_jobs(self) -> List[DownloadJob]:
         """
@@ -242,34 +197,21 @@ class DownloadQueueServiceBase(ABC):
         pass
 
     @abstractmethod
-    def cancel_all_jobs(self) -> None:
+    def cancel_all_jobs(self):
         """Cancel all active and enquedjobs."""
         pass
 
     @abstractmethod
-    def prune_jobs(self) -> None:
+    def prune_jobs(self):
         """Prune completed and errored queue items from the job list."""
         pass
 
     @abstractmethod
-    def cancel_job(self, job: DownloadJob) -> None:
+    def cancel_job(self, job: DownloadJob):
         """Cancel the job, clearing partial downloads and putting it into ERROR state."""
         pass
 
     @abstractmethod
-    def join(self) -> None:
+    def join(self):
         """Wait until all jobs are off the queue."""
         pass
-
-    @abstractmethod
-    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
-        """Wait until the indicated download job has reached a terminal state.
-
-        This will block until the indicated install job has completed,
-        been cancelled, or errored out.
-
-        :param job: The job to wait on.
-        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
-        the job hasn't completed within the indicated time.
-        """
-        pass

invokeai/app/services/download/download_default.py

@@ -4,8 +4,8 @@
 import os
 import re
 import threading
-import time
 import traceback
+from logging import Logger
 from pathlib import Path
 from queue import Empty, PriorityQueue
 from typing import Any, Dict, List, Optional, Set
@@ -21,7 +21,6 @@ from invokeai.backend.util.logging import InvokeAILogger
 
 from .download_base import (
     DownloadEventHandler,
-    DownloadExceptionHandler,
     DownloadJob,
     DownloadJobCancelledException,
     DownloadJobStatus,
@@ -37,6 +36,18 @@ DOWNLOAD_CHUNK_SIZE = 100000
 class DownloadQueueService(DownloadQueueServiceBase):
     """Class for queued download of models."""
 
+    _jobs: Dict[int, DownloadJob]
+    _max_parallel_dl: int = 5
+    _worker_pool: Set[threading.Thread]
+    _queue: PriorityQueue[DownloadJob]
+    _stop_event: threading.Event
+    _lock: threading.Lock
+    _logger: Logger
+    _events: Optional[EventServiceBase] = None
+    _next_job_id: int = 0
+    _accept_download_requests: bool = False
+    _requests: requests.sessions.Session
+
     def __init__(
         self,
         max_parallel_dl: int = 5,
@@ -49,12 +60,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
         :param max_parallel_dl: Number of simultaneous downloads allowed [5].
         :param requests_session: Optional requests.sessions.Session object, for unit tests.
         """
-        self._jobs: Dict[int, DownloadJob] = {}
+        self._jobs = {}
         self._next_job_id = 0
-        self._queue: PriorityQueue[DownloadJob] = PriorityQueue()
+        self._queue = PriorityQueue()
         self._stop_event = threading.Event()
-        self._job_completed_event = threading.Event()
-        self._worker_pool: Set[threading.Thread] = set()
+        self._worker_pool = set()
         self._lock = threading.Lock()
         self._logger = InvokeAILogger.get_logger("DownloadQueueService")
         self._event_bus = event_bus
@@ -89,33 +99,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
             self._stop_event.set()
             self._worker_pool.clear()
 
-    def submit_download_job(
-        self,
-        job: DownloadJob,
-        on_start: Optional[DownloadEventHandler] = None,
-        on_progress: Optional[DownloadEventHandler] = None,
-        on_complete: Optional[DownloadEventHandler] = None,
-        on_cancelled: Optional[DownloadEventHandler] = None,
-        on_error: Optional[DownloadExceptionHandler] = None,
-    ) -> None:
-        """Enqueue a download job."""
-        if not self._accept_download_requests:
-            raise ServiceInactiveException(
-                "The download service is not currently accepting requests. Please call start() to initialize the service."
-            )
-        with self._lock:
-            job.id = self._next_job_id
-            self._next_job_id += 1
-            job.set_callbacks(
-                on_start=on_start,
-                on_progress=on_progress,
-                on_complete=on_complete,
-                on_cancelled=on_cancelled,
-                on_error=on_error,
-            )
-            self._jobs[job.id] = job
-            self._queue.put(job)
-
     def download(
         self,
         source: AnyHttpUrl,
@@ -126,27 +109,32 @@ class DownloadQueueService(DownloadQueueServiceBase):
         on_progress: Optional[DownloadEventHandler] = None,
         on_complete: Optional[DownloadEventHandler] = None,
         on_cancelled: Optional[DownloadEventHandler] = None,
-        on_error: Optional[DownloadExceptionHandler] = None,
+        on_error: Optional[DownloadEventHandler] = None,
     ) -> DownloadJob:
-        """Create and enqueue a download job and return it."""
+        """Create a download job and return its ID."""
         if not self._accept_download_requests:
             raise ServiceInactiveException(
                 "The download service is not currently accepting requests. Please call start() to initialize the service."
             )
-        job = DownloadJob(
-            source=source,
-            dest=dest,
-            priority=priority,
-            access_token=access_token,
-        )
-        self.submit_download_job(
-            job,
-            on_start=on_start,
-            on_progress=on_progress,
-            on_complete=on_complete,
-            on_cancelled=on_cancelled,
-            on_error=on_error,
-        )
+        with self._lock:
+            id = self._next_job_id
+            self._next_job_id += 1
+            job = DownloadJob(
+                id=id,
+                source=source,
+                dest=dest,
+                priority=priority,
+                access_token=access_token,
+            )
+            job.set_callbacks(
+                on_start=on_start,
+                on_progress=on_progress,
+                on_complete=on_complete,
+                on_cancelled=on_cancelled,
+                on_error=on_error,
+            )
+            self._jobs[id] = job
+            self._queue.put(job)
         return job
 
     def join(self) -> None:
@@ -162,7 +150,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
         with self._lock:
             to_delete = set()
             for job_id, job in self._jobs.items():
-                if job.in_terminal_state:
+                if self._in_terminal_state(job):
                     to_delete.add(job_id)
             for job_id in to_delete:
                 del self._jobs[job_id]
@@ -184,21 +172,18 @@ class DownloadQueueService(DownloadQueueServiceBase):
         with self._lock:
             job.cancel()
 
-    def cancel_all_jobs(self) -> None:
+    def cancel_all_jobs(self, preserve_partial: bool = False) -> None:
         """Cancel all jobs (those not in enqueued, running or paused state)."""
         for job in self._jobs.values():
-            if not job.in_terminal_state:
+            if not self._in_terminal_state(job):
                 self.cancel_job(job)
 
-    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
-        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
-        start = time.time()
-        while not job.in_terminal_state:
-            if self._job_completed_event.wait(timeout=0.25):  # in case we miss an event
-                self._job_completed_event.clear()
-            if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
-        return job
+    def _in_terminal_state(self, job: DownloadJob) -> bool:
+        return job.status in [
+            DownloadJobStatus.COMPLETED,
+            DownloadJobStatus.CANCELLED,
+            DownloadJobStatus.ERROR,
+        ]
 
     def _start_workers(self, max_workers: int) -> None:
         """Start the requested number of worker threads."""
@@ -220,6 +205,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
                 job = self._queue.get(timeout=1)
             except Empty:
                 continue
+
             try:
                 job.job_started = get_iso_timestamp()
                 self._do_download(job)
@@ -228,14 +214,13 @@ class DownloadQueueService(DownloadQueueServiceBase):
             except (OSError, HTTPError) as excp:
                 job.error_type = excp.__class__.__name__ + f"({str(excp)})"
                 job.error = traceback.format_exc()
-                self._signal_job_error(job, excp)
+                self._signal_job_error(job)
             except DownloadJobCancelledException:
                 self._signal_job_cancelled(job)
                 self._cleanup_cancelled_job(job)
 
             finally:
                 job.job_ended = get_iso_timestamp()
-                self._job_completed_event.set()  # signal a change to terminal state
                 self._queue.task_done()
         self._logger.debug(f"Download queue worker thread {threading.current_thread().name} exiting.")
 
@@ -250,8 +235,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
         resp = self._requests.get(str(url), headers=header, stream=True)
         if not resp.ok:
             raise HTTPError(resp.reason)
-
-        job.content_type = resp.headers.get("Content-Type")
         content_length = int(resp.headers.get("content-length", 0))
         job.total_bytes = content_length
 
@@ -313,7 +296,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
                     self._signal_job_progress(job)
 
         # if we get here we are done and can rename the file to the original dest
-        self._logger.debug(f"{job.source}: saved to {job.download_path} (bytes={job.bytes})")
         in_progress_path.rename(job.download_path)
 
     def _validate_filename(self, directory: str, filename: str) -> bool:
@@ -340,9 +322,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
             try:
                 job.on_start(job)
             except Exception as e:
-                self._logger.error(
-                    f"An error occurred while processing the on_start callback: {traceback.format_exception(e)}"
-                )
+                self._logger.error(e)
         if self._event_bus:
             assert job.download_path
             self._event_bus.emit_download_started(str(job.source), job.download_path.as_posix())
@@ -352,9 +332,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
             try:
                 job.on_progress(job)
             except Exception as e:
-                self._logger.error(
-                    f"An error occurred while processing the on_progress callback: {traceback.format_exception(e)}"
-                )
+                self._logger.error(e)
         if self._event_bus:
             assert job.download_path
             self._event_bus.emit_download_progress(
@@ -370,9 +348,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
             try:
                 job.on_complete(job)
             except Exception as e:
-                self._logger.error(
-                    f"An error occurred while processing the on_complete callback: {traceback.format_exception(e)}"
-                )
+                self._logger.error(e)
         if self._event_bus:
             assert job.download_path
             self._event_bus.emit_download_complete(
@@ -380,36 +356,29 @@ class DownloadQueueService(DownloadQueueServiceBase):
             )
 
     def _signal_job_cancelled(self, job: DownloadJob) -> None:
-        if job.status not in [DownloadJobStatus.RUNNING, DownloadJobStatus.WAITING]:
-            return
         job.status = DownloadJobStatus.CANCELLED
         if job.on_cancelled:
             try:
                 job.on_cancelled(job)
             except Exception as e:
-                self._logger.error(
-                    f"An error occurred while processing the on_cancelled callback: {traceback.format_exception(e)}"
-                )
+                self._logger.error(e)
         if self._event_bus:
             self._event_bus.emit_download_cancelled(str(job.source))
 
-    def _signal_job_error(self, job: DownloadJob, excp: Optional[Exception] = None) -> None:
+    def _signal_job_error(self, job: DownloadJob) -> None:
         job.status = DownloadJobStatus.ERROR
-        self._logger.error(f"{str(job.source)}: {traceback.format_exception(excp)}")
         if job.on_error:
             try:
-                job.on_error(job, excp)
+                job.on_error(job)
             except Exception as e:
-                self._logger.error(
-                    f"An error occurred while processing the on_error callback: {traceback.format_exception(e)}"
-                )
+                self._logger.error(e)
         if self._event_bus:
             assert job.error_type
             assert job.error
             self._event_bus.emit_download_error(str(job.source), error_type=job.error_type, error=job.error)
 
     def _cleanup_cancelled_job(self, job: DownloadJob) -> None:
-        self._logger.debug(f"Cleaning up leftover files from cancelled download job {job.download_path}")
+        self._logger.warning(f"Cleaning up leftover files from cancelled download job {job.download_path}")
         try:
             if job.download_path:
                 partial_file = self._in_progress_path(job.download_path)
@@ -420,11 +389,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
-#   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))
+#   download_service.download('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().job_update
 class TqdmProgress(object):
     """TQDM-based progress bar object to use in on_progress handlers."""
 
-    _bars: Dict[int, tqdm]  # type: ignore
+    _bars: Dict[int, tqdm]  # the tqdm object
     _last: Dict[int, int]  # last bytes downloaded
 
     def __init__(self) -> None:  # noqa D107

invokeai/app/services/events/events_base.py

@@ -1,7 +1,7 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Optional
 
 from invokeai.app.services.invocation_processor.invocation_processor_common import ProgressImage
 from invokeai.app.services.session_queue.session_queue_common import (
@@ -11,7 +11,8 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueStatus,
 )
 from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_manager import AnyModelConfig
+from invokeai.backend.model_management.model_manager import ModelInfo
+from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
 
 
 class EventServiceBase:
@@ -170,7 +171,10 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_config: AnyModelConfig,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: SubModelType,
     ) -> None:
         """Emitted when a model is requested"""
         self.__emit_queue_event(
@@ -180,7 +184,10 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(),
+                "model_name": model_name,
+                "base_model": base_model,
+                "model_type": model_type,
+                "submodel": submodel,
             },
         )
 
@@ -190,7 +197,11 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_config: AnyModelConfig,
+        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_queue_event(
@@ -200,7 +211,13 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_config": model_config.model_dump(),
+                "model_name": model_name,
+                "base_model": base_model,
+                "model_type": model_type,
+                "submodel": submodel,
+                "hash": model_info.hash,
+                "location": str(model_info.location),
+                "precision": str(model_info.precision),
             },
         )
 
@@ -387,72 +404,53 @@ class EventServiceBase:
             },
         )
 
-    def emit_model_install_downloading(
-        self,
-        source: str,
-        local_path: str,
-        bytes: int,
-        total_bytes: int,
-        parts: List[Dict[str, Union[str, int]]],
-    ) -> None:
+    def emit_model_install_started(self, source: str) -> None:
         """
-        Emit at intervals while the install job is in progress (remote models only).
-
-        :param source: Source of the model
-        :param local_path: Where model is downloading to
-        :param parts: Progress of downloading URLs that comprise the model, if any.
-        :param bytes: Number of bytes downloaded so far.
-        :param total_bytes: Total size of download, including all files.
-        This emits a Dict with keys "source", "local_path", "bytes" and "total_bytes".
-        """
-        self.__emit_model_event(
-            event_name="model_install_downloading",
-            payload={
-                "source": source,
-                "local_path": local_path,
-                "bytes": bytes,
-                "total_bytes": total_bytes,
-                "parts": parts,
-            },
-        )
-
-    def emit_model_install_running(self, source: str) -> None:
-        """
-        Emit once when an install job becomes active.
+        Emitted when an install job is started.
 
         :param source: Source of the model; local path, repo_id or url
         """
         self.__emit_model_event(
-            event_name="model_install_running",
+            event_name="model_install_started",
             payload={"source": source},
         )
 
-    def emit_model_install_completed(self, source: str, key: str, total_bytes: Optional[int] = None) -> None:
+    def emit_model_install_completed(self, source: str, key: str) -> None:
         """
-        Emit when an install job is completed successfully.
+        Emitted when an install job is completed successfully.
 
         :param source: Source of the model; local path, repo_id or url
         :param key: Model config record key
-        :param total_bytes: Size of the model (may be None for installation of a local path)
         """
         self.__emit_model_event(
             event_name="model_install_completed",
             payload={
                 "source": source,
-                "total_bytes": total_bytes,
                 "key": key,
             },
         )
 
-    def emit_model_install_cancelled(self, source: str) -> None:
+    def emit_model_install_progress(
+        self,
+        source: str,
+        current_bytes: int,
+        total_bytes: int,
+    ) -> None:
         """
-        Emit when an install job is cancelled.
+        Emitted while the install job is in progress.
+        (Downloaded models only)
 
-        :param source: Source of the model; local path, repo_id or url
+        :param source: Source of the model
+        :param current_bytes: Number of bytes downloaded so far
+        :param total_bytes: Total bytes to download
         """
         self.__emit_model_event(
-            event_name="model_install_cancelled",
-            payload={"source": source},
+            event_name="model_install_progress",
+            payload={
+                "source": source,
+                "current_bytes": int,
+                "total_bytes": int,
+            },
         )
 
     def emit_model_install_error(
@@ -462,11 +460,10 @@ class EventServiceBase:
         error: str,
     ) -> None:
         """
-        Emit when an install job encounters an exception.
+        Emitted when an install job encounters an exception.
 
         :param source: Source of the model
-        :param error_type: The name of the exception
-        :param error: A text description of the exception
+        :param exception: The exception that raised the error
         """
         self.__emit_model_event(
             event_name="model_install_error",

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -1,16 +1,12 @@
+import cProfile
 import time
 import traceback
-from contextlib import suppress
 from threading import BoundedSemaphore, Event, Thread
 from typing import Optional
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.baseinvocation import InvocationContext
 from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
-from invokeai.app.services.invocation_stats.invocation_stats_common import (
-    GESStatsNotFoundError,
-)
-from invokeai.app.util.profiler import Profiler
 
 from ..invoker import Invoker
 from .invocation_processor_base import InvocationProcessorABC
@@ -23,7 +19,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker: Invoker
     __threadLimit: BoundedSemaphore
 
-    def start(self, invoker: Invoker) -> None:
+    def start(self, invoker) -> None:
         # if we do want multithreading at some point, we could make this configurable
         self.__threadLimit = BoundedSemaphore(1)
         self.__invoker = invoker
@@ -44,26 +40,8 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
             self.__threadLimit.acquire()
             queue_item: Optional[InvocationQueueItem] = None
 
-            profiler = (
-                Profiler(
-                    logger=self.__invoker.services.logger,
-                    output_dir=self.__invoker.services.configuration.profiles_path,
-                    prefix=self.__invoker.services.configuration.profile_prefix,
-                )
-                if self.__invoker.services.configuration.profile_graphs
-                else None
-            )
-
-            def stats_cleanup(graph_execution_state_id: str) -> None:
-                if profiler:
-                    profile_path = profiler.stop()
-                    stats_path = profile_path.with_suffix(".json")
-                    self.__invoker.services.performance_statistics.dump_stats(
-                        graph_execution_state_id=graph_execution_state_id, output_path=stats_path
-                    )
-                with suppress(GESStatsNotFoundError):
-                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state_id)
-                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state_id)
+            profiler = None
+            last_gesid = None
 
             while not stop_event.is_set():
                 try:
@@ -76,8 +54,19 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     time.sleep(0.5)
                     continue
 
-                if profiler and profiler.profile_id != queue_item.graph_execution_state_id:
-                    profiler.start(profile_id=queue_item.graph_execution_state_id)
+                if last_gesid != queue_item.graph_execution_state_id:
+                    if profiler is not None:
+                        # I'm not sure what would cause us to get here, but if we do, we should restart the profiler for
+                        # the new graph_execution_state_id.
+                        profiler.disable()
+                        logger.info(f"Stopped profiler for {last_gesid}.")
+                        profiler = None
+                        last_gesid = None
+
+                    profiler = cProfile.Profile()
+                    profiler.enable()
+                    last_gesid = queue_item.graph_execution_state_id
+                    logger.info(f"Started profiling {last_gesid}.")
 
                 try:
                     graph_execution_state = self.__invoker.services.graph_execution_manager.get(
@@ -162,12 +151,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                             source_node_id=source_node_id,
                             result=outputs.model_dump(),
                         )
+                    self.__invoker.services.performance_statistics.log_stats()
 
                 except KeyboardInterrupt:
                     pass
 
                 except CanceledException:
-                    stats_cleanup(graph_execution_state.id)
+                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
                     pass
 
                 except Exception as e:
@@ -192,6 +182,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         error_type=e.__class__.__name__,
                         error=error,
                     )
+                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state.id)
                     pass
 
                 # Check queue to see if this is canceled, and skip if so
@@ -229,7 +220,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         queue_id=queue_item.session_queue_id,
                         graph_execution_state_id=graph_execution_state.id,
                     )
-                    stats_cleanup(graph_execution_state.id)
+                    if profiler is not None:
+                        profiler.disable()
+                        dump_path = f"{last_gesid}.prof"
+                        profiler.dump_stats(dump_path)
+                        logger.info(f"Saved profile to {dump_path}.")
+                        profiler = None
+                        last_gesid = None
 
         except KeyboardInterrupt:
             pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor

invokeai/app/services/invocation_services.py

@@ -22,7 +22,9 @@ if TYPE_CHECKING:
     from .invocation_stats.invocation_stats_base import InvocationStatsServiceBase
     from .item_storage.item_storage_base import ItemStorageABC
     from .latents_storage.latents_storage_base import LatentsStorageBase
+    from .model_install import ModelInstallServiceBase
     from .model_manager.model_manager_base import ModelManagerServiceBase
+    from .model_records import ModelRecordServiceBase
     from .names.names_base import NameServiceBase
     from .session_processor.session_processor_base import SessionProcessorBase
     from .session_queue.session_queue_base import SessionQueueBase
@@ -48,7 +50,9 @@ class InvocationServices:
     latents: "LatentsStorageBase"
     logger: "Logger"
     model_manager: "ModelManagerServiceBase"
+    model_records: "ModelRecordServiceBase"
     download_queue: "DownloadQueueServiceBase"
+    model_install: "ModelInstallServiceBase"
     processor: "InvocationProcessorABC"
     performance_statistics: "InvocationStatsServiceBase"
     queue: "InvocationQueueABC"
@@ -74,7 +78,9 @@ class InvocationServices:
         latents: "LatentsStorageBase",
         logger: "Logger",
         model_manager: "ModelManagerServiceBase",
+        model_records: "ModelRecordServiceBase",
         download_queue: "DownloadQueueServiceBase",
+        model_install: "ModelInstallServiceBase",
         processor: "InvocationProcessorABC",
         performance_statistics: "InvocationStatsServiceBase",
         queue: "InvocationQueueABC",
@@ -98,7 +104,9 @@ class InvocationServices:
         self.latents = latents
         self.logger = logger
         self.model_manager = model_manager
+        self.model_records = model_records
         self.download_queue = download_queue
+        self.model_install = model_install
         self.processor = processor
         self.performance_statistics = performance_statistics
         self.queue = queue

invokeai/app/services/invocation_stats/invocation_stats_base.py

@@ -29,28 +29,37 @@ writes to the system log is stored in InvocationServices.performance_statistics.
 """
 
 from abc import ABC, abstractmethod
-from pathlib import Path
-from typing import Iterator
+from contextlib import AbstractContextManager
+from typing import Dict
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation
-from invokeai.app.services.invocation_stats.invocation_stats_common import InvocationStatsSummary
+from invokeai.backend.model_management.model_cache import CacheStats
+
+from .invocation_stats_common import NodeLog
 
 
 class InvocationStatsServiceBase(ABC):
     "Abstract base class for recording node memory/time performance statistics"
 
+    # {graph_id => NodeLog}
+    _stats: Dict[str, NodeLog]
+    _cache_stats: Dict[str, CacheStats]
+    ram_used: float
+    ram_changed: float
+
     @abstractmethod
-    def __init__(self) -> None:
+    def __init__(self):
         """
         Initialize the InvocationStatsService and reset counters to zero
         """
+        pass
 
     @abstractmethod
     def collect_stats(
         self,
         invocation: BaseInvocation,
         graph_execution_state_id: str,
-    ) -> Iterator[None]:
+    ) -> AbstractContextManager:
         """
         Return a context object that will capture the statistics on the execution
         of invocaation. Use with: to place around the part of the code that executes the invocation.
@@ -60,38 +69,53 @@ class InvocationStatsServiceBase(ABC):
         pass
 
     @abstractmethod
-    def reset_stats(self, graph_execution_state_id: str) -> None:
+    def reset_stats(self, graph_execution_state_id: str):
         """
-        Reset all statistics for the indicated graph.
-        :param graph_execution_state_id: The id of the session whose stats to reset.
-        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
+        Reset all statistics for the indicated graph
+        :param graph_execution_state_id
         """
         pass
 
     @abstractmethod
-    def log_stats(self, graph_execution_state_id: str) -> None:
+    def reset_all_stats(self):
+        """Zero all statistics"""
+        pass
+
+    @abstractmethod
+    def update_invocation_stats(
+        self,
+        graph_id: str,
+        invocation_type: str,
+        time_used: float,
+        vram_used: float,
+    ):
+        """
+        Add timing information on execution of a node. Usually
+        used internally.
+        :param graph_id: ID of the graph that is currently executing
+        :param invocation_type: String literal type of the node
+        :param time_used: Time used by node's exection (sec)
+        :param vram_used: Maximum VRAM used during exection (GB)
+        """
+        pass
+
+    @abstractmethod
+    def log_stats(self):
         """
         Write out the accumulated statistics to the log or somewhere else.
-        :param graph_execution_state_id: The id of the session whose stats to log.
-        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
         """
         pass
 
     @abstractmethod
-    def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
+    def update_mem_stats(
+        self,
+        ram_used: float,
+        ram_changed: float,
+    ):
         """
-        Gets the accumulated statistics for the indicated graph.
-        :param graph_execution_state_id: The id of the session whose stats to get.
-        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
-        """
-        pass
+        Update the collector with RAM memory usage info.
 
-    @abstractmethod
-    def dump_stats(self, graph_execution_state_id: str, output_path: Path) -> None:
-        """
-        Write out the accumulated statistics to the indicated path as JSON.
-        :param graph_execution_state_id: The id of the session whose stats to dump.
-        :param output_path: The file to write the stats to.
-        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
+        :param ram_used: How much RAM is currently in use.
+        :param ram_changed: How much RAM changed since last generation.
         """
         pass

invokeai/app/services/invocation_stats/invocation_stats_common.py

@@ -1,183 +1,25 @@
-from collections import defaultdict
-from dataclasses import asdict, dataclass
-from typing import Any, Optional
+from dataclasses import dataclass, field
+from typing import Dict
 
-
-class GESStatsNotFoundError(Exception):
-    """Raised when execution stats are not found for a given Graph Execution State."""
+# size of GIG in bytes
+GIG = 1073741824
 
 
 @dataclass
-class NodeExecutionStatsSummary:
-    """The stats for a specific type of node."""
+class NodeStats:
+    """Class for tracking execution stats of an invocation node"""
 
-    node_type: str
-    num_calls: int
-    time_used_seconds: float
-    peak_vram_gb: float
+    calls: int = 0
+    time_used: float = 0.0  # seconds
+    max_vram: float = 0.0  # GB
+    cache_hits: int = 0
+    cache_misses: int = 0
+    cache_high_watermark: int = 0
 
 
 @dataclass
-class ModelCacheStatsSummary:
-    """The stats for the model cache."""
+class NodeLog:
+    """Class for tracking node usage"""
 
-    high_water_mark_gb: float
-    cache_size_gb: float
-    total_usage_gb: float
-    cache_hits: int
-    cache_misses: int
-    models_cached: int
-    models_cleared: int
-
-
-@dataclass
-class GraphExecutionStatsSummary:
-    """The stats for the graph execution state."""
-
-    graph_execution_state_id: str
-    execution_time_seconds: float
-    # `wall_time_seconds`, `ram_usage_gb` and `ram_change_gb` are derived from the node execution stats.
-    # In some situations, there are no node stats, so these values are optional.
-    wall_time_seconds: Optional[float]
-    ram_usage_gb: Optional[float]
-    ram_change_gb: Optional[float]
-
-
-@dataclass
-class InvocationStatsSummary:
-    """
-    The accumulated stats for a graph execution.
-    Its `__str__` method returns a human-readable stats summary.
-    """
-
-    vram_usage_gb: Optional[float]
-    graph_stats: GraphExecutionStatsSummary
-    model_cache_stats: ModelCacheStatsSummary
-    node_stats: list[NodeExecutionStatsSummary]
-
-    def __str__(self) -> str:
-        _str = ""
-        _str = f"Graph stats: {self.graph_stats.graph_execution_state_id}\n"
-        _str += f"{'Node':>30} {'Calls':>7} {'Seconds':>9} {'VRAM Used':>10}\n"
-
-        for summary in self.node_stats:
-            _str += f"{summary.node_type:>30} {summary.num_calls:>7} {summary.time_used_seconds:>8.3f}s {summary.peak_vram_gb:>9.3f}G\n"
-
-        _str += f"TOTAL GRAPH EXECUTION TIME: {self.graph_stats.execution_time_seconds:7.3f}s\n"
-
-        if self.graph_stats.wall_time_seconds is not None:
-            _str += f"TOTAL GRAPH WALL TIME: {self.graph_stats.wall_time_seconds:7.3f}s\n"
-
-        if self.graph_stats.ram_usage_gb is not None and self.graph_stats.ram_change_gb is not None:
-            _str += f"RAM used by InvokeAI process: {self.graph_stats.ram_usage_gb:4.2f}G ({self.graph_stats.ram_change_gb:+5.3f}G)\n"
-
-        _str += f"RAM used to load models: {self.model_cache_stats.total_usage_gb:4.2f}G\n"
-        if self.vram_usage_gb:
-            _str += f"VRAM in use: {self.vram_usage_gb:4.3f}G\n"
-        _str += "RAM cache statistics:\n"
-        _str += f"   Model cache hits: {self.model_cache_stats.cache_hits}\n"
-        _str += f"   Model cache misses: {self.model_cache_stats.cache_misses}\n"
-        _str += f"   Models cached: {self.model_cache_stats.models_cached}\n"
-        _str += f"   Models cleared from cache: {self.model_cache_stats.models_cleared}\n"
-        _str += f"   Cache high water mark: {self.model_cache_stats.high_water_mark_gb:4.2f}/{self.model_cache_stats.cache_size_gb:4.2f}G\n"
-
-        return _str
-
-    def as_dict(self) -> dict[str, Any]:
-        """Returns the stats as a dictionary."""
-        return asdict(self)
-
-
-@dataclass
-class NodeExecutionStats:
-    """Class for tracking execution stats of an invocation node."""
-
-    invocation_type: str
-
-    start_time: float  # Seconds since the epoch.
-    end_time: float  # Seconds since the epoch.
-
-    start_ram_gb: float  # GB
-    end_ram_gb: float  # GB
-
-    peak_vram_gb: float  # GB
-
-    def total_time(self) -> float:
-        return self.end_time - self.start_time
-
-
-class GraphExecutionStats:
-    """Class for tracking execution stats of a graph."""
-
-    def __init__(self):
-        self._node_stats_list: list[NodeExecutionStats] = []
-
-    def add_node_execution_stats(self, node_stats: NodeExecutionStats):
-        self._node_stats_list.append(node_stats)
-
-    def get_total_run_time(self) -> float:
-        """Get the total time spent executing nodes in the graph."""
-        total = 0.0
-        for node_stats in self._node_stats_list:
-            total += node_stats.total_time()
-        return total
-
-    def get_first_node_stats(self) -> NodeExecutionStats | None:
-        """Get the stats of the first node in the graph (by start_time)."""
-        first_node = None
-        for node_stats in self._node_stats_list:
-            if first_node is None or node_stats.start_time < first_node.start_time:
-                first_node = node_stats
-
-        assert first_node is not None
-        return first_node
-
-    def get_last_node_stats(self) -> NodeExecutionStats | None:
-        """Get the stats of the last node in the graph (by end_time)."""
-        last_node = None
-        for node_stats in self._node_stats_list:
-            if last_node is None or node_stats.end_time > last_node.end_time:
-                last_node = node_stats
-
-        return last_node
-
-    def get_graph_stats_summary(self, graph_execution_state_id: str) -> GraphExecutionStatsSummary:
-        """Get a summary of the graph stats."""
-        first_node = self.get_first_node_stats()
-        last_node = self.get_last_node_stats()
-
-        wall_time_seconds: Optional[float] = None
-        ram_usage_gb: Optional[float] = None
-        ram_change_gb: Optional[float] = None
-
-        if last_node and first_node:
-            wall_time_seconds = last_node.end_time - first_node.start_time
-            ram_usage_gb = last_node.end_ram_gb
-            ram_change_gb = last_node.end_ram_gb - first_node.start_ram_gb
-
-        return GraphExecutionStatsSummary(
-            graph_execution_state_id=graph_execution_state_id,
-            execution_time_seconds=self.get_total_run_time(),
-            wall_time_seconds=wall_time_seconds,
-            ram_usage_gb=ram_usage_gb,
-            ram_change_gb=ram_change_gb,
-        )
-
-    def get_node_stats_summaries(self) -> list[NodeExecutionStatsSummary]:
-        """Get a summary of the node stats."""
-        summaries: list[NodeExecutionStatsSummary] = []
-        node_stats_by_type: dict[str, list[NodeExecutionStats]] = defaultdict(list)
-
-        for node_stats in self._node_stats_list:
-            node_stats_by_type[node_stats.invocation_type].append(node_stats)
-
-        for node_type, node_type_stats_list in node_stats_by_type.items():
-            num_calls = len(node_type_stats_list)
-            time_used = sum([n.total_time() for n in node_type_stats_list])
-            peak_vram = max([n.peak_vram_gb for n in node_type_stats_list])
-            summary = NodeExecutionStatsSummary(
-                node_type=node_type, num_calls=num_calls, time_used_seconds=time_used, peak_vram_gb=peak_vram
-            )
-            summaries.append(summary)
-
-        return summaries
+    # {node_type => NodeStats}
+    nodes: Dict[str, NodeStats] = field(default_factory=dict)

invokeai/app/services/invocation_stats/invocation_stats_default.py

@@ -1,8 +1,5 @@
-import json
 import time
-from contextlib import contextmanager
-from pathlib import Path
-from typing import Iterator
+from typing import Dict
 
 import psutil
 import torch
@@ -10,167 +7,161 @@ import torch
 import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
-from invokeai.backend.model_manager.load.model_cache import CacheStats
+from invokeai.app.services.model_manager.model_manager_base import ModelManagerServiceBase
+from invokeai.backend.model_management.model_cache import CacheStats
 
 from .invocation_stats_base import InvocationStatsServiceBase
-from .invocation_stats_common import (
-    GESStatsNotFoundError,
-    GraphExecutionStats,
-    GraphExecutionStatsSummary,
-    InvocationStatsSummary,
-    ModelCacheStatsSummary,
-    NodeExecutionStats,
-    NodeExecutionStatsSummary,
-)
-
-# Size of 1GB in bytes.
-GB = 2**30
+from .invocation_stats_common import GIG, NodeLog, NodeStats
 
 
 class InvocationStatsService(InvocationStatsServiceBase):
     """Accumulate performance information about a running graph. Collects time spent in each node,
     as well as the maximum and current VRAM utilisation for CUDA systems"""
 
+    _invoker: Invoker
+
     def __init__(self):
-        # Maps graph_execution_state_id to GraphExecutionStats.
-        self._stats: dict[str, GraphExecutionStats] = {}
-        # Maps graph_execution_state_id to model manager CacheStats.
-        self._cache_stats: dict[str, CacheStats] = {}
+        # {graph_id => NodeLog}
+        self._stats: Dict[str, NodeLog] = {}
+        self._cache_stats: Dict[str, CacheStats] = {}
+        self.ram_used: float = 0.0
+        self.ram_changed: float = 0.0
 
     def start(self, invoker: Invoker) -> None:
         self._invoker = invoker
 
-    @contextmanager
-    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str) -> Iterator[None]:
-        # This is to handle case of the model manager not being initialized, which happens
-        # during some tests.
-        services = self._invoker.services
-        if not self._stats.get(graph_execution_state_id):
-            # First time we're seeing this graph_execution_state_id.
-            self._stats[graph_execution_state_id] = GraphExecutionStats()
-            self._cache_stats[graph_execution_state_id] = CacheStats()
+    class StatsContext:
+        """Context manager for collecting statistics."""
 
-            # Prune stale stats. There should be none since we're starting a new graph, but just in case.
-            self._prune_stale_stats()
+        invocation: BaseInvocation
+        collector: "InvocationStatsServiceBase"
+        graph_id: str
+        start_time: float
+        ram_used: int
+        model_manager: ModelManagerServiceBase
 
-        # Record state before the invocation.
-        start_time = time.time()
-        start_ram = psutil.Process().memory_info().rss
-        if torch.cuda.is_available():
-            torch.cuda.reset_peak_memory_stats()
+        def __init__(
+            self,
+            invocation: BaseInvocation,
+            graph_id: str,
+            model_manager: ModelManagerServiceBase,
+            collector: "InvocationStatsServiceBase",
+        ):
+            """Initialize statistics for this run."""
+            self.invocation = invocation
+            self.collector = collector
+            self.graph_id = graph_id
+            self.start_time = 0.0
+            self.ram_used = 0
+            self.model_manager = model_manager
 
-        assert services.model_manager.load is not None
-        services.model_manager.load.ram_cache.stats = self._cache_stats[graph_execution_state_id]
+        def __enter__(self):
+            self.start_time = time.time()
+            if torch.cuda.is_available():
+                torch.cuda.reset_peak_memory_stats()
+            self.ram_used = psutil.Process().memory_info().rss
+            if self.model_manager:
+                self.model_manager.collect_cache_stats(self.collector._cache_stats[self.graph_id])
 
-        try:
-            # Let the invocation run.
-            yield None
-        finally:
-            # Record state after the invocation.
-            node_stats = NodeExecutionStats(
-                invocation_type=invocation.get_type(),
-                start_time=start_time,
-                end_time=time.time(),
-                start_ram_gb=start_ram / GB,
-                end_ram_gb=psutil.Process().memory_info().rss / GB,
-                peak_vram_gb=torch.cuda.max_memory_allocated() / GB if torch.cuda.is_available() else 0.0,
+        def __exit__(self, *args):
+            """Called on exit from the context."""
+            ram_used = psutil.Process().memory_info().rss
+            self.collector.update_mem_stats(
+                ram_used=ram_used / GIG,
+                ram_changed=(ram_used - self.ram_used) / GIG,
+            )
+            self.collector.update_invocation_stats(
+                graph_id=self.graph_id,
+                invocation_type=self.invocation.type,  # type: ignore # `type` is not on the `BaseInvocation` model, but *is* on all invocations
+                time_used=time.time() - self.start_time,
+                vram_used=torch.cuda.max_memory_allocated() / GIG if torch.cuda.is_available() else 0.0,
             )
-            self._stats[graph_execution_state_id].add_node_execution_stats(node_stats)
 
-    def _prune_stale_stats(self) -> None:
-        """Check all graphs being tracked and prune any that have completed/errored.
+    def collect_stats(
+        self,
+        invocation: BaseInvocation,
+        graph_execution_state_id: str,
+    ) -> StatsContext:
+        if not self._stats.get(graph_execution_state_id):  # first time we're seeing this
+            self._stats[graph_execution_state_id] = NodeLog()
+            self._cache_stats[graph_execution_state_id] = CacheStats()
+        return self.StatsContext(invocation, graph_execution_state_id, self._invoker.services.model_manager, self)
 
-        This shouldn't be necessary, but we don't have totally robust upstream handling of graph completions/errors, so
-        for now we call this function periodically to prevent them from accumulating.
-        """
-        to_prune: list[str] = []
-        for graph_execution_state_id in self._stats:
+    def reset_all_stats(self):
+        """Zero all statistics"""
+        self._stats = {}
+
+    def reset_stats(self, graph_execution_id: str):
+        try:
+            self._stats.pop(graph_execution_id)
+        except KeyError:
+            logger.warning(f"Attempted to clear statistics for unknown graph {graph_execution_id}")
+
+    def update_mem_stats(
+        self,
+        ram_used: float,
+        ram_changed: float,
+    ):
+        self.ram_used = ram_used
+        self.ram_changed = ram_changed
+
+    def update_invocation_stats(
+        self,
+        graph_id: str,
+        invocation_type: str,
+        time_used: float,
+        vram_used: float,
+    ):
+        if not self._stats[graph_id].nodes.get(invocation_type):
+            self._stats[graph_id].nodes[invocation_type] = NodeStats()
+        stats = self._stats[graph_id].nodes[invocation_type]
+        stats.calls += 1
+        stats.time_used += time_used
+        stats.max_vram = max(stats.max_vram, vram_used)
+
+    def log_stats(self):
+        completed = set()
+        errored = set()
+        for graph_id, _node_log in self._stats.items():
             try:
-                graph_execution_state = self._invoker.services.graph_execution_manager.get(graph_execution_state_id)
-            except ItemNotFoundError:
-                # TODO(ryand): What would cause this? Should this exception just be allowed to propagate?
-                logger.warning(f"Failed to get graph state for {graph_execution_state_id}.")
+                current_graph_state = self._invoker.services.graph_execution_manager.get(graph_id)
+            except Exception:
+                errored.add(graph_id)
                 continue
 
-            if not graph_execution_state.is_complete():
-                # The graph is still running, don't prune it.
+            if not current_graph_state.is_complete():
                 continue
 
-            to_prune.append(graph_execution_state_id)
+            total_time = 0
+            logger.info(f"Graph stats: {graph_id}")
+            logger.info(f"{'Node':>30} {'Calls':>7}{'Seconds':>9} {'VRAM Used':>10}")
+            for node_type, stats in self._stats[graph_id].nodes.items():
+                logger.info(f"{node_type:>30}  {stats.calls:>4}   {stats.time_used:7.3f}s     {stats.max_vram:4.3f}G")
+                total_time += stats.time_used
 
-        for graph_execution_state_id in to_prune:
-            del self._stats[graph_execution_state_id]
-            del self._cache_stats[graph_execution_state_id]
+            cache_stats = self._cache_stats[graph_id]
+            hwm = cache_stats.high_watermark / GIG
+            tot = cache_stats.cache_size / GIG
+            loaded = sum(list(cache_stats.loaded_model_sizes.values())) / GIG
 
-        if len(to_prune) > 0:
-            logger.info(f"Pruned stale graph stats for {to_prune}.")
+            logger.info(f"TOTAL GRAPH EXECUTION TIME:  {total_time:7.3f}s")
+            logger.info("RAM used by InvokeAI process: " + "%4.2fG" % self.ram_used + f" ({self.ram_changed:+5.3f}G)")
+            logger.info(f"RAM used to load models: {loaded:4.2f}G")
+            if torch.cuda.is_available():
+                logger.info("VRAM in use: " + "%4.3fG" % (torch.cuda.memory_allocated() / GIG))
+            logger.info("RAM cache statistics:")
+            logger.info(f"   Model cache hits: {cache_stats.hits}")
+            logger.info(f"   Model cache misses: {cache_stats.misses}")
+            logger.info(f"   Models cached: {cache_stats.in_cache}")
+            logger.info(f"   Models cleared from cache: {cache_stats.cleared}")
+            logger.info(f"   Cache high water mark: {hwm:4.2f}/{tot:4.2f}G")
 
-    def reset_stats(self, graph_execution_state_id: str):
-        try:
-            del self._stats[graph_execution_state_id]
-            del self._cache_stats[graph_execution_state_id]
-        except KeyError as e:
-            raise GESStatsNotFoundError(
-                f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
-            ) from e
+            completed.add(graph_id)
 
-    def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
-        graph_stats_summary = self._get_graph_summary(graph_execution_state_id)
-        node_stats_summaries = self._get_node_summaries(graph_execution_state_id)
-        model_cache_stats_summary = self._get_model_cache_summary(graph_execution_state_id)
-        vram_usage_gb = torch.cuda.memory_allocated() / GB if torch.cuda.is_available() else None
+        for graph_id in completed:
+            del self._stats[graph_id]
+            del self._cache_stats[graph_id]
 
-        return InvocationStatsSummary(
-            graph_stats=graph_stats_summary,
-            model_cache_stats=model_cache_stats_summary,
-            node_stats=node_stats_summaries,
-            vram_usage_gb=vram_usage_gb,
-        )
-
-    def log_stats(self, graph_execution_state_id: str) -> None:
-        stats = self.get_stats(graph_execution_state_id)
-        logger.info(str(stats))
-
-    def dump_stats(self, graph_execution_state_id: str, output_path: Path) -> None:
-        stats = self.get_stats(graph_execution_state_id)
-        with open(output_path, "w") as f:
-            f.write(json.dumps(stats.as_dict(), indent=2))
-
-    def _get_model_cache_summary(self, graph_execution_state_id: str) -> ModelCacheStatsSummary:
-        try:
-            cache_stats = self._cache_stats[graph_execution_state_id]
-        except KeyError as e:
-            raise GESStatsNotFoundError(
-                f"Attempted to get model cache statistics for unknown graph {graph_execution_state_id}: {e}."
-            ) from e
-
-        return ModelCacheStatsSummary(
-            cache_hits=cache_stats.hits,
-            cache_misses=cache_stats.misses,
-            high_water_mark_gb=cache_stats.high_watermark / GB,
-            cache_size_gb=cache_stats.cache_size / GB,
-            total_usage_gb=sum(list(cache_stats.loaded_model_sizes.values())) / GB,
-            models_cached=cache_stats.in_cache,
-            models_cleared=cache_stats.cleared,
-        )
-
-    def _get_graph_summary(self, graph_execution_state_id: str) -> GraphExecutionStatsSummary:
-        try:
-            graph_stats = self._stats[graph_execution_state_id]
-        except KeyError as e:
-            raise GESStatsNotFoundError(
-                f"Attempted to get graph statistics for unknown graph {graph_execution_state_id}: {e}."
-            ) from e
-
-        return graph_stats.get_graph_stats_summary(graph_execution_state_id)
-
-    def _get_node_summaries(self, graph_execution_state_id: str) -> list[NodeExecutionStatsSummary]:
-        try:
-            graph_stats = self._stats[graph_execution_state_id]
-        except KeyError as e:
-            raise GESStatsNotFoundError(
-                f"Attempted to get node statistics for unknown graph {graph_execution_state_id}: {e}."
-            ) from e
-
-        return graph_stats.get_node_stats_summaries()
+        for graph_id in errored:
+            del self._stats[graph_id]
+            del self._cache_stats[graph_id]

invokeai/app/services/item_storage/item_storage_base.py

@@ -1,8 +1,10 @@
 from abc import ABC, abstractmethod
-from typing import Callable, Generic, TypeVar
+from typing import Callable, Generic, Optional, TypeVar
 
 from pydantic import BaseModel
 
+from invokeai.app.services.shared.pagination import PaginatedResults
+
 T = TypeVar("T", bound=BaseModel)
 
 
@@ -20,26 +22,26 @@ class ItemStorageABC(ABC, Generic[T]):
 
     @abstractmethod
     def get(self, item_id: str) -> T:
-        """
-        Gets the item.
-        :param item_id: the id of the item to get
-        :raises ItemNotFoundError: if the item is not found
-        """
+        """Gets the item, parsing it into a Pydantic model"""
+        pass
+
+    @abstractmethod
+    def get_raw(self, item_id: str) -> Optional[str]:
+        """Gets the raw item as a string, skipping Pydantic parsing"""
         pass
 
     @abstractmethod
     def set(self, item: T) -> None:
-        """
-        Sets the item. The id will be extracted based on id_field.
-        :param item: the item to set
-        """
+        """Sets the item"""
         pass
 
     @abstractmethod
-    def delete(self, item_id: str) -> None:
-        """
-        Deletes the item, if it exists.
-        """
+    def list(self, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
+        """Gets a paginated list of items"""
+        pass
+
+    @abstractmethod
+    def search(self, query: str, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
         pass
 
     def on_changed(self, on_changed: Callable[[T], None]) -> None:

invokeai/app/services/item_storage/item_storage_common.py

@@ -1,5 +0,0 @@
-class ItemNotFoundError(KeyError):
-    """Raised when an item is not found in storage"""
-
-    def __init__(self, item_id: str) -> None:
-        super().__init__(f"Item with id {item_id} not found")

invokeai/app/services/item_storage/item_storage_memory.py

@@ -1,52 +0,0 @@
-from collections import OrderedDict
-from contextlib import suppress
-from typing import Generic, TypeVar
-
-from pydantic import BaseModel
-
-from invokeai.app.services.item_storage.item_storage_base import ItemStorageABC
-from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
-
-T = TypeVar("T", bound=BaseModel)
-
-
-class ItemStorageMemory(ItemStorageABC[T], Generic[T]):
-    """
-    Provides a simple in-memory storage for items, with a maximum number of items to store.
-    The storage uses the LRU strategy to evict items from storage when the max has been reached.
-    """
-
-    def __init__(self, id_field: str = "id", max_items: int = 10) -> None:
-        super().__init__()
-        if max_items < 1:
-            raise ValueError("max_items must be at least 1")
-        if not id_field:
-            raise ValueError("id_field must not be empty")
-        self._id_field = id_field
-        self._items: OrderedDict[str, T] = OrderedDict()
-        self._max_items = max_items
-
-    def get(self, item_id: str) -> T:
-        # If the item exists, move it to the end of the OrderedDict.
-        item = self._items.pop(item_id, None)
-        if item is None:
-            raise ItemNotFoundError(item_id)
-        self._items[item_id] = item
-        return item
-
-    def set(self, item: T) -> None:
-        item_id = getattr(item, self._id_field)
-        if item_id in self._items:
-            # If item already exists, remove it and add it to the end
-            self._items.pop(item_id)
-        elif len(self._items) >= self._max_items:
-            # If cache is full, evict the least recently used item
-            self._items.popitem(last=False)
-        self._items[item_id] = item
-        self._on_changed(item)
-
-    def delete(self, item_id: str) -> None:
-        # This is a no-op if the item doesn't exist.
-        with suppress(KeyError):
-            del self._items[item_id]
-            self._on_deleted(item_id)

invokeai/app/services/item_storage/item_storage_sqlite.py

@@ -0,0 +1,147 @@
+import sqlite3
+import threading
+from typing import Generic, Optional, TypeVar, get_args
+
+from pydantic import BaseModel, TypeAdapter
+
+from invokeai.app.services.shared.pagination import PaginatedResults
+from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
+
+from .item_storage_base import ItemStorageABC
+
+T = TypeVar("T", bound=BaseModel)
+
+
+class SqliteItemStorage(ItemStorageABC, Generic[T]):
+    _table_name: str
+    _conn: sqlite3.Connection
+    _cursor: sqlite3.Cursor
+    _id_field: str
+    _lock: threading.RLock
+    _validator: Optional[TypeAdapter[T]]
+
+    def __init__(self, db: SqliteDatabase, table_name: str, id_field: str = "id"):
+        super().__init__()
+
+        self._lock = db.lock
+        self._conn = db.conn
+        self._table_name = table_name
+        self._id_field = id_field  # TODO: validate that T has this field
+        self._cursor = self._conn.cursor()
+        self._validator: Optional[TypeAdapter[T]] = None
+
+        self._create_table()
+
+    def _create_table(self):
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""CREATE TABLE IF NOT EXISTS {self._table_name} (
+                item TEXT,
+                id TEXT GENERATED ALWAYS AS (json_extract(item, '$.{self._id_field}')) VIRTUAL NOT NULL);"""
+            )
+            self._cursor.execute(
+                f"""CREATE UNIQUE INDEX IF NOT EXISTS {self._table_name}_id ON {self._table_name}(id);"""
+            )
+        finally:
+            self._lock.release()
+
+    def _parse_item(self, item: str) -> T:
+        if self._validator is None:
+            """
+            We don't get access to `__orig_class__` in `__init__()`, and we need this before start(), so
+            we can create it when it is first needed instead.
+            __orig_class__ is technically an implementation detail of the typing module, not a supported API
+            """
+            self._validator = TypeAdapter(get_args(self.__orig_class__)[0])  # type: ignore [attr-defined]
+        return self._validator.validate_json(item)
+
+    def set(self, item: T):
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""INSERT OR REPLACE INTO {self._table_name} (item) VALUES (?);""",
+                (item.model_dump_json(warnings=False, exclude_none=True),),
+            )
+            self._conn.commit()
+        finally:
+            self._lock.release()
+        self._on_changed(item)
+
+    def get(self, id: str) -> Optional[T]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(f"""SELECT item FROM {self._table_name} WHERE id = ?;""", (str(id),))
+            result = self._cursor.fetchone()
+        finally:
+            self._lock.release()
+
+        if not result:
+            return None
+
+        return self._parse_item(result[0])
+
+    def get_raw(self, id: str) -> Optional[str]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(f"""SELECT item FROM {self._table_name} WHERE id = ?;""", (str(id),))
+            result = self._cursor.fetchone()
+        finally:
+            self._lock.release()
+
+        if not result:
+            return None
+
+        return result[0]
+
+    def delete(self, id: str):
+        try:
+            self._lock.acquire()
+            self._cursor.execute(f"""DELETE FROM {self._table_name} WHERE id = ?;""", (str(id),))
+            self._conn.commit()
+        finally:
+            self._lock.release()
+        self._on_deleted(id)
+
+    def list(self, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""SELECT item FROM {self._table_name} LIMIT ? OFFSET ?;""",
+                (per_page, page * per_page),
+            )
+            result = self._cursor.fetchall()
+
+            items = [self._parse_item(r[0]) for r in result]
+
+            self._cursor.execute(f"""SELECT count(*) FROM {self._table_name};""")
+            count = self._cursor.fetchone()[0]
+        finally:
+            self._lock.release()
+
+        pageCount = int(count / per_page) + 1
+
+        return PaginatedResults[T](items=items, page=page, pages=pageCount, per_page=per_page, total=count)
+
+    def search(self, query: str, page: int = 0, per_page: int = 10) -> PaginatedResults[T]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                f"""SELECT item FROM {self._table_name} WHERE item LIKE ? LIMIT ? OFFSET ?;""",
+                (f"%{query}%", per_page, page * per_page),
+            )
+            result = self._cursor.fetchall()
+
+            items = [self._parse_item(r[0]) for r in result]
+
+            self._cursor.execute(
+                f"""SELECT count(*) FROM {self._table_name} WHERE item LIKE ?;""",
+                (f"%{query}%",),
+            )
+            count = self._cursor.fetchone()[0]
+        finally:
+            self._lock.release()
+
+        pageCount = int(count / per_page) + 1
+
+        return PaginatedResults[T](items=items, page=page, pages=pageCount, per_page=per_page, total=count)

invokeai/app/services/latents_storage/latents_storage_base.py

@@ -1,12 +1,10 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
 from abc import ABC, abstractmethod
-from typing import Callable, Union
+from typing import Callable
 
 import torch
 
-from invokeai.app.invocations.compel import ConditioningFieldData
-
 
 class LatentsStorageBase(ABC):
     """Responsible for storing and retrieving latents."""
@@ -22,10 +20,8 @@ class LatentsStorageBase(ABC):
     def get(self, name: str) -> torch.Tensor:
         pass
 
-    # (LS) Added a Union with ConditioningFieldData to fix type mismatch errors in compel.py
-    # Not 100% sure this isn't an existing bug.
     @abstractmethod
-    def save(self, name: str, data: Union[torch.Tensor, ConditioningFieldData]) -> None:
+    def save(self, name: str, data: torch.Tensor) -> None:
         pass
 
     @abstractmethod

invokeai/app/services/latents_storage/latents_storage_disk.py

@@ -5,7 +5,6 @@ from typing import Union
 
 import torch
 
-from invokeai.app.invocations.compel import ConditioningFieldData
 from invokeai.app.services.invoker import Invoker
 
 from .latents_storage_base import LatentsStorageBase
@@ -28,7 +27,7 @@ class DiskLatentsStorage(LatentsStorageBase):
         latent_path = self.get_path(name)
         return torch.load(latent_path)
 
-    def save(self, name: str, data: Union[torch.Tensor, ConditioningFieldData]) -> None:
+    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)

invokeai/app/services/latents_storage/latents_storage_forward_cache.py

@@ -1,11 +1,10 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
 from queue import Queue
-from typing import Dict, Optional, Union
+from typing import Dict, Optional
 
 import torch
 
-from invokeai.app.invocations.compel import ConditioningFieldData
 from invokeai.app.services.invoker import Invoker
 
 from .latents_storage_base import LatentsStorageBase
@@ -47,9 +46,7 @@ class ForwardCacheLatentsStorage(LatentsStorageBase):
         self.__set_cache(name, latent)
         return latent
 
-    # TODO: (LS) ConditioningFieldData added as Union because of type-checking errors
-    # in compel.py. Unclear whether this is a long-standing bug, but seems to run.
-    def save(self, name: str, data: Union[torch.Tensor, ConditioningFieldData]) -> None:
+    def save(self, name: str, data: torch.Tensor) -> None:
         self.__underlying_storage.save(name, data)
         self.__set_cache(name, data)
         self._on_changed(data)

invokeai/app/services/model_install/__init__.py

@@ -1,7 +1,6 @@
 """Initialization file for model install service package."""
 
 from .model_install_base import (
-    CivitaiModelSource,
     HFModelSource,
     InstallStatus,
     LocalModelSource,
@@ -23,5 +22,4 @@ __all__ = [
     "LocalModelSource",
     "HFModelSource",
     "URLModelSource",
-    "CivitaiModelSource",
 ]

invokeai/app/services/model_install/model_install_base.py

@@ -1,44 +1,27 @@
-# Copyright 2023 Lincoln D. Stein and the InvokeAI development team
-"""Baseclass definitions for the model installer."""
-
 import re
 import traceback
 from abc import ABC, abstractmethod
 from enum import Enum
 from pathlib import Path
-from typing import Any, Dict, List, Literal, Optional, Set, Union
+from typing import Any, Dict, List, Literal, Optional, Union
 
-from pydantic import BaseModel, Field, PrivateAttr, field_validator
+from pydantic import BaseModel, Field, field_validator
 from pydantic.networks import AnyHttpUrl
 from typing_extensions import Annotated
 
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
-from invokeai.app.services.events.events_base import EventServiceBase
-from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.events import EventServiceBase
 from invokeai.app.services.model_records import ModelRecordServiceBase
-from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..model_metadata import ModelMetadataStoreBase
+from invokeai.backend.model_manager import AnyModelConfig
 
 
 class InstallStatus(str, Enum):
     """State of an install job running in the background."""
 
     WAITING = "waiting"  # waiting to be dequeued
-    DOWNLOADING = "downloading"  # downloading of model files in process
     RUNNING = "running"  # being processed
     COMPLETED = "completed"  # finished running
     ERROR = "error"  # terminated with an error message
-    CANCELLED = "cancelled"  # terminated with an error message
-
-
-class ModelInstallPart(BaseModel):
-    url: AnyHttpUrl
-    path: Path
-    bytes: int = 0
-    total_bytes: int = 0
 
 
 class UnknownInstallJobException(Exception):
@@ -91,31 +74,12 @@ class LocalModelSource(StringLikeSource):
         return Path(self.path).as_posix()
 
 
-class CivitaiModelSource(StringLikeSource):
-    """A Civitai version id, with optional variant and access token."""
-
-    version_id: int
-    variant: Optional[ModelRepoVariant] = None
-    access_token: Optional[str] = None
-    type: Literal["civitai"] = "civitai"
-
-    def __str__(self) -> str:
-        """Return string version of repoid when string rep needed."""
-        base: str = str(self.version_id)
-        base += f" ({self.variant})" if self.variant else ""
-        return base
-
-
 class HFModelSource(StringLikeSource):
-    """
-    A HuggingFace repo_id with optional variant, sub-folder and access token.
-    Note that the variant option, if not provided to the constructor, will default to fp16, which is
-    what people (almost) always want.
-    """
+    """A HuggingFace repo_id, with optional variant and sub-folder."""
 
     repo_id: str
-    variant: Optional[ModelRepoVariant] = ModelRepoVariant.FP16
-    subfolder: Optional[Path] = None
+    variant: Optional[str] = None
+    subfolder: Optional[str | Path] = None
     access_token: Optional[str] = None
     type: Literal["hf"] = "hf"
 
@@ -129,8 +93,8 @@ class HFModelSource(StringLikeSource):
     def __str__(self) -> str:
         """Return string version of repoid when string rep needed."""
         base: str = self.repo_id
-        base += f":{self.variant or ''}"
         base += f":{self.subfolder}" if self.subfolder else ""
+        base += f" ({self.variant})" if self.variant else ""
         return base
 
 
@@ -139,22 +103,19 @@ class URLModelSource(StringLikeSource):
 
     url: AnyHttpUrl
     access_token: Optional[str] = None
-    type: Literal["url"] = "url"
+    type: Literal["generic_url"] = "generic_url"
 
     def __str__(self) -> str:
         """Return string version of the url when string rep needed."""
         return str(self.url)
 
 
-ModelSource = Annotated[
-    Union[LocalModelSource, HFModelSource, CivitaiModelSource, URLModelSource], Field(discriminator="type")
-]
+ModelSource = Annotated[Union[LocalModelSource, HFModelSource, URLModelSource], Field(discriminator="type")]
 
 
 class ModelInstallJob(BaseModel):
     """Object that tracks the current status of an install request."""
 
-    id: int = Field(description="Unique ID for this job")
     status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
     config_in: Dict[str, Any] = Field(
         default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
@@ -167,74 +128,15 @@ class ModelInstallJob(BaseModel):
     )
     source: ModelSource = Field(description="Source (URL, repo_id, or local path) of model")
     local_path: Path = Field(description="Path to locally-downloaded model; may be the same as the source")
-    bytes: int = Field(
-        default=0, description="For a remote model, the number of bytes downloaded so far (may not be available)"
-    )
-    total_bytes: int = Field(default=0, description="Total size of the model to be installed")
-    source_metadata: Optional[AnyModelRepoMetadata] = Field(
-        default=None, description="Metadata provided by the model source"
-    )
-    download_parts: Set[DownloadJob] = Field(
-        default_factory=set, description="Download jobs contributing to this install"
-    )
-    # internal flags and transitory settings
-    _install_tmpdir: Optional[Path] = PrivateAttr(default=None)
-    _exception: Optional[Exception] = PrivateAttr(default=None)
+    error_type: Optional[str] = Field(default=None, description="Class name of the exception that led to status==ERROR")
+    error: Optional[str] = Field(default=None, description="Error traceback")  # noqa #501
 
     def set_error(self, e: Exception) -> None:
         """Record the error and traceback from an exception."""
-        self._exception = e
+        self.error_type = e.__class__.__name__
+        self.error = "".join(traceback.format_exception(e))
         self.status = InstallStatus.ERROR
 
-    def cancel(self) -> None:
-        """Call to cancel the job."""
-        self.status = InstallStatus.CANCELLED
-
-    @property
-    def error_type(self) -> Optional[str]:
-        """Class name of the exception that led to status==ERROR."""
-        return self._exception.__class__.__name__ if self._exception else None
-
-    @property
-    def error(self) -> Optional[str]:
-        """Error traceback."""
-        return "".join(traceback.format_exception(self._exception)) if self._exception else None
-
-    @property
-    def cancelled(self) -> bool:
-        """Set status to CANCELLED."""
-        return self.status == InstallStatus.CANCELLED
-
-    @property
-    def errored(self) -> bool:
-        """Return true if job has errored."""
-        return self.status == InstallStatus.ERROR
-
-    @property
-    def waiting(self) -> bool:
-        """Return true if job is waiting to run."""
-        return self.status == InstallStatus.WAITING
-
-    @property
-    def downloading(self) -> bool:
-        """Return true if job is downloading."""
-        return self.status == InstallStatus.DOWNLOADING
-
-    @property
-    def running(self) -> bool:
-        """Return true if job is running."""
-        return self.status == InstallStatus.RUNNING
-
-    @property
-    def complete(self) -> bool:
-        """Return true if job completed without errors."""
-        return self.status == InstallStatus.COMPLETED
-
-    @property
-    def in_terminal_state(self) -> bool:
-        """Return true if job is in a terminal state."""
-        return self.status in [InstallStatus.COMPLETED, InstallStatus.ERROR, InstallStatus.CANCELLED]
-
 
 class ModelInstallServiceBase(ABC):
     """Abstract base class for InvokeAI model installation."""
@@ -244,8 +146,6 @@ class ModelInstallServiceBase(ABC):
         self,
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
-        download_queue: DownloadQueueServiceBase,
-        metadata_store: ModelMetadataStoreBase,
         event_bus: Optional["EventServiceBase"] = None,
     ):
         """
@@ -256,14 +156,12 @@ class ModelInstallServiceBase(ABC):
         :param event_bus: InvokeAI event bus for reporting events to.
         """
 
-    # make the invoker optional here because we don't need it and it
-    # makes the installer harder to use outside the web app
     @abstractmethod
-    def start(self, invoker: Optional[Invoker] = None) -> None:
+    def start(self, *args: Any, **kwarg: Any) -> None:
         """Start the installer service."""
 
     @abstractmethod
-    def stop(self, invoker: Optional[Invoker] = None) -> None:
+    def stop(self, *args: Any, **kwarg: Any) -> None:
         """Stop the model install service. After this the objection can be safely deleted."""
 
     @property
@@ -326,43 +224,6 @@ class ModelInstallServiceBase(ABC):
         :returns id: The string ID of the registered model.
         """
 
-    @abstractmethod
-    def heuristic_import(
-        self,
-        source: str,
-        config: Optional[Dict[str, Any]] = None,
-        access_token: Optional[str] = None,
-    ) -> ModelInstallJob:
-        r"""Install the indicated model using heuristics to interpret user intentions.
-
-        :param source: String source
-        :param config: Optional dict. Any fields in this dict
-         will override corresponding autoassigned probe fields in the
-         model's config record as described in `import_model()`.
-        :param access_token: Optional access token for remote sources.
-
-        The source can be:
-        1. A local file path in posix() format (`/foo/bar` or `C:\foo\bar`)
-        2. An http or https URL (`https://foo.bar/foo`)
-        3. A HuggingFace repo_id (`foo/bar`, `foo/bar:fp16`, `foo/bar:fp16:vae`)
-
-        We extend the HuggingFace repo_id syntax to include the variant and the
-        subfolder or path. The following are acceptable alternatives:
-            stabilityai/stable-diffusion-v4
-            stabilityai/stable-diffusion-v4:fp16
-            stabilityai/stable-diffusion-v4:fp16:vae
-            stabilityai/stable-diffusion-v4::/checkpoints/sd4.safetensors
-            stabilityai/stable-diffusion-v4:onnx:vae
-
-        Because a local file path can look like a huggingface repo_id, the logic
-        first checks whether the path exists on disk, and if not, it is treated as
-        a parseable huggingface repo.
-
-        The previous support for recursing into a local folder and loading all model-like files
-        has been removed.
-        """
-        pass
-
     @abstractmethod
     def import_model(
         self,
@@ -403,13 +264,9 @@ class ModelInstallServiceBase(ABC):
         """
 
     @abstractmethod
-    def get_job_by_source(self, source: ModelSource) -> List[ModelInstallJob]:
+    def get_job(self, source: ModelSource) -> List[ModelInstallJob]:
         """Return the ModelInstallJob(s) corresponding to the provided source."""
 
-    @abstractmethod
-    def get_job_by_id(self, id: int) -> ModelInstallJob:
-        """Return the ModelInstallJob corresponding to the provided id. Raises ValueError if no job has that ID."""
-
     @abstractmethod
     def list_jobs(self) -> List[ModelInstallJob]:  # noqa D102
         """
@@ -421,32 +278,16 @@ class ModelInstallServiceBase(ABC):
         """Prune all completed and errored jobs."""
 
     @abstractmethod
-    def cancel_job(self, job: ModelInstallJob) -> None:
-        """Cancel the indicated job."""
-
-    @abstractmethod
-    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
-        """Wait for the indicated job to reach a terminal state.
-
-        This will block until the indicated install job has completed,
-        been cancelled, or errored out.
-
-        :param job: The job to wait on.
-        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
-        the job hasn't completed within the indicated time.
-        """
-
-    @abstractmethod
-    def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:
+    def wait_for_installs(self) -> List[ModelInstallJob]:
         """
         Wait for all pending installs to complete.
 
         This will block until all pending installs have
-        completed, been cancelled, or errored out.
+        completed, been cancelled, or errored out. It will
+        block indefinitely if one or more jobs are in the
+        paused state.
 
-        :param timeout: Wait up to indicated number of seconds. Raise an Exception('timeout') if
-        installs do not complete within the indicated time. A timeout of zero (the default)
-        will block indefinitely until the installs complete.
+        It will return the current list of jobs.
         """
 
     @abstractmethod
@@ -462,22 +303,3 @@ class ModelInstallServiceBase(ABC):
     @abstractmethod
     def sync_to_config(self) -> None:
         """Synchronize models on disk to those in the model record database."""
-
-    @abstractmethod
-    def download_and_cache(self, source: Union[str, AnyHttpUrl], access_token: Optional[str] = None) -> Path:
-        """
-        Download the model file located at source to the models cache and return its Path.
-
-        :param source: A Url or a string that can be converted into one.
-        :param access_token: Optional access token to access restricted resources.
-
-        The model file will be downloaded into the system-wide model cache
-        (`models/.cache`) if it isn't already there. Note that the model cache
-        is periodically cleared of infrequently-used entries when the model
-        converter runs.
-
-        Note that this doesn't automaticallly install or register the model, but is
-        intended for use by nodes that need access to models that aren't directly
-        supported by InvokeAI. The downloading process takes advantage of the download queue
-        to avoid interrupting other operations.
-        """

invokeai/app/services/model_install/model_install_default.py

@@ -1,71 +1,60 @@
 """Model installation class."""
 
-import os
-import re
 import threading
-import time
 from hashlib import sha256
+from logging import Logger
 from pathlib import Path
-from queue import Empty, Queue
+from queue import Queue
 from random import randbytes
 from shutil import copyfile, copytree, move, rmtree
-from tempfile import mkdtemp
 from typing import Any, Dict, List, Optional, Set, Union
 
-from huggingface_hub import HfFolder
-from pydantic.networks import AnyHttpUrl
-from requests import Session
-
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase, TqdmProgress
-from invokeai.app.services.events.events_base import EventServiceBase
-from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase
+from invokeai.app.services.events import EventServiceBase
+from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase, UnknownModelException
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
     InvalidModelConfigException,
-    ModelRepoVariant,
     ModelType,
 )
 from invokeai.backend.model_manager.hash import FastModelHash
-from invokeai.backend.model_manager.metadata import (
-    AnyModelRepoMetadata,
-    CivitaiMetadataFetch,
-    HuggingFaceMetadataFetch,
-    ModelMetadataWithFiles,
-    RemoteModelFile,
-)
 from invokeai.backend.model_manager.probe import ModelProbe
 from invokeai.backend.model_manager.search import ModelSearch
 from invokeai.backend.util import Chdir, InvokeAILogger
-from invokeai.backend.util.devices import choose_precision, choose_torch_device
 
 from .model_install_base import (
-    CivitaiModelSource,
-    HFModelSource,
     InstallStatus,
     LocalModelSource,
     ModelInstallJob,
     ModelInstallServiceBase,
     ModelSource,
-    StringLikeSource,
-    URLModelSource,
 )
 
-TMPDIR_PREFIX = "tmpinstall_"
+# marker that the queue is done and that thread should exit
+STOP_JOB = ModelInstallJob(
+    source=LocalModelSource(path="stop"),
+    local_path=Path("/dev/null"),
+)
 
 
 class ModelInstallService(ModelInstallServiceBase):
     """class for InvokeAI model installation."""
 
+    _app_config: InvokeAIAppConfig
+    _record_store: ModelRecordServiceBase
+    _event_bus: Optional[EventServiceBase] = None
+    _install_queue: Queue[ModelInstallJob]
+    _install_jobs: List[ModelInstallJob]
+    _logger: Logger
+    _cached_model_paths: Set[Path]
+    _models_installed: Set[str]
+
     def __init__(
         self,
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
-        download_queue: DownloadQueueServiceBase,
         event_bus: Optional[EventServiceBase] = None,
-        session: Optional[Session] = None,
     ):
         """
         Initialize the installer object.
@@ -78,20 +67,10 @@ class ModelInstallService(ModelInstallServiceBase):
         self._record_store = record_store
         self._event_bus = event_bus
         self._logger = InvokeAILogger.get_logger(name=self.__class__.__name__)
-        self._install_jobs: List[ModelInstallJob] = []
-        self._install_queue: Queue[ModelInstallJob] = Queue()
-        self._cached_model_paths: Set[Path] = set()
-        self._models_installed: Set[str] = set()
-        self._lock = threading.Lock()
-        self._stop_event = threading.Event()
-        self._downloads_changed_event = threading.Event()
-        self._install_completed_event = threading.Event()
-        self._download_queue = download_queue
-        self._download_cache: Dict[AnyHttpUrl, ModelInstallJob] = {}
-        self._running = False
-        self._session = session
-        self._next_job_id = 0
-        self._metadata_store = record_store.metadata_store  # for convenience
+        self._install_jobs = []
+        self._install_queue = Queue()
+        self._cached_model_paths = set()
+        self._models_installed = set()
 
     @property
     def app_config(self) -> InvokeAIAppConfig:  # noqa D102
@@ -105,31 +84,69 @@ class ModelInstallService(ModelInstallServiceBase):
     def event_bus(self) -> Optional[EventServiceBase]:  # noqa D102
         return self._event_bus
 
-    # make the invoker optional here because we don't need it and it
-    # makes the installer harder to use outside the web app
-    def start(self, invoker: Optional[Invoker] = None) -> None:
+    def start(self, *args: Any, **kwarg: Any) -> None:
         """Start the installer thread."""
-        with self._lock:
-            if self._running:
-                raise Exception("Attempt to start the installer service twice")
-            self._start_installer_thread()
-            self._remove_dangling_install_dirs()
-            self.sync_to_config()
+        self._start_installer_thread()
+        self.sync_to_config()
 
-    def stop(self, invoker: Optional[Invoker] = None) -> None:
+    def stop(self, *args: Any, **kwarg: Any) -> None:
         """Stop the installer thread; after this the object can be deleted and garbage collected."""
-        with self._lock:
-            if not self._running:
-                raise Exception("Attempt to stop the install service before it was started")
-            self._stop_event.set()
-            with self._install_queue.mutex:
-                self._install_queue.queue.clear()  # get rid of pending jobs
-            active_jobs = [x for x in self.list_jobs() if x.running]
-            if active_jobs:
-                self._logger.warning("Waiting for active install job to complete")
-            self.wait_for_installs()
-            self._download_cache.clear()
-            self._running = False
+        self._install_queue.put(STOP_JOB)
+
+    def _start_installer_thread(self) -> None:
+        threading.Thread(target=self._install_next_item, daemon=True).start()
+
+    def _install_next_item(self) -> None:
+        done = False
+        while not done:
+            job = self._install_queue.get()
+            if job == STOP_JOB:
+                done = True
+                continue
+
+            assert job.local_path is not None
+            try:
+                self._signal_job_running(job)
+                if job.inplace:
+                    key = self.register_path(job.local_path, job.config_in)
+                else:
+                    key = self.install_path(job.local_path, job.config_in)
+                job.config_out = self.record_store.get_model(key)
+                self._signal_job_completed(job)
+
+            except (OSError, DuplicateModelException, InvalidModelConfigException) as excp:
+                self._signal_job_errored(job, excp)
+            finally:
+                self._install_queue.task_done()
+        self._logger.info("Install thread exiting")
+
+    def _signal_job_running(self, job: ModelInstallJob) -> None:
+        job.status = InstallStatus.RUNNING
+        self._logger.info(f"{job.source}: model installation started")
+        if self._event_bus:
+            self._event_bus.emit_model_install_started(str(job.source))
+
+    def _signal_job_completed(self, job: ModelInstallJob) -> None:
+        job.status = InstallStatus.COMPLETED
+        assert job.config_out
+        self._logger.info(
+            f"{job.source}: model installation completed. {job.local_path} registered key {job.config_out.key}"
+        )
+        if self._event_bus:
+            assert job.local_path is not None
+            assert job.config_out is not None
+            key = job.config_out.key
+            self._event_bus.emit_model_install_completed(str(job.source), key)
+
+    def _signal_job_errored(self, job: ModelInstallJob, excp: Exception) -> None:
+        job.set_error(excp)
+        self._logger.info(f"{job.source}: model installation encountered an exception: {job.error_type}")
+        if self._event_bus:
+            error_type = job.error_type
+            error = job.error
+            assert error_type is not None
+            assert error is not None
+            self._event_bus.emit_model_install_error(str(job.source), error_type, error)
 
     def register_path(
         self,
@@ -138,7 +155,7 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if not config.get("source"):
+        if config.get("source") is None:
             config["source"] = model_path.resolve().as_posix()
         return self._register(model_path, config)
 
@@ -149,20 +166,13 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if not config.get("source"):
+        if config.get("source") is None:
             config["source"] = model_path.resolve().as_posix()
 
         info: AnyModelConfig = self._probe_model(Path(model_path), config)
-        old_hash = info.current_hash
-        dest_path = (
-            self.app_config.models_path / info.base.value / info.type.value / (config.get("name") or model_path.name)
-        )
-        try:
-            new_path = self._copy_model(model_path, dest_path)
-        except FileExistsError as excp:
-            raise DuplicateModelException(
-                f"A model named {model_path.name} is already installed at {dest_path.as_posix()}"
-            ) from excp
+        old_hash = info.original_hash
+        dest_path = self.app_config.models_path / info.base.value / info.type.value / model_path.name
+        new_path = self._copy_model(model_path, dest_path)
         new_hash = FastModelHash.hash(new_path)
         assert new_hash == old_hash, f"{model_path}: Model hash changed during installation, possibly corrupted."
 
@@ -172,100 +182,43 @@ class ModelInstallService(ModelInstallServiceBase):
             info,
         )
 
-    def heuristic_import(
+    def import_model(
         self,
-        source: str,
+        source: ModelSource,
         config: Optional[Dict[str, Any]] = None,
-        access_token: Optional[str] = None,
-    ) -> ModelInstallJob:
-        variants = "|".join(ModelRepoVariant.__members__.values())
-        hf_repoid_re = f"^([^/:]+/[^/:]+)(?::({variants})?(?::/?([^:]+))?)?$"
-        source_obj: Optional[StringLikeSource] = None
+    ) -> ModelInstallJob:  # noqa D102
+        if not config:
+            config = {}
 
-        if Path(source).exists():  # A local file or directory
-            source_obj = LocalModelSource(path=Path(source))
-        elif match := re.match(hf_repoid_re, source):
-            source_obj = HFModelSource(
-                repo_id=match.group(1),
-                variant=match.group(2) if match.group(2) else None,  # pass None rather than ''
-                subfolder=Path(match.group(3)) if match.group(3) else None,
-                access_token=access_token,
+        # Installing a local path
+        if isinstance(source, LocalModelSource) and Path(source.path).exists():  # a path that is already on disk
+            job = ModelInstallJob(
+                source=source,
+                config_in=config,
+                local_path=Path(source.path),
             )
-        elif re.match(r"^https?://[^/]+", source):
-            source_obj = URLModelSource(
-                url=AnyHttpUrl(source),
-                access_token=access_token,
-            )
-        else:
-            raise ValueError(f"Unsupported model source: '{source}'")
-        return self.import_model(source_obj, config)
+            self._install_jobs.append(job)
+            self._install_queue.put(job)
+            return job
 
-    def import_model(self, source: ModelSource, config: Optional[Dict[str, Any]] = None) -> ModelInstallJob:  # noqa D102
-        similar_jobs = [x for x in self.list_jobs() if x.source == source and not x.in_terminal_state]
-        if similar_jobs:
-            self._logger.warning(f"There is already an active install job for {source}. Not enqueuing.")
-            return similar_jobs[0]
-
-        if isinstance(source, LocalModelSource):
-            install_job = self._import_local_model(source, config)
-            self._install_queue.put(install_job)  # synchronously install
-        elif isinstance(source, CivitaiModelSource):
-            install_job = self._import_from_civitai(source, config)
-        elif isinstance(source, HFModelSource):
-            install_job = self._import_from_hf(source, config)
-        elif isinstance(source, URLModelSource):
-            install_job = self._import_from_url(source, config)
-        else:
-            raise ValueError(f"Unsupported model source: '{type(source)}'")
-
-        self._install_jobs.append(install_job)
-        return install_job
+        else:  # here is where we'd download a URL or repo_id. Implementation pending download queue.
+            raise UnknownModelException("File or directory not found")
 
     def list_jobs(self) -> List[ModelInstallJob]:  # noqa D102
         return self._install_jobs
 
-    def get_job_by_source(self, source: ModelSource) -> List[ModelInstallJob]:  # noqa D102
+    def get_job(self, source: ModelSource) -> List[ModelInstallJob]:  # noqa D102
         return [x for x in self._install_jobs if x.source == source]
 
-    def get_job_by_id(self, id: int) -> ModelInstallJob:  # noqa D102
-        jobs = [x for x in self._install_jobs if x.id == id]
-        if not jobs:
-            raise ValueError(f"No job with id {id} known")
-        assert len(jobs) == 1
-        assert isinstance(jobs[0], ModelInstallJob)
-        return jobs[0]
-
-    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
-        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
-        start = time.time()
-        while not job.in_terminal_state:
-            if self._install_completed_event.wait(timeout=5):  # in case we miss an event
-                self._install_completed_event.clear()
-            if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
-        return job
-
-    # TODO: Better name? Maybe wait_for_jobs()? Maybe too easily confused with above
-    def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:  # noqa D102
-        """Block until all installation jobs are done."""
-        start = time.time()
-        while len(self._download_cache) > 0:
-            if self._downloads_changed_event.wait(timeout=0.25):  # in case we miss an event
-                self._downloads_changed_event.clear()
-            if timeout > 0 and time.time() - start > timeout:
-                raise TimeoutError("Timeout exceeded")
+    def wait_for_installs(self) -> List[ModelInstallJob]:  # noqa D102
         self._install_queue.join()
         return self._install_jobs
 
-    def cancel_job(self, job: ModelInstallJob) -> None:
-        """Cancel the indicated job."""
-        job.cancel()
-        with self._lock:
-            self._cancel_download_parts(job)
-
     def prune_jobs(self) -> None:
         """Prune all completed and errored jobs."""
-        unfinished_jobs = [x for x in self._install_jobs if not x.in_terminal_state]
+        unfinished_jobs = [
+            x for x in self._install_jobs if x.status not in [InstallStatus.COMPLETED, InstallStatus.ERROR]
+        ]
         self._install_jobs = unfinished_jobs
 
     def sync_to_config(self) -> None:
@@ -281,142 +234,10 @@ class ModelInstallService(ModelInstallServiceBase):
         self._cached_model_paths = {Path(x.path) for x in self.record_store.all_models()}
         callback = self._scan_install if install else self._scan_register
         search = ModelSearch(on_model_found=callback)
-        self._models_installed.clear()
+        self._models_installed: Set[str] = set()
         search.search(scan_dir)
         return list(self._models_installed)
 
-    def unregister(self, key: str) -> None:  # noqa D102
-        self.record_store.del_model(key)
-
-    def delete(self, key: str) -> None:  # noqa D102
-        """Unregister the model. Delete its files only if they are within our models directory."""
-        model = self.record_store.get_model(key)
-        models_dir = self.app_config.models_path
-        model_path = models_dir / model.path
-        if model_path.is_relative_to(models_dir):
-            self.unconditionally_delete(key)
-        else:
-            self.unregister(key)
-
-    def unconditionally_delete(self, key: str) -> None:  # noqa D102
-        model = self.record_store.get_model(key)
-        path = self.app_config.models_path / model.path
-        if path.is_dir():
-            rmtree(path)
-        else:
-            path.unlink()
-        self.unregister(key)
-
-    def download_and_cache(
-        self,
-        source: Union[str, AnyHttpUrl],
-        access_token: Optional[str] = None,
-        timeout: int = 0,
-    ) -> Path:
-        """Download the model file located at source to the models cache and return its Path."""
-        model_hash = sha256(str(source).encode("utf-8")).hexdigest()[0:32]
-        model_path = self._app_config.models_convert_cache_path / model_hash
-
-        # We expect the cache directory to contain one and only one downloaded file.
-        # We don't know the file's name in advance, as it is set by the download
-        # content-disposition header.
-        if model_path.exists():
-            contents = [x for x in model_path.iterdir() if x.is_file()]
-            if len(contents) > 0:
-                return contents[0]
-
-        model_path.mkdir(parents=True, exist_ok=True)
-        job = self._download_queue.download(
-            source=AnyHttpUrl(str(source)),
-            dest=model_path,
-            access_token=access_token,
-            on_progress=TqdmProgress().update,
-        )
-        self._download_queue.wait_for_job(job, timeout)
-        if job.complete:
-            assert job.download_path is not None
-            return job.download_path
-        else:
-            raise Exception(job.error)
-
-    # --------------------------------------------------------------------------------------------
-    # Internal functions that manage the installer threads
-    # --------------------------------------------------------------------------------------------
-    def _start_installer_thread(self) -> None:
-        threading.Thread(target=self._install_next_item, daemon=True).start()
-        self._running = True
-
-    def _install_next_item(self) -> None:
-        done = False
-        while not done:
-            if self._stop_event.is_set():
-                done = True
-                continue
-            try:
-                job = self._install_queue.get(timeout=1)
-            except Empty:
-                continue
-
-            assert job.local_path is not None
-            try:
-                if job.cancelled:
-                    self._signal_job_cancelled(job)
-
-                elif job.errored:
-                    self._signal_job_errored(job)
-
-                elif (
-                    job.waiting or job.downloading
-                ):  # local jobs will be in waiting state, remote jobs will be downloading state
-                    job.total_bytes = self._stat_size(job.local_path)
-                    job.bytes = job.total_bytes
-                    self._signal_job_running(job)
-                    job.config_in["source"] = str(job.source)
-                    if job.inplace:
-                        key = self.register_path(job.local_path, job.config_in)
-                    else:
-                        key = self.install_path(job.local_path, job.config_in)
-                    job.config_out = self.record_store.get_model(key)
-
-                    # enter the metadata, if there is any
-                    if job.source_metadata:
-                        self._metadata_store.add_metadata(key, job.source_metadata)
-                    self._signal_job_completed(job)
-
-            except InvalidModelConfigException as excp:
-                if any(x.content_type is not None and "text/html" in x.content_type for x in job.download_parts):
-                    job.set_error(
-                        InvalidModelConfigException(
-                            f"At least one file in {job.local_path} is an HTML page, not a model. This can happen when an access token is required to download."
-                        )
-                    )
-                else:
-                    job.set_error(excp)
-                self._signal_job_errored(job)
-
-            except (OSError, DuplicateModelException) as excp:
-                job.set_error(excp)
-                self._signal_job_errored(job)
-
-            finally:
-                # if this is an install of a remote file, then clean up the temporary directory
-                if job._install_tmpdir is not None:
-                    rmtree(job._install_tmpdir)
-                self._install_completed_event.set()
-                self._install_queue.task_done()
-
-        self._logger.info("Install thread exiting")
-
-    # --------------------------------------------------------------------------------------------
-    # Internal functions that manage the models directory
-    # --------------------------------------------------------------------------------------------
-    def _remove_dangling_install_dirs(self) -> None:
-        """Remove leftover tmpdirs from aborted installs."""
-        path = self._app_config.models_path
-        for tmpdir in path.glob(f"{TMPDIR_PREFIX}*"):
-            self._logger.info(f"Removing dangling temporary directory {tmpdir}")
-            rmtree(tmpdir)
-
     def _scan_models_directory(self) -> None:
         """
         Scan the models directory for new and missing models.
@@ -499,6 +320,28 @@ class ModelInstallService(ModelInstallServiceBase):
             pass
         return True
 
+    def unregister(self, key: str) -> None:  # noqa D102
+        self.record_store.del_model(key)
+
+    def delete(self, key: str) -> None:  # noqa D102
+        """Unregister the model. Delete its files only if they are within our models directory."""
+        model = self.record_store.get_model(key)
+        models_dir = self.app_config.models_path
+        model_path = models_dir / model.path
+        if model_path.is_relative_to(models_dir):
+            self.unconditionally_delete(key)
+        else:
+            self.unregister(key)
+
+    def unconditionally_delete(self, key: str) -> None:  # noqa D102
+        model = self.record_store.get_model(key)
+        path = self.app_config.models_path / model.path
+        if path.is_dir():
+            rmtree(path)
+        else:
+            path.unlink()
+        self.unregister(key)
+
     def _copy_model(self, old_path: Path, new_path: Path) -> Path:
         if old_path == new_path:
             return old_path
@@ -554,292 +397,3 @@ class ModelInstallService(ModelInstallServiceBase):
             info.config = legacy_conf.relative_to(self.app_config.root_dir).as_posix()
         self.record_store.add_model(key, info)
         return key
-
-    def _next_id(self) -> int:
-        with self._lock:
-            id = self._next_job_id
-            self._next_job_id += 1
-        return id
-
-    @staticmethod
-    def _guess_variant() -> Optional[ModelRepoVariant]:
-        """Guess the best HuggingFace variant type to download."""
-        precision = choose_precision(choose_torch_device())
-        return ModelRepoVariant.FP16 if precision == "float16" else None
-
-    def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        return ModelInstallJob(
-            id=self._next_id(),
-            source=source,
-            config_in=config or {},
-            local_path=Path(source.path),
-            inplace=source.inplace,
-        )
-
-    def _import_from_civitai(self, source: CivitaiModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        if not source.access_token:
-            self._logger.info("No Civitai access token provided; some models may not be downloadable.")
-        metadata = CivitaiMetadataFetch(self._session).from_id(str(source.version_id))
-        assert isinstance(metadata, ModelMetadataWithFiles)
-        remote_files = metadata.download_urls(session=self._session)
-        return self._import_remote_model(source=source, config=config, metadata=metadata, remote_files=remote_files)
-
-    def _import_from_hf(self, source: HFModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        # Add user's cached access token to HuggingFace requests
-        source.access_token = source.access_token or HfFolder.get_token()
-        if not source.access_token:
-            self._logger.info("No HuggingFace access token present; some models may not be downloadable.")
-
-        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id, source.variant)
-        assert isinstance(metadata, ModelMetadataWithFiles)
-        remote_files = metadata.download_urls(
-            variant=source.variant or self._guess_variant(),
-            subfolder=source.subfolder,
-            session=self._session,
-        )
-
-        return self._import_remote_model(
-            source=source,
-            config=config,
-            remote_files=remote_files,
-            metadata=metadata,
-        )
-
-    def _import_from_url(self, source: URLModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        # URLs from Civitai or HuggingFace will be handled specially
-        url_patterns = {
-            r"^https?://civitai.com/": CivitaiMetadataFetch,
-            r"^https?://huggingface.co/[^/]+/[^/]+$": HuggingFaceMetadataFetch,
-        }
-        metadata = None
-        for pattern, fetcher in url_patterns.items():
-            if re.match(pattern, str(source.url), re.IGNORECASE):
-                metadata = fetcher(self._session).from_url(source.url)
-                break
-        self._logger.debug(f"metadata={metadata}")
-        if metadata and isinstance(metadata, ModelMetadataWithFiles):
-            remote_files = metadata.download_urls(session=self._session)
-        else:
-            remote_files = [RemoteModelFile(url=source.url, path=Path("."), size=0)]
-        return self._import_remote_model(
-            source=source,
-            config=config,
-            metadata=metadata,
-            remote_files=remote_files,
-        )
-
-    def _import_remote_model(
-        self,
-        source: ModelSource,
-        remote_files: List[RemoteModelFile],
-        metadata: Optional[AnyModelRepoMetadata],
-        config: Optional[Dict[str, Any]],
-    ) -> ModelInstallJob:
-        # TODO: Replace with tempfile.tmpdir() when multithreading is cleaned up.
-        # Currently the tmpdir isn't automatically removed at exit because it is
-        # being held in a daemon thread.
-        if len(remote_files) == 0:
-            raise ValueError(f"{source}: No downloadable files found")
-        tmpdir = Path(
-            mkdtemp(
-                dir=self._app_config.models_path,
-                prefix=TMPDIR_PREFIX,
-            )
-        )
-        install_job = ModelInstallJob(
-            id=self._next_id(),
-            source=source,
-            config_in=config or {},
-            source_metadata=metadata,
-            local_path=tmpdir,  # local path may change once the download has started due to content-disposition handling
-            bytes=0,
-            total_bytes=0,
-        )
-        # In the event that there is a subfolder specified in the source,
-        # we need to remove it from the destination path in order to avoid
-        # creating unwanted subfolders
-        if hasattr(source, "subfolder") and source.subfolder:
-            root = Path(remote_files[0].path.parts[0])
-            subfolder = root / source.subfolder
-        else:
-            root = Path(".")
-            subfolder = Path(".")
-
-        # we remember the path up to the top of the tmpdir so that it may be
-        # removed safely at the end of the install process.
-        install_job._install_tmpdir = tmpdir
-        assert install_job.total_bytes is not None  # to avoid type checking complaints in the loop below
-
-        self._logger.info(f"Queuing {source} for downloading")
-        self._logger.debug(f"remote_files={remote_files}")
-        for model_file in remote_files:
-            url = model_file.url
-            path = root / model_file.path.relative_to(subfolder)
-            self._logger.info(f"Downloading {url} => {path}")
-            install_job.total_bytes += model_file.size
-            assert hasattr(source, "access_token")
-            dest = tmpdir / path.parent
-            dest.mkdir(parents=True, exist_ok=True)
-            download_job = DownloadJob(
-                source=url,
-                dest=dest,
-                access_token=source.access_token,
-            )
-            self._download_cache[download_job.source] = install_job  # matches a download job to an install job
-            install_job.download_parts.add(download_job)
-
-            self._download_queue.submit_download_job(
-                download_job,
-                on_start=self._download_started_callback,
-                on_progress=self._download_progress_callback,
-                on_complete=self._download_complete_callback,
-                on_error=self._download_error_callback,
-                on_cancelled=self._download_cancelled_callback,
-            )
-        return install_job
-
-    def _stat_size(self, path: Path) -> int:
-        size = 0
-        if path.is_file():
-            size = path.stat().st_size
-        elif path.is_dir():
-            for root, _, files in os.walk(path):
-                size += sum(self._stat_size(Path(root, x)) for x in files)
-        return size
-
-    # ------------------------------------------------------------------
-    # Callbacks are executed by the download queue in a separate thread
-    # ------------------------------------------------------------------
-    def _download_started_callback(self, download_job: DownloadJob) -> None:
-        self._logger.info(f"{download_job.source}: model download started")
-        with self._lock:
-            install_job = self._download_cache[download_job.source]
-            install_job.status = InstallStatus.DOWNLOADING
-
-            assert download_job.download_path
-            if install_job.local_path == install_job._install_tmpdir:
-                partial_path = download_job.download_path.relative_to(install_job._install_tmpdir)
-                dest_name = partial_path.parts[0]
-                install_job.local_path = install_job._install_tmpdir / dest_name
-
-            # Update the total bytes count for remote sources.
-            if not install_job.total_bytes:
-                install_job.total_bytes = sum(x.total_bytes for x in install_job.download_parts)
-
-    def _download_progress_callback(self, download_job: DownloadJob) -> None:
-        with self._lock:
-            install_job = self._download_cache[download_job.source]
-            if install_job.cancelled:  # This catches the case in which the caller directly calls job.cancel()
-                self._cancel_download_parts(install_job)
-            else:
-                # update sizes
-                install_job.bytes = sum(x.bytes for x in install_job.download_parts)
-                self._signal_job_downloading(install_job)
-
-    def _download_complete_callback(self, download_job: DownloadJob) -> None:
-        with self._lock:
-            install_job = self._download_cache[download_job.source]
-            self._download_cache.pop(download_job.source, None)
-
-            # are there any more active jobs left in this task?
-            if all(x.complete for x in install_job.download_parts):
-                #  now enqueue job for actual installation into the models directory
-                self._install_queue.put(install_job)
-
-            # Let other threads know that the number of downloads has changed
-            self._downloads_changed_event.set()
-
-    def _download_error_callback(self, download_job: DownloadJob, excp: Optional[Exception] = None) -> None:
-        with self._lock:
-            install_job = self._download_cache.pop(download_job.source, None)
-            assert install_job is not None
-            assert excp is not None
-            install_job.set_error(excp)
-            self._logger.error(
-                f"Cancelling {install_job.source} due to an error while downloading {download_job.source}: {str(excp)}"
-            )
-            self._cancel_download_parts(install_job)
-
-            # Let other threads know that the number of downloads has changed
-            self._downloads_changed_event.set()
-
-    def _download_cancelled_callback(self, download_job: DownloadJob) -> None:
-        with self._lock:
-            install_job = self._download_cache.pop(download_job.source, None)
-            if not install_job:
-                return
-            self._downloads_changed_event.set()
-            self._logger.warning(f"Download {download_job.source} cancelled.")
-            # if install job has already registered an error, then do not replace its status with cancelled
-            if not install_job.errored:
-                install_job.cancel()
-            self._cancel_download_parts(install_job)
-
-            # Let other threads know that the number of downloads has changed
-            self._downloads_changed_event.set()
-
-    def _cancel_download_parts(self, install_job: ModelInstallJob) -> None:
-        # on multipart downloads, _cancel_components() will get called repeatedly from the download callbacks
-        # do not lock here because it gets called within a locked context
-        for s in install_job.download_parts:
-            self._download_queue.cancel_job(s)
-
-        if all(x.in_terminal_state for x in install_job.download_parts):
-            # When all parts have reached their terminal state, we finalize the job to clean up the temporary directory and other resources
-            self._install_queue.put(install_job)
-
-    # ------------------------------------------------------------------------------------------------
-    # Internal methods that put events on the event bus
-    # ------------------------------------------------------------------------------------------------
-    def _signal_job_running(self, job: ModelInstallJob) -> None:
-        job.status = InstallStatus.RUNNING
-        self._logger.info(f"{job.source}: model installation started")
-        if self._event_bus:
-            self._event_bus.emit_model_install_running(str(job.source))
-
-    def _signal_job_downloading(self, job: ModelInstallJob) -> None:
-        if self._event_bus:
-            parts: List[Dict[str, str | int]] = [
-                {
-                    "url": str(x.source),
-                    "local_path": str(x.download_path),
-                    "bytes": x.bytes,
-                    "total_bytes": x.total_bytes,
-                }
-                for x in job.download_parts
-            ]
-            assert job.bytes is not None
-            assert job.total_bytes is not None
-            self._event_bus.emit_model_install_downloading(
-                str(job.source),
-                local_path=job.local_path.as_posix(),
-                parts=parts,
-                bytes=job.bytes,
-                total_bytes=job.total_bytes,
-            )
-
-    def _signal_job_completed(self, job: ModelInstallJob) -> None:
-        job.status = InstallStatus.COMPLETED
-        assert job.config_out
-        self._logger.info(
-            f"{job.source}: model installation completed. {job.local_path} registered key {job.config_out.key}"
-        )
-        if self._event_bus:
-            assert job.local_path is not None
-            assert job.config_out is not None
-            key = job.config_out.key
-            self._event_bus.emit_model_install_completed(str(job.source), key)
-
-    def _signal_job_errored(self, job: ModelInstallJob) -> None:
-        self._logger.info(f"{job.source}: model installation encountered an exception: {job.error_type}\n{job.error}")
-        if self._event_bus:
-            error_type = job.error_type
-            error = job.error
-            assert error_type is not None
-            assert error is not None
-            self._event_bus.emit_model_install_error(str(job.source), error_type, error)
-
-    def _signal_job_cancelled(self, job: ModelInstallJob) -> None:
-        self._logger.info(f"{job.source}: model installation was cancelled")
-        if self._event_bus:
-            self._event_bus.emit_model_install_cancelled(str(job.source))

invokeai/app/services/model_load/__init__.py

@@ -1,6 +0,0 @@
-"""Initialization file for model load service module."""
-
-from .model_load_base import ModelLoadServiceBase
-from .model_load_default import ModelLoadService
-
-__all__ = ["ModelLoadServiceBase", "ModelLoadService"]

invokeai/app/services/model_load/model_load_base.py

@@ -1,40 +0,0 @@
-# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
-"""Base class for model loader."""
-
-from abc import ABC, abstractmethod
-from typing import Optional
-
-from invokeai.app.invocations.baseinvocation import InvocationContext
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
-from invokeai.backend.model_manager.load import LoadedModel
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
-from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
-
-
-class ModelLoadServiceBase(ABC):
-    """Wrapper around AnyModelLoader."""
-
-    @abstractmethod
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> LoadedModel:
-        """
-        Given a model's configuration, load it and return the LoadedModel object.
-
-        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
-        :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context: Invocation context used for event reporting
-        """
-
-    @property
-    @abstractmethod
-    def ram_cache(self) -> ModelCacheBase[AnyModel]:
-        """Return the RAM cache used by this loader."""
-
-    @property
-    @abstractmethod
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""

invokeai/app/services/model_load/model_load_default.py

@@ -1,106 +0,0 @@
-# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
-"""Implementation of model loader service."""
-
-from typing import Optional, Type
-
-from invokeai.app.invocations.baseinvocation import InvocationContext
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
-from invokeai.backend.model_manager.load import LoadedModel, ModelLoaderRegistry, ModelLoaderRegistryBase
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
-from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
-from invokeai.backend.util.logging import InvokeAILogger
-
-from .model_load_base import ModelLoadServiceBase
-
-
-class ModelLoadService(ModelLoadServiceBase):
-    """Wrapper around ModelLoaderRegistry."""
-
-    def __init__(
-        self,
-        app_config: InvokeAIAppConfig,
-        ram_cache: ModelCacheBase[AnyModel],
-        convert_cache: ModelConvertCacheBase,
-        registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
-    ):
-        """Initialize the model load service."""
-        logger = InvokeAILogger.get_logger(self.__class__.__name__)
-        logger.setLevel(app_config.log_level.upper())
-        self._logger = logger
-        self._app_config = app_config
-        self._ram_cache = ram_cache
-        self._convert_cache = convert_cache
-        self._registry = registry
-
-    @property
-    def ram_cache(self) -> ModelCacheBase[AnyModel]:
-        """Return the RAM cache used by this loader."""
-        return self._ram_cache
-
-    @property
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""
-        return self._convert_cache
-
-    def load_model(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> LoadedModel:
-        """
-        Given a model's configuration, load it and return the LoadedModel object.
-
-        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
-        :param submodel: For main (pipeline models), the submodel to fetch.
-        :param context: Invocation context used for event reporting
-        """
-        if context:
-            self._emit_load_event(
-                context=context,
-                model_config=model_config,
-            )
-
-        implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
-        loaded_model: LoadedModel = implementation(
-            app_config=self._app_config,
-            logger=self._logger,
-            ram_cache=self._ram_cache,
-            convert_cache=self._convert_cache,
-        ).load_model(model_config, submodel_type)
-
-        if context:
-            self._emit_load_event(
-                context=context,
-                model_config=model_config,
-                loaded=True,
-            )
-        return loaded_model
-
-    def _emit_load_event(
-        self,
-        context: InvocationContext,
-        model_config: AnyModelConfig,
-        loaded: Optional[bool] = False,
-    ) -> None:
-        if context.services.queue.is_canceled(context.graph_execution_state_id):
-            raise CanceledException()
-
-        if not loaded:
-            context.services.events.emit_model_load_started(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
-                model_config=model_config,
-            )
-        else:
-            context.services.events.emit_model_load_completed(
-                queue_id=context.queue_id,
-                queue_item_id=context.queue_item_id,
-                queue_batch_id=context.queue_batch_id,
-                graph_execution_state_id=context.graph_execution_state_id,
-                model_config=model_config,
-            )

invokeai/app/services/model_manager/__init__.py

@@ -1,17 +1 @@
-"""Initialization file for model manager service."""
-
-from invokeai.backend.model_manager import AnyModel, AnyModelConfig, BaseModelType, ModelType, SubModelType
-from invokeai.backend.model_manager.load import LoadedModel
-
-from .model_manager_default import ModelManagerService, ModelManagerServiceBase
-
-__all__ = [
-    "ModelManagerServiceBase",
-    "ModelManagerService",
-    "AnyModel",
-    "AnyModelConfig",
-    "BaseModelType",
-    "ModelType",
-    "SubModelType",
-    "LoadedModel",
-]
+from .model_manager_default import ModelManagerService  # noqa F401

invokeai/app/services/model_manager/model_manager_base.py

@@ -1,67 +1,286 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
+from logging import Logger
+from pathlib import Path
+from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
 
-from typing_extensions import Self
+from pydantic import Field
 
-from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.backend.model_management import (
+    AddModelResult,
+    BaseModelType,
+    MergeInterpolationMethod,
+    ModelInfo,
+    ModelType,
+    SchedulerPredictionType,
+    SubModelType,
+)
+from invokeai.backend.model_management.model_cache import CacheStats
 
-from ..config import InvokeAIAppConfig
-from ..download import DownloadQueueServiceBase
-from ..events.events_base import EventServiceBase
-from ..model_install import ModelInstallServiceBase
-from ..model_load import ModelLoadServiceBase
-from ..model_records import ModelRecordServiceBase
-from ..shared.sqlite.sqlite_database import SqliteDatabase
+if TYPE_CHECKING:
+    from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext
 
 
 class ModelManagerServiceBase(ABC):
-    """Abstract base class for the model manager service."""
+    """Responsible for managing models on disk and in memory"""
 
-    # attributes:
-    # store: ModelRecordServiceBase = Field(description="An instance of the model record configuration service.")
-    # install: ModelInstallServiceBase = Field(description="An instance of the model install service.")
-    # load: ModelLoadServiceBase = Field(description="An instance of the model load service.")
-
-    @classmethod
     @abstractmethod
-    def build_model_manager(
-        cls,
-        app_config: InvokeAIAppConfig,
-        db: SqliteDatabase,
-        download_queue: DownloadQueueServiceBase,
-        events: EventServiceBase,
-    ) -> Self:
+    def __init__(
+        self,
+        config: InvokeAIAppConfig,
+        logger: Logger,
+    ):
         """
-        Construct the model manager service instance.
-
-        Use it rather than the __init__ constructor. This class
-        method simplifies the construction considerably.
+        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
 
-    @property
     @abstractmethod
-    def store(self) -> ModelRecordServiceBase:
-        """Return the ModelRecordServiceBase used to store and retrieve configuration records."""
+    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 load(self) -> ModelLoadServiceBase:
-        """Return the ModelLoadServiceBase used to load models from their configuration records."""
-        pass
-
-    @property
-    @abstractmethod
-    def install(self) -> ModelInstallServiceBase:
-        """Return the ModelInstallServiceBase used to download and manipulate model files."""
+    def logger(self):
         pass
 
     @abstractmethod
-    def start(self, invoker: Invoker) -> None:
+    def model_exists(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+    ) -> bool:
         pass
 
     @abstractmethod
-    def stop(self, invoker: Invoker) -> None:
+    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
+        ModelNotFoundException 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 rename_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        new_name: str,
+    ):
+        """
+        Rename the indicated model.
+        """
+        pass
+
+    @abstractmethod
+    def list_checkpoint_configs(self) -> List[Path]:
+        """
+        List the checkpoint config paths from ROOT/configs/stable-diffusion.
+        """
+        pass
+
+    @abstractmethod
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Literal[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_length=2, max_length=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,
+        merge_dest_directory: Optional[Path] = None,
+    ) -> 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)
+        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
+        """
+        pass
+
+    @abstractmethod
+    def search_for_models(self, directory: Path) -> List[Path]:
+        """
+        Return list of all models found in the designated directory.
+        """
+        pass
+
+    @abstractmethod
+    def sync_to_config(self):
+        """
+        Re-read models.yaml, rescan the models directory, and reimport models
+        in the autoimport directories. Call after making changes outside the
+        model manager API.
+        """
+        pass
+
+    @abstractmethod
+    def collect_cache_stats(self, cache_stats: CacheStats):
+        """
+        Reset model cache statistics for graph with graph_id.
+        """
+        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

invokeai/app/services/model_manager/model_manager_default.py

@@ -1,149 +1,413 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
-"""Implementation of ModelManagerServiceBase."""
 
-from typing import Optional
+from __future__ import annotations
 
-from typing_extensions import Self
+from logging import Logger
+from pathlib import Path
+from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
 
-from invokeai.app.invocations.baseinvocation import InvocationContext
-from invokeai.app.services.invoker import Invoker
-from invokeai.backend.model_manager import AnyModelConfig, BaseModelType, LoadedModel, ModelType, SubModelType
-from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
-from invokeai.backend.util.logging import InvokeAILogger
+import torch
+from pydantic import Field
+
+from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
+from invokeai.backend.model_management import (
+    AddModelResult,
+    BaseModelType,
+    MergeInterpolationMethod,
+    ModelInfo,
+    ModelManager,
+    ModelMerger,
+    ModelNotFoundException,
+    ModelType,
+    SchedulerPredictionType,
+    SubModelType,
+)
+from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.backend.model_management.model_search import FindModels
+from invokeai.backend.util import choose_precision, choose_torch_device
 
-from ..config import InvokeAIAppConfig
-from ..download import DownloadQueueServiceBase
-from ..events.events_base import EventServiceBase
-from ..model_install import ModelInstallService, ModelInstallServiceBase
-from ..model_load import ModelLoadService, ModelLoadServiceBase
-from ..model_records import ModelRecordServiceBase, UnknownModelException
 from .model_manager_base import ModelManagerServiceBase
 
+if TYPE_CHECKING:
+    from invokeai.app.invocations.baseinvocation import InvocationContext
 
+
+# simple implementation
 class ModelManagerService(ModelManagerServiceBase):
-    """
-    The ModelManagerService handles various aspects of model installation, maintenance and loading.
-
-    It bundles three distinct services:
-    model_manager.store   -- Routines to manage the database of model configuration records.
-    model_manager.install -- Routines to install, move and delete models.
-    model_manager.load    -- Routines to load models into memory.
-    """
+    """Responsible for managing models on disk and in memory"""
 
     def __init__(
         self,
-        store: ModelRecordServiceBase,
-        install: ModelInstallServiceBase,
-        load: ModelLoadServiceBase,
+        config: InvokeAIAppConfig,
+        logger: Logger,
     ):
-        self._store = store
-        self._install = install
-        self._load = load
+        """
+        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"
 
-    @property
-    def store(self) -> ModelRecordServiceBase:
-        return self._store
+        logger.debug(f"Config file={config_file}")
 
-    @property
-    def install(self) -> ModelInstallServiceBase:
-        return self._install
+        device = torch.device(choose_torch_device())
+        device_name = torch.cuda.get_device_name() if device == torch.device("cuda") else ""
+        logger.info(f"GPU device = {device} {device_name}")
 
-    @property
-    def load(self) -> ModelLoadServiceBase:
-        return self._load
+        precision = config.precision
+        if precision == "auto":
+            precision = choose_precision(device)
+        dtype = torch.float32 if precision == "float32" else torch.float16
 
-    def start(self, invoker: Invoker) -> None:
-        for service in [self._store, self._install, self._load]:
-            if hasattr(service, "start"):
-                service.start(invoker)
+        # 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 `ram_cache_size` config setting
+        max_cache_size = config.ram_cache_size
 
-    def stop(self, invoker: Invoker) -> None:
-        for service in [self._store, self._install, self._load]:
-            if hasattr(service, "stop"):
-                service.stop(invoker)
+        logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
 
-    def load_model_by_config(
-        self,
-        model_config: AnyModelConfig,
-        submodel_type: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> LoadedModel:
-        return self.load.load_model(model_config, submodel_type, context)
+        sequential_offload = config.sequential_guidance
 
-    def load_model_by_key(
-        self,
-        key: str,
-        submodel_type: Optional[SubModelType] = None,
-        context: Optional[InvocationContext] = None,
-    ) -> LoadedModel:
-        config = self.store.get_model(key)
-        return self.load.load_model(config, submodel_type, context)
+        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 load_model_by_attr(
+    def get_model(
         self,
         model_name: str,
         base_model: BaseModelType,
         model_type: ModelType,
         submodel: Optional[SubModelType] = None,
         context: Optional[InvocationContext] = None,
-    ) -> LoadedModel:
+    ) -> ModelInfo:
         """
-        Given a model's attributes, search the database for it, and if found, load and return the LoadedModel object.
-
-        This is provided for API compatability with the get_model() method
-        in the original model manager. However, note that LoadedModel is
-        not the same as the original ModelInfo that ws returned.
-
-        :param model_name: Name of to be fetched.
-        :param base_model: Base model
-        :param model_type: Type of the model
-        :param submodel: For main (pipeline models), the submodel to fetch
-        :param context: The invocation context.
-
-        Exceptions: UnknownModelException -- model with this key not known
-                    NotImplementedException -- a model loader was not provided at initialization time
-                    ValueError -- more than one model matches this combination
+        Retrieve the indicated model. submodel can be used to get a
+        part (such as the vae) of a diffusers mode.
         """
-        configs = self.store.search_by_attr(model_name, base_model, model_type)
-        if len(configs) == 0:
-            raise UnknownModelException(f"{base_model}/{model_type}/{model_name}: Unknown model")
-        elif len(configs) > 1:
-            raise ValueError(f"{base_model}/{model_type}/{model_name}: More than one model matches.")
+
+        # we can emit model loading events if we are executing with access to the invocation context
+        if context:
+            self._emit_load_event(
+                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 context:
+            self._emit_load_event(
+                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) -> Union[dict, None]:
+        """
+        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) -> Union[dict, None]:
+        """
+        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,
+    ) -> 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.
+        """
+        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
+        ModelNotFoundException 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 ModelNotFoundException(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.
+        """
+        self.logger.debug(f"delete model {model_name}")
+        self.mgr.del_model(model_name, base_model, model_type)
+        self.mgr.commit()
+
+    def convert_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: Literal[ModelType.Main, ModelType.Vae],
+        convert_dest_directory: Optional[Path] = Field(
+            default=None, description="Optional directory location for merged model"
+        ),
+    ) -> 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']
+        :param convert_dest_directory: Save the converted model to the designated directory (`models/etc/etc` by default)
+
+        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, convert_dest_directory)
+
+    def collect_cache_stats(self, cache_stats: CacheStats):
+        """
+        Reset model cache statistics for graph with graph_id.
+        """
+        self.mgr.cache.stats = cache_stats
+
+    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,
+        context: InvocationContext,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        submodel: Optional[SubModelType] = None,
+        model_info: Optional[ModelInfo] = None,
+    ):
+        if context.services.queue.is_canceled(context.graph_execution_state_id):
+            raise CanceledException()
+
+        if model_info:
+            context.services.events.emit_model_load_completed(
+                queue_id=context.queue_id,
+                queue_item_id=context.queue_item_id,
+                queue_batch_id=context.queue_batch_id,
+                graph_execution_state_id=context.graph_execution_state_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+                model_info=model_info,
+            )
         else:
-            return self.load.load_model(configs[0], submodel, context)
+            context.services.events.emit_model_load_started(
+                queue_id=context.queue_id,
+                queue_item_id=context.queue_item_id,
+                queue_batch_id=context.queue_batch_id,
+                graph_execution_state_id=context.graph_execution_state_id,
+                model_name=model_name,
+                base_model=base_model,
+                model_type=model_type,
+                submodel=submodel,
+            )
 
-    @classmethod
-    def build_model_manager(
-        cls,
-        app_config: InvokeAIAppConfig,
-        model_record_service: ModelRecordServiceBase,
-        download_queue: DownloadQueueServiceBase,
-        events: EventServiceBase,
-    ) -> Self:
+    @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.
         """
-        Construct the model manager service instance.
+        return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
 
-        For simplicity, use this class method rather than the __init__ constructor.
+    def merge_models(
+        self,
+        model_names: List[str] = Field(
+            default=None, min_length=2, max_length=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: float = 0.5,
+        interp: Optional[MergeInterpolationMethod] = None,
+        force: bool = False,
+        merge_dest_directory: Optional[Path] = Field(
+            default=None, description="Optional directory location for merged model"
+        ),
+    ) -> AddModelResult:
         """
-        logger = InvokeAILogger.get_logger(cls.__name__)
-        logger.setLevel(app_config.log_level.upper())
+        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)
+        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
+        """
+        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,
+                merge_dest_directory=merge_dest_directory,
+            )
+        except AssertionError as e:
+            raise ValueError(e)
+        return result
 
-        ram_cache = ModelCache(
-            max_cache_size=app_config.ram_cache_size, max_vram_cache_size=app_config.vram_cache_size, logger=logger
+    def search_for_models(self, directory: Path) -> List[Path]:
+        """
+        Return list of all models found in the designated directory.
+        """
+        search = FindModels([directory], self.logger)
+        return search.list_models()
+
+    def sync_to_config(self):
+        """
+        Re-read models.yaml, rescan the models directory, and reimport models
+        in the autoimport directories. Call after making changes outside the
+        model manager API.
+        """
+        return self.mgr.sync_to_config()
+
+    def list_checkpoint_configs(self) -> List[Path]:
+        """
+        List the checkpoint config paths from ROOT/configs/stable-diffusion.
+        """
+        config = self.mgr.app_config
+        conf_path = config.legacy_conf_path
+        root_path = config.root_path
+        return [(conf_path / x).relative_to(root_path) for x in conf_path.glob("**/*.yaml")]
+
+    def rename_model(
+        self,
+        model_name: str,
+        base_model: BaseModelType,
+        model_type: ModelType,
+        new_name: Optional[str] = None,
+        new_base: Optional[BaseModelType] = None,
+    ):
+        """
+        Rename the indicated model. Can provide a new name and/or a new base.
+        :param model_name: Current name of the model
+        :param base_model: Current base of the model
+        :param model_type: Model type (can't be changed)
+        :param new_name: New name for the model
+        :param new_base: New base for the model
+        """
+        self.mgr.rename_model(
+            base_model=base_model,
+            model_type=model_type,
+            model_name=model_name,
+            new_name=new_name,
+            new_base=new_base,
         )
-        convert_cache = ModelConvertCache(
-            cache_path=app_config.models_convert_cache_path, max_size=app_config.convert_cache_size
-        )
-        loader = ModelLoadService(
-            app_config=app_config,
-            ram_cache=ram_cache,
-            convert_cache=convert_cache,
-            registry=ModelLoaderRegistry,
-        )
-        installer = ModelInstallService(
-            app_config=app_config,
-            record_store=model_record_service,
-            download_queue=download_queue,
-            event_bus=events,
-        )
-        return cls(store=model_record_service, install=installer, load=loader)

invokeai/app/services/model_metadata/__init__.py

@@ -1,9 +0,0 @@
-"""Init file for ModelMetadataStoreService module."""
-
-from .metadata_store_base import ModelMetadataStoreBase
-from .metadata_store_sql import ModelMetadataStoreSQL
-
-__all__ = [
-    "ModelMetadataStoreBase",
-    "ModelMetadataStoreSQL",
-]

invokeai/app/services/model_metadata/metadata_store_base.py

@@ -1,65 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
-"""
-Storage for Model Metadata
-"""
-
-from abc import ABC, abstractmethod
-from typing import List, Set, Tuple
-
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-
-class ModelMetadataStoreBase(ABC):
-    """Store, search and fetch model metadata retrieved from remote repositories."""
-
-    @abstractmethod
-    def add_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> None:
-        """
-        Add a block of repo metadata to a model record.
-
-        The model record config must already exist in the database with the
-        same key. Otherwise a FOREIGN KEY constraint exception will be raised.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to store
-        """
-
-    @abstractmethod
-    def get_metadata(self, model_key: str) -> AnyModelRepoMetadata:
-        """Retrieve the ModelRepoMetadata corresponding to model key."""
-
-    @abstractmethod
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:  # key, metadata
-        """Dump out all the metadata."""
-
-    @abstractmethod
-    def update_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> AnyModelRepoMetadata:
-        """
-        Update metadata corresponding to the model with the indicated key.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to update
-        """
-
-    @abstractmethod
-    def list_tags(self) -> Set[str]:
-        """Return all tags in the tags table."""
-
-    @abstractmethod
-    def search_by_tag(self, tags: Set[str]) -> Set[str]:
-        """Return the keys of models containing all of the listed tags."""
-
-    @abstractmethod
-    def search_by_author(self, author: str) -> Set[str]:
-        """Return the keys of models authored by the indicated author."""
-
-    @abstractmethod
-    def search_by_name(self, name: str) -> Set[str]:
-        """
-        Return the keys of models with the indicated name.
-
-        Note that this is the name of the model given to it by
-        the remote source. The user may have changed the local
-        name. The local name will be located in the model config
-        record object.
-        """

invokeai/app/services/model_metadata/metadata_store_sql.py

@@ -1,222 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Development Team
-"""
-SQL Storage for Model Metadata
-"""
-
-import sqlite3
-from typing import List, Optional, Set, Tuple
-
-from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, UnknownMetadataException
-from invokeai.backend.model_manager.metadata.fetch import ModelMetadataFetchBase
-
-from .metadata_store_base import ModelMetadataStoreBase
-
-
-class ModelMetadataStoreSQL(ModelMetadataStoreBase):
-    """Store, search and fetch model metadata retrieved from remote repositories."""
-
-    def __init__(self, db: SqliteDatabase):
-        """
-        Initialize a new object from preexisting sqlite3 connection and threading lock objects.
-
-        :param conn: sqlite3 connection object
-        :param lock: threading Lock object
-        """
-        super().__init__()
-        self._db = db
-        self._cursor = self._db.conn.cursor()
-
-    def add_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> None:
-        """
-        Add a block of repo metadata to a model record.
-
-        The model record config must already exist in the database with the
-        same key. Otherwise a FOREIGN KEY constraint exception will be raised.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to store
-        """
-        json_serialized = metadata.model_dump_json()
-        with self._db.lock:
-            try:
-                self._cursor.execute(
-                    """--sql
-                    INSERT INTO model_metadata(
-                       id,
-                       metadata
-                    )
-                    VALUES (?,?);
-                    """,
-                    (
-                        model_key,
-                        json_serialized,
-                    ),
-                )
-                self._update_tags(model_key, metadata.tags)
-                self._db.conn.commit()
-            except sqlite3.IntegrityError as excp:  # FOREIGN KEY error: the key was not in model_config table
-                self._db.conn.rollback()
-                raise UnknownMetadataException from excp
-            except sqlite3.Error as excp:
-                self._db.conn.rollback()
-                raise excp
-
-    def get_metadata(self, model_key: str) -> AnyModelRepoMetadata:
-        """Retrieve the ModelRepoMetadata corresponding to model key."""
-        with self._db.lock:
-            self._cursor.execute(
-                """--sql
-                SELECT metadata FROM model_metadata
-                WHERE id=?;
-                """,
-                (model_key,),
-            )
-            rows = self._cursor.fetchone()
-            if not rows:
-                raise UnknownMetadataException("model metadata not found")
-            return ModelMetadataFetchBase.from_json(rows[0])
-
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:  # key, metadata
-        """Dump out all the metadata."""
-        with self._db.lock:
-            self._cursor.execute(
-                """--sql
-                SELECT id,metadata FROM model_metadata;
-                """,
-                (),
-            )
-            rows = self._cursor.fetchall()
-        return [(x[0], ModelMetadataFetchBase.from_json(x[1])) for x in rows]
-
-    def update_metadata(self, model_key: str, metadata: AnyModelRepoMetadata) -> AnyModelRepoMetadata:
-        """
-        Update metadata corresponding to the model with the indicated key.
-
-        :param model_key: Existing model key in the `model_config` table
-        :param metadata: ModelRepoMetadata object to update
-        """
-        json_serialized = metadata.model_dump_json()  # turn it into a json string.
-        with self._db.lock:
-            try:
-                self._cursor.execute(
-                    """--sql
-                    UPDATE model_metadata
-                    SET
-                        metadata=?
-                    WHERE id=?;
-                    """,
-                    (json_serialized, model_key),
-                )
-                if self._cursor.rowcount == 0:
-                    raise UnknownMetadataException("model metadata not found")
-                self._update_tags(model_key, metadata.tags)
-                self._db.conn.commit()
-            except sqlite3.Error as e:
-                self._db.conn.rollback()
-                raise e
-
-        return self.get_metadata(model_key)
-
-    def list_tags(self) -> Set[str]:
-        """Return all tags in the tags table."""
-        self._cursor.execute(
-            """--sql
-            select tag_text from tags;
-            """
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def search_by_tag(self, tags: Set[str]) -> Set[str]:
-        """Return the keys of models containing all of the listed tags."""
-        with self._db.lock:
-            try:
-                matches: Optional[Set[str]] = None
-                for tag in tags:
-                    self._cursor.execute(
-                        """--sql
-                        SELECT a.model_id FROM model_tags AS a,
-                                                     tags AS b
-                        WHERE a.tag_id=b.tag_id
-                          AND b.tag_text=?;
-                        """,
-                        (tag,),
-                    )
-                    model_keys = {x[0] for x in self._cursor.fetchall()}
-                    if matches is None:
-                        matches = model_keys
-                    matches = matches.intersection(model_keys)
-            except sqlite3.Error as e:
-                raise e
-        return matches if matches else set()
-
-    def search_by_author(self, author: str) -> Set[str]:
-        """Return the keys of models authored by the indicated author."""
-        self._cursor.execute(
-            """--sql
-            SELECT id FROM model_metadata
-            WHERE author=?;
-            """,
-            (author,),
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def search_by_name(self, name: str) -> Set[str]:
-        """
-        Return the keys of models with the indicated name.
-
-        Note that this is the name of the model given to it by
-        the remote source. The user may have changed the local
-        name. The local name will be located in the model config
-        record object.
-        """
-        self._cursor.execute(
-            """--sql
-            SELECT id FROM model_metadata
-            WHERE name=?;
-            """,
-            (name,),
-        )
-        return {x[0] for x in self._cursor.fetchall()}
-
-    def _update_tags(self, model_key: str, tags: Set[str]) -> None:
-        """Update tags for the model referenced by model_key."""
-        # remove previous tags from this model
-        self._cursor.execute(
-            """--sql
-            DELETE FROM model_tags
-            WHERE model_id=?;
-            """,
-            (model_key,),
-        )
-
-        for tag in tags:
-            self._cursor.execute(
-                """--sql
-                INSERT OR IGNORE INTO tags (
-                  tag_text
-                  )
-                VALUES (?);
-                """,
-                (tag,),
-            )
-            self._cursor.execute(
-                """--sql
-                SELECT tag_id
-                FROM tags
-                WHERE tag_text = ?
-                LIMIT 1;
-                """,
-                (tag,),
-            )
-            tag_id = self._cursor.fetchone()[0]
-            self._cursor.execute(
-                """--sql
-                INSERT OR IGNORE INTO model_tags (
-                   model_id,
-                   tag_id
-                  )
-                VALUES (?,?);
-                """,
-                (model_key, tag_id),
-            )

invokeai/app/services/model_records/__init__.py

@@ -4,8 +4,6 @@ from .model_records_base import (  # noqa F401
     InvalidModelException,
     ModelRecordServiceBase,
     UnknownModelException,
-    ModelSummary,
-    ModelRecordOrderBy,
 )
 from .model_records_sql import ModelRecordServiceSQL  # noqa F401
 
@@ -15,6 +13,4 @@ __all__ = [
     "DuplicateModelException",
     "InvalidModelException",
     "UnknownModelException",
-    "ModelSummary",
-    "ModelRecordOrderBy",
 ]

invokeai/app/services/model_records/model_records_base.py

@@ -4,22 +4,10 @@ Abstract base class for storing and retrieving model configuration records.
 """
 
 from abc import ABC, abstractmethod
-from enum import Enum
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import List, Optional, Union
 
-from pydantic import BaseModel, Field
-
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelFormat,
-    ModelType,
-)
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..model_metadata import ModelMetadataStoreBase
+from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelFormat, ModelType
 
 
 class DuplicateModelException(Exception):
@@ -38,33 +26,11 @@ class ConfigFileVersionMismatchException(Exception):
     """Raised on an attempt to open a config with an incompatible version."""
 
 
-class ModelRecordOrderBy(str, Enum):
-    """The order in which to return model summaries."""
-
-    Default = "default"  # order by type, base, format and name
-    Type = "type"
-    Base = "base"
-    Name = "name"
-    Format = "format"
-
-
-class ModelSummary(BaseModel):
-    """A short summary of models for UI listing purposes."""
-
-    key: str = Field(description="model key")
-    type: ModelType = Field(description="model type")
-    base: BaseModelType = Field(description="base model")
-    format: ModelFormat = Field(description="model format")
-    name: str = Field(description="model name")
-    description: str = Field(description="short description of model")
-    tags: Set[str] = Field(description="tags associated with model")
-
-
 class ModelRecordServiceBase(ABC):
     """Abstract base class for storage and retrieval of model configs."""
 
     @abstractmethod
-    def add_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def add_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
         """
         Add a model to the database.
 
@@ -88,7 +54,7 @@ class ModelRecordServiceBase(ABC):
         pass
 
     @abstractmethod
-    def update_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def update_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
         """
         Update the model, returning the updated version.
 
@@ -109,51 +75,10 @@ class ModelRecordServiceBase(ABC):
         """
         pass
 
-    @property
-    @abstractmethod
-    def metadata_store(self) -> ModelMetadataStoreBase:
-        """Return a ModelMetadataStore initialized on the same database."""
-        pass
-
-    @abstractmethod
-    def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
-        """
-        Retrieve metadata (if any) from when model was downloaded from a repo.
-
-        :param key: Model key
-        """
-        pass
-
-    @abstractmethod
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:
-        """List metadata for all models that have it."""
-        pass
-
-    @abstractmethod
-    def search_by_metadata_tag(self, tags: Set[str]) -> List[AnyModelConfig]:
-        """
-        Search model metadata for ones with all listed tags and return their corresponding configs.
-
-        :param tags: Set of tags to search for. All tags must be present.
-        """
-        pass
-
-    @abstractmethod
-    def list_tags(self) -> Set[str]:
-        """Return a unique set of all the model tags in the metadata database."""
-        pass
-
-    @abstractmethod
-    def list_models(
-        self, page: int = 0, per_page: int = 10, order_by: ModelRecordOrderBy = ModelRecordOrderBy.Default
-    ) -> PaginatedResults[ModelSummary]:
-        """Return a paginated summary listing of each model in the database."""
-        pass
-
     @abstractmethod
     def exists(self, key: str) -> bool:
         """
-        Return True if a model with the indicated key exists in the database.
+        Return True if a model with the indicated key exists in the databse.
 
         :param key: Unique key for the model to be deleted
         """

invokeai/app/services/model_records/model_records_sql.py

@@ -42,11 +42,9 @@ Typical usage:
 
 import json
 import sqlite3
-from math import ceil
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import List, Optional, Union
 
-from invokeai.app.services.shared.pagination import PaginatedResults
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
@@ -54,15 +52,11 @@ from invokeai.backend.model_manager.config import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, UnknownMetadataException
 
-from ..model_metadata import ModelMetadataStoreBase, ModelMetadataStoreSQL
 from ..shared.sqlite.sqlite_database import SqliteDatabase
 from .model_records_base import (
     DuplicateModelException,
-    ModelRecordOrderBy,
     ModelRecordServiceBase,
-    ModelSummary,
     UnknownModelException,
 )
 
@@ -70,23 +64,21 @@ from .model_records_base import (
 class ModelRecordServiceSQL(ModelRecordServiceBase):
     """Implementation of the ModelConfigStore ABC using a SQL database."""
 
-    def __init__(self, db: SqliteDatabase, metadata_store: ModelMetadataStoreBase):
+    _db: SqliteDatabase
+    _cursor: sqlite3.Cursor
+
+    def __init__(self, db: SqliteDatabase):
         """
         Initialize a new object from preexisting sqlite3 connection and threading lock objects.
 
-        :param db: Sqlite connection object
+        :param conn: sqlite3 connection object
+        :param lock: threading Lock object
         """
         super().__init__()
         self._db = db
-        self._cursor = db.conn.cursor()
-        self._metadata_store = metadata_store
+        self._cursor = self._db.conn.cursor()
 
-    @property
-    def db(self) -> SqliteDatabase:
-        """Return the underlying database."""
-        return self._db
-
-    def add_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def add_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
         """
         Add a model to the database.
 
@@ -159,7 +151,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 self._db.conn.rollback()
                 raise e
 
-    def update_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def update_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
         """
         Update the model, returning the updated version.
 
@@ -200,7 +192,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE id=?;
                 """,
                 (key,),
@@ -208,7 +200,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
             rows = self._cursor.fetchone()
             if not rows:
                 raise UnknownModelException("model not found")
-            model = ModelConfigFactory.make_config(json.loads(rows[0]), timestamp=rows[1])
+            model = ModelConfigFactory.make_config(json.loads(rows[0]))
         return model
 
     def exists(self, key: str) -> bool:
@@ -266,14 +258,12 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 f"""--sql
-                select config, strftime('%s',updated_at) FROM model_config
+                select config FROM model_config
                 {where};
                 """,
                 tuple(bindings),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
 
     def search_by_path(self, path: Union[str, Path]) -> List[AnyModelConfig]:
@@ -282,14 +272,12 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE path=?;
                 """,
                 (str(path),),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
 
     def search_by_hash(self, hash: str) -> List[AnyModelConfig]:
@@ -298,104 +286,10 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config, strftime('%s',updated_at) FROM model_config
+                SELECT config FROM model_config
                 WHERE original_hash=?;
                 """,
                 (hash,),
             )
-            results = [
-                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
-            ]
+            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
         return results
-
-    @property
-    def metadata_store(self) -> ModelMetadataStoreBase:
-        """Return a ModelMetadataStore initialized on the same database."""
-        return self._metadata_store
-
-    def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
-        """
-        Retrieve metadata (if any) from when model was downloaded from a repo.
-
-        :param key: Model key
-        """
-        store = self.metadata_store
-        try:
-            metadata = store.get_metadata(key)
-            return metadata
-        except UnknownMetadataException:
-            return None
-
-    def search_by_metadata_tag(self, tags: Set[str]) -> List[AnyModelConfig]:
-        """
-        Search model metadata for ones with all listed tags and return their corresponding configs.
-
-        :param tags: Set of tags to search for. All tags must be present.
-        """
-        store = ModelMetadataStoreSQL(self._db)
-        keys = store.search_by_tag(tags)
-        return [self.get_model(x) for x in keys]
-
-    def list_tags(self) -> Set[str]:
-        """Return a unique set of all the model tags in the metadata database."""
-        store = ModelMetadataStoreSQL(self._db)
-        return store.list_tags()
-
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:
-        """List metadata for all models that have it."""
-        store = ModelMetadataStoreSQL(self._db)
-        return store.list_all_metadata()
-
-    def list_models(
-        self, page: int = 0, per_page: int = 10, order_by: ModelRecordOrderBy = ModelRecordOrderBy.Default
-    ) -> PaginatedResults[ModelSummary]:
-        """Return a paginated summary listing of each model in the database."""
-        ordering = {
-            ModelRecordOrderBy.Default: "a.type, a.base, a.format, a.name",
-            ModelRecordOrderBy.Type: "a.type",
-            ModelRecordOrderBy.Base: "a.base",
-            ModelRecordOrderBy.Name: "a.name",
-            ModelRecordOrderBy.Format: "a.format",
-        }
-
-        def _fixup(summary: Dict[str, str]) -> Dict[str, Union[str, int, Set[str]]]:
-            """Fix up results so that there are no null values."""
-            result: Dict[str, Union[str, int, Set[str]]] = {}
-            for key, item in summary.items():
-                result[key] = item or ""
-            result["tags"] = set(json.loads(summary["tags"] or "[]"))
-            return result
-
-        # Lock so that the database isn't updated while we're doing the two queries.
-        with self._db.lock:
-            # query1: get the total number of model configs
-            self._cursor.execute(
-                """--sql
-                select count(*) from model_config;
-                """,
-                (),
-            )
-            total = int(self._cursor.fetchone()[0])
-
-            # query2: fetch key fields from the join of model_config and model_metadata
-            self._cursor.execute(
-                f"""--sql
-                SELECT a.id as key, a.type, a.base, a.format, a.name,
-                       json_extract(a.config, '$.description') as description,
-                       json_extract(b.metadata, '$.tags') as tags
-                FROM model_config AS a
-                LEFT JOIN model_metadata AS b on a.id=b.id
-                ORDER BY {ordering[order_by]} -- using ? to bind doesn't work here for some reason
-                LIMIT ?
-                OFFSET ?;
-                """,
-                (
-                    per_page,
-                    page * per_page,
-                ),
-            )
-            rows = self._cursor.fetchall()
-            items = [ModelSummary.model_validate(_fixup(dict(x))) for x in rows]
-            return PaginatedResults(
-                page=page, pages=ceil(total / per_page), per_page=per_page, total=total, items=items
-            )

invokeai/app/services/shared/graph.py

@@ -2,7 +2,7 @@
 
 import copy
 import itertools
-from typing import Annotated, Any, Optional, TypeVar, Union, get_args, get_origin, get_type_hints
+from typing import Annotated, Any, Optional, Union, get_args, get_origin, get_type_hints
 
 import networkx as nx
 from pydantic import BaseModel, ConfigDict, field_validator, model_validator
@@ -141,16 +141,6 @@ def are_connections_compatible(
     return are_connection_types_compatible(from_node_field, to_node_field)
 
 
-T = TypeVar("T")
-
-
-def copydeep(obj: T) -> T:
-    """Deep-copies an object. If it is a pydantic model, use the model's copy method."""
-    if isinstance(obj, BaseModel):
-        return obj.model_copy(deep=True)
-    return copy.deepcopy(obj)
-
-
 class NodeAlreadyInGraphError(ValueError):
     pass
 
@@ -1128,22 +1118,17 @@ class GraphExecutionState(BaseModel):
 
     def _prepare_inputs(self, node: BaseInvocation):
         input_edges = [e for e in self.execution_graph.edges if e.destination.node_id == node.id]
-        # Inputs must be deep-copied, else if a node mutates the object, other nodes that get the same input
-        # will see the mutation.
         if isinstance(node, CollectInvocation):
             output_collection = [
-                copydeep(getattr(self.results[edge.source.node_id], edge.source.field))
+                getattr(self.results[edge.source.node_id], edge.source.field)
                 for edge in input_edges
                 if edge.destination.field == "item"
             ]
             node.collection = output_collection
         else:
             for edge in input_edges:
-                setattr(
-                    node,
-                    edge.destination.field,
-                    copydeep(getattr(self.results[edge.source.node_id], edge.source.field)),
-                )
+                output_value = getattr(self.results[edge.source.node_id], edge.source.field)
+                setattr(node, edge.destination.field, output_value)
 
     # TODO: Add API for modifying underlying graph that checks if the change will be valid given the current execution state
     def _is_edge_valid(self, edge: Edge) -> bool:

invokeai/app/services/shared/sqlite/sqlite_util.py

@@ -6,9 +6,6 @@ from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_1 import build_migration_1
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_2 import build_migration_2
 from invokeai.app.services.shared.sqlite_migrator.migrations.migration_3 import build_migration_3
-from invokeai.app.services.shared.sqlite_migrator.migrations.migration_4 import build_migration_4
-from invokeai.app.services.shared.sqlite_migrator.migrations.migration_5 import build_migration_5
-from invokeai.app.services.shared.sqlite_migrator.migrations.migration_6 import build_migration_6
 from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_impl import SqliteMigrator
 
 
@@ -31,10 +28,7 @@ def init_db(config: InvokeAIAppConfig, logger: Logger, image_files: ImageFileSto
     migrator = SqliteMigrator(db=db)
     migrator.register_migration(build_migration_1())
     migrator.register_migration(build_migration_2(image_files=image_files, logger=logger))
-    migrator.register_migration(build_migration_3(app_config=config, logger=logger))
-    migrator.register_migration(build_migration_4())
-    migrator.register_migration(build_migration_5())
-    migrator.register_migration(build_migration_6())
+    migrator.register_migration(build_migration_3())
     migrator.run_migrations()
 
     return db

invokeai/app/services/shared/sqlite_migrator/migrations/migration_2.py

@@ -11,6 +11,8 @@ from invokeai.app.services.workflow_records.workflow_records_common import (
     UnsafeWorkflowWithVersionValidator,
 )
 
+from .util.migrate_yaml_config_1 import MigrateModelYamlToDb1
+
 
 class Migration2Callback:
     def __init__(self, image_files: ImageFileStorageBase, logger: Logger):
@@ -23,6 +25,8 @@ class Migration2Callback:
         self._drop_old_workflow_tables(cursor)
         self._add_workflow_library(cursor)
         self._drop_model_manager_metadata(cursor)
+        self._recreate_model_config(cursor)
+        self._migrate_model_config_records(cursor)
         self._migrate_embedded_workflows(cursor)
 
     def _add_images_has_workflow(self, cursor: sqlite3.Cursor) -> None:
@@ -96,6 +100,45 @@ class Migration2Callback:
         """Drops the `model_manager_metadata` table."""
         cursor.execute("DROP TABLE IF EXISTS model_manager_metadata;")
 
+    def _recreate_model_config(self, cursor: sqlite3.Cursor) -> None:
+        """
+        Drops the `model_config` table, recreating it.
+
+        In 3.4.0, this table used explicit columns but was changed to use json_extract 3.5.0.
+
+        Because this table is not used in production, we are able to simply drop it and recreate it.
+        """
+
+        cursor.execute("DROP TABLE IF EXISTS model_config;")
+
+        cursor.execute(
+            """--sql
+            CREATE TABLE IF NOT EXISTS model_config (
+                id TEXT NOT NULL PRIMARY KEY,
+                -- The next 3 fields are enums in python, unrestricted string here
+                base TEXT GENERATED ALWAYS as (json_extract(config, '$.base')) VIRTUAL NOT NULL,
+                type TEXT GENERATED ALWAYS as (json_extract(config, '$.type')) VIRTUAL NOT NULL,
+                name TEXT GENERATED ALWAYS as (json_extract(config, '$.name')) VIRTUAL NOT NULL,
+                path TEXT GENERATED ALWAYS as (json_extract(config, '$.path')) VIRTUAL NOT NULL,
+                format TEXT GENERATED ALWAYS as (json_extract(config, '$.format')) VIRTUAL NOT NULL,
+                original_hash TEXT, -- could be null
+                -- Serialized JSON representation of the whole config object,
+                -- which will contain additional fields from subclasses
+                config 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')),
+                -- unique constraint on combo of name, base and type
+                UNIQUE(name, base, type)
+            );
+            """
+        )
+
+    def _migrate_model_config_records(self, cursor: sqlite3.Cursor) -> None:
+        """After updating the model config table, we repopulate it."""
+        model_record_migrator = MigrateModelYamlToDb1(cursor)
+        model_record_migrator.migrate()
+
     def _migrate_embedded_workflows(self, cursor: sqlite3.Cursor) -> None:
         """
         In the v3.5.0 release, InvokeAI changed how it handles embedded workflows. The `images` table in

invokeai/app/services/shared/sqlite_migrator/migrations/migration_3.py

@@ -1,16 +1,13 @@
 import sqlite3
-from logging import Logger
 
-from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
 
 from .util.migrate_yaml_config_1 import MigrateModelYamlToDb1
 
 
 class Migration3Callback:
-    def __init__(self, app_config: InvokeAIAppConfig, logger: Logger) -> None:
-        self._app_config = app_config
-        self._logger = logger
+    def __init__(self) -> None:
+        pass
 
     def __call__(self, cursor: sqlite3.Cursor) -> None:
         self._drop_model_manager_metadata(cursor)
@@ -57,12 +54,11 @@ class Migration3Callback:
 
     def _migrate_model_config_records(self, cursor: sqlite3.Cursor) -> None:
         """After updating the model config table, we repopulate it."""
-        self._logger.info("Migrating model config records from models.yaml to database")
-        model_record_migrator = MigrateModelYamlToDb1(self._app_config, self._logger, cursor)
+        model_record_migrator = MigrateModelYamlToDb1(cursor)
         model_record_migrator.migrate()
 
 
-def build_migration_3(app_config: InvokeAIAppConfig, logger: Logger) -> Migration:
+def build_migration_3() -> Migration:
     """
     Build the migration from database version 2 to 3.
 
@@ -73,7 +69,7 @@ def build_migration_3(app_config: InvokeAIAppConfig, logger: Logger) -> Migratio
     migration_3 = Migration(
         from_version=2,
         to_version=3,
-        callback=Migration3Callback(app_config=app_config, logger=logger),
+        callback=Migration3Callback(),
     )
 
     return migration_3

invokeai/app/services/shared/sqlite_migrator/migrations/migration_4.py

@@ -1,83 +0,0 @@
-import sqlite3
-
-from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
-
-
-class Migration4Callback:
-    """Callback to do step 4 of migration."""
-
-    def __call__(self, cursor: sqlite3.Cursor) -> None:  # noqa D102
-        self._create_model_metadata(cursor)
-        self._create_model_tags(cursor)
-        self._create_tags(cursor)
-        self._create_triggers(cursor)
-
-    def _create_model_metadata(self, cursor: sqlite3.Cursor) -> None:
-        """Create the table used to store model metadata downloaded from remote sources."""
-        cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS model_metadata (
-                id TEXT NOT NULL PRIMARY KEY,
-                name TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.name')) VIRTUAL NOT NULL,
-                author TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.author')) VIRTUAL NOT NULL,
-                -- Serialized JSON representation of the whole metadata object,
-                -- which will contain additional fields from subclasses
-                metadata 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')),
-                FOREIGN KEY(id) REFERENCES model_config(id) ON DELETE CASCADE
-            );
-            """
-        )
-
-    def _create_model_tags(self, cursor: sqlite3.Cursor) -> None:
-        cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS model_tags (
-                model_id TEXT NOT NULL,
-                tag_id INTEGER NOT NULL,
-                FOREIGN KEY(model_id) REFERENCES model_config(id) ON DELETE CASCADE,
-                FOREIGN KEY(tag_id) REFERENCES tags(tag_id) ON DELETE CASCADE,
-                UNIQUE(model_id,tag_id)
-            );
-            """
-        )
-
-    def _create_tags(self, cursor: sqlite3.Cursor) -> None:
-        cursor.execute(
-            """--sql
-            CREATE TABLE IF NOT EXISTS tags (
-                tag_id INTEGER NOT NULL PRIMARY KEY,
-                tag_text TEXT NOT NULL UNIQUE
-            );
-            """
-        )
-
-    def _create_triggers(self, cursor: sqlite3.Cursor) -> None:
-        cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS model_metadata_updated_at
-            AFTER UPDATE
-            ON model_metadata FOR EACH ROW
-            BEGIN
-                UPDATE model_metadata SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE id = old.id;
-            END;
-            """
-        )
-
-
-def build_migration_4() -> Migration:
-    """
-    Build the migration from database version 3 to 4.
-
-    Adds the tables needed to store model metadata and tags.
-    """
-    migration_4 = Migration(
-        from_version=3,
-        to_version=4,
-        callback=Migration4Callback(),
-    )
-
-    return migration_4

invokeai/app/services/shared/sqlite_migrator/migrations/migration_5.py

@@ -1,34 +0,0 @@
-import sqlite3
-
-from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
-
-
-class Migration5Callback:
-    def __call__(self, cursor: sqlite3.Cursor) -> None:
-        self._drop_graph_executions(cursor)
-
-    def _drop_graph_executions(self, cursor: sqlite3.Cursor) -> None:
-        """Drops the `graph_executions` table."""
-
-        cursor.execute(
-            """--sql
-            DROP TABLE IF EXISTS graph_executions;
-            """
-        )
-
-
-def build_migration_5() -> Migration:
-    """
-    Build the migration from database version 4 to 5.
-
-    Introduced in v3.6.3, this migration:
-    - Drops the `graph_executions` table. We are able to do this because we are moving the graph storage
-      to be purely in-memory.
-    """
-    migration_5 = Migration(
-        from_version=4,
-        to_version=5,
-        callback=Migration5Callback(),
-    )
-
-    return migration_5

invokeai/app/services/shared/sqlite_migrator/migrations/migration_6.py

@@ -1,62 +0,0 @@
-import sqlite3
-
-from invokeai.app.services.shared.sqlite_migrator.sqlite_migrator_common import Migration
-
-
-class Migration6Callback:
-    def __call__(self, cursor: sqlite3.Cursor) -> None:
-        self._recreate_model_triggers(cursor)
-        self._delete_ip_adapters(cursor)
-
-    def _recreate_model_triggers(self, cursor: sqlite3.Cursor) -> None:
-        """
-        Adds the timestamp trigger to the model_config table.
-
-        This trigger was inadvertently dropped in earlier migration scripts.
-        """
-
-        cursor.execute(
-            """--sql
-            CREATE TRIGGER IF NOT EXISTS model_config_updated_at
-            AFTER UPDATE
-            ON model_config FOR EACH ROW
-            BEGIN
-                UPDATE model_config SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
-                    WHERE id = old.id;
-            END;
-            """
-        )
-
-    def _delete_ip_adapters(self, cursor: sqlite3.Cursor) -> None:
-        """
-        Delete all the IP adapters.
-
-        The model manager will automatically find and re-add them after the migration
-        is done. This allows the manager to add the correct image encoder to their
-        configuration records.
-        """
-
-        cursor.execute(
-            """--sql
-            DELETE FROM model_config
-              WHERE type='ip_adapter';
-            """
-        )
-
-
-def build_migration_6() -> Migration:
-    """
-    Build the migration from database version 5 to 6.
-
-    This migration does the following:
-    - Adds the model_config_updated_at trigger if it does not exist
-    - Delete all ip_adapter models so that the model prober can find and
-      update with the correct image processor model.
-    """
-    migration_6 = Migration(
-        from_version=5,
-        to_version=6,
-        callback=Migration6Callback(),
-    )
-
-    return migration_6

invokeai/app/services/shared/sqlite_migrator/migrations/util/migrate_yaml_config_1.py

@@ -23,6 +23,7 @@ from invokeai.backend.model_manager.config import (
     ModelType,
 )
 from invokeai.backend.model_manager.hash import FastModelHash
+from invokeai.backend.util.logging import InvokeAILogger
 
 ModelsValidator = TypeAdapter(AnyModelConfig)
 
@@ -45,9 +46,10 @@ class MigrateModelYamlToDb1:
     logger: Logger
     cursor: sqlite3.Cursor
 
-    def __init__(self, config: InvokeAIAppConfig, logger: Logger, cursor: sqlite3.Cursor = None) -> None:
-        self.config = config
-        self.logger = logger
+    def __init__(self, cursor: sqlite3.Cursor = None) -> None:
+        self.config = InvokeAIAppConfig.get_config()
+        self.config.parse_args()
+        self.logger = InvokeAILogger.get_logger()
         self.cursor = cursor
 
     def get_yaml(self) -> DictConfig:
@@ -72,12 +74,7 @@ class MigrateModelYamlToDb1:
                 continue
 
             base_type, model_type, model_name = str(model_key).split("/")
-            try:
-                hash = FastModelHash.hash(self.config.models_path / stanza.path)
-            except OSError:
-                self.logger.warning(f"The model at {stanza.path} is not a valid file or directory. Skipping migration.")
-                continue
-
+            hash = FastModelHash.hash(self.config.models_path / stanza.path)
             assert isinstance(model_key, str)
             new_key = sha1(model_key.encode("utf-8")).hexdigest()
 

invokeai/app/services/workflow_records/default_workflows/ESRGAN Upscaling with Canny ControlNet.json

@@ -1,4 +1,5 @@
 {
+  "id": "6bfa0b3a-7090-4cd9-ad2d-a4b8662b6e71",
   "name": "ESRGAN Upscaling with Canny ControlNet",
   "author": "InvokeAI",
   "description": "Sample workflow for using Upscaling with ControlNet with SD1.5",
@@ -76,12 +77,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 1250,
         "y": 1500
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "d8ace142-c05f-4f1d-8982-88dc7473958d",
@@ -147,12 +148,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 227,
       "position": {
         "x": 700,
         "y": 1375
-      },
-      "width": 320,
-      "height": 193
+      }
     },
     {
       "id": "771bdf6a-0813-4099-a5d8-921a138754d4",
@@ -213,12 +214,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 225,
       "position": {
         "x": 375,
         "y": 1900
-      },
-      "width": 320,
-      "height": 189
+      }
     },
     {
       "id": "f7564dd2-9539-47f2-ac13-190804461f4e",
@@ -314,12 +315,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 340,
       "position": {
         "x": 775,
         "y": 1900
-      },
-      "width": 320,
-      "height": 295
+      }
     },
     {
       "id": "1d887701-df21-4966-ae6e-a7d82307d7bd",
@@ -415,12 +416,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 340,
       "position": {
         "x": 1200,
         "y": 1900
-      },
-      "width": 320,
-      "height": 293
+      }
     },
     {
       "id": "ca1d020c-89a8-4958-880a-016d28775cfa",
@@ -433,7 +434,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.1.1",
+        "version": "1.1.0",
         "nodePack": "invokeai",
         "inputs": {
           "image": {
@@ -536,12 +537,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 511,
       "position": {
         "x": 1650,
         "y": 1900
-      },
-      "width": 320,
-      "height": 451
+      }
     },
     {
       "id": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
@@ -639,12 +640,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 1650,
         "y": 1775
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "c3737554-8d87-48ff-a6f8-e71d2867f434",
@@ -657,7 +658,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
@@ -865,12 +866,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 705,
       "position": {
         "x": 2128.740065979906,
         "y": 1232.6219060454753
-      },
-      "width": 320,
-      "height": 612
+      }
     },
     {
       "id": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
@@ -977,12 +978,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 267,
       "position": {
         "x": 2559.4751127537957,
         "y": 1246.6000376741406
-      },
-      "width": 320,
-      "height": 224
+      }
     },
     {
       "id": "5ca498a4-c8c8-4580-a396-0c984317205d",
@@ -1078,12 +1079,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 1650,
         "y": 1675
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
@@ -1136,12 +1137,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 1250,
         "y": 1200
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "eb8f6f8a-c7b1-4914-806e-045ee2717a35",
@@ -1194,168 +1195,168 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 1650,
         "y": 1600
-      },
-      "width": 320,
-      "height": 24
+      }
     }
   ],
   "edges": [
     {
       "id": "5ca498a4-c8c8-4580-a396-0c984317205d-f50624ce-82bf-41d0-bdf7-8aab11a80d48-collapsed",
-      "type": "collapsed",
       "source": "5ca498a4-c8c8-4580-a396-0c984317205d",
-      "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48"
+      "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
+      "type": "collapsed"
     },
     {
       "id": "eb8f6f8a-c7b1-4914-806e-045ee2717a35-f50624ce-82bf-41d0-bdf7-8aab11a80d48-collapsed",
-      "type": "collapsed",
       "source": "eb8f6f8a-c7b1-4914-806e-045ee2717a35",
-      "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48"
+      "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
+      "type": "collapsed"
     },
     {
       "id": "reactflow__edge-771bdf6a-0813-4099-a5d8-921a138754d4image-f7564dd2-9539-47f2-ac13-190804461f4eimage",
-      "type": "default",
       "source": "771bdf6a-0813-4099-a5d8-921a138754d4",
       "target": "f7564dd2-9539-47f2-ac13-190804461f4e",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-f7564dd2-9539-47f2-ac13-190804461f4eimage-1d887701-df21-4966-ae6e-a7d82307d7bdimage",
-      "type": "default",
       "source": "f7564dd2-9539-47f2-ac13-190804461f4e",
       "target": "1d887701-df21-4966-ae6e-a7d82307d7bd",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-5ca498a4-c8c8-4580-a396-0c984317205dwidth-f50624ce-82bf-41d0-bdf7-8aab11a80d48width",
-      "type": "default",
       "source": "5ca498a4-c8c8-4580-a396-0c984317205d",
       "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
+      "type": "default",
       "sourceHandle": "width",
       "targetHandle": "width"
     },
     {
       "id": "reactflow__edge-5ca498a4-c8c8-4580-a396-0c984317205dheight-f50624ce-82bf-41d0-bdf7-8aab11a80d48height",
-      "type": "default",
       "source": "5ca498a4-c8c8-4580-a396-0c984317205d",
       "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
+      "type": "default",
       "sourceHandle": "height",
       "targetHandle": "height"
     },
     {
       "id": "reactflow__edge-f50624ce-82bf-41d0-bdf7-8aab11a80d48noise-c3737554-8d87-48ff-a6f8-e71d2867f434noise",
-      "type": "default",
       "source": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-5ca498a4-c8c8-4580-a396-0c984317205dlatents-c3737554-8d87-48ff-a6f8-e71d2867f434latents",
-      "type": "default",
       "source": "5ca498a4-c8c8-4580-a396-0c984317205d",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-e8bf67fe-67de-4227-87eb-79e86afdfc74conditioning-c3737554-8d87-48ff-a6f8-e71d2867f434negative_conditioning",
-      "type": "default",
       "source": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16bconditioning-c3737554-8d87-48ff-a6f8-e71d2867f434positive_conditioning",
-      "type": "default",
       "source": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-d8ace142-c05f-4f1d-8982-88dc7473958dclip-63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16bclip",
-      "type": "default",
       "source": "d8ace142-c05f-4f1d-8982-88dc7473958d",
       "target": "63b6ab7e-5b05-4d1b-a3b1-42d8e53ce16b",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-d8ace142-c05f-4f1d-8982-88dc7473958dclip-e8bf67fe-67de-4227-87eb-79e86afdfc74clip",
-      "type": "default",
       "source": "d8ace142-c05f-4f1d-8982-88dc7473958d",
       "target": "e8bf67fe-67de-4227-87eb-79e86afdfc74",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-1d887701-df21-4966-ae6e-a7d82307d7bdimage-ca1d020c-89a8-4958-880a-016d28775cfaimage",
-      "type": "default",
       "source": "1d887701-df21-4966-ae6e-a7d82307d7bd",
       "target": "ca1d020c-89a8-4958-880a-016d28775cfa",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-ca1d020c-89a8-4958-880a-016d28775cfacontrol-c3737554-8d87-48ff-a6f8-e71d2867f434control",
-      "type": "default",
       "source": "ca1d020c-89a8-4958-880a-016d28775cfa",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "control",
       "targetHandle": "control"
     },
     {
       "id": "reactflow__edge-c3737554-8d87-48ff-a6f8-e71d2867f434latents-3ed9b2ef-f4ec-40a7-94db-92e63b583ec0latents",
-      "type": "default",
       "source": "c3737554-8d87-48ff-a6f8-e71d2867f434",
       "target": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-d8ace142-c05f-4f1d-8982-88dc7473958dvae-3ed9b2ef-f4ec-40a7-94db-92e63b583ec0vae",
-      "type": "default",
       "source": "d8ace142-c05f-4f1d-8982-88dc7473958d",
       "target": "3ed9b2ef-f4ec-40a7-94db-92e63b583ec0",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
       "id": "reactflow__edge-f7564dd2-9539-47f2-ac13-190804461f4eimage-5ca498a4-c8c8-4580-a396-0c984317205dimage",
-      "type": "default",
       "source": "f7564dd2-9539-47f2-ac13-190804461f4e",
       "target": "5ca498a4-c8c8-4580-a396-0c984317205d",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-d8ace142-c05f-4f1d-8982-88dc7473958dunet-c3737554-8d87-48ff-a6f8-e71d2867f434unet",
-      "type": "default",
       "source": "d8ace142-c05f-4f1d-8982-88dc7473958d",
       "target": "c3737554-8d87-48ff-a6f8-e71d2867f434",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-d8ace142-c05f-4f1d-8982-88dc7473958dvae-5ca498a4-c8c8-4580-a396-0c984317205dvae",
-      "type": "default",
       "source": "d8ace142-c05f-4f1d-8982-88dc7473958d",
       "target": "5ca498a4-c8c8-4580-a396-0c984317205d",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
       "id": "reactflow__edge-eb8f6f8a-c7b1-4914-806e-045ee2717a35value-f50624ce-82bf-41d0-bdf7-8aab11a80d48seed",
-      "type": "default",
       "source": "eb8f6f8a-c7b1-4914-806e-045ee2717a35",
       "target": "f50624ce-82bf-41d0-bdf7-8aab11a80d48",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     }

invokeai/app/services/workflow_records/default_workflows/Multi ControlNet (Canny & Depth).json

@@ -1,4 +1,5 @@
 {
+  "id": "1e385b84-86f8-452e-9697-9e5abed20518",
   "name": "Multi ControlNet (Canny & Depth)",
   "author": "InvokeAI",
   "description": "A sample workflow using canny & depth ControlNets to guide the generation process. ",
@@ -92,12 +93,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 225,
       "position": {
         "x": 3625,
         "y": -75
-      },
-      "width": 320,
-      "height": 189
+      }
     },
     {
       "id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
@@ -110,7 +111,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.1.1",
+        "version": "1.1.0",
         "nodePack": "invokeai",
         "inputs": {
           "image": {
@@ -213,12 +214,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 511,
       "position": {
         "x": 4477.604342844504,
         "y": -49.39005411272677
-      },
-      "width": 320,
-      "height": 451
+      }
     },
     {
       "id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
@@ -271,12 +272,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 4075,
         "y": -825
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
@@ -342,12 +343,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 227,
       "position": {
         "x": 3600,
         "y": -1000
-      },
-      "width": 320,
-      "height": 193
+      }
     },
     {
       "id": "7ce68934-3419-42d4-ac70-82cfc9397306",
@@ -400,12 +401,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 4075,
         "y": -1125
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "d204d184-f209-4fae-a0a1-d152800844e1",
@@ -418,7 +419,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.1.1",
+        "version": "1.1.0",
         "nodePack": "invokeai",
         "inputs": {
           "image": {
@@ -521,12 +522,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 511,
       "position": {
         "x": 4479.68542130465,
         "y": -618.4221638099414
-      },
-      "width": 320,
-      "height": 451
+      }
     },
     {
       "id": "c4b23e64-7986-40c4-9cad-46327b12e204",
@@ -587,12 +588,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 225,
       "position": {
         "x": 3625,
         "y": -425
-      },
-      "width": 320,
-      "height": 189
+      }
     },
     {
       "id": "ca4d5059-8bfb-447f-b415-da0faba5a143",
@@ -632,12 +633,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 104,
       "position": {
         "x": 4875,
         "y": -575
-      },
-      "width": 320,
-      "height": 87
+      }
     },
     {
       "id": "018b1214-c2af-43a7-9910-fb687c6726d7",
@@ -733,12 +734,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 340,
       "position": {
         "x": 4100,
         "y": -75
-      },
-      "width": 320,
-      "height": 293
+      }
     },
     {
       "id": "c826ba5e-9676-4475-b260-07b85e88753c",
@@ -834,12 +835,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 340,
       "position": {
         "x": 4095.757337055795,
         "y": -455.63440891935863
-      },
-      "width": 320,
-      "height": 293
+      }
     },
     {
       "id": "9db25398-c869-4a63-8815-c6559341ef12",
@@ -946,12 +947,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 267,
       "position": {
         "x": 5675,
         "y": -825
-      },
-      "width": 320,
-      "height": 224
+      }
     },
     {
       "id": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
@@ -964,7 +965,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
@@ -1172,12 +1173,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 705,
       "position": {
         "x": 5274.672987098195,
         "y": -823.0752416664332
-      },
-      "width": 320,
-      "height": 612
+      }
     },
     {
       "id": "2e77a0a1-db6a-47a2-a8bf-1e003be6423b",
@@ -1274,12 +1275,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 4875,
         "y": -675
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "8b260b4d-3fd6-44d4-b1be-9f0e43c628ce",
@@ -1332,146 +1333,146 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 4875,
         "y": -750
-      },
-      "width": 320,
-      "height": 24
+      }
     }
   ],
   "edges": [
     {
       "id": "8b260b4d-3fd6-44d4-b1be-9f0e43c628ce-2e77a0a1-db6a-47a2-a8bf-1e003be6423b-collapsed",
-      "type": "collapsed",
       "source": "8b260b4d-3fd6-44d4-b1be-9f0e43c628ce",
-      "target": "2e77a0a1-db6a-47a2-a8bf-1e003be6423b"
+      "target": "2e77a0a1-db6a-47a2-a8bf-1e003be6423b",
+      "type": "collapsed"
     },
     {
       "id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9clip-7ce68934-3419-42d4-ac70-82cfc9397306clip",
-      "type": "default",
       "source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
       "target": "7ce68934-3419-42d4-ac70-82cfc9397306",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9clip-273e3f96-49ea-4dc5-9d5b-9660390f14e1clip",
-      "type": "default",
       "source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
       "target": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-a33199c2-8340-401e-b8a2-42ffa875fc1ccontrol-ca4d5059-8bfb-447f-b415-da0faba5a143item",
-      "type": "default",
       "source": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
       "target": "ca4d5059-8bfb-447f-b415-da0faba5a143",
+      "type": "default",
       "sourceHandle": "control",
       "targetHandle": "item"
     },
     {
       "id": "reactflow__edge-d204d184-f209-4fae-a0a1-d152800844e1control-ca4d5059-8bfb-447f-b415-da0faba5a143item",
-      "type": "default",
       "source": "d204d184-f209-4fae-a0a1-d152800844e1",
       "target": "ca4d5059-8bfb-447f-b415-da0faba5a143",
+      "type": "default",
       "sourceHandle": "control",
       "targetHandle": "item"
     },
     {
       "id": "reactflow__edge-8e860e51-5045-456e-bf04-9a62a2a5c49eimage-018b1214-c2af-43a7-9910-fb687c6726d7image",
-      "type": "default",
       "source": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
       "target": "018b1214-c2af-43a7-9910-fb687c6726d7",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-018b1214-c2af-43a7-9910-fb687c6726d7image-a33199c2-8340-401e-b8a2-42ffa875fc1cimage",
-      "type": "default",
       "source": "018b1214-c2af-43a7-9910-fb687c6726d7",
       "target": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-c4b23e64-7986-40c4-9cad-46327b12e204image-c826ba5e-9676-4475-b260-07b85e88753cimage",
-      "type": "default",
       "source": "c4b23e64-7986-40c4-9cad-46327b12e204",
       "target": "c826ba5e-9676-4475-b260-07b85e88753c",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-c826ba5e-9676-4475-b260-07b85e88753cimage-d204d184-f209-4fae-a0a1-d152800844e1image",
-      "type": "default",
       "source": "c826ba5e-9676-4475-b260-07b85e88753c",
       "target": "d204d184-f209-4fae-a0a1-d152800844e1",
+      "type": "default",
       "sourceHandle": "image",
       "targetHandle": "image"
     },
     {
       "id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9vae-9db25398-c869-4a63-8815-c6559341ef12vae",
-      "type": "default",
       "source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
       "target": "9db25398-c869-4a63-8815-c6559341ef12",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
       "id": "reactflow__edge-ac481b7f-08bf-4a9d-9e0c-3a82ea5243celatents-9db25398-c869-4a63-8815-c6559341ef12latents",
-      "type": "default",
       "source": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
       "target": "9db25398-c869-4a63-8815-c6559341ef12",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-ca4d5059-8bfb-447f-b415-da0faba5a143collection-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cecontrol",
-      "type": "default",
       "source": "ca4d5059-8bfb-447f-b415-da0faba5a143",
       "target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
+      "type": "default",
       "sourceHandle": "collection",
       "targetHandle": "control"
     },
     {
       "id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9unet-ac481b7f-08bf-4a9d-9e0c-3a82ea5243ceunet",
-      "type": "default",
       "source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
       "target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-273e3f96-49ea-4dc5-9d5b-9660390f14e1conditioning-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cenegative_conditioning",
-      "type": "default",
       "source": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
       "target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-7ce68934-3419-42d4-ac70-82cfc9397306conditioning-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cepositive_conditioning",
-      "type": "default",
       "source": "7ce68934-3419-42d4-ac70-82cfc9397306",
       "target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-2e77a0a1-db6a-47a2-a8bf-1e003be6423bnoise-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cenoise",
-      "type": "default",
       "source": "2e77a0a1-db6a-47a2-a8bf-1e003be6423b",
       "target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-8b260b4d-3fd6-44d4-b1be-9f0e43c628cevalue-2e77a0a1-db6a-47a2-a8bf-1e003be6423bseed",
-      "type": "default",
       "source": "8b260b4d-3fd6-44d4-b1be-9f0e43c628ce",
       "target": "2e77a0a1-db6a-47a2-a8bf-1e003be6423b",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     }

invokeai/app/services/workflow_records/default_workflows/Prompt from File.json

@@ -20,6 +20,7 @@
     "category": "default",
     "version": "2.0.0"
   },
+  "id": "d1609af5-eb0a-4f73-b573-c9af96a8d6bf",
   "nodes": [
     {
       "id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
@@ -72,12 +73,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 925,
         "y": -200
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
@@ -167,12 +168,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 580,
       "position": {
         "x": 475,
         "y": -400
-      },
-      "width": 320,
-      "height": 506
+      }
     },
     {
       "id": "1b89067c-3f6b-42c8-991f-e3055789b251",
@@ -232,12 +233,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 925,
         "y": -400
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
@@ -303,12 +304,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 227,
       "position": {
         "x": 0,
         "y": -375
-      },
-      "width": 320,
-      "height": 193
+      }
     },
     {
       "id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
@@ -361,12 +362,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 925,
         "y": -275
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
@@ -464,12 +465,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 925,
         "y": 25
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
@@ -523,12 +524,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 925,
         "y": -50
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
@@ -635,12 +636,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 267,
       "position": {
         "x": 2037.861329274915,
         "y": -329.8393457509562
-      },
-      "width": 320,
-      "height": 224
+      }
     },
     {
       "id": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
@@ -653,7 +654,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
@@ -861,112 +862,112 @@
           }
         }
       },
+      "width": 320,
+      "height": 705,
       "position": {
         "x": 1570.9941088179146,
         "y": -407.6505491604564
-      },
-      "width": 320,
-      "height": 612
+      }
     }
   ],
   "edges": [
     {
       "id": "1b89067c-3f6b-42c8-991f-e3055789b251-fc9d0e35-a6de-4a19-84e1-c72497c823f6-collapsed",
-      "type": "collapsed",
       "source": "1b89067c-3f6b-42c8-991f-e3055789b251",
-      "target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6"
+      "target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
+      "type": "collapsed"
     },
     {
       "id": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5-0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77-collapsed",
-      "type": "collapsed",
       "source": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
-      "target": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77"
+      "target": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
+      "type": "collapsed"
     },
     {
       "id": "reactflow__edge-1b7e0df8-8589-4915-a4ea-c0088f15d642collection-1b89067c-3f6b-42c8-991f-e3055789b251collection",
-      "type": "default",
       "source": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
       "target": "1b89067c-3f6b-42c8-991f-e3055789b251",
+      "type": "default",
       "sourceHandle": "collection",
       "targetHandle": "collection"
     },
     {
       "id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426clip-fc9d0e35-a6de-4a19-84e1-c72497c823f6clip",
-      "type": "default",
       "source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
       "target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-1b89067c-3f6b-42c8-991f-e3055789b251item-fc9d0e35-a6de-4a19-84e1-c72497c823f6prompt",
-      "type": "default",
       "source": "1b89067c-3f6b-42c8-991f-e3055789b251",
       "target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
+      "type": "default",
       "sourceHandle": "item",
       "targetHandle": "prompt"
     },
     {
       "id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426clip-c2eaf1ba-5708-4679-9e15-945b8b432692clip",
-      "type": "default",
       "source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
       "target": "c2eaf1ba-5708-4679-9e15-945b8b432692",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5value-0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77seed",
-      "type": "default",
       "source": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
       "target": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     },
     {
       "id": "reactflow__edge-fc9d0e35-a6de-4a19-84e1-c72497c823f6conditioning-2fb1577f-0a56-4f12-8711-8afcaaaf1d5epositive_conditioning",
-      "type": "default",
       "source": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
       "target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-c2eaf1ba-5708-4679-9e15-945b8b432692conditioning-2fb1577f-0a56-4f12-8711-8afcaaaf1d5enegative_conditioning",
-      "type": "default",
       "source": "c2eaf1ba-5708-4679-9e15-945b8b432692",
       "target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77noise-2fb1577f-0a56-4f12-8711-8afcaaaf1d5enoise",
-      "type": "default",
       "source": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
       "target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426unet-2fb1577f-0a56-4f12-8711-8afcaaaf1d5eunet",
-      "type": "default",
       "source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
       "target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-2fb1577f-0a56-4f12-8711-8afcaaaf1d5elatents-491ec988-3c77-4c37-af8a-39a0c4e7a2a1latents",
-      "type": "default",
       "source": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
       "target": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426vae-491ec988-3c77-4c37-af8a-39a0c4e7a2a1vae",
-      "type": "default",
       "source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
       "target": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     }

invokeai/app/services/workflow_records/default_workflows/Text to Image with LoRA.json

@@ -25,9 +25,10 @@
     }
   ],
   "meta": {
-    "category": "default",
-    "version": "2.0.0"
+    "version": "2.0.0",
+    "category": "default"
   },
+  "id": "a9d70c39-4cdd-4176-9942-8ff3fe32d3b1",
   "nodes": [
     {
       "id": "85b77bb2-c67a-416a-b3e8-291abe746c44",
@@ -79,12 +80,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 3425,
         "y": -300
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
@@ -149,12 +150,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 227,
       "position": {
         "x": 2500,
         "y": -600
-      },
-      "width": 320,
-      "height": 193
+      }
     },
     {
       "id": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
@@ -242,12 +243,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 252,
       "position": {
         "x": 2975,
         "y": -600
-      },
-      "width": 320,
-      "height": 218
+      }
     },
     {
       "id": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
@@ -299,12 +300,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 256,
       "position": {
         "x": 3425,
         "y": -575
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
@@ -317,7 +318,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "inputs": {
           "positive_conditioning": {
             "id": "025ff44b-c4c6-4339-91b4-5f461e2cadc5",
@@ -524,12 +525,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 705,
       "position": {
         "x": 3975,
         "y": -575
-      },
-      "width": 320,
-      "height": 612
+      }
     },
     {
       "id": "ea18915f-2c5b-4569-b725-8e9e9122e8d3",
@@ -626,12 +627,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 3425,
         "y": 75
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "6fd74a17-6065-47a5-b48b-f4e2b8fa7953",
@@ -684,12 +685,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 3425,
         "y": 0
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
@@ -795,106 +796,106 @@
           }
         }
       },
+      "width": 320,
+      "height": 267,
       "position": {
         "x": 4450,
         "y": -550
-      },
-      "width": 320,
-      "height": 224
+      }
     }
   ],
   "edges": [
     {
       "id": "6fd74a17-6065-47a5-b48b-f4e2b8fa7953-ea18915f-2c5b-4569-b725-8e9e9122e8d3-collapsed",
-      "type": "collapsed",
       "source": "6fd74a17-6065-47a5-b48b-f4e2b8fa7953",
-      "target": "ea18915f-2c5b-4569-b725-8e9e9122e8d3"
+      "target": "ea18915f-2c5b-4569-b725-8e9e9122e8d3",
+      "type": "collapsed"
     },
     {
       "id": "reactflow__edge-24e9d7ed-4836-4ec4-8f9e-e747721f9818clip-c41e705b-f2e3-4d1a-83c4-e34bb9344966clip",
-      "type": "default",
       "source": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
       "target": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-c41e705b-f2e3-4d1a-83c4-e34bb9344966clip-c3fa6872-2599-4a82-a596-b3446a66cf8bclip",
-      "type": "default",
       "source": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
       "target": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-24e9d7ed-4836-4ec4-8f9e-e747721f9818unet-c41e705b-f2e3-4d1a-83c4-e34bb9344966unet",
-      "type": "default",
       "source": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
       "target": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-c41e705b-f2e3-4d1a-83c4-e34bb9344966unet-ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63unet",
-      "type": "default",
       "source": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
       "target": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-85b77bb2-c67a-416a-b3e8-291abe746c44conditioning-ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63negative_conditioning",
-      "type": "default",
       "source": "85b77bb2-c67a-416a-b3e8-291abe746c44",
       "target": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-c3fa6872-2599-4a82-a596-b3446a66cf8bconditioning-ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63positive_conditioning",
-      "type": "default",
       "source": "c3fa6872-2599-4a82-a596-b3446a66cf8b",
       "target": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-ea18915f-2c5b-4569-b725-8e9e9122e8d3noise-ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63noise",
-      "type": "default",
       "source": "ea18915f-2c5b-4569-b725-8e9e9122e8d3",
       "target": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-6fd74a17-6065-47a5-b48b-f4e2b8fa7953value-ea18915f-2c5b-4569-b725-8e9e9122e8d3seed",
-      "type": "default",
       "source": "6fd74a17-6065-47a5-b48b-f4e2b8fa7953",
       "target": "ea18915f-2c5b-4569-b725-8e9e9122e8d3",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     },
     {
       "id": "reactflow__edge-ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63latents-a9683c0a-6b1f-4a5e-8187-c57e764b3400latents",
-      "type": "default",
       "source": "ad487d0c-dcbb-49c5-bb8e-b28d4cbc5a63",
       "target": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-24e9d7ed-4836-4ec4-8f9e-e747721f9818vae-a9683c0a-6b1f-4a5e-8187-c57e764b3400vae",
-      "type": "default",
       "source": "24e9d7ed-4836-4ec4-8f9e-e747721f9818",
       "target": "a9683c0a-6b1f-4a5e-8187-c57e764b3400",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
       "id": "reactflow__edge-c41e705b-f2e3-4d1a-83c4-e34bb9344966clip-85b77bb2-c67a-416a-b3e8-291abe746c44clip",
-      "type": "default",
       "source": "c41e705b-f2e3-4d1a-83c4-e34bb9344966",
       "target": "85b77bb2-c67a-416a-b3e8-291abe746c44",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     }

invokeai/app/services/workflow_records/default_workflows/TextToImage_SD15.json

@@ -84,12 +84,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 259,
       "position": {
         "x": 1000,
         "y": 350
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "55705012-79b9-4aac-9f26-c0b10309785b",
@@ -187,12 +187,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 388,
       "position": {
         "x": 600,
         "y": 325
-      },
-      "width": 320,
-      "height": 388
+      }
     },
     {
       "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
@@ -258,12 +258,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 226,
       "position": {
         "x": 600,
         "y": 25
-      },
-      "width": 320,
-      "height": 193
+      }
     },
     {
       "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
@@ -316,12 +316,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 259,
       "position": {
         "x": 1000,
         "y": 25
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
@@ -375,12 +375,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 600,
         "y": 275
-      },
-      "width": 320,
-      "height": 32
+      }
     },
     {
       "id": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
@@ -393,7 +393,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
@@ -601,12 +601,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 703,
       "position": {
         "x": 1400,
         "y": 25
-      },
-      "width": 320,
-      "height": 612
+      }
     },
     {
       "id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
@@ -713,86 +713,86 @@
           }
         }
       },
+      "width": 320,
+      "height": 266,
       "position": {
         "x": 1800,
         "y": 25
-      },
-      "width": 320,
-      "height": 224
+      }
     }
   ],
   "edges": [
     {
       "id": "reactflow__edge-ea94bc37-d995-4a83-aa99-4af42479f2f2value-55705012-79b9-4aac-9f26-c0b10309785bseed",
-      "type": "default",
       "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
       "target": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     },
     {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-7d8bf987-284f-413a-b2fd-d825445a5d6cclip",
-      "type": "default",
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
       "target": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-93dc02a4-d05b-48ed-b99c-c9b616af3402clip",
-      "type": "default",
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
       "target": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-eea2702a-19fb-45b5-9d75-56b4211ec03cnoise",
-      "type": "default",
       "source": "55705012-79b9-4aac-9f26-c0b10309785b",
       "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-7d8bf987-284f-413a-b2fd-d825445a5d6cconditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cpositive_conditioning",
-      "type": "default",
       "source": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
       "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-93dc02a4-d05b-48ed-b99c-c9b616af3402conditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cnegative_conditioning",
-      "type": "default",
       "source": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
       "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8unet-eea2702a-19fb-45b5-9d75-56b4211ec03cunet",
-      "type": "default",
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
       "target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-eea2702a-19fb-45b5-9d75-56b4211ec03clatents-58c957f5-0d01-41fc-a803-b2bbf0413d4flatents",
-      "type": "default",
       "source": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
       "target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8vae-58c957f5-0d01-41fc-a803-b2bbf0413d4fvae",
-      "type": "default",
       "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
       "target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     }
   ]
-}
+}

invokeai/app/services/workflow_records/default_workflows/TextToImage_SDXL.json

@@ -80,12 +80,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 750,
         "y": -225
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "719dabe8-8297-4749-aea1-37be301cd425",
@@ -126,12 +126,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 258,
       "position": {
         "x": 750,
         "y": -125
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
@@ -279,12 +279,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 750,
         "y": 200
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "55705012-79b9-4aac-9f26-c0b10309785b",
@@ -382,12 +382,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 388,
       "position": {
         "x": 375,
         "y": 0
-      },
-      "width": 320,
-      "height": 336
+      }
     },
     {
       "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
@@ -441,12 +441,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 375,
         "y": -50
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
@@ -471,7 +471,8 @@
               "isCollection": false,
               "isCollectionOrScalar": false,
               "name": "SDXLMainModelField"
-            }
+            },
+            "value": null
           }
         },
         "outputs": {
@@ -517,12 +518,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 257,
       "position": {
         "x": 375,
         "y": -500
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
@@ -670,12 +671,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 750,
         "y": -175
-      },
-      "width": 320,
-      "height": 24
+      }
     },
     {
       "id": "63e91020-83b2-4f35-b174-ad9692aabb48",
@@ -782,12 +783,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 266,
       "position": {
         "x": 1475,
         "y": -500
-      },
-      "width": 320,
-      "height": 224
+      }
     },
     {
       "id": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
@@ -800,7 +801,7 @@
         "notes": "",
         "isIntermediate": true,
         "useCache": true,
-        "version": "1.5.1",
+        "version": "1.5.0",
         "nodePack": "invokeai",
         "inputs": {
           "positive_conditioning": {
@@ -1008,12 +1009,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 702,
       "position": {
         "x": 1125,
         "y": -500
-      },
-      "width": 320,
-      "height": 612
+      }
     },
     {
       "id": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
@@ -1037,7 +1038,8 @@
               "isCollection": false,
               "isCollectionOrScalar": false,
               "name": "VAEModelField"
-            }
+            },
+            "value": null
           }
         },
         "outputs": {
@@ -1053,12 +1055,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 161,
       "position": {
         "x": 375,
         "y": -225
-      },
-      "width": 320,
-      "height": 139
+      }
     },
     {
       "id": "ade2c0d3-0384-4157-b39b-29ce429cfa15",
@@ -1099,12 +1101,12 @@
           }
         }
       },
+      "width": 320,
+      "height": 258,
       "position": {
         "x": 750,
         "y": -500
-      },
-      "width": 320,
-      "height": 219
+      }
     },
     {
       "id": "ad8fa655-3a76-43d0-9c02-4d7644dea650",
@@ -1157,162 +1159,162 @@
           }
         }
       },
+      "width": 320,
+      "height": 32,
       "position": {
         "x": 750,
         "y": 150
-      },
-      "width": 320,
-      "height": 24
+      }
     }
   ],
   "edges": [
     {
       "id": "3774ec24-a69e-4254-864c-097d07a6256f-faf965a4-7530-427b-b1f3-4ba6505c2a08-collapsed",
-      "type": "collapsed",
       "source": "3774ec24-a69e-4254-864c-097d07a6256f",
-      "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08"
+      "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "collapsed"
     },
     {
       "id": "ad8fa655-3a76-43d0-9c02-4d7644dea650-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204-collapsed",
-      "type": "collapsed",
       "source": "ad8fa655-3a76-43d0-9c02-4d7644dea650",
-      "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204"
+      "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "collapsed"
     },
     {
       "id": "reactflow__edge-ea94bc37-d995-4a83-aa99-4af42479f2f2value-55705012-79b9-4aac-9f26-c0b10309785bseed",
-      "type": "default",
       "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
       "target": "55705012-79b9-4aac-9f26-c0b10309785b",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "seed"
     },
     {
       "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip-faf965a4-7530-427b-b1f3-4ba6505c2a08clip",
-      "type": "default",
       "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
       "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip2-faf965a4-7530-427b-b1f3-4ba6505c2a08clip2",
-      "type": "default",
       "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
       "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "default",
       "sourceHandle": "clip2",
       "targetHandle": "clip2"
     },
     {
       "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204clip",
-      "type": "default",
       "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
       "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "default",
       "sourceHandle": "clip",
       "targetHandle": "clip"
     },
     {
       "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip2-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204clip2",
-      "type": "default",
       "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
       "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "default",
       "sourceHandle": "clip2",
       "targetHandle": "clip2"
     },
     {
       "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22unet-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbunet",
-      "type": "default",
       "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
       "target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
+      "type": "default",
       "sourceHandle": "unet",
       "targetHandle": "unet"
     },
     {
       "id": "reactflow__edge-faf965a4-7530-427b-b1f3-4ba6505c2a08conditioning-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbpositive_conditioning",
-      "type": "default",
       "source": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
       "target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "positive_conditioning"
     },
     {
       "id": "reactflow__edge-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204conditioning-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbnegative_conditioning",
-      "type": "default",
       "source": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
       "target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
+      "type": "default",
       "sourceHandle": "conditioning",
       "targetHandle": "negative_conditioning"
     },
     {
       "id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbnoise",
-      "type": "default",
       "source": "55705012-79b9-4aac-9f26-c0b10309785b",
       "target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
+      "type": "default",
       "sourceHandle": "noise",
       "targetHandle": "noise"
     },
     {
       "id": "reactflow__edge-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfblatents-63e91020-83b2-4f35-b174-ad9692aabb48latents",
-      "type": "default",
       "source": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
       "target": "63e91020-83b2-4f35-b174-ad9692aabb48",
+      "type": "default",
       "sourceHandle": "latents",
       "targetHandle": "latents"
     },
     {
       "id": "reactflow__edge-0093692f-9cf4-454d-a5b8-62f0e3eb3bb8vae-63e91020-83b2-4f35-b174-ad9692aabb48vae",
-      "type": "default",
       "source": "0093692f-9cf4-454d-a5b8-62f0e3eb3bb8",
       "target": "63e91020-83b2-4f35-b174-ad9692aabb48",
+      "type": "default",
       "sourceHandle": "vae",
       "targetHandle": "vae"
     },
     {
       "id": "reactflow__edge-ade2c0d3-0384-4157-b39b-29ce429cfa15value-faf965a4-7530-427b-b1f3-4ba6505c2a08prompt",
-      "type": "default",
       "source": "ade2c0d3-0384-4157-b39b-29ce429cfa15",
       "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "prompt"
     },
     {
       "id": "reactflow__edge-719dabe8-8297-4749-aea1-37be301cd425value-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204prompt",
-      "type": "default",
       "source": "719dabe8-8297-4749-aea1-37be301cd425",
       "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "prompt"
     },
     {
       "id": "reactflow__edge-719dabe8-8297-4749-aea1-37be301cd425value-ad8fa655-3a76-43d0-9c02-4d7644dea650string_left",
-      "type": "default",
       "source": "719dabe8-8297-4749-aea1-37be301cd425",
       "target": "ad8fa655-3a76-43d0-9c02-4d7644dea650",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "string_left"
     },
     {
       "id": "reactflow__edge-ad8fa655-3a76-43d0-9c02-4d7644dea650value-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204style",
-      "type": "default",
       "source": "ad8fa655-3a76-43d0-9c02-4d7644dea650",
       "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "style"
     },
     {
       "id": "reactflow__edge-ade2c0d3-0384-4157-b39b-29ce429cfa15value-3774ec24-a69e-4254-864c-097d07a6256fstring_left",
-      "type": "default",
       "source": "ade2c0d3-0384-4157-b39b-29ce429cfa15",
       "target": "3774ec24-a69e-4254-864c-097d07a6256f",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "string_left"
     },
     {
       "id": "reactflow__edge-3774ec24-a69e-4254-864c-097d07a6256fvalue-faf965a4-7530-427b-b1f3-4ba6505c2a08style",
-      "type": "default",
       "source": "3774ec24-a69e-4254-864c-097d07a6256f",
       "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
+      "type": "default",
       "sourceHandle": "value",
       "targetHandle": "style"
     }
   ]
-}
+}

invokeai/app/services/workflow_records/workflow_records_common.py

@@ -31,7 +31,6 @@ class WorkflowRecordOrderBy(str, Enum, metaclass=MetaEnum):
 class WorkflowCategory(str, Enum, metaclass=MetaEnum):
     User = "user"
     Default = "default"
-    Project = "project"
 
 
 class WorkflowMeta(BaseModel):

invokeai/app/util/misc.py

@@ -5,7 +5,7 @@ import uuid
 import numpy as np
 
 
-def get_timestamp() -> int:
+def get_timestamp():
     return int(datetime.datetime.now(datetime.timezone.utc).timestamp())
 
 
@@ -20,16 +20,16 @@ def get_datetime_from_iso_timestamp(iso_timestamp: str) -> datetime.datetime:
 SEED_MAX = np.iinfo(np.uint32).max
 
 
-def get_random_seed() -> int:
+def get_random_seed():
     rng = np.random.default_rng(seed=None)
     return int(rng.integers(0, SEED_MAX))
 
 
-def uuid_string() -> str:
+def uuid_string():
     res = uuid.uuid4()
     return str(res)
 
 
-def is_optional(value: typing.Any) -> bool:
+def is_optional(value: typing.Any):
     """Checks if a value is typed as Optional. Note that Optional is sugar for Union[x, None]."""
     return typing.get_origin(value) is typing.Union and type(None) in typing.get_args(value)

invokeai/app/util/profiler.py

@@ -1,67 +0,0 @@
-import cProfile
-from logging import Logger
-from pathlib import Path
-from typing import Optional
-
-
-class Profiler:
-    """
-    Simple wrapper around cProfile.
-
-    Usage
-    ```
-      # Create a profiler
-      profiler = Profiler(logger, output_dir, "sql_query_perf")
-      # Start a new profile
-      profiler.start("my_profile")
-      # Do stuff
-      profiler.stop()
-    ```
-
-    Visualize a profile as a flamegraph with [snakeviz](https://jiffyclub.github.io/snakeviz/)
-    ```sh
-      snakeviz my_profile.prof
-    ```
-
-    Visualize a profile as directed graph with [graphviz](https://graphviz.org/download/) & [gprof2dot](https://github.com/jrfonseca/gprof2dot)
-    ```sh
-      gprof2dot -f pstats my_profile.prof | dot -Tpng -o my_profile.png
-      # SVG or PDF may be nicer - you can search for function names
-      gprof2dot -f pstats my_profile.prof | dot -Tsvg -o my_profile.svg
-      gprof2dot -f pstats my_profile.prof | dot -Tpdf -o my_profile.pdf
-    ```
-    """
-
-    def __init__(self, logger: Logger, output_dir: Path, prefix: Optional[str] = None) -> None:
-        self._logger = logger.getChild(f"profiler.{prefix}" if prefix else "profiler")
-        self._output_dir = output_dir
-        self._output_dir.mkdir(parents=True, exist_ok=True)
-        self._profiler: Optional[cProfile.Profile] = None
-        self._prefix = prefix
-
-        self.profile_id: Optional[str] = None
-
-    def start(self, profile_id: str) -> None:
-        if self._profiler:
-            self.stop()
-
-        self.profile_id = profile_id
-
-        self._profiler = cProfile.Profile()
-        self._profiler.enable()
-        self._logger.info(f"Started profiling {self.profile_id}.")
-
-    def stop(self) -> Path:
-        if not self._profiler:
-            raise RuntimeError("Profiler not initialized. Call start() first.")
-        self._profiler.disable()
-
-        filename = f"{self._prefix}_{self.profile_id}.prof" if self._prefix else f"{self.profile_id}.prof"
-        path = Path(self._output_dir, filename)
-
-        self._profiler.dump_stats(path)
-        self._logger.info(f"Stopped profiling, profile dumped to {path}.")
-        self._profiler = None
-        self.profile_id = None
-
-        return path

invokeai/app/util/step_callback.py

@@ -3,7 +3,7 @@ from PIL import Image
 
 from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException, ProgressImage
 
-from ...backend.model_manager import BaseModelType
+from ...backend.model_management.models import BaseModelType
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.util.util import image_to_dataURL
 from ..invocations.baseinvocation import InvocationContext

invokeai/backend/__init__.py

@@ -1,3 +1,5 @@
 """
 Initialization file for invokeai.backend
 """
+from .model_management import BaseModelType, ModelCache, ModelInfo, ModelManager, ModelType, SubModelType  # noqa: F401
+from .model_management.models import SilenceWarnings  # noqa: F401

invokeai/backend/embeddings/__init__.py

@@ -1,4 +0,0 @@
-"""Initialization file for invokeai.backend.embeddings modules."""
-
-# from .model_patcher import ModelPatcher
-# __all__ = ["ModelPatcher"]

invokeai/backend/embeddings/embedding_base.py

@@ -1,12 +0,0 @@
-"""Base class for LoRA and Textual Inversion models.
-
-The EmbeddingRaw class is the base class of LoRAModelRaw and TextualInversionModelRaw,
-and is used for type checking of calls to the model patcher.
-
-The use of "Raw" here is a historical artifact, and carried forward in
-order to avoid confusion.
-"""
-
-
-class EmbeddingModelRaw:
-    """Base class for LoRA and Textual Inversion models."""