final documentation fixes prior to release

this will help the readability of issues a lot 🤓

.dockerignore

@@ -0,0 +1,3 @@
+*
+!environment*.yml
+!docker-build

.github/CODEOWNERS

@@ -0,0 +1,4 @@
+ldm/invoke/pngwriter.py @CapableWeb
+ldm/invoke/server_legacy.py @CapableWeb
+scripts/legacy_api.py @CapableWeb
+tests/legacy_tests.sh @CapableWeb

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -0,0 +1,102 @@
+name: 🐞 Bug Report
+
+description: File a bug report
+
+title: '[bug]: '
+
+labels: ['bug']
+
+# assignees:
+#   - moderator_bot
+#   - lstein
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this Bug Report!
+
+  - type: checkboxes
+    attributes:
+      label: Is there an existing issue for this?
+      description: |
+        Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
+        irst to see if an issue already exists for the bug you encountered.
+      options:
+        - label: I have searched the existing issues
+          required: true
+
+  - type: markdown
+    attributes:
+      value: __Describe your environment__
+
+  - type: dropdown
+    id: os_dropdown
+    attributes:
+      label: OS
+      description: Which operating System did you use when the bug occured
+      multiple: false
+      options:
+        - 'Linux'
+        - 'Windows'
+        - 'macOS'
+    validations:
+      required: true
+
+  - type: dropdown
+    id: gpu_dropdown
+    attributes:
+      label: GPU
+      description: Which kind of Graphic-Adapter is your System using
+      multiple: false
+      options:
+        - 'cuda'
+        - 'amd'
+        - 'mps'
+        - 'cpu'
+    validations:
+      required: true
+
+  - type: input
+    id: vram
+    attributes:
+      label: VRAM
+      description: Size of the VRAM if known
+      placeholder: 8GB
+    validations:
+      required: false
+
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: |
+        Briefly describe what happened, what you expected to happen and how to reproduce this bug.
+      placeholder: When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Screenshots
+      description: If applicable, add screenshots to help explain your problem
+      placeholder: this is what the result looked like <screenshot>
+    validations:
+      required: false
+
+  - type: textarea
+    attributes:
+      label: Additional context
+      description: Add any other context about the problem here
+      placeholder: Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
+    validations:
+      required: false
+
+  - type: input
+    id: contact
+    attributes:
+      label: Contact Details
+      description: __OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
+      placeholder: ex. email@example.com, discordname, twitter, ...
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/FEATURE_REQUEST.yml

@@ -0,0 +1,56 @@
+name: Feature Request
+description: Commit a idea or Request a new feature
+title: '[enhancement]: '
+labels: ['enhancement']
+# assignees:
+#   - lstein
+#   - tildebyte
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this Feature request!
+
+  - type: checkboxes
+    attributes:
+      label: Is there an existing issue for this?
+      description: |
+        Please make use of the [search function](https://github.com/invoke-ai/InvokeAI/labels/enhancement)
+        to see if a simmilar issue already exists for the feature you want to request
+      options:
+        - label: I have searched the existing issues
+          required: true
+
+  - type: input
+    id: contact
+    attributes:
+      label: Contact Details
+      description: __OPTIONAL__ How could we get in touch with you if we need more info (besides this issue)?
+      placeholder: ex. email@example.com, discordname, twitter, ...
+    validations:
+      required: false
+
+  - type: textarea
+    id: whatisexpected
+    attributes:
+      label: What should this feature add?
+      description: Please try to explain the functionality this feature should add
+      placeholder: |
+        Instead of one huge textfield, it would be nice to have forms for bug-reports, feature-requests, ...
+        Great benefits with automatic labeling, assigning and other functionalitys not available in that form
+        via old-fashioned markdown-templates. I would also love to see the use of a moderator bot 🤖 like
+        https://github.com/marketplace/actions/issue-moderator-with-commands to auto close old issues and other things
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Alternatives
+      description: Describe alternatives you've considered
+      placeholder: A clear and concise description of any alternative solutions or features you've considered.
+
+  - type: textarea
+    attributes:
+      label: Aditional Content
+      description: Add any other context or screenshots about the feature request here.
+      placeholder: This is a Mockup of the design how I imagine it <screenshot>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,36 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Describe your environment**
-- GPU: [cuda/amd/mps/cpu]
-- VRAM: [if known]
-- CPU arch: [x86/arm]
-- OS: [Linux/Windows/macOS]
-- Python: [Anaconda/miniconda/miniforge/pyenv/other (explain)]
-- Branch: [if `git status` says anything other than "On branch main" paste it here]
-- Commit: [run `git show` and paste the line that starts with "Merge" here]
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,14 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Project-Documentation
+    url: https://invoke-ai.github.io/InvokeAI/
+    about: Should be your first place to go when looking for manuals/FAQs regarding our InvokeAI Toolkit
+  - name: Discord
+    url: https://discord.gg/ZmtBAhwWhy
+    about: Our Discord Community could maybe help you out via live-chat
+  - name: GitHub Community Support
+    url: https://github.com/orgs/community/discussions
+    about: Please ask and answer questions regarding the GitHub Platform here.
+  - name: GitHub Security Bug Bounty
+    url: https://bounty.github.com/
+    about: Please report security vulnerabilities of the GitHub Platform here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,20 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/workflows/build-container.yml

@@ -0,0 +1,42 @@
+# Building the Image without pushing to confirm it is still buildable
+# confirum functionality would unfortunately need way more resources
+name: build container image
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - name: prepare docker-tag
+        env:
+          repository: ${{ github.repository }}
+        run: echo "dockertag=${repository,,}" >> $GITHUB_ENV
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Cache Docker layers
+        uses: actions/cache@v2
+        with:
+          path: /tmp/.buildx-cache
+          key: buildx-${{ hashFiles('docker-build/Dockerfile') }}
+      - name: Build container
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          file: docker-build/Dockerfile
+          platforms: linux/amd64
+          push: false
+          tags: ${{ env.dockertag }}:latest
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache

.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 +46,35 @@ 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
-        uses: actions/cache@v3
-        env:
-          cache-name: 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 \
+              -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+              -o models/ldm/stable-diffusion-v1/model.ckpt \
+              -L https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+
+      - name: Activate Conda Env
+        uses: conda-incubator/setup-miniconda@v2
         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 }}
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+
       - name: Use Cached Huggingface and Torch models
-        id: cache-huggingface-torch
+        id: cache-hugginface-torch
         uses: actions/cache@v3
         env:
-          cache-name: cache-huggingface-torch
+          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-dream-conda.yml

@@ -1,97 +0,0 @@
-name: Test Dream with Conda
-on:
-  push:
-    branches:
-      - 'main'
-      - 'development'
-jobs:
-  os_matrix:
-    strategy:
-      matrix:
-        os: [ ubuntu-latest, macos-12 ]
-    name: Test dream.py on ${{ matrix.os }} with conda
-    runs-on: ${{ matrix.os }}
-    steps:
-      - run: |
-          echo The PR was merged
-      - name: Set platform variables
-        id: vars
-        run: |
-          # Note, can't "activate" via github action; specifying the env's python has the same effect
-          if [ "$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: Use Cached Stable Diffusion v1.4 Model
-        id: cache-sd-v1-4
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-sd-v1-4
-        with:
-          path: models/ldm/stable-diffusion-v1/model.ckpt
-          key: ${{ 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
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-conda-env-ldm
-        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 }}
-      - 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-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 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/dream.py --from_file tests/preflight_prompts.txt
-          elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
-            time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/dev_prompts.txt
-          fi
-          mkdir -p outputs/img-samples
-      - name: Archive results
-        uses: actions/upload-artifact@v3
-        with:
-          name: results
-          path: outputs/img-samples

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

@@ -0,0 +1,113 @@
+name: Test invoke.py
+on:
+  push:
+    branches:
+      - 'main'
+      - 'development'
+      - 'fix-gh-actions-fork'
+  pull_request:
+    branches:
+      - 'main'
+      - 'development'
+
+jobs:
+  matrix:
+    strategy:
+      fail-fast: false
+      matrix:
+        stable-diffusion-model:
+          # - 'https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt'
+          - 'https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt'
+        os:
+          - ubuntu-latest
+          - macOS-12
+        include:
+          - os: ubuntu-latest
+            environment-file: environment.yml
+            default-shell: bash -l {0}
+          - os: macOS-12
+            environment-file: environment-mac.yml
+            default-shell: bash -l {0}
+          # - stable-diffusion-model: https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+          #   stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+          #   stable-diffusion-model-switch: stable-diffusion-1.4
+          - stable-diffusion-model: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-dl-path: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+            stable-diffusion-model-switch: stable-diffusion-1.5
+    name: ${{ matrix.os }} with ${{ matrix.stable-diffusion-model-switch }}
+    runs-on: ${{ matrix.os }}
+    env:
+      CONDA_ENV_NAME: invokeai
+    defaults:
+      run:
+        shell: ${{ matrix.default-shell }}
+    steps:
+      - name: Checkout sources
+        id: checkout-sources
+        uses: actions/checkout@v3
+
+      - name: create models.yaml from example
+        run: cp configs/models.yaml.example configs/models.yaml
+
+      - name: Use cached conda packages
+        id: use-cached-conda-packages
+        uses: actions/cache@v3
+        with:
+          path: ~/conda_pkgs_dir
+          key: conda-pkgs-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles(matrix.environment-file) }}
+
+      - name: Activate Conda Env
+        id: activate-conda-env
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+          activate-environment: ${{ env.CONDA_ENV_NAME }}
+          environment-file: ${{ matrix.environment-file }}
+          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/validate_pr_prompt.txt" >> $GITHUB_ENV
+
+      - name: Download ${{ matrix.stable-diffusion-model-switch }}
+        id: download-stable-diffusion-model
+        run: |
+          [[ -d models/ldm/stable-diffusion-v1 ]] \
+            || mkdir -p models/ldm/stable-diffusion-v1
+          curl \
+            -H "Authorization: Bearer ${{ secrets.HUGGINGFACE_TOKEN }}" \
+            -o ${{ matrix.stable-diffusion-model-dl-path }} \
+            -L ${{ matrix.stable-diffusion-model }}
+
+      - name: run preload_models.py
+        id: run-preload-models
+        run: |
+          python scripts/preload_models.py \
+            --no-interactive
+
+      - name: Run the tests
+        id: run-tests
+        run: |
+          time python scripts/invoke.py \
+            --model ${{ matrix.stable-diffusion-model-switch }} \
+            --from_file ${{ env.TEST_PROMPTS }}
+
+      - name: export conda env
+        id: export-conda-env
+        run: |
+          mkdir -p outputs/img-samples
+          conda env export --name ${{ env.CONDA_ENV_NAME }} > outputs/img-samples/environment-${{ runner.os }}-${{ runner.arch }}.yml
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results_${{ matrix.os }}_${{ matrix.stable-diffusion-model-switch }}
+          path: outputs/img-samples

.gitignore

@@ -1,7 +1,10 @@
 # ignore default image save location and model symbolic link
 outputs/
 models/ldm/stable-diffusion-v1/model.ckpt
-ldm/dream/restoration/codeformer/weights
+ldm/invoke/restoration/codeformer/weights
+# ignore user models config
+configs/models.user.yaml
+config/models.user.yml
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -180,7 +183,7 @@ src
 **/__pycache__/
 outputs
 
-# Logs and associated folders 
+# Logs and associated folders
 # created from generated embeddings.
 logs
 testtube
@@ -195,7 +198,13 @@ checkpoints
 .scratch/
 .vscode/
 gfpgan/
-models/ldm/stable-diffusion-v1/model.sha256
+models/ldm/stable-diffusion-v1/*.sha256
 
 # GFPGAN model files
 gfpgan/
+
+# config file (will be created by installer)
+configs/models.yaml
+
+# weights (will be created by installer)
+models/ldm/stable-diffusion-v1/*.ckpt

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

@@ -2,14 +2,7 @@
 
 # InvokeAI: A Stable Diffusion Toolkit
 
-_Note: This fork is rapidly evolving. Please use the
-[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to
-report bugs and make feature requests. Be sure to use the provided
-templates. They will help aid diagnose issues faster._
-
-_This repository was formally known as lstein/stable-diffusion_
-
-# **Table of Contents**
+_Formerly known as lstein/stable-diffusion_
 
 ![project logo](docs/assets/logo.png)
 
@@ -24,7 +17,7 @@ _This repository was formally known as lstein/stable-diffusion_
 [CI checks on dev badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
 [CI checks on dev link]: https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
 [CI checks on main badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
-[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions/workflows/test-dream-conda.yml
+[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
 [discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
 [discord link]: https://discord.gg/ZmtBAhwWhy
 [github forks badge]: https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
@@ -41,10 +34,18 @@ _This repository was formally known as lstein/stable-diffusion_
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 </div>
 
-This is a fork of [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion), the open
-source text-to-image generator. It provides a streamlined process with various new features and
-options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on
-GPU cards with as little as 4 GB or RAM.
+This is a fork of
+[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion),
+the open source text-to-image generator. It provides a streamlined
+process with various new features and options to aid the image
+generation process. It runs on Windows, Mac and Linux machines, with
+GPU cards with as little as 4 GB of RAM. It provides both a polished
+Web interface (see below), and an easy-to-use command-line interface.
+
+**Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
+
+<div align="center"><img src="docs/assets/invoke-web-server-1.png" width=640></div>
+
 
 _Note: This fork is rapidly evolving. Please use the
 [Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
@@ -67,11 +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
 
@@ -88,84 +89,100 @@ You wil need one of the following:
 
 #### Disk
 
-- At least 6 GB of free disk space for the machine learning model, Python, and all its dependencies.
+- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
-#### Note
+**Note**
+
+If you have a Nvidia 10xx series card (e.g. the 1080ti), please
+run the dream script in full-precision mode as shown below.
+
+Similarly, specify full-precision mode on Apple M1 hardware.
 
 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 `dream.py` with the `--precision=float32` flag:
+you can try starting `invoke.py` with the `--precision=float32` flag:
 
 ```bash
-(ldm) ~/stable-diffusion$ python scripts/dream.py --precision=float32
+(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
 ```
 
 ### Features
 
 #### Major Features
 
-- [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)
-- [Web Server](docs/features/WEB.md)
-- [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
 
-- vNEXT (TODO 2022)
+### v2.1.0 major changes <small>(2 November 2022)</small> 
 
-  - Deprecated `--full_precision` / `-F`. Simply omit it and `dream.py` will auto
+    - [Inpainting](https://invoke-ai.github.io/InvokeAI/features/INPAINTING/) support in the WebGUI
+    - Greatly improved navigation and user experience in the [WebGUI](https://invoke-ai.github.io/InvokeAI/features/WEB/)
+    - The prompt syntax has been enhanced with [prompt weighting, cross-attention and prompt merging](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/).
+    - You can now load [multiple models and switch among them quickly](https://docs.google.com/presentation/d/1WywGA1rny7bpFh7CLSdTr4nNpVKdlUeT0Bj0jCsILyU/edit?usp=sharing) without leaving the CLI.
+    - The installation process (via `scripts/preload_models.py`) now lets you select among several popular [Stable Diffusion models](https://invoke-ai.github.io/InvokeAI/installation/INSTALLING_MODELS/) and downloads and installs them on your behalf. Among other models, this script will install the current Stable Diffusion 1.5 model as well as a StabilityAI variable autoencoder (VAE) which improves face generation.
+    -  Tired of struggling with photoeditors to get the masked region of for inpainting just right? Let the AI make the mask for you using [text masking](https://docs.google.com/presentation/d/1pWoY510hCVjz0M6X9CBbTznZgW2W5BYNKrmZm7B45q8/edit#slide=id.p). This feature allows you to specify the part of the image to paint over using just English-language phrases.
+    -  Tired of seeing the head of your subjects cropped off? Uncrop them in the CLI with the [outcrop feature](https://invoke-ai.github.io/InvokeAI/features/OUTPAINTING/#outcrop).
+    - Tired of seeing your subject's bodies duplicated or mangled when generating larger-dimension images? Check out the `--hires` option in the CLI, or select the corresponding toggle in the WebGUI.
+    - We now support textual inversion and fine-tune .bin styles and subjects from the Hugging Face archive of [SD Concepts](https://huggingface.co/sd-concepts-library). Load the .bin file using the `--embedding_path` option. (The next version will support merging and loading of multiple simultaneous models).
+    <a href="https://invoke-ai.github.io/InvokeAI/CHANGELOG/>Complete Changelog</a>
+
+- 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
+    via a new python process (which could break the environment)
+
+- v2.0.0 (9 October 2022)
+
+  - `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://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://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://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>
+  - 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://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`.
 
-- v1.14 (11 September 2022)
-
-  - 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 (3 September 2022
-
-  - Support image variations (see [VARIATIONS](docs/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 dream.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](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
@@ -183,7 +200,7 @@ 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
@@ -197,4 +214,4 @@ 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/modules/create_cmd_parser.py

@@ -1,6 +1,6 @@
 import argparse
 import os
-from ldm.dream.args import PRECISION_CHOICES
+from ldm.invoke.args import PRECISION_CHOICES
 
 
 def create_cmd_parser():

backend/modules/parameters.py

@@ -15,7 +15,7 @@ SAMPLER_CHOICES = [
 
 def parameters_to_command(params):
     """
-    Converts dict of parameters into a `dream.py` REPL command.
+    Converts dict of parameters into a `invoke.py` REPL command.
     """
 
     switches = list()
@@ -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

@@ -1,821 +0,0 @@
-import mimetypes
-import transformers
-import json
-import os
-import traceback
-import eventlet
-import glob
-import shlex
-import math
-import shutil
-import sys
-
-sys.path.append(".")
-
-from argparse import ArgumentTypeError
-from modules.create_cmd_parser import create_cmd_parser
-
-parser = create_cmd_parser()
-opt = parser.parse_args()
-
-
-from flask_socketio import SocketIO
-from flask import Flask, send_from_directory, url_for, jsonify
-from pathlib import Path
-from PIL import Image
-from pytorch_lightning import logging
-from threading import Event
-from uuid import uuid4
-from send2trash import send2trash
-
-
-from ldm.generate import Generate
-from ldm.dream.restoration import Restoration
-from ldm.dream.pngwriter import PngWriter, retrieve_metadata
-from ldm.dream.args import APP_ID, APP_VERSION, calculate_init_img_hash
-from ldm.dream.conditioning import split_weighted_subprompts
-
-from modules.parameters import parameters_to_command
-
-
-"""
-USER CONFIG
-"""
-if opt.cors and "*" in opt.cors:
-    raise ArgumentTypeError('"*" is not an allowed CORS origin')
-
-
-output_dir = "outputs/"  # Base output directory for images
-host = opt.host  # Web & socket.io host
-port = opt.port  # Web & socket.io port
-verbose = opt.verbose  # enables copious socket.io logging
-precision = opt.precision
-free_gpu_mem = opt.free_gpu_mem
-embedding_path = opt.embedding_path
-additional_allowed_origins = (
-    opt.cors if opt.cors else []
-)  # additional CORS allowed origins
-model = "stable-diffusion-1.4"
-
-"""
-END USER CONFIG
-"""
-
-
-print("* Initializing, be patient...\n")
-
-
-"""
-SERVER SETUP
-"""
-
-
-# fix missing mimetypes on windows due to registry wonkiness
-mimetypes.add_type("application/javascript", ".js")
-mimetypes.add_type("text/css", ".css")
-
-app = Flask(__name__, static_url_path="", static_folder="../frontend/dist/")
-
-
-app.config["OUTPUTS_FOLDER"] = "../outputs"
-
-
-@app.route("/outputs/<path:filename>")
-def outputs(filename):
-    return send_from_directory(app.config["OUTPUTS_FOLDER"], filename)
-
-
-@app.route("/", defaults={"path": ""})
-def serve(path):
-    return send_from_directory(app.static_folder, "index.html")
-
-
-logger = True if verbose else False
-engineio_logger = True if verbose else False
-
-# default 1,000,000, needs to be higher for socketio to accept larger images
-max_http_buffer_size = 10000000
-
-cors_allowed_origins = [f"http://{host}:{port}"] + additional_allowed_origins
-
-socketio = SocketIO(
-    app,
-    logger=logger,
-    engineio_logger=engineio_logger,
-    max_http_buffer_size=max_http_buffer_size,
-    cors_allowed_origins=cors_allowed_origins,
-    ping_interval=(50, 50),
-    ping_timeout=60,
-)
-
-
-"""
-END SERVER SETUP
-"""
-
-
-"""
-APP SETUP
-"""
-
-
-class CanceledException(Exception):
-    pass
-
-
-try:
-    gfpgan, codeformer, esrgan = None, None, None
-    from ldm.dream.restoration.base import Restoration
-
-    restoration = Restoration()
-    gfpgan, codeformer = restoration.load_face_restore_models()
-    esrgan = restoration.load_esrgan()
-
-    # coreformer.process(self, image, strength, device, seed=None, fidelity=0.75)
-
-except (ModuleNotFoundError, ImportError):
-    print(traceback.format_exc(), file=sys.stderr)
-    print(">> You may need to install the ESRGAN and/or GFPGAN modules")
-
-canceled = Event()
-
-# reduce logging outputs to error
-transformers.logging.set_verbosity_error()
-logging.getLogger("pytorch_lightning").setLevel(logging.ERROR)
-
-# Initialize and load model
-generate = Generate(
-    model,
-    precision=precision,
-    embedding_path=embedding_path,
-)
-generate.free_gpu_mem = free_gpu_mem
-generate.load_model()
-
-
-# location for "finished" images
-result_path = os.path.join(output_dir, "img-samples/")
-
-# temporary path for intermediates
-intermediate_path = os.path.join(result_path, "intermediates/")
-
-# path for user-uploaded init images and masks
-init_image_path = os.path.join(result_path, "init-images/")
-mask_image_path = os.path.join(result_path, "mask-images/")
-
-# txt log
-log_path = os.path.join(result_path, "dream_log.txt")
-
-# make all output paths
-[
-    os.makedirs(path, exist_ok=True)
-    for path in [result_path, intermediate_path, init_image_path, mask_image_path]
-]
-
-
-"""
-END APP SETUP
-"""
-
-
-"""
-SOCKET.IO LISTENERS
-"""
-
-
-@socketio.on("requestSystemConfig")
-def handle_request_capabilities():
-    print(f">> System config requested")
-    config = get_system_config()
-    socketio.emit("systemConfig", config)
-
-
-@socketio.on("requestImages")
-def handle_request_images(page=1, offset=0, last_mtime=None):
-    chunk_size = 50
-
-    if last_mtime:
-        print(f">> Latest images requested")
-    else:
-        print(
-            f">> Page {page} of images requested (page size {chunk_size} offset {offset})"
-        )
-
-    paths = glob.glob(os.path.join(result_path, "*.png"))
-    sorted_paths = sorted(paths, key=lambda x: os.path.getmtime(x), reverse=True)
-
-    if last_mtime:
-        image_paths = filter(lambda x: os.path.getmtime(x) > last_mtime, sorted_paths)
-    else:
-
-        image_paths = sorted_paths[
-            slice(chunk_size * (page - 1) + offset, chunk_size * page + offset)
-        ]
-        page = page + 1
-
-    image_array = []
-
-    for path in image_paths:
-        metadata = retrieve_metadata(path)
-        image_array.append(
-            {
-                "url": path,
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata["sd-metadata"],
-            }
-        )
-
-    socketio.emit(
-        "galleryImages",
-        {
-            "images": image_array,
-            "nextPage": page,
-            "offset": offset,
-            "onlyNewImages": True if last_mtime else False,
-        },
-    )
-
-
-@socketio.on("generateImage")
-def handle_generate_image_event(
-    generation_parameters, esrgan_parameters, gfpgan_parameters
-):
-    print(
-        f">> Image generation requested: {generation_parameters}\nESRGAN parameters: {esrgan_parameters}\nGFPGAN parameters: {gfpgan_parameters}"
-    )
-    generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
-
-
-@socketio.on("runESRGAN")
-def handle_run_esrgan_event(original_image, esrgan_parameters):
-    print(
-        f'>> ESRGAN upscale requested for "{original_image["url"]}": {esrgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Upscaling"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = esrgan.process(
-        image=image,
-        upsampler_scale=esrgan_parameters["upscale"][0],
-        strength=esrgan_parameters["upscale"][1],
-        seed=seed,
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    esrgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=esrgan_parameters,
-        original_image_path=original_image["url"],
-        type="esrgan",
-    )
-    command = parameters_to_command(esrgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="esrgan")
-
-    write_log_message(f'[Upscaled] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "esrganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.getmtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("runGFPGAN")
-def handle_run_gfpgan_event(original_image, gfpgan_parameters):
-    print(
-        f'>> GFPGAN face fix requested for "{original_image["url"]}": {gfpgan_parameters}'
-    )
-    progress = {
-        "currentStep": 1,
-        "totalSteps": 1,
-        "currentIteration": 1,
-        "totalIterations": 1,
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = Image.open(original_image["url"])
-
-    seed = (
-        original_image["metadata"]["seed"]
-        if "seed" in original_image["metadata"]
-        else "unknown_seed"
-    )
-
-    progress["currentStatus"] = "Fixing faces"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    image = gfpgan.process(
-        image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
-    )
-
-    progress["currentStatus"] = "Saving image"
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    gfpgan_parameters["seed"] = seed
-    metadata = parameters_to_post_processed_image_metadata(
-        parameters=gfpgan_parameters,
-        original_image_path=original_image["url"],
-        type="gfpgan",
-    )
-    command = parameters_to_command(gfpgan_parameters)
-
-    path = save_image(image, command, metadata, result_path, postprocessing="gfpgan")
-
-    write_log_message(f'[Fixed faces] "{original_image["url"]}" > "{path}": {command}')
-
-    progress["currentStatus"] = "Finished"
-    progress["currentStep"] = 0
-    progress["totalSteps"] = 0
-    progress["currentIteration"] = 0
-    progress["totalIterations"] = 0
-    progress["isProcessing"] = False
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    socketio.emit(
-        "gfpganResult",
-        {
-            "url": os.path.relpath(path),
-            "mtime": os.path.mtime(path),
-            "metadata": metadata,
-        },
-    )
-
-
-@socketio.on("cancel")
-def handle_cancel():
-    print(f">> Cancel processing requested")
-    canceled.set()
-    socketio.emit("processingCanceled")
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("deleteImage")
-def handle_delete_image(path, uuid):
-    print(f'>> Delete requested "{path}"')
-    send2trash(path)
-    socketio.emit("imageDeleted", {"url": path, "uuid": uuid})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadInitialImage")
-def handle_upload_initial_image(bytes, name):
-    print(f'>> Init image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(init_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("initialImageUploaded", {"url": file_path, "uuid": ""})
-
-
-# TODO: I think this needs a safety mechanism.
-@socketio.on("uploadMaskImage")
-def handle_upload_mask_image(bytes, name):
-    print(f'>> Mask image upload requested "{name}"')
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    file_path = os.path.join(mask_image_path, name)
-    os.makedirs(os.path.dirname(file_path), exist_ok=True)
-    newFile = open(file_path, "wb")
-    newFile.write(bytes)
-    socketio.emit("maskImageUploaded", {"url": file_path, "uuid": ""})
-
-
-"""
-END SOCKET.IO LISTENERS
-"""
-
-
-"""
-ADDITIONAL FUNCTIONS
-"""
-
-
-def get_system_config():
-    return {
-        "model": "stable diffusion",
-        "model_id": model,
-        "model_hash": generate.model_hash,
-        "app_id": APP_ID,
-        "app_version": APP_VERSION,
-    }
-
-
-def parameters_to_post_processed_image_metadata(parameters, original_image_path, type):
-    # top-level metadata minus `image` or `images`
-    metadata = get_system_config()
-
-    orig_hash = calculate_init_img_hash(original_image_path)
-
-    image = {"orig_path": original_image_path, "orig_hash": orig_hash}
-
-    if type == "esrgan":
-        image["type"] = "esrgan"
-        image["scale"] = parameters["upscale"][0]
-        image["strength"] = parameters["upscale"][1]
-    elif type == "gfpgan":
-        image["type"] = "gfpgan"
-        image["strength"] = parameters["gfpgan_strength"]
-    else:
-        raise TypeError(f"Invalid type: {type}")
-
-    metadata["image"] = image
-    return metadata
-
-
-def parameters_to_generated_image_metadata(parameters):
-    # top-level metadata minus `image` or `images`
-
-    metadata = get_system_config()
-    # 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",
-        "seamless",
-    ]
-
-    rfc_dict = {}
-
-    for item in parameters.items():
-        key, value = item
-        if key in rfc266_img_fields:
-            rfc_dict[key] = value
-
-    postprocessing = []
-
-    # 'postprocessing' is either null or an
-    if "gfpgan_strength" in parameters:
-
-        postprocessing.append(
-            {"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
-        )
-
-    if "upscale" in parameters:
-        postprocessing.append(
-            {
-                "type": "esrgan",
-                "scale": int(parameters["upscale"][0]),
-                "strength": float(parameters["upscale"][1]),
-            }
-        )
-
-    rfc_dict["postprocessing"] = postprocessing if len(postprocessing) > 0 else None
-
-    # semantic drift
-    rfc_dict["sampler"] = parameters["sampler_name"]
-
-    # display weighted subprompts (liable to change)
-    subprompts = split_weighted_subprompts(parameters["prompt"])
-    subprompts = [{"prompt": x[0], "weight": x[1]} for x in subprompts]
-    rfc_dict["prompt"] = subprompts
-
-    # 'variations' should always exist and be an array, empty or consisting of {'seed': seed, 'weight': weight} pairs
-    variations = []
-
-    if "with_variations" in parameters:
-        variations = [
-            {"seed": x[0], "weight": x[1]} for x in parameters["with_variations"]
-        ]
-
-    rfc_dict["variations"] = variations
-
-    if "init_img" in parameters:
-        rfc_dict["type"] = "img2img"
-        rfc_dict["strength"] = parameters["strength"]
-        rfc_dict["fit"] = parameters["fit"]  # TODO: Noncompliant
-        rfc_dict["orig_hash"] = calculate_init_img_hash(parameters["init_img"])
-        rfc_dict["init_image_path"] = parameters["init_img"]  # TODO: Noncompliant
-        rfc_dict["sampler"] = "ddim"  # TODO: FIX ME WHEN IMG2IMG SUPPORTS ALL SAMPLERS
-        if "init_mask" in parameters:
-            rfc_dict["mask_hash"] = calculate_init_img_hash(
-                parameters["init_mask"]
-            )  # TODO: Noncompliant
-            rfc_dict["mask_image_path"] = parameters["init_mask"]  # TODO: Noncompliant
-    else:
-        rfc_dict["type"] = "txt2img"
-
-    metadata["image"] = rfc_dict
-
-    return metadata
-
-
-def make_unique_init_image_filename(name):
-    uuid = uuid4().hex
-    split = os.path.splitext(name)
-    name = f"{split[0]}.{uuid}{split[1]}"
-    return name
-
-
-def write_log_message(message, log_path=log_path):
-    """Logs the filename and parameters used to generate or process that image to log file"""
-    message = f"{message}\n"
-    with open(log_path, "a", encoding="utf-8") as file:
-        file.writelines(message)
-
-
-def save_image(
-    image, command, metadata, output_dir, step_index=None, postprocessing=False
-):
-    pngwriter = PngWriter(output_dir)
-    prefix = pngwriter.unique_prefix()
-
-    seed = "unknown_seed"
-
-    if "image" in metadata:
-        if "seed" in metadata["image"]:
-            seed = metadata["image"]["seed"]
-
-    filename = f"{prefix}.{seed}"
-
-    if step_index:
-        filename += f".{step_index}"
-    if postprocessing:
-        filename += f".postprocessed"
-
-    filename += ".png"
-
-    path = pngwriter.save_image_and_prompt_to_png(
-        image=image, dream_prompt=command, metadata=metadata, name=filename
-    )
-
-    return path
-
-
-def calculate_real_steps(steps, strength, has_init_image):
-    return math.floor(strength * steps) if has_init_image else steps
-
-
-def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters):
-    canceled.clear()
-
-    step_index = 1
-    prior_variations = (
-        generation_parameters["with_variations"]
-        if "with_variations" in generation_parameters
-        else []
-    )
-    """
-    If a result image is used as an init image, and then deleted, we will want to be
-    able to use it as an init image in the future. Need to copy it.
-
-    If the init/mask image doesn't exist in the init_image_path/mask_image_path,
-    make a unique filename for it and copy it there.
-    """
-    if "init_img" in generation_parameters:
-        filename = os.path.basename(generation_parameters["init_img"])
-        if not os.path.exists(os.path.join(init_image_path, filename)):
-            unique_filename = make_unique_init_image_filename(filename)
-            new_path = os.path.join(init_image_path, unique_filename)
-            shutil.copy(generation_parameters["init_img"], new_path)
-            generation_parameters["init_img"] = new_path
-        if "init_mask" in generation_parameters:
-            filename = os.path.basename(generation_parameters["init_mask"])
-            if not os.path.exists(os.path.join(mask_image_path, filename)):
-                unique_filename = make_unique_init_image_filename(filename)
-                new_path = os.path.join(init_image_path, unique_filename)
-                shutil.copy(generation_parameters["init_img"], new_path)
-                generation_parameters["init_mask"] = new_path
-
-    totalSteps = calculate_real_steps(
-        steps=generation_parameters["steps"],
-        strength=generation_parameters["strength"]
-        if "strength" in generation_parameters
-        else None,
-        has_init_image="init_img" in generation_parameters,
-    )
-
-    progress = {
-        "currentStep": 1,
-        "totalSteps": totalSteps,
-        "currentIteration": 1,
-        "totalIterations": generation_parameters["iterations"],
-        "currentStatus": "Preparing",
-        "isProcessing": True,
-        "currentStatusHasSteps": False,
-    }
-
-    socketio.emit("progressUpdate", progress)
-    eventlet.sleep(0)
-
-    def image_progress(sample, step):
-        if canceled.is_set():
-            raise CanceledException
-
-        nonlocal step_index
-        nonlocal generation_parameters
-        nonlocal progress
-
-        progress["currentStep"] = step + 1
-        progress["currentStatus"] = "Generating"
-        progress["currentStatusHasSteps"] = True
-
-        if (
-            generation_parameters["progress_images"]
-            and step % 5 == 0
-            and step < generation_parameters["steps"] - 1
-        ):
-            image = generate.sample_to_image(sample)
-
-            metadata = parameters_to_generated_image_metadata(generation_parameters)
-            command = parameters_to_command(generation_parameters)
-            path = save_image(image, command, metadata, intermediate_path, step_index=step_index, postprocessing=False)
-
-            step_index += 1
-            socketio.emit(
-                "intermediateResult",
-                {
-                    "url": os.path.relpath(path),
-                    "mtime": os.path.getmtime(path),
-                    "metadata": metadata,
-                },
-            )
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-    def image_done(image, seed, first_seed):
-        nonlocal generation_parameters
-        nonlocal esrgan_parameters
-        nonlocal gfpgan_parameters
-        nonlocal progress
-
-        step_index = 1
-        nonlocal prior_variations
-
-        progress["currentStatus"] = "Generation complete"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        all_parameters = generation_parameters
-        postprocessing = False
-
-        if (
-            "variation_amount" in all_parameters
-            and all_parameters["variation_amount"] > 0
-        ):
-            first_seed = first_seed or seed
-            this_variation = [[seed, all_parameters["variation_amount"]]]
-            all_parameters["with_variations"] = prior_variations + this_variation
-            all_parameters["seed"] = first_seed
-        elif ("with_variations" in all_parameters):
-            all_parameters["seed"] = first_seed
-        else:
-            all_parameters["seed"] = seed
-
-        if esrgan_parameters:
-            progress["currentStatus"] = "Upscaling"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = esrgan.process(
-                image=image,
-                upsampler_scale=esrgan_parameters["level"],
-                strength=esrgan_parameters["strength"],
-                seed=seed,
-            )
-
-            postprocessing = True
-            all_parameters["upscale"] = [
-                esrgan_parameters["level"],
-                esrgan_parameters["strength"],
-            ]
-
-        if gfpgan_parameters:
-            progress["currentStatus"] = "Fixing faces"
-            progress["currentStatusHasSteps"] = False
-            socketio.emit("progressUpdate", progress)
-            eventlet.sleep(0)
-
-            image = gfpgan.process(
-                image=image, strength=gfpgan_parameters["strength"], seed=seed
-            )
-            postprocessing = True
-            all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
-
-        progress["currentStatus"] = "Saving image"
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        metadata = parameters_to_generated_image_metadata(all_parameters)
-        command = parameters_to_command(all_parameters)
-
-        path = save_image(
-            image, command, metadata, result_path, postprocessing=postprocessing
-        )
-
-        print(f'>> Image generated: "{path}"')
-        write_log_message(f'[Generated] "{path}": {command}')
-
-        if progress["totalIterations"] > progress["currentIteration"]:
-            progress["currentStep"] = 1
-            progress["currentIteration"] += 1
-            progress["currentStatus"] = "Iteration finished"
-            progress["currentStatusHasSteps"] = False
-        else:
-            progress["currentStep"] = 0
-            progress["totalSteps"] = 0
-            progress["currentIteration"] = 0
-            progress["totalIterations"] = 0
-            progress["currentStatus"] = "Finished"
-            progress["isProcessing"] = False
-
-        socketio.emit("progressUpdate", progress)
-        eventlet.sleep(0)
-
-        socketio.emit(
-            "generationResult",
-            {
-                "url": os.path.relpath(path),
-                "mtime": os.path.getmtime(path),
-                "metadata": metadata,
-            },
-        )
-        eventlet.sleep(0)
-
-    try:
-        generate.prompt2image(
-            **generation_parameters,
-            step_callback=image_progress,
-            image_callback=image_done,
-        )
-
-    except KeyboardInterrupt:
-        raise
-    except CanceledException:
-        pass
-    except Exception as e:
-        socketio.emit("error", {"message": (str(e))})
-        print("\n")
-        traceback.print_exc()
-        print("\n")
-
-
-"""
-END ADDITIONAL FUNCTIONS
-"""
-
-
-if __name__ == "__main__":
-    print(f">> Starting server at http://{host}:{port}")
-    socketio.run(app, host=host, port=port)

configs/autoencoder/autoencoder_kl_16x16x16.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 16
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 16
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_32x32x4.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 4
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 4
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_64x64x3.yaml

@@ -1,54 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 3
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 3
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,2,4 ]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [ ]
-      dropout: 0.0
-
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_8x8x64.yaml

@@ -1,53 +0,0 @@
-model:
-  base_learning_rate: 4.5e-6
-  target: ldm.models.autoencoder.AutoencoderKL
-  params:
-    monitor: "val/rec_loss"
-    embed_dim: 64
-    lossconfig:
-      target: ldm.modules.losses.LPIPSWithDiscriminator
-      params:
-        disc_start: 50001
-        kl_weight: 0.000001
-        disc_weight: 0.5
-
-    ddconfig:
-      double_z: True
-      z_channels: 64
-      resolution: 256
-      in_channels: 3
-      out_ch: 3
-      ch: 128
-      ch_mult: [ 1,1,2,2,4,4]  # num_down = len(ch_mult)-1
-      num_res_blocks: 2
-      attn_resolutions: [16,8]
-      dropout: 0.0
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 12
-    wrap: True
-    train:
-      target: ldm.data.imagenet.ImageNetSRTrain
-      params:
-        size: 256
-        degradation: pil_nearest
-    validation:
-      target: ldm.data.imagenet.ImageNetSRValidation
-      params:
-        size: 256
-        degradation: pil_nearest
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 1000
-        max_images: 8
-        increase_log_steps: True
-
-  trainer:
-    benchmark: True
-    accumulate_grad_batches: 2

configs/latent-diffusion/celebahq-ldm-vq-4.yaml

@@ -1,86 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: models/first_stage_models/vq-f4/model.ckpt
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.CelebAHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.CelebAHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin-ldm-vq-f8.yaml

@@ -1,98 +0,0 @@
-model:
-  base_learning_rate: 1.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 256
-        attention_resolutions:
-        #note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 32 for f8
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 4
-        n_embed: 16384
-        ckpt_path: configs/first_stage_models/vq-f8/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 32
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        embed_dim: 512
-        key: class_label
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 64
-    num_workers: 12
-    wrap: false
-    train:
-      target: ldm.data.imagenet.ImageNetTrain
-      params:
-        config:
-          size: 256
-    validation:
-      target: ldm.data.imagenet.ImageNetValidation
-      params:
-        config:
-          size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/cin256-v2.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: class_label
-    image_size: 64
-    channels: 3
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss
-    use_ema: False
-    
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 192
-        attention_resolutions:
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 5
-        num_heads: 1
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 512
-    
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.ClassEmbedder
-      params:
-        n_classes: 1001
-        embed_dim: 512
-        key: class_label

configs/latent-diffusion/ffhq-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        embed_dim: 3
-        n_embed: 8192
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 42
-    num_workers: 5
-    wrap: false
-    train:
-      target: taming.data.faceshq.FFHQTrain
-      params:
-        size: 256
-    validation:
-      target: taming.data.faceshq.FFHQValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_bedrooms-ldm-vq-4.yaml

@@ -1,85 +0,0 @@
-model:
-  base_learning_rate: 2.0e-06
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0195
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    image_size: 64
-    channels: 3
-    monitor: val/loss_simple_ema
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 64
-        in_channels: 3
-        out_channels: 3
-        model_channels: 224
-        attention_resolutions:
-        # note: this isn\t actually the resolution but
-        # the downsampling factor, i.e. this corresnponds to
-        # attention on spatial resolution 8,16,32, as the
-        # spatial reolution of the latents is 64 for f4
-        - 8
-        - 4
-        - 2
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        num_head_channels: 32
-    first_stage_config:
-      target: ldm.models.autoencoder.VQModelInterface
-      params:
-        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
-        embed_dim: 3
-        n_embed: 8192
-        ddconfig:
-          double_z: false
-          z_channels: 3
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config: __is_unconditional__
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 48
-    num_workers: 5
-    wrap: false
-    train:
-      target: ldm.data.lsun.LSUNBedroomsTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNBedroomsValidation
-      params:
-        size: 256
-
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/lsun_churches-ldm-kl-8.yaml

@@ -1,91 +0,0 @@
-model:
-  base_learning_rate: 5.0e-5   # set to target_lr by starting main.py with '--scale_lr False'
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.0155
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    loss_type: l1
-    first_stage_key: "image"
-    cond_stage_key: "image"
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: False
-    concat_mode: False
-    scale_by_std: True
-    monitor: 'val/loss_simple_ema'
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [10000]
-        cycle_lengths: [10000000000000]
-        f_start: [1.e-6]
-        f_max: [1.]
-        f_min: [ 1.]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 192
-        attention_resolutions: [ 1, 2, 4, 8 ]   # 32, 16, 8, 4
-        num_res_blocks: 2
-        channel_mult: [ 1,2,2,4,4 ]  # 32, 16, 8, 4, 2
-        num_heads: 8
-        use_scale_shift_norm: True
-        resblock_updown: True
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: "val/rec_loss"
-        ckpt_path: "models/first_stage_models/kl-f8/model.ckpt"
-        ddconfig:
-          double_z: True
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
-          num_res_blocks: 2
-          attn_resolutions: [ ]
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config: "__is_unconditional__"
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 96
-    num_workers: 5
-    wrap: False
-    train:
-      target: ldm.data.lsun.LSUNChurchesTrain
-      params:
-        size: 256
-    validation:
-      target: ldm.data.lsun.LSUNChurchesValidation
-      params:
-        size: 256
-
-lightning:
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 5000
-        max_images: 8
-        increase_log_steps: False
-
-
-  trainer:
-    benchmark: True

configs/latent-diffusion/txt2img-1p4B-eval.yaml

@@ -1,71 +0,0 @@
-model:
-  base_learning_rate: 5.0e-05
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.012
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: caption
-    image_size: 32
-    channels: 4
-    cond_stage_trainable: true
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions:
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 4
-        - 4
-        num_heads: 8
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 1280
-        use_checkpoint: true
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.BERTEmbedder
-      params:
-        n_embed: 1280
-        n_layer: 32

configs/models.yaml

@@ -1,18 +0,0 @@
-# This file describes the alternative machine learning models
-#  available to the dream script.
-#
-# To add a new model, follow the examples below. Each
-# model requires a model config file, a weights file,
-# and the width and height of the images it
-# was trained on.
-
-laion400m:
-    config:  configs/latent-diffusion/txt2img-1p4B-eval.yaml
-    weights: models/ldm/text2img-large/model.ckpt
-    width: 256
-    height: 256
-stable-diffusion-1.4:
-    config:  configs/stable-diffusion/v1-inference.yaml
-    weights: models/ldm/stable-diffusion-v1/model.ckpt
-    width: 512
-    height: 512

configs/models.yaml.example

@@ -0,0 +1,27 @@
+# This file describes the alternative machine learning models
+# available to InvokeAI script.
+#
+# To add a new model, follow the examples below. Each
+# model requires a model config file, a weights file,
+# and the width and height of the images it
+# was trained on.
+stable-diffusion-1.5:
+  description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+  weights: ./models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+  config: ./configs/stable-diffusion/v1-inference.yaml
+  width: 512
+  height: 512
+  vae: ./models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  default: true
+stable-diffusion-1.4:
+  description: Stable Diffusion inference model version 1.4
+  config: configs/stable-diffusion/v1-inference.yaml
+  weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  description: RunwayML SD 1.5 model optimized for inpainting

configs/retrieval-augmented-diffusion/768x768.yaml

@@ -1,68 +0,0 @@
-model:
-  base_learning_rate: 0.0001
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.0015
-    linear_end: 0.015
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: jpg
-    cond_stage_key: nix
-    image_size: 48
-    channels: 16
-    cond_stage_trainable: false
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_by_std: false
-    scale_factor: 0.22765929
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 48
-        in_channels: 16
-        out_channels: 16
-        model_channels: 448
-        attention_resolutions:
-        - 4
-        - 2
-        - 1
-        num_res_blocks: 2
-        channel_mult:
-        - 1
-        - 2
-        - 3
-        - 4
-        use_scale_shift_norm: false
-        resblock_updown: false
-        num_head_channels: 32
-        use_spatial_transformer: true
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: true
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        monitor: val/rec_loss
-        embed_dim: 16
-        ddconfig:
-          double_z: true
-          z_channels: 16
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 1
-          - 2
-          - 2
-          - 4
-          num_res_blocks: 2
-          attn_resolutions:
-          - 16
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-    cond_stage_config:
-      target: torch.nn.Identity

configs/stable-diffusion/v1-inference.yaml

@@ -32,7 +32,7 @@ model:
         placeholder_strings: ["*"]
         initializer_words: ['face', 'man', 'photo', 'africanmale']
         per_image_tokens: false
-        num_vectors_per_token: 6
+        num_vectors_per_token: 1
         progressive_words: False
 
     unet_config:
@@ -76,4 +76,4 @@ model:
           target: torch.nn.Identity
 
     cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-inpainting-inference.yaml

@@ -0,0 +1,79 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['face', 'man', 'photo', 'africanmale']
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

docker-build/Dockerfile

@@ -1,57 +1,74 @@
-FROM        debian 
+FROM ubuntu AS get_miniconda
 
-ARG         gsd
-ENV         GITHUB_STABLE_DIFFUSION $gsd
+SHELL ["/bin/bash", "-c"]
 
-ARG         rsd
-ENV         REQS $rsd
+# install wget
+RUN apt-get update \
+  && apt-get install -y \
+    wget \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
 
-ARG         cs
-ENV         CONDA_SUBDIR $cs
+# download and install miniconda
+ARG conda_version=py39_4.12.0-Linux-x86_64
+ARG conda_prefix=/opt/conda
+RUN wget --progress=dot:giga -O /miniconda.sh \
+  https://repo.anaconda.com/miniconda/Miniconda3-${conda_version}.sh \
+  && bash /miniconda.sh -b -p ${conda_prefix} \
+  && rm -f /miniconda.sh
 
-ENV         PIP_EXISTS_ACTION="w"
+FROM ubuntu AS invokeai
 
-# TODO: Optimize image size
+# use bash
+SHELL [ "/bin/bash", "-c" ]
 
-SHELL       ["/bin/bash", "-c"]
+# clean bashrc
+RUN echo "" > ~/.bashrc
 
-WORKDIR     /
-RUN         apt update && apt upgrade -y \
-            && apt install -y \
-            git \
-            libgl1-mesa-glx \
-            libglib2.0-0 \
-            pip \
-            python3 \
-            && git clone $GITHUB_STABLE_DIFFUSION
+# Install necesarry packages
+RUN apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    gcc \
+    git \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    pip \
+    python3 \
+    python3-dev \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
 
-# Install Anaconda or Miniconda
-COPY        anaconda.sh .
-RUN         bash anaconda.sh -b -u -p /anaconda && /anaconda/bin/conda init bash
+# clone repository and create symlinks
+ARG invokeai_git=https://github.com/invoke-ai/InvokeAI.git
+ARG project_name=invokeai
+RUN git clone ${invokeai_git} /${project_name} \
+  && mkdir /${project_name}/models/ldm/stable-diffusion-v1 \
+  && ln -s /data/models/sd-v1-4.ckpt /${project_name}/models/ldm/stable-diffusion-v1/model.ckpt \
+  && ln -s /data/outputs/ /${project_name}/outputs
 
-# SD 
-WORKDIR     /stable-diffusion 
-RUN         source ~/.bashrc \
-            && conda create -y --name ldm && conda activate ldm \
-            && conda config --env --set subdir $CONDA_SUBDIR \
-            && pip3 install -r $REQS \   
-            && pip3 install basicsr facexlib realesrgan \          
-            && mkdir models/ldm/stable-diffusion-v1 \
-            && ln -s "/data/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt 
+# set workdir
+WORKDIR /${project_name}
 
-# Face restoreation
-# by default expected in a sibling directory to stable-diffusion
-WORKDIR     /       
-RUN         git clone https://github.com/TencentARC/GFPGAN.git 
+# install conda env and preload models
+ARG conda_prefix=/opt/conda
+ARG conda_env_file=environment.yml
+COPY --from=get_miniconda ${conda_prefix} ${conda_prefix}
+RUN source ${conda_prefix}/etc/profile.d/conda.sh \
+  && conda init bash \
+  && source ~/.bashrc \
+  && conda env create \
+    --name ${project_name} \
+    --file ${conda_env_file} \
+  && rm -Rf ~/.cache \
+  && conda clean -afy \
+  && echo "conda activate ${project_name}" >> ~/.bashrc \
+  && ln -s /data/models/GFPGANv1.4.pth ./src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth \
+  && conda activate ${project_name} \
+  && python scripts/preload_models.py
 
-WORKDIR     /GFPGAN 
-RUN         pip3 install -r requirements.txt \
-            && python3 setup.py develop \
-            && ln -s "/data/GFPGANv1.4.pth" experiments/pretrained_models/GFPGANv1.4.pth
-
-WORKDIR     /stable-diffusion 
-RUN         python3 scripts/preload_models.py         
-
-WORKDIR     /
-COPY        entrypoint.sh .
-ENTRYPOINT ["/entrypoint.sh"]
+# Copy entrypoint and set env
+ENV CONDA_PREFIX=${conda_prefix}
+ENV PROJECT_NAME=${project_name}
+COPY docker-build/entrypoint.sh /
+ENTRYPOINT [ "/entrypoint.sh" ]

docker-build/build.sh

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+set -e
+# IMPORTANT: You need to have a token on huggingface.co to be able to download the checkpoint!!!
+# configure values by using env when executing build.sh
+# f.e. env ARCH=aarch64 GITHUB_INVOKE_AI=https://github.com/yourname/yourfork.git ./build.sh
+
+source ./docker-build/env.sh || echo "please run from repository root" || exit 1
+
+invokeai_conda_version=${INVOKEAI_CONDA_VERSION:-py39_4.12.0-${platform/\//-}}
+invokeai_conda_prefix=${INVOKEAI_CONDA_PREFIX:-\/opt\/conda}
+invokeai_conda_env_file=${INVOKEAI_CONDA_ENV_FILE:-environment.yml}
+invokeai_git=${INVOKEAI_GIT:-https://github.com/invoke-ai/InvokeAI.git}
+huggingface_token=${HUGGINGFACE_TOKEN?}
+
+# print the settings
+echo "You are using these values:"
+echo -e "project_name:\t\t ${project_name}"
+echo -e "volumename:\t\t ${volumename}"
+echo -e "arch:\t\t\t ${arch}"
+echo -e "platform:\t\t ${platform}"
+echo -e "invokeai_conda_version:\t ${invokeai_conda_version}"
+echo -e "invokeai_conda_prefix:\t ${invokeai_conda_prefix}"
+echo -e "invokeai_conda_env_file: ${invokeai_conda_env_file}"
+echo -e "invokeai_git:\t\t ${invokeai_git}"
+echo -e "invokeai_tag:\t\t ${invokeai_tag}\n"
+
+_runAlpine() {
+  docker run \
+    --rm \
+    --interactive \
+    --tty \
+    --mount source="$volumename",target=/data \
+    --workdir /data \
+    alpine "$@"
+}
+
+_copyCheckpoints() {
+  echo "creating subfolders for models and outputs"
+  _runAlpine mkdir models
+  _runAlpine mkdir outputs
+  echo -n "downloading sd-v1-4.ckpt"
+  _runAlpine wget --header="Authorization: Bearer ${huggingface_token}" -O models/sd-v1-4.ckpt https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
+  echo "done"
+  echo "downloading GFPGANv1.4.pth"
+  _runAlpine wget -O models/GFPGANv1.4.pth https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth
+}
+
+_checkVolumeContent() {
+  _runAlpine ls -lhA /data/models
+}
+
+_getModelMd5s() {
+  _runAlpine  \
+    alpine sh -c "md5sum /data/models/*"
+}
+
+if [[ -n "$(docker volume ls -f name="${volumename}" -q)" ]]; then
+  echo "Volume already exists"
+  if [[ -z "$(_checkVolumeContent)" ]]; then
+    echo "looks empty, copying checkpoint"
+    _copyCheckpoints
+  fi
+  echo "Models in ${volumename}:"
+  _checkVolumeContent
+else
+  echo -n "createing docker volume "
+  docker volume create "${volumename}"
+  _copyCheckpoints
+fi
+
+# Build Container
+docker build \
+  --platform="${platform}" \
+  --tag "${invokeai_tag}" \
+  --build-arg project_name="${project_name}" \
+  --build-arg conda_version="${invokeai_conda_version}" \
+  --build-arg conda_prefix="${invokeai_conda_prefix}" \
+  --build-arg conda_env_file="${invokeai_conda_env_file}" \
+  --build-arg invokeai_git="${invokeai_git}" \
+  --file ./docker-build/Dockerfile \
+  .

docker-build/entrypoint.sh

@@ -1,10 +1,8 @@
 #!/bin/bash
+set -e
 
-cd /stable-diffusion
+source "${CONDA_PREFIX}/etc/profile.d/conda.sh"
+conda activate "${PROJECT_NAME}"
 
-if [ $# -eq 0 ]; then
-    python3 scripts/dream.py --full_precision -o /data
-    # bash
-else
-    python3 scripts/dream.py --full_precision -o /data "$@"
-fi
+python scripts/invoke.py \
+  ${@:---web --host=0.0.0.0}

docker-build/env.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+project_name=${PROJECT_NAME:-invokeai}
+volumename=${VOLUMENAME:-${project_name}_data}
+arch=${ARCH:-x86_64}
+platform=${PLATFORM:-Linux/${arch}}
+invokeai_tag=${INVOKEAI_TAG:-${project_name}-${arch}}
+
+export project_name
+export volumename
+export arch
+export platform
+export invokeai_tag

docker-build/run.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+set -e
+
+source ./docker-build/env.sh || echo "please run from repository root" || exit 1
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform "$platform" \
+  --name "$project_name" \
+  --hostname "$project_name" \
+  --mount source="$volumename",target=/data \
+  --publish 9090:9090 \
+  "$invokeai_tag" ${1:+$@}

docs/CHANGELOG.md

@@ -1,51 +1,194 @@
-# **Changelog**
+---
+title: Changelog
+---
 
-## v1.13 (in process)
+# :octicons-log-16: **Changelog**
 
-- 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 dream> 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 dream.py command line as the default.
+## v2.1.0 (2 November 2022)
+- update mac instructions to use invokeai for env name by @willwillems in https://github.com/invoke-ai/InvokeAI/pull/1030
+- Update .gitignore by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/1040
+- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579 missing after merge by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in https://github.com/invoke-ai/InvokeAI/pull/1060
+- Print out the device type which is used by @manzke in https://github.com/invoke-ai/InvokeAI/pull/1073
+- Hires Addition by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/1063
+- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
+- Forward dream.py to invoke.py using the same interpreter, add deprecation warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
+- fix noisy images at high step counts by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1086
+- Generalize facetool strength argument by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1078
+- Enable fast switching among models at the invoke> command line by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in https://github.com/invoke-ai/InvokeAI/pull/1095
+- Update generate.py by @unreleased in https://github.com/invoke-ai/InvokeAI/pull/1109
+- Update 'ldm' env to 'invokeai' in troubleshooting steps by @19wolf in https://github.com/invoke-ai/InvokeAI/pull/1125
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in https://github.com/invoke-ai/InvokeAI/pull/1123
+- Fix broken doc links, fix malaprop in the project subtitle by @majick in https://github.com/invoke-ai/InvokeAI/pull/1131
+- Only output facetool parameters if enhancing faces by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1119
+- Update gitignore to ignore codeformer weights at new location by @spezialspezial in https://github.com/invoke-ai/InvokeAI/pull/1136
+- fix links to point to invoke-ai.github.io #1117 by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1143
+- Rework-mkdocs by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1144
+- add option to CLI and pngwriter that allows user to set PNG compression level by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
+- Fix img2img DDIM index out of bound by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1137
+- Fix gh actions by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1128
+- update mac instructions to use invokeai for env name by @willwillems in https://github.com/invoke-ai/InvokeAI/pull/1030
+- Update .gitignore by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/1040
+- reintroduce fix for m1 from https://github.com/invoke-ai/InvokeAI/pull/579 missing after merge by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in https://github.com/invoke-ai/InvokeAI/pull/1060
+- Print out the device type which is used by @manzke in https://github.com/invoke-ai/InvokeAI/pull/1073
+- Hires Addition by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/1063
+- fix for "1 leaked semaphore objects to clean up at shutdown" on M1 by @skurovec in https://github.com/invoke-ai/InvokeAI/pull/1081
+- Forward dream.py to invoke.py using the same interpreter, add deprecation warning by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1077
+- fix noisy images at high step counts by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1086
+- Generalize facetool strength argument by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1078
+- Enable fast switching among models at the invoke> command line by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in https://github.com/invoke-ai/InvokeAI/pull/1095
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in https://github.com/invoke-ai/InvokeAI/pull/1123
+- Only output facetool parameters if enhancing faces by @db3000 in https://github.com/invoke-ai/InvokeAI/pull/1119
+- add option to CLI and pngwriter that allows user to set PNG compression level by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1127
+- Fix img2img DDIM index out of bound by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1137
+- Add text prompt to inpaint mask support by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1133
+- Respect http[s] protocol when making socket.io middleware by @damian0815 in https://github.com/invoke-ai/InvokeAI/pull/976
+- WebUI: Adds Codeformer support by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1151
+- Skips normalizing prompts for web UI metadata by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1165
+- Add Asymmetric Tiling by @carson-katri in https://github.com/invoke-ai/InvokeAI/pull/1132
+- Web UI: Increases max CFG Scale to 200 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1172
+- Corrects color channels in face restoration; Fixes #1167 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1175
+- Flips channels using array slicing instead of using OpenCV by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1178
+- Fix typo in docs: s/Formally/Formerly by @noodlebox in https://github.com/invoke-ai/InvokeAI/pull/1176
+- fix clipseg loading problems by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1177
+- Correct color channels in upscale using array slicing by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1181
+- Web UI: Filters existing images when adding new images; Fixes #1085 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1171
+- fix a number of bugs in textual inversion by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1190
+- Improve !fetch, add !replay command by @ArDiouscuros in https://github.com/invoke-ai/InvokeAI/pull/882
+- Fix generation of image with s>1000 by @holstvoogd in https://github.com/invoke-ai/InvokeAI/pull/951
+- Web UI: Gallery improvements by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1198
+- Update CLI.md by @krummrey in https://github.com/invoke-ai/InvokeAI/pull/1211
+- outcropping improvements by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1207
+- add support for loading VAE autoencoders by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1216
+- remove duplicate fix_func for MPS by @wfng92 in https://github.com/invoke-ai/InvokeAI/pull/1210
+- Metadata storage and retrieval fixes by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1204
+- nix: add shell.nix file by @Cloudef in https://github.com/invoke-ai/InvokeAI/pull/1170
+- Web UI: Changes vite dist asset paths to relative by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1185
+- Web UI: Removes isDisabled from PromptInput by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1187
+- Allow user to generate images with initial noise as on M1 / mps system by @ArDiouscuros in https://github.com/invoke-ai/InvokeAI/pull/981
+- feat: adding filename format template by @plucked in https://github.com/invoke-ai/InvokeAI/pull/968
+- Web UI: Fixes broken bundle by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1242
+- Support runwayML custom inpainting model by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1243
+- Update IMG2IMG.md by @talitore in https://github.com/invoke-ai/InvokeAI/pull/1262
+- New dockerfile - including a build- and a run- script as well as a GH-Action by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1233
+- cut over from karras to model noise schedule for higher steps by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1222
+- Prompt tweaks by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1268
+- Outpainting implementation by @Kyle0654 in https://github.com/invoke-ai/InvokeAI/pull/1251
+- fixing aspect ratio on hires by @tjennings in https://github.com/invoke-ai/InvokeAI/pull/1249
+- Fix-build-container-action by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1274
+- handle all unicode characters by @damian0815 in https://github.com/invoke-ai/InvokeAI/pull/1276
+- adds models.user.yml to .gitignore by @JakeHL in https://github.com/invoke-ai/InvokeAI/pull/1281
+- remove debug branch, set fail-fast to false by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1284
+- Protect-secrets-on-pr by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1285
+- Web UI: Adds initial inpainting implementation by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/1225
+- fix environment-mac.yml - tested on x64 and arm64 by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1289
+- Use proper authentication to download model by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1287
+- Prevent indexing error for mode RGB by @spezialspezial in https://github.com/invoke-ai/InvokeAI/pull/1294
+- Integrate sd-v1-5 model into test matrix (easily expandable), remove unecesarry caches by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1293
+- add --no-interactive to preload_models step by @mauwii in https://github.com/invoke-ai/InvokeAI/pull/1302
+- 1-click installer and updater. Uses micromamba to install git and conda into a contained environment (if necessary) before running the normal installation script by @cmdr2 in https://github.com/invoke-ai/InvokeAI/pull/1253
+- preload_models.py script downloads the weight files by @lstein in https://github.com/invoke-ai/InvokeAI/pull/1290
+
+## 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
+    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.
+- 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 [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 [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
+    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.
 
 ---
 
-## v1.12 (28 August 2022)
+## 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 dream.py script. Invoke by adding --web to
-  the dream.py command arguments.
+- 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 dream> command line. [Blessedcoolant](https://github.com/blessedcoolant)
+- You can now swap samplers on the invoke> command line. [Blessedcoolant](https://github.com/blessedcoolant)
 
 ---
 
-## v1.11 (26 August 2022)
+## 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-dream** 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)
+- 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 (25 August 2022)
+## v1.10 <small>(25 August 2022)</small>
 
 - A barebones but fully functional interactive web server for online generation of txt2img and img2img.
 
 ---
 
-## v1.09 (24 August 2022)
+## 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). [
@@ -55,9 +198,9 @@
 
 ---
 
-## v1.08 (24 August 2022)
+## v1.08 <small>(24 August 2022)</small>
 
-- Escape single quotes on the dream> command before trying to parse. This avoids
+- 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.
@@ -66,7 +209,7 @@
 
 ---
 
-## v1.07 (23 August 2022)
+## 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
@@ -74,14 +217,14 @@
 
 ---
 
-## v1.06 (23 August 2022)
+## 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 (22 August 2022 - after the drop)
+## 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),
@@ -94,12 +237,12 @@
   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 dream> prompt to set and retrieve
+- You can use the "cd" and "pwd" commands at the invoke> prompt to set and retrieve
   the path of the output directory.
 
 ---
 
-## v1.04 (22 August 2022 - after the drop)
+## 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
@@ -107,14 +250,14 @@
 
 ---
 
-## v1.03 (22 August 2022)
+## 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 (21 August 2022)
+## 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,
@@ -123,15 +266,15 @@
 
 ---
 
-## v1.01 (21 August 2022)
+## v1.01 <small>(21 August 2022)</small>
 
 - added k_lms sampling.
   **Please run "conda env update" 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 dream.py to get slower but more accurate image generation
+  Pass argument --full_precision to invoke.py to get slower but more accurate image generation
 
 ---
 
 ## Links
 
-- **[Read Me](../readme.md)**
+- **[Read Me](index.md)**

docs/assets/preflight-checks/outputs/invoke_log.md

@@ -0,0 +1,116 @@
+## 000001.1863159593.png
+![](000001.1863159593.png)
+
+banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+## 000002.1151955949.png
+![](000002.1151955949.png)
+
+banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+## 000003.2736230502.png
+![](000003.2736230502.png)
+
+banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+## 000004.42.png
+![](000004.42.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+## 000005.42.png
+![](000005.42.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+## 000006.478163327.png
+![](000006.478163327.png)
+
+banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+## 000007.2407640369.png
+![](000007.2407640369.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+## 000008.2772421987.png
+![](000008.2772421987.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+## 000009.3532317557.png
+![](000009.3532317557.png)
+
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+## 000010.2028635318.png
+![](000010.2028635318.png)
+
+banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+## 000011.1111168647.png
+![](000011.1111168647.png)
+
+pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+## 000012.1476370516.png
+![](000012.1476370516.png)
+
+pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms
+## 000013.4281108706.png
+![](000013.4281108706.png)
+
+banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+## 000014.2396987386.png
+![](000014.2396987386.png)
+
+old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+## 000015.1252923272.png
+![](000015.1252923272.png)
+
+old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+## 000016.2633891320.png
+![](000016.2633891320.png)
+
+old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+## 000017.1134411920.png
+![](000017.1134411920.png)
+
+old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+## 000018.47.png
+![](000018.47.png)
+
+big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000019.47.png
+![](000019.47.png)
+
+big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000020.47.png
+![](000020.47.png)
+
+big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000021.47.png
+![](000021.47.png)
+
+big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000022.47.png
+![](000022.47.png)
+
+dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000023.47.png
+![](000023.47.png)
+
+dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+## 000024.1029061431.png
+![](000024.1029061431.png)
+
+medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+## 000025.1284519352.png
+![](000025.1284519352.png)
+
+bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+## curly.942491079.gfpgan.png
+![](curly.942491079.gfpgan.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -G 0.8 -ft gfpgan -U 2.0 0.75
+## curly.942491079.outcrop.png
+![](curly.942491079.outcrop.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64
+## curly.942491079.outpaint.png
+![](curly.942491079.outpaint.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -D top 64
+## curly.942491079.outcrop-01.png
+![](curly.942491079.outcrop-01.png)
+
+!fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64

docs/assets/preflight-checks/outputs/invoke_log.txt

@@ -0,0 +1,29 @@
+outputs/preflight/000001.1863159593.png: banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000002.1151955949.png: banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+outputs/preflight/000003.2736230502.png: banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+outputs/preflight/000004.42.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000005.42.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000006.478163327.png: banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+outputs/preflight/000007.2407640369.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+outputs/preflight/000008.2772421987.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+outputs/preflight/000009.3532317557.png: banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+outputs/preflight/000010.2028635318.png: banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000011.1111168647.png: pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000012.1476370516.png: pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000013.4281108706.png: banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+outputs/preflight/000014.2396987386.png: old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+outputs/preflight/000015.1252923272.png: old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+outputs/preflight/000016.2633891320.png: old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+outputs/preflight/000017.1134411920.png: old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+outputs/preflight/000018.47.png: big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000019.47.png: big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000020.47.png: big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000021.47.png: big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000022.47.png: dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000023.47.png: dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+outputs/preflight/000024.1029061431.png: medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+outputs/preflight/000025.1284519352.png: bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+outputs/preflight/curly.942491079.gfpgan.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -G 0.8 -ft gfpgan -U 2.0 0.75
+outputs/preflight/curly.942491079.outcrop.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64
+outputs/preflight/curly.942491079.outpaint.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -D top 64
+outputs/preflight/curly.942491079.outcrop-01.png: !fix ./docs/assets/preflight-checks/inputs/curly.png -s 50 -S 942491079 -W 512 -H 512 -C 7.5 -A k_lms -c top 64

docs/assets/preflight-checks/preflight_prompts.txt

@@ -0,0 +1,61 @@
+# outputs/preflight/000001.1863159593.png
+banana sushi -s 50 -S 1863159593 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000002.1151955949.png
+banana sushi -s 50 -S 1151955949 -W 512 -H 512 -C 7.5 -A plms
+# outputs/preflight/000003.2736230502.png
+banana sushi -s 50 -S 2736230502 -W 512 -H 512 -C 7.5 -A ddim
+# outputs/preflight/000004.42.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000005.42.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000006.478163327.png
+banana sushi -s 50 -S 478163327 -W 640 -H 448 -C 7.5 -A k_lms
+# outputs/preflight/000007.2407640369.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2407640369:0.1
+# outputs/preflight/000007.2772421987.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 2772421987:0.1
+# outputs/preflight/000007.3532317557.png
+banana sushi -s 50 -S 42 -W 512 -H 512 -C 7.5 -A k_lms -V 3532317557:0.1
+# outputs/preflight/000008.2028635318.png
+banana sushi -s 50 -S 2028635318 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000009.1111168647.png
+pond with waterlillies -s 50 -S 1111168647 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000010.1476370516.png
+pond with waterlillies -s 50 -S 1476370516 -W 512 -H 512 -C 7.5 -A k_lms --seamless
+# outputs/preflight/000011.4281108706.png
+banana sushi -s 50 -S 4281108706 -W 960 -H 960 -C 7.5 -A k_lms
+# outputs/preflight/000012.2396987386.png
+old sea captain with crow on shoulder -s 50 -S 2396987386 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_lms -f 0.75
+# outputs/preflight/000013.1252923272.png
+old sea captain with crow on shoulder -s 50 -S 1252923272 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512-transparent.png -A k_lms -f 0.75
+# outputs/preflight/000014.2633891320.png
+old sea captain with crow on shoulder -s 50 -S 2633891320 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A plms -f 0.75
+# outputs/preflight/000015.1134411920.png
+old sea captain with crow on shoulder -s 50 -S 1134411920 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/Lincoln-and-Parrot-512.png -A k_euler_a -f 0.75
+# outputs/preflight/000016.42.png
+big red dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000017.42.png
+big red++++ dog playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000018.42.png
+big red dog playing with cat+++ -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000019.42.png
+big (red dog).swap(tiger) playing with cat -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000020.42.png
+dog:1,cat:2 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000021.42.png
+dog:2,cat:1 -s 50 -S 47 -W 512 -H 512 -C 7.5 -A k_lms
+# outputs/preflight/000022.1029061431.png
+medusa with cobras -s 50 -S 1029061431 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm hair
+# outputs/preflight/000023.1284519352.png
+bearded man -s 50 -S 1284519352 -W 512 -H 512 -C 7.5 -I docs/assets/preflight-checks/inputs/curly.png -A k_lms -f 0.75 -tm face
+# outputs/preflight/000024.curly.hair.deselected.png
+!mask -I docs/assets/preflight-checks/inputs/curly.png -tm hair
+# outputs/preflight/curly.942491079.gfpgan.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -U2 -G0.8
+# outputs/preflight/curly.942491079.outcrop.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -c top 64
+# outputs/preflight/curly.942491079.outpaint.png
+!fix ./docs/assets/preflight-checks/inputs/curly.png -D top 64
+# outputs/preflight/curly.942491079.outcrop-01.png
+!switch inpainting-1.5
+!fix ./docs/assets/preflight-checks/inputs/curly.png -c top 64