update requirements to address #1149

Taken from `main` PR #1147 
Author: eltociear

.github/workflows/create-caches.yml

@@ -1,26 +1,43 @@
 name: Create Caches
-on:
-  workflow_dispatch
+
+on: workflow_dispatch
+
 jobs:
-  build:
+  os_matrix:
     strategy:
       matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Create Caches on ${{ matrix.os }} conda
+        os: [ubuntu-latest, macos-latest]
+        include:
+          - os: ubuntu-latest
+            environment-file: environment.yml
+            default-shell: bash -l {0}
+          - os: macos-latest
+            environment-file: environment-mac.yml
+            default-shell: bash -l {0}
+    name: Test invoke.py on ${{ matrix.os }} with conda
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
     steps:
-      - name: Set platform variables
-        id: vars
-        run: |
-            if [ "$RUNNER_OS" = "macOS" ]; then
-                echo "::set-output name=ENV_FILE::environment-mac.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-            elif [ "$RUNNER_OS" = "Linux" ]; then
-                echo "::set-output name=ENV_FILE::environment.yml"
-                echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-            fi
       - name: Checkout sources
         uses: actions/checkout@v3
+
+      - name: setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-activate-base: false
+          auto-update-conda: false
+          miniconda-version: latest
+
+      - name: set environment
+        run: |
+          [[ "$GITHUB_REF" == 'refs/heads/main' ]] \
+            && echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV \
+            || echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+          echo "CONDA_ROOT=$CONDA" >> $GITHUB_ENV
+          echo "CONDA_ENV_NAME=invokeai" >> $GITHUB_ENV
+
       - name: Use Cached Stable Diffusion v1.4 Model
         id: cache-sd-v1-4
         uses: actions/cache@v3
@@ -29,42 +46,52 @@ jobs:
         with:
           path: models/ldm/stable-diffusion-v1/model.ckpt
           key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
+          restore-keys: ${{ env.cache-name }}
+
       - name: Download Stable Diffusion v1.4 Model
         if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
         run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
+          [[ -d models/ldm/stable-diffusion-v1 ]] \
+            || mkdir -p models/ldm/stable-diffusion-v1
+          [[ -r models/ldm/stable-diffusion-v1/model.ckpt ]] \
+            || curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
+
+      - name: Use cached Conda Environment
         uses: actions/cache@v3
         env:
-          cache-name: cache-conda-env-ldm
+          cache-name: cache-conda-env-${{ env.CONDA_ENV_NAME }}
+          conda-env-file: ${{ matrix.environment-file }}
         with:
-          path: ~/.conda/envs/ldm
+          path: ${{ env.CONDA_ROOT }}/envs/${{ env.CONDA_ENV_NAME }}
           key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
-        run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
-      - name: Use Cached Huggingface and Torch models
-        id: cache-huggingface-torch
+          restore-keys: ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(env.conda-env-file) }}
+
+      - name: Use cached Conda Packages
         uses: actions/cache@v3
         env:
-          cache-name: cache-huggingface-torch
+          cache-name: cache-conda-env-${{ env.CONDA_ENV_NAME }}
+          conda-env-file: ${{ matrix.environment-file }}
+        with:
+          path: ${{ env.CONDA_PKGS_DIR }}
+          key: ${{ env.cache-name }}
+          restore-keys: ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(env.conda-env-file) }}
+
+      - name: Activate Conda Env
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+
+      - name: Use Cached Huggingface and Torch models
+        id: cache-hugginface-torch
+        uses: actions/cache@v3
+        env:
+          cache-name: cache-hugginface-torch
         with:
           path: ~/.cache
           key: ${{ env.cache-name }}
           restore-keys: |
             ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-huggingface-torch.outputs.cache-hit != 'true' }}
-        run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
+
+      - name: run preload_models.py
+        run: python scripts/preload_models.py

.github/workflows/mkdocs-flow.yml

@@ -1,28 +0,0 @@
-name: Deploy
-on:
-  push:
-    branches:
-      - main
-  # pull_request:
-  #   branches:
-  #     - main
-jobs:
-  build:
-    name: Deploy docs to GitHub Pages
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - name: Build
-        uses: Tiryoh/actions-mkdocs@v0
-        with:
-          mkdocs_version: 'latest' # option
-          requirements: '/requirements-mkdocs.txt' # option
-          configfile: '/mkdocs.yml' # option
-      - name: Deploy
-        uses: peaceiris/actions-gh-pages@v3
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: ./site

.github/workflows/mkdocs-material.yml

@@ -0,0 +1,40 @@
+name: mkdocs-material
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  mkdocs-material:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout sources
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: install requirements
+        run: |
+          python -m \
+            pip install -r requirements-mkdocs.txt
+
+      - name: confirm buildability
+        run: |
+          python -m \
+            mkdocs build \
+            --clean \
+            --verbose
+
+      - name: deploy to gh-pages
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: |
+          python -m \
+            mkdocs gh-deploy \
+            --clean \
+            --force

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

@@ -4,29 +4,55 @@ on:
     branches:
       - 'main'
       - 'development'
+      - 'fix-gh-actions-fork'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
 jobs:
   os_matrix:
     strategy:
       matrix:
-        os: [ ubuntu-latest, macos-12 ]
+        os: [ubuntu-latest, macos-latest]
+        include:
+          - os: ubuntu-latest
+            environment-file: environment.yml
+            default-shell: bash -l {0}
+          - os: macos-latest
+            environment-file: environment-mac.yml
+            default-shell: bash -l {0}
     name: Test invoke.py on ${{ matrix.os }} with conda
     runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
     steps:
-      - run: |
-          echo The PR was merged
-      - name: Set platform variables
-        id: vars
-        run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ "$RUNNER_OS" = "macOS" ]; then
-              echo "::set-output name=ENV_FILE::environment-mac.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/local/miniconda/envs/ldm/bin/python"
-          elif [ "$RUNNER_OS" = "Linux" ]; then
-              echo "::set-output name=ENV_FILE::environment.yml"
-              echo "::set-output name=PYTHON_BIN::/usr/share/miniconda/envs/ldm/bin/python"
-          fi
       - name: Checkout sources
         uses: actions/checkout@v3
+
+      - name: setup miniconda
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-activate-base: false
+          auto-update-conda: false
+          miniconda-version: latest
+
+      - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to development branch validation
+        if: ${{ github.ref == 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/dev_prompts.txt" >> $GITHUB_ENV
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' && github.ref != 'refs/heads/development' }}
+        run: echo "TEST_PROMPTS=tests/pr_prompt.txt" >> $GITHUB_ENV
+
+      - name: set conda environment name
+        run: echo "CONDA_ENV_NAME=invokeai" >> $GITHUB_ENV
+
       - name: Use Cached Stable Diffusion v1.4 Model
         id: cache-sd-v1-4
         uses: actions/cache@v3
@@ -35,31 +61,40 @@ jobs:
         with:
           path: models/ldm/stable-diffusion-v1/model.ckpt
           key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}
+          restore-keys: ${{ env.cache-name }}
+
       - name: Download Stable Diffusion v1.4 Model
         if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
         run: |
-          if [ ! -e models/ldm/stable-diffusion-v1 ]; then
-              mkdir -p models/ldm/stable-diffusion-v1
-          fi
-          if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
-            curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
-          fi
-      - name: Use Cached Dependencies
-        id: cache-conda-env-ldm
+          [[ -d models/ldm/stable-diffusion-v1 ]] \
+            || mkdir -p models/ldm/stable-diffusion-v1
+          [[ -r models/ldm/stable-diffusion-v1/model.ckpt ]] \
+            || curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
+
+      - name: Use cached Conda Environment
         uses: actions/cache@v3
         env:
-          cache-name: cache-conda-env-ldm
+          cache-name: cache-conda-env-${{ env.CONDA_ENV_NAME }}
+          conda-env-file: ${{ matrix.environment-file }}
         with:
-          path: ~/.conda/envs/ldm
-          key: ${{ env.cache-name }}
-          restore-keys: |
-            ${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(steps.vars.outputs.ENV_FILE) }}
-      - name: Install Dependencies
-        if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
-        run: |
-          conda env create -f ${{ steps.vars.outputs.ENV_FILE }}
+          path: ${{ env.CONDA }}/envs/${{ env.CONDA_ENV_NAME }}
+          key: env-${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(env.conda-env-file) }}
+
+      - name: Use cached Conda Packages
+        uses: actions/cache@v3
+        env:
+          cache-name: cache-conda-pkgs-${{ env.CONDA_ENV_NAME }}
+          conda-env-file: ${{ matrix.environment-file }}
+        with:
+          path: ${{ env.CONDA_PKGS_DIR }}
+          key: pkgs-${{ env.cache-name }}-${{ runner.os }}-${{ hashFiles(env.conda-env-file) }}
+
+      - name: Activate Conda Env
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+
       - name: Use Cached Huggingface and Torch models
         id: cache-hugginface-torch
         uses: actions/cache@v3
@@ -70,28 +105,22 @@ jobs:
           key: ${{ env.cache-name }}
           restore-keys: |
             ${{ env.cache-name }}-${{ hashFiles('scripts/preload_models.py') }}
-      - name: Download Huggingface and Torch models
-        if: ${{ steps.cache-hugginface-torch.outputs.cache-hit != 'true' }}
-        run: |
-          ${{ steps.vars.outputs.PYTHON_BIN }} scripts/preload_models.py
-#       - name: Run tmate
-#         uses: mxschmitt/action-tmate@v3
-#         timeout-minutes: 30
+
+      - name: run preload_models.py
+        run: python scripts/preload_models.py
+
       - name: Run the tests
         run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ $(uname) = "Darwin" ]; then
-              export PYTORCH_ENABLE_MPS_FALLBACK=1
-          fi
-          # Utterly hacky, but I don't know how else to do this
-          if [[ ${{ github.ref }} == 'refs/heads/master' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/preflight_prompts.txt
-          elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/dev_prompts.txt
-          fi
+          time python scripts/invoke.py \
+            --from_file ${{ env.TEST_PROMPTS }}
+
+      - name: export conda env
+        run: |
           mkdir -p outputs/img-samples
+          conda env export --name ${{ env.CONDA_ENV_NAME }} > outputs/img-samples/environment-${{ runner.os }}.yml
+
       - name: Archive results
         uses: actions/upload-artifact@v3
         with:
-          name: results
+          name: results_${{ matrix.os }}
           path: outputs/img-samples

.gitignore

@@ -1,7 +1,7 @@
 # ignore default image save location and model symbolic link
 outputs/
 models/ldm/stable-diffusion-v1/model.ckpt
-ldm/dream/restoration/codeformer/weights
+**/restoration/codeformer/weights
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -180,7 +180,7 @@ src
 **/__pycache__/
 outputs
 
-# Logs and associated folders 
+# Logs and associated folders
 # created from generated embeddings.
 logs
 testtube

LICENSE

@@ -1,17 +1,6 @@
 MIT License
 
-Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
-
-This software is derived from a fork of the source code available from
-https://github.com/pesser/stable-diffusion and
-https://github.com/CompViz/stable-diffusion. They carry the following
-copyrights:
-
-Copyright (c) 2022 Machine Vision and Learning Group, LMU Munich
-Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
-
-Please see individual source code files for copyright and authorship
-attributions.
+Copyright (c) 2022 InvokeAI Team
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -68,11 +68,11 @@ requests. Be sure to use the provided templates. They will help aid diagnose iss
 This fork is supported across multiple platforms. You can find individual installation instructions
 below.
 
-- #### [Linux](docs/installation/INSTALL_LINUX.md)
+- #### [Linux](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_LINUX/)
 
-- #### [Windows](docs/installation/INSTALL_WINDOWS.md)
+- #### [Windows](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_WINDOWS/)
 
-- #### [Macintosh](docs/installation/INSTALL_MAC.md)
+- #### [Macintosh](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_MAC/)
 
 ### Hardware Requirements
 
@@ -103,34 +103,33 @@ errors like 'expected type Float but found Half' or 'not implemented for Half'
 you can try starting `invoke.py` with the `--precision=float32` flag:
 
 ```bash
-(ldm) ~/stable-diffusion$ python scripts/invoke.py --precision=float32
+(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
 ```
 
 ### Features
 
 #### Major Features
 
-- [Web Server](docs/features/WEB.md)
-- [Interactive Command Line Interface](docs/features/CLI.md)
-- [Image To Image](docs/features/IMG2IMG.md)
-- [Inpainting Support](docs/features/INPAINTING.md)
-- [Outpainting Support](docs/features/OUTPAINTING.md)
-- [Upscaling, face-restoration and outpainting](docs/features/POSTPROCESS.md)
-- [Seamless Tiling](docs/features/OTHER.md#seamless-tiling)
-- [Google Colab](docs/features/OTHER.md#google-colab)
-- [Reading Prompts From File](docs/features/PROMPTS.md#reading-prompts-from-a-file)
-- [Shortcut: Reusing Seeds](docs/features/OTHER.md#shortcuts-reusing-seeds)
-- [Prompt Blending](docs/features/PROMPTS.md#prompt-blending)
-- [Thresholding and Perlin Noise Initialization Options](/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
-- [Negative/Unconditioned Prompts](docs/features/PROMPTS.md#negative-and-unconditioned-prompts)
-- [Variations](docs/features/VARIATIONS.md)
-- [Personalizing Text-to-Image Generation](docs/features/TEXTUAL_INVERSION.md)
-- [Simplified API for text to image generation](docs/features/OTHER.md#simplified-api)
+- [Web Server](https://invoke-ai.github.io/InvokeAI/features/WEB/)
+- [Interactive Command Line Interface](https://invoke-ai.github.io/InvokeAI/features/CLI/)
+- [Image To Image](https://invoke-ai.github.io/InvokeAI/features/IMG2IMG/)
+- [Inpainting Support](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/)
+- [Outpainting Support](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/)
+- [Upscaling, face-restoration and outpainting](https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/)
+- [Reading Prompts From File](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#reading-prompts-from-a-file)
+- [Prompt Blending](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#prompt-blending)
+- [Thresholding and Perlin Noise Initialization Options](https://invoke-ai.github.io/InvokeAI/features/OTHER/#thresholding-and-perlin-noise-initialization-options)
+- [Negative/Unconditioned Prompts](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts)
+- [Variations](https://invoke-ai.github.io/InvokeAI/features/VARIATIONS/)
+- [Personalizing Text-to-Image Generation](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
+- [Simplified API for text to image generation](https://invoke-ai.github.io/InvokeAI/features/OTHER/#simplified-api)
 
 #### Other Features
 
-- [Creating Transparent Regions for Inpainting](docs/features/INPAINTING.md#creating-transparent-regions-for-inpainting)
-- [Preload Models](docs/features/OTHER.md#preload-models)
+- [Google Colab](https://invoke-ai.github.io/InvokeAI/features/OTHER/#google-colab)
+- [Seamless Tiling](https://invoke-ai.github.io/InvokeAI/features/OTHER/#seamless-tiling)
+- [Shortcut: Reusing Seeds](https://invoke-ai.github.io/InvokeAI/features/OTHER/#shortcuts-reusing-seeds)
+- [Preload Models](https://invoke-ai.github.io/InvokeAI/features/OTHER/#preload-models)
 
 ### Latest Changes
 
@@ -144,33 +143,33 @@ you can try starting `invoke.py` with the `--precision=float32` flag:
   - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
     for backward compatibility.
   - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-  - Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/INPAINTING.md">inpainting</a> and <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OUTPAINTING.md">outpainting</a>
+  - Support for <a href="https://invoke-ai.github.io/InvokeAI/features/INPAINTING/">inpainting</a> and <a href="https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/">outpainting</a>
   - img2img runs on all k* samplers
-  - Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/PROMPTS.md#negative-and-unconditioned-prompts">negative prompts</a>
+  - Support for <a href="https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts">negative prompts</a>
   - Support for CodeFormer face reconstruction
   - Support for Textual Inversion on Macintoshes
-  - Support in both WebGUI and CLI for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/POSTPROCESS.md">post-processing of previously-generated images</a>
+  - Support in both WebGUI and CLI for <a href="https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/">post-processing of previously-generated images</a>
     using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
     and "embiggen" upscaling. See the `!fix` command.
-  - New `--hires` option on `invoke>` line allows <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.md#this-is-an-example-of-txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
+  - New `--hires` option on `invoke>` line allows <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/#txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
   - New `--perlin` and `--threshold` options allow you to add and control variation
     during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
   - Extensive metadata now written into PNG files, allowing reliable regeneration of images
     and tweaking of previous settings.
   - Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
-  - Improved <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.md">command-line completion behavior</a>.
+  - Improved <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/">command-line completion behavior</a>.
     New commands added:
-       * List command-line history with `!history`
-       * Search command-line history with `!search`
-       * Clear history with `!clear`
+    - List command-line history with `!history`
+    - Search command-line history with `!search`
+    - Clear history with `!clear`
   - Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
     configure. To switch away from auto use the new flag like `--precision=float32`.
 
-For older changelogs, please visit the **[CHANGELOG](docs/features/CHANGELOG.md)**.
+For older changelogs, please visit the **[CHANGELOG](https://invoke-ai.github.io/InvokeAI/CHANGELOG#v114-11-september-2022)**.
 
 ### Troubleshooting
 
-Please check out our **[Q&A](docs/help/TROUBLESHOOT.md)** to get solutions for common installation
+Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
 
 # Contributing
@@ -188,7 +187,7 @@ changes.
 ### Contributors
 
 This fork is a combined effort of various people from across the world.
-[Check out the list of all these amazing people](docs/other/CONTRIBUTORS.md). We thank them for
+[Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
 ### Support
@@ -202,4 +201,4 @@ Original portions of the software are Copyright (c) 2020
 ### Further Reading
 
 Please see the original README for more information on this software and underlying algorithm,
-located in the file [README-CompViz.md](docs/other/README-CompViz.md).
+located in the file [README-CompViz.md](https://invoke-ai.github.io/InvokeAI/other/README-CompViz/).

backend/invoke_ai_web_server.py

@@ -319,7 +319,7 @@ class InvokeAIWebServer:
                 elif postprocessing_parameters['type'] == 'gfpgan':
                     image = self.gfpgan.process(
                         image=image,
-                        strength=postprocessing_parameters['gfpgan_strength'],
+                        strength=postprocessing_parameters['facetool_strength'],
                         seed=seed,
                     )
                 else:
@@ -625,7 +625,7 @@ class InvokeAIWebServer:
                         seed=seed,
                     )
                     postprocessing = True
-                    all_parameters['gfpgan_strength'] = gfpgan_parameters[
+                    all_parameters['facetool_strength'] = gfpgan_parameters[
                         'strength'
                     ]
 
@@ -723,6 +723,7 @@ class InvokeAIWebServer:
                 'height',
                 'extra',
                 'seamless',
+                'hires_fix',
             ]
 
             rfc_dict = {}
@@ -735,12 +736,12 @@ class InvokeAIWebServer:
             postprocessing = []
 
             # 'postprocessing' is either null or an
-            if 'gfpgan_strength' in parameters:
+            if 'facetool_strength' in parameters:
 
                 postprocessing.append(
                     {
                         'type': 'gfpgan',
-                        'strength': float(parameters['gfpgan_strength']),
+                        'strength': float(parameters['facetool_strength']),
                     }
                 )
 
@@ -837,7 +838,7 @@ class InvokeAIWebServer:
             elif parameters['type'] == 'gfpgan':
                 postprocessing_metadata['type'] = 'gfpgan'
                 postprocessing_metadata['strength'] = parameters[
-                    'gfpgan_strength'
+                    'facetool_strength'
                 ]
             else:
                 raise TypeError(f"Invalid type: {parameters['type']}")

backend/modules/parameters.py

@@ -36,6 +36,8 @@ def parameters_to_command(params):
         switches.append(f'-A {params["sampler_name"]}')
     if "seamless" in params and params["seamless"] == True:
         switches.append(f"--seamless")
+    if "hires_fix" in params and params["hires_fix"] == True:
+        switches.append(f"--hires")
     if "init_img" in params and len(params["init_img"]) > 0:
         switches.append(f'-I {params["init_img"]}')
     if "init_mask" in params and len(params["init_mask"]) > 0:
@@ -46,8 +48,14 @@ def parameters_to_command(params):
         switches.append(f'-f {params["strength"]}')
         if "fit" in params and params["fit"] == True:
             switches.append(f"--fit")
-    if "gfpgan_strength" in params and params["gfpgan_strength"]:
+    if "facetool" in params:
+        switches.append(f'-ft {params["facetool"]}')
+    if "facetool_strength" in params and params["facetool_strength"]:
+        switches.append(f'-G {params["facetool_strength"]}')
+    elif "gfpgan_strength" in params and params["gfpgan_strength"]:
         switches.append(f'-G {params["gfpgan_strength"]}')
+    if "codeformer_fidelity" in params:
+        switches.append(f'-cf {params["codeformer_fidelity"]}')
     if "upscale" in params and params["upscale"]:
         switches.append(f'-U {params["upscale"][0]} {params["upscale"][1]}')
     if "variation_amount" in params and params["variation_amount"] > 0:

backend/server.py

@@ -349,7 +349,7 @@ def handle_run_gfpgan_event(original_image, gfpgan_parameters):
     eventlet.sleep(0)
 
     image = gfpgan.process(
-        image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
+        image=image, strength=gfpgan_parameters["facetool_strength"], seed=seed
     )
 
     progress["currentStatus"] = "Saving image"
@@ -464,7 +464,7 @@ def parameters_to_post_processed_image_metadata(parameters, original_image_path,
         image["strength"] = parameters["upscale"][1]
     elif type == "gfpgan":
         image["type"] = "gfpgan"
-        image["strength"] = parameters["gfpgan_strength"]
+        image["strength"] = parameters["facetool_strength"]
     else:
         raise TypeError(f"Invalid type: {type}")
 
@@ -493,6 +493,7 @@ def parameters_to_generated_image_metadata(parameters):
         "height",
         "extra",
         "seamless",
+        "hires_fix",
     ]
 
     rfc_dict = {}
@@ -505,10 +506,10 @@ def parameters_to_generated_image_metadata(parameters):
     postprocessing = []
 
     # 'postprocessing' is either null or an
-    if "gfpgan_strength" in parameters:
+    if "facetool_strength" in parameters:
 
         postprocessing.append(
-            {"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
+            {"type": "gfpgan", "strength": float(parameters["facetool_strength"])}
         )
 
     if "upscale" in parameters:
@@ -751,7 +752,7 @@ def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
                 image=image, strength=gfpgan_parameters["strength"], seed=seed
             )
             postprocessing = True
-            all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
+            all_parameters["facetool_strength"] = gfpgan_parameters["strength"]
 
         progress["currentStatus"] = "Saving image"
         socketio.emit("progressUpdate", progress)

configs/models.yaml

@@ -9,10 +9,12 @@
 laion400m:
     config:  configs/latent-diffusion/txt2img-1p4B-eval.yaml
     weights: models/ldm/text2img-large/model.ckpt
+    description: Latent Diffusion LAION400M model
     width: 256
     height: 256
 stable-diffusion-1.4:
     config:  configs/stable-diffusion/v1-inference.yaml
     weights: models/ldm/stable-diffusion-v1/model.ckpt
+    description: Stable Diffusion inference model version 1.4
     width: 512
     height: 512

docs/CHANGELOG.md

@@ -6,64 +6,64 @@ title: Changelog
 
 ## v2.0.1 (13 October 2022)
 
-  - fix noisy images at high step count when using k* samplers
-  - dream.py script now calls invoke.py module directly rather than
+- fix noisy images at high step count when using k* samplers
+- dream.py script now calls invoke.py module directly rather than
     via a new python process (which could break the environment)
 
 ## v2.0.0 <small>(9 October 2022)</small>
 
-  - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
+- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
     for backward compatibility.
-  - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-  - Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/INPAINTING.md">inpainting</a> and <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OUTPAINTING.md">outpainting</a>
-  - img2img runs on all k* samplers
-  - Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/PROMPTS.md#negative-and-unconditioned-prompts">negative prompts</a>
-  - Support for CodeFormer face reconstruction
-  - Support for Textual Inversion on Macintoshes
-  - Support in both WebGUI and CLI for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/POSTPROCESS.md">post-processing of previously-generated images</a>
+- Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
+- Support for [inpainting](features/INPAINTING.md) and [outpainting](features/OUTPAINTING.md)
+- img2img runs on all k* samplers
+- Support for [negative prompts](features/PROMPTS.md#negative-and-unconditioned-prompts)
+- Support for CodeFormer face reconstruction
+- Support for Textual Inversion on Macintoshes
+- Support in both WebGUI and CLI for [post-processing of previously-generated images](features/POSTPROCESS.md)
     using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
     and "embiggen" upscaling. See the `!fix` command.
-  - New `--hires` option on `invoke>` line allows <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.m#this-is-an-example-of-txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
-  - New `--perlin` and `--threshold` options allow you to add and control variation
-    during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
-  - Extensive metadata now written into PNG files, allowing reliable regeneration of images
+- New `--hires` option on `invoke>` line allows [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img), at the cost of some performance.
+- New `--perlin` and `--threshold` options allow you to add and control variation
+    during image generation (see [Thresholding and Perlin Noise Initialization](features/OTHER.md#thresholding-and-perlin-noise-initialization-options))
+- Extensive metadata now written into PNG files, allowing reliable regeneration of images
     and tweaking of previous settings.
-  - Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
-  - Improved <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.m">command-line completion behavior</a>.
+- Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
+- Improved [command-line completion behavior](features/CLI.md)
     New commands added:
-       * List command-line history with `!history`
-       * Search command-line history with `!search`
-       * Clear history with `!clear`
-  - Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
+  - List command-line history with `!history`
+  - Search command-line history with `!search`
+  - Clear history with `!clear`
+- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
     configure. To switch away from auto use the new flag like `--precision=float32`.
 
 ## v1.14 <small>(11 September 2022)</small>
 
-  - Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
-  - Full support for Apple hardware with M1 or M2 chips.
-  - Add "seamless mode" for circular tiling of image. Generates beautiful effects.
+- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
+- Full support for Apple hardware with M1 or M2 chips.
+- Add "seamless mode" for circular tiling of image. Generates beautiful effects.
     ([prixt](https://github.com/prixt)).
-  - Inpainting support.
-  - Improved web server GUI.
-  - Lots of code and documentation cleanups.
+- Inpainting support.
+- Improved web server GUI.
+- Lots of code and documentation cleanups.
 
 ## v1.13 <small>(3 September 2022)</small>
 
-  - Support image variations (see [VARIATIONS](features/VARIATIONS.md)
+- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
     ([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
-  - Supports a Google Colab notebook for a standalone server running on Google hardware
+- Supports a Google Colab notebook for a standalone server running on Google hardware
     [Arturo Mendivil](https://github.com/artmen1516)
-  - WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
+- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
     [Kevin Gibbons](https://github.com/bakkot)
-  - WebUI supports incremental display of in-progress images during generation
+- WebUI supports incremental display of in-progress images during generation
     [Kevin Gibbons](https://github.com/bakkot)
-  - A new configuration file scheme that allows new models (including upcoming
+- A new configuration file scheme that allows new models (including upcoming
     stable-diffusion-v1.5) to be added without altering the code.
     ([David Wager](https://github.com/maddavid12))
-  - Can specify --grid on invoke.py command line as the default.
-  - Miscellaneous internal bug and stability fixes.
-  - Works on M1 Apple hardware.
-  - Multiple bug fixes.
+- Can specify --grid on invoke.py command line as the default.
+- Miscellaneous internal bug and stability fixes.
+- Works on M1 Apple hardware.
+- Multiple bug fixes.
 
 ---
 
@@ -88,7 +88,7 @@ title: Changelog
   Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch.
 - Variant generation support temporarily disabled pending more general solution.
 - Created a feature branch named **yunsaki-morphing-invoke** which adds experimental support for
-  iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
+  iteratively modifying the prompt and its parameters. Please see[Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
   for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified
   significantly.
 

docs/features/CHANGELOG.md

@@ -1,143 +0,0 @@
----
-title: Changelog
----
-
-# :octicons-log-16: Changelog
-
-## v1.13
-
-- Supports a Google Colab notebook for a standalone server running on Google
-  hardware [Arturo Mendivil](https://github.com/artmen1516)
-- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
-  [Kevin Gibbons](https://github.com/bakkot)
-- WebUI supports incremental display of in-progress images during generation
-  [Kevin Gibbons](https://github.com/bakkot)
-- Output directory can be specified on the invoke> command line.
-- The grid was displaying duplicated images when not enough images to fill the
-  final row [Muhammad Usama](https://github.com/SMUsamaShah)
-- Can specify --grid on invoke.py command line as the default.
-- Miscellaneous internal bug and stability fixes.
-
----
-
-## v1.12 <small>(28 August 2022)</small>
-
-- Improved file handling, including ability to read prompts from standard input.
-  (kudos to [Yunsaki](https://github.com/yunsaki)
-- The web server is now integrated with the invoke.py script. Invoke by adding
-  --web to the invoke.py command arguments.
-- Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
-  enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
-  VRAM requirements are modestly reduced. Thanks to both
-  [Blessedcoolant](https://github.com/blessedcoolant) and
-  [Oceanswave](https://github.com/oceanswave) for their work on this.
-- You can now swap samplers on the invoke> command line.
-  [Blessedcoolant](https://github.com/blessedcoolant)
-
----
-
-## v1.11 <small>(26 August 2022)</small>
-
-- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module.
-  (kudos to [Oceanswave](https://github.com/Oceanswave))
-- You now can specify a seed of -1 to use the previous image's seed, -2 to use
-  the seed for the image generated before that, etc. Seed memory only extends
-  back to the previous command, but will work on all images generated with the
-  -n# switch.
-- Variant generation support temporarily disabled pending more general solution.
-- Created a feature branch named **yunsaki-morphing-invoke** which adds
-  experimental support for iteratively modifying the prompt and its parameters.
-  Please
-  see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) for
-  a synopsis of how this works. Note that when this feature is eventually added
-  to the main branch, it will may be modified significantly.
-
----
-
-## v1.10 <small>(25 August 2022)</small>
-
-- A barebones but fully functional interactive web server for online generation
-  of txt2img and img2img.
-
----
-
-## v1.09 <small>(24 August 2022)</small>
-
-- A new -v option allows you to generate multiple variants of an initial image
-  in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave).
-- [See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
-- Added ability to personalize text to image generation (kudos to
-  [Oceanswave](https://github.com/Oceanswave) and
-  [nicolai256](https://github.com/nicolai256))
-- Enabled all of the samplers from k_diffusion
-
----
-
-## v1.08 <small>(24 August 2022)</small>
-
-- Escape single quotes on the invoke> command before trying to parse. This avoids
-  parse errors.
-- Removed instruction to get Python3.8 as first step in Windows install.
-  Anaconda3 does it for you.
-- Added bounds checks for numeric arguments that could cause crashes.
-- Cleaned up the copyright and license agreement files.
-
----
-
-## v1.07 <small>(23 August 2022)</small>
-
-- Image filenames will now never fill gaps in the sequence, but will be assigned
-  the next higher name in the chosen directory. This ensures that the alphabetic
-  and chronological sort orders are the same.
-
----
-
-## v1.06 <small>(23 August 2022)</small>
-
-- Added weighted prompt support contributed by
-  [xraxra](https://github.com/xraxra)
-- Example of using weighted prompts to tweak a demonic figure contributed by
-  [bmaltais](https://github.com/bmaltais)
-
----
-
-## v1.05 <small>(22 August 2022 - after the drop)</small>
-
-- Filenames now use the following formats: 000010.95183149.png -- Two files
-  produced by the same command (e.g. -n2), 000010.26742632.png -- distinguished
-  by a different seed.
-    000011.455191342.01.png -- Two files produced by the same command using
-    000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed.
-    000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid
-  can be regenerated with the indicated key
-
-- It should no longer be possible for one image to overwrite another
-- You can use the "cd" and "pwd" commands at the invoke> prompt to set and
-  retrieve the path of the output directory.
-
-## v1.04 <small>(22 August 2022 - after the drop)</small>
-
-- Updated README to reflect installation of the released weights.
-- Suppressed very noisy and inconsequential warning when loading the frozen CLIP
-  tokenizer.
-
-## v1.03 <small>(22 August 2022)</small>
-
-- The original txt2img and img2img scripts from the CompViz repository have been
-  moved into a subfolder named "orig_scripts", to reduce confusion.
-
-## v1.02 <small>(21 August 2022)</small>
-
-- A copy of the prompt and all of its switches and options is now stored in the
-  corresponding image in a tEXt metadata field named "Dream". You can read the
-  prompt using scripts/images2prompt.py, or an image editor that allows you to
-  explore the full metadata. **Please run "conda env update -f environment.yaml"
-  to load the k_lms dependencies!!**
-
-## v1.01 <small>(21 August 2022)</small>
-
-- added k_lms sampling. **Please run "conda env update -f environment.yaml" to
-  load the k_lms dependencies!!**
-- use half precision arithmetic by default, resulting in faster execution and
-  lower memory requirements Pass argument --full_precision to invoke.py to get
-  slower but more accurate image generation

docs/features/CLI.md

@@ -85,6 +85,7 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
 | `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
 | `--model <modelname>`                     |                                           | `stable-diffusion-1.4`                         | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" |
 | `--full_precision`                        | `-F`                                      | `False`                                        | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards.   |
+| `--png_compression <0-9>`                 | `-z<0-9>`                                 |  6                                             | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
 | `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
 | `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
 | `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
@@ -100,9 +101,7 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
 | `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
 | `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
 
-!!! warning deprecated
-
-    These arguments are deprecated but still work:
+!!! warning "These arguments are deprecated but still work"
 
     <div align="center" markdown>
 
@@ -131,7 +130,7 @@ from text ([txt2img](#txt2img)), to embellish an existing image or sketch
 
 ### txt2img
 
-!!! example
+!!! example ""
 
     ```bash
     invoke> waterfall and rainbow -W640 -H480
@@ -144,46 +143,47 @@ Here are the invoke> command that apply to txt2img:
 
 | Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description |
 |--------------------|------------|---------------------|--------------|
-| `"my prompt"`        |            |                    | Text prompt to use. The quotation marks are optional. |
-| `--width <int>`      | `-W<int>`   | `512`                 | Width of generated image |
-| `--height <int>`     | `-H<int>`   | `512`                 | Height of generated image |
-| `--iterations <int>` | `-n<int>`   | `1`                   | How many images to generate from this prompt |
-| `--steps <int>`      | `-s<int>`   | `50`                  | How many steps of refinement to apply |
-| `--cfg_scale <float>`| `-C<float>` | `7.5`                 | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0 |
-| `--seed <int>`       | `-S<int>`   | `None`                | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
-| `--sampler <sampler>`| `-A<sampler>`| `k_lms`              | Sampler to use. Use -h to get list of available samplers. |
-| `--hires_fix`        |           |                     | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
-| `--grid`             | `-g`        | `False`               | Turn on grid mode to return a single image combining all the images generated by this prompt |
-| `--individual`       | `-i`        | `True`                | Turn off grid mode (deprecated; leave off `--grid` instead) |
-| `--outdir <path>`    |  `-o<path>` | `outputs/img_samples`  | Temporarily change the location of these images |
-| `--seamless`         |           | `False`               | Activate seamless tiling for interesting effects |
-| `--log_tokenization` | `-t`        | `False`               | Display a color-coded list of the parsed tokens derived from the prompt |
-| `--skip_normalization`| `-x`       | `False`               | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
-| `--upscale <int> <float>` | `-U <int> <float>` | `-U 1 0.75`| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
-| `--gfpgan_strength <float>`  | `-G <float>` | `-G0`        | Fix faces using the GFPGAN algorithm; argument indicates how hard the algorithm should try (0.0-1.0) |
-| `--save_original`    | `-save_orig`| `False`               | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
-| `--variation <float>`  |`-v<float>`| `0.0`                 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
-| `--with_variations <pattern>` | `-V<pattern>`| `None`      | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |
+| "my prompt"        |            |                    | Text prompt to use. The quotation marks are optional. |
+| --width <int>      | -W<int>   | 512                 | Width of generated image |
+| --height <int>     | -H<int>   | 512                 | Height of generated image |
+| --iterations <int> | -n<int>   | 1                   | How many images to generate from this prompt |
+| --steps <int>      | -s<int>   | 50                  | How many steps of refinement to apply |
+| --cfg_scale <float>| -C<float> | 7.5                 | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0 |
+| --seed <int>       | -S<int>   | None                | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
+| --sampler <sampler>| -A<sampler>| k_lms              | Sampler to use. Use -h to get list of available samplers. |
+| --hires_fix        |           |                     | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
+| `--png_compression <0-9>` | `-z<0-9>` |  6           | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
+| --grid             | -g        | False               | Turn on grid mode to return a single image combining all the images generated by this prompt |
+| --individual       | -i        | True                | Turn off grid mode (deprecated; leave off --grid instead) |
+| --outdir <path>    |  -o<path> | outputs/img_samples  | Temporarily change the location of these images |
+| --seamless         |           | False               | Activate seamless tiling for interesting effects |
+| --log_tokenization | -t        | False               | Display a color-coded list of the parsed tokens derived from the prompt |
+| --skip_normalization| -x       | False               | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
+| --upscale <int> <float> | -U <int> <float> | -U 1 0.75| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
+| --facetool_strength <float>  | -G <float> | -G0        | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) |
+| --facetool <name> | -ft <name> | -ft gfpgan | Select face restoration algorithm to use: gfpgan, codeformer |
+| --codeformer_fidelity | -cf <float> | 0.75 | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
+| --save_original    | -save_orig| False               | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
+| --variation <float>  |-v<float>| 0.0                 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with -S<seed> and -n<int> to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
+| --with_variations <pattern> |    | None              | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |
+| --save_intermediates <n>    |    | None              | Save the image from every nth step into an "intermediates" folder inside the output directory |
 
-!!! note
+Note that the width and height of the image must be multiples of
+64. You can provide different values, but they will be rounded down to
+the nearest multiple of 64.
 
-    The width and height of the image must be multiples of
-    64. You can provide different values, but they will be rounded down to
-    the nearest multiple of 64.
 
-### img2img
+### This is an example of img2img:	
 
-!!! example
+~~~~
+invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
+~~~~
 
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-    ```
-
-    This will modify the indicated vacation photograph by making it more
-    like the prompt. Results will vary greatly depending on what is in the
-    image. We also ask to `--fit` the image into a box no bigger than
-    640x480. Otherwise the image size will be identical to the provided
-    photo and you may run out of memory if it is large.
+This will modify the indicated vacation photograph by making it more
+like the prompt. Results will vary greatly depending on what is in the
+image. We also ask to --fit the image into a box no bigger than
+640x480. Otherwise the image size will be identical to the provided
+photo and you may run out of memory if it is large.
 
 In addition to the command-line options recognized by txt2img, img2img
 accepts additional options:
@@ -196,7 +196,7 @@ accepts additional options:
 
 ### inpainting
 
-!!! example
+!!! example ""
 
     ```bash
     invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
@@ -216,10 +216,14 @@ well as the --mask (-M) argument:
 |--------------------|------------|---------------------|--------------|
 | `--init_mask <path>` | `-M<path>`   | `None`                |Path to an image the same size as the initial_image, with areas for inpainting made transparent.|
 
-## Convenience commands
+# Other Commands
 
-In addition to the standard image generation arguments, there are a
-series of convenience commands that begin with !:
+The CLI offers a number of commands that begin with "!".
+
+## Postprocessing images
+
+To postprocess a file using face restoration or upscaling, use the
+`!fix` command.
 
 ### `!fix`
 
@@ -252,19 +256,161 @@ Some examples:
     Outputs:
     [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
 
+# Model selection and importation
+
+The CLI allows you to add new models on the fly, as well as to switch
+among them rapidly without leaving the script.
+
+## !models
+
+This prints out a list of the models defined in `config/models.yaml'.
+The active model is bold-faced
+
+Example:
+<pre>
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
+waifu-diffusion           not loaded  Waifu Diffusion v1.3
+</pre>
+
+## !switch <model>
+
+This quickly switches from one model to another without leaving the 
+CLI script. `invoke.py` uses a memory caching system; once a model
+has been loaded, switching back and forth is quick. The following
+example shows this in action. Note how the second column of the 
+`!models` table changes to `cached` after a model is first loaded,
+and that the long initialization step is not needed when loading
+a cached model.
+
+<pre>
+invoke> !models
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          cached  Stable Diffusion v1.4</b>
+waifu-diffusion               active  Waifu Diffusion v1.3
+
+invoke> !switch waifu-diffusion
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+   | LatentDiffusion: Running in eps-prediction mode
+   | DiffusionWrapper has 859.52 M params.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Using faster float16 precision
+>> Model loaded in 18.24s
+>> Max VRAM used to load the model: 2.17G 
+>> Current VRAM usage:2.17G
+>> Setting Sampler to k_lms
+
+invoke> !models
+laion400m                 not loaded  <no description>
+stable-diffusion-1.4          cached  Stable Diffusion v1.4
+<b>waifu-diffusion               active  Waifu Diffusion v1.3</b>
+
+invoke> !switch stable-diffusion-1.4
+>> Caching model waifu-diffusion in system RAM
+>> Retrieving model stable-diffusion-1.4 from system RAM cache
+>> Setting Sampler to k_lms
+
+invoke> !models
+laion400m                 not loaded  <no description>
+<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
+waifu-diffusion               cached  Waifu Diffusion v1.3
+</pre>
+
+## !import_model <path/to/model/weights>
+
+This command imports a new model weights file into InvokeAI, makes it
+available for image generation within the script, and writes out the
+configuration for the model into `config/models.yaml` for use in 
+subsequent sessions.
+
+Provide `!import_model` with the path to a weights file ending in
+`.ckpt`.  If you type a partial path and press tab, the CLI will
+autocomplete. Although it will also autocomplete to `.vae` files,
+these are not currenty supported (but will be soon).
+
+When you hit return, the CLI will prompt you to fill in additional
+information about the model, including the short name you wish to use
+for it with the `!switch` command, a brief description of the model,
+the default image width and height to use with this model, and the
+model's configuration file. The latter three fields are automatically
+filled with reasonable defaults. In the example below, the bold-faced
+text shows what the user typed in with the exception of the width,
+height and configuration file paths, which were filled in
+automatically.
+
+Example:
+
+<pre>
+invoke> <b>!import_model models/ldm/stable-diffusion-v1/	model-epoch08-float16.ckpt</b>
+>> Model import in process. Please enter the values needed to configure this model:
+
+Name for this model: <b>waifu-diffusion</b>
+Description of this model: <b>Waifu Diffusion v1.3</b>
+Configuration file for this model: <b>configs/stable-diffusion/v1-inference.yaml</b>
+Default image width: <b>512</b>
+Default image height: <b>512</b>
+>> New configuration:
+waifu-diffusion:
+  config: configs/stable-diffusion/v1-inference.yaml
+  description: Waifu Diffusion v1.3
+  height: 512
+  weights: models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+  width: 512
+OK to import [n]? <b>y</b>
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
+   | LatentDiffusion: Running in eps-prediction mode
+   | DiffusionWrapper has 859.52 M params.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
+   | Making attention of type 'vanilla' with 512 in_channels
+   | Using faster float16 precision
+invoke> 
+</pre>
+
+##!edit_model <name_of_model>
+
+The `!edit_model` command can be used to modify a model that is
+already defined in `config/models.yaml`. Call it with the short
+name of the model you wish to modify, and it will allow you to
+modify the model's `description`, `weights` and other fields.
+
+Example:
+<pre>
+invoke> <b>!edit_model waifu-diffusion</b>
+>> Editing model waifu-diffusion from configuration file ./configs/models.yaml
+description: <b>Waifu diffusion v1.4beta</b>
+weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
+config: configs/stable-diffusion/v1-inference.yaml
+width: 512
+height: 512
+
+>> New configuration:
+waifu-diffusion:
+  config: configs/stable-diffusion/v1-inference.yaml
+  description: Waifu diffusion v1.4beta
+  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+  height: 512
+  width: 512
+
+OK to import [n]? y
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+...
+</pre>
+=======
     invoke> !fix 000017.4829112.gfpgan-00.png --embiggen 3
     ...lots of text...
     Outputs:
     [2] outputs/img-samples/000018.2273800735.embiggen-00.png: !fix "outputs/img-samples/000017.243781548.gfpgan-00.png" -s 50 -S 2273800735 -W 512 -H 512 -C 7.5 -A k_lms --embiggen 3.0 0.75 0.25
     ```
+# History processing
 
-### `!fetch`
-
-This command retrieves the generation parameters from a previously
-generated image and either loads them into the command line.  You may
-provide either the name of a file in the current output directory, or
-a full file path.
-
+The CLI provides a series of convenient commands for reviewing previous
+actions, retrieving them, modifying them, and re-running them.
 ```bash
 invoke> !fetch 0000015.8929913.png
 # the script returns the next line, ready for editing and running:
@@ -299,7 +445,23 @@ invoke> !20
 invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
 ```
 
-### `!search <search string>`
+## !fetch
+
+This command retrieves the generation parameters from a previously
+generated image and either loads them into the command line.  You may
+provide either the name of a file in the current output directory, or
+a full file path.
+
+~~~
+invoke> !fetch 0000015.8929913.png
+# the script returns the next line, ready for editing and running:
+invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
+~~~
+
+Note that this command may behave unexpectedly if given a PNG file that
+was not generated by InvokeAI.
+
+### !search <search string>
 
 This is similar to !history but it only returns lines that contain
 `search string`. For example:

docs/features/IMG2IMG.md

@@ -17,15 +17,15 @@ tree on a hill with a river, nature photograph, national geographic -I./test-pic
 
 This will take the original image shown here:
 
-<div align="center" markdown>
+<figure markdown>
 <img src="https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png" width=350>
-</div>
+</figure>
 
 and generate a new image based on it as shown here:
 
-<div align="center" markdown>
+<figure markdown>
 <img src="https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png" width=350>
-</div>
+</figure>
 
 The `--init_img` (`-I`) option gives the path to the seed picture. `--strength` (`-f`) controls how much
 the original will be modified, ranging from `0.0` (keep the original intact), to `1.0` (ignore the
@@ -41,11 +41,10 @@ interesting variants.
 Note that the prompt makes a big difference. For example, this slight variation on the prompt produces
 a very different image:
 
-`photograph of a tree on a hill with a river`
-
-<div align="center" markdown>
+<figure markdown>
 <img src="https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png" width=350>
-</div>
+<caption markdown>photograph of a tree on a hill with a river</caption>
+</figure>
 
 !!! tip
 
@@ -59,16 +58,13 @@ information underneath the transparent needs to be preserved, not erased.
 
 !!! warning
 
-    `img2img` does not work properly on initial images smaller than 512x512. Please scale your
-    image to at least 512x512 before using it. Larger images are not a problem, but may run out of VRAM on your
-    GPU card.
-
-    To fix this, use the `--fit` option, which downscales the initial image to fit within the box specified
-    by width x height:
-
-    ```bash
-    invoke> "tree on a hill with a river, national geographic" -I./test-pictures/big-sketch.png -H512 -W512 --fit
-    ```
+**IMPORTANT ISSUE** `img2img` does not work properly on initial images smaller than 512x512. Please scale your
+image to at least 512x512 before using it. Larger images are not a problem, but may run out of VRAM on your
+GPU card. To fix this, use the --fit option, which downscales the initial image to fit within the box specified
+by width x height:
+~~~
+tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
+~~~
 
 ## How does it actually work, though?
 
@@ -78,13 +74,13 @@ gaussian noise and progressively refines it over the requested number of steps,
 
 **Let's start** by thinking about vanilla `prompt2img`, just generating an image from a prompt. If the step count is 10, then the "latent space" (Stable Diffusion's internal representation of the image) for the prompt "fire" with seed `1592514025` develops something like this:
 
-```bash
+```commandline
 invoke> "fire" -s10 -W384 -H384 -S1592514025
 ```
 
-<div align="center" markdown>
+<figure markdown>
 ![latent steps](../assets/img2img/000019.steps.png)
-</div>
+</figure>
 
 Put simply: starting from a frame of fuzz/static, SD finds details in each frame that it thinks look like "fire" and brings them a little bit more into focus, gradually scrubbing out the fuzz until a clear image remains.
 
@@ -94,28 +90,28 @@ Put simply: starting from a frame of fuzz/static, SD finds details in each frame
 
 I want SD to draw a fire based on this hand-drawn image:
 
-<div align="center" markdown>
+<figure markdown>
 ![drawing of a fireplace](../assets/img2img/fire-drawing.png)
-</div>
+</figure>
 
 Let's only do 10 steps, to make it easier to see what's happening. If strength is `0.7`, this is what the internal steps the algorithm has to take will look like:
 
-<div align="center" markdown>
+<figure markdown>
 ![gravity32](../assets/img2img/000032.steps.gravity.png)
-</div>
+</figure>
 
 With strength `0.4`, the steps look more like this:
 
-<div align="center" markdown>
+<figure markdown>
 ![gravity30](../assets/img2img/000030.steps.gravity.png)
-</div>
+</figure>
 
 Notice how much more fuzzy the starting image is for strength `0.7` compared to `0.4`, and notice also how much longer the sequence is with `0.7`:
 
 |  | strength = 0.7 | strength = 0.4 |
-| -- | :--: | :--: |
-| initial image that SD sees | ![step-0-32](../assets/img2img/000032.step-0.png) | ![step-0-30](../assets/img2img/000030.step-0.png) |
-| steps argument to `dream>` | `-S10` | `-S10` |
+| -- | -- | -- |
+| initial image that SD sees | ![](../assets/img2img/000032.step-0.png) | ![](../assets/img2img/000030.step-0.png) |
+| steps argument to `invoke>` | `-S10` | `-S10` |
 | steps actually taken | 7 | 4 |
 | latent space at each step | ![gravity32](../assets/img2img/000032.steps.gravity.png) | ![gravity30](../assets/img2img/000030.steps.gravity.png) |
 | output | ![000032.1592514025](../assets/img2img/000032.1592514025.png) | ![000030.1592514025](../assets/img2img/000030.1592514025.png) |
@@ -124,11 +120,13 @@ Both of the outputs look kind of like what I was thinking of. With the strength
 
 If you want to try this out yourself, all of these are using a seed of `1592514025` with a width/height of `384`, step count `10`, the default sampler (`k_lms`), and the single-word prompt `"fire"`:
 
-```bash
+If you want to try this out yourself, all of these are using a seed of `1592514025` with a width/height of `384`, step count `10`, the default sampler (`k_lms`), and the single-word prompt `fire`:
+
+```commandline
 invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
 ```
 
-The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `invoke.py` and check your `outputs/img-samples/intermediates` folder while generating an image.
+The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `invoke.py` and check your `outputs/img-samples/intermediates` folder while generating an image. 
 
 ### Compensating for the reduced step count
 
@@ -136,43 +134,52 @@ After putting this guide together I was curious to see how the difference would
 
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD does `20` steps from my image):
 
-```bash
+```commandline
 invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 ```
 
-<div align="center" markdown>
+<figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
-</div>
+</figure>
 
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to make sure SD does `20` steps from my image):
 
-```bash
+```commandline
 invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
 ```
 
-<div align="center" markdown>
+<figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
-</div>
+</figure>
 
 In both cases the image is nice and clean and "finished", but because at strength `0.7` Stable Diffusion has been give so much more freedom to improve on my badly-drawn flames, they've come out looking much better. You can really see the difference when looking at the latent steps. There's more noise on the first image with strength `0.7`:
 
+<figure markdown>
 ![gravity46](../assets/img2img/000046.steps.gravity.png)
+</figure>
 
 than there is for strength `0.4`:
 
+<figure markdown>
 ![gravity35](../assets/img2img/000035.steps.gravity.png)
+</figure>
 
 and that extra noise gives the algorithm more choices when it is evaluating how to denoise any particular pixel in the image.
 
 Unfortunately, it seems that `img2img` is very sensitive to the step count. Here's strength `0.7` with a step count of `29` (SD did 19 steps from my image):
 
-<div align="center" markdown>
+<figure markdown>
 ![gravity45](../assets/img2img/000045.1592514025.png)
-</div>
+</figure>
 
 By comparing the latents we can sort of see that something got interpreted differently enough on the third or fourth step to lead to a rather different interpretation of the flames.
 
+<figure markdown>
 ![gravity46](../assets/img2img/000046.steps.gravity.png)
+</figure>
+
+<figure markdown>
 ![gravity45](../assets/img2img/000045.steps.gravity.png)
+</figure>
 
 This is the result of a difference in the de-noising "schedule" - basically the noise has to be cleaned by a certain degree each step or the model won't "converge" on the image properly (see [stable diffusion blog](https://huggingface.co/blog/stable_diffusion) for more about that). A different step count means a different schedule, which means things get interpreted slightly differently at every step.

docs/features/INPAINTING.md

@@ -6,21 +6,29 @@ title: Inpainting
 
 ## **Creating Transparent Regions for Inpainting**
 
-Inpainting is really cool. To do it, you start with an initial image and use a photoeditor to make
-one or more regions transparent (i.e. they have a "hole" in them). You then provide the path to this
-image at the invoke> command line using the `-I` switch. Stable Diffusion will only paint within the
-transparent region.
+Inpainting is really cool. To do it, you start with an initial image
+and use a photoeditor to make one or more regions transparent
+(i.e. they have a "hole" in them). You then provide the path to this
+image at the dream> command line using the `-I` switch. Stable
+Diffusion will only paint within the transparent region.
 
-There's a catch. In the current implementation, you have to prepare the initial image correctly so
-that the underlying colors are preserved under the transparent area. Many imaging editing
-applications will by default erase the color information under the transparent pixels and replace
-them with white or black, which will lead to suboptimal inpainting. You also must take care to
-export the PNG file in such a way that the color information is preserved.
+There's a catch. In the current implementation, you have to prepare
+the initial image correctly so that the underlying colors are
+preserved under the transparent area. Many imaging editing
+applications will by default erase the color information under the
+transparent pixels and replace them with white or black, which will
+lead to suboptimal inpainting. It often helps to apply incomplete
+transparency, such as any value between 1 and 99%
 
-If your photoeditor is erasing the underlying color information, `invoke.py` will give you a big fat
-warning. If you can't find a way to coax your photoeditor to retain color values under transparent
-areas, then you can combine the `-I` and `-M` switches to provide both the original unedited image
-and the masked (partially transparent) image:
+You also must take care to export the PNG file in such a way that the
+color information is preserved. There is often an option in the export
+dialog that lets you specify this.
+
+If your photoeditor is erasing the underlying color information,
+`dream.py` will give you a big fat warning. If you can't find a way to
+coax your photoeditor to retain color values under transparent areas,
+then you can combine the `-I` and `-M` switches to provide both the
+original unedited image and the masked (partially transparent) image:
 
 ```bash
 invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
@@ -28,6 +36,26 @@ invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent
 
 We are hoping to get rid of the need for this workaround in an upcoming release.
 
+### Inpainting is not changing the masked region enough!
+
+One of the things to understand about how inpainting works is that it
+is equivalent to running img2img on just the masked (transparent)
+area. img2img builds on top of the existing image data, and therefore
+will attempt to preserve colors, shapes and textures to the best of
+its ability. Unfortunately this means that if you want to make a
+dramatic change in the inpainted region, for example replacing a red
+wall with a blue one, the algorithm will fight you.
+
+You have a couple of options. The first is to increase the values of
+the requested steps (`-sXXX`), strength (`-f0.XX`), and/or
+condition-free guidance (`-CXX.X`). If this is not working for you, a
+more extreme step is to provide the `--inpaint_replace 0.X` (`-r0.X`)
+option. This value ranges from 0.0 to 1.0. The higher it is the less
+attention the algorithm will pay to the data underneath the masked
+region. At high values this will enable you to replace colored regions
+entirely, but beware that the masked region mayl not blend in with the
+surrounding unmasked regions as well.
+
 ---
 
 ## Recipe for GIMP
@@ -35,10 +63,10 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
 [GIMP](https://www.gimp.org/) is a popular Linux photoediting tool.
 
 1. Open image in GIMP.
-2. Layer --> Transparency --> Add Alpha Channel
-3. Use lasoo tool to select region to mask
-4. Choose Select --> Float to create a floating selection
-5. Open the Layers toolbar (++ctrl+l++) and select "Floating Selection"
+2. Layer->Transparency->Add Alpha Channel
+3. Use lasso tool to select region to mask
+4. Choose Select -> Float to create a floating selection
+5. Open the Layers toolbar (^L) and select "Floating Selection"
 6. Set opacity to a value between 0% and 99%
 7. Export as PNG
 8. In the export dialogue, Make sure the "Save colour values from
@@ -50,28 +78,40 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
 
 1. Open image in Photoshop
 
-    <div align="center" markdown>![step1](../assets/step1.png)</div>
+    <figure markdown>
+    ![step1](../assets/step1.png)
+    </figure>
 
 2. Use any of the selection tools (Marquee, Lasso, or Wand) to select the area you desire to inpaint.
 
-    <div align="center" markdown>![step2](../assets/step2.png)</div>
+    <figure markdown>
+    ![step2](../assets/step2.png)
+    </figure>
 
 3. Because we'll be applying a mask over the area we want to preserve, you should now select the inverse by using the ++shift+ctrl+i++ shortcut, or right clicking and using the "Select Inverse" option.
 
-4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the undrlying image, or your inpainting results will be dramatically impacted.
+4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the underlying image, or your inpainting results will be dramatically impacted.
 
-    <div align="center" markdown>![step4](../assets/step4.png)</div>
+    <figure markdown>
+    ![step4](../assets/step4.png)
+    </figure>
 
 5. Make sure to hide any background layers that are present. You should see the mask applied to your image layer, and the image on your canvas should display the checkered background.
 
-    <div align="center" markdown>![step5](../assets/step5.png)</div>
+    <figure markdown>
+    ![step5](../assets/step5.png)
+    </figure>
 
 6. Save the image as a transparent PNG by using `File`-->`Save a Copy` from the menu bar, or by using the keyboard shortcut ++alt+ctrl+s++
 
-    <div align="center" markdown>![step6](../assets/step6.png)</div>
+    <figure markdown>
+    ![step6](../assets/step6.png)
+    </figure>
 
 7. After following the inpainting instructions above (either through the CLI or the Web UI), marvel at your newfound ability to selectively invoke. Lookin' good!
 
-    <div align="center" markdown>![step7](../assets/step7.png)</div>
+    <figure markdown>
+   ![step7](../assets/step7.png)
+    </figure>
 
 8. In the export dialogue, Make sure the "Save colour values from transparent pixels" checkbox is selected.  

docs/features/OUTPAINTING.md

@@ -25,9 +25,9 @@ implementations.
 
 Consider this image:
 
-<div align="center" markdown>
+<figure markdown>
 ![curly_woman](../assets/outpainting/curly.png)
-</div>
+</figure>
 
 Pretty nice, but it's annoying that the top of her head is cut
 off. She's also a bit off center. Let's fix that!
@@ -44,9 +44,9 @@ specify any number of pixels to extend. You can also abbreviate
 
 The result looks like this:
 
-<div align="center" markdown>
+<figure markdown>
 ![curly_woman_outcrop](../assets/outpainting/curly-outcrop.png)
-</div>
+</figure>
 
 The new image is actually slightly larger than the original (576x576,
 because 64 pixels were added to the top and right sides.)
@@ -78,9 +78,9 @@ invoke> !fix images/curly.png --out_direction top 64
 
 The result is shown here:
 
-<div align="center" markdown>
+<figure markdown>
 ![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png)
-</div>
+</figure>
 
 Although the effect is similar, there are significant differences from
 outcropping:

docs/features/POSTPROCESS.md

@@ -70,7 +70,7 @@ If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 ### Face Restoration
 
-`-G : <gfpgan_strength>`
+`-G : <facetool_strength>`
 
 This prompt argument controls the strength of the face restoration that is being
 applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.

docs/features/PROMPTS.md

@@ -47,33 +47,33 @@ original prompt:
 
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
-<div align="center" markdown>
+<figure markdown>
 ![step1](../assets/negative_prompt_walkthru/step1.png)
-</div>
+</figure>
 
 That image has a woman, so if we want the horse without a rider, we can influence the image not to have a woman by putting [woman] in the prompt, like this:
 
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
-<div align="center" markdown>
+<figure markdown>
 ![step2](../assets/negative_prompt_walkthru/step2.png)
-</div>
+</figure>
 
 That's nice - but say we also don't want the image to be quite so blue. We can add "blue" to the list of negative prompts, so it's now [woman blue]:
 
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
-<div align="center" markdown>
+<figure markdown>
 ![step3](../assets/negative_prompt_walkthru/step3.png)
-</div>
+</figure>
 
 Getting close - but there's no sense in having a saddle when our horse doesn't have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
-<div align="center" markdown>
+<figure markdown>
 ![step4](../assets/negative_prompt_walkthru/step4.png)
-</div>
+</figure>
 
 !!! notes "Notes about this feature:"
 
@@ -112,56 +112,56 @@ different results each time you run them.
 
 ---
 
-<div align="center" markdown>
+<figure markdown>
 ### "blue sphere, red cube, hybrid"
-</div>
+</figure>
 
 This example doesn't use melding at all and represents the default way
 of mixing concepts.
 
-<div align="center" markdown>
+<figure markdown>
 ![blue-sphere-red-cube-hyprid](../assets/prompt-blending/blue-sphere-red-cube-hybrid.png)
-</div>
+</figure>
 
 It's interesting to see how the AI expressed the concept of "cube" as
 the four quadrants of the enclosing frame. If you look closely, there
 is depth there, so the enclosing frame is actually a cube.
 
-<div align="center" markdown>
+<figure markdown>
 ### "blue sphere:0.25 red cube:0.75 hybrid"
 
 ![blue-sphere-25-red-cube-75](../assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png)
-</div>
+</figure>
 
 Now that's interesting. We get neither a blue sphere nor a red cube,
 but a red sphere embedded in a brick wall, which represents a melding
 of concepts within the AI's "latent space" of semantic
 representations. Where is Ludwig Wittgenstein when you need him?
 
-<div align="center" markdown>
+<figure markdown>
 ### "blue sphere:0.75 red cube:0.25 hybrid"
 
 ![blue-sphere-75-red-cube-25](../assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png)
-</div>
+</figure>
 
 Definitely more blue-spherey. The cube is gone entirely, but it's
 really cool abstract art.
 
-<div align="center" markdown>
+<figure markdown>
 ### "blue sphere:0.5 red cube:0.5 hybrid"
 
 ![blue-sphere-5-red-cube-5-hybrid](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png)
-</div>
+</figure>
 
 Whoa...! I see blue and red, but no spheres or cubes. Is the word
 "hybrid" summoning up the concept of some sort of scifi creature?
 Let's find out.
 
-<div align="center" markdown>
+<figure markdown>
 ### "blue sphere:0.5 red cube:0.5"
 
 ![blue-sphere-5-red-cube-5](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png)
-</div>
+</figure>
 
 Indeed, removing the word "hybrid" produces an image that is more like
 what we'd expect.

docs/index.md

@@ -12,7 +12,7 @@ title: Home
 -->
 <div align="center" markdown>
 
-# ^^**InvokeAI: A Stable Diffusion Toolkit**^^ :tools: <br> <small>Formally known as lstein/stable-diffusion</small>
+# ^^**InvokeAI: A Stable Diffusion Toolkit**^^ :tools: <br> <small>Formerly known as lstein/stable-diffusion</small>
 
 ![project logo](assets/logo.png)
 
@@ -86,74 +86,57 @@ You wil need one of the following:
 
 - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
-!!! note
+!!! info
 
     If you are have a Nvidia 10xx series card (e.g. the 1080ti), please run the invoke script in
     full-precision mode as shown below.
 
     Similarly, specify full-precision mode on Apple M1 hardware.
 
-    To run in full-precision mode, start `invoke.py` with the `--full_precision` flag:
+    Precision is auto configured based on the device. If however you encounter errors like 
+    `expected type Float but found Half` or `not implemented for Half` you can try starting 
+    `invoke.py` with the `--precision=float32` flag:
 
     ```bash
     (invokeai) ~/InvokeAI$ python scripts/invoke.py --full_precision
     ```
+
 ## :octicons-log-16: Latest Changes
 
+### v2.0.1 <small>(13 October 2022)</small>
+
+- fix noisy images at high step count when using k* samplers
+- dream.py script now calls invoke.py module directly rather than
+  via a new python process (which could break the environment)
+
 ### v2.0.0 <small>(9 October 2022)</small>
+
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
-    for backward compatibility.
+  for backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/INPAINTING.md">inpainting</a> and <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OUTPAINTING.md">outpainting</a>
+- Support for <a href="https://invoke-ai.github.io/InvokeAI/features/INPAINTING/">inpainting</a> and <a href="https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/">outpainting</a>
 - img2img runs on all k* samplers
-- Support for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/PROMPTS.md#negative-and-unconditioned-prompts">negative prompts</a>
+- Support for <a href="https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#negative-and-unconditioned-prompts">negative prompts</a>
 - Support for CodeFormer face reconstruction
 - Support for Textual Inversion on Macintoshes
-- Support in both WebGUI and CLI for <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/POSTPROCESS.md">post-processing of previously-generated images</a>
-    using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
-    and "embiggen" upscaling. See the `!fix` command.
-- New `--hires` option on `invoke>` line allows <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.m#this-is-an-example-of-txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
+- Support in both WebGUI and CLI for <a href="https://invoke-ai.github.io/InvokeAI/features/POSTPROCESS/">post-processing of previously-generated images</a>
+  using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E infinite canvas),
+  and "embiggen" upscaling. See the `!fix` command.
+- New `--hires` option on `invoke>` line allows <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/#txt2img">larger images to be created without duplicating elements</a>, at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control variation
-    during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
+  during image generation (see <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options">Thresholding and Perlin Noise Initialization</a>
 - Extensive metadata now written into PNG files, allowing reliable regeneration of images
-    and tweaking of previous settings.
+  and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac platforms.
-- Improved <a href="https://github.com/invoke-ai/InvokeAI/blob/main/docs/features/CLI.m">command-line completion behavior</a>.
-    New commands added:
-       * List command-line history with `!history`
-       * Search command-line history with `!search`
-       * Clear history with `!clear`
+- Improved <a href="https://invoke-ai.github.io/InvokeAI/features/CLI/">command-line completion behavior</a>.
+  New commands added:
+  - List command-line history with `!history`
+  - Search command-line history with `!search`
+  - Clear history with `!clear`
 - Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
-    configure. To switch away from auto use the new flag like `--precision=float32`.
+  configure. To switch away from auto use the new flag like `--precision=float32`.
 
-### v1.14 <small>(11 September 2022)</small>
-
-- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
-- Full support for Apple hardware with M1 or M2 chips.
-- Add "seamless mode" for circular tiling of image. Generates beautiful effects.
-  ([prixt](https://github.com/prixt)).
-- Inpainting support.
-- Improved web server GUI.
-- Lots of code and documentation cleanups.
-
-### v1.13 <small>(3 September 2022</small>
-
-- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
-  ([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
-- Supports a Google Colab notebook for a standalone server running on Google hardware
-  [Arturo Mendivil](https://github.com/artmen1516)
-- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling
-  [Kevin Gibbons](https://github.com/bakkot)
-- WebUI supports incremental display of in-progress images during generation
-  [Kevin Gibbons](https://github.com/bakkot)
-- A new configuration file scheme that allows new models (including upcoming stable-diffusion-v1.5)
-  to be added without altering the code. ([David Wager](https://github.com/maddavid12))
-- Can specify --grid on invoke.py command line as the default.
-- Miscellaneous internal bug and stability fixes.
-- Works on M1 Apple hardware.
-- Multiple bug fixes.
-
-For older changelogs, please visit the **[CHANGELOG](features/CHANGELOG.md)**.
+For older changelogs, please visit the **[CHANGELOG](CHANGELOG.md#v114-11-september-2022)**.
 
 ## :material-target: Troubleshooting
 

docs/installation/INSTALL_MAC.md

@@ -51,7 +51,15 @@ While that is downloading, open Terminal and run the following commands one at a
         brew install cmake protobuf rust
         ```
 
-        Then choose the kind of your Mac and install miniconda:
+        Then clone the InvokeAI repository:
+        
+        ```bash title="Clone the InvokeAI repository:
+         # Clone the Invoke AI repo
+         git clone https://github.com/invoke-ai/InvokeAI.git
+         cd InvokeAI
+         ```
+  
+      Choose the appropriate architecture for your system and install miniconda:
 
         === "M1 arm64"
 
@@ -81,7 +89,7 @@ While that is downloading, open Terminal and run the following commands one at a
 
 !!! todo "Clone the Invoke AI repo"
 
-    ```bash 
+```bash 
     git clone https://github.com/invoke-ai/InvokeAI.git
     cd InvokeAI
     ```
@@ -178,7 +186,7 @@ conda install \
   pytorch \
   torchvision \
   -c pytorch-nightly \
-  -n ldm
+  -n invokeai
 ```
 
 If it takes forever to run `conda env create -f environment-mac.yml`, try this:
@@ -202,11 +210,11 @@ conda update \
 
 ---
 
-### "No module named cv2", torch, 'ldm', 'transformers', 'taming', etc
+### "No module named cv2", torch, 'invokeai', 'transformers', 'taming', etc
 
 There are several causes of these errors:
 
-1. Did you remember to `conda activate ldm`? If your terminal prompt begins with
+1. Did you remember to `conda activate invokeai`? If your terminal prompt begins with
    "(invokeai)" then you activated it. If it begins with "(base)" or something else
    you haven't.
 
@@ -221,17 +229,17 @@ There are several causes of these errors:
 
     ```bash
     conda deactivate
-    conda env remove -n ldm
+    conda env remove -n invokeai
     conda env create -f environment-mac.yml
     ```
 
-4. If you have activated the ldm virtual environment and tried rebuilding it,
+4. If you have activated the invokeai virtual environment and tried rebuilding it,
    maybe the problem could be that I have something installed that you don't and
    you'll just need to manually install it. Make sure you activate the virtual
    environment so it installs there instead of globally.
 
     ```bash
-    conda activate ldm
+    conda activate invokeai
     pip install <package name>
     ```
 
@@ -290,11 +298,11 @@ output of `python3 -V` and `python -V`.
 
 ```bash
 (invokeai) % which python
-/Users/name/miniforge3/envs/ldm/bin/python
+/Users/name/miniforge3/envs/invokeai/bin/python
 ```
 
 The above is what you'll see if you have miniforge and correctly activated the
-ldm environment, while usingd the standalone setup instructions above.
+invokeai environment, while usingd the standalone setup instructions above.
 
 If you otherwise installed via pyenv, you will get this result:
 
@@ -474,7 +482,7 @@ this issue too. I should probably test it.
 ### "view size is not compatible with input tensor's size and stride"
 
 ```bash
-File "/opt/anaconda3/envs/ldm/lib/python3.10/site-packages/torch/nn/functional.py", line 2511, in layer_norm
+File "/opt/anaconda3/envs/invokeai/lib/python3.10/site-packages/torch/nn/functional.py", line 2511, in layer_norm
 return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
 RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
 ```
@@ -510,7 +518,7 @@ Generating:   0%|                                                              |
                                                                                                     loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible
 LLVM ERROR: Failed to infer result type(s).
 Abort trap: 6
-/Users/[...]/opt/anaconda3/envs/ldm/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
+/Users/[...]/opt/anaconda3/envs/invokeai/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
   warnings.warn('resource_tracker: There appear to be %d '
 ```
 

environment-mac.yml

@@ -3,55 +3,53 @@ channels:
   - pytorch
   - conda-forge
 dependencies:
-  - python==3.9.13
-  - pip==22.2.2
+  - python>=3.9, <3.10
+  - pip>=22.2
 
   # pytorch left unpinned
-  - pytorch==1.12.1
-  - torchvision==0.13.1
-
+  - pytorch
+  - torchvision
   # I suggest to keep the other deps sorted for convenience.
   # To determine what the latest versions should be, run:
   #
   # ```shell
-  # sed -E 's/ldm/ldm-updated/;20,99s/- ([^=]+)==.+/- \1/' environment-mac.yml > environment-mac-updated.yml
-  # CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac-updated.yml && conda list -n ldm-updated | awk ' {print "  - " $1 "==" $2;} '
+  # sed -E 's/invokeai/invokeai-updated/;20,99s/- ([^=]+)==.+/- \1/' environment-mac.yml > environment-mac-updated.yml
+  # CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac-updated.yml && conda list -n invokeai-updated | awk ' {print "  - " $1 "==" $2;} '
   # ```
-  - albumentations==1.2.1
-  - coloredlogs==15.0.1
-  - einops==0.4.1
-  - grpcio==1.46.4
-  - humanfriendly==10.0
-  - imageio==2.21.2
-  - imageio-ffmpeg==0.4.7
-  - imgaug==0.4.0
-  - kornia==0.6.7
-  - mpmath==1.2.1
-  - nomkl=1.0
-  - numpy==1.23.2
-  - omegaconf==2.1.1
-  - openh264==2.3.0
-  - onnx==1.12.0
-  - onnxruntime==1.12.1
-  - pudb==2022.1
-  - pytorch-lightning==1.7.5
-  - scipy==1.9.1
-  - streamlit==1.12.2
-  - sympy==1.10.1
-  - tensorboard==2.10.0
-  - torchmetrics==0.9.3
+  - albumentations
+  - coloredlogs
+  - einops
+  - grpcio
+  - humanfriendly
+  - imageio
+  - imageio-ffmpeg
+  - imgaug
+  - kornia
+  - mpmath
+  - nomkl
+  - numpy
+  - omegaconf
+  - openh264
+  - onnx
+  - onnxruntime
+  - pudb
+  - pytorch-lightning
+  - scipy
+  - streamlit
+  - sympy
+  - tensorboard
+  - torchmetrics
   - pip:
       - flask==2.1.3
       - flask_socketio==5.3.0
       - flask_cors==3.0.10
       - dependency_injector==4.40.0
       - eventlet==0.33.1
-      - opencv-python==4.6.0
-      - protobuf==3.19.5
+      - protobuf==3.19.6
       - realesrgan==0.2.5.0
       - send2trash==1.8.0
       - test-tube==0.7.5
-      - transformers==4.21.2
+      - transformers==4.21.3
       - torch-fidelity==0.3.0
       - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
       - -e git+https://github.com/openai/CLIP.git@main#egg=clip

environment.yml

@@ -4,18 +4,18 @@ channels:
   - defaults
 dependencies:
   - python>=3.9
-  - pip=20.3
-  - cudatoolkit=11.3
-  - pytorch=1.11.0
-  - torchvision=0.12.0
-  - numpy=1.19.2
+  - pip>=22.2
+  - cudatoolkit
+  - pytorch
+  - torchvision
+  - numpy
   - pip:
     - albumentations==0.4.3
     - opencv-python==4.5.5.64
     - pudb==2019.2
     - imageio==2.9.0
     - imageio-ffmpeg==0.4.2
-    - pytorch-lightning==1.4.2
+    - pytorch-lightning==1.7.7
     - omegaconf==2.1.1
     - realesrgan==0.2.5.0
     - test-tube>=0.7.5
@@ -25,8 +25,8 @@ dependencies:
     - einops==0.3.0
     - pyreadline3
     - torch-fidelity==0.3.0
-    - transformers==4.19.2
-    - torchmetrics==0.6.0
+    - transformers==4.21.3
+    - torchmetrics==0.7.0
     - flask==2.1.3
     - flask_socketio==5.3.0
     - flask_cors==3.0.10

frontend/dist/index.html

@@ -6,7 +6,7 @@
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>InvokeAI - A Stable Diffusion Toolkit</title>
   <link rel="shortcut icon" type="icon" href="/assets/favicon.0d253ced.ico" />
-  <script type="module" crossorigin src="/assets/index.989a0ca2.js"></script>
+  <script type="module" crossorigin src="/assets/index.ea68b5f5.js"></script>
   <link rel="stylesheet" href="/assets/index.58175ea1.css">
 </head>
 

frontend/src/app/constants.ts

@@ -50,6 +50,7 @@ export const PARAMETERS: { [key: string]: string } = {
   maskPath: 'Initial Image Mask',
   shouldFitToWidthHeight: 'Fit Initial Image',
   seamless: 'Seamless Tiling',
+  hiresFix: 'High Resolution Optimizations',
 };
 
 export const NUMPY_RAND_MIN = 0;

frontend/src/app/features.ts

@@ -14,10 +14,13 @@ export enum Feature {
   FACE_CORRECTION,
   IMAGE_TO_IMAGE,
 }
-
+/** For each tooltip in the UI, the below feature definitions & props will pull relevant information into the tooltip.
+ * 
+ * To-do: href & GuideImages are placeholders, and are not currently utilized, but will be updated (along with the tooltip UI) as feature and UI development and we get a better idea on where things "forever homes" will be . 
+ */
 export const FEATURES: Record<Feature, FeatureHelpInfo> = {
   [Feature.PROMPT]: {
-    text: 'This field will take all prompt text, including both content and stylistic terms. CLI Commands will not work in the prompt.',
+    text: 'This field will take all prompt text, including both content and stylistic terms. While weights can be included in the prompt, standard CLI Commands/parameters will not work.',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
@@ -27,17 +30,16 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
     guideImage: 'asset/path.gif',
   },
   [Feature.OTHER]: {
-    text: 'Additional Options',
-    href: 'link/to/docs/feature3.html',
+    text: 'These options will enable alternative processing modes for Invoke. Seamless tiling will work to generate repeating patterns in the output. High Resolution Optimization performs a two-step generation cycle, and should be used at higher resolutions when you desire a more coherent image/composition. ',    href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.SEED]: {
-    text: 'Seed values provide an initial set of noise which guide the denoising process.',
+    text: 'Seed values provide an initial set of noise which guide the denoising process, and can be randomized or populated with a seed from a previous invocation. The Threshold feature can be used to mitigate undesirable outcomes at higher CFG values (try between 0-10), and Perlin can be used to add Perlin noise into the denoising process - Both serve to add variation to your outputs. ',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.VARIATIONS]: {
-    text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed.',
+    text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed - Interesting variations on the seed are found between 0.1 and 0.3.',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
@@ -47,8 +49,8 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
     guideImage: 'asset/path.gif',
   },
   [Feature.FACE_CORRECTION]: {
-    text: 'Using GFPGAN or CodeFormer, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs.',
-    href: 'link/to/docs/feature2.html',
+    text: 'Using GFPGAN, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs, resulting in more appealing faces (with less respect for accuracy of the original subject).',
+    href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.IMAGE_TO_IMAGE]: {

frontend/src/app/invokeai.d.ts

@@ -55,6 +55,7 @@ export declare type CommonGeneratedImageMetadata = {
   width: number;
   height: number;
   seamless: boolean;
+  hires_fix: boolean;
   extra: null | Record<string, never>; // Pending development of RFC #266
 };
 

frontend/src/app/socketio/emitters.ts

@@ -76,7 +76,7 @@ const makeSocketIOEmitters = (
       const { gfpganStrength } = getState().options;
 
       const gfpganParameters = {
-        gfpgan_strength: gfpganStrength,
+        facetool_strength: gfpganStrength,
       };
       socketio.emit('runPostprocessing', imageToProcess, {
         type: 'gfpgan',

frontend/src/common/util/parameterTranslation.ts

@@ -29,6 +29,7 @@ export const frontendToBackendParameters = (
     sampler,
     seed,
     seamless,
+    hiresFix,
     shouldUseInitImage,
     img2imgStrength,
     initialImagePath,
@@ -59,6 +60,7 @@ export const frontendToBackendParameters = (
     sampler_name: sampler,
     seed,
     seamless,
+    hires_fix: hiresFix,
     progress_images: shouldDisplayInProgress,
   };
 
@@ -123,10 +125,11 @@ export const backendToFrontendParameters = (parameters: {
     sampler_name,
     seed,
     seamless,
+    hires_fix,
     progress_images,
     variation_amount,
     with_variations,
-    gfpgan_strength,
+    facetool_strength,
     upscale,
     init_img,
     init_mask,
@@ -151,9 +154,9 @@ export const backendToFrontendParameters = (parameters: {
     }
   }
 
-  if (gfpgan_strength > 0) {
+  if (facetool_strength > 0) {
     options.shouldRunGFPGAN = true;
-    options.gfpganStrength = gfpgan_strength;
+    options.gfpganStrength = facetool_strength;
   }
 
   if (upscale) {
@@ -185,6 +188,7 @@ export const backendToFrontendParameters = (parameters: {
     options.sampler = sampler_name;
     options.seed = seed;
     options.seamless = seamless;
+    options.hiresFix = hires_fix;
   }
 
   return options;

frontend/src/features/gallery/ImageMetaDataViewer/ImageMetadataViewer.tsx

@@ -16,11 +16,13 @@ import {
   setCfgScale,
   setGfpganStrength,
   setHeight,
+  setHiresFix,
   setImg2imgStrength,
   setInitialImagePath,
   setMaskPath,
   setPrompt,
   setSampler,
+  setSeamless,
   setSeed,
   setSeedWeights,
   setShouldFitToWidthHeight,
@@ -116,6 +118,7 @@ const ImageMetadataViewer = memo(
       steps,
       cfg_scale,
       seamless,
+      hires_fix,
       width,
       height,
       strength,
@@ -214,7 +217,14 @@ const ImageMetadataViewer = memo(
                 <MetadataItem
                   label="Seamless"
                   value={seamless}
-                  onClick={() => dispatch(setWidth(seamless))}
+                  onClick={() => dispatch(setSeamless(seamless))}
+                />
+              )}
+              {hires_fix && (
+                <MetadataItem
+                  label="High Resolution Optimization"
+                  value={hires_fix}
+                  onClick={() => dispatch(setHiresFix(hires_fix))}
                 />
               )}
               {width && (

frontend/src/features/options/HiresOptions.tsx

@@ -0,0 +1,32 @@
+import { Flex } from '@chakra-ui/react';
+import { RootState } from '../../app/store';
+import { useAppDispatch, useAppSelector } from '../../app/store';
+import { setHiresFix } from './optionsSlice';
+import { ChangeEvent } from 'react';
+import IAISwitch from '../../common/components/IAISwitch';
+
+/**
+ * Image output options. Includes width, height, seamless tiling.
+ */
+const HiresOptions = () => {
+  const dispatch = useAppDispatch();
+
+  const hiresFix = useAppSelector((state: RootState) => state.options.hiresFix);
+
+  const handleChangeHiresFix = (e: ChangeEvent<HTMLInputElement>) =>
+    dispatch(setHiresFix(e.target.checked));
+
+
+  return (
+    <Flex gap={2} direction={'column'}>
+      <IAISwitch
+        label="High Res Optimization"
+        fontSize={'md'}
+        isChecked={hiresFix}
+        onChange={handleChangeHiresFix}
+      />
+    </Flex>
+  );
+};
+
+export default HiresOptions;

frontend/src/features/options/OutputOptions.tsx

@@ -1,29 +1,14 @@
 import { Flex } from '@chakra-ui/react';
-import { RootState } from '../../app/store';
-import { useAppDispatch, useAppSelector } from '../../app/store';
-import { setSeamless } from './optionsSlice';
-import { ChangeEvent } from 'react';
-import IAISwitch from '../../common/components/IAISwitch';
 
-/**
- * Image output options. Includes width, height, seamless tiling.
- */
+import HiresOptions from './HiresOptions';
+import SeamlessOptions from './SeamlessOptions';
+
 const OutputOptions = () => {
-  const dispatch = useAppDispatch();
-
-  const seamless = useAppSelector((state: RootState) => state.options.seamless);
-
-  const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
-    dispatch(setSeamless(e.target.checked));
 
   return (
     <Flex gap={2} direction={'column'}>
-      <IAISwitch
-        label="Seamless tiling"
-        fontSize={'md'}
-        isChecked={seamless}
-        onChange={handleChangeSeamless}
-      />
+      <SeamlessOptions />
+      <HiresOptions />
     </Flex>
   );
 };

frontend/src/features/options/SeamlessOptions.tsx

@@ -0,0 +1,28 @@
+import { Flex } from '@chakra-ui/react';
+import { RootState } from '../../app/store';
+import { useAppDispatch, useAppSelector } from '../../app/store';
+import { setSeamless } from './optionsSlice';
+import { ChangeEvent } from 'react';
+import IAISwitch from '../../common/components/IAISwitch';
+
+const SeamlessOptions = () => {
+  const dispatch = useAppDispatch();
+
+  const seamless = useAppSelector((state: RootState) => state.options.seamless);
+
+  const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
+    dispatch(setSeamless(e.target.checked));
+
+  return (
+    <Flex gap={2} direction={'column'}>
+      <IAISwitch
+        label="Seamless tiling"
+        fontSize={'md'}
+        isChecked={seamless}
+        onChange={handleChangeSeamless}
+      />
+    </Flex>
+  );
+};
+
+export default SeamlessOptions;

frontend/src/features/options/optionsSlice.ts

@@ -25,6 +25,7 @@ export interface OptionsState {
   initialImagePath: string | null;
   maskPath: string;
   seamless: boolean;
+  hiresFix: boolean;
   shouldFitToWidthHeight: boolean;
   shouldGenerateVariations: boolean;
   variationAmount: number;
@@ -50,6 +51,7 @@ const initialOptionsState: OptionsState = {
   perlin: 0,
   seed: 0,
   seamless: false,
+  hiresFix: false,
   shouldUseInitImage: false,
   img2imgStrength: 0.75,
   initialImagePath: null,
@@ -138,6 +140,9 @@ export const optionsSlice = createSlice({
     setSeamless: (state, action: PayloadAction<boolean>) => {
       state.seamless = action.payload;
     },
+    setHiresFix: (state, action: PayloadAction<boolean>) => {
+      state.hiresFix = action.payload;
+    },
     setShouldFitToWidthHeight: (state, action: PayloadAction<boolean>) => {
       state.shouldFitToWidthHeight = action.payload;
     },
@@ -180,6 +185,7 @@ export const optionsSlice = createSlice({
         threshold,
         perlin,
         seamless,
+        hires_fix,
         width,
         height,
         strength,
@@ -256,6 +262,7 @@ export const optionsSlice = createSlice({
       if (perlin) state.perlin = perlin;
       if (typeof perlin === 'undefined') state.perlin = 0;      
       if (typeof seamless === 'boolean') state.seamless = seamless;
+      if (typeof hires_fix === 'boolean') state.hiresFix = hires_fix;
       if (width) state.width = width;
       if (height) state.height = height;
     },
@@ -301,6 +308,7 @@ export const {
   setSampler,
   setSeed,
   setSeamless,
+  setHiresFix,
   setImg2imgStrength,
   setGfpganStrength,
   setUpscalingLevel,

ldm/generate.py

@@ -33,6 +33,25 @@ from ldm.invoke.args import metadata_from_png
 from ldm.invoke.image_util import InitImageResizer
 from ldm.invoke.devices import choose_torch_device, choose_precision
 from ldm.invoke.conditioning import get_uc_and_c
+from ldm.invoke.model_cache import ModelCache
+
+def fix_func(orig):
+    if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
+        def new_func(*args, **kw):
+            device = kw.get("device", "mps")
+            kw["device"]="cpu"
+            return orig(*args, **kw).to(device)
+        return new_func
+    return orig
+
+torch.rand = fix_func(torch.rand)
+torch.rand_like = fix_func(torch.rand_like)
+torch.randn = fix_func(torch.randn)
+torch.randn_like = fix_func(torch.randn_like)
+torch.randint = fix_func(torch.randint)
+torch.randint_like = fix_func(torch.randint_like)
+torch.bernoulli = fix_func(torch.bernoulli)
+torch.multinomial = fix_func(torch.multinomial)
 
 def fix_func(orig):
     if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
@@ -113,7 +132,7 @@ gr = Generate(
 
           # these are deprecated - use conf and model instead
           weights     = path to model weights ('models/ldm/stable-diffusion-v1/model.ckpt')
-          config      = path to model configuraiton ('configs/stable-diffusion/v1-inference.yaml')
+          config      = path to model configuration ('configs/stable-diffusion/v1-inference.yaml')
           )
 
 """
@@ -141,12 +160,11 @@ class Generate:
             esrgan=None,
             free_gpu_mem=False,
     ):
-        models              = OmegaConf.load(conf)
-        mconfig             = models[model]
-        self.weights        = mconfig.weights if weights is None else weights
-        self.config         = mconfig.config  if config  is None else config
-        self.height         = mconfig.height
-        self.width          = mconfig.width
+        mconfig             = OmegaConf.load(conf)
+        self.model_name     = model
+        self.height         = None
+        self.width          = None
+        self.model_cache    = None
         self.iterations     = 1
         self.steps          = 50
         self.cfg_scale      = 7.5
@@ -155,8 +173,10 @@ class Generate:
         self.precision      = precision
         self.strength       = 0.75
         self.seamless       = False
+        self.hires_fix      = False
         self.embedding_path = embedding_path
         self.model          = None     # empty for now
+        self.model_hash     = None
         self.sampler        = None
         self.device         = None
         self.session_peakmem = None
@@ -167,11 +187,13 @@ class Generate:
         self.codeformer = codeformer
         self.esrgan = esrgan
         self.free_gpu_mem = free_gpu_mem
+        self.size_matters = True  # used to warn once about large image sizes and VRAM
 
         # Note that in previous versions, there was an option to pass the
         # device to Generate(). However the device was then ignored, so
         # it wasn't actually doing anything. This logic could be reinstated.
         device_type = choose_torch_device()
+        print(f'>> Using device_type {device_type}')
         self.device = torch.device(device_type)
         if full_precision:
             if self.precision != 'auto':
@@ -182,6 +204,9 @@ class Generate:
         if self.precision == 'auto':
             self.precision = choose_precision(self.device)
 
+        # model caching system for fast switching
+        self.model_cache = ModelCache(mconfig,self.device,self.precision)
+
         # for VRAM usage statistics
         self.session_peakmem = torch.cuda.max_memory_allocated() if self._has_cuda else None
         transformers.logging.set_verbosity_error()
@@ -249,10 +274,12 @@ class Generate:
             embiggen_tiles =    None,
             # these are specific to GFPGAN/ESRGAN
             facetool         = None,
-            gfpgan_strength  = 0,
+            facetool_strength  = 0,
             codeformer_fidelity = None,
             save_original    = False,
             upscale          = None,
+            # this is specific to inpainting and causes more extreme inpainting
+            inpaint_replace  = 0.0,
             # Set this True to handle KeyboardInterrupt internally
             catch_interrupts = False,
             hires_fix        = False,
@@ -269,9 +296,10 @@ class Generate:
            height                          // height of image, in multiples of 64 (512)
            cfg_scale                       // how strongly the prompt influences the image (7.5) (must be >1)
            seamless                        // whether the generated image should tile
+           hires_fix                        // whether the Hires Fix should be applied during generation
            init_img                        // path to an initial image
            strength                        // strength for noising/unnoising init_img. 0.0 preserves image exactly, 1.0 replaces it completely
-           gfpgan_strength                 // strength for GFPGAN. 0.0 preserves image exactly, 1.0 replaces it completely
+           facetool_strength               // strength for GFPGAN/CodeFormer. 0.0 preserves image exactly, 1.0 replaces it completely
            ddim_eta                        // image randomness (eta=0.0 means the same seed always produces the same image)
            step_callback                   // a function or method that will be called each step
            image_callback                  // a function or method that will be called each time an image is generated
@@ -302,6 +330,7 @@ class Generate:
         width = width or self.width
         height = height or self.height
         seamless = seamless or self.seamless
+        hires_fix = hires_fix or self.hires_fix
         cfg_scale = cfg_scale or self.cfg_scale
         ddim_eta = ddim_eta or self.ddim_eta
         iterations = iterations or self.iterations
@@ -312,7 +341,12 @@ class Generate:
         with_variations = [] if with_variations is None else with_variations
 
         # will instantiate the model or return it from cache
-        model = self.load_model()
+        model = self.set_model(self.model_name)
+
+        # self.width and self.height are set by set_model()
+        # to the width and height of the image training set
+        width = width or self.width
+        height = height or self.height
         
         for m in model.modules():
             if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
@@ -344,6 +378,7 @@ class Generate:
                 f'variation weights must be in [0.0, 1.0]: got {[weight for _, weight in with_variations]}'
 
         width, height, _ = self._resolution_check(width, height, log=True)
+        assert inpaint_replace >=0.0 and inpaint_replace <= 1.0,'inpaint_replace must be between 0.0 and 1.0'
 
         if sampler_name and (sampler_name != self.sampler_name):
             self.sampler_name = sampler_name
@@ -371,6 +406,8 @@ class Generate:
                 height,
                 fit=fit,
             )
+
+            # TODO: Hacky selection of operation to perform. Needs to be refactored.
             if (init_image is not None) and (mask_image is not None):
                 generator = self._make_inpaint()
             elif (embiggen != None or embiggen_tiles != None):
@@ -385,6 +422,7 @@ class Generate:
             generator.set_variation(
                 self.seed, variation_amount, with_variations
             )
+
             results = generator.generate(
                 prompt,
                 iterations=iterations,
@@ -406,6 +444,7 @@ class Generate:
                 perlin=perlin,
                 embiggen=embiggen,
                 embiggen_tiles=embiggen_tiles,
+                inpaint_replace=inpaint_replace,
             )
 
             if init_color:
@@ -413,11 +452,11 @@ class Generate:
                                     reference_image_path = init_color,
                                     image_callback       = image_callback)
 
-            if upscale is not None or gfpgan_strength > 0:
+            if upscale is not None or facetool_strength > 0:
                 self.upscale_and_reconstruct(results,
                                              upscale        = upscale,
                                              facetool       = facetool,
-                                             strength       = gfpgan_strength,
+                                             strength       = facetool_strength,
                                              codeformer_fidelity = codeformer_fidelity,
                                              save_original  = save_original,
                                              image_callback = image_callback)
@@ -460,7 +499,7 @@ class Generate:
             self,
             image_path,
             tool                = 'gfpgan',  # one of 'upscale', 'gfpgan', 'codeformer', 'outpaint', or 'embiggen'
-            gfpgan_strength     = 0.0,
+            facetool_strength   = 0.0,
             codeformer_fidelity = 0.75,
             upscale             = None,
             out_direction       = None,
@@ -507,11 +546,11 @@ class Generate:
                 facetool = 'codeformer'
             elif tool == 'upscale':
                 facetool = 'gfpgan'   # but won't be run
-                gfpgan_strength = 0
+                facetool_strength = 0
             return self.upscale_and_reconstruct(
                 [[image,seed]],
                 facetool = facetool,
-                strength = gfpgan_strength,
+                strength = facetool_strength,
                 codeformer_fidelity = codeformer_fidelity,
                 save_original = save_original,
                 upscale = upscale,
@@ -602,8 +641,9 @@ class Generate:
             # this returns a torch tensor
             init_mask = self._create_init_mask(image, width, height, fit=fit)
             
-        if (image.width * image.height) > (self.width * self.height):
+        if (image.width * image.height) > (self.width * self.height) and self.size_matters:
             print(">> This input is larger than your defaults. If you run out of memory, please use a smaller image.")
+            self.size_matters = False
 
         init_image   = self._create_init_image(image,width,height,fit=fit)                   # this returns a torch tensor
 
@@ -653,29 +693,40 @@ class Generate:
         return self.generators['inpaint']
 
     def load_model(self):
-        """Load and initialize the model from configuration variables passed at object creation time"""
-        if self.model is None:
-            seed_everything(random.randrange(0, np.iinfo(np.uint32).max))
-            try:
-                model = self._load_model_from_config(self.config, self.weights)
-                if self.embedding_path is not None:
-                    model.embedding_manager.load(
-                        self.embedding_path, self.precision == 'float32' or self.precision == 'autocast'
-                    )
-                self.model = model.to(self.device)
-                # model.to doesn't change the cond_stage_model.device used to move the tokenizer output, so set it here
-                self.model.cond_stage_model.device = self.device
-            except AttributeError as e:
-                print(f'>> Error loading model. {str(e)}', file=sys.stderr)
-                print(traceback.format_exc(), file=sys.stderr)
-                raise SystemExit from e
+        '''
+        preload model identified in self.model_name
+        '''
+        self.set_model(self.model_name)
 
-            self._set_sampler()
+    def set_model(self,model_name):
+        """ 
+        Given the name of a model defined in models.yaml, will load and initialize it
+        and return the model object. Previously-used models will be cached.
+        """
+        if self.model_name == model_name and self.model is not None:
+            return self.model
 
-            for m in self.model.modules():
-                if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
-                    m._orig_padding_mode = m.padding_mode
+        model_data = self.model_cache.get_model(model_name)
+        if model_data is None or len(model_data) == 0:
+            print(f'** Model switch failed **')
+            return self.model
 
+        self.model = model_data['model']
+        self.width = model_data['width']
+        self.height= model_data['height']
+        self.model_hash = model_data['hash']
+
+        # uncache generators so they pick up new models
+        self.generators = {}
+        
+        seed_everything(random.randrange(0, np.iinfo(np.uint32).max))
+        if self.embedding_path is not None:
+            model.embedding_manager.load(
+                self.embedding_path, self.precision == 'float32' or self.precision == 'autocast'
+            )
+
+        self._set_sampler()
+        self.model_name = model_name
         return self.model
 
     def correct_colors(self,
@@ -779,53 +830,6 @@ class Generate:
 
         print(msg)
 
-    # Be warned: config is the path to the model config file, not the invoke conf file!
-    # Also note that we can get config and weights from self, so why do we need to
-    # pass them as args?
-    def _load_model_from_config(self, config, weights):
-        print(f'>> Loading model from {weights}')
-
-        # for usage statistics
-        device_type = choose_torch_device()
-        if device_type == 'cuda':
-            torch.cuda.reset_peak_memory_stats()
-        tic = time.time()
-
-        # this does the work
-        c     = OmegaConf.load(config)
-        with open(weights,'rb') as f:
-            weight_bytes = f.read()
-        self.model_hash  = self._cached_sha256(weights,weight_bytes)
-        pl_sd = torch.load(io.BytesIO(weight_bytes), map_location='cpu')
-        del weight_bytes
-        sd    = pl_sd['state_dict']
-        model = instantiate_from_config(c.model)
-        m, u  = model.load_state_dict(sd, strict=False)
-
-        if self.precision == 'float16':
-            print('>> Using faster float16 precision')
-            model.to(torch.float16)
-        else:
-            print('>> Using more accurate float32 precision')
-
-        model.to(self.device)
-        model.eval()
-
-        # usage statistics
-        toc = time.time()
-        print(
-            f'>> Model loaded in', '%4.2fs' % (toc - tic)
-        )
-        if self._has_cuda():
-            print(
-                '>> Max VRAM used to load the model:',
-                '%4.2fG' % (torch.cuda.max_memory_allocated() / 1e9),
-                '\n>> Current VRAM usage:'
-                '%4.2fG' % (torch.cuda.memory_allocated() / 1e9),
-            )
-
-        return model
-
     def _load_img(self, img, width, height)->Image:
         if isinstance(img, Image.Image):
             image = img
@@ -969,26 +973,6 @@ class Generate:
     def _has_cuda(self):
         return self.device.type == 'cuda'
 
-    def _cached_sha256(self,path,data):
-        dirname    = os.path.dirname(path)
-        basename   = os.path.basename(path)
-        base, _    = os.path.splitext(basename)
-        hashpath   = os.path.join(dirname,base+'.sha256')
-        if os.path.exists(hashpath) and os.path.getmtime(path) <= os.path.getmtime(hashpath):
-            with open(hashpath) as f:
-                hash = f.read()
-            return hash
-        print(f'>> Calculating sha256 hash of weights file')
-        tic = time.time()
-        sha = hashlib.sha256()
-        sha.update(data)
-        hash = sha.hexdigest()
-        toc = time.time()
-        print(f'>> sha256 = {hash}','(%4.2fs)' % (toc - tic))
-        with open(hashpath,'w') as f:
-            f.write(hash)
-        return hash
-
     def write_intermediate_images(self,modulus,path):
         counter = -1
         if not os.path.exists(path):

ldm/invoke/args.py

@@ -239,12 +239,17 @@ class Args(object):
                 switches.append(f'--init_color {a["init_color"]}')
             if a['strength'] and a['strength']>0:
                 switches.append(f'-f {a["strength"]}')
+            if a['inpaint_replace']:
+                switches.append(f'--inpaint_replace')
         else:
             switches.append(f'-A {a["sampler_name"]}')
 
-        # gfpgan-specific parameters
-        if a['gfpgan_strength']:
-            switches.append(f'-G {a["gfpgan_strength"]}')
+        # facetool-specific parameters, only print if running facetool
+        if a['facetool_strength']:
+            switches.append(f'-G {a["facetool_strength"]}')
+            switches.append(f'-ft {a["facetool"]}')
+            if a["facetool"] == "codeformer":
+                switches.append(f'-cf {a["codeformer_fidelity"]}')
 
         if a['outcrop']:
             switches.append(f'-c {" ".join([str(u) for u in a["outcrop"]])}')
@@ -262,11 +267,12 @@ class Args(object):
         # outpainting parameters
         if a['out_direction']:
             switches.append(f'-D {" ".join([str(u) for u in a["out_direction"]])}')
+
         # LS: slight semantic drift which needs addressing in the future:
         # 1. Variations come out of the stored metadata as a packed string with the keyword "variations"
         # 2. However, they come out of the CLI (and probably web) with the keyword "with_variations" and
         #    in broken-out form. Variation (1) should be changed to comply with (2)
-        if a['with_variations']:
+        if a['with_variations'] and len(a['with_variations'])>0:
             formatted_variations = ','.join(f'{seed}:{weight}' for seed, weight in (a["with_variations"]))
             switches.append(f'-V {formatted_variations}')
         if 'variations' in a and len(a['variations'])>0:
@@ -372,6 +378,14 @@ class Args(object):
             default='stable-diffusion-1.4',
             help='Indicates which diffusion model to load. (currently "stable-diffusion-1.4" (default) or "laion400m")',
         )
+        model_group.add_argument(
+            '--png_compression','-z',
+            type=int,
+            default=6,
+            choices=range(0,9),
+            dest='png_compression',
+            help='level of PNG compression, from 0 (none) to 9 (maximum). Default is 6.'
+        )
         model_group.add_argument(
             '--sampler',
             '-A',
@@ -643,6 +657,14 @@ class Args(object):
             dest='save_intermediates',
             help='Save every nth intermediate image into an "intermediates" directory within the output directory'
         )
+        render_group.add_argument(
+            '--png_compression','-z',
+            type=int,
+            default=6,
+            choices=range(0,10),
+            dest='png_compression',
+            help='level of PNG compression, from 0 (none) to 9 (maximum). Default is 6.'
+        )
         img2img_group.add_argument(
             '-I',
             '--init_img',
@@ -690,6 +712,13 @@ class Args(object):
             metavar=('direction','pixels'),
             help='Outcrop the image with one or more direction/pixel pairs: -c top 64 bottom 128 left 64 right 64',
         )
+        img2img_group.add_argument(
+            '-r',
+            '--inpaint_replace',
+            type=float,
+            default=0.0,
+            help='when inpainting, adjust how aggressively to replace the part of the picture under the mask, from 0.0 (a gentle merge) to 1.0 (replace entirely)',
+        )
         postprocessing_group.add_argument(
             '-ft',
             '--facetool',
@@ -699,6 +728,7 @@ class Args(object):
         )
         postprocessing_group.add_argument(
             '-G',
+            '--facetool_strength',
             '--gfpgan_strength',
             type=float,
             help='The strength at which to apply the face restoration to the result.',
@@ -795,7 +825,8 @@ def metadata_dumps(opt,
 
     # remove any image keys not mentioned in RFC #266
     rfc266_img_fields = ['type','postprocessing','sampler','prompt','seed','variations','steps',
-                         'cfg_scale','threshold','perlin','step_number','width','height','extra','strength']
+                         'cfg_scale','threshold','perlin','step_number','width','height','extra','strength',
+                         'init_img','init_mask']
 
     rfc_dict ={}
 
@@ -816,11 +847,15 @@ def metadata_dumps(opt,
     # 'variations' should always exist and be an array, empty or consisting of {'seed': seed, 'weight': weight} pairs
     rfc_dict['variations'] = [{'seed':x[0],'weight':x[1]} for x in opt.with_variations] if opt.with_variations else []
 
+    # if variations are present then we need to replace 'seed' with 'orig_seed'
+    if hasattr(opt,'first_seed'):
+        rfc_dict['seed'] = opt.first_seed
+
     if opt.init_img:
-        rfc_dict['type']           = 'img2img'
-        rfc_dict['strength_steps'] = rfc_dict.pop('strength')
-        rfc_dict['orig_hash']      = calculate_init_img_hash(opt.init_img)
-        rfc_dict['sampler']        = 'ddim'  # TODO: FIX ME WHEN IMG2IMG SUPPORTS ALL SAMPLERS
+        rfc_dict['type']            = 'img2img'
+        rfc_dict['strength_steps']  = rfc_dict.pop('strength')
+        rfc_dict['orig_hash']       = calculate_init_img_hash(opt.init_img)
+        rfc_dict['inpaint_replace'] = opt.inpaint_replace
     else:
         rfc_dict['type']  = 'txt2img'
         rfc_dict.pop('strength')

ldm/invoke/generator/base.py

@@ -5,6 +5,7 @@ including img2img, txt2img, and inpaint
 import torch
 import numpy as  np
 import random
+import os
 from tqdm import tqdm, trange
 from PIL               import Image
 from einops import rearrange, repeat
@@ -168,3 +169,14 @@ class Generator():
 
         return v2
 
+    # this is a handy routine for debugging use. Given a generated sample,
+    # convert it into a PNG image and store it at the indicated path
+    def save_sample(self, sample, filepath):
+        image = self.sample_to_image(sample)
+        dirname = os.path.dirname(filepath) or '.'
+        if not os.path.exists(dirname):
+            print(f'** creating directory {dirname}')
+            os.makedirs(dirname, exist_ok=True)
+        image.save(filepath,'PNG')
+
+        

ldm/invoke/generator/inpaint.py

@@ -18,7 +18,7 @@ class Inpaint(Img2Img):
     @torch.no_grad()
     def get_make_image(self,prompt,sampler,steps,cfg_scale,ddim_eta,
                        conditioning,init_image,mask_image,strength,
-                       step_callback=None,**kwargs):
+                       step_callback=None,inpaint_replace=False,**kwargs):
         """
         Returns a function returning an image derived from the prompt and
         the initial image + mask.  Return value depends on the seed at
@@ -58,6 +58,14 @@ class Inpaint(Img2Img):
                 noise=x_T
             )
 
+            # to replace masked area with latent noise, weighted by inpaint_replace strength
+            if inpaint_replace > 0.0:
+                print(f'>> inpaint will replace what was under the mask with a strength of {inpaint_replace}')
+                l_noise = self.get_noise(kwargs['width'],kwargs['height'])
+                inverted_mask = 1.0-mask_image  # there will be 1s where the mask is
+                masked_region = (1.0-inpaint_replace) * inverted_mask * z_enc + inpaint_replace * inverted_mask * l_noise
+                z_enc   = z_enc * mask_image + masked_region
+
             # decode it
             samples = sampler.decode(
                 z_enc,

ldm/invoke/model_cache.py

@@ -0,0 +1,281 @@
+'''
+Manage a cache of Stable Diffusion model files for fast switching. 
+They are moved between GPU and CPU as necessary. If CPU memory falls
+below a preset minimum, the least recently used model will be
+cleared and loaded from disk when next needed.
+'''
+
+import torch
+import os
+import io
+import time
+import gc
+import hashlib
+import psutil
+import transformers
+from sys import getrefcount
+from omegaconf import OmegaConf
+from omegaconf.errors import ConfigAttributeError
+from ldm.util import instantiate_from_config
+
+GIGS=2**30
+AVG_MODEL_SIZE=2.1*GIGS
+DEFAULT_MIN_AVAIL=2*GIGS
+
+class ModelCache(object):
+    def __init__(self, config:OmegaConf, device_type:str, precision:str, min_avail_mem=DEFAULT_MIN_AVAIL):
+        '''
+        Initialize with the path to the models.yaml config file,
+        the torch device type, and precision. The optional
+        min_avail_mem argument specifies how much unused system
+        (CPU) memory to preserve. The cache of models in RAM will
+        grow until this value is approached. Default is 2G.
+        '''
+        # prevent nasty-looking CLIP log message
+        transformers.logging.set_verbosity_error()
+        self.config = config
+        self.precision = precision
+        self.device = torch.device(device_type)
+        self.min_avail_mem = min_avail_mem
+        self.models = {}
+        self.stack = []  # this is an LRU FIFO
+        self.current_model = None
+
+    def get_model(self, model_name:str):
+        '''
+        Given a model named identified in models.yaml, return
+        the model object. If in RAM will load into GPU VRAM.
+        If on disk, will load from there.
+        '''
+        if model_name not in self.config:
+            print(f'** "{model_name}" is not a known model name. Please check your models.yaml file')
+            return None
+
+        if self.current_model != model_name:
+            self.unload_model(self.current_model)
+        
+        if model_name in self.models:
+            requested_model = self.models[model_name]['model']
+            print(f'>> Retrieving model {model_name} from system RAM cache')
+            self.models[model_name]['model'] = self._model_from_cpu(requested_model)
+            width = self.models[model_name]['width']
+            height = self.models[model_name]['height']
+            hash = self.models[model_name]['hash']
+        else:
+            self._check_memory()
+            try:
+                requested_model, width, height, hash = self._load_model(model_name)
+                self.models[model_name] = {}
+                self.models[model_name]['model'] = requested_model
+                self.models[model_name]['width'] = width
+                self.models[model_name]['height'] = height
+                self.models[model_name]['hash'] = hash
+            except Exception as e:
+                print(f'** model {model_name} could not be loaded: {str(e)}')
+                print(f'** restoring {self.current_model}')
+                return self.get_model(self.current_model)
+        
+        self.current_model = model_name
+        self._push_newest_model(model_name)
+        return {
+            'model':requested_model,
+            'width':width,
+            'height':height,
+            'hash': hash
+        }
+
+    def list_models(self) -> dict:
+        '''
+        Return a dict of models in the format:
+        { model_name1: {'status': ('active'|'cached'|'not loaded'),
+                        'description': description,
+                       },
+          model_name2: { etc }
+        '''
+        result = {}
+        for name in self.config:
+            try:
+                description = self.config[name].description
+            except ConfigAttributeError:
+                description = '<no description>'
+            if self.current_model == name:
+                status = 'active'
+            elif name in self.models:
+                status = 'cached'
+            else:
+                status = 'not loaded'
+            result[name]={}
+            result[name]['status']=status
+            result[name]['description']=description
+        return result
+    
+    def print_models(self):
+        '''
+        Print a table of models, their descriptions, and load status
+        '''
+        models = self.list_models()
+        for name in models:
+            line = f'{name:25s} {models[name]["status"]:>10s}  {models[name]["description"]}'
+            if models[name]['status'] == 'active':
+                print(f'\033[1m{line}\033[0m')
+            else:
+                print(line)
+
+    def add_model(self, model_name:str, model_attributes:dict, clobber=False) ->str:
+        '''
+        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 and a YAML
+        string will be returned.
+        '''
+        omega = self.config
+        # check that all the required fields are present
+        for field in ('description','weights','height','width','config'):
+            assert field in model_attributes, f'required field {field} is missing'
+
+        assert (clobber or model_name not in omega), f'attempt to overwrite existing model definition "{model_name}"'
+        config = omega[model_name] if model_name in omega else {}
+        for field in model_attributes:
+            config[field] = model_attributes[field]
+
+        omega[model_name] = config
+        return OmegaConf.to_yaml(omega)
+    
+    def _check_memory(self):
+        avail_memory = psutil.virtual_memory()[1]
+        if AVG_MODEL_SIZE + self.min_avail_mem > avail_memory:
+            least_recent_model = self._pop_oldest_model()
+            if least_recent_model is not None:
+                del self.models[least_recent_model]
+                gc.collect()
+
+        
+    def _load_model(self, model_name:str):
+        """Load and initialize the model from configuration variables passed at object creation time"""
+        if model_name not in self.config:
+            print(f'"{model_name}" is not a known model name. Please check your models.yaml file')
+            return None
+
+        mconfig = self.config[model_name]
+        config = mconfig.config
+        weights = mconfig.weights
+        width = mconfig.width
+        height = mconfig.height
+
+        print(f'>> Loading {model_name} from {weights}')
+
+        # for usage statistics
+        if self._has_cuda():
+            torch.cuda.reset_peak_memory_stats()
+            torch.cuda.empty_cache()
+
+        tic = time.time()
+
+        # this does the work
+        c     = OmegaConf.load(config)
+        with open(weights,'rb') as f:
+            weight_bytes = f.read()
+        model_hash  = self._cached_sha256(weights,weight_bytes)
+        pl_sd = torch.load(io.BytesIO(weight_bytes), map_location='cpu')
+        del weight_bytes
+        sd    = pl_sd['state_dict']
+        model = instantiate_from_config(c.model)
+        m, u  = model.load_state_dict(sd, strict=False)
+
+        if self.precision == 'float16':
+            print('   | Using faster float16 precision')
+            model.to(torch.float16)
+        else:
+            print('   | Using more accurate float32 precision')
+
+        model.to(self.device)
+        # model.to doesn't change the cond_stage_model.device used to move the tokenizer output, so set it here
+        model.cond_stage_model.device = self.device
+        model.eval()
+
+        for m in model.modules():
+            if isinstance(m, (torch.nn.Conv2d, torch.nn.ConvTranspose2d)):
+                m._orig_padding_mode = m.padding_mode
+
+        # usage statistics
+        toc = time.time()
+        print(f'>> Model loaded in', '%4.2fs' % (toc - tic))
+        if self._has_cuda():
+            print(
+                '>> Max VRAM used to load the model:',
+                '%4.2fG' % (torch.cuda.max_memory_allocated() / 1e9),
+                '\n>> Current VRAM usage:'
+                '%4.2fG' % (torch.cuda.memory_allocated() / 1e9),
+            )
+        return model, width, height, model_hash
+        
+    def unload_model(self, model_name:str):
+        if model_name not in self.models:
+            return
+        print(f'>> Caching model {model_name} in system RAM')
+        model = self.models[model_name]['model']
+        self.models[model_name]['model'] = self._model_to_cpu(model)
+        gc.collect()
+        if self._has_cuda():
+            torch.cuda.empty_cache()
+
+    def _model_to_cpu(self,model):
+        if self.device != 'cpu':
+            model.cond_stage_model.device = 'cpu'
+            model.first_stage_model.to('cpu')
+            model.cond_stage_model.to('cpu') 
+            model.model.to('cpu')
+            return model.to('cpu')
+        else:
+            return model
+
+    def _model_from_cpu(self,model):
+        if self.device != 'cpu':
+            model.to(self.device)
+            model.first_stage_model.to(self.device)
+            model.cond_stage_model.to(self.device)
+            model.cond_stage_model.device = self.device
+        return model
+
+    def _pop_oldest_model(self):
+        '''
+        Remove the first element of the FIFO, which ought
+        to be the least recently accessed model. Do not
+        pop the last one, because it is in active use!
+        '''
+        if len(self.stack) > 1:
+            return self.stack.pop(0)
+
+    def _push_newest_model(self,model_name:str):
+        '''
+        Maintain a simple FIFO. First element is always the
+        least recent, and last element is always the most recent.
+        '''
+        try:
+            self.stack.remove(model_name)
+        except ValueError:
+            pass
+        self.stack.append(model_name)
+        
+    def _has_cuda(self):
+        return self.device.type == 'cuda'
+
+    def _cached_sha256(self,path,data):
+        dirname    = os.path.dirname(path)
+        basename   = os.path.basename(path)
+        base, _    = os.path.splitext(basename)
+        hashpath   = os.path.join(dirname,base+'.sha256')
+        if os.path.exists(hashpath) and os.path.getmtime(path) <= os.path.getmtime(hashpath):
+            with open(hashpath) as f:
+                hash = f.read()
+            return hash
+        print(f'>> Calculating sha256 hash of weights file')
+        tic = time.time()
+        sha = hashlib.sha256()
+        sha.update(data)
+        hash = sha.hexdigest()
+        toc = time.time()
+        print(f'>> sha256 = {hash}','(%4.2fs)' % (toc - tic))
+        with open(hashpath,'w') as f:
+            f.write(hash)
+        return hash

ldm/invoke/pngwriter.py

@@ -33,13 +33,13 @@ class PngWriter:
 
     # saves image named _image_ to outdir/name, writing metadata from prompt
     # returns full path of output
-    def save_image_and_prompt_to_png(self, image, dream_prompt, name, metadata=None):
+    def save_image_and_prompt_to_png(self, image, dream_prompt, name, metadata=None, compress_level=6):
         path = os.path.join(self.outdir, name)
         info = PngImagePlugin.PngInfo()
         info.add_text('Dream', dream_prompt)
         if metadata:
           info.add_text('sd-metadata', json.dumps(metadata))
-        image.save(path, 'PNG', pnginfo=info)
+        image.save(path, 'PNG', pnginfo=info, compress_level=compress_level)
         return path
 
     def retrieve_metadata(self,img_basename):

ldm/invoke/readline.py

@@ -21,6 +21,8 @@ except (ImportError,ModuleNotFoundError):
     readline_available = False
 
 IMG_EXTENSIONS     = ('.png','.jpg','.jpeg','.PNG','.JPG','.JPEG','.gif','.GIF')
+WEIGHT_EXTENSIONS  = ('.ckpt','.bae')
+CONFIG_EXTENSIONS  = ('.yaml','.yml')
 COMMANDS = (
     '--steps','-s',
     '--seed','-S',
@@ -42,13 +44,25 @@ COMMANDS = (
     '--embedding_path',
     '--device',
     '--grid','-g',
-    '--gfpgan_strength','-G',
+    '--facetool','-ft',
+    '--facetool_strength','-G',
+    '--codeformer_fidelity','-cf',
     '--upscale','-U',
     '-save_orig','--save_original',
     '--skip_normalize','-x',
     '--log_tokenization','-t',
     '--hires_fix',
+    '--inpaint_replace','-r',
+    '--png_compression','-z',
     '!fix','!fetch','!history','!search','!clear',
+    '!models','!switch','!import_model','!edit_model'
+    )
+MODEL_COMMANDS = (
+    '!switch',
+    '!edit_model',
+    )
+WEIGHT_COMMANDS = (
+    '!import_model',
     )
 IMG_PATH_COMMANDS = (
     '--outdir[=\s]',
@@ -61,16 +75,19 @@ IMG_FILE_COMMANDS=(
     '--init_color[=\s]',
     '--embedding_path[=\s]',
     )
-path_regexp = '('+'|'.join(IMG_PATH_COMMANDS+IMG_FILE_COMMANDS) + ')\s*\S*$'
+path_regexp   = '('+'|'.join(IMG_PATH_COMMANDS+IMG_FILE_COMMANDS) + ')\s*\S*$'
+weight_regexp = '('+'|'.join(WEIGHT_COMMANDS) + ')\s*\S*$'
 
 class Completer(object):
-    def __init__(self, options):
+    def __init__(self, options, models=[]):
         self.options     = sorted(options)
+        self.models      = sorted(models)
         self.seeds       = set()
         self.matches     = list()
         self.default_dir = None
         self.linebuffer  = None
         self.auto_history_active = True
+        self.extensions = None
         return
 
     def complete(self, text, state):
@@ -81,7 +98,13 @@ class Completer(object):
         buffer = readline.get_line_buffer()
 
         if state == 0:
-            if re.search(path_regexp,buffer):
+
+            # extensions defined, so go directly into path completion mode
+            if self.extensions is not None:
+                self.matches = self._path_completions(text, state, self.extensions)
+                
+            # looking for an image file
+            elif re.search(path_regexp,buffer):
                 do_shortcut = re.search('^'+'|'.join(IMG_FILE_COMMANDS),buffer)
                 self.matches = self._path_completions(text, state, IMG_EXTENSIONS,shortcut_ok=do_shortcut)
 
@@ -89,6 +112,13 @@ class Completer(object):
             elif re.search('(-S\s*|--seed[=\s])\d*$',buffer): 
                 self.matches= self._seed_completions(text,state)
 
+            # looking for a model
+            elif re.match('^'+'|'.join(MODEL_COMMANDS),buffer):
+                self.matches= self._model_completions(text, state)
+
+            elif re.search(weight_regexp,buffer):
+                self.matches = self._path_completions(text, state, WEIGHT_EXTENSIONS)
+
             # This is the first time for this text, so build a match list.
             elif text:
                 self.matches = [
@@ -105,6 +135,13 @@ class Completer(object):
             response = None
         return response
 
+    def complete_extensions(self, extensions:list):
+        '''
+        If called with a list of extensions, will force completer
+        to do file path completions.
+        '''
+        self.extensions=extensions
+
     def add_history(self,line):
         '''
         Pass thru to readline
@@ -189,6 +226,21 @@ class Completer(object):
         matches.sort()
         return matches
 
+    def _model_completions(self, text, state):
+        m = re.search('(!switch\s+)(\w*)',text)
+        if m:
+            switch  = m.groups()[0]
+            partial = m.groups()[1]
+        else:
+            switch  = ''
+            partial = text
+        matches = list()
+        for s in self.models:
+            if s.startswith(partial):
+                matches.append(switch+s)
+        matches.sort()
+        return matches
+
     def _pre_input_hook(self):
         if self.linebuffer:
             readline.insert_text(self.linebuffer)
@@ -267,9 +319,9 @@ class DummyCompleter(Completer):
     def set_line(self,line):
         print(f'# {line}')
 
-def get_completer(opt:Args)->Completer:
+def get_completer(opt:Args, models=[])->Completer:
     if readline_available:
-        completer = Completer(COMMANDS)
+        completer = Completer(COMMANDS,models)
 
         readline.set_completer(
             completer.complete

ldm/invoke/server.py

@@ -31,12 +31,13 @@ def build_opt(post_data, seed, gfpgan_model_exists):
     setattr(opt, 'embiggen', None)
     setattr(opt, 'embiggen_tiles', None)
 
-    setattr(opt, 'gfpgan_strength', float(post_data['gfpgan_strength']) if gfpgan_model_exists else 0)
+    setattr(opt, 'facetool_strength', float(post_data['facetool_strength']) if gfpgan_model_exists else 0)
     setattr(opt, 'upscale', [int(post_data['upscale_level']), float(post_data['upscale_strength'])] if post_data['upscale_level'] != '' else None)
     setattr(opt, 'progress_images', 'progress_images' in post_data)
     setattr(opt, 'seed', None if int(post_data['seed']) == -1 else int(post_data['seed']))
     setattr(opt, 'threshold', float(post_data['threshold']))
     setattr(opt, 'perlin', float(post_data['perlin']))
+    setattr(opt, 'hires_fix', 'hires_fix' in post_data)
     setattr(opt, 'variation_amount', float(post_data['variation_amount']) if int(post_data['seed']) != -1 else 0)
     setattr(opt, 'with_variations', [])
     setattr(opt, 'embiggen', None)
@@ -196,7 +197,7 @@ class DreamServer(BaseHTTPRequestHandler):
                 ) + '\n',"utf-8"))
 
             # control state of the "postprocessing..." message
-            upscaling_requested = opt.upscale or opt.gfpgan_strength > 0
+            upscaling_requested = opt.upscale or opt.facetool_strength > 0
             nonlocal images_generated # NB: Is this bad python style? It is typical usage in a perl closure.
             nonlocal images_upscaled  # NB: Is this bad python style? It is typical usage in a perl closure.
             if upscaled:

ldm/models/diffusion/ddpm.py

@@ -106,7 +106,7 @@ class DDPM(pl.LightningModule):
         ], 'currently only supporting "eps" and "x0"'
         self.parameterization = parameterization
         print(
-            f'{self.__class__.__name__}: Running in {self.parameterization}-prediction mode'
+            f'   | {self.__class__.__name__}: Running in {self.parameterization}-prediction mode'
         )
         self.cond_stage_model = None
         self.clip_denoised = clip_denoised
@@ -1353,7 +1353,7 @@ class LatentDiffusion(DDPM):
                 num_downs = self.first_stage_model.encoder.num_resolutions - 1
                 rescale_latent = 2 ** (num_downs)
 
-                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # get top left positions of patches as conforming for the bbbox tokenizer, therefore we
                 # need to rescale the tl patch coordinates to be in between (0,1)
                 tl_patch_coordinates = [
                     (

ldm/modules/diffusionmodules/model.py

@@ -49,9 +49,15 @@ class Upsample(nn.Module):
                                         padding=1)
 
     def forward(self, x):
+        cpu_m1_cond = True if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available() and \
+                              x.size()[0] * x.size()[1] * x.size()[2] * x.size()[3] % 2**27 == 0 else False
+        if cpu_m1_cond:
+            x = x.to('cpu')  # send to cpu
         x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
         if self.with_conv:
             x = self.conv(x)
+        if cpu_m1_cond:
+            x = x.to('mps')  # return to mps
         return x
 
 
@@ -117,6 +123,14 @@ class ResnetBlock(nn.Module):
                                                     padding=0)
 
     def forward(self, x, temb):
+        if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
+            x_size = x.size()
+            if (x_size[0] * x_size[1] * x_size[2] * x_size[3]) % 2**29 == 0:
+                self.to('cpu')
+                x = x.to('cpu')
+            else:
+                self.to('mps')
+                x = x.to('mps')
         h = self.norm1(x)
         h = silu(h)
         h = self.conv1(h)
@@ -245,7 +259,7 @@ class AttnBlock(nn.Module):
 
 def make_attn(in_channels, attn_type="vanilla"):
     assert attn_type in ["vanilla", "linear", "none"], f'attn_type {attn_type} unknown'
-    print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
+    print(f"   | Making attention of type '{attn_type}' with {in_channels} in_channels")
     if attn_type == "vanilla":
         return AttnBlock(in_channels)
     elif attn_type == "none":
@@ -521,7 +535,7 @@ class Decoder(nn.Module):
         block_in = ch*ch_mult[self.num_resolutions-1]
         curr_res = resolution // 2**(self.num_resolutions-1)
         self.z_shape = (1,z_channels,curr_res,curr_res)
-        print("Working with z of shape {} = {} dimensions.".format(
+        print("   | Working with z of shape {} = {} dimensions.".format(
             self.z_shape, np.prod(self.z_shape)))
 
         # z to block_in

ldm/modules/diffusionmodules/util.py

@@ -64,7 +64,8 @@ def make_ddim_timesteps(
 ):
     if ddim_discr_method == 'uniform':
         c = num_ddpm_timesteps // num_ddim_timesteps
-        ddim_timesteps = np.asarray(list(range(0, num_ddpm_timesteps, c)))
+        # ddim_timesteps = np.asarray(list(range(0, num_ddpm_timesteps, c)))
+        ddim_timesteps = (np.arange(0, num_ddim_timesteps) * c).astype(int)
     elif ddim_discr_method == 'quad':
         ddim_timesteps = (
             (
@@ -81,8 +82,8 @@ def make_ddim_timesteps(
 
     # assert ddim_timesteps.shape[0] == num_ddim_timesteps
     # add one to get the final alpha values right (the ones from first scale to data during sampling)
-#    steps_out = ddim_timesteps + 1
-    steps_out = ddim_timesteps
+    steps_out = ddim_timesteps + 1
+    # steps_out = ddim_timesteps
 
     if verbose:
         print(f'Selected timesteps for ddim sampler: {steps_out}')

ldm/util.py

@@ -75,7 +75,7 @@ def count_params(model, verbose=False):
     total_params = sum(p.numel() for p in model.parameters())
     if verbose:
         print(
-            f'{model.__class__.__name__} has {total_params * 1.e-6:.2f} M params.'
+            f'   | {model.__class__.__name__} has {total_params * 1.e-6:.2f} M params.'
         )
     return total_params
 

notebooks/Stable_Diffusion_AI_Notebook.ipynb

@@ -6,7 +6,7 @@
         "id": "ycYWcsEKc6w7"
       },
       "source": [
-        "# Stable Diffusion AI Notebook (Release 1.14)\n",
+        "# Stable Diffusion AI Notebook (Release 2.0.0)\n",
         "\n",
         "<img src=\"https://user-images.githubusercontent.com/60411196/186547976-d9de378a-9de8-4201-9c25-c057a9c59bad.jpeg\" alt=\"stable-diffusion-ai\" width=\"170px\"/> <br>\n",
         "#### Instructions:\n",
@@ -58,8 +58,8 @@
         "from os.path import exists\n",
         "\n",
         "!git clone --quiet https://github.com/invoke-ai/InvokeAI.git # Original repo\n",
-        "%cd /content/stable-diffusion/\n",
-        "!git checkout --quiet tags/release-1.14.1"
+        "%cd /content/InvokeAI/\n",
+        "!git checkout --quiet tags/v2.0.0"
       ]
     },
     {
@@ -79,6 +79,7 @@
         "!pip install colab-xterm\n",
         "!pip install -r requirements-lin-win-colab-CUDA.txt\n",
         "!pip install clean-fid torchtext\n",
+        "!pip install transformers\n",
         "gc.collect()"
       ]
     },
@@ -106,7 +107,7 @@
       "source": [
         "#@title 5. Load small ML models required\n",
         "import gc\n",
-        "%cd /content/stable-diffusion/\n",
+        "%cd /content/InvokeAI/\n",
         "!python scripts/preload_models.py\n",
         "gc.collect()"
       ]
@@ -171,18 +172,18 @@
         "import os \n",
         "\n",
         "# Folder creation if it doesn't exist\n",
-        "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\"):\n",
+        "if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1\"):\n",
         "     print(\"❗ Dir stable-diffusion-v1 already exists\")\n",
         "else:\n",
-        "    %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n",
+        "    %mkdir /content/InvokeAI/models/ldm/stable-diffusion-v1\n",
         "    print(\"✅ Dir stable-diffusion-v1 created\")\n",
         "\n",
         "# Symbolic link if it doesn't exist\n",
-        "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
+        "if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
         "    print(\"❗ Symlink already created\")\n",
         "else: \n",
         "    src = model_path\n",
-        "    dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n",
+        "    dst = '/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt'\n",
         "    os.symlink(src, dst) \n",
         "    print(\"✅ Symbolic link created successfully\")"
       ]
@@ -207,7 +208,7 @@
       "source": [
         "#@title 9. Run Terminal and Execute Dream bot\n",
         "#@markdown <font color=\"blue\">Steps:</font> <br>\n",
-        "#@markdown 1. Execute command `python scripts/dream.py` to run dream bot.<br>\n",
+        "#@markdown 1. Execute command `python scripts/invoke.py` to run InvokeAI.<br>\n",
         "#@markdown 2. After initialized you'll see `Dream>` line.<br>\n",
         "#@markdown 3. Example text: `Astronaut floating in a distant galaxy` <br>\n",
         "#@markdown 4. To quit Dream bot use: `q` command.<br>\n",
@@ -233,7 +234,7 @@
         "%matplotlib inline\n",
         "\n",
         "images = []\n",
-        "for img_path in sorted(glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'), reverse=True):\n",
+        "for img_path in sorted(glob.glob('/content/InvokeAI/outputs/img-samples/*.png'), reverse=True):\n",
         "    images.append(mpimg.imread(img_path))\n",
         "\n",
         "images = images[:15] \n",

requirements-linux-arm64.txt

@@ -12,12 +12,12 @@ pillow==9.2.0
 pudb==2019.2
 torch==1.12.1
 torchvision==0.13.0
-pytorch-lightning==1.4.2
+pytorch-lightning==1.7.7
 streamlit==1.12.0
 test-tube>=0.7.5
 torch-fidelity==0.3.0
 torchmetrics==0.6.0
-transformers==4.19.2
+transformers==4.21.3
 -e git+https://github.com/openai/CLIP.git@main#egg=clip
 -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
 -e git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion

requirements-mac-MPS-CPU.txt

@@ -1,6 +1,6 @@
 -r requirements.txt
 
-protobuf==3.19.4
+protobuf==3.19.6
 torch
 torchvision
 -e .

scripts/invoke.py

@@ -9,6 +9,7 @@ import copy
 import warnings
 import time
 import traceback
+import yaml
 sys.path.append('.')    # corrects a weird problem on Macs
 from ldm.invoke.readline import get_completer
 from ldm.invoke.args import Args, metadata_dumps, metadata_from_png, dream_cmd_from_png
@@ -16,8 +17,6 @@ from ldm.invoke.pngwriter import PngWriter, retrieve_metadata, write_metadata
 from ldm.invoke.image_util import make_grid
 from ldm.invoke.log import write_log
 from omegaconf import OmegaConf
-from backend.invoke_ai_web_server import InvokeAIWebServer
-
 
 def main():
     """Initialize command-line parsers and the diffusion model"""
@@ -33,7 +32,7 @@ def main():
         print('--weights argument has been deprecated. Please edit ./configs/models.yaml, and select the weights using --model instead.')
         sys.exit(-1)
 
-    print('* Initializing, be patient...\n')
+    print('* Initializing, be patient...')
     from ldm.generate import Generate
 
     # these two lines prevent a horrible warning message from appearing
@@ -42,45 +41,7 @@ def main():
     transformers.logging.set_verbosity_error()
 
     # Loading Face Restoration and ESRGAN Modules
-    try:
-        gfpgan, codeformer, esrgan = None, None, None
-        if opt.restore or opt.esrgan:
-            from ldm.invoke.restoration import Restoration
-            restoration = Restoration()
-            if opt.restore:
-                gfpgan, codeformer = restoration.load_face_restore_models(opt.gfpgan_dir, opt.gfpgan_model_path)
-            else:
-                print('>> Face restoration disabled')
-            if opt.esrgan:
-                esrgan = restoration.load_esrgan(opt.esrgan_bg_tile)
-            else:
-                print('>> Upscaling disabled')
-        else:
-            print('>> Face restoration and upscaling disabled')
-    except (ModuleNotFoundError, ImportError):
-        print(traceback.format_exc(), file=sys.stderr)
-        print('>> You may need to install the ESRGAN and/or GFPGAN modules')
-
-    # creating a simple text2image object with a handful of
-    # defaults passed on the command line.
-    # additional parameters will be added (or overriden) during
-    # the user input loop
-    try:
-        gen = Generate(
-            conf           = opt.conf,
-            model          = opt.model,
-            sampler_name   = opt.sampler_name,
-            embedding_path = opt.embedding_path,
-            full_precision = opt.full_precision,
-            precision      = opt.precision,
-            gfpgan=gfpgan,
-            codeformer=codeformer,
-            esrgan=esrgan,
-            free_gpu_mem=opt.free_gpu_mem,
-            )
-    except (FileNotFoundError, IOError, KeyError) as e:
-        print(f'{e}. Aborting.')
-        sys.exit(-1)
+    gfpgan,codeformer,esrgan = load_face_restoration(opt)
 
     # make sure the output directory exists
     if not os.path.exists(opt.outdir):
@@ -100,6 +61,24 @@ def main():
             print(f'{e}. Aborting.')
             sys.exit(-1)
 
+    # creating a Generate object:
+    try:
+        gen = Generate(
+            conf           = opt.conf,
+            model          = opt.model,
+            sampler_name   = opt.sampler_name,
+            embedding_path = opt.embedding_path,
+            full_precision = opt.full_precision,
+            precision      = opt.precision,
+            gfpgan=gfpgan,
+            codeformer=codeformer,
+            esrgan=esrgan,
+            free_gpu_mem=opt.free_gpu_mem,
+            )
+    except (FileNotFoundError, IOError, KeyError) as e:
+        print(f'{e}. Aborting.')
+        sys.exit(-1)
+
     if opt.seamless:
         print(">> changed to seamless tiling mode")
 
@@ -116,7 +95,10 @@ def main():
             "\n* Initialization done! Awaiting your command (-h for help, 'q' to quit)"
         )
 
-    main_loop(gen, opt, infile)
+    try:
+        main_loop(gen, opt, infile)
+    except KeyboardInterrupt:
+        print("\ngoodbye!")
 
 # TODO: main_loop() has gotten busy. Needs to be refactored.
 def main_loop(gen, opt, infile):
@@ -124,12 +106,13 @@ def main_loop(gen, opt, infile):
     done = False
     path_filter = re.compile(r'[<>:"/\\|?*]')
     last_results = list()
-    model_config = OmegaConf.load(opt.conf)[opt.model]
+    model_config = OmegaConf.load(opt.conf)
 
     # The readline completer reads history from the .dream_history file located in the
     # output directory specified at the time of script launch. We do not currently support
     # changing the history file midstream when the output directory is changed.
-    completer   = get_completer(opt)
+    completer   = get_completer(opt, models=list(model_config.keys()))
+    completer.set_default_dir(opt.outdir)
     output_cntr = completer.get_current_history_length()+1
 
     # os.pathconf is not available on Windows
@@ -141,11 +124,9 @@ def main_loop(gen, opt, infile):
         name_max = 255
 
     while not done:
-        operation = 'generate'   # default operation, alternative is 'postprocess'
 
-        if completer:
-            completer.set_default_dir(opt.outdir)
-            
+        operation = 'generate'
+
         try:
             command = get_next_command(infile)
         except EOFError:
@@ -164,41 +145,10 @@ def main_loop(gen, opt, infile):
             break
 
         if command.startswith('!'):
-            subcommand = command[1:]
+            command, operation = do_command(command, gen, opt, completer)
 
-            if subcommand.startswith('dream'):   # in case a stored prompt still contains the !dream command
-                command = command.replace('!dream ','',1)
-
-            elif subcommand.startswith('fix'):
-                command = command.replace('!fix ','',1)
-                operation = 'postprocess'
-
-            elif subcommand.startswith('fetch'):
-                file_path = command.replace('!fetch ','',1)
-                retrieve_dream_command(opt,file_path,completer)
-                continue
-
-            elif subcommand.startswith('history'):
-                completer.show_history()
-                continue
-
-            elif subcommand.startswith('search'):
-                search_str = command.replace('!search ','',1)
-                completer.show_history(search_str)
-                continue
-
-            elif subcommand.startswith('clear'):
-                completer.clear_history()
-                continue
-
-            elif re.match('^(\d+)',subcommand):
-                command_no = re.match('^(\d+)',subcommand).groups()[0]
-                command    = completer.get_line(int(command_no))
-                completer.set_line(command)
-                continue
-                
-            else:  # not a recognized subcommand, so give the --help text
-                command = '-h'
+        if operation is None:
+            continue
 
         if opt.parse_cmd(command) is None:
             continue
@@ -218,9 +168,9 @@ def main_loop(gen, opt, infile):
 
         # width and height are set by model if not specified
         if not opt.width:
-            opt.width = model_config.width
+            opt.width = gen.width
         if not opt.height:
-            opt.height = model_config.height
+            opt.height = gen.height
 
         # retrieve previous value of init image if requested
         if opt.init_img is not None and re.match('^-\\d+$', opt.init_img):
@@ -323,6 +273,7 @@ def main_loop(gen, opt, infile):
                             model_hash = gen.model_hash,
                         ),
                         name      = filename,
+                        compress_level = opt.png_compression,
                     )
 
                     # update rfc metadata
@@ -394,13 +345,162 @@ def main_loop(gen, opt, infile):
 
     print('goodbye!')
 
+def do_command(command:str, gen, opt:Args, completer) -> tuple:
+    operation = 'generate'   # default operation, alternative is 'postprocess'
+
+    if command.startswith('!dream'):   # in case a stored prompt still contains the !dream command
+        command = command.replace('!dream ','',1)
+
+    elif command.startswith('!fix'):
+        command = command.replace('!fix ','',1)
+        operation = 'postprocess'
+
+    elif command.startswith('!switch'):
+        model_name = command.replace('!switch ','',1)
+        gen.set_model(model_name)
+        completer.add_history(command)
+        operation = None
+        
+    elif command.startswith('!models'):
+        gen.model_cache.print_models()
+        operation = None
+
+    elif command.startswith('!import'):
+        path = shlex.split(command)
+        if len(path) < 2:
+            print('** please provide a path to a .ckpt or .vae model file')
+        elif not os.path.exists(path[1]):
+            print(f'** {path[1]}: file not found')
+        else:
+            add_weights_to_config(path[1], gen, opt, completer)
+        completer.add_history(command)
+        operation = None
+
+    elif command.startswith('!edit'):
+        path = shlex.split(command)
+        if len(path) < 2:
+            print('** please provide the name of a model')
+        else:
+            edit_config(path[1], gen, opt, completer)
+        completer.add_history(command)
+        operation = None
+
+    elif command.startswith('!fetch'):
+        file_path = command.replace('!fetch ','',1)
+        retrieve_dream_command(opt,file_path,completer)
+        operation = None
+
+    elif command.startswith('!history'):
+        completer.show_history()
+        operation = None
+
+    elif command.startswith('!search'):
+        search_str = command.replace('!search ','',1)
+        completer.show_history(search_str)
+        operation = None
+
+    elif command.startswith('!clear'):
+        completer.clear_history()
+        operation = None
+
+    elif re.match('^!(\d+)',command):
+        command_no = re.match('^!(\d+)',command).groups()[0]
+        command    = completer.get_line(int(command_no))
+        completer.set_line(command)
+        operation = None
+
+    else:  # not a recognized command, so give the --help text
+        command = '-h'
+    return command, operation
+
+def add_weights_to_config(model_path:str, gen, opt, completer):
+    print(f'>> Model import in process. Please enter the values needed to configure this model:')
+    print()
+
+    new_config = {}
+    new_config['weights'] = model_path
+
+    done = False
+    while not done:
+        model_name = input('Short name for this model: ')
+        if not re.match('^[\w._-]+$',model_name):
+            print('** model name must contain only words, digits and the characters [._-] **')
+        else:
+            done = True
+    new_config['description'] = input('Description of this model: ')
+
+    completer.complete_extensions(('.yaml','.yml'))
+    completer.linebuffer = 'configs/stable-diffusion/v1-inference.yaml'
+    
+    done = False
+    while not done:
+        new_config['config'] = input('Configuration file for this model: ')
+        done = os.path.exists(new_config['config'])
+
+    completer.complete_extensions(None)
+
+    for field in ('width','height'):
+        done = False
+        while not done:
+            try:
+                completer.linebuffer = '512'
+                value = int(input(f'Default image {field}: '))
+                assert value >= 64 and value <= 2048
+                new_config[field] = value
+                done = True
+            except:
+                print('** Please enter a valid integer between 64 and 2048')
+
+    if write_config_file(opt.conf, gen, model_name, new_config):
+        gen.set_model(model_name)
+
+def edit_config(model_name:str, gen, opt, completer):
+    config = gen.model_cache.config
+    
+    if model_name not in config:
+        print(f'** Unknown model {model_name}')
+        return
+    
+    print(f'\n>> Editing model {model_name} from configuration file {opt.conf}')
+
+    conf = config[model_name]
+    new_config = {}
+    completer.complete_extensions(('.yaml','.yml','.ckpt','.vae'))
+    for field in ('description', 'weights', 'config', 'width','height'):
+        completer.linebuffer = str(conf[field]) if field in conf else ''
+        new_value = input(f'{field}: ')
+        new_config[field] = int(new_value) if field in ('width','height') else new_value
+    completer.complete_extensions(None)
+
+    if write_config_file(opt.conf, gen, model_name, new_config, clobber=True):
+        gen.set_model(model_name)
+    
+def write_config_file(conf_path, gen, model_name, new_config, clobber=False):
+    op = 'modify' if clobber else 'import'
+    print('\n>> New configuration:')
+    print(yaml.dump({model_name:new_config}))
+    if input(f'OK to {op} [n]? ') not in ('y','Y'):
+        return False
+
+    try:
+        yaml_str = gen.model_cache.add_model(model_name, new_config, clobber)
+    except AssertionError as e:
+        print(f'** configuration failed: {str(e)}')
+        return False
+    
+    tmpfile = os.path.join(os.path.dirname(conf_path),'new_config.tmp')
+    with open(tmpfile, 'w') as outfile:
+        outfile.write(yaml_str)
+    os.rename(tmpfile,conf_path)
+    return True
+
 def do_postprocess (gen, opt, callback):
     file_path = opt.prompt     # treat the prompt as the file pathname
     if os.path.dirname(file_path) == '': #basename given
         file_path = os.path.join(opt.outdir,file_path)
 
     tool=None
-    if opt.gfpgan_strength > 0:
+    if opt.facetool_strength > 0:
         tool = opt.facetool
     elif opt.embiggen:
         tool = 'embiggen'
@@ -416,7 +516,7 @@ def do_postprocess (gen, opt, callback):
         gen.apply_postprocessor(
             image_path      = file_path,
             tool            = tool,
-            gfpgan_strength = opt.gfpgan_strength,
+            facetool_strength = opt.facetool_strength,
             codeformer_fidelity = opt.codeformer_fidelity,
             save_original       = opt.save_original,
             upscale             = opt.upscale,
@@ -511,6 +611,7 @@ def get_next_command(infile=None) -> str:  # command string
 
 def invoke_ai_web_server_loop(gen, gfpgan, codeformer, esrgan):
     print('\n* --web was specified, starting web server...')
+    from backend.invoke_ai_web_server import InvokeAIWebServer
     # Change working directory to the stable-diffusion directory
     os.chdir(
         os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
@@ -549,6 +650,27 @@ def split_variations(variations_string) -> list:
     else:
         return parts
 
+def load_face_restoration(opt):
+    try:
+        gfpgan, codeformer, esrgan = None, None, None
+        if opt.restore or opt.esrgan:
+            from ldm.invoke.restoration import Restoration
+            restoration = Restoration()
+            if opt.restore:
+                gfpgan, codeformer = restoration.load_face_restore_models(opt.gfpgan_dir, opt.gfpgan_model_path)
+            else:
+                print('>> Face restoration disabled')
+            if opt.esrgan:
+                esrgan = restoration.load_esrgan(opt.esrgan_bg_tile)
+            else:
+                print('>> Upscaling disabled')
+        else:
+            print('>> Face restoration and upscaling disabled')
+    except (ModuleNotFoundError, ImportError):
+        print(traceback.format_exc(), file=sys.stderr)
+        print('>> You may need to install the ESRGAN and/or GFPGAN modules')
+    return gfpgan,codeformer,esrgan
+    
 def make_step_callback(gen, opt, prefix):
     destination = os.path.join(opt.outdir,'intermediates',prefix)
     os.makedirs(destination,exist_ok=True)

server/models.py

@@ -35,13 +35,14 @@ class DreamBase():
   perlin: float = 0.0
   sampler_name: string = 'klms'
   seamless: bool = False
+  hires_fix: bool = False
   model: str = None # The model to use (currently unused)
   embeddings = None # The embeddings to use (currently unused)
   progress_images: bool = False
 
   # GFPGAN
   enable_gfpgan: bool
-  gfpgan_strength: float = 0
+  facetool_strength: float = 0
 
   # Upscale
   enable_upscale: bool
@@ -91,12 +92,13 @@ class DreamBase():
       # model: str = None # The model to use (currently unused)
       # embeddings = None # The embeddings to use (currently unused)
       self.seamless = 'seamless' in j
+      self.hires_fix = 'hires_fix' in j
       self.progress_images = 'progress_images' in j
 
     # GFPGAN
     self.enable_gfpgan = 'enable_gfpgan' in j and bool(j.get('enable_gfpgan'))
     if self.enable_gfpgan:
-      self.gfpgan_strength = float(j.get('gfpgan_strength'))
+      self.facetool_strength = float(j.get('facetool_strength'))
 
     # Upscale
     self.enable_upscale = 'enable_upscale' in j and bool(j.get('enable_upscale'))

server/services.py

@@ -334,11 +334,11 @@ class GeneratorService:
       # TODO: Support no generation (just upscaling/gfpgan)
 
       upscale = None if not jobRequest.enable_upscale else jobRequest.upscale
-      gfpgan_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.gfpgan_strength
+      facetool_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.facetool_strength
 
       if not jobRequest.enable_generate:
         # If not generating, check if we're upscaling or running gfpgan
-        if not upscale and not gfpgan_strength:
+        if not upscale and not facetool_strength:
           # Invalid settings (TODO: Add message to help user)
           raise CanceledException()
 
@@ -347,7 +347,7 @@ class GeneratorService:
         self.__model.upscale_and_reconstruct(
           image_list = [[image,0]],
           upscale = upscale,
-          strength = gfpgan_strength,
+          strength = facetool_strength,
           save_original = False,
           image_callback = lambda image, seed, upscaled=False: self.__on_image_result(jobRequest, image, seed, upscaled))
 
@@ -371,10 +371,11 @@ class GeneratorService:
           steps            = jobRequest.steps,
           variation_amount = jobRequest.variation_amount,
           with_variations  = jobRequest.with_variations,
-          gfpgan_strength  = gfpgan_strength,
+          facetool_strength = facetool_strength,
           upscale          = upscale,
           sampler_name     = jobRequest.sampler_name,
           seamless         = jobRequest.seamless,
+          hires_fix        = jobRequest.hires_fix,
           embiggen         = jobRequest.embiggen,
           embiggen_tiles   = jobRequest.embiggen_tiles,
           step_callback    = lambda sample, step: self.__on_progress(jobRequest, sample, step),

setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='invoke-ai',
-    version='2.0.0',
+    version='2.0.2',
     description='',
     packages=find_packages(),
     install_requires=[

static/dream_web/index.html

@@ -144,8 +144,8 @@
             <input type="checkbox" name="enable_gfpgan" id="enable_gfpgan">
             <label for="enable_gfpgan">Enable gfpgan</label>
           </legend>
-          <label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength:</label>
-          <input value="0.8" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.05">
+          <label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength:</label>
+          <input value="0.8" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.05">
         </fieldset>
         <fieldset id="upscale">
           <legend>

static/legacy_web/index.html

@@ -100,8 +100,8 @@
 	</fieldset>
         <fieldset id="gfpgan">
 	  <div class="section-header">Post-processing options</div>
-          <label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength (0 to disable):</label>
-          <input value="0.0" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.1">
+          <label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength (0 to disable):</label>
+          <input value="0.0" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.1">
           <label title="Upscaling to perform using ESRGAN." for="upscale_level">Upscaling Level</label>
           <select id="upscale_level" name="upscale_level" value="">
             <option value="" selected>None</option>

tests/pr_prompt.txt

@@ -0,0 +1 @@
+banana sushi -Ak_lms -S42 -s10