Path->str in call to expand_prompts

- Previous PR to truncate long filenames won't work on windows due to
lack of support for os.pathconf(). This works around the limitation by
hardcoding the value for PC_NAME_MAX when pathconf is unavailable.
- The `multiprocessing` send() and recv() methods weren't working
properly on Windows due to issues involving `utf-8` encoding and
pickling/unpickling. Changed these calls to `send_bytes()` and
`recv_bytes()` , which seems to fix the issue.

Not fully tested on Windows since I lack a GPU machine to test on, but
is working on CPU.

.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit='.env/*'
+source='.'
+
+[report]
+show_missing = true

.dockerignore

@@ -1,3 +1,25 @@
+# use this file as a whitelist
 *
-!environment*.yml
-!docker-build
+!invokeai
+!ldm
+!pyproject.toml
+
+# Guard against pulling in any models that might exist in the directory tree
+**/*.pt*
+**/*.ckpt
+
+# ignore frontend but whitelist dist
+invokeai/frontend/
+!invokeai/frontend/dist/
+
+# ignore invokeai/assets but whitelist invokeai/assets/web
+invokeai/assets/
+!invokeai/assets/web/
+
+# Byte-compiled / optimized / DLL files
+**/__pycache__/
+**/*.py[cod]
+
+# Distribution / packaging
+*.egg-info/
+*.egg

.editorconfig

@@ -0,0 +1,30 @@
+root = true
+
+# All files
+[*]
+max_line_length = 80
+charset = utf-8
+end_of_line = lf
+indent_size = 2
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+# Python
+[*.py]
+indent_size = 4
+max_line_length = 120
+
+# css
+[*.css]
+indent_size = 4
+
+# flake8
+[.flake8]
+indent_size = 4
+
+# Markdown MkDocs
+[docs/**/*.md]
+max_line_length = 80
+indent_size = 4
+indent_style = unset

.flake8

@@ -0,0 +1,37 @@
+[flake8]
+max-line-length = 120
+extend-ignore =
+    # See https://github.com/PyCQA/pycodestyle/issues/373
+    E203,
+    # use Bugbear's B950 instead
+    E501,
+    # from black repo https://github.com/psf/black/blob/main/.flake8
+    E266, W503, B907
+extend-select =
+    # Bugbear line length
+    B950
+extend-exclude =
+    scripts/orig_scripts/*
+    ldm/models/*
+    ldm/modules/*
+    ldm/data/*
+    ldm/generate.py
+    ldm/util.py
+    ldm/simplet2i.py
+per-file-ignores =
+    # B950 line too long
+    # W605 invalid escape sequence
+    # F841 assigned to but never used
+    # F401 imported but unused
+    tests/test_prompt_parser.py: B950, W605, F401
+    tests/test_textual_inversion.py: F841, B950
+    # B023 Function definition does not bind loop variable
+    scripts/legacy_api.py: F401, B950, B023, F841
+    ldm/invoke/__init__.py: F401
+    # B010 Do not call setattr with a constant attribute value
+    ldm/invoke/server_legacy.py: B010
+# =====================
+# flake-quote settings:
+# =====================
+# Set this to match black style:
+inline-quotes = double

.gitattributes

@@ -1,4 +1,4 @@
 # Auto normalizes line endings on commit so devs don't need to change local settings.
-# Only affects text files and ignores other file types. 
+# Only affects text files and ignores other file types.
 # For more info see: https://www.aleksandrhovhannisyan.com/blog/crlf-vs-lf-normalizing-line-endings-in-git/
 * text=auto

.github/CODEOWNERS

@@ -1,5 +1,61 @@
-ldm/invoke/pngwriter.py @CapableWeb
-ldm/invoke/server_legacy.py @CapableWeb
-scripts/legacy_api.py @CapableWeb
-tests/legacy_tests.sh @CapableWeb
-installer/ @tildebyte
+# continuous integration
+/.github/workflows/ @mauwii @lstein @blessedcoolant
+
+# documentation
+/docs/ @lstein @mauwii @blessedcoolant
+mkdocs.yml @mauwii @lstein
+
+# installation and configuration
+/pyproject.toml @mauwii @lstein @ebr
+/docker/ @mauwii
+/scripts/ @ebr @lstein @blessedcoolant
+/installer/ @ebr @lstein 
+ldm/invoke/config @lstein @ebr
+invokeai/assets @lstein @blessedcoolant
+invokeai/configs @lstein @ebr  @blessedcoolant
+/ldm/invoke/_version.py @lstein @blessedcoolant
+
+# web ui
+/invokeai/frontend @blessedcoolant @psychedelicious
+/invokeai/backend @blessedcoolant @psychedelicious
+
+# generation and model management
+/ldm/*.py @lstein @blessedcoolant
+/ldm/generate.py @lstein @keturn
+/ldm/invoke/args.py @lstein @blessedcoolant
+/ldm/invoke/ckpt* @lstein @blessedcoolant
+/ldm/invoke/ckpt_generator @lstein @blessedcoolant
+/ldm/invoke/CLI.py @lstein @blessedcoolant
+/ldm/invoke/config @lstein @ebr @mauwii @blessedcoolant
+/ldm/invoke/generator @keturn @damian0815
+/ldm/invoke/globals.py @lstein @blessedcoolant 
+/ldm/invoke/merge_diffusers.py @lstein @blessedcoolant
+/ldm/invoke/model_manager.py @lstein @blessedcoolant
+/ldm/invoke/txt2mask.py @lstein @blessedcoolant
+/ldm/invoke/patchmatch.py @Kyle0654 @lstein
+/ldm/invoke/restoration @lstein @blessedcoolant
+
+# attention, textual inversion, model configuration
+/ldm/models @damian0815 @keturn @blessedcoolant
+/ldm/modules/textual_inversion_manager.py @lstein @blessedcoolant
+/ldm/modules/attention.py @damian0815 @keturn
+/ldm/modules/diffusionmodules @damian0815 @keturn
+/ldm/modules/distributions @damian0815 @keturn
+/ldm/modules/ema.py  @damian0815 @keturn
+/ldm/modules/embedding_manager.py @lstein
+/ldm/modules/encoders @damian0815 @keturn
+/ldm/modules/image_degradation @damian0815 @keturn
+/ldm/modules/losses  @damian0815 @keturn
+/ldm/modules/x_transformer.py @damian0815 @keturn
+
+# Nodes
+apps/ @Kyle0654 @jpphoto
+
+# legacy REST API
+# these are dead code
+#/ldm/invoke/pngwriter.py @CapableWeb
+#/ldm/invoke/server_legacy.py @CapableWeb
+#/scripts/legacy_api.py @CapableWeb
+#/tests/legacy_tests.sh @CapableWeb
+
+

.github/workflows/build-container.yml

@@ -1,48 +1,111 @@
-# 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'
+      - 'update/ci/docker/*'
+      - 'update/docker/*'
+    paths:
+      - 'pyproject.toml'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
+      - 'docker/Dockerfile'
+    tags:
+      - 'v*.*.*'
+  workflow_dispatch:
+
 
 jobs:
   docker:
+    if: github.event.pull_request.draft == false
     strategy:
       fail-fast: false
       matrix:
-        arch:
-          - x86_64
-          - aarch64
+        flavor:
+          - amd
+          - cuda
+          - cpu
         include:
-          - arch: x86_64
-            conda-env-file: environment-lin-cuda.yml
-          - arch: aarch64
-            conda-env-file: environment-lin-aarch64.yml
+          - flavor: amd
+            pip-extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+          - flavor: cuda
+            pip-extra-index-url: ''
+          - flavor: cpu
+            pip-extra-index-url: 'https://download.pytorch.org/whl/cpu'
     runs-on: ubuntu-latest
-    name: ${{ matrix.arch }}
+    name: ${{ matrix.flavor }}
+    env:
+      PLATFORMS: 'linux/amd64,linux/arm64'
+      DOCKERFILE: 'docker/Dockerfile'
     steps:
-      - name: prepare docker-tag
-        env:
-          repository: ${{ github.repository }}
-        run: echo "dockertag=${repository,,}" >> $GITHUB_ENV
       - name: Checkout
         uses: actions/checkout@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          images: |
+            ghcr.io/${{ github.repository }}
+            ${{ vars.DOCKERHUB_REPOSITORY }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+            type=sha,enable=true,prefix=sha-,format=short
+          flavor: |
+            latest=${{ matrix.flavor == 'cuda' && github.ref == 'refs/heads/main' }}
+            suffix=-${{ matrix.flavor }},onlatest=false
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
+        with:
+          platforms: ${{ env.PLATFORMS }}
+
+      - name: Login to GitHub Container Registry
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Login to Docker Hub
+        if: github.event_name != 'pull_request' && vars.DOCKERHUB_REPOSITORY != ''
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
       - name: Build container
-        uses: docker/build-push-action@v3
+        id: docker_build
+        uses: docker/build-push-action@v4
         with:
           context: .
-          file: docker-build/Dockerfile
-          platforms: Linux/${{ matrix.arch }}
-          push: false
-          tags: ${{ env.dockertag }}:${{ matrix.arch }}
-          build-args: |
-            conda_env_file=${{ matrix.conda-env-file }}
-            conda_version=py39_4.12.0-Linux-${{ matrix.arch }}
-            invokeai_git=${{ github.repository }}
-            invokeai_branch=${{ github.ref_name }}
+          file: ${{ env.DOCKERFILE }}
+          platforms: ${{ env.PLATFORMS }}
+          push: ${{ github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: PIP_EXTRA_INDEX_URL=${{ matrix.pip-extra-index-url }}
+          cache-from: |
+            type=gha,scope=${{ github.ref_name }}-${{ matrix.flavor }}
+            type=gha,scope=main-${{ matrix.flavor }}
+          cache-to: type=gha,mode=max,scope=${{ github.ref_name }}-${{ matrix.flavor }}
+
+      - name: Docker Hub Description
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' && vars.DOCKERHUB_REPOSITORY != ''
+        uses: peter-evans/dockerhub-description@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: ${{ vars.DOCKERHUB_REPOSITORY }}
+          short-description: ${{ github.event.repository.description }}

.github/workflows/clean-caches.yml

@@ -0,0 +1,34 @@
+name: cleanup caches by a branch
+on:
+  pull_request:
+    types:
+      - closed
+  workflow_dispatch:
+
+jobs:
+  cleanup:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+
+      - name: Cleanup
+        run: |
+          gh extension install actions/gh-actions-cache
+
+          REPO=${{ github.repository }}
+          BRANCH=${{ github.ref }}
+
+          echo "Fetching list of cache key"
+          cacheKeysForPR=$(gh actions-cache list -R $REPO -B $BRANCH | cut -f 1 )
+
+          ## Setting this to not fail the workflow while deleting cache keys.
+          set +e
+          echo "Deleting caches..."
+          for cacheKey in $cacheKeysForPR
+          do
+              gh actions-cache delete $cacheKey -R $REPO -B $BRANCH --confirm
+          done
+          echo "Done"
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/lint-frontend.yml

@@ -0,0 +1,29 @@
+name: Lint frontend
+
+on:
+  pull_request:
+    paths:
+      - 'invokeai/frontend/**'
+  push:
+    paths:
+      - 'invokeai/frontend/**'
+
+defaults:
+  run:
+    working-directory: invokeai/frontend
+
+jobs:
+  lint-frontend:
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Setup Node 18
+        uses: actions/setup-node@v3
+        with:
+          node-version: '18'
+      - uses: actions/checkout@v3
+      - run: 'yarn install --frozen-lockfile'
+      - run: 'yarn tsc'
+      - run: 'yarn run madge'
+      - run: 'yarn run lint --max-warnings=0'
+      - run: 'yarn run prettier --check'

.github/workflows/mkdocs-material.yml

@@ -7,7 +7,12 @@ on:
 
 jobs:
   mkdocs-material:
+    if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
+    env:
+      REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
+      REPO_NAME: '${{ github.repository }}'
+      SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
     steps:
       - name: checkout sources
         uses: actions/checkout@v3
@@ -18,11 +23,15 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
 
       - name: install requirements
+        env:
+          PIP_USE_PEP517: 1
         run: |
           python -m \
-            pip install -r requirements-mkdocs.txt
+            pip install ".[docs]"
 
       - name: confirm buildability
         run: |

.github/workflows/pyflakes.yml

@@ -0,0 +1,20 @@
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+      - development
+      - 'release-candidate-*'
+
+jobs:
+  pyflakes:
+    name: runner / pyflakes
+    if: github.event.pull_request.draft == false
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: pyflakes
+        uses: reviewdog/action-pyflakes@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          reporter: github-pr-review

.github/workflows/pypi-release.yml

@@ -0,0 +1,41 @@
+name: PyPI Release
+
+on:
+  push:
+    paths:
+      - 'ldm/invoke/_version.py'
+  workflow_dispatch:
+
+jobs:
+  release:
+    if: github.repository == 'invoke-ai/InvokeAI'
+    runs-on: ubuntu-22.04
+    env:
+      TWINE_USERNAME: __token__
+      TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+      TWINE_NON_INTERACTIVE: 1
+    steps:
+      - name: checkout sources
+        uses: actions/checkout@v3
+
+      - name: install deps
+        run: pip install --upgrade build twine
+
+      - name: build package
+        run: python3 -m build
+
+      - name: check distribution
+        run: twine check dist/*
+
+      - name: check PyPI versions
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3'
+        run: |
+          pip install --upgrade requests
+          python -c "\
+          import scripts.pypi_helper; \
+          EXISTS=scripts.pypi_helper.local_on_pypi(); \
+          print(f'PACKAGE_EXISTS={EXISTS}')" >> $GITHUB_ENV
+
+      - name: upload package
+        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != ''
+        run: twine upload dist/*

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

@@ -1,126 +0,0 @@
-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-lin-cuda.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: ${{ matrix.default-shell }}
-    steps:
-      - name: Checkout sources
-        id: checkout-sources
-        uses: actions/checkout@v3
-
-      - name: create models.yaml from example
-        run: cp configs/models.yaml.example configs/models.yaml
-
-      - name: create environment.yml
-        run: cp environments-and-requirements/${{ matrix.environment-file }} environment.yml
-
-      - 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: environment.yml
-          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" >> $GITHUB_ENV
-
-      - name: Use Cached Stable Diffusion Model
-        id: cache-sd-model
-        uses: actions/cache@v3
-        env:
-          cache-name: cache-${{ matrix.stable-diffusion-model-switch }}
-        with:
-          path: ${{ matrix.stable-diffusion-model-dl-path }}
-          key: ${{ env.cache-name }}
-
-      - name: Download ${{ matrix.stable-diffusion-model-switch }}
-        id: download-stable-diffusion-model
-        if: ${{ steps.cache-sd-model.outputs.cache-hit != 'true' }}
-        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

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

@@ -0,0 +1,67 @@
+name: Test invoke.py pip
+on:
+  pull_request:
+    paths-ignore:
+      - 'pyproject.toml'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
+  merge_group:
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  matrix:
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        python-version:
+          # - '3.9'
+          - '3.10'
+        pytorch:
+          # - linux-cuda-11_6
+          - linux-cuda-11_7
+          - linux-rocm-5_2
+          - linux-cpu
+          - macos-default
+          - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
+        include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
+          - pytorch: linux-cuda-11_7
+            os: ubuntu-22.04
+            github-env: $GITHUB_ENV
+          - pytorch: linux-rocm-5_2
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+            github-env: $GITHUB_ENV
+          - pytorch: linux-cpu
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/cpu'
+            github-env: $GITHUB_ENV
+          - pytorch: macos-default
+            os: macOS-12
+            github-env: $GITHUB_ENV
+          - pytorch: windows-cpu
+            os: windows-2022
+            github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
+    name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
+    runs-on: ${{ matrix.os }}
+    steps:
+      - run: 'echo "No build required"'

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

@@ -0,0 +1,148 @@
+name: Test invoke.py pip
+on:
+  push:
+    branches:
+      - 'main'
+    paths:
+      - 'pyproject.toml'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
+  pull_request:
+    paths:
+      - 'pyproject.toml'
+      - 'ldm/**'
+      - 'invokeai/backend/**'
+      - 'invokeai/configs/**'
+      - 'invokeai/frontend/dist/**'
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  matrix:
+    if: github.event.pull_request.draft == false
+    strategy:
+      matrix:
+        python-version:
+          # - '3.9'
+          - '3.10'
+        pytorch:
+          # - linux-cuda-11_6
+          - linux-cuda-11_7
+          - linux-rocm-5_2
+          - linux-cpu
+          - macos-default
+          - windows-cpu
+          # - windows-cuda-11_6
+          # - windows-cuda-11_7
+        include:
+          # - pytorch: linux-cuda-11_6
+          #   os: ubuntu-22.04
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $GITHUB_ENV
+          - pytorch: linux-cuda-11_7
+            os: ubuntu-22.04
+            github-env: $GITHUB_ENV
+          - pytorch: linux-rocm-5_2
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+            github-env: $GITHUB_ENV
+          - pytorch: linux-cpu
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/cpu'
+            github-env: $GITHUB_ENV
+          - pytorch: macos-default
+            os: macOS-12
+            github-env: $GITHUB_ENV
+          - pytorch: windows-cpu
+            os: windows-2022
+            github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_6
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
+          #   github-env: $env:GITHUB_ENV
+          # - pytorch: windows-cuda-11_7
+          #   os: windows-2022
+          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
+          #   github-env: $env:GITHUB_ENV
+    name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
+    runs-on: ${{ matrix.os }}
+    env:
+      PIP_USE_PEP517: '1'
+    steps:
+      - name: Checkout sources
+        id: checkout-sources
+        uses: actions/checkout@v3
+
+      - name: set test prompt to main branch validation
+        if: ${{ github.ref == 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
+
+      - name: set test prompt to Pull Request validation
+        if: ${{ github.ref != 'refs/heads/main' }}
+        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
+
+      - name: setup python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install invokeai
+        env:
+          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
+        run: >
+          pip3 install
+          --editable=".[test]"
+
+      - name: run pytest
+        id: run-pytest
+        run: pytest
+
+      - name: set INVOKEAI_OUTDIR
+        run: >
+          python -c
+          "import os;from ldm.invoke.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
+          >> ${{ matrix.github-env }}
+
+      - name: run invokeai-configure
+        id: run-preload-models
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
+        run: >
+          invokeai-configure
+          --yes
+          --default_only
+          --full-precision
+        # can't use fp16 weights without a GPU
+
+      - name: run invokeai
+        id: run-invokeai
+        env:
+          # Set offline mode to make sure configure preloaded successfully.
+          HF_HUB_OFFLINE: 1
+          HF_DATASETS_OFFLINE: 1
+          TRANSFORMERS_OFFLINE: 1
+        run: >
+          invokeai
+          --no-patchmatch
+          --no-nsfw_checker
+          --from_file ${{ env.TEST_PROMPTS }}
+          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+
+      - name: Archive results
+        id: archive-results
+        uses: actions/upload-artifact@v3
+        with:
+          name: results
+          path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -1,4 +1,6 @@
 # ignore default image save location and model symbolic link
+.idea/
+embeddings/
 outputs/
 models/ldm/stable-diffusion-v1/model.ckpt
 **/restoration/codeformer/weights
@@ -6,6 +8,7 @@ models/ldm/stable-diffusion-v1/model.ckpt
 # ignore user models config
 configs/models.user.yaml
 config/models.user.yml
+invokeai.init
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -65,11 +68,13 @@ htmlcov/
 .cache
 nosetests.xml
 coverage.xml
+cov.xml
 *.cover
 *.py,cover
 .hypothesis/
 .pytest_cache/
 cover/
+junit/
 
 # Translations
 *.mo
@@ -193,11 +198,7 @@ checkpoints
 .DS_Store
 
 # Let the frontend manage its own gitignore
-!frontend/*
-frontend/apt-get
-frontend/dist
-frontend/sudo
-frontend/update
+!invokeai/frontend/*
 
 # Scratch folder
 .scratch/
@@ -218,7 +219,7 @@ models/clipseg
 models/gfpgan
 
 # ignore initfile
-invokeai.init
+.invokeai
 
 # ignore environment.yml and requirements.txt
 # these are links to the real files in environments-and-requirements
@@ -226,12 +227,11 @@ environment.yml
 requirements.txt
 
 # source installer files
-source_installer/*zip
-source_installer/invokeAI
-install.bat
-install.sh
-update.bat
-update.sh
+installer/*zip
+installer/install.bat
+installer/install.sh
+installer/update.bat
+installer/update.sh
 
-# this may be present if the user created a venv
-invokeai
+# no longer stored in source directory
+models

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/psf/black
+    rev: 23.1.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        additional_dependencies:
+          - flake8-black
+          - flake8-bugbear
+          - flake8-comprehensions
+          - flake8-simplify
+
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: 'v3.0.0-alpha.4'
+    hooks:
+      - id: prettier
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: check-toml
+      - id: end-of-file-fixer
+      - id: no-commit-to-branch
+        args: ['--branch', 'main']
+      - id: trailing-whitespace

.prettierignore

@@ -0,0 +1,14 @@
+invokeai/frontend/.husky
+invokeai/frontend/patches
+
+# Ignore artifacts:
+build
+coverage
+static
+invokeai/frontend/dist
+
+# Ignore all HTML files:
+*.html
+
+# Ignore deprecated docs
+docs/installation/deprecated_documentation

.prettierrc.yaml

@@ -1,9 +1,9 @@
-endOfLine: lf
-tabWidth: 2
-useTabs: false
-singleQuote: true
-quoteProps: as-needed
 embeddedLanguageFormatting: auto
+endOfLine: lf
+singleQuote: true
+semi: true
+trailingComma: es5
+useTabs: false
 overrides:
   - files: '*.md'
     options:
@@ -11,3 +11,9 @@ overrides:
       printWidth: 80
       parser: markdown
       cursorOffset: -1
+  - files: docs/**/*.md
+    options:
+      tabWidth: 4
+  - files: 'invokeai/frontend/public/locales/*.json'
+    options:
+      tabWidth: 4

.pytest.ini

@@ -0,0 +1,5 @@
+[pytest]
+DJANGO_SETTINGS_MODULE = webtas.settings
+; python_files = tests.py test_*.py *_tests.py
+
+addopts = --cov=. --cov-config=.coveragerc --cov-report xml:cov.xml

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior
+may be reported to the community leaders responsible for enforcement
+at https://github.com/invoke-ai/InvokeAI/issues.  All complaints will
+be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

InvokeAI_Statement_of_Values.md

@@ -0,0 +1,84 @@
+<img src="docs/assets/invoke_ai_banner.png" align="center">
+
+Invoke-AI is a community of software developers, researchers, and user
+interface experts who have come together on a voluntary basis to build
+software tools which support cutting edge AI text-to-image
+applications. This community is open to anyone who wishes to
+contribute to the effort and has the skill and time to do so.
+
+# Our Values
+
+The InvokeAI team is a diverse community which includes individuals
+from various parts of the world and many walks of life. Despite our
+differences, we share a number of core values which we ask prospective
+contributors to understand and respect. We believe:
+
+1. That Open Source Software is a positive force in the world. We
+create software that can be used, reused, and redistributed, without
+restrictions, under a straightforward Open Source license (MIT). We
+believe that Open Source benefits society as a whole by increasing the
+availability of high quality software to all.
+
+2. That those who create software should receive proper attribution
+for their creative work. While we support the exchange and reuse of
+Open Source Software, we feel strongly that the original authors of a
+piece of code should receive credit for their contribution, and we
+endeavor to do so whenever possible.
+
+3. That there is moral ambiguity surrounding AI-assisted art. We are
+aware of the moral and ethical issues surrounding the release of the
+Stable Diffusion model and similar products. We are aware that, due to
+the composition of their training sets, current AI-generated image
+models are biased against certain ethnic groups, cultural concepts of
+beauty, ethnic stereotypes, and gender roles.
+
+      1. We recognize the potential for harm to these groups that these biases
+       represent and trust that future AI models will take steps towards
+       reducing or eliminating the biases noted above, respect and give due
+       credit to the artists whose work is sourced, and call on developers
+       and users to favor these models over the older ones as they become
+       available.
+
+4. We are deeply committed to ensuring that this technology benefits
+everyone, including artists. We see AI art not as a replacement for
+the artist, but rather as a tool to empower them. With that
+in mind, we are constantly debating how to build systems that put
+artists’ needs first: tools which can be readily integrated into an
+artist’s existing workflows and practices, enhancing their work and
+helping them to push it further. Every decision we take as a team,
+which includes several artists, aims to build towards that goal.
+
+5. That artificial intelligence can be a force for good in the world,
+but must be used responsibly. Artificial intelligence technologies
+have the potential to improve society, in everything from cancer care,
+to customer service, to creative writing.
+
+     1. While we do not believe that software should arbitrarily limit what
+     users can do with it, we recognize that when used irresponsibly, AI
+     has the potential to do much harm. Our Discord server is actively
+     moderated in order to minimize the potential of harm from
+     user-contributed images. In addition, we ask users of our software to
+     refrain from using it in any way that would cause mental, emotional or
+     physical harm to individuals and vulnerable populations including (but
+     not limited to) women; minors; ethnic minorities; religious groups;
+     members of LGBTQIA communities; and people with disabilities or
+     impairments.
+
+     2. Note that some of the image generation AI models which the Invoke-AI
+     toolkit supports carry licensing agreements which impose restrictions
+     on how the model is used. We ask that our users read and agree to
+     these terms if they wish to make use of these models. These agreements
+     are distinct from the MIT license which applies to the InvokeAI
+     software and source code.
+
+6. That mutual respect is key to a healthy software development
+community. Members of the InvokeAI community are expected to treat
+each other with respect, beneficence, and empathy. Each of us has a
+different background and a unique set of skills. We strive to help
+each other grow and gain new skills, and we apportion expectations in
+a way that balances the members' time, skillset, and interest
+area. Disputes are resolved by open and honest communication.
+
+## Signature
+
+This document has been collectively crafted and approved by the current InvokeAI team members, as of 28 Nov 2022: **lstein** (Lincoln Stein), **blessedcoolant**, **hipsterusername** (Kent Keirsey), **Kyle0654** (Kyle Schouviller), **damian0815**, **mauwii** (Matthias Wild), **Netsvetaev** (Artur Netsvetaev), **psychedelicious**, **tildebyte**, **keturn**, and **ebr** (Eugene Brodsky). Although individuals within the group may hold differing views on particular details and/or their implications, we are all in agreement about its fundamental statements, as well as their significance and importance to this project moving forward.

README.md

@@ -1,23 +1,19 @@
 <div align="center">
 
+![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
+
 # InvokeAI: A Stable Diffusion Toolkit
 
-_Formerly known as lstein/stable-diffusion_
-
-![project logo](docs/assets/logo.png)
-
 [![discord badge]][discord link]
 
 [![latest release badge]][latest release link] [![github stars badge]][github stars link] [![github forks badge]][github forks link]
 
-[![CI checks on main badge]][CI checks on main link] [![CI checks on dev badge]][CI checks on dev link] [![latest commit to dev badge]][latest commit to dev link]
+[![CI checks on main badge]][CI checks on main link] [![latest commit to main badge]][latest commit to main link]
 
-[![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link]
+[![github open issues badge]][github open issues link] [![github open prs badge]][github open prs link] [![translation status badge]][translation status link]
 
-[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-invoke-conda.yml
+[CI checks on main link]:https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Amain
 [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
@@ -28,161 +24,252 @@ _Formerly known as lstein/stable-diffusion_
 [github open prs link]: https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
 [github stars badge]: https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
-[latest commit to dev badge]: https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
-[latest commit to dev link]: https://github.com/invoke-ai/InvokeAI/commits/development
+[latest commit to main badge]: https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/main?icon=github&color=yellow&label=last%20dev%20commit&cache=900
+[latest commit to main link]: https://github.com/invoke-ai/InvokeAI/commits/main
 [latest release badge]: https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
+[translation status badge]: https://hosted.weblate.org/widgets/invokeai/-/svg-badge.svg
+[translation status link]: https://hosted.weblate.org/engage/invokeai/
+
 </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, 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.
+InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
-**Quick links**: [<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>]
+**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
 
-<div align="center"><img src="docs/assets/invoke-web-server-1.png" width=640></div>
-
-
-_Note: This fork is rapidly evolving. Please use the
+_Note: InvokeAI is rapidly evolving. Please use the
 [Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
-requests. Be sure to use the provided templates. They will help aid diagnose issues faster._
+requests. Be sure to use the provided templates. They will help us diagnose issues faster._
+
+<div align="center">
+
+![canvas preview](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/canvas_preview.png)
+
+</div>
 
 ## Table of Contents
 
-1. [Installation](#installation)
-2. [Hardware Requirements](#hardware-requirements)
-3. [Features](#features)
-4. [Latest Changes](#latest-changes)
-5. [Troubleshooting](#troubleshooting)
-6. [Contributing](#contributing)
-7. [Contributors](#contributors)
-8. [Support](#support)
-9. [Further Reading](#further-reading)
+1. [Quick Start](#getting-started-with-invokeai)
+2. [Installation](#detailed-installation-instructions)
+3. [Hardware Requirements](#hardware-requirements)
+4. [Features](#features)
+5. [Latest Changes](#latest-changes)
+6. [Troubleshooting](#troubleshooting)
+7. [Contributing](#contributing)
+8. [Contributors](#contributors)
+9. [Support](#support)
+10. [Further Reading](#further-reading)
 
-### Installation
+## Getting Started with InvokeAI
 
-This fork is supported across multiple platforms. You can find individual installation instructions
-below.
+For full installation and upgrade instructions, please see:
+[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
-- #### [Linux](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_LINUX/)
+### Automatic Installer (suggested for 1st time users)
 
-- #### [Windows](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_WINDOWS/)
+1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
 
-- #### [Macintosh](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_MAC/)
+2. Download the .zip file for your OS (Windows/macOS/Linux).
 
-### Hardware Requirements
+3. Unzip the file.
 
-#### System
+4. If you are on Windows, double-click on the `install.bat` script. On
+macOS, open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. On Linux, run `install.sh`.
 
-You wil need one of the following:
+5. You'll be asked to confirm the location of the folder in which
+to install InvokeAI and its image generation model files. Pick a
+location with at least 15 GB of free memory. More if you plan on
+installing lots of models.
+
+6. Wait while the installer does its thing. After installing the software,
+the installer will launch a script that lets you configure InvokeAI and
+select a set of starting image generaiton models.
+
+7. Find the folder that InvokeAI was installed into (it is not the
+same as the unpacked zip file directory!) The default location of this
+folder (if you didn't change it in step 5) is `~/invokeai` on
+Linux/Mac systems, and `C:\Users\YourName\invokeai` on Windows. This directory will contain launcher scripts named `invoke.sh` and `invoke.bat`.
+
+8. On Windows systems, double-click on the `invoke.bat` file. On
+macOS, open a Terminal window, drag `invoke.sh` from the folder into
+the Terminal, and press return. On Linux, run `invoke.sh`
+
+9. Press 2 to open the "browser-based UI", press enter/return, wait a
+minute or two for Stable Diffusion to start up, then open your browser
+and go to http://localhost:9090.
+
+10. Type `banana sushi` in the box on the top left and click `Invoke`
+
+### Command-Line Installation (for users familiar with Terminals)
+
+You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
+not supported.
+
+1. Open a command-line window on your machine. The PowerShell is recommended for Windows.
+2. Create a directory to install InvokeAI into. You'll need at least 15 GB of free space:
+
+    ```terminal
+    mkdir invokeai
+    ````
+
+3. Create a virtual environment named `.venv` inside this directory and activate it:
+
+    ```terminal
+    cd invokeai
+    python -m venv .venv --prompt InvokeAI
+    ```
+
+4. Activate the virtual environment (do it every time you run InvokeAI)
+
+    _For Linux/Mac users:_
+
+    ```sh
+    source .venv/bin/activate
+    ```
+
+    _For Windows users:_
+
+    ```ps
+    .venv\Scripts\activate
+    ```
+
+5. Install the InvokeAI module and its dependencies. Choose the command suited for your platform & GPU.
+
+    _For Windows/Linux with an NVIDIA GPU:_
+
+    ```terminal
+    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    ```
+
+    _For Linux with an AMD GPU:_
+
+    ```sh
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    ```
+
+    _For Macintoshes, either Intel or M1/M2:_
+
+    ```sh
+    pip install InvokeAI --use-pep517
+    ```
+
+6. Configure InvokeAI and install a starting set of image generation models (you only need to do this once):
+
+    ```terminal
+    invokeai-configure
+    ```
+
+7. Launch the web server (do it every time you run InvokeAI):
+
+    ```terminal
+    invokeai --web
+    ```
+
+8. Point your browser to http://localhost:9090 to bring up the web interface.
+9. Type `banana sushi` in the box on the top left and click `Invoke`.
+
+Be sure to activate the virtual environment each time before re-launching InvokeAI,
+using `source .venv/bin/activate` or `.venv\Scripts\activate`.
+
+### Detailed Installation Instructions
+
+This fork is supported across Linux, Windows and Macintosh. Linux
+users can use either an Nvidia-based card (with CUDA support) or an
+AMD card (using the ROCm driver). For full installation and upgrade
+instructions, please see:
+[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
+
+## Hardware Requirements
+
+InvokeAI is supported across Linux, Windows and macOS. Linux
+users can use either an Nvidia-based card (with CUDA support) or an
+AMD card (using the ROCm driver).
+
+### System
+
+You will need one of the following:
 
 - An NVIDIA-based graphics card with 4 GB or more VRAM memory.
 - An Apple computer with an M1 chip.
+- An AMD-based graphics card with 4GB or more VRAM memory. (Linux only)
 
-#### Memory
+We do not recommend the GTX 1650 or 1660 series video cards. They are
+unable to run in half-precision mode and do not have sufficient VRAM
+to render 512x512 images.
+
+### Memory
 
 - At least 12 GB Main Memory RAM.
 
-#### Disk
+### Disk
 
 - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
-**Note**
+## Features
 
-If you have a Nvidia 10xx series card (e.g. the 1080ti), please
-run the dream script in full-precision mode as shown below.
+Feature documentation can be reviewed by navigating to [the InvokeAI Documentation page](https://invoke-ai.github.io/InvokeAI/features/)
 
-Similarly, specify full-precision mode on Apple M1 hardware.
+### *Web Server & UI*
 
-Precision is auto configured based on the device. If however you encounter
-errors like 'expected type Float but found Half' or 'not implemented for Half'
-you can try starting `invoke.py` with the `--precision=float32` flag:
+InvokeAI offers a locally hosted Web Server & React Frontend, with an industry leading user experience. The Web-based UI allows for simple and intuitive workflows, and is responsive for use on mobile devices and tablets accessing the web server.
 
-```bash
-(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
-```
+### *Unified Canvas*
 
-### Features
+The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
 
-#### Major Features
+### *Advanced Prompt Syntax*
 
-- [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)
+InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
 
-#### Other Features
+### *Command Line Interface*
 
-- [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)
+For users utilizing a terminal-based environment, or who want to take advantage of CLI features, InvokeAI offers an extensive and actively supported command-line interface that provides the full suite of generation functionality available in the tool.
+
+### Other features
+
+- *Support for both ckpt and diffusers models*
+- *SD 2.0, 2.1 support*
+- *Noise Control & Tresholding*
+- *Popular Sampler Support*
+- *Upscaling & Face Restoration Tools*
+- *Embedding Manager & Support*
+- *Model Manager & Support*
+
+### Coming Soon
+
+- *Node-Based Architecture & UI*
+- And more...
 
 ### Latest Changes
 
-- 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)
+For our latest changes, view our [Release
+Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
+[CHANGELOG](docs/CHANGELOG.md).
 
-- 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`.
-
-For older changelogs, please visit the **[CHANGELOG](https://invoke-ai.github.io/InvokeAI/CHANGELOG#v114-11-september-2022)**.
-
-### Troubleshooting
+## Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
 
-# Contributing
+## Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
-cleanup, testing, or code reviews, is very much encouraged to do so. If you are unfamiliar with how
-to contribute to GitHub projects, here is a
-[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github).
+cleanup, testing, or code reviews, is very much encouraged to do so.
 
-A full set of contribution guidelines, along with templates, are in progress, but for now the most
-important thing is to **make your pull request against the "development" branch**, and not against
-"main". This will help keep public breakage to a minimum and will allow you to propose more radical
-changes.
+To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.
+
+If you'd like to help with translation, please see our [translation guide](docs/other/TRANSLATION.md).
+
+If you are unfamiliar with how
+to contribute to GitHub projects, here is a
+[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). A full set of contribution guidelines, along with templates, are in progress. You can **make your pull request against the "main" branch**.
+
+We hope you enjoy using our software as much as we enjoy creating it,
+and we hope that some of those of you who are reading this will elect
+to become part of our community.
+
+Welcome to InvokeAI!
 
 ### Contributors
 
@@ -190,15 +277,11 @@ This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
+Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
+
 ### Support
 
-For support, please use this repository's GitHub Issues tracking service. Feel free to send me an
-email if you use and like the script.
+For support, please use this repository's GitHub Issues tracking service, or join the Discord.
 
-Original portions of the software are Copyright (c) 2020
-[Lincoln D. Stein](https://github.com/lstein)
+Original portions of the software are Copyright (c) 2023 by respective contributors.
 
-### Further Reading
-
-Please see the original README for more information on this software and underlying algorithm,
-located in the file [README-CompViz.md](https://invoke-ai.github.io/InvokeAI/other/README-CompViz/).

Stable_Diffusion_v1_Model_Card.md

@@ -21,7 +21,7 @@ This model card focuses on the model associated with the Stable Diffusion model,
 
 # Uses
 
-## Direct Use 
+## Direct Use
 The model is intended for research purposes only. Possible research areas and
 tasks include
 
@@ -68,11 +68,11 @@ Using the model to generate content that is cruel to individuals is a misuse of
   considerations.
 
 ### Bias
-While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. 
-Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), 
-which consists of images that are primarily limited to English descriptions. 
-Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. 
-This affects the overall output of the model, as white and western cultures are often set as the default. Further, the 
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
+Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
+which consists of images that are primarily limited to English descriptions.
+Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
+This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
 ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
 
 
@@ -84,7 +84,7 @@ The model developers used the following dataset for training the model:
 - LAION-2B (en) and subsets thereof (see next section)
 
 **Training Procedure**
-Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
+Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
 
 - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
 - Text prompts are encoded through a ViT-L/14 text-encoder.
@@ -108,12 +108,12 @@ filtered to images with an original size `>= 512x512`, estimated aesthetics scor
 - **Batch:** 32 x 8 x 2 x 4 = 2048
 - **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
 
-## Evaluation Results 
+## Evaluation Results
 Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
 5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
 steps show the relative improvements of the checkpoints:
 
-![pareto](assets/v1-variants-scores.jpg) 
+![pareto](assets/v1-variants-scores.jpg)
 
 Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution.  Not optimized for FID scores.
 ## Environmental Impact

backend/modules/parameters.py

@@ -1,69 +0,0 @@
-from backend.modules.parse_seed_weights import parse_seed_weights
-import argparse
-
-SAMPLER_CHOICES = [
-    "ddim",
-    "k_dpm_2_a",
-    "k_dpm_2",
-    "k_euler_a",
-    "k_euler",
-    "k_heun",
-    "k_lms",
-    "plms",
-]
-
-
-def parameters_to_command(params):
-    """
-    Converts dict of parameters into a `invoke.py` REPL command.
-    """
-
-    switches = list()
-
-    if "prompt" in params:
-        switches.append(f'"{params["prompt"]}"')
-    if "steps" in params:
-        switches.append(f'-s {params["steps"]}')
-    if "seed" in params:
-        switches.append(f'-S {params["seed"]}')
-    if "width" in params:
-        switches.append(f'-W {params["width"]}')
-    if "height" in params:
-        switches.append(f'-H {params["height"]}')
-    if "cfg_scale" in params:
-        switches.append(f'-C {params["cfg_scale"]}')
-    if "sampler_name" in 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:
-        switches.append(f'-M {params["init_mask"]}')
-    if "init_color" in params and len(params["init_color"]) > 0:
-        switches.append(f'--init_color {params["init_color"]}')
-    if "strength" in params and "init_img" in params:
-        switches.append(f'-f {params["strength"]}')
-        if "fit" in params and params["fit"] == True:
-            switches.append(f"--fit")
-    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:
-        switches.append(f'-v {params["variation_amount"]}')
-        if "with_variations" in params:
-            seed_weight_pairs = ",".join(
-                f"{seed}:{weight}" for seed, weight in params["with_variations"]
-            )
-            switches.append(f"-V {seed_weight_pairs}")
-
-    return " ".join(switches)

configs/models.yaml.example

@@ -1,27 +0,0 @@
-# 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/stable-diffusion/v1-finetune.yaml

@@ -1,110 +0,0 @@
-model:
-  base_learning_rate: 5.0e-03
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: caption
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: true   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-    embedding_reg_weight: 0.0
-
-    personalization_config:
-      target: ldm.modules.embedding_manager.EmbeddingManager
-      params:
-        placeholder_strings: ["*"]
-        initializer_words: ["sculpture"]
-        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: 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: 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.FrozenCLIPEmbedder
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 1
-    num_workers: 2
-    wrap: false
-    train:
-      target: ldm.data.personalized.PersonalizedBase
-      params:
-        size: 512
-        set: train
-        per_image_tokens: false
-        repeats: 100
-    validation:
-      target: ldm.data.personalized.PersonalizedBase
-      params:
-        size: 512
-        set: val
-        per_image_tokens: false
-        repeats: 10
-
-lightning:
-  modelcheckpoint:
-    params:
-      every_n_train_steps: 500
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 500
-        max_images: 8
-        increase_log_steps: False
-
-  trainer:
-    benchmark: True
-    max_steps: 4000000
-#    max_steps: 4000
-    

configs/stable-diffusion/v1-inference.yaml

@@ -1,79 +0,0 @@
-model:
-  base_learning_rate: 1.0e-04
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  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: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 10000 ]
-        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: 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: 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

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

@@ -1,79 +0,0 @@
-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

configs/stable-diffusion/v1-m1-finetune.yaml

@@ -1,110 +0,0 @@
-model:
-  base_learning_rate: 5.0e-03
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: image
-    cond_stage_key: caption
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: true   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-    embedding_reg_weight: 0.0
-
-    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: 6
-        progressive_words: False
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32 # unused
-        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: 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.FrozenCLIPEmbedder
-
-data:
-  target: main.DataModuleFromConfig
-  params:
-    batch_size: 1
-    num_workers: 2
-    wrap: false
-    train:
-      target: ldm.data.personalized.PersonalizedBase
-      params:
-        size: 512
-        set: train
-        per_image_tokens: false
-        repeats: 100
-    validation:
-      target: ldm.data.personalized.PersonalizedBase
-      params:
-        size: 512
-        set: val
-        per_image_tokens: false
-        repeats: 10
-
-lightning:
-  modelcheckpoint:
-    params:
-      every_n_train_steps: 500
-  callbacks:
-    image_logger:
-      target: main.ImageLogger
-      params:
-        batch_frequency: 500
-        max_images: 5
-        increase_log_steps: False
-
-  trainer:
-    benchmark: False
-    max_steps: 6200
-#    max_steps: 4000
-    

docker-build/Dockerfile

@@ -1,84 +0,0 @@
-FROM ubuntu AS get_miniconda
-
-SHELL ["/bin/bash", "-c"]
-
-# install wget
-RUN apt-get update \
-  && apt-get install -y \
-    wget \
-  && apt-get clean \
-  && rm -rf /var/lib/apt/lists/*
-
-# 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
-
-FROM ubuntu AS invokeai
-
-# use bash
-SHELL [ "/bin/bash", "-c" ]
-
-# clean bashrc
-RUN echo "" > ~/.bashrc
-
-# 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/*
-
-# clone repository, create models.yaml and create symlinks
-ARG invokeai_git=invoke-ai/InvokeAI
-ARG invokeai_branch=main
-ARG project_name=invokeai
-ARG conda_env_file=environment-lin-cuda.yml
-RUN git clone -b ${invokeai_branch} https://github.com/${invokeai_git}.git "/${project_name}" \
-  && cp \
-    "/${project_name}/configs/models.yaml.example" \
-    "/${project_name}/configs/models.yaml" \
-  && ln -sf \
-    "/${project_name}/environments-and-requirements/${conda_env_file}" \
-    "/${project_name}/environment.yml" \
-  && ln -sf \
-    /data/models/v1-5-pruned-emaonly.ckpt \
-    "/${project_name}/models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt" \
-  && ln -sf \
-    /data/outputs/ \
-    "/${project_name}/outputs"
-
-# set workdir
-WORKDIR "/${project_name}"
-
-# install conda env and preload models
-ARG conda_prefix=/opt/conda
-COPY --from=get_miniconda "${conda_prefix}" "${conda_prefix}"
-RUN source "${conda_prefix}/etc/profile.d/conda.sh" \
-  && conda init bash \
-  && source ~/.bashrc \
-  && conda env create \
-    --name "${project_name}" \
-  && rm -Rf ~/.cache \
-  && conda clean -afy \
-  && echo "conda activate ${project_name}" >> ~/.bashrc
-
-RUN source ~/.bashrc \
-  && python scripts/preload_models.py \
-    --no-interactive
-
-# Copy entrypoint and set env
-ENV CONDA_PREFIX="${conda_prefix}"
-ENV PROJECT_NAME="${project_name}"
-COPY docker-build/entrypoint.sh /
-ENTRYPOINT [ "/entrypoint.sh" ]

docker-build/build.sh

@@ -1,84 +0,0 @@
-#!/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-lin-cuda.yml}
-invokeai_git=${INVOKEAI_GIT:-invoke-ai/InvokeAI}
-invokeai_branch=${INVOKEAI_BRANCH:-main}
-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 "downloading v1-5-pruned-emaonly.ckpt"
-  _runAlpine wget \
-    --header="Authorization: Bearer ${huggingface_token}" \
-    -O models/v1-5-pruned-emaonly.ckpt \
-    https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
-  echo "done"
-}
-
-_checkVolumeContent() {
-  _runAlpine ls -lhA /data/models
-}
-
-_getModelMd5s() {
-  _runAlpine  \
-    alpine sh -c "md5sum /data/models/*.ckpt"
-}
-
-if [[ -n "$(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="${invokeai_git}" \
-  --build-arg invokeai_branch="${invokeai_branch}" \
-  --file ./docker-build/Dockerfile \
-  .

docker-build/entrypoint.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-set -e
-
-source "${CONDA_PREFIX}/etc/profile.d/conda.sh"
-conda activate "${PROJECT_NAME}"
-
-python scripts/invoke.py \
-  ${@:---web --host=0.0.0.0}

docker-build/env.sh

@@ -1,13 +0,0 @@
-#!/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

@@ -1,15 +0,0 @@
-#!/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" ${1:+$@}

docker/Dockerfile

@@ -0,0 +1,103 @@
+# syntax=docker/dockerfile:1
+
+ARG PYTHON_VERSION=3.9
+##################
+##  base image  ##
+##################
+FROM python:${PYTHON_VERSION}-slim AS python-base
+
+LABEL org.opencontainers.image.authors="mauwii@outlook.de"
+
+# prepare for buildkit cache
+RUN rm -f /etc/apt/apt.conf.d/docker-clean \
+  && echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache
+
+# Install necessary packages
+RUN \
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    libgl1-mesa-glx=20.3.* \
+    libglib2.0-0=2.66.* \
+    libopencv-dev=4.5.*
+
+# set working directory and env
+ARG APPDIR=/usr/src
+ARG APPNAME=InvokeAI
+WORKDIR ${APPDIR}
+ENV PATH ${APPDIR}/${APPNAME}/bin:$PATH
+# Keeps Python from generating .pyc files in the container
+ENV PYTHONDONTWRITEBYTECODE 1
+# Turns off buffering for easier container logging
+ENV PYTHONUNBUFFERED 1
+# don't fall back to legacy build system
+ENV PIP_USE_PEP517=1
+
+#######################
+##  build pyproject  ##
+#######################
+FROM python-base AS pyproject-builder
+
+# Install dependencies
+RUN \
+  --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt,sharing=locked \
+  apt-get update \
+  && apt-get install -y \
+    --no-install-recommends \
+    build-essential=12.9 \
+    gcc=4:10.2.* \
+    python3-dev=3.9.*
+
+# prepare pip for buildkit cache
+ARG PIP_CACHE_DIR=/var/cache/buildkit/pip
+ENV PIP_CACHE_DIR ${PIP_CACHE_DIR}
+RUN mkdir -p ${PIP_CACHE_DIR}
+
+# create virtual environment
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+  python3 -m venv "${APPNAME}" \
+  --upgrade-deps
+
+# copy sources
+COPY --link . .
+
+# install pyproject.toml
+ARG PIP_EXTRA_INDEX_URL
+ENV PIP_EXTRA_INDEX_URL ${PIP_EXTRA_INDEX_URL}
+RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+  "${APPNAME}/bin/pip" install .
+
+# build patchmatch
+RUN python3 -c "from patchmatch import patch_match"
+
+#####################
+##  runtime image  ##
+#####################
+FROM python-base AS runtime
+
+# Create a new user
+ARG UNAME=appuser
+RUN useradd \
+  --no-log-init \
+  -m \
+  -U \
+  "${UNAME}"
+
+# create volume directory
+ARG VOLUME_DIR=/data
+RUN mkdir -p "${VOLUME_DIR}" \
+  && chown -R "${UNAME}" "${VOLUME_DIR}"
+
+# setup runtime environment
+USER ${UNAME}
+COPY --chown=${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
+ENV INVOKEAI_ROOT ${VOLUME_DIR}
+ENV TRANSFORMERS_CACHE ${VOLUME_DIR}/.cache
+ENV INVOKE_MODEL_RECONFIGURE "--yes --default_only"
+EXPOSE 9090
+ENTRYPOINT [ "invokeai" ]
+CMD [ "--web", "--host", "0.0.0.0", "--port", "9090" ]
+VOLUME [ "${VOLUME_DIR}" ]

docker/build.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+set -e
+
+# If you want to build a specific flavor, set the CONTAINER_FLAVOR environment variable
+#   e.g. CONTAINER_FLAVOR=cpu ./build.sh
+#   Possible Values are:
+#     - cpu
+#     - cuda
+#     - rocm
+#   Don't forget to also set it when executing run.sh
+#   if it is not set, the script will try to detect the flavor by itself.
+#
+# Doc can be found here:
+#   https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
+
+SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
+cd "$SCRIPTDIR" || exit 1
+
+source ./env.sh
+
+DOCKERFILE=${INVOKE_DOCKERFILE:-./Dockerfile}
+
+# print the settings
+echo -e "You are using these values:\n"
+echo -e "Dockerfile:\t\t${DOCKERFILE}"
+echo -e "index-url:\t\t${PIP_EXTRA_INDEX_URL:-none}"
+echo -e "Volumename:\t\t${VOLUMENAME}"
+echo -e "Platform:\t\t${PLATFORM}"
+echo -e "Container Registry:\t${CONTAINER_REGISTRY}"
+echo -e "Container Repository:\t${CONTAINER_REPOSITORY}"
+echo -e "Container Tag:\t\t${CONTAINER_TAG}"
+echo -e "Container Flavor:\t${CONTAINER_FLAVOR}"
+echo -e "Container Image:\t${CONTAINER_IMAGE}\n"
+
+# Create docker volume
+if [[ -n "$(docker volume ls -f name="${VOLUMENAME}" -q)" ]]; then
+    echo -e "Volume already exists\n"
+else
+    echo -n "creating docker volume "
+    docker volume create "${VOLUMENAME}"
+fi
+
+# Build Container
+DOCKER_BUILDKIT=1 docker build \
+    --platform="${PLATFORM:-linux/amd64}" \
+    --tag="${CONTAINER_IMAGE:-invokeai}" \
+    ${CONTAINER_FLAVOR:+--build-arg="CONTAINER_FLAVOR=${CONTAINER_FLAVOR}"} \
+    ${PIP_EXTRA_INDEX_URL:+--build-arg="PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}"} \
+    ${PIP_PACKAGE:+--build-arg="PIP_PACKAGE=${PIP_PACKAGE}"} \
+    --file="${DOCKERFILE}" \
+    ..

docker/env.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+
+# This file is used to set environment variables for the build.sh and run.sh scripts.
+
+# Try to detect the container flavor if no PIP_EXTRA_INDEX_URL got specified
+if [[ -z "$PIP_EXTRA_INDEX_URL" ]]; then
+
+  # Activate virtual environment if not already activated and exists
+  if [[ -z $VIRTUAL_ENV ]]; then
+    [[ -e "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" ]] \
+      && source "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" \
+      && echo "Activated virtual environment: $VIRTUAL_ENV"
+  fi
+
+  # Decide which container flavor to build if not specified
+  if [[ -z "$CONTAINER_FLAVOR" ]] && python -c "import torch" &>/dev/null; then
+    # Check for CUDA and ROCm
+    CUDA_AVAILABLE=$(python -c "import torch;print(torch.cuda.is_available())")
+    ROCM_AVAILABLE=$(python -c "import torch;print(torch.version.hip is not None)")
+    if [[ "${CUDA_AVAILABLE}" == "True" ]]; then
+      CONTAINER_FLAVOR="cuda"
+    elif [[ "${ROCM_AVAILABLE}" == "True" ]]; then
+      CONTAINER_FLAVOR="rocm"
+    else
+      CONTAINER_FLAVOR="cpu"
+    fi
+  fi
+
+  # Set PIP_EXTRA_INDEX_URL based on container flavor
+  if [[ "$CONTAINER_FLAVOR" == "rocm" ]]; then
+    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/rocm"
+  elif [[ "$CONTAINER_FLAVOR" == "cpu" ]]; then
+    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
+  # elif [[ -z "$CONTAINER_FLAVOR" || "$CONTAINER_FLAVOR" == "cuda" ]]; then
+  #   PIP_PACKAGE=${PIP_PACKAGE-".[xformers]"}
+  fi
+fi
+
+# Variables shared by build.sh and run.sh
+REPOSITORY_NAME="${REPOSITORY_NAME-$(basename "$(git rev-parse --show-toplevel)")}"
+REPOSITORY_NAME="${REPOSITORY_NAME,,}"
+VOLUMENAME="${VOLUMENAME-"${REPOSITORY_NAME}_data"}"
+ARCH="${ARCH-$(uname -m)}"
+PLATFORM="${PLATFORM-linux/${ARCH}}"
+INVOKEAI_BRANCH="${INVOKEAI_BRANCH-$(git branch --show)}"
+CONTAINER_REGISTRY="${CONTAINER_REGISTRY-"ghcr.io"}"
+CONTAINER_REPOSITORY="${CONTAINER_REPOSITORY-"$(whoami)/${REPOSITORY_NAME}"}"
+CONTAINER_FLAVOR="${CONTAINER_FLAVOR-cuda}"
+CONTAINER_TAG="${CONTAINER_TAG-"${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}"}"
+CONTAINER_IMAGE="${CONTAINER_REGISTRY}/${CONTAINER_REPOSITORY}:${CONTAINER_TAG}"
+CONTAINER_IMAGE="${CONTAINER_IMAGE,,}"

docker/run.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+set -e
+
+# How to use: https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
+
+SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
+cd "$SCRIPTDIR" || exit 1
+
+source ./env.sh
+
+# Create outputs directory if it does not exist
+[[ -d ./outputs ]] || mkdir ./outputs
+
+echo -e "You are using these values:\n"
+echo -e "Volumename:\t${VOLUMENAME}"
+echo -e "Invokeai_tag:\t${CONTAINER_IMAGE}"
+echo -e "local Models:\t${MODELSPATH:-unset}\n"
+
+docker run \
+  --interactive \
+  --tty \
+  --rm \
+  --platform="${PLATFORM}" \
+  --name="${REPOSITORY_NAME,,}" \
+  --hostname="${REPOSITORY_NAME,,}" \
+  --mount=source="${VOLUMENAME}",target=/data \
+  --mount type=bind,source="$(pwd)"/outputs,target=/data/outputs \
+  ${MODELSPATH:+--mount="type=bind,source=${MODELSPATH},target=/data/models"} \
+  ${HUGGING_FACE_HUB_TOKEN:+--env="HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN}"} \
+  --publish=9090:9090 \
+  --cap-add=sys_nice \
+  ${GPU_FLAGS:+--gpus="${GPU_FLAGS}"} \
+  "${CONTAINER_IMAGE}" ${@:+$@}
+
+# Remove Trash folder
+for f in outputs/.Trash*; do
+  if [ -e "$f" ]; then
+    rm -Rf "$f"
+    break
+  fi
+done

docs/.markdownlint.jsonc

@@ -0,0 +1,5 @@
+{
+  "MD046": false,
+  "MD007": false,
+  "MD030": false
+}

docs/CHANGELOG.md

@@ -4,180 +4,377 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
+## v2.3.0 <small>(15 January 2023)</small>
+
+**Transition to diffusers
+
+Version 2.3 provides support for both the traditional `.ckpt` weight
+checkpoint files as well as the HuggingFace `diffusers` format. This
+introduces several changes you should know about.
+
+1. The models.yaml format has been updated. There are now two
+   different type of configuration stanza. The traditional ckpt
+   one will look like this, with a `format` of `ckpt` and a
+   `weights` field that points to the absolute or ROOTDIR-relative
+   location of the ckpt file.
+
+   ```
+   inpainting-1.5:
+      description: RunwayML SD 1.5 model optimized for inpainting (4.27 GB)
+      repo_id: runwayml/stable-diffusion-inpainting
+      format: ckpt
+      width: 512
+      height: 512
+      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
+   ```
+
+  A configuration stanza for a diffusers model hosted at HuggingFace will look like this,
+  with a `format` of `diffusers` and a `repo_id` that points to the
+  repository ID of the model on HuggingFace:
+
+  ```
+  stable-diffusion-2.1:
+  description: Stable Diffusion version 2.1 diffusers model (5.21 GB)
+  repo_id: stabilityai/stable-diffusion-2-1
+  format: diffusers
+  ```
+
+  A configuration stanza for a diffuers model stored locally should
+  look like this, with a `format` of `diffusers`, but a `path` field
+  that points at the directory that contains `model_index.json`:
+
+  ```
+  waifu-diffusion:
+  description: Latest waifu diffusion 1.4
+  format: diffusers
+  path: models/diffusers/hakurei-haifu-diffusion-1.4
+  ```
+
+2. In order of precedence, InvokeAI will now use HF_HOME, then
+   XDG_CACHE_HOME, then finally default to `ROOTDIR/models` to
+   store HuggingFace diffusers models.
+
+   Consequently, the format of the models directory has changed to
+   mimic the HuggingFace cache directory. When HF_HOME and XDG_HOME
+   are not set, diffusers models are now automatically downloaded
+   and retrieved from the directory `ROOTDIR/models/diffusers`,
+   while other models are stored in the directory
+   `ROOTDIR/models/hub`. This organization is the same as that used
+   by HuggingFace for its cache management.
+
+   This allows you to share diffusers and ckpt model files easily with
+   other machine learning applications that use the HuggingFace
+   libraries. To do this, set the environment variable HF_HOME
+   before starting up InvokeAI to tell it what directory to
+   cache models in. To tell InvokeAI to use the standard HuggingFace
+   cache directory, you would set HF_HOME like this (Linux/Mac):
+
+   `export HF_HOME=~/.cache/huggingface`
+
+   Both HuggingFace and InvokeAI will fall back to the XDG_CACHE_HOME
+   environment variable if HF_HOME is not set; this path
+   takes precedence over `ROOTDIR/models` to allow for the same sharing
+   with other machine learning applications that use HuggingFace
+   libraries.
+
+3. If you upgrade to InvokeAI 2.3.* from an earlier version, there
+   will be a one-time migration from the old models directory format
+   to the new one. You will see a message about this the first time
+   you start `invoke.py`.
+
+4. Both the front end back ends of the model manager have been
+   rewritten to accommodate diffusers. You can import models using
+   their local file path, using their URLs, or their HuggingFace
+   repo_ids. On the command line, all these syntaxes work:
+
+   ```
+   !import_model stabilityai/stable-diffusion-2-1-base
+   !import_model /opt/sd-models/sd-1.4.ckpt
+   !import_model https://huggingface.co/Fictiverse/Stable_Diffusion_PaperCut_Model/blob/main/PaperCut_v1.ckpt
+   ```
+
+**KNOWN BUGS (15 January 2023)
+
+1. On CUDA systems, the 768 pixel stable-diffusion-2.0 and
+   stable-diffusion-2.1 models can only be run as `diffusers` models
+   when the `xformer` library is installed and configured. Without
+   `xformers`, InvokeAI returns black images.
+
+2. Inpainting and outpainting have regressed in quality.
+
+Both these issues are being actively worked on.
+
+## v2.2.4 <small>(11 December 2022)</small>
+
+**the `invokeai` directory**
+
+Previously there were two directories to worry about, the directory that
+contained the InvokeAI source code and the launcher scripts, and the `invokeai`
+directory that contained the models files, embeddings, configuration and
+outputs. With the 2.2.4 release, this dual system is done away with, and
+everything, including the `invoke.bat` and `invoke.sh` launcher scripts, now
+live in a directory named `invokeai`. By default this directory is located in
+your home directory (e.g. `\Users\yourname` on Windows), but you can select
+where it goes at install time.
+
+After installation, you can delete the install directory (the one that the zip
+file creates when it unpacks). Do **not** delete or move the `invokeai`
+directory!
+
+**Initialization file `invokeai/invokeai.init`**
+
+You can place frequently-used startup options in this file, such as the default
+number of steps or your preferred sampler. To keep everything in one place, this
+file has now been moved into the `invokeai` directory and is named
+`invokeai.init`.
+
+**To update from Version 2.2.3**
+
+The easiest route is to download and unpack one of the 2.2.4 installer files.
+When it asks you for the location of the `invokeai` runtime directory, respond
+with the path to the directory that contains your 2.2.3 `invokeai`. That is, if
+`invokeai` lives at `C:\Users\fred\invokeai`, then answer with `C:\Users\fred`
+and answer "Y" when asked if you want to reuse the directory.
+
+The `update.sh` (`update.bat`) script that came with the 2.2.3 source installer
+does not know about the new directory layout and won't be fully functional.
+
+**To update to 2.2.5 (and beyond) there's now an update path**
+
+As they become available, you can update to more recent versions of InvokeAI
+using an `update.sh` (`update.bat`) script located in the `invokeai` directory.
+Running it without any arguments will install the most recent version of
+InvokeAI. Alternatively, you can get set releases by running the `update.sh`
+script with an argument in the command shell. This syntax accepts the path to
+the desired release's zip file, which you can find by clicking on the green
+"Code" button on this repository's home page.
+
+**Other 2.2.4 Improvements**
+
+- Fix InvokeAI GUI initialization by @addianto in #1687
+- fix link in documentation by @lstein in #1728
+- Fix broken link by @ShawnZhong in #1736
+- Remove reference to binary installer by @lstein in #1731
+- documentation fixes for 2.2.3 by @lstein in #1740
+- Modify installer links to point closer to the source installer by @ebr in
+  #1745
+- add documentation warning about 1650/60 cards by @lstein in #1753
+- Fix Linux source URL in installation docs by @andybearman in #1756
+- Make install instructions discoverable in readme by @damian0815 in #1752
+- typo fix by @ofirkris in #1755
+- Non-interactive model download (support HUGGINGFACE_TOKEN) by @ebr in #1578
+- fix(srcinstall): shell installer - cp scripts instead of linking by @tildebyte
+  in #1765
+- stability and usage improvements to binary & source installers by @lstein in
+  #1760
+- fix off-by-one bug in cross-attention-control by @damian0815 in #1774
+- Eventually update APP_VERSION to 2.2.3 by @spezialspezial in #1768
+- invoke script cds to its location before running by @lstein in #1805
+- Make PaperCut and VoxelArt models load again by @lstein in #1730
+- Fix --embedding_directory / --embedding_path not working by @blessedcoolant in
+  #1817
+- Clean up readme by @hipsterusername in #1820
+- Optimized Docker build with support for external working directory by @ebr in
+  #1544
+- disable pushing the cloud container by @mauwii in #1831
+- Fix docker push github action and expand with additional metadata by @ebr in
+  #1837
+- Fix Broken Link To Notebook by @VedantMadane in #1821
+- Account for flat models by @spezialspezial in #1766
+- Update invoke.bat.in isolate environment variables by @lynnewu in #1833
+- Arch Linux Specific PatchMatch Instructions & fixing conda install on linux by
+  @SammCheese in #1848
+- Make force free GPU memory work in img2img by @addianto in #1844
+- New installer by @lstein
+
+## v2.2.3 <small>(2 December 2022)</small>
+
+!!! Note
+
+    This point release removes references to the binary installer from the
+    installation guide. The binary installer is not stable at the current
+    time. First time users are encouraged to use the "source" installer as
+    described in [Installing InvokeAI with the Source Installer](installation/deprecated_documentation/INSTALL_SOURCE.md)
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](features/UNIFIED_CANVAS.md). This new workflow is the
+biggest enhancement added to the WebUI to date, and unlocks a stunning amount of
+potential for users to create and iterate on their creations. The following
+sections describe what's new for InvokeAI.
+
+## v2.2.2 <small>(30 November 2022)</small>
+
+!!! note
+
+    The binary installer is not ready for prime time. First time users are recommended to install via the "source" installer accessible through the links at the bottom of this page.****
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](https://invoke-ai.github.io/InvokeAI/features/UNIFIED_CANVAS/).
+This new workflow is the biggest enhancement added to the WebUI to date, and
+unlocks a stunning amount of potential for users to create and iterate on their
+creations. The following sections describe what's new for InvokeAI.
+
+## v2.2.0 <small>(2 December 2022)</small>
+
+With InvokeAI 2.2, this project now provides enthusiasts and professionals a
+robust workflow solution for creating AI-generated and human facilitated
+compositions. Additional enhancements have been made as well, improving safety,
+ease of use, and installation.
+
+Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
+512x768 image (and less for smaller images), and is compatible with
+Windows/Linux/Mac (M1 & M2).
+
+You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
+introduces the main WebUI enhancement for version 2.2 -
+[The Unified Canvas](features/UNIFIED_CANVAS.md). This new workflow is the
+biggest enhancement added to the WebUI to date, and unlocks a stunning amount of
+potential for users to create and iterate on their creations. The following
+sections describe what's new for InvokeAI.
+
+## v2.1.3 <small>(13 November 2022)</small>
+
+- A choice of installer scripts that automate installation and configuration.
+  See
+  [Installation](installation/index.md).
+- A streamlined manual installation process that works for both Conda and
+  PIP-only installs. See
+  [Manual Installation](installation/020_INSTALL_MANUAL.md).
+- The ability to save frequently-used startup options (model to load, steps,
+  sampler, etc) in a `.invokeai` file. See
+  [Client](features/CLI.md)
+- Support for AMD GPU cards (non-CUDA) on Linux machines.
+- Multiple bugs and edge cases squashed.
+
 ## v2.1.0 <small>(2 November 2022)</small>
 
-- 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
+- update mac instructions to use invokeai for env name by @willwillems in #1030
+- Update .gitignore by @blessedcoolant in #1040
+- reintroduce fix for m1 from #579 missing after merge by @skurovec in #1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in #1060
+- Print out the device type which is used by @manzke in #1073
+- Hires Addition by @hipsterusername in #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
+  @skurovec in #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
+  warning by @db3000 in #1077
+- fix noisy images at high step counts by @lstein in #1086
+- Generalize facetool strength argument by @db3000 in #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
+  #1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in #1095
+- Update generate.py by @unreleased in #1109
+- Update 'ldm' env to 'invokeai' in troubleshooting steps by @19wolf in #1125
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in #1123
+- Fix broken doc links, fix malaprop in the project subtitle by @majick in #1131
+- Only output facetool parameters if enhancing faces by @db3000 in #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
+  @spezialspezial in #1136
+- fix links to point to invoke-ai.github.io #1117 by @mauwii in #1143
+- Rework-mkdocs by @mauwii in #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
+  by @lstein in #1127
+- Fix img2img DDIM index out of bound by @wfng92 in #1137
+- Fix gh actions by @mauwii in #1128
+- update mac instructions to use invokeai for env name by @willwillems in #1030
+- Update .gitignore by @blessedcoolant in #1040
+- reintroduce fix for m1 from #579 missing after merge by @skurovec in #1056
+- Update Stable_Diffusion_AI_Notebook.ipynb (Take 2) by @ChloeL19 in #1060
+- Print out the device type which is used by @manzke in #1073
+- Hires Addition by @hipsterusername in #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
+  @skurovec in #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
+  warning by @db3000 in #1077
+- fix noisy images at high step counts by @lstein in #1086
+- Generalize facetool strength argument by @db3000 in #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
+  #1066
+- Fix Typo, committed changing ldm environment to invokeai by @jdries3 in #1095
+- Fixed documentation typos and resolved merge conflicts by @rupeshs in #1123
+- Only output facetool parameters if enhancing faces by @db3000 in #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
+  by @lstein in #1127
+- Fix img2img DDIM index out of bound by @wfng92 in #1137
+- Add text prompt to inpaint mask support by @lstein in #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
+  #976
+- WebUI: Adds Codeformer support by @psychedelicious in #1151
+- Skips normalizing prompts for web UI metadata by @psychedelicious in #1165
+- Add Asymmetric Tiling by @carson-katri in #1132
+- Web UI: Increases max CFG Scale to 200 by @psychedelicious in #1172
 - Corrects color channels in face restoration; Fixes #1167 by @psychedelicious
-  in https://github.com/invoke-ai/InvokeAI/pull/1175
+  in #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
+  in #1178
+- Fix typo in docs: s/Formally/Formerly by @noodlebox in #1176
+- fix clipseg loading problems by @lstein in #1177
+- Correct color channels in upscale using array slicing by @wfng92 in #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
+  @psychedelicious in #1171
+- fix a number of bugs in textual inversion by @lstein in #1190
+- Improve !fetch, add !replay command by @ArDiouscuros in #882
+- Fix generation of image with s>1000 by @holstvoogd in #951
+- Web UI: Gallery improvements by @psychedelicious in #1198
+- Update CLI.md by @krummrey in #1211
+- outcropping improvements by @lstein in #1207
+- add support for loading VAE autoencoders by @lstein in #1216
+- remove duplicate fix_func for MPS by @wfng92 in #1210
+- Metadata storage and retrieval fixes by @lstein in #1204
+- nix: add shell.nix file by @Cloudef in #1170
+- Web UI: Changes vite dist asset paths to relative by @psychedelicious in #1185
+- Web UI: Removes isDisabled from PromptInput by @psychedelicious in #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
+  @ArDiouscuros in #981
+- feat: adding filename format template by @plucked in #968
+- Web UI: Fixes broken bundle by @psychedelicious in #1242
+- Support runwayML custom inpainting model by @lstein in #1243
+- Update IMG2IMG.md by @talitore in #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
+  by @mauwii in #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
+  #1222
+- Prompt tweaks by @lstein in #1268
+- Outpainting implementation by @Kyle0654 in #1251
+- fixing aspect ratio on hires by @tjennings in #1249
+- Fix-build-container-action by @mauwii in #1274
+- handle all unicode characters by @damian0815 in #1276
+- adds models.user.yml to .gitignore by @JakeHL in #1281
+- remove debug branch, set fail-fast to false by @mauwii in #1284
+- Protect-secrets-on-pr by @mauwii in #1285
+- Web UI: Adds initial inpainting implementation by @psychedelicious in #1225
+- fix environment-mac.yml - tested on x64 and arm64 by @mauwii in #1289
+- Use proper authentication to download model by @mauwii in #1287
+- Prevent indexing error for mode RGB by @spezialspezial in #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
+  unecesarry caches by @mauwii in #1293
+- add --no-interactive to configure_invokeai step by @mauwii in #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
+  script by @cmdr2 in #1253
+- configure_invokeai.py script downloads the weight files by @lstein in #1290
 
 ## v2.0.1 <small>(13 October 2022)</small>
 

docs/contributing/ARCHITECTURE.md

@@ -0,0 +1,93 @@
+# Invoke.AI Architecture
+
+```mermaid
+flowchart TB
+
+  subgraph apps[Applications]
+    webui[WebUI]
+    cli[CLI]
+
+  subgraph webapi[Web API]
+    api[HTTP API]
+    sio[Socket.IO]
+  end
+
+  end
+
+  subgraph invoke[Invoke]
+    direction LR
+    invoker
+    services
+    sessions
+    invocations
+  end
+
+  subgraph core[AI Core]
+    Generate
+  end
+
+  webui --> webapi
+  webapi --> invoke
+  cli --> invoke
+
+  invoker --> services & sessions
+  invocations --> services
+  sessions --> invocations
+
+  services --> core
+
+  %% Styles
+  classDef sg fill:#5028C8,font-weight:bold,stroke-width:2,color:#fff,stroke:#14141A
+  classDef default stroke-width:2px,stroke:#F6B314,color:#fff,fill:#14141A
+
+  class apps,webapi,invoke,core sg
+
+```
+
+## Applications
+
+Applications are built on top of the invoke framework. They should construct `invoker` and then interact through it. They should avoid interacting directly with core code in order to support a variety of configurations.
+
+### Web UI
+
+The Web UI is built on top of an HTTP API built with [FastAPI](https://fastapi.tiangolo.com/) and [Socket.IO](https://socket.io/). The frontend code is found in `/frontend` and the backend code is found in `/ldm/invoke/app/api_app.py` and `/ldm/invoke/app/api/`. The code is further organized as such:
+
+| Component | Description |
+| --- | --- |
+| api_app.py | Sets up the API app, annotates the OpenAPI spec with additional data, and runs the API |
+| dependencies | Creates all invoker services and the invoker, and provides them to the API |
+| events | An eventing system that could in the future be adapted to support horizontal scale-out |
+| sockets | The Socket.IO interface - handles listening to and emitting session events (events are defined in the events service module) |
+| routers | API definitions for different areas of API functionality |
+
+### CLI
+
+The CLI is built automatically from invocation metadata, and also supports invocation piping and auto-linking. Code is available in `/ldm/invoke/app/cli_app.py`.
+
+## Invoke
+
+The Invoke framework provides the interface to the underlying AI systems and is built with flexibility and extensibility in mind. There are four major concepts: invoker, sessions, invocations, and services.
+
+### Invoker
+
+The invoker (`/ldm/invoke/app/services/invoker.py`) is the primary interface through which applications interact with the framework. Its primary purpose is to create, manage, and invoke sessions. It also maintains two sets of services:
+- **invocation services**, which are used by invocations to interact with core functionality.
+- **invoker services**, which are used by the invoker to manage sessions and manage the invocation queue.
+
+### Sessions
+
+Invocations and links between them form a graph, which is maintained in a session. Sessions can be queued for invocation, which will execute their graph (either the next ready invocation, or all invocations). Sessions also maintain execution history for the graph (including storage of any outputs). An invocation may be added to a session at any time, and there is capability to add and entire graph at once, as well as to automatically link new invocations to previous invocations. Invocations can not be deleted or modified once added.
+
+The session graph does not support looping. This is left as an application problem to prevent additional complexity in the graph.
+
+### Invocations
+
+Invocations represent individual units of execution, with inputs and outputs. All invocations are located in `/ldm/invoke/app/invocations`, and are all automatically discovered and made available in the applications. These are the primary way to expose new functionality in Invoke.AI, and the [implementation guide](INVOCATIONS.md) explains how to add new invocations.
+
+### Services
+
+Services provide invocations access AI Core functionality and other necessary functionality (e.g. image storage). These are available in `/ldm/invoke/app/services`. As a general rule, new services should provide an interface as an abstract base class, and may provide a lightweight local implementation by default in their module. The goal for all services should be to enable the usage of different implementations (e.g. using cloud storage for image storage), but should not load any module dependencies unless that implementation has been used (i.e. don't import anything that won't be used, especially if it's expensive to import).
+
+## AI Core
+
+The AI Core is represented by the rest of the code base (i.e. the code outside of `/ldm/invoke/app/`).

docs/contributing/INVOCATIONS.md

@@ -0,0 +1,105 @@
+# Invocations
+
+Invocations represent a single operation, its inputs, and its outputs. These operations and their outputs can be chained together to generate and modify images.
+
+## Creating a new invocation
+
+To create a new invocation, either find the appropriate module file in `/ldm/invoke/app/invocations` to add your invocation to, or create a new one in that folder. All invocations in that folder will be discovered and made available to the CLI and API automatically. Invocations make use of [typing](https://docs.python.org/3/library/typing.html) and [pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration into the CLI and API.
+
+An invocation looks like this:
+
+```py
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+    type: Literal['upscale'] = 'upscale'
+
+    # Inputs
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image = ImageField(image_type = image_type, image_name = image_name)
+        )
+```
+
+Each portion is important to implement correctly.
+
+### Class definition and type
+```py
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+    type: Literal['upscale'] = 'upscale'
+```
+All invocations must derive from `BaseInvocation`. They should have a docstring that declares what they do in a single, short line. They should also have a `type` with a type hint that's `Literal["command_name"]`, where `command_name` is what the user will type on the CLI or use in the API to create this invocation. The `command_name` must be unique. The `type` must be assigned to the value of the literal in the type hint.
+
+### Inputs
+```py
+    # Inputs
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description="The upscale level")
+```
+Inputs consist of three parts: a name, a type hint, and a `Field` with default, description, and validation information. For example:
+| Part | Value | Description |
+| ---- | ----- | ----------- |
+| Name | `strength` | This field is referred to as `strength` |
+| Type Hint | `float` | This field must be of type `float` |
+| Field | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
+
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this field to be parsed with `None` as a value, which enables linking to previous invocations. All fields should either provide a default value or allow `None` as a value, so that they can be overwritten with a linked output from another invocation.
+
+The special type `ImageField` is also used here. All images are passed as `ImageField`, which protects them from pydantic validation errors (since images only ever come from links).
+
+Finally, note that for all linking, the `type` of the linked fields must match. If the `name` also matches, then the field can be **automatically linked** to a previous invocation by name and matching.
+
+### Invoke Function
+```py
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
+        )
+
+        # Results are image and seed, unwrap for now
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image = ImageField(image_type = image_type, image_name = image_name)
+        )
+```
+The `invoke` function is the last portion of an invocation. It is provided an `InvocationContext` which contains services to perform work as well as a `session_id` for use as needed. It should return a class with output values that derives from `BaseInvocationOutput`.
+
+Before being called, the invocation will have all of its fields set from defaults, inputs, and finally links (overriding in that order).
+
+Assume that this invocation may be running simultaneously with other invocations, may be running on another machine, or in other interesting scenarios. If you need functionality, please provide it as a service in the `InvocationServices` class, and make sure it can be overridden.
+
+### Outputs
+```py
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+    type: Literal['image'] = 'image'
+
+    image: ImageField = Field(default=None, description="The output image")
+```
+Output classes look like an invocation class without the invoke method. Prefer to use an existing output class if available, and prefer to name inputs the same as outputs when possible, to promote automatic invocation linking.

docs/features/CLI.md

@@ -1,43 +1,56 @@
 ---
-title: CLI
+title: Command-Line Interface
 ---
 
 # :material-bash: CLI
 
 ## **Interactive Command Line Interface**
 
-The `invoke.py` script, located in `scripts/`, provides an interactive interface
-to image generation similar to the "invoke mothership" bot that Stable AI
-provided on its Discord server.
+The InvokeAI command line interface (CLI) provides scriptable access
+to InvokeAI's features.Some advanced features are only available
+through the CLI, though they eventually find their way into the WebUI.
 
-Unlike the `txt2img.py` and `img2img.py` scripts provided in the original
-[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) source
-code repository, the time-consuming initialization of the AI model
-initialization only happens once. After that image generation from the
-command-line interface is very fast.
+The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
+selecting option (1). Alternatively, it can be launched directly from
+the command line by activating the InvokeAI environment and giving the
+command:
+
+```bash
+invokeai
+```
+
+After some startup messages, you will be presented with the `invoke> `
+prompt. Here you can type prompts to generate images and issue other
+commands to load and manipulate generative models. The CLI has a large
+number of command-line options that control its behavior. To get a
+concise summary of the options, call `invokeai` with the `--help` argument:
+
+```bash
+invokeai --help
+```
 
 The script uses the readline library to allow for in-line editing, command
 history (++up++ and ++down++), autocompletion, and more. To help keep track of
 which prompts generated which images, the script writes a log file of image
 names and prompts to the selected output directory.
 
-In addition, as of version 1.02, it also writes the prompt into the PNG file's
-metadata where it can be retrieved using `scripts/images2prompt.py`
-
-The script is confirmed to work on Linux, Windows and Mac systems.
-
-!!! note
-
-    This script runs from the command-line or can be used as a Web application. The Web GUI is
-    currently rudimentary, but a much better replacement is on its way.
+Here is a typical session
 
 ```bash
-(invokeai) ~/stable-diffusion$ python3 ./scripts/invoke.py
+PS1:C:\Users\fred> invokeai
 * Initializing, be patient...
-Loading model from models/ldm/text2img-large/model.ckpt
-(...more initialization messages...)
-
-* Initialization done! Awaiting your command...
+* Initializing, be patient...
+>> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
+>> Internet connectivity is True
+>> InvokeAI, version 2.3.0-rc5
+>> InvokeAI runtime directory is "/home/lstein/invokeai"
+>> GFPGAN Initialized
+>> CodeFormer Initialized
+>> ESRGAN Initialized
+>> Using device_type cuda
+>> xformers memory-efficient attention is available and enabled
+     (...more initialization messages...)
+* Initialization done! Awaiting your command (-h for help, 'q' to quit)
 invoke> ashley judd riding a camel -n2 -s150
 Outputs:
    outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
@@ -47,27 +60,15 @@ invoke> "there's a fly in my soup" -n6 -g
     outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
     seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
 invoke> q
-
-# this shows how to retrieve the prompt stored in the saved image's metadata
-(invokeai) ~/stable-diffusion$ python ./scripts/images2prompt.py outputs/img_samples/*.png
-00009.png: "ashley judd riding a camel" -s150 -S 416354203
-00010.png: "ashley judd riding a camel" -s150 -S 1362479620
-00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
 ```
 
 ![invoke-py-demo](../assets/dream-py-demo.png)
 
-The `invoke>` prompt's arguments are pretty much identical to those used in the
-Discord bot, except you don't need to type `!invoke` (it doesn't hurt if you
-do). A significant change is that creation of individual images is now the
-default unless `--grid` (`-g`) is given. A full list is given in
-[List of prompt arguments](#list-of-prompt-arguments).
-
 ## Arguments
 
-The script itself also recognizes a series of command-line switches that will
-change important global defaults, such as the directory for image outputs and
-the location of the model weight files.
+The script recognizes a series of command-line switches that will
+change important global defaults, such as the directory for image
+outputs and the location of the model weight files.
 
 ### List of arguments recognized at the command line
 
@@ -82,10 +83,14 @@ overridden on a per-prompt basis (see
 | `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                          | Location for generated images.                                                                       |
 | `--prompt_as_dir`                         | `-p`                                      | `False`                                        | Name output directories using the prompt text.                                                       |
 | `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
-| `--model <modelname>`                     |                                           | `stable-diffusion-1.4`                         | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" |
-| `--full_precision`                        | `-F`                                      | `False`                                        | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards.   |
+| `--model <modelname>`                     |                                           | `stable-diffusion-1.5`                         | Loads the initial model specified in configs/models.yaml. |
+| `--ckpt_convert `           |                                                         | `False`                                        | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
+| `--autoconvert <path>`                    |                          | `None`                                        | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
+| `--precision`                             |                                           | `fp16`                                         | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
 | `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                            | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
 | `--safety-checker`                        |                                           | `False`                                        | Activate safety checker for NSFW and other potentially disturbing imagery                            |
+| `--patchmatch`, `--no-patchmatch`                 |                                   | `--patchmatch`                                        | Load/Don't load the PatchMatch inpainting extension    |
+| `--xformers`, `--no-xformers`                 |                                   | `--xformers`                                        | Load/Don't load the Xformers memory-efficient attention module (CUDA only)    |
 | `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
 | `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
 | `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
@@ -109,6 +114,7 @@ overridden on a per-prompt basis (see
 
     | Argument           |  Shortcut  |  Default            |  Description |
     |--------------------|------------|---------------------|--------------|
+    | `--full_precision`  |             | `False`                | Same as `--precision=fp32`|
     | `--weights <path>`   |            | `None`                | Path to weights file; use `--model stable-diffusion-1.4` instead |
     | `--laion400m`        | `-l`         | `False`               | Use older LAION400m weights; use `--model=laion400m` instead |
 
@@ -130,20 +136,34 @@ file should contain the startup options as you would type them on the
 command line (`--steps=10 --grid`), one argument per line, or a
 mixture of both using any of the accepted command switch formats:
 
-!!! example ""
+!!! example "my unmodified initialization file"
 
-    ```bash
-    --web
-    --steps=28
-    --grid
-    -f 0.6 -C 11.0 -A k_euler_a
+    ```bash title="~/.invokeai" linenums="1"
+    # InvokeAI initialization file
+    # This is the InvokeAI initialization file, which contains command-line default values.
+    # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
+    # or renaming it and then running invokeai-configure again.
+
+    # The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
+    --root="/Users/mauwii/invokeai"
+
+    # the --outdir option controls the default location of image files.
+    --outdir="/Users/mauwii/invokeai/outputs"
+
+    # You may place other  frequently-used startup commands here, one or more per line.
+    # Examples:
+    # --web --host=0.0.0.0
+    # --steps=20
+    # -Ak_euler_a -C10.0
     ```
 
-Note that the initialization file only accepts the command line arguments.
-There are additional arguments that you can provide on the `invoke>` command
-line (such as `-n` or `--iterations`) that cannot be entered into this file.
-Also be alert for empty blank lines at the end of the file, which will cause
-an arguments error at startup time.
+!!! note
+
+    The  initialization file only accepts the command line arguments.
+    There are additional arguments that you can provide on the `invoke>` command
+    line (such as `-n` or `--iterations`) that cannot be entered into this file.
+    Also be alert for empty blank lines at the end of the file, which will cause
+    an arguments error at startup time.
 
 ## List of prompt arguments
 
@@ -194,16 +214,20 @@ Here are the invoke> command that apply to txt2img:
 | `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
 | `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this.                                                                                                                                                           |
 | `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
+| `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
+| `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
 
-Note that the width and height of the image must be multiples of 64. You can
-provide different values, but they will be rounded down to the nearest multiple
-of 64.
+!!! note
 
-### This is an example of img2img:
+    the width and height of the image must be multiples of 64. You can
+    provide different values, but they will be rounded down to the nearest multiple
+    of 64.
 
-```
-invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-```
+!!! example "This is a example of img2img"
+
+    ```bash
+    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
+    ```
 
 This will modify the indicated vacation photograph by making it more like the
 prompt. Results will vary greatly depending on what is in the image. We also ask
@@ -253,7 +277,7 @@ description of the part of the image to replace. For example, if you have an
 image of a breakfast plate with a bagel, toast and scrambled eggs, you can
 selectively mask the bagel and replace it with a piece of cake this way:
 
-```
+```bash
 invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
 ```
 
@@ -265,20 +289,26 @@ are getting too much or too little masking you can adjust the threshold down (to
 get more mask), or up (to get less). In this example, by passing `-tm` a higher
 value, we are insisting on a more stringent classification.
 
-```
+```bash
 invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
 ```
 
-# Other Commands
+### Custom Styles and Subjects
+
+You can load and use hundreds of community-contributed Textual
+Inversion models just by typing the appropriate trigger phrase. Please
+see [Concepts Library](CONCEPTS.md) for more details.
+
+## Other Commands
 
 The CLI offers a number of commands that begin with "!".
 
-## Postprocessing images
+### Postprocessing images
 
 To postprocess a file using face restoration or upscaling, use the `!fix`
 command.
 
-### `!fix`
+#### `!fix`
 
 This command runs a post-processor on a previously-generated image. It takes a
 PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
@@ -305,19 +335,21 @@ Some examples:
     [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
     ```
 
-### !mask
+#### `!mask`
 
 This command takes an image, a text prompt, and uses the `clipseg` algorithm to
 automatically generate a mask of the area that matches the text prompt. It is
 useful for debugging the text masking process prior to inpainting with the
 `--text_mask` argument. See [INPAINTING.md] for details.
 
-## Model selection and importation
+### Model selection and importation
 
-The CLI allows you to add new models on the fly, as well as to switch among them
-rapidly without leaving the script.
+The CLI allows you to add new models on the fly, as well as to switch
+among them rapidly without leaving the script. There are several
+different model formats, each described in the [Model Installation
+Guide](../installation/050_INSTALLING_MODELS.md).
 
-### !models
+#### `!models`
 
 This prints out a list of the models defined in `config/models.yaml'. The active
 model is bold-faced
@@ -325,12 +357,12 @@ model is bold-faced
 Example:
 
 <pre>
-laion400m                 not loaded  <no description>
-<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
-waifu-diffusion           not loaded  Waifu Diffusion v1.3
+inpainting-1.5            not loaded  Stable Diffusion inpainting model
+<b>stable-diffusion-1.5          active  Stable Diffusion v1.5</b>
+waifu-diffusion           not loaded  Waifu Diffusion v1.4
 </pre>
 
-### !switch <model>
+#### `!switch <model>`
 
 This quickly switches from one model to another without leaving the CLI script.
 `invoke.py` uses a memory caching system; once a model has been loaded,
@@ -339,43 +371,30 @@ Note how the second column of the `!models` table changes to `cached` after a
 model is first loaded, and that the long initialization step is not needed when
 loading a cached model.
 
-<pre>
-invoke> !models
-laion400m                 not loaded  <no description>
-<b>stable-diffusion-1.4          cached  Stable Diffusion v1.4</b>
-waifu-diffusion               active  Waifu Diffusion v1.3
+#### `!import_model <hugging_face_repo_ID>`
 
-invoke> !switch waifu-diffusion
->> Caching model stable-diffusion-1.4 in system RAM
->> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
-   | LatentDiffusion: Running in eps-prediction mode
-   | DiffusionWrapper has 859.52 M params.
-   | Making attention of type 'vanilla' with 512 in_channels
-   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
-   | Making attention of type 'vanilla' with 512 in_channels
-   | Using faster float16 precision
->> Model loaded in 18.24s
->> Max VRAM used to load the model: 2.17G 
->> Current VRAM usage:2.17G
->> Setting Sampler to k_lms
+This imports and installs a `diffusers`-style model that is stored on
+the [HuggingFace Web Site](https://huggingface.co). You can look up
+any [Stable Diffusion diffusers
+model](https://huggingface.co/models?library=diffusers) and install it
+with a command like the following:
 
-invoke> !models
-laion400m                 not loaded  <no description>
-stable-diffusion-1.4          cached  Stable Diffusion v1.4
-<b>waifu-diffusion               active  Waifu Diffusion v1.3</b>
+```bash
+!import_model prompthero/openjourney
+```
 
-invoke> !switch stable-diffusion-1.4
->> Caching model waifu-diffusion in system RAM
->> Retrieving model stable-diffusion-1.4 from system RAM cache
->> Setting Sampler to k_lms
+#### `!import_model <path/to/diffusers/directory>`
 
-invoke> !models
-laion400m                 not loaded  <no description>
-<b>stable-diffusion-1.4          active  Stable Diffusion v1.4</b>
-waifu-diffusion               cached  Waifu Diffusion v1.3
-</pre>
+If you have a copy of a `diffusers`-style model saved to disk, you can
+import it by passing the path to model's top-level directory.
 
-### !import_model <path/to/model/weights>
+#### `!import_model <url>`
+
+For a `.ckpt` or `.safetensors` file, if you have a direct download
+URL for the file, you can provide it to `!import_model` and the file
+will be downloaded and installed for you.
+
+#### `!import_model <path/to/model/weights.ckpt>`
 
 This command imports a new model weights file into InvokeAI, makes it available
 for image generation within the script, and writes out the configuration for the
@@ -395,37 +414,14 @@ below, the bold-faced text shows what the user typed in with the exception of
 the width, height and configuration file paths, which were filled in
 automatically.
 
-Example:
+#### `!import_model <path/to/directory_of_models>`
 
-<pre>
-invoke> <b>!import_model models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt</b>
->> Model import in process. Please enter the values needed to configure this model:
+If you provide the path of a directory that contains one or more
+`.ckpt` or `.safetensors` files, the CLI will scan the directory and
+interactively offer to import the models it finds there. Also see the
+`--autoconvert` command-line option.
 
-Name for this model: <b>waifu-diffusion</b>
-Description of this model: <b>Waifu Diffusion v1.3</b>
-Configuration file for this model: <b>configs/stable-diffusion/v1-inference.yaml</b>
-Default image width: <b>512</b>
-Default image height: <b>512</b>
->> New configuration:
-waifu-diffusion:
-  config: configs/stable-diffusion/v1-inference.yaml
-  description: Waifu Diffusion v1.3
-  height: 512
-  weights: models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
-  width: 512
-OK to import [n]? <b>y</b>
->> Caching model stable-diffusion-1.4 in system RAM
->> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
-   | LatentDiffusion: Running in eps-prediction mode
-   | DiffusionWrapper has 859.52 M params.
-   | Making attention of type 'vanilla' with 512 in_channels
-   | Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
-   | Making attention of type 'vanilla' with 512 in_channels
-   | Using faster float16 precision
-invoke> 
-</pre>
-
-###!edit_model <name_of_model>
+#### `!edit_model <name_of_model>`
 
 The `!edit_model` command can be used to modify a model that is already defined
 in `config/models.yaml`. Call it with the short name of the model you wish to
@@ -457,17 +453,12 @@ OK to import [n]? y
 ...
 </pre>
 
-======= invoke> !fix 000017.4829112.gfpgan-00.png --embiggen 3 ...lots of
-text... Outputs: [2] outputs/img-samples/000018.2273800735.embiggen-00.png: !fix
-"outputs/img-samples/000017.243781548.gfpgan-00.png" -s 50 -S 2273800735 -W 512
--H 512 -C 7.5 -A k_lms --embiggen 3.0 0.75 0.25 ```
-
-## History processing
+### History processing
 
 The CLI provides a series of convenient commands for reviewing previous actions,
 retrieving them, modifying them, and re-running them.
 
-### !history
+#### `!history`
 
 The invoke script keeps track of all the commands you issue during a session,
 allowing you to re-run them. On Mac and Linux systems, it also writes the
@@ -479,20 +470,22 @@ during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
 can then repeat a command by using the command `!NNN`, where "NNN" is the
 history line number. For example:
 
-```bash
-invoke> !history
-...
-[14] happy woman sitting under tree wearing broad hat and flowing garment
-[15] beautiful woman sitting under tree wearing broad hat and flowing garment
-[18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
-[20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-...
-invoke> !20
-invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-```
+!!! example ""
 
-### !fetch
+    ```bash
+    invoke> !history
+    ...
+    [14] happy woman sitting under tree wearing broad hat and flowing garment
+    [15] beautiful woman sitting under tree wearing broad hat and flowing garment
+    [18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
+    [20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    ...
+    invoke> !20
+    invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    ```
+
+####`!fetch`
 
 This command retrieves the generation parameters from a previously generated
 image and either loads them into the command line (Linux|Mac), or prints them
@@ -502,33 +495,36 @@ a folder with image png files, and wildcard \*.png to retrieve the dream command
 used to generate the images, and save them to a file commands.txt for further
 processing.
 
-This example loads the generation command for a single png file:
+!!! example "load the generation command for a single png file"
 
-```bash
-invoke> !fetch 0000015.8929913.png
-# the script returns the next line, ready for editing and running:
-invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
-```
+    ```bash
+    invoke> !fetch 0000015.8929913.png
+    # the script returns the next line, ready for editing and running:
+    invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
+    ```
 
-This one fetches the generation commands from a batch of files and stores them
-into `selected.txt`:
+!!! example "fetch the generation commands from a batch of files and store them into `selected.txt`"
 
-```bash
-invoke> !fetch outputs\selected-imgs\*.png selected.txt
-```
+    ```bash
+    invoke> !fetch outputs\selected-imgs\*.png selected.txt
+    ```
 
-### !replay
+#### `!replay`
 
 This command replays a text file generated by !fetch or created manually
 
-```
-invoke> !replay outputs\selected-imgs\selected.txt
-```
+!!! example
 
-Note that these commands may behave unexpectedly if given a PNG file that was
-not generated by InvokeAI.
+    ```bash
+    invoke> !replay outputs\selected-imgs\selected.txt
+    ```
 
-### !search <search string>
+!!! note
+
+    These commands may behave unexpectedly if given a PNG file that was
+    not generated by InvokeAI.
+
+#### `!search <search string>`
 
 This is similar to !history but it only returns lines that contain
 `search string`. For example:
@@ -538,7 +534,7 @@ invoke> !search surreal
 [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
 ```
 
-### `!clear`
+#### `!clear`
 
 This clears the search history from memory and disk. Be advised that this
 operation is irreversible and does not issue any warnings!

docs/features/CONCEPTS.md

@@ -0,0 +1,164 @@
+---
+title: Styles and Subjects
+---
+
+# :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
+
+## Using Textual Inversion Files
+
+Textual inversion (TI) files are small models that customize the output of
+Stable Diffusion image generation. They can augment SD with specialized subjects
+and artistic styles. They are also known as "embeds" in the machine learning
+world.
+
+Each TI file introduces one or more vocabulary terms to the SD model. These are
+known in InvokeAI as "triggers." Triggers are often, but not always, denoted
+using angle brackets as in "<trigger-phrase>". The two most common type of
+TI files that you'll encounter are `.pt` and `.bin` files, which are produced by
+different TI training packages. InvokeAI supports both formats, but its
+[built-in TI training system](TEXTUAL_INVERSION.md) produces `.pt`.
+
+The [Hugging Face company](https://huggingface.co/sd-concepts-library) has
+amassed a large ligrary of >800 community-contributed TI files covering a
+broad range of subjects and styles. InvokeAI has built-in support for this
+library which downloads and merges TI files automatically upon request. You can
+also install your own or others' TI files by placing them in a designated
+directory.
+
+You may also be interested in using [LoRA Models](LORAS.md) to
+generate images with specialized styles and subjects.
+
+### An Example
+
+Here are a few examples to illustrate how Textual Inversion works. All
+these images were generated using the command-line client and the
+Stable Diffusion 1.5 model:
+
+|         Japanese gardener          | Japanese gardener <ghibli-face> | Japanese gardener <hoi4-leaders> | Japanese gardener <cartoona-animals> |
+| :--------------------------------: | :-----------------------------------: | :------------------------------------: | :----------------------------------------: |
+| ![](../assets/concepts/image1.png) |  ![](../assets/concepts/image2.png)   |   ![](../assets/concepts/image3.png)   |     ![](../assets/concepts/image4.png)     |
+
+You can also combine styles and concepts:
+
+<figure markdown>
+  | A portrait of &lt;alf&gt; in &lt;cartoona-animal&gt; style |
+  | :--------------------------------------------------------: |
+  | ![](../assets/concepts/image5.png)                         |
+</figure>
+## Using a Hugging Face Concept
+
+!!! warning "Authenticating to HuggingFace"
+
+    Some concepts require valid authentication to HuggingFace. Without it, they will not be downloaded
+    and will be silently ignored.
+
+    If you used an installer to install InvokeAI, you may have already set a HuggingFace token.
+    If you skipped this step, you can:
+
+    - run the InvokeAI configuration script again (if you used a manual installer): `invokeai-configure`
+    - set one of the `HUGGINGFACE_TOKEN` or `HUGGING_FACE_HUB_TOKEN` environment variables to contain your token
+
+    Finally, if you already used any HuggingFace library on your computer, you might already have a token
+    in your local cache. Check for a hidden `.huggingface` directory in your home folder. If it
+    contains a `token` file, then you are all set.
+
+
+Hugging Face TI concepts are downloaded and installed automatically as you
+require them. This requires your machine to be connected to the Internet. To
+find out what each concept is for, you can browse the
+[Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
+look at examples of what each concept produces.
+
+When you have an idea of a concept you wish to try, go to the command-line
+client (CLI) and type a `<` character and the beginning of the Hugging Face
+concept name you wish to load. Press ++tab++, and the CLI will show you all
+matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
+~800 concepts, but be prepared to scroll up to see them all! If there is more
+than one match you can continue to type and ++tab++ until the concept is
+completed.
+
+!!! example
+
+    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
+
+    ```py
+    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
+    ```
+
+    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
+    because this is a unique match.
+
+    Finish your prompt and generate as usual. You may include multiple concept terms
+    in the prompt.
+
+If you have never used this concept before, you will see a message that the TI
+model is being downloaded and installed. After this, the concept will be saved
+locally (in the `models/sd-concepts-library` directory) for future use.
+
+Several steps happen during downloading and installation, including a scan of
+the file for malicious code. Should any errors occur, you will be warned and the
+concept will fail to load. Generation will then continue treating the trigger
+term as a normal string of characters (e.g. as literal `<ghibli-face>`).
+
+You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
+autocompletion at this time.
+
+## Installing your Own TI Files
+
+You may install any number of `.pt` and `.bin` files simply by copying them into
+the `embeddings` directory of the InvokeAI runtime directory (usually `invokeai`
+in your home directory). You may create subdirectories in order to organize the
+files in any way you wish. Be careful not to overwrite one file with another.
+For example, TI files generated by the Hugging Face toolkit share the named
+`learned_embedding.bin`. You can use subdirectories to keep them distinct.
+
+At startup time, InvokeAI will scan the `embeddings` directory and load any TI
+files it finds there. At startup you will see messages similar to these:
+
+```bash
+>> Loading embeddings from /data/lstein/invokeai-2.3/embeddings
+   | Loading v1 embedding file: style-hamunaptra
+   | Loading v4 embedding file: embeddings/learned_embeds-steps-500.bin
+   | Loading v2 embedding file: lfa
+   | Loading v3 embedding file: easynegative
+   | Loading v1 embedding file: rem_rezero
+   | Loading v2 embedding file: midj-strong
+   | Loading v4 embedding file: anime-background-style-v2/learned_embeds.bin
+   | Loading v4 embedding file: kamon-style/learned_embeds.bin
+   ** Notice: kamon-style/learned_embeds.bin was trained on a model with an incompatible token dimension: 768 vs 1024.
+>> Textual inversion triggers: <anime-background-style-v2>, <easynegative>, <lfa>, <midj-strong>, <milo>, Rem3-2600, Style-Hamunaptra
+```
+
+Textual Inversion embeddings trained on version 1.X stable diffusion
+models are incompatible with version 2.X models and vice-versa.
+
+After the embeddings load, InvokeAI will print out a list of all the
+recognized trigger terms. To trigger the term, include it in the
+prompt exactly as written, including angle brackets if any and
+respecting the capitalization.
+
+There are at least four different embedding file formats, and each uses
+a different convention for the trigger terms. In some cases, the
+trigger term is specified in the file contents and may or may not be
+surrounded by angle brackets. In the example above, `Rem3-2600`,
+`Style-Hamunaptra`, and `<midj-strong>` were specified this way and
+there is no easy way to change the term.
+
+In other cases the trigger term is not contained within the embedding
+file. In this case, InvokeAI constructs a trigger term consisting of
+the base name of the file (without the file extension) surrounded by
+angle brackets. In the example above `<easynegative`> is such a file
+(the filename was `easynegative.safetensors`). In such cases, you can
+change the trigger term simply by renaming the file.
+
+## Training your own Textual Inversion models
+
+InvokeAI provides a script that lets you train your own Textual
+Inversion embeddings using a small number (about a half-dozen) images
+of your desired style or subject. Please see [Textual
+Inversion](TEXTUAL_INVERSION.md) for details.
+
+## Further Reading
+
+Please see [the repository](https://github.com/rinongal/textual_inversion) and
+associated paper for details and limitations.

docs/features/EMBIGGEN.md

@@ -85,7 +85,7 @@ increasing size, every tile after the first in a row or column
 effectively only covers an extra `1 - overlap_ratio` on each axis. If
 the input/`--init_img` is same size as a tile, the ideal (for time)
 scaling factors with the default overlap (0.25) are 1.75, 2.5, 3.25,
-4.0 etc..
+4.0, etc.
 
 `-embiggen_tiles <spaced list of tiles>`
 
@@ -100,6 +100,15 @@ Tiles are numbered starting with one, and left-to-right,
 top-to-bottom.  So, if you are generating a 3x3 tiled image, the
 middle row would be `4 5 6`.
 
+`-embiggen_strength <strength>`
+
+Another advanced option if you want to experiment with the strength parameter
+that embiggen uses when it calls Img2Img. Values range from 0.0 to 1.0
+and lower values preserve more of the character of the initial image.
+Values that are too high will result in a completely different end image,
+while values that are too low will result in an image not dissimilar to one
+you would get with ESRGAN upscaling alone. The default value is 0.4.
+
 ### Examples
 
 !!! example ""

docs/features/IMG2IMG.md

@@ -4,29 +4,38 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-## `img2img`
+Both the Web and command-line interfaces provide an "img2img" feature
+that lets you seed your creations with an initial drawing or
+photo. This is a really cool feature that tells stable diffusion to
+build the prompt on top of the image you provide, preserving the
+original's basic shape and layout.
 
-This script also provides an `img2img` feature that lets you seed your creations
-with an initial drawing or photo. This is a really cool feature that tells
-stable diffusion to build the prompt on top of the image you provide, preserving
-the original's basic shape and layout. To use it, provide the `--init_img`
-option as shown here:
+See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
+in the InvokeAI web server. This document describes how to use img2img
+in the command-line tool.
 
-```commandline
-tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
-```
+## Basic Usage
 
-This will take the original image shown here:
+Launch the command-line client by launching `invoke.sh`/`invoke.bat`
+and choosing option (1). Alternative, activate the InvokeAI
+environment and issue the command `invokeai`.
 
-<figure markdown>
-![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 }
-</figure>
+Once the `invoke> ` prompt appears, you can start an img2img render by
+pointing to a seed file with the `-I` option as shown here:
 
-and generate a new image based on it as shown here:
+!!! example ""
 
-<figure markdown>
-![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 }
-</figure>
+    ```commandline
+    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
+    ```
+
+    <figure markdown>
+
+    | original image | generated image |
+    | :------------: | :-------------: |
+    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
+
+    </figure>
 
 The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
 (`-f`) controls how much the original will be modified, ranging from `0.0` (keep
@@ -88,13 +97,15 @@ from a prompt. If the step count is 10, then the "latent space" (Stable
 Diffusion's internal representation of the image) for the prompt "fire" with
 seed `1592514025` develops something like this:
 
-```bash
-invoke> "fire" -s10 -W384 -H384 -S1592514025
-```
+!!! example ""
 
-<figure markdown>
-![latent steps](../assets/img2img/000019.steps.png)
-</figure>
+    ```bash
+    invoke> "fire" -s10 -W384 -H384 -S1592514025
+    ```
+
+    <figure markdown>
+    ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
+    </figure>
 
 Put simply: starting from a frame of fuzz/static, SD finds details in each frame
 that it thinks look like "fire" and brings them a little bit more into focus,
@@ -109,25 +120,23 @@ into the sequence at the appropriate point, with just the right amount of noise.
 
 ### A concrete example
 
-I want SD to draw a fire based on this hand-drawn image:
+!!! example "I want SD to draw a fire based on this hand-drawn image"
 
-<figure markdown>
-![drawing of a fireplace](../assets/img2img/fire-drawing.png)
-</figure>
+    ![drawing of a fireplace](../assets/img2img/fire-drawing.png){ align=left }
 
-Let's only do 10 steps, to make it easier to see what's happening. If strength
-is `0.7`, this is what the internal steps the algorithm has to take will look
-like:
+    Let's only do 10 steps, to make it easier to see what's happening. If strength
+    is `0.7`, this is what the internal steps the algorithm has to take will look
+    like:
 
-<figure markdown>
-![gravity32](../assets/img2img/000032.steps.gravity.png)
-</figure>
+    <figure markdown>
+    ![gravity32](../assets/img2img/000032.steps.gravity.png)
+    </figure>
 
-With strength `0.4`, the steps look more like this:
+    With strength `0.4`, the steps look more like this:
 
-<figure markdown>
-![gravity30](../assets/img2img/000030.steps.gravity.png)
-</figure>
+    <figure markdown>
+    ![gravity30](../assets/img2img/000030.steps.gravity.png)
+    </figure>
 
 Notice how much more fuzzy the starting image is for strength `0.7` compared to
 `0.4`, and notice also how much longer the sequence is with `0.7`:

docs/features/INPAINTING.md

@@ -158,7 +158,7 @@ when filling in missing regions. It has an almost uncanny ability to blend the
 new regions with existing ones in a semantically coherent way.
 
 To install the inpainting model, follow the
-[instructions](../installation/INSTALLING_MODELS.md) for installing a new model.
+[instructions](../installation/050_INSTALLING_MODELS.md) for installing a new model.
 You may use either the CLI (`invoke.py` script) or directly edit the
 `configs/models.yaml` configuration file to do this. The main thing to watch out
 for is that the the model `config` option must be set up to use

docs/features/LORAS.md

@@ -0,0 +1,100 @@
+---
+title: Low-Rank Adaptation (LoRA) Models
+---
+
+# :material-library-shelves: Using Low-Rank Adaptation (LoRA) Models
+
+## Introduction
+
+LoRA is a technique for fine-tuning Stable Diffusion models using much
+less time and memory than traditional training techniques. The
+resulting model files are much smaller than full model files, and can
+be used to generate specialized styles and subjects.
+
+LoRAs are built on top of Stable Diffusion v1.x or 2.x checkpoint or
+diffusers models. To load a LoRA, you include its name in the text
+prompt using a simple syntax described below. While you will generally
+get the best results when you use the same model the LoRA was trained
+on, they will work to a greater or lesser extent with other models.
+The major caveat is that a LoRA built on top of a SD v1.x model cannot
+be used with a v2.x model, and vice-versa. If you try, you will get an
+error! You may refer to multiple LoRAs in your prompt.
+
+When you apply a LoRA in a prompt you can specify a weight. The higher
+the weight, the more influence it will have on the image. Useful
+ranges for weights are usually in the 0.0 to 1.0 range (with ranges
+between 0.5 and 1.0 being most typical). However you can specify a
+higher weight if you wish. Like models, each LoRA has a slightly
+different useful weight range and will interact with other generation
+parameters such as the CFG, step count and sampler. The author of the
+LoRA will often provide guidance on the best settings, but feel free
+to experiment. Be aware that it often helps to reduce the CFG value
+when using LoRAs.
+
+## Installing LoRAs
+
+This is very easy! Download a LoRA model file from your favorite site
+(e.g. [CIVITAI](https://civitai.com) and place it in the `loras`
+folder in the InvokeAI root directory (usually `~invokeai/loras` on
+Linux/Macintosh machines, and `C:\Users\your-name\invokeai/loras` on
+Windows systems). If the `loras` folder does not already exist, just
+create it. The vast majority of LoRA models use the Kohya file format,
+which is a type of `.safetensors` file.
+
+You may change where InvokeAI looks for the `loras` folder by passing the
+`--lora_directory` option to the `invoke.sh`/`invoke.bat` launcher, or
+by placing the option in `invokeai.init`. For example:
+
+```
+invoke.sh --lora_directory=C:\Users\your-name\SDModels\lora
+```
+
+## Using a LoRA in your prompt
+
+To activate a LoRA use the syntax `withLora(my-lora-name,weight)`
+somewhere in the text of the prompt. The position doesn't matter; use
+whatever is most comfortable for you.
+
+For example, if you have a LoRA named `parchment_people.safetensors`
+in your `loras` directory, you can load it with a weight of 0.9 with a
+prompt like this one:
+
+```
+family sitting at dinner table withLora(parchment_people,0.9)
+```
+
+Add additional `withLora()` phrases to load more LoRAs.
+
+You may omit the weight entirely to default to a weight of 1.0:
+
+```
+family sitting at dinner table withLora(parchment_people)
+```
+
+If you watch the console as your prompt executes, you will see
+messages relating to the loading and execution of the LoRA. If things
+don't work as expected, note down the console messages and report them
+on the InvokeAI Issues pages or Discord channel.
+
+That's pretty much all you need to know!
+
+## Training Kohya Models
+
+InvokeAI cannot currently train LoRA models, but it can load and use
+existing LoRA ones to generate images. While there are several LoRA
+model file formats, the predominant one is ["Kohya"
+format](https://github.com/kohya-ss/sd-scripts), written by [Kohya
+S.](https://github.com/kohya-ss). InvokeAI provides support for this
+format. For creating your own Kohya models, we recommend the Windows
+GUI written by former InvokeAI-team member
+[bmaltais](https://github.com/bmaltais), which can be found at
+[kohya_ss](https://github.com/bmaltais/kohya_ss).
+
+We can also recommend the [HuggingFace DreamBooth Training
+UI](https://huggingface.co/spaces/lora-library/LoRA-DreamBooth-Training-UI),
+a paid service that supports both Textual Inversion and LoRA training.
+
+You may also be interested in [Textual
+Inversion](TEXTUAL_INVERSION.md) training, which is supported by
+InvokeAI as a text console and command-line tool.
+

docs/features/MODEL_MERGING.md

@@ -0,0 +1,76 @@
+---
+title: Model Merging
+---
+
+# :material-image-off: Model Merging
+
+## How to Merge Models
+
+As of version 2.3, InvokeAI comes with a script that allows you to
+merge two or three diffusers-type models into a new merged model. The
+resulting model will combine characteristics of the original, and can
+be used to teach an old model new tricks.
+
+You may run the merge script by starting the invoke launcher
+(`invoke.sh` or `invoke.bat`) and choosing the option for _merge
+models_. This will launch a text-based interactive user interface that
+prompts you to select the models to merge, how to merge them, and the
+merged model name.
+
+Alternatively you may activate InvokeAI's virtual environment from the
+command line, and call the script via `merge_models --gui` to open up
+a version that has a nice graphical front end. To get the commandline-
+only version, omit `--gui`.
+
+The user interface for the text-based interactive script is
+straightforward. It shows you a series of setting fields. Use control-N (^N)
+to move to the next field, and control-P (^P) to move to the previous
+one. You can also use TAB and shift-TAB to move forward and
+backward. Once you are in a multiple choice field, use the up and down
+cursor arrows to move to your desired selection, and press <SPACE> or
+<ENTER> to select it. Change text fields by typing in them, and adjust
+scrollbars using the left and right arrow keys.
+
+Once you are happy with your settings, press the OK button. Note that
+there may be two pages of settings, depending on the height of your
+screen, and the OK button may be on the second page. Advance past the
+last field of the first page to get to the second page, and reverse
+this to get back.
+
+If the merge runs successfully, it will create a new diffusers model
+under the selected name and register it with InvokeAI.
+
+## The Settings
+
+* Model Selection -- there are three multiple choice fields that
+  display all the diffusers-style models that InvokeAI knows about.
+  If you do not see the model you are looking for, then it is probably
+  a legacy checkpoint model and needs to be converted using the
+  `invoke` command-line client and its `!optimize` command. You
+  must select at least two models to merge. The third can be left at
+  "None" if you desire.
+
+* Alpha -- This is the ratio to use when combining models. It ranges
+  from 0 to 1. The higher the value, the more weight is given to the
+  2d and (optionally) 3d models. So if you have two models named "A"
+  and "B", an alpha value of 0.25 will give you a merged model that is
+  25% A and 75% B.
+
+* Interpolation Method -- This is the method used to combine
+  weights. The options are "weighted_sum" (the default), "sigmoid",
+  "inv_sigmoid" and "add_difference". Each produces slightly different
+  results. When three models are in use, only "add_difference" is
+  available. (TODO: cite a reference that describes what these
+  interpolation methods actually do and how to decide among them).
+
+* Force -- Not all models are compatible with each other. The merge
+  script will check for compatibility and refuse to merge ones that
+  are incompatible. Set this checkbox to try merging anyway.
+
+* Name for merged model - This is the name for the new model. Please
+  use InvokeAI conventions - only alphanumeric letters and the
+  characters ".+-".
+
+## Caveats
+
+This is a new script and may contain bugs.

docs/features/NSFW.md

@@ -0,0 +1,89 @@
+---
+title: The NSFW Checker
+---
+
+# :material-image-off: NSFW Checker
+
+## The NSFW ("Safety") Checker
+
+The Stable Diffusion image generation models will produce sexual
+imagery if deliberately prompted, and will occasionally produce such
+images when this is not intended. Such images are colloquially known
+as "Not Safe for Work" (NSFW). This behavior is due to the nature of
+the training set that Stable Diffusion was trained on, which culled
+millions of "aesthetic" images from the Internet.
+
+You may not wish to be exposed to these images, and in some
+jurisdictions it may be illegal to publicly distribute such imagery,
+including mounting a publicly-available server that provides
+unfiltered images to the public. Furthermore, the [Stable Diffusion
+weights
+License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-ModelWeights.txt)
+forbids the model from being used to "exploit any of the
+vulnerabilities of a specific group of persons."
+
+For these reasons Stable Diffusion offers a "safety checker," a
+machine learning model trained to recognize potentially disturbing
+imagery. When a potentially NSFW image is detected, the checker will
+blur the image and paste a warning icon on top. The checker can be
+turned on and off on the command line using `--nsfw_checker` and
+`--no-nsfw_checker`.
+
+At installation time, InvokeAI will ask whether the checker should be
+activated by default (neither argument given on the command line). The
+response is stored in the InvokeAI initialization file (usually
+`.invokeai` in your home directory). You can change the default at any
+time by opening this file in a text editor and commenting or
+uncommenting the line `--nsfw_checker`.
+
+## Caveats
+
+There are a number of caveats that you need to be aware of.
+
+### Accuracy
+
+The checker is [not perfect](https://arxiv.org/abs/2210.04610).It will
+occasionally flag innocuous images (false positives), and will
+frequently miss violent and gory imagery (false negatives). It rarely
+fails to flag sexual imagery, but this has been known to happen. For
+these reasons, the InvokeAI team prefers to refer to the software as a
+"NSFW Checker" rather than "safety checker."
+
+### Memory Usage and Performance
+
+The NSFW checker consumes an additional 1.2G of GPU VRAM on top of the
+3.4G of VRAM used by Stable Diffusion v1.5 (this is with
+half-precision arithmetic). This means that the checker will not run
+successfully on GPU cards with less than 6GB VRAM, and will reduce the
+size of the images that you can produce.
+
+The checker also introduces a slight performance penalty. Images will
+take ~1 second longer to generate when the checker is
+activated. Generally this is not noticeable.
+
+### Intermediate Images in the Web UI
+
+The checker only operates on the final image produced by the Stable
+Diffusion algorithm. If you are using the Web UI and have enabled the
+display of intermediate images, you will briefly be exposed to a
+low-resolution (mosaicized) version of the final image before it is
+flagged by the checker and replaced by a fully blurred version. You
+are encouraged to turn **off** intermediate image rendering when you
+are using the checker. Future versions of InvokeAI will apply
+additional blurring to intermediate images when the checker is active.
+
+### Watermarking
+
+InvokeAI does not apply any sort of watermark to images it
+generates. However, it does write metadata into the PNG data area,
+including the prompt used to generate the image and relevant parameter
+settings. These fields can be examined using the `sd-metadata.py`
+script that comes with the InvokeAI package.
+
+Note that several other Stable Diffusion distributions offer
+wavelet-based "invisible" watermarking. We have experimented with the
+library used to generate these watermarks and have reached the
+conclusion that while the watermarking library may be adding
+watermarks to PNG images, the currently available version is unable to
+retrieve them successfully. If and when a functioning version of the
+library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -133,29 +133,6 @@ outputs = g.txt2img("a unicorn in manhattan")
 
 Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
 
-Please see ldm/generate.py for more information. A set of example scripts is coming RSN.
+Please see the documentation in ldm/generate.py for more information.
 
 ---
-
-## **Preload Models**
-
-In situations where you have limited internet connectivity or are blocked behind a firewall, you can
-use the preload script to preload the required files for Stable Diffusion to run.
-
-The preload script `scripts/preload_models.py` needs to be run once at least while connected to the
-internet. In the following runs, it will load up the cached versions of the required files from the
-`.cache` directory of the system.
-
-```bash
-(invokeai) ~/stable-diffusion$ python3 ./scripts/preload_models.py
-preloading bert tokenizer...
-Downloading: 100%|██████████████████████████████████| 28.0/28.0 [00:00<00:00, 49.3kB/s]
-Downloading: 100%|██████████████████████████████████| 226k/226k [00:00<00:00, 2.79MB/s]
-Downloading: 100%|██████████████████████████████████| 455k/455k [00:00<00:00, 4.36MB/s]
-Downloading: 100%|██████████████████████████████████| 570/570 [00:00<00:00, 477kB/s]
-...success
-preloading kornia requirements...
-Downloading: "https://github.com/DagnyT/hardnet/raw/master/pretrained/train_liberty_with_aug/checkpoint_liberty_with_aug.pth" to /u/lstein/.cache/torch/hub/checkpoints/checkpoint_liberty_with_aug.pth
-100%|███████████████████████████████████████████████| 5.10M/5.10M [00:00<00:00, 101MB/s]
-...success
-```

docs/features/OUTPAINTING.md

@@ -120,7 +120,7 @@ A number of caveats:
    (`--iterations`) argument.
 
 3. Your results will be _much_ better if you use the `inpaint-1.5` model
-   released by runwayML and installed by default by `scripts/preload_models.py`.
+   released by runwayML and installed by default by `invokeai-configure`.
    This model was trained specifically to harmoniously fill in image gaps. The
    standard model will work as well, but you may notice color discontinuities at
    the border.

docs/features/POSTPROCESS.md

@@ -28,21 +28,17 @@ should "just work" without further intervention. Simply pass the `--upscale`
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
-loaded when you run `scripts/preload_models.py`. If GFPAN is failing with an
+loaded when you run `invokeai-configure`. If GFPAN is failing with an
 error, please run the following from the InvokeAI directory:
 
 ```bash
-python scripts/preload_models.py
+invokeai-configure
 ```
 
 If you do not run this script in advance, the GFPGAN module will attempt to
 download the models files the first time you try to perform facial
 reconstruction.
 
-## Usage
-
-You will now have access to two new prompt arguments.
-
 ### Upscaling
 
 `-U : <upscaling_factor> <upscaling_strength>`
@@ -110,7 +106,7 @@ This repo also allows you to perform face restoration using
 [CodeFormer](https://github.com/sczhou/CodeFormer).
 
 In order to setup CodeFormer to work, you need to download the models like with
-GFPGAN. You can do this either by running `preload_models.py` or by manually
+GFPGAN. You can do this either by running `invokeai-configure` or by manually
 downloading the
 [model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
 and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
@@ -119,7 +115,7 @@ You can use `-ft` prompt argument to swap between CodeFormer and the default
 GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
 strength of the restoration effect.
 
-### Usage
+### CodeFormer Usage
 
 The following command will perform face restoration with CodeFormer instead of
 the default gfpgan.
@@ -160,7 +156,7 @@ A new file named `000044.2945021133.fixed.png` will be created in the output
 directory. Note that the `!fix` command does not replace the original file,
 unlike the behavior at generate time.
 
-### Disabling
+## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and

docs/features/PROMPTS.md

@@ -20,16 +20,55 @@ would type at the invoke> prompt:
 Then pass this file's name to `invoke.py` when you invoke it:
 
 ```bash
-(invokeai) ~/stable-diffusion$ python3 scripts/invoke.py --from_file "path/to/prompts.txt"
+python scripts/invoke.py --from_file "/path/to/prompts.txt"
 ```
 
-You may read a series of prompts from standard input by providing a filename of
-`-`:
+You may also read a series of prompts from standard input by providing
+a filename of `-`. For example, here is a python script that creates a
+matrix of prompts, each one varying slightly:
 
 ```bash
-(invokeai) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/invoke.py --from_file -
+#!/usr/bin/env python
+
+adjectives = ['sunny','rainy','overcast']
+samplers = ['k_lms','k_euler_a','k_heun']
+cfg = [7.5, 9, 11]
+
+for adj in adjectives:
+    for samp in samplers:
+        for cg in cfg:
+            print(f'a {adj} day -A{samp} -C{cg}')
 ```
 
+Its output looks like this (abbreviated):
+
+```bash
+a sunny day -Aklms -C7.5
+a sunny day -Aklms -C9
+a sunny day -Aklms -C11
+a sunny day -Ak_euler_a -C7.5
+a sunny day -Ak_euler_a -C9
+...
+a overcast day -Ak_heun -C9
+a overcast day -Ak_heun -C11
+```
+
+To feed it to invoke.py, pass the filename of "-"
+
+```bash
+python matrix.py | python scripts/invoke.py --from_file -
+```
+
+When the script is finished, each of the 27 combinations
+of adjective, sampler and CFG will be executed.
+
+The command-line interface provides `!fetch` and `!replay` commands
+which allow you to read the prompts from a single previously-generated
+image or a whole directory of them, write the prompts to a file, and
+then replay them. Or you can create your own file of prompts and feed
+them to the command-line client from within an interactive session.
+See [Command-Line Interface](CLI.md) for details.
+
 ---
 
 ## **Negative and Unconditioned Prompts**
@@ -51,7 +90,9 @@ original prompt:
 `#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
+
 ![step1](../assets/negative_prompt_walkthru/step1.png)
+
 </figure>
 
 That image has a woman, so if we want the horse without a rider, we can
@@ -61,7 +102,9 @@ this:
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
+
 ![step2](../assets/negative_prompt_walkthru/step2.png)
+
 </figure>
 
 That's nice - but say we also don't want the image to be quite so blue. We can
@@ -70,7 +113,9 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
+
 ![step3](../assets/negative_prompt_walkthru/step3.png)
+
 </figure>
 
 Getting close - but there's no sense in having a saddle when our horse doesn't
@@ -79,7 +124,9 @@ have a rider, so we'll add one more negative prompt: [woman blue saddle].
 `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
 
 <figure markdown>
+
 ![step4](../assets/negative_prompt_walkthru/step4.png)
+
 </figure>
 
 !!! notes "Notes about this feature:"
@@ -124,8 +171,12 @@ this prompt of `a man picking apricots from a tree`, let's see what happens if
 we increase and decrease how much attention we want Stable Diffusion to pay to
 the word `apricots`:
 
+<figure markdown>
+
 ![an AI generated image of a man picking apricots from a tree](../assets/prompt_syntax/apricots-0.png)
 
+</figure>
+
 Using `-` to reduce apricot-ness:
 
 | `a man picking apricots- from a tree`                                                                                          | `a man picking apricots-- from a tree`                                                                                                        | `a man picking apricots--- from a tree`                                                                                                    |
@@ -141,8 +192,12 @@ Using `+` to increase apricot-ness:
 You can also change the balance between different parts of a prompt. For
 example, below is a `mountain man`:
 
+<figure markdown>
+
 ![an AI generated image of a mountain man](../assets/prompt_syntax/mountain-man.png)
 
+</figure>
+
 And here he is with more mountain:
 
 | `mountain+ man`                                | `mountain++ man`                               | `mountain+++ man`                              |
@@ -184,28 +239,24 @@ Generate an image with a given prompt, record the seed of the image, and then
 use the `prompt2prompt` syntax to substitute words in the original prompt for
 words in a new prompt. This works for `img2img` as well.
 
-- `a ("fluffy cat").swap("smiling dog") eating a hotdog`.
-  - quotes optional: `a (fluffy cat).swap(smiling dog) eating a hotdog`.
-  - for single word substitutions parentheses are also optional:
-    `a cat.swap(dog) eating a hotdog`.
-- Supports options `s_start`, `s_end`, `t_start`, `t_end` (each 0-1) loosely
-  corresponding to bloc97's `prompt_edit_spatial_start/_end` and
-  `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
-  intuitively understand.
-  - Example usage:`a (cat).swap(dog, s_end=0.3) eating a hotdog` - the `s_end`
-    argument means that the "spatial" (self-attention) edit will stop having any
-    effect after 30% (=0.3) of the steps have been done, leaving Stable
-    Diffusion with 70% of the steps where it is free to decide for itself how to
-    reshape the cat-form into a dog form.
-  - The numbers represent a percentage through the step sequence where the edits
-    should happen. 0 means the start (noisy starting image), 1 is the end (final
-    image).
-    - For img2img, the step sequence does not start at 0 but instead at
-      (1-strength) - so if strength is 0.7, s_start and s_end must both be
-      greater than 0.3 (1-0.7) to have any effect.
-- Convenience option `shape_freedom` (0-1) to specify how much "freedom" Stable
-  Diffusion should have to change the shape of the subject being swapped.
-  - `a (cat).swap(dog, shape_freedom=0.5) eating a hotdog`.
+For example, consider the prompt `a cat.swap(dog) playing with a ball in the forest`. Normally, because of the word words interact with each other when doing a stable diffusion image generation, these two prompts would generate different compositions:
+  - `a cat playing with a ball in the forest`
+  - `a dog playing with a ball in the forest`
+
+| `a cat playing with a ball in the forest` | `a dog playing with a ball in the forest` |
+| --- | --- |
+| img | img |
+
+
+      - For multiple word swaps, use parentheses: `a (fluffy cat).swap(barking dog) playing with a ball in the forest`.
+      - To swap a comma, use quotes: `a ("fluffy, grey cat").swap("big, barking dog") playing with a ball in the forest`.
+- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to bloc97's `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
+  intuitively understand. `t_start` and `t_end` are used to control on which steps cross-attention control should run. With the default values `t_start=0` and `t_end=1`, cross-attention control is active on every step of image generation. Other values can be used to turn cross-attention control off for part of the image generation process.
+    - For example, if doing a diffusion with 10 steps for the prompt is `a cat.swap(dog, t_start=0.3, t_end=1.0) playing with a ball in the forest`, the first 3 steps will be run as `a cat playing with a ball in the forest`, while the last 7 steps will run as `a dog playing with a ball in the forest`, but the pixels that represent `dog` will be locked to the pixels that would have represented `cat` if the `cat` prompt had been used instead.
+    - Conversely, for `a cat.swap(dog, t_start=0, t_end=0.7) playing with a ball in the forest`, the first 7 steps will run as `a dog playing with a ball in the forest` with the pixels that represent `dog` locked to the same pixels that would have represented `cat` if the `cat` prompt was being used instead. The final 3 steps will just run `a cat playing with a ball in the forest`.
+    > For img2img, the step sequence does not start at 0 but instead at `(1.0-strength)` - so if the img2img `strength` is `0.7`, `t_start` and `t_end` must both be greater than `0.3` (`1.0-0.7`) to have any effect.
+
+Prompt2prompt `.swap()` is not compatible with xformers, which will be temporarily disabled when doing a `.swap()` - so you should expect to use more VRAM and run slower that with xformers enabled.
 
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
@@ -259,14 +310,18 @@ usual, unless you fix the seed, the prompts will give you different results each
 time you run them.
 
 <figure markdown>
+
 ### "blue sphere, red cube, hybrid"
+
 </figure>
 
 This example doesn't use melding at all and represents the default way of mixing
 concepts.
 
 <figure markdown>
+
 ![blue-sphere-red-cube-hyprid](../assets/prompt-blending/blue-sphere-red-cube-hybrid.png)
+
 </figure>
 
 It's interesting to see how the AI expressed the concept of "cube" as the four
@@ -274,6 +329,7 @@ quadrants of the enclosing frame. If you look closely, there is depth there, so
 the enclosing frame is actually a cube.
 
 <figure markdown>
+
 ### "blue sphere:0.25 red cube:0.75 hybrid"
 
 ![blue-sphere-25-red-cube-75](../assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png)
@@ -286,6 +342,7 @@ the AI's "latent space" of semantic representations. Where is Ludwig
 Wittgenstein when you need him?
 
 <figure markdown>
+
 ### "blue sphere:0.75 red cube:0.25 hybrid"
 
 ![blue-sphere-75-red-cube-25](../assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png)
@@ -296,6 +353,7 @@ Definitely more blue-spherey. The cube is gone entirely, but it's really cool
 abstract art.
 
 <figure markdown>
+
 ### "blue sphere:0.5 red cube:0.5 hybrid"
 
 ![blue-sphere-5-red-cube-5-hybrid](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png)
@@ -306,6 +364,7 @@ Whoa...! I see blue and red, but no spheres or cubes. Is the word "hybrid"
 summoning up the concept of some sort of scifi creature? Let's find out.
 
 <figure markdown>
+
 ### "blue sphere:0.5 red cube:0.5"
 
 ![blue-sphere-5-red-cube-5](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png)

docs/features/TEXTUAL_INVERSION.md

@@ -10,83 +10,326 @@ You may personalize the generated images to provide your own styles or objects
 by training a new LDM checkpoint and introducing a new vocabulary to the fixed
 model as a (.pt) embeddings file. Alternatively, you may use or train
 HuggingFace Concepts embeddings files (.bin) from
-<https://huggingface.co/sd-concepts-library> and its associated notebooks.
+<https://huggingface.co/sd-concepts-library> and its associated
+notebooks.
 
-## **Training**
+## **Hardware and Software Requirements**
 
-To train, prepare a folder that contains images sized at 512x512 and execute the
-following:
+You will need a GPU to perform training in a reasonable length of
+time, and at least 12 GB of VRAM. We recommend using the [`xformers`
+library](../installation/070_INSTALL_XFORMERS) to accelerate the
+training process further. During training, about ~8 GB is temporarily
+needed in order to store intermediate models, checkpoints and logs.
 
-### WINDOWS
+## **Preparing for Training**
 
-As the default backend is not available on Windows, if you're using that
-platform, set the environment variable `PL_TORCH_DISTRIBUTED_BACKEND` to `gloo`
+To train, prepare a folder that contains 3-5 images that illustrate
+the object or concept. It is good to provide a variety of examples or
+poses to avoid overtraining the system. Format these images as PNG
+(preferred) or JPG. You do not need to resize or crop the images in
+advance, but for more control you may wish to do so.
 
-```bash
-python3 ./main.py -t \
-    --base ./configs/stable-diffusion/v1-finetune.yaml \
-    --actual_resume ./models/ldm/stable-diffusion-v1/model.ckpt \
-    -n my_cat \
-    --gpus 0 \
-    --data_root D:/textual-inversion/my_cat \
-    --init_word 'cat'
+Place the training images in a directory on the machine InvokeAI runs
+on. We recommend placing them in a subdirectory of the
+`text-inversion-training-data` folder located in the InvokeAI root
+directory, ordinarily `~/invokeai` (Linux/Mac), or
+`C:\Users\your_name\invokeai` (Windows). For example, to create an
+embedding for the "psychedelic" style, you'd place the training images
+into the directory
+`~invokeai/text-inversion-training-data/psychedelic`.
+
+## **Launching Training Using the Console Front End**
+
+InvokeAI 2.3 and higher comes with a text console-based training front
+end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
+start the front end by selecting choice (3):
+
+```sh
+Do you want to generate images using the
+1. command-line
+2. browser-based UI
+3. textual inversion training
+4. open the developer console
+Please enter 1, 2, 3, or 4: [1] 3
 ```
 
-During the training process, files will be created in
-`/logs/[project][time][project]/` where you can see the process.
+From the command line, with the InvokeAI virtual environment active,
+you can launch the front end with the command `invokeai-ti --gui`.
 
-Conditioning contains the training prompts inputs, reconstruction the input
-images for the training epoch samples, samples scaled for a sample of the prompt
-and one with the init word provided.
+This will launch a text-based front end that will look like this:
 
-On a RTX3090, the process for SD will take ~1h @1.6 iterations/sec.
+<figure markdown>
+![ti-frontend](../assets/textual-inversion/ti-frontend.png)
+</figure>
 
-!!! note
+The interface is keyboard-based. Move from field to field using
+control-N (^N) to move to the next field and control-P (^P) to the
+previous one. <Tab> and <shift-TAB> work as well. Once a field is
+active, use the cursor keys. In a checkbox group, use the up and down
+cursor keys to move from choice to choice, and <space> to select a
+choice. In a scrollbar, use the left and right cursor keys to increase
+and decrease the value of the scroll. In textfields, type the desired
+values.
 
-    According to the associated paper, the optimal number of
-    images is 3-5. Your model may not converge if you use more images than
-    that.
+The number of parameters may look intimidating, but in most cases the
+predefined defaults work fine. The red circled fields in the above
+illustration are the ones you will adjust most frequently.
 
-Training will run indefinitely, but you may wish to stop it (with ctrl-c) before
-the heat death of the universe, when you find a low loss epoch or around ~5000
-iterations. Note that you can set a fixed limit on the number of training steps
-by decreasing the "max_steps" option in
-configs/stable_diffusion/v1-finetune.yaml (currently set to 4000000)
+### Model Name
 
-## **Run the Model**
+This will list all the diffusers models that are currently
+installed. Select the one you wish to use as the basis for your
+embedding. Be aware that if you use a SD-1.X-based model for your
+training, you will only be able to use this embedding with other
+SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
+be able to use the embeddings with models based on SD-2.X.
 
-Once the model is trained, specify the trained .pt or .bin file when starting
-invoke using
+### Trigger Term
 
-```bash
-python3 ./scripts/invoke.py \
-    --embedding_path /path/to/embedding.pt
+This is the prompt term you will use to trigger the embedding. Type a
+single word or phrase you wish to use as the trigger, example
+"psychedelic" (without angle brackets). Within InvokeAI, you will then
+be able to activate the trigger using the syntax `<psychedelic>`.
+
+### Initializer
+
+This is a single character that is used internally during the training
+process as a placeholder for the trigger term. It defaults to "*" and
+can usually be left alone.
+
+### Resume from last saved checkpoint
+
+As training proceeds, textual inversion will write a series of
+intermediate files that can be used to resume training from where it
+was left off in the case of an interruption. This checkbox will be
+automatically selected if you provide a previously used trigger term
+and at least one checkpoint file is found on disk.
+
+Note that as of 20 January 2023, resume does not seem to be working
+properly due to an issue with the upstream code.
+
+### Data Training Directory
+
+This is the location of the images to be used for training. When you
+select a trigger term like "my-trigger", the frontend will prepopulate
+this field with `~/invokeai/text-inversion-training-data/my-trigger`,
+but you can change the path to wherever you want.
+
+### Output Destination Directory
+
+This is the location of the logs, checkpoint files, and embedding
+files created during training. When you select a trigger term like
+"my-trigger", the frontend will prepopulate this field with
+`~/invokeai/text-inversion-output/my-trigger`, but you can change the
+path to wherever you want.
+
+### Image resolution
+
+The images in the training directory will be automatically scaled to
+the value you use here. For best results, you will want to use the
+same default resolution of the underlying model (512 pixels for
+SD-1.5, 768 for the larger version of SD-2.1).
+
+### Center crop images
+
+If this is selected, your images will be center cropped to make them
+square before resizing them to the desired resolution. Center cropping
+can indiscriminately cut off the top of subjects' heads for portrait
+aspect images, so if you have images like this, you may wish to use a
+photoeditor to manually crop them to a square aspect ratio.
+
+### Mixed precision
+
+Select the floating point precision for the embedding. "no" will
+result in a full 32-bit precision, "fp16" will provide 16-bit
+precision, and "bf16" will provide mixed precision (only available
+when XFormers is used).
+
+### Max training steps
+
+How many steps the training will take before the model converges. Most
+training sets will converge with 2000-3000 steps.
+
+### Batch size
+
+This adjusts how many training images are processed simultaneously in
+each step. Higher values will cause the training process to run more
+quickly, but use more memory. The default size is selected based on
+whether you have the `xformers` memory-efficient attention library
+installed. If `xformers` is available, the batch size will be 8,
+otherwise 3.  These values were chosen to allow training to run with
+GPUs with as little as 12 GB VRAM.
+
+### Learning rate
+
+The rate at which the system adjusts its internal weights during
+training. Higher values risk overtraining (getting the same image each
+time), and lower values will take more steps to train a good
+model. The default of 0.0005 is conservative; you may wish to increase
+it to 0.005 to speed up training.
+
+### Scale learning rate by number of GPUs, steps and batch size
+
+If this is selected (the default) the system will adjust the provided
+learning rate to improve performance.
+
+### Use xformers acceleration
+
+This will activate XFormers memory-efficient attention, which will
+reduce memory requirements by half or more and allow you to select a
+higher batch size. You need to have XFormers installed for this to
+have an effect.
+
+### Learning rate scheduler
+
+This adjusts how the learning rate changes over the course of
+training. The default "constant" means to use a constant learning rate
+for the entire training session. The other values scale the learning
+rate according to various formulas.
+
+Only "constant" is supported by the XFormers library.
+
+### Gradient accumulation steps
+
+This is a parameter that allows you to use bigger batch sizes than
+your GPU's VRAM would ordinarily accommodate, at the cost of some
+performance.
+
+### Warmup steps
+
+If "constant_with_warmup" is selected in the learning rate scheduler,
+then this provides the number of warmup steps. Warmup steps have a
+very low learning rate, and are one way of preventing early
+overtraining.
+
+## The training run
+
+Start the training run by advancing to the OK button (bottom right)
+and pressing <enter>. A series of progress messages will be displayed
+as the training process proceeds. This may take an hour or two,
+depending on settings and the speed of your system. Various log and
+checkpoint files will be written into the output directory (ordinarily
+`~/invokeai/text-inversion-output/my-model/`)
+
+At the end of successful training, the system will copy the file
+`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
+directory, using a subdirectory named after the trigger token. For
+example, if the trigger token was `psychedelic`, then look for the
+embeddings file in
+`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
+
+You may now launch InvokeAI and try out a prompt that uses the trigger
+term. For example `a plate of banana sushi in <psychedelic> style`.
+
+## **Training with the Command-Line Script**
+
+Training can also be done using a traditional command-line script. It
+can be launched from within the "developer's console", or from the
+command line after activating InvokeAI's virtual environment.
+
+It accepts a large number of arguments, which can be summarized by
+passing the `--help` argument:
+
+```sh
+invokeai-ti --help
 ```
 
-Then, to utilize your subject at the invoke prompt
-
-```bash
-invoke> "a photo of *"
+Typical usage is shown here:
+```sh
+invokeai-ti \
+       --model=stable-diffusion-1.5 \
+       --resolution=512 \
+       --learnable_property=style \
+       --initializer_token='*' \
+       --placeholder_token='<psychedelic>' \
+       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
+       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
+       --scale_lr \
+       --train_batch_size=8 \
+       --gradient_accumulation_steps=4 \
+       --max_train_steps=3000 \
+       --learning_rate=0.0005 \
+       --resume_from_checkpoint=latest \
+       --lr_scheduler=constant \
+       --mixed_precision=fp16 \
+       --only_save_embeds
 ```
 
-This also works with image2image
+## Using Distributed Training
 
-```bash
-invoke> "waterfall and rainbow in the style of *" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4
+If you have multiple GPUs on one machine, or a cluster of GPU-enabled
+machines, you can activate distributed training. See the [HuggingFace
+Accelerate pages](https://huggingface.co/docs/accelerate/index) for
+full information, but the basic recipe is:
+
+1. Enter the InvokeAI developer's console command line by selecting
+option [8] from the `invoke.sh`/`invoke.bat` script.
+
+2. Configurate Accelerate using `accelerate config`:
+```sh
+accelerate config
+```
+This will guide you through the configuration process, including
+specifying how many machines you will run training on and the number
+of GPUs pe rmachine.
+
+You only need to do this once.
+
+3. Launch training from the command line using `accelerate launch`. Be sure
+that your current working directory is the InvokeAI root directory (usually
+named `invokeai` in your home directory):
+
+```sh
+accelerate launch .venv/bin/invokeai-ti \
+       --model=stable-diffusion-1.5 \
+       --resolution=512 \
+       --learnable_property=object \
+       --initializer_token='*' \
+       --placeholder_token='<shraddha>' \
+       --train_data_dir=/home/lstein/invokeai/text-inversion-training-data/shraddha \
+       --output_dir=/home/lstein/invokeai/text-inversion-training/shraddha \
+       --scale_lr \
+       --train_batch_size=10 \
+       --gradient_accumulation_steps=4 \
+       --max_train_steps=2000 \
+       --learning_rate=0.0005 \
+       --lr_scheduler=constant \
+       --mixed_precision=fp16 \
+       --only_save_embeds
 ```
 
-For .pt files it's also possible to train multiple tokens (modify the
-placeholder string in `configs/stable-diffusion/v1-finetune.yaml`) and combine
-LDM checkpoints using:
+## Using Embeddings
 
-```bash
-python3 ./scripts/merge_embeddings.py \
-    --manager_ckpts /path/to/first/embedding.pt \
-    [</path/to/second/embedding.pt>,[...]] \
-    --output_path /path/to/output/embedding.pt
-```
+After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.
 
-Credit goes to rinongal and the repository
+These will be automatically loaded when you start InvokeAI.
 
-Please see [the repository](https://github.com/rinongal/textual_inversion) and
-associated paper for details and limitations.
+Add the trigger word, surrounded by angle brackets, to use that embedding. For example, if your trigger word was `terence`, use `<terence>` in prompts. This is the same syntax used by the HuggingFace concepts library.
+
+**Note:** `.pt` embeddings do not require the angle brackets.
+
+## Troubleshooting
+
+### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
+
+Messages like this indicate you trained the embedding on a different base model than the currently selected one.
+
+For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
+
+## Reading
+
+For more information on textual inversion, please see the following
+resources:
+
+* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
+  associated paper for details and limitations.
+* [HuggingFace's textual inversion training
+  page](https://huggingface.co/docs/diffusers/training/text_inversion)
+* [HuggingFace example script
+  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
+  (Note that this script is similar to, but not identical, to
+  `textual_inversion`, but produces embed files that are completely compatible.
+
+---
+
+copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/UNIFIED_CANVAS.md

@@ -0,0 +1,284 @@
+---
+title: Unified Canvas
+---
+
+The Unified Canvas is a tool designed to streamline and simplify the process of
+composing an image using Stable Diffusion. It offers artists all of the
+available Stable Diffusion generation modes (Text To Image, Image To Image,
+Inpainting, and Outpainting) as a single unified workflow. The flexibility of
+the tool allows you to tweak and edit image generations, extend images beyond
+their initial size, and to create new content in a freeform way both inside and
+outside of existing images.
+
+This document explains the basics of using the Unified Canvas, introducing you
+to its features and tools one by one. It also describes some of the more
+advanced tools available to power users of the Canvas.
+
+## Basics
+
+The Unified Canvas consists of two layers: the **Base Layer** and the **Mask
+Layer**. You can swap from one layer to the other by selecting the layer you
+want in the drop-down menu on the top left corner of the Unified Canvas, or by
+pressing the (Q) hotkey.
+
+### Base Layer
+
+The **Base Layer** is the image content currently managed by the Canvas, and can
+be exported at any time to the gallery by using the **Save to Gallery** option.
+When the Base Layer is selected, the Brush (B) and Eraser (E) tools will
+directly manipulate the base layer. Any images uploaded to the Canvas, or sent
+to the Unified Canvas from the gallery, will clear out all existing content and
+set the Base layer to the new image.
+
+### Staging Area
+
+When you generate images, they will display in the Canvas's **Staging Area**,
+alongside the Staging Area toolbar buttons. While the Staging Area is active,
+you cannot interact with the Canvas itself.
+
+<figure markdown>
+
+![staging area](../assets/canvas/staging_area.png)
+
+</figure>
+
+Accepting generations will commit the new generation to the **Base Layer**. You
+can review all generated images using the Prev/Next arrows, save any individual
+generations to your gallery (without committing to the Base layer) or discard
+generations. While you can Undo a discard in an individual Canvas session, any
+generations that are not saved will be lost when the Canvas resets.
+
+### Mask Layer
+
+The **Mask Layer** consists of any masked sections that have been created to
+inform Inpainting generations. You can paint a new mask, or edit an existing
+mask, using the Brush tool and the Eraser with the Mask layer set as your Active
+layer. Any masked areas will only affect generation inside of the current
+bounding box.
+
+### Bounding Box
+
+When generating a new image, Invoke will process and apply new images within the
+area denoted by the **Bounding Box**. The Width & Height settings of the
+Bounding Box, as well as its location within the Unified Canvas and pixels or
+empty space that it encloses, determine how new invocations are generated - see
+[Inpainting & Outpainting](#inpainting-and-outpainting) below. The Bounding Box
+can be moved and resized using the Move (V) tool. It can also be resized using
+the Bounding Box options in the Options Panel. By using these controls you can
+generate larger or smaller images, control which sections of the image are being
+processed, as well as control Bounding Box tools like the Bounding Box
+fill/erase.
+
+### <a name="inpainting-and-outpainting"></a> Inpainting & Outpainting
+
+"Inpainting" means asking the AI to refine part of an image while leaving the
+rest alone. For example, updating a portrait of your grandmother to have her
+wear a biker's jacket.
+
+|                         masked original                         |                                       inpaint result                                       |
+| :-------------------------------------------------------------: | :----------------------------------------------------------------------------------------: |
+| ![granny with a mask applied](../assets/canvas/mask_granny.png) | ![just like magic, granny with a biker's jacket](../assets/canvas/biker_jacket_granny.png) |
+
+"Outpainting" means asking the AI to expand the original image beyond its
+original borders, making a bigger image that's still based on the original. For
+example, extending the above image of your Grandmother in a biker's jacket to
+include her wearing jeans (and while we're at it, a motorcycle!)
+
+<figure markdown>
+
+![more magic - granny with a tattooed arm, denim pants, and an obscured motorcycle](../assets/canvas/biker_granny.png)
+
+</figure>
+
+When you are using the Unified Canvas, Invoke decides automatically whether to
+do Inpainting, Outpainting, ImageToImage, or TextToImage by looking inside the
+area enclosed by the Bounding Box. It chooses the appropriate type of generation
+based on whether the Bounding Box contains empty (transparent) areas on the Base
+layer, or whether it contains colored areas from previous generations (or from
+painted brushstrokes) on the Base layer, and/or whether the Mask layer contains
+any brushstrokes. See [Generation Methods](#generation-methods) below for more
+information.
+
+## Getting Started
+
+To get started with the Unified Canvas, you will want to generate a new base
+layer using Txt2Img or importing an initial image. We'll refer to either of
+these methods as the "initial image" in the below guide.
+
+From there, you can consider the following techniques to augment your image:
+
+- **New Images**: Move the bounding box to an empty area of the Canvas, type in
+  your prompt, and Invoke, to generate a new image using the Text to Image
+  function.
+- **Image Correction**: Use the color picker and brush tool to paint corrections
+  on the image, switch to the Mask layer, and brush a mask over your painted
+  area to use **Inpainting**. You can also use the **ImageToImage** generation
+  method to invoke new interpretations of the image.
+- **Image Expansion**: Move the bounding box to include a portion of your
+  initial image, and a portion of transparent/empty pixels, then Invoke using a
+  prompt that describes what you'd like to see in that area. This will Outpaint
+  the image. You'll typically find more coherent results if you keep about
+  50-60% of the original image in the bounding box. Make sure that the Image To
+  Image Strength slider is set to a high value - you may need to set it higher
+  than you are used to.
+- **New Content on Existing Images**: If you want to add new details or objects
+  into your image, use the brush tool to paint a sketch of what you'd like to
+  see on the image, switch to the Mask layer, and brush a mask over your painted
+  area to use **Inpainting**. If the masked area is small, consider using a
+  smaller bounding box to take advantage of Invoke's automatic Scaling features,
+  which can help to produce better details.
+- **And more**: There are a number of creative ways to use the Canvas, and the
+  above are just starting points. We're excited to see what you come up with!
+
+## <a name="generation-methods"></a> Generation Methods
+
+The Canvas can use all generation methods available (Txt2Img, Img2Img,
+Inpainting, and Outpainting), and these will be automatically selected and used
+based on the current selection area within the Bounding Box.
+
+### Text to Image
+
+If the Bounding Box is placed over an area of Canvas with an **empty Base
+Layer**, invoking a new image will use **TextToImage**. This generates an
+entirely new image based on your prompt.
+
+### Image to Image
+
+If the Bounding Box is placed over an area of Canvas with an **existing Base
+Layer area with no transparent pixels or masks**, invoking a new image will use
+**ImageToImage**. This uses the image within the bounding box and your prompt to
+interpret a new image. The image will be closer to your original image at lower
+Image to Image strengths.
+
+### Inpainting
+
+If the Bounding Box is placed over an area of Canvas with an **existing Base
+Layer and any pixels selected using the Mask layer**, invoking a new image will
+use **Inpainting**. Inpainting uses the existing colors/forms in the masked area
+in order to generate a new image for the masked area only. The unmasked portion
+of the image will remain the same. Image to Image strength applies to the
+inpainted area.
+
+If you desire something completely different from the original image in your new
+generation (i.e., if you want Invoke to ignore existing colors/forms), consider
+toggling the Inpaint Replace setting on, and use high values for both Inpaint
+Replace and Image To Image Strength.
+
+!!! note
+
+    By default, the **Scale Before Processing** option &mdash; which
+    inpaints more coherent details by generating at a larger resolution and then
+    scaling &mdash; is only activated when the Bounding Box is relatively small.
+    To get the best inpainting results you should therefore resize your Bounding
+    Box to the smallest area that contains your mask and enough surrounding detail
+    to help Stable Diffusion understand the context of what you want it to draw.
+    You should also update your prompt so that it describes _just_ the area within
+    the Bounding Box.
+
+### Outpainting
+
+If the Bounding Box is placed over an area of Canvas partially filled by an
+existing Base Layer area and partially by transparent pixels or masks, invoking
+a new image will use **Outpainting**, as well as **Inpainting** any masked
+areas.
+
+---
+
+## Advanced Features
+
+Features with non-obvious behavior are detailed below, in order to provide
+clarity on the intent and common use cases we expect for utilizing them.
+
+### Toolbar
+
+#### Mask Options
+
+- **Enable Mask** - This flag can be used to Enable or Disable the currently
+  painted mask. If you have painted a mask, but you don't want it affect the
+  next invocation, but you _also_ don't want to delete it, then you can set this
+  option to Disable. When you want the mask back, set this back to Enable.
+- **Preserve Masked Area** - When enabled, Preserve Masked Area inverts the
+  effect of the Mask on the Inpainting process. Pixels in masked areas will be
+  kept unchanged, and unmasked areas will be regenerated.
+
+#### Creative Tools
+
+- **Brush - Base/Mask Modes** - The Brush tool switches automatically between
+  different modes of operation for the Base and Mask layers respectively.
+    - On the Base layer, the brush will directly paint on the Canvas using the
+      color selected on the Brush Options menu.
+    - On the Mask layer, the brush will create a new mask. If you're finding the
+      mask difficult to see over the existing content of the Unified Canvas, you
+      can change the color it is drawn with using the color selector on the Mask
+      Options dropdown.
+- **Erase Bounding Box** - On the Base layer, erases all pixels within the
+  Bounding Box.
+- **Fill Bounding Box** - On the Base layer, fills all pixels within the
+  Bounding Box with the currently selected color.
+
+#### Canvas Tools
+
+- **Move Tool** - Allows for manipulation of the Canvas view (by dragging on the
+  Canvas, outside the bounding box), the Bounding Box (by dragging the edges of
+  the box), or the Width/Height of the Bounding Box (by dragging one of the 9
+  directional handles).
+- **Reset View** - Click to re-orients the view to the center of the Bounding
+  Box.
+- **Merge Visible** - If your browser is having performance problems drawing the
+  image in the Unified Canvas, click this to consolidate all of the information
+  currently being rendered by your browser into a merged copy of the image. This
+  lowers the resource requirements and should improve performance.
+
+### Seam Correction
+
+When doing Inpainting or Outpainting, Invoke needs to merge the pixels generated
+by Stable Diffusion into your existing image. To do this, the area around the
+`seam` at the boundary between your image and the new generation is
+automatically blended to produce a seamless output. In a fully automatic
+process, a mask is generated to cover the seam, and then the area of the seam is
+Inpainted.
+
+Although the default options should work well most of the time, sometimes it can
+help to alter the parameters that control the seam Inpainting. A wider seam and
+a blur setting of about 1/3 of the seam have been noted as producing
+consistently strong results (e.g. 96 wide and 16 blur - adds up to 32 blur with
+both sides). Seam strength of 0.7 is best for reducing hard seams.
+
+- **Seam Size** - The size of the seam masked area. Set higher to make a larger
+  mask around the seam.
+- **Seam Blur** - The size of the blur that is applied on _each_ side of the
+  masked area.
+- **Seam Strength** - The Image To Image Strength parameter used for the
+  Inpainting generation that is applied to the seam area.
+- **Seam Steps** - The number of generation steps that should be used to Inpaint
+  the seam.
+
+### Infill & Scaling
+
+- **Scale Before Processing & W/H**: When generating images with a bounding box
+  smaller than the optimized W/H of the model (e.g., 512x512 for SD1.5), this
+  feature first generates at a larger size with the same aspect ratio, and then
+  scales that image down to fill the selected area. This is particularly useful
+  when inpainting very small details. Scaling is optional but is enabled by
+  default.
+- **Inpaint Replace**: When Inpainting, the default method is to utilize the
+  existing RGB values of the Base layer to inform the generation process. If
+  Inpaint Replace is enabled, noise is generated and blended with the existing
+  pixels (completely replacing the original RGB values at an Inpaint Replace
+  value of 1). This can help generate more variation from the pixels on the Base
+  layers.
+    - When using Inpaint Replace you should use a higher Image To Image Strength
+      value, especially at higher Inpaint Replace values
+- **Infill Method**: Invoke currently supports two methods for producing RGB
+  values for use in the Outpainting process: Patchmatch and Tile. We believe
+  that Patchmatch is the superior method, however we provide support for Tile in
+  case Patchmatch cannot be installed or is unavailable on your computer.
+- **Tile Size**: The Tile method for Outpainting sources small portions of the
+  original image and randomly place these into the areas being Outpainted. This
+  value sets the size of those tiles.
+
+## Hot Keys
+
+The Unified Canvas is a tool that excels when you use hotkeys. You can view the
+full list of keyboard shortcuts, updated with all new features, by clicking the
+Keyboard Shortcuts icon at the top right of the InvokeAI WebUI.

docs/features/WEB.md

@@ -5,11 +5,14 @@ title: InvokeAI Web Server
 # :material-web: InvokeAI Web Server
 
 As of version 2.0.0, this distribution comes with a full-featured web server
-(see screenshot). To use it, run the `invoke.py` script by adding the `--web`
-option:
+(see screenshot).
+
+To use it, launch the `invoke.sh`/`invoke.bat` script and select
+option (2). Alternatively, with the InvokeAI environment active, run
+the `invokeai` script by adding the `--web` option:
 
 ```bash
-(invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web
+invokeai --web
 ```
 
 You can then connect to the server by pointing your web browser at
@@ -19,17 +22,23 @@ address of the host you are running it on, or the wildcard `0.0.0.0`. For
 example:
 
 ```bash
-(invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web --host 0.0.0.0
+invoke.sh --host 0.0.0.0
 ```
 
-## Quick guided walkthrough of the WebGUI's features
+or
 
-While most of the WebGUI's features are intuitive, here is a guided walkthrough
+```bash
+invokeai --web --host 0.0.0.0
+```
+
+## Quick guided walkthrough of the WebUI's features
+
+While most of the WebUI's features are intuitive, here is a guided walkthrough
 through its various components.
 
 ![Invoke Web Server - Major Components](../assets/invoke-web-server-1.png){:width="640px"}
 
-The screenshot above shows the Text to Image tab of the WebGUI. There are three
+The screenshot above shows the Text to Image tab of the WebUI. There are three
 main sections:
 
 1. A **control panel** on the left, which contains various settings for text to
@@ -63,12 +72,14 @@ From top to bottom, these are:
 1. Text to Image - generate images from text
 2. Image to Image - from an uploaded starting image (drawing or photograph)
    generate a new one, modified by the text prompt
-3. Inpainting (pending) - Interactively erase portions of a starting image and
-   have the AI fill in the erased region from a text prompt.
-4. Outpainting (pending) - Interactively add blank space to the borders of a
-   starting image and fill in the background from a text prompt.
-5. Postprocessing (pending) - Interactively postprocess generated images using a
-   variety of filters.
+3. Unified Canvas - Interactively combine multiple images, extend them
+   with outpainting,and modify interior portions of the image with
+   inpainting, erase portions of a starting image and have the AI fill in
+   the erased region from a text prompt.
+4. Workflow Management (not yet implemented) - this panel will allow you to create
+   pipelines of common operations and combine them into workflows.
+5. Training (not yet implemented) - this panel will provide an interface to [textual
+   inversion training](TEXTUAL_INVERSION.md) and fine tuning.
 
 The inpainting, outpainting and postprocessing tabs are currently in
 development. However, limited versions of their features can already be accessed
@@ -76,18 +87,18 @@ through the Text to Image and Image to Image tabs.
 
 ## Walkthrough
 
-The following walkthrough will exercise most (but not all) of the WebGUI's
+The following walkthrough will exercise most (but not all) of the WebUI's
 feature set.
 
 ### Text to Image
 
-1. Launch the WebGUI using `python scripts/invoke.py --web` and connect to it
+1. Launch the WebUI using `python scripts/invoke.py --web` and connect to it
    with your browser by accessing `http://localhost:9090`. If the browser and
    server are running on different machines on your LAN, add the option
    `--host 0.0.0.0` to the launch command line and connect to the machine
    hosting the web server using its IP address or domain name.
 
-2. If all goes well, the WebGUI should come up and you'll see a green
+2. If all goes well, the WebUI should come up and you'll see a green
    `connected` message on the upper right.
 
 #### Basics
@@ -234,7 +245,7 @@ walkthrough.
 
 2.  Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or click
     the blank area to get an upload dialog. The image will load into an area
-    marked _Initial Image_. (The WebGUI will also load the most
+    marked _Initial Image_. (The WebUI will also load the most
     recently-generated image from the gallery into a section on the left, but
     this image will be replaced in the next step.)
 
@@ -284,13 +295,17 @@ initial image" icons are located.
 
 ![Invoke Web Server - Use as Image Links](../assets/invoke-web-server-9.png){:width="640px"}
 
+### Unified Canvas
+
+See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
+
 ## Parting remarks
 
 This concludes the walkthrough, but there are several more features that you can
 explore. Please check out the [Command Line Interface](CLI.md) documentation for
 further explanation of the advanced features that were not covered here.
 
-The WebGUI is only rapid development. Check back regularly for updates!
+The WebUI is only rapid development. Check back regularly for updates!
 
 ## Reference
 
@@ -303,6 +318,8 @@ The WebGUI is only rapid development. Check back regularly for updates!
 | `--cors [CORS ...]`                     | Additional allowed origins, comma-separated                                                                                                |
 | `--host HOST`                           | Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.                                  |
 | `--port PORT`                           | Web server: Port to listen on                                                                                                              |
+| `--certfile CERTFILE`                   | Web server: Path to certificate file to use for SSL. Use together with --keyfile                                                           |
+| `--keyfile KEYFILE`                     | Web server: Path to private key file to use for SSL. Use together with --certfile'                                                         |
 | `--gui`                                 | Start InvokeAI GUI - This is the "desktop mode" version of the web app. It uses Flask to create a desktop app experience of the webserver. |
 
 ### Web Specific Features

docs/features/WEBUIHOTKEYS.md

@@ -4,59 +4,72 @@ title: WebUI Hotkey List
 
 # :material-keyboard: **WebUI Hotkey List**
 
-## General
+## App Hotkeys
 
-| Setting           | Hotkey                 |
-| ----------------- | ---------------------- |
-| ++a++             | Set All Parameters     |
-| ++s++             | Set Seed               |
-| ++u++             | Upscale                |
-| ++r++             | Restoration            |
-| ++i++             | Show Metadata          |
-| ++d++ ++d++ ++l++ | Delete Image           |
-| ++alt+a++         | Focus prompt input     |
-| ++shift+i++       | Send To Image to Image |
-| ++ctrl+enter++    | Start processing       |
-| ++shift+x++       | cancel Processing      |
-| ++shift+d++       | Toggle Dark Mode       |
-| ++"`"++           | Toggle console         |
+| Setting         | Hotkey             |
+| --------------- | ------------------ |
+| ++ctrl+enter++  | Invoke             |
+| ++shift+x++     | Cancel             |
+| ++alt+a++       | Focus Prompt       |
+| ++o++           | Toggle Options     |
+| ++shift+o++     | Pin Options        |
+| ++z++           | Toggle Viewer      |
+| ++g++           | Toggle Gallery     |
+| ++f++           | Maximize Workspace |
+| ++1++ - ++5++   | Change Tabs        |
+| ++"`"++         | Toggle Console     |
 
-## Tabs
+## General Hotkeys
 
-| Setting | Hotkey                    |
-| ------- | ------------------------- |
-| ++1++   | Go to Text To Image Tab   |
-| ++2++   | Go to Image to Image Tab  |
-| ++3++   | Go to Inpainting Tab      |
-| ++4++   | Go to Outpainting Tab     |
-| ++5++   | Go to Nodes Tab           |
-| ++6++   | Go to Post Processing Tab |
+| Setting        | Hotkey                 |
+| -------------- | ---------------------- |
+| ++p++          | Set Prompt             |
+| ++s++          | Set Seed               |
+| ++a++          | Set Parameters         |
+| ++shift+r++    | Restore Faces          |
+| ++shift+u++    | Upscale                |
+| ++i++          | Show Info              |
+| ++shift+i++    | Send To Image To Image |
+| ++del++        | Delete Image           |
+| ++esc++        | Close Panels           |
 
-## Gallery
+## Gallery Hotkeys
 
-| Setting        | Hotkey                          |
-| -------------- | ------------------------------- |
-| ++g++          | Toggle Gallery                  |
-| ++left++       | Go to previous image in gallery |
-| ++right++      | Go to next image in gallery     |
-| ++shift+p++    | Pin gallery                     |
-| ++shift+up++   | Increase gallery image size     |
-| ++shift+down++ | Decrease gallery image size     |
-| ++shift+r++    | Reset image gallery size        |
+| Setting               | Hotkey                      |
+| ----------------------| --------------------------- |
+| ++arrow-left++        | Previous Image              |
+| ++arrow-right++       | Next Image                  |
+| ++shift+g++           | Toggle Gallery Pin          |
+| ++shift+arrow-up++    | Increase Gallery Image Size |
+| ++shift+arrow-down++  | Decrease Gallery Image Size |
 
-## Inpainting
+## Unified Canvas Hotkeys
 
-| Setting                      | Hotkey                |
-| ---------------------------- | --------------------- |
-| ++"["++                      | Decrease brush size   |
-| ++"]"++                      | Increase brush size   |
-| ++alt+"["++                  | Decrease mask opacity |
-| ++alt+"]"++                  | Increase mask opacity |
-| ++b++                        | Select brush          |
-| ++e++                        | Select eraser         |
-| ++ctrl+z++                   | Undo brush stroke     |
-| ++ctrl+shift+z++, ++ctrl+y++ | Redo brush stroke     |
-| ++h++                        | Hide mask             |
-| ++shift+m++                  | Invert mask           |
-| ++shift+c++                  | Clear mask            |
-| ++shift+j++                  | Expand canvas         |
+| Setting                           | Hotkey                 |
+| --------------------------------- | ---------------------- |
+| ++b++                             | Select Brush           |
+| ++e++                             | Select Eraser          |
+| ++bracket-left++                  | Decrease Brush Size    |
+| ++bracket-right++                 | Increase Brush Size    |
+| ++shift+bracket-left++            | Decrease Brush Opacity |
+| ++shift+bracket-right++           | Increase Brush Opacity |
+| ++v++                             | Move Tool              |
+| ++shift+f++                       | Fill Bounding Box      |
+| ++del++ / ++backspace++           | Erase Bounding Box     |
+| ++c++                             | Select Color Picker    |
+| ++n++                             | Toggle Snap            |
+| ++"Hold Space"++                  | Quick Toggle Move      |
+| ++q++                             | Toggle Layer           |
+| ++shift+c++                       | Clear Mask             |
+| ++h++                             | Hide Mask              |
+| ++shift+h++                       | Show/Hide Bounding Box |
+| ++shift+m++                       | Merge Visible          |
+| ++shift+s++                       | Save To Gallery        |
+| ++ctrl+c++                        | Copy To Clipboard      |
+| ++shift+d++                       | Download Image         |
+| ++ctrl+z++                        | Undo                   |
+| ++ctrl+y++ / ++ctrl+shift+z++     | Redo                   |
+| ++r++                             | Reset View             |
+| ++arrow-left++                    | Previous Staging Image |
+| ++arrow-right++                   | Next Staging Image     |
+| ++enter++                         | Accept Staging Image   |

docs/features/index.md

@@ -0,0 +1,85 @@
+---
+title: Overview
+---
+
+-   The Basics
+
+    -   The [Web User Interface](WEB.md)
+
+        Guide to the Web interface. Also see the
+        [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
+
+    -   The [Unified Canvas](UNIFIED_CANVAS.md)
+
+        Build complex scenes by combine and modifying multiple images in a
+        stepwise fashion. This feature combines img2img, inpainting and
+        outpainting in a single convenient digital artist-optimized user
+        interface.
+
+    -   The [Command Line Interface (CLI)](CLI.md)
+
+        Scriptable access to InvokeAI's features.
+
+    -   [Visual Manual for InvokeAI](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
+
+-   Image Generation
+
+    -   [Prompt Engineering](PROMPTS.md)
+
+        Get the images you want with the InvokeAI prompt engineering language.
+
+    -   [Post-Processing](POSTPROCESS.md)
+
+        Restore mangled faces and make images larger with upscaling. Also see
+        the [Embiggen Upscaling Guide](EMBIGGEN.md).
+
+    -   The [Concepts Library](CONCEPTS.md)
+
+        Add custom subjects and styles using HuggingFace's repository of
+        embeddings.
+
+    -   [Image-to-Image Guide for the CLI](IMG2IMG.md)
+
+        Use a seed image to build new creations in the CLI.
+
+    -   [Inpainting Guide for the CLI](INPAINTING.md)
+
+        Selectively erase and replace portions of an existing image in the CLI.
+
+    -   [Outpainting Guide for the CLI](OUTPAINTING.md)
+
+        Extend the borders of the image with an "outcrop" function within the
+        CLI.
+
+    -   [Generating Variations](VARIATIONS.md)
+
+        Have an image you like and want to generate many more like it?
+        Variations are the ticket.
+
+-   Model Management
+
+    -   [Model Installation](../installation/050_INSTALLING_MODELS.md)
+
+        Learn how to import third-party models and switch among them. This guide
+        also covers optimizing models to load quickly.
+
+    -   [Merging Models](MODEL_MERGING.md)
+
+        Teach an old model new tricks. Merge 2-3 models together to create a new
+        model that combines characteristics of the originals.
+
+    -   [Textual Inversion](TEXTUAL_INVERSION.md)
+
+        Personalize models by adding your own style or subjects.
+
+-   Other Features
+
+    -   [The NSFW Checker](NSFW.md)
+
+        Prevent InvokeAI from displaying unwanted racy images.
+
+    -   [Miscellaneous](OTHER.md)
+
+        Run InvokeAI on Google Colab, generate images with repeating patterns,
+        batch process a file of prompts, increase the "creativity" of image
+        generation by adding initial noise, and more!

docs/help/IDE-Settings/index.md

@@ -0,0 +1,4 @@
+# :octicons-file-code-16: IDE-Settings
+
+Here we will share settings for IDEs used by our developers, maybe you can find
+something interestening which will help to boost your development efficency 🔥

docs/help/IDE-Settings/vs-code.md

@@ -0,0 +1,250 @@
+---
+title: Visual Studio Code
+---
+
+# :material-microsoft-visual-studio-code:Visual Studio Code
+
+The Workspace Settings are stored in the project (repository) root and get
+higher priorized than your user settings.
+
+This helps to have different settings for different projects, while the user
+settings get used as a default value if no workspace settings are provided.
+
+## tasks.json
+
+First we will create a task configuration which will create a virtual
+environment and update the deps (pip, setuptools and wheel).
+
+Into this venv we will then install the pyproject.toml in editable mode with
+dev, docs and test dependencies.
+
+```json title=".vscode/tasks.json"
+{
+    // See https://go.microsoft.com/fwlink/?LinkId=733558
+    // for the documentation about the tasks.json format
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "Create virtual environment",
+            "detail": "Create .venv and upgrade pip, setuptools and wheel",
+            "command": "python3",
+            "args": [
+                "-m",
+                "venv",
+                ".venv",
+                "--prompt",
+                "InvokeAI",
+                "--upgrade-deps"
+            ],
+            "runOptions": {
+                "instanceLimit": 1,
+                "reevaluateOnRerun": true
+            },
+            "group": {
+                "kind": "build"
+            },
+            "presentation": {
+                "echo": true,
+                "reveal": "always",
+                "focus": false,
+                "panel": "shared",
+                "showReuseMessage": true,
+                "clear": false
+            }
+        },
+        {
+            "label": "build InvokeAI",
+            "detail": "Build pyproject.toml with extras dev, docs and test",
+            "command": "${workspaceFolder}/.venv/bin/python3",
+            "args": [
+                "-m",
+                "pip",
+                "install",
+                "--use-pep517",
+                "--editable",
+                ".[dev,docs,test]"
+            ],
+            "dependsOn": "Create virtual environment",
+            "dependsOrder": "sequence",
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "presentation": {
+                "echo": true,
+                "reveal": "always",
+                "focus": false,
+                "panel": "shared",
+                "showReuseMessage": true,
+                "clear": false
+            }
+        }
+    ]
+}
+```
+
+The fastest way to build InvokeAI now is ++cmd+shift+b++
+
+## launch.json
+
+This file is used to define debugger configurations, so that you can one-click
+launch and monitor the application, set halt points to inspect specific states,
+...
+
+```json title=".vscode/launch.json"
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "invokeai web",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/invokeai",
+            "justMyCode": true
+        },
+        {
+            "name": "invokeai cli",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/invokeai",
+            "justMyCode": true
+        },
+        {
+            "name": "mkdocs serve",
+            "type": "python",
+            "request": "launch",
+            "program": ".venv/bin/mkdocs",
+            "args": ["serve"],
+            "justMyCode": true
+        }
+    ]
+}
+```
+
+Then you only need to hit ++f5++ and the fun begins :nerd: (It is asumed that
+you have created a virtual environment via the [tasks](#tasksjson) from the
+previous step.)
+
+## extensions.json
+
+A list of recommended vscode-extensions to make your life easier:
+
+```json title=".vscode/extensions.json"
+{
+    "recommendations": [
+        "editorconfig.editorconfig",
+        "github.vscode-pull-request-github",
+        "ms-python.black-formatter",
+        "ms-python.flake8",
+        "ms-python.isort",
+        "ms-python.python",
+        "ms-python.vscode-pylance",
+        "redhat.vscode-yaml",
+        "tamasfe.even-better-toml",
+        "eamodio.gitlens",
+        "foxundermoon.shell-format",
+        "timonwong.shellcheck",
+        "esbenp.prettier-vscode",
+        "davidanson.vscode-markdownlint",
+        "yzhang.markdown-all-in-one",
+        "bierner.github-markdown-preview",
+        "ms-azuretools.vscode-docker",
+        "mads-hartmann.bash-ide-vscode"
+    ]
+}
+```
+
+## settings.json
+
+With bellow settings your files already get formated when you save them (only
+your modifications if available), which will help you to not run into trouble
+with the pre-commit hooks. If the hooks fail, they will prevent you from
+commiting, but most hooks directly add a fixed version, so that you just need to
+stage and commit them:
+
+```json title=".vscode/settings.json"
+{
+    "[json]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.quickSuggestions": {
+            "comments": false,
+            "strings": true,
+            "other": true
+        },
+        "editor.suggest.insertMode": "replace",
+        "gitlens.codeLens.scopes": ["document"]
+    },
+    "[jsonc]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "file"
+    },
+    "[toml]": {
+        "editor.defaultFormatter": "tamasfe.even-better-toml",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[yaml]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[markdown]": {
+        "editor.defaultFormatter": "esbenp.prettier-vscode",
+        "editor.rulers": [80],
+        "editor.unicodeHighlight.ambiguousCharacters": false,
+        "editor.unicodeHighlight.invisibleCharacters": false,
+        "diffEditor.ignoreTrimWhitespace": false,
+        "editor.wordWrap": "on",
+        "editor.quickSuggestions": {
+            "comments": "off",
+            "strings": "off",
+            "other": "off"
+        },
+        "editor.formatOnSave": true,
+        "editor.formatOnSaveMode": "modificationsIfAvailable"
+    },
+    "[shellscript]": {
+        "editor.defaultFormatter": "foxundermoon.shell-format"
+    },
+    "[ignore]": {
+        "editor.defaultFormatter": "foxundermoon.shell-format"
+    },
+    "editor.rulers": [88],
+    "evenBetterToml.formatter.alignEntries": false,
+    "evenBetterToml.formatter.allowedBlankLines": 1,
+    "evenBetterToml.formatter.arrayAutoExpand": true,
+    "evenBetterToml.formatter.arrayTrailingComma": true,
+    "evenBetterToml.formatter.arrayAutoCollapse": true,
+    "evenBetterToml.formatter.columnWidth": 88,
+    "evenBetterToml.formatter.compactArrays": true,
+    "evenBetterToml.formatter.compactInlineTables": true,
+    "evenBetterToml.formatter.indentEntries": false,
+    "evenBetterToml.formatter.inlineTableExpand": true,
+    "evenBetterToml.formatter.reorderArrays": true,
+    "evenBetterToml.formatter.reorderKeys": true,
+    "evenBetterToml.formatter.compactEntries": false,
+    "evenBetterToml.schema.enabled": true,
+    "python.analysis.typeCheckingMode": "basic",
+    "python.formatting.provider": "black",
+    "python.languageServer": "Pylance",
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.testing.pytestArgs": [
+        "tests",
+        "--cov=ldm",
+        "--cov-branch",
+        "--cov-report=term:skip-covered"
+    ],
+    "yaml.schemas": {
+        "https://json.schemastore.org/prettierrc.json": "${workspaceFolder}/.prettierrc.yaml"
+    }
+}
+```

docs/help/SAMPLER_CONVERGENCE.md

@@ -39,7 +39,7 @@ Looking for a short version? Here's a TL;DR in 3 tables.
 !!! tip "suggestions"
 
     For most use cases, `K_LMS`, `K_HEUN` and `K_DPM_2` are the best choices (the latter 2 run 0.5x as quick, but tend to converge 2x as quick as `K_LMS`). At very low steps (≤ `-s8`), `K_HEUN` and `K_DPM_2` are not recommended. Use `K_LMS` instead.
-    
+
     For variability, use `K_EULER_A` (runs 2x as quick as `K_DPM_2_A`).
 
 ---

docs/help/contributing/010_PULL_REQUEST.md

@@ -0,0 +1,135 @@
+---
+title: Pull-Request
+---
+
+# :octicons-git-pull-request-16: Pull-Request
+
+## pre-requirements
+
+To follow the steps in this tutorial you will need:
+
+-   [GitHub](https://github.com) account
+-   [git](https://git-scm.com/downloads) source controll
+-   Text / Code Editor (personally I preffer
+    [Visual Studio Code](https://code.visualstudio.com/Download))
+-   Terminal:
+    -   If you are on Linux/MacOS you can use bash or zsh
+    -   for Windows Users the commands are written for PowerShell
+
+## Fork Repository
+
+The first step to be done if you want to contribute to InvokeAI, is to fork the
+rpeository.
+
+Since you are already reading this doc, the easiest way to do so is by clicking
+[here](https://github.com/invoke-ai/InvokeAI/fork). You could also open
+[InvokeAI](https://github.com/invoke-ai/InvoekAI) and click on the "Fork" Button
+in the top right.
+
+## Clone your fork
+
+After you forked the Repository, you should clone it to your dev machine:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    git clone https://github.com/<github username>/InvokeAI \
+    && cd InvokeAI
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    git clone https://github.com/<github username>/InvokeAI `
+    && cd InvokeAI
+    ```
+
+## Install in Editable Mode
+
+To install InvokeAI in editable mode, (as always) we recommend to create and
+activate a venv first. Afterwards you can install the InvokeAI Package,
+including dev and docs extras in editable mode, follwed by the installation of
+the pre-commit hook:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    python -m venv .venv \
+      --prompt InvokeAI \
+      --upgrade-deps \
+    && source .venv/bin/activate \
+    && pip install \
+      --upgrade-deps \
+      --use-pep517 \
+      --editable=".[dev,docs]" \
+    && pre-commit install
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    python -m venv .venv `
+      --prompt InvokeAI `
+      --upgrade-deps `
+    && .venv/scripts/activate.ps1 `
+    && pip install `
+      --upgrade `
+      --use-pep517 `
+      --editable=".[dev,docs]" `
+    && pre-commit install
+    ```
+
+## Create a branch
+
+Make sure you are on main branch, from there create your feature branch:
+
+=== ":fontawesome-brands-linux:Linux / :simple-apple:macOS"
+
+    ``` sh
+    git checkout main \
+    && git pull \
+    && git checkout -B <branch name>
+    ```
+
+=== ":fontawesome-brands-windows:Windows"
+
+    ``` powershell
+    git checkout main `
+    && git pull `
+    && git checkout -B <branch name>
+    ```
+
+## Commit your changes
+
+When you are done with adding / updating content, you need to commit those
+changes to your repository before you can actually open an PR:
+
+```{ .sh .annotate }
+git add <files you have changed> # (1)!
+git commit -m "A commit message which describes your change"
+git push
+```
+
+1. Replace this with a space seperated list of the files you changed, like:
+   `README.md foo.sh bar.json baz`
+
+## Create a Pull Request
+
+After pushing your changes, you are ready to create a Pull Request. just head
+over to your fork on [GitHub](https://github.com), which should already show you
+a message that there have been recent changes on your feature branch and a green
+button which you could use to create the PR.
+
+The default target for your PRs would be the main branch of
+[invoke-ai/InvokeAI](https://github.com/invoke-ai/InvokeAI)
+
+Another way would be to create it in VS-Code or via the GitHub CLI (or even via
+the GitHub CLI in a VS-Code Terminal Window 🤭):
+
+```sh
+gh pr create
+```
+
+The CLI will inform you if there are still unpushed commits on your branch. It
+will also prompt you for things like the the Title and the Body (Description) if
+you did not already pass them as arguments.

docs/help/contributing/020_ISSUES.md

@@ -0,0 +1,26 @@
+---
+title: Issues
+---
+
+# :octicons-issue-opened-16: Issues
+
+## :fontawesome-solid-bug: Report a bug
+
+If you stumbled over a bug while using InvokeAI, we would apreciate it a lot if
+you
+[open a issue](https://github.com/invoke-ai/InvokeAI/issues/new?assignees=&labels=bug&template=BUG_REPORT.yml&title=%5Bbug%5D%3A+)
+to inform us about the details so that our developers can look into it.
+
+If you also know how to fix the bug, take a look [here](010_PULL_REQUEST.md) to
+find out how to create a Pull Request.
+
+## Request a feature
+
+If you have a idea for a new feature on your mind which you would like to see in
+InvokeAI, there is a
+[feature request](https://github.com/invoke-ai/InvokeAI/issues/new?assignees=&labels=bug&template=BUG_REPORT.yml&title=%5Bbug%5D%3A+)
+available in the issues section of the repository.
+
+If you are just curious which features already got requested you can find the
+overview of open requests
+[here](https://github.com/invoke-ai/InvokeAI/labels/enhancement)

docs/help/contributing/030_DOCS.md

@@ -0,0 +1,32 @@
+---
+title: docs
+---
+
+# :simple-readthedocs: MkDocs-Material
+
+If you want to contribute to the docs, there is a easy way to verify the results
+of your changes before commiting them.
+
+Just follow the steps in the [Pull-Requests](010_PULL_REQUEST.md) docs, there we
+already
+[create a venv and install the docs extras](010_PULL_REQUEST.md#install-in-editable-mode).
+When installed it's as simple as:
+
+```sh
+mkdocs serve
+```
+
+This will build the docs locally and serve them on your local host, even
+auto-refresh is included, so you can just update a doc, save it and tab to the
+browser, without the needs of restarting the `mkdocs serve`.
+
+More information about the "mkdocs flavored markdown syntax" can be found
+[here](https://squidfunk.github.io/mkdocs-material/reference/).
+
+## :material-microsoft-visual-studio-code:VS-Code
+
+We also provide a
+[launch configuration for VS-Code](../IDE-Settings/vs-code.md#launchjson) which
+includes a `mkdocs serve` entrypoint as well. You also don't have to worry about
+the formatting since this is automated via prettier, but this is of course not
+limited to VS-Code.

docs/help/contributing/090_NODE_TRANSFORMATION.md

@@ -0,0 +1,76 @@
+# Tranformation to nodes
+
+## Current state
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| generate(generate);
+    web --> |txt2img| generate(generate);
+    cli --> |txt2img| generate(generate);
+    cli --> |img2img| generate(generate);
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+```
+
+## Transitional Architecture
+
+### first step
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| img2img_node(Img2img node);
+    web --> |txt2img| generate(generate);
+    img2img_node --> model_manager;
+    img2img_node --> generators;
+    cli --> |txt2img| generate;
+    cli --> |img2img| generate;
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+```
+
+### second step
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img| img2img_node(img2img node);
+    img2img_node --> model_manager;
+    img2img_node --> generators;
+    web --> |txt2img| txt2img_node(txt2img node);
+    cli --> |txt2img| txt2img_node;
+    cli --> |img2img| generate(generate);
+    generate --> model_manager;
+    generate --> generators;
+    generate --> ti_manager[TI Manager];
+    generate --> etc;
+    txt2img_node --> model_manager;
+    txt2img_node --> generators;
+    txt2img_node --> ti_manager[TI Manager];
+```
+
+## Final Architecture
+
+```mermaid
+flowchart TD
+    web[WebUI];
+    cli[CLI];
+    web --> |img2img|img2img_node(img2img node);
+    cli --> |img2img|img2img_node;
+    web --> |txt2img|txt2img_node(txt2img node);
+    cli --> |txt2img|txt2img_node;
+    img2img_node --> model_manager;
+    txt2img_node --> model_manager;
+    img2img_node --> generators;
+    txt2img_node --> generators;
+    img2img_node --> ti_manager[TI Manager];
+    txt2img_node --> ti_manager[TI Manager];
+```

docs/help/contributing/index.md

@@ -0,0 +1,16 @@
+---
+title: Contributing
+---
+
+# :fontawesome-solid-code-commit: Contributing
+
+There are different ways how you can contribute to
+[InvokeAI](https://github.com/invoke-ai/InvokeAI), like Translations, opening
+Issues for Bugs or ideas how to improve.
+
+This Section of the docs will explain some of the different ways of how you can
+contribute to make it easier for newcommers as well as advanced users :nerd:
+
+If you want to contribute code, but you do not have an exact idea yet, take a
+look at the currently open
+[:fontawesome-solid-bug: Bug Reports](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)

docs/help/index.md

@@ -0,0 +1,12 @@
+# :material-help:Help
+
+If you are looking for help with the installation of InvokeAI, please take a
+look into the [Installation](../installation/index.md) section of the docs.
+
+Here you will find help to topics like
+
+-   how to contribute
+-   configuration recommendation for IDEs
+
+If you have an Idea about what's missing and aren't scared from contributing,
+just take a look at [DOCS](./contributing/030_DOCS.md) to find out how to do so.

docs/index.html

@@ -1,19 +0,0 @@
-<!-- HTML for static distribution bundle build -->
-<!DOCTYPE html>
-<html lang="en">
-  <head>
-    <meta charset="UTF-8">
-    <title>Swagger UI</title>
-    <link rel="stylesheet" type="text/css" href="swagger-ui/swagger-ui.css" />
-    <link rel="stylesheet" type="text/css" href="swagger-ui/index.css" />
-    <link rel="icon" type="image/png" href="swagger-ui/favicon-32x32.png" sizes="32x32" />
-    <link rel="icon" type="image/png" href="swagger-ui/favicon-16x16.png" sizes="16x16" />
-  </head>
-
-  <body>
-    <div id="swagger-ui"></div>
-    <script src="swagger-ui/swagger-ui-bundle.js" charset="UTF-8"> </script>
-    <script src="swagger-ui/swagger-ui-standalone-preset.js" charset="UTF-8"> </script>
-    <script src="swagger-ui/swagger-initializer.js" charset="UTF-8"> </script>
-  </body>
-</html>

docs/index.md

@@ -2,19 +2,20 @@
 title: Home
 ---
 
+# :octicons-home-16: Home
+
 <!--
   The Docs you find here (/docs/*) are built and deployed via mkdocs. If you want to run a local version to verify your changes, it's as simple as::
 
   ```bash
-  pip install -r requirements-mkdocs.txt
+  pip install -r docs/requirements-mkdocs.txt
   mkdocs serve
   ```
 -->
+
 <div align="center" markdown>
 
-# ^^**InvokeAI: A Stable Diffusion Toolkit**^^ :tools: <br> <small>Formerly known as lstein/stable-diffusion</small>
-
-[![project logo](assets/logo.png)](https://github.com/invoke-ai/InvokeAI)
+[![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
 
@@ -30,36 +31,36 @@ title: Home
 [![github open prs badge]][github open prs link]
 
 [ci checks on dev badge]:
-  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
+    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
+    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
+    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-invoke-conda.yml
+    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
+    https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
 [github forks link]:
-  https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
+    https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
 [github open issues badge]:
-  https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
 [github open issues link]:
-  https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
+    https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
 [github open prs badge]:
-  https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
 [github open prs link]:
-  https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
+    https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
 [github stars badge]:
-  https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
+    https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
 [latest commit to dev badge]:
-  https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
+    https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to dev link]:
-  https://github.com/invoke-ai/InvokeAI/commits/development
+    https://github.com/invoke-ai/InvokeAI/commits/development
 [latest release badge]:
-  https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
+    https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 
 </div>
@@ -70,7 +71,11 @@ image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
 Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
 
-**Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</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>]
+**Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</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="assets/invoke-web-server-1.png" width=640></div>
 
@@ -78,142 +83,439 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
 
     This fork is rapidly evolving. Please use the [Issues tab](https://github.com/invoke-ai/InvokeAI/issues) to report bugs and make feature requests. Be sure to use the provided templates. They will help aid diagnose issues faster.
 
-## :octicons-package-dependencies-24: Installation
-
-This fork is supported across multiple platforms. You can find individual
-installation instructions below.
-
-- :fontawesome-brands-linux: [Linux](installation/INSTALL_LINUX.md)
-- :fontawesome-brands-windows: [Windows](installation/INSTALL_WINDOWS.md)
-- :fontawesome-brands-apple: [Macintosh](installation/INSTALL_MAC.md)
-
 ## :fontawesome-solid-computer: Hardware Requirements
 
 ### :octicons-cpu-24: System
 
 You wil need one of the following:
 
-- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
+-   :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+-   :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
+    only)
+-   :fontawesome-brands-apple: An Apple computer with an M1 chip.
 
-### :fontawesome-solid-memory: Memory
+We do **not recommend** the following video cards due to issues with their
+running in half-precision mode and having insufficient VRAM to render 512x512
+images in full-precision mode:
 
-- At least 12 GB Main Memory RAM.
+-   NVIDIA 10xx series cards such as the 1080ti
+-   GTX 1650 series cards
+-   GTX 1660 series cards
 
-### :fontawesome-regular-hard-drive: Disk
+### :fontawesome-solid-memory: Memory and Disk
 
-- At least 12 GB of free disk space for the machine learning model, Python, and
-  all its dependencies.
+-   At least 12 GB Main Memory RAM.
+-   At least 18 GB of free disk space for the machine learning model, Python,
+    and all its dependencies.
 
-!!! info
+## :octicons-package-dependencies-24: Installation
 
-    If you are have a Nvidia 10xx series card (e.g. the 1080ti), please run the invoke script in
-    full-precision mode as shown below.
+This fork is supported across Linux, Windows and Macintosh. Linux users can use
+either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
+driver).
 
-    Similarly, specify full-precision mode on Apple M1 hardware.
+### [Installation Getting Started Guide](installation)
 
-    Precision is auto configured based on the device. If however you encounter errors like
-    `expected type Float but found Half` or `not implemented for Half` you can try starting
-    `invoke.py` with the `--precision=float32` flag:
+#### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
 
-    ```bash
-    (invokeai) ~/InvokeAI$ python scripts/invoke.py --full_precision
-    ```
+This method is recommended for 1st time users
+
+#### [Manual Installation](installation/020_INSTALL_MANUAL.md)
+
+This method is recommended for experienced users and developers
+
+#### [Docker Installation](installation/040_INSTALL_DOCKER.md)
+
+This method is recommended for those familiar with running Docker containers
+
+### Other Installation Guides
+
+-   [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
+-   [XFormers](installation/070_INSTALL_XFORMERS.md)
+-   [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
+-   [Installing New Models](installation/050_INSTALLING_MODELS.md)
+
+## :octicons-gift-24: InvokeAI Features
+
+### The InvokeAI Web Interface
+
+-   [WebUI overview](features/WEB.md)
+-   [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
+-   [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+-   [Visual Manual for InvokeAI v2.3.1](https://docs.google.com/presentation/d/e/2PACX-1vSE90aC7bVVg0d9KXVMhy-Wve-wModgPFp7AGVTOCgf4xE03SnV24mjdwldolfCr59D_35oheHe4Cow/pub?start=false&loop=true&delayms=60000) (contributed by Statcomm)
+
+<!-- separator -->
+
+<!-- separator -->
+
+### The InvokeAI Command Line Interface
+
+-   [Command Line Interace Reference Guide](features/CLI.md)
+<!-- separator -->
+
+### Image Management
+
+-   [Image2Image](features/IMG2IMG.md)
+-   [Inpainting](features/INPAINTING.md)
+-   [Outpainting](features/OUTPAINTING.md)
+-   [Adding custom styles and subjects](features/CONCEPTS.md)
+-   [Using LoRA models](features/LORAS.md)
+-   [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
+-   [Embiggen upscaling](features/EMBIGGEN.md)
+-   [Other Features](features/OTHER.md)
+
+<!-- separator -->
+
+### Model Management
+
+-   [Installing](installation/050_INSTALLING_MODELS.md)
+-   [Model Merging](features/MODEL_MERGING.md)
+-   [Adding custom styles and subjects via embeddings](features/CONCEPTS.md)
+-   [Textual Inversion](features/TEXTUAL_INVERSION.md)
+-   [Not Safe for Work (NSFW) Checker](features/NSFW.md)
+<!-- seperator -->
+
+### Prompt Engineering
+
+-   [Prompt Syntax](features/PROMPTS.md)
+-   [Generating Variations](features/VARIATIONS.md)
 
 ## :octicons-log-16: Latest Changes
 
-### v2.1.0 <small>(2 November 2022)</small>
+### v2.3.3 <small>(29 March 2023)</small>
 
-- [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).
-- ...
+#### Bug Fixes
+1. When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
+2. Textual inversion will select an appropriate batchsize based on whether `xformers` is active, and will default to `xformers` enabled if the library is detected.
+3. The batch script log file names have been fixed to be compatible with Windows.
+4. Occasional corruption of the `.next_prefix` file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
+5. An infinite loop when opening the developer's console from within the `invoke.sh` script has been corrected.
 
-### v2.0.1 <small>(13 October 2022)</small>
+#### Enhancements
+1. It is now possible to load and run several community-contributed SD-2.0 based models, including the infamous "Illuminati" model.
+2. The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI `embeddings` directory.
+3. If no `--model` is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
+4. On Linux systems, the `invoke.sh` launcher now uses a prettier console-based interface. To take advantage of it, install the `dialog` package using your package manager (e.g. `sudo apt install dialog`).
+5. When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
+```
+my-favorite-model.ckpt
+my-favorite-model.yaml
+my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
+```
 
-- 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)
+### v2.3.2 <small>(13 March 2023)</small>
 
-### v2.0.0 <small>(9 October 2022)</small>
+#### Bugfixes
 
-- `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`.
+Since version 2.3.1 the following bugs have been fixed:
 
-For older changelogs, please visit the
-**[CHANGELOG](CHANGELOG/#v114-11-september-2022)**.
+1. Black images appearing for potential NSFW images when generating with legacy checkpoint models and both `--no-nsfw_checker` and `--ckpt_convert` turned on.
+2. Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
+3. The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
+4. When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
+5. Crashes that occurred during model merging.
+6. Restore previous naming of Stable Diffusion base and 768 models.
+7. Upgraded to latest versions of `diffusers`, `transformers`, `safetensors` and `accelerate` libraries upstream. We hope that this will fix the `assertion NDArray > 2**32` issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
+
+As part of the upgrade to `diffusers`, the location of the diffusers-based models has changed from `models/diffusers` to `models/hub`. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your `models/diffusers` directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
+
+#### New "Invokeai-batch" script
+
+2.3.2 introduces a new command-line only script called
+`invokeai-batch` that can be used to generate hundreds of images from
+prompts and settings that vary systematically. This can be used to try
+the same prompt across multiple combinations of models, steps, CFG
+settings and so forth. It also allows you to template prompts and
+generate a combinatorial list like: ``` a shack in the mountains,
+photograph a shack in the mountains, watercolor a shack in the
+mountains, oil painting a chalet in the mountains, photograph a chalet
+in the mountains, watercolor a chalet in the mountains, oil painting a
+shack in the desert, photograph ...  ```
+
+If you have a system with multiple GPUs, or a single GPU with lots of
+VRAM, you can parallelize generation across the combinatorial set,
+reducing wait times and using your system's resources efficiently
+(make sure you have good GPU cooling).
+
+To try `invokeai-batch` out. Launch the "developer's console" using
+the `invoke` launcher script, or activate the invokeai virtual
+environment manually. From the console, give the command
+`invokeai-batch --help` in order to learn how the script works and
+create your first template file for dynamic prompt generation.
+
+### v2.3.1 <small>(26 February 2023)</small>
+
+This is primarily a bugfix release, but it does provide several new features that will improve the user experience. 
+
+#### Enhanced support for model management
+
+InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
+
+There are three ways of accessing the model management features:
+
+1. ***From the WebUI***, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
+
+![image](https://user-images.githubusercontent.com/111189/220638091-918492cc-0719-4194-b033-3741e8289b30.png)
+
+2. **Using the Model Installer App**
+
+Choose option (5) _download and install models_ from the `invoke` launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
+
+Command-line users can start this app using the command `invokeai-model-install`.
+
+![image](https://user-images.githubusercontent.com/111189/220660363-22ff3a2e-8082-410e-a818-d2b3a0529bac.png)
+
+3. **Using the Command Line Client (CLI)**
+
+The `!install_model` and `!convert_model` commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
+
+Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do **not** need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
+
+Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management.
+
+#### An Improved Installer Experience
+
+The installer now launches a console-based UI for setting and changing commonly-used startup options:
+
+![image](https://user-images.githubusercontent.com/111189/220644777-3d3a90ca-f9e2-4e6d-93da-cbdd66bf12f3.png)
+
+After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time,  you can edit the startup options by launching `invoke.sh`/`invoke.bat` and entering option (6) _change InvokeAI startup options_
+
+Command-line users can launch the new configure app using `invokeai-configure`.
+
+This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch `invoke.sh` or `invoke.bat` and choose option (9) _update InvokeAI_ . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
+
+![image](https://user-images.githubusercontent.com/111189/220650124-30a77137-d9cd-406e-a87d-d8283f99a4b3.png)
+
+Command-line users can run this interface by typing `invokeai-configure`
+
+#### Image Symmetry Options
+
+There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting _Symmetry_ from the image generation settings, or within the CLI by using the options `--h_symmetry_time_pct` and `--v_symmetry_time_pct` (these can be abbreviated to `--h_sym` and `--v_sym` like all other options).
+
+![image](https://user-images.githubusercontent.com/111189/220658687-47fd0f2c-7069-4d95-aec9-7196fceb360d.png)
+
+#### A New Unified Canvas Look
+
+This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select _Use Canvas Beta Layout_:
+
+![image](https://user-images.githubusercontent.com/111189/220646958-b7eca95e-dc39-4cd2-b277-63eac98ed446.png)
+
+Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
+
+![image](https://user-images.githubusercontent.com/111189/220647560-4a9265a1-6926-44f9-9d08-e1ef2ce61ff8.png)
+
+#### Model conversion and merging within the WebUI
+
+The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the `invoke.sh`/`invoke.bat` scripts.
+
+#### An easier way to contribute translations to the WebUI
+
+We have migrated our translation efforts to [Weblate](https://hosted.weblate.org/engage/invokeai/), a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief [translation guide](https://github.com/invoke-ai/InvokeAI/blob/v2.3.1/docs/other/TRANSLATION.md) for more information on how to contribute.
+
+#### Numerous internal bugfixes and performance issues
+
+This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to `diffusers 0.13.0`, and using the `compel` library for prompt parsing. See [Detailed Change Log](#full-change-log) for a detailed list of bugs caught and squished.
+
+#### Summary of InvokeAI command line scripts (all accessible via the launcher menu)
+
+| Command                  | Description                                                         |
+|--------------------------|---------------------------------------------------------------------|
+| `invokeai`               | Command line interface                                              |
+| `invokeai --web`         | Web interface                                                       |
+| `invokeai-model-install` | Model installer with console forms-based front end                  |
+| `invokeai-ti --gui`      | Textual inversion, with a console forms-based front end             |
+| `invokeai-merge --gui`   | Model merging, with a console forms-based front end                 |
+| `invokeai-configure`     | Startup configuration; can also be used to reinstall support models |
+| `invokeai-update`        | InvokeAI software updater                                           |
+
+
+### v2.3.0 <small>(9 February 2023)</small>
+
+#### Migration to Stable Diffusion `diffusers` models
+
+Previous versions of InvokeAI supported the original model file format
+introduced with Stable Diffusion 1.4. In the original format, known variously as
+"checkpoint", or "legacy" format, there is a single large weights file ending
+with `.ckpt` or `.safetensors`. Though this format has served the community
+well, it has a number of disadvantages, including file size, slow loading times,
+and a variety of non-standard variants that require special-case code to handle.
+In addition, because checkpoint files are actually a bundle of multiple machine
+learning sub-models, it is hard to swap different sub-models in and out, or to
+share common sub-models. A new format, introduced by the StabilityAI company in
+collaboration with HuggingFace, is called `diffusers` and consists of a
+directory of individual models. The most immediate benefit of `diffusers` is
+that they load from disk very quickly. A longer term benefit is that in the near
+future `diffusers` models will be able to share common sub-models, dramatically
+reducing disk space when you have multiple fine-tune models derived from the
+same base.
+
+When you perform a new install of version 2.3.0, you will be offered the option
+to install the `diffusers` versions of a number of popular SD models, including
+Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of
+2.1). These will act and work just like the checkpoint versions. Do not be
+concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk!
+InvokeAI 2.3.0 can still load these and generate images from them without any
+extra intervention on your part.
+
+To take advantage of the optimized loading times of `diffusers` models, InvokeAI
+offers options to convert legacy checkpoint models into optimized `diffusers`
+models. If you use the `invokeai` command line interface, the relevant commands
+are:
+
+-   `!convert_model` -- Take the path to a local checkpoint file or a URL that
+    is pointing to one, convert it into a `diffusers` model, and import it into
+    InvokeAI's models registry file.
+-   `!optimize_model` -- If you already have a checkpoint model in your InvokeAI
+    models file, this command will accept its short name and convert it into a
+    like-named `diffusers` model, optionally deleting the original checkpoint
+    file.
+-   `!import_model` -- Take the local path of either a checkpoint file or a
+    `diffusers` model directory and import it into InvokeAI's registry file. You
+    may also provide the ID of any diffusers model that has been published on
+    the
+    [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads)
+    and it will be downloaded and installed automatically.
+
+The WebGUI offers similar functionality for model management.
+
+For advanced users, new command-line options provide additional functionality.
+Launching `invokeai` with the argument `--autoconvert <path to directory>` takes
+the path to a directory of checkpoint files, automatically converts them into
+`diffusers` models and imports them. Each time the script is launched, the
+directory will be scanned for new checkpoint files to be loaded. Alternatively,
+the `--ckpt_convert` argument will cause any checkpoint or safetensors model
+that is already registered with InvokeAI to be converted into a `diffusers`
+model on the fly, allowing you to take advantage of future diffusers-only
+features without explicitly converting the model and saving it to disk.
+
+Please see
+[INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/)
+for more information on model management in both the command-line and Web
+interfaces.
+
+#### Support for the `XFormers` Memory-Efficient Crossattention Package
+
+On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once
+installed, the`xformers` package dramatically reduces the memory footprint of
+loaded Stable Diffusion models files and modestly increases image generation
+speed. `xformers` will be installed and activated automatically if you specify a
+CUDA system at install time.
+
+The caveat with using `xformers` is that it introduces slightly
+non-deterministic behavior, and images generated using the same seed and other
+settings will be subtly different between invocations. Generally the changes are
+unnoticeable unless you rapidly shift back and forth between images, but to
+disable `xformers` and restore fully deterministic behavior, you may launch
+InvokeAI using the `--no-xformers` option. This is most conveniently done by
+opening the file `invokeai/invokeai.init` with a text editor, and adding the
+line `--no-xformers` at the bottom.
+
+#### A Negative Prompt Box in the WebUI
+
+There is now a separate text input box for negative prompts in the WebUI. This
+is convenient for stashing frequently-used negative prompts ("mangled limbs, bad
+anatomy"). The `[negative prompt]` syntax continues to work in the main prompt
+box as well.
+
+To see exactly how your prompts are being parsed, launch `invokeai` with the
+`--log_tokenization` option. The console window will then display the
+tokenization process for both positive and negative prompts.
+
+#### Model Merging
+
+Version 2.3.0 offers an intuitive user interface for merging up to three Stable
+Diffusion models using an intuitive user interface. Model merging allows you to
+mix the behavior of models to achieve very interesting effects. To use this,
+each of the models must already be imported into InvokeAI and saved in
+`diffusers` format, then launch the merger using a new menu item in the InvokeAI
+launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line
+with `invokeai-merge --gui`. You will be prompted to select the models to merge,
+the proportions in which to mix them, and the mixing algorithm. The script will
+create a new merged `diffusers` model and import it into InvokeAI for your use.
+
+See
+[MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/)
+for more details.
+
+#### Textual Inversion Training
+
+Textual Inversion (TI) is a technique for training a Stable Diffusion model to
+emit a particular subject or style when triggered by a keyword phrase. You can
+perform TI training by placing a small number of images of the subject or style
+in a directory, and choosing a distinctive trigger phrase, such as
+"pointillist-style". After successful training, The subject or style will be
+activated by including `<pointillist-style>` in your prompt.
+
+Previous versions of InvokeAI were able to perform TI, but it required using a
+command-line script with dozens of obscure command-line arguments. Version 2.3.0
+features an intuitive TI frontend that will build a TI model on top of any
+`diffusers` model. To access training you can launch from a new item in the
+launcher script or from the command line using `invokeai-ti --gui`.
+
+See
+[TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/)
+for further details.
+
+#### A New Installer Experience
+
+The InvokeAI installer has been upgraded in order to provide a smoother and
+hopefully more glitch-free experience. In addition, InvokeAI is now packaged as
+a PyPi project, allowing developers and power-users to install InvokeAI with the
+command `pip install InvokeAI  --use-pep517`. Please see
+[Installation](#installation) for details.
+
+Developers should be aware that the `pip` installation procedure has been
+simplified and that the `conda` method is no longer supported at all.
+Accordingly, the `environments_and_requirements` directory has been deleted from
+the repository.
+
+#### Command-line name changes
+
+All of InvokeAI's functionality, including the WebUI, command-line interface,
+textual inversion training and model merging, can all be accessed from the
+`invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been
+expanded to add the new functionality. For the convenience of developers and
+power users, we have normalized the names of the InvokeAI command-line scripts:
+
+-   `invokeai` -- Command-line client
+-   `invokeai --web` -- Web GUI
+-   `invokeai-merge --gui` -- Model merging script with graphical front end
+-   `invokeai-ti --gui` -- Textual inversion script with graphical front end
+-   `invokeai-configure` -- Configuration tool for initializing the `invokeai`
+    directory and selecting popular starter models.
+
+For backward compatibility, the old command names are also recognized, including
+`invoke.py` and `configure-invokeai.py`. However, these are deprecated and will
+eventually be removed.
+
+Developers should be aware that the locations of the script's source code has
+been moved. The new locations are:
+
+-   `invokeai` => `ldm/invoke/CLI.py`
+-   `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
+-   `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
+-   `invokeai-merge` => `ldm/invoke/merge_diffusers`
+
+Developers are strongly encouraged to perform an "editable" install of InvokeAI
+using `pip install -e .  --use-pep517` in the Git repository, and then to call
+the scripts using their 2.3.0 names, rather than executing the scripts directly.
+Developers should also be aware that the several important data files have been
+relocated into a new directory named `invokeai`. This includes the WebGUI's
+`frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used
+by the installer to select starter models. Eventually all InvokeAI modules will
+be in subdirectories of `invokeai`.
+
+Please see
+[2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0)
+for further details. For older changelogs, please visit the
+**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
 
 ## :material-target: Troubleshooting
 
 Please check out our
-**[:material-frequently-asked-questions: Q&A](help/TROUBLESHOOT.md)** to get
-solutions for common installation problems and other issues.
+**[:material-frequently-asked-questions: Troubleshooting Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)**
+to get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing
 
@@ -239,8 +541,8 @@ thank them for their time, hard work and effort.
 For support, please use this repository's GitHub Issues tracking service. Feel
 free to send me an email if you use and like the script.
 
-Original portions of the software are Copyright (c) 2020
-[Lincoln D. Stein](https://github.com/lstein)
+Original portions of the software are Copyright (c) 2022-23 by
+[The InvokeAI Team](https://github.com/invoke-ai).
 
 ## :octicons-book-24: Further Reading
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -0,0 +1,520 @@
+---
+title: Installing with the Automated Installer
+---
+
+# InvokeAI Automated Installation
+
+## Introduction
+
+The automated installer is a Python script that automates the steps
+needed to install and run InvokeAI on a stock computer running recent
+versions of Linux, MacOS or Windows. It will leave you with a version
+that runs a stable version of InvokeAI with the option to upgrade to
+experimental versions later.
+
+## Walk through
+
+1.  <a name="hardware_requirements">**Hardware Requirements**: </a>Make sure that your system meets the [hardware
+    requirements](../index.md#hardware-requirements) and has the
+    appropriate GPU drivers installed. For a system with an NVIDIA
+    card installed, you will need to install the CUDA driver, while
+    AMD-based cards require the ROCm driver. In most cases, if you've
+    already used the system for gaming or other graphics-intensive
+    tasks, the appropriate drivers will already be installed. If
+    unsure, check the [GPU Driver Guide](030_INSTALL_CUDA_AND_ROCM.md)
+
+    !!! info "Required Space"
+
+        Installation requires roughly 18G of free disk space to load
+        the libraries and recommended model weights files.
+
+        Regardless of your destination disk, your *system drive*
+        (`C:\` on Windows, `/` on macOS/Linux) requires at least 6GB
+        of free disk space to download and cache python
+        dependencies.
+
+	NOTE for Linux users: if your temporary directory is mounted
+        as a `tmpfs`, ensure it has sufficient space.
+
+2.  <a name="software_requirements">**Software Requirements**: </a>Check that your system has an up-to-date Python installed. To do
+    this, open up a command-line window ("Terminal" on Linux and
+    Macintosh, "Command" or "Powershell" on Windows) and type `python
+    --version`. If Python is installed, it will print out the version
+    number. If it is version `3.9.*` or `3.10.*`, you meet
+    requirements. We do not recommend using Python 3.11 or higher,
+    as not all the libraries that InvokeAI depends on work properly
+    with this version.
+
+    !!! warning "What to do if you have an unsupported version"
+
+        Go to [Python Downloads](https://www.python.org/downloads/)
+        and download the appropriate installer package for your
+        platform. We recommend [Version
+        3.10.9](https://www.python.org/downloads/release/python-3109/),
+        which has been extensively tested with InvokeAI.
+
+    _Please select your platform in the section below for platform-specific
+    setup requirements._
+
+    === "Windows"
+        During the Python configuration process, look out for a
+        checkbox to add Python to your PATH and select it. If the
+        install script complains that it can't find python, then open
+        the Python installer again and choose "Modify" existing
+        installation.
+
+        Installation requires an up to date version of the Microsoft
+        Visual C libraries. Please install the 2015-2022 libraries
+        available here:
+        https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
+
+        Please double-click on the file `WinLongPathsEnabled.reg` and
+        accept the dialog box that asks you if you wish to modify your registry.
+        This activates long filename support on your system and will prevent
+        mysterious errors during installation.
+
+    === "Linux"
+         To install an appropriate version of Python on Ubuntu 22.04
+         and higher, run the following:
+
+         ```
+         sudo apt update
+         sudo apt install -y python3 python3-pip python3-venv
+         sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
+         ```
+
+         On Ubuntu 20.04, the process is slightly different:
+
+         ```
+         sudo apt update
+         sudo apt install -y software-properties-common
+         sudo add-apt-repository -y ppa:deadsnakes/ppa
+         sudo apt install python3.10 python3-pip python3.10-venv
+         sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
+         ```
+
+         Both `python` and `python3` commands are now pointing at
+         Python3.10. You can still access older versions of Python by
+         calling `python2`, `python3.8`, etc.
+
+         Linux systems require a couple of additional graphics
+         libraries to be installed for proper functioning of
+         `python3-opencv`. Please run the following:
+
+         `sudo apt update && sudo apt install -y libglib2.0-0 libgl1-mesa-glx`
+
+    === "Mac"
+
+        After installing Python, you may need to run the
+        following command from the Terminal in order to install the Web
+        certificates needed to download model data from https sites. If
+        you see lots of CERTIFICATE ERRORS during the last part of the
+        install, this is the problem, and you can fix it with this command:
+
+            `/Applications/Python\ 3.10/Install\ Certificates.command`
+
+        You may need to install the Xcode command line tools. These
+        are a set of tools that are needed to run certain applications in a
+        Terminal, including InvokeAI. This package is provided
+        directly by Apple. To install, open a terminal window and run `xcode-select --install`. You will get a macOS system popup guiding you through the
+        install. If you already have them installed, you will instead see some
+        output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
+
+3.  **Download the Installer**: The InvokeAI installer is distributed as a ZIP files. Go to the
+    [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),
+    and look for a file named:
+
+    - InvokeAI-installer-v2.X.X.zip
+
+    where "2.X.X" is the latest released version. The file is located
+    at the very bottom of the release page, under **Assets**.
+
+4.  **Unpack the installer**: Unpack the zip file into a convenient directory. This will create a new
+    directory named "InvokeAI-Installer". When unpacked, the directory
+    will look like this:
+
+    <figure markdown>
+    ![zipfile-screenshot](../assets/installer-walkthrough/unpacked-zipfile.png)
+    </figure>
+
+5.  **Launch the installer script from the desktop**: If you are using a desktop GUI, double-click the installer file
+    appropriate for your platform. It will be named `install.bat` on
+    Windows systems and `install.sh` on Linux and Macintosh
+    systems. Be aware that your system's file browser may suppress the
+    display of the file extension.
+
+    On Windows systems if you get an "Untrusted Publisher" warning.
+    Click on "More Info" and then select "Run Anyway." You trust us, right?
+
+6.  **[Alternative] Launch the installer script from the command line**: Alternatively, from the command line, run the shell script or .bat file:
+
+    ```cmd
+    C:\Documents\Linco> cd InvokeAI-Installer
+    C:\Documents\Linco\invokeAI> .\install.bat
+    ```
+
+7.  **Select the location to install InvokeAI**: The script will ask you to choose where to install InvokeAI. Select a
+    directory with at least 18G of free space for a full install. InvokeAI and
+    all its support files will be installed into a new directory named
+    `invokeai` located at the location you specify.
+
+    <figure markdown>
+    ![confirm-install-directory-screenshot](../assets/installer-walkthrough/confirm-directory.png)
+    </figure>
+
+    - The default is to install the `invokeai` directory in your home directory,
+      usually `C:\Users\YourName\invokeai` on Windows systems,
+      `/home/YourName/invokeai` on Linux systems, and `/Users/YourName/invokeai`
+      on Macintoshes, where "YourName" is your login name.
+
+    -If you have previously installed InvokeAI, you will be asked to
+     confirm whether you want to reinstall into this directory.  You
+     may choose to reinstall, in which case your version will be upgraded,
+     or choose a different directory.
+
+    - The script uses tab autocompletion to suggest directory path completions.
+      Type part of the path (e.g. "C:\Users") and press ++tab++ repeatedly
+      to suggest completions.
+
+8.  **Select your GPU**: The installer will autodetect your platform and will request you to
+    confirm the type of GPU your graphics card has. On Linux systems,
+    you will have the choice of CUDA (NVidia cards), ROCm (AMD cards),
+    or CPU (no graphics acceleration). On Windows, you'll have the
+    choice of CUDA vs CPU, and on Macs you'll be offered CPU only. When
+    you select CPU on M1 or M2 Macintoshes, you will get MPS-based
+    graphics acceleration without installing additional drivers. If you
+    are unsure what GPU you are using, you can ask the installer to
+    guess.
+
+9.  **Watch it go!**: Sit back and let the install script work. It will install the third-party
+    libraries needed by InvokeAI and the application itself.
+
+    Be aware that some of the library download and install steps take a long
+    time. In particular, the `pytorch` package is quite large and often appears
+    to get "stuck" at 99.9%. Have patience and the installation step will
+    eventually resume. However, there are occasions when the library install
+    does legitimately get stuck. If you have been waiting for more than ten
+    minutes and nothing is happening, you can interrupt the script with ^C. You
+    may restart it and it will pick up where it left off.
+
+    <figure markdown>
+    ![initial-settings-screenshot](../assets/installer-walkthrough/settings-form.png)
+    </figure>
+
+10. **Post-install Configuration**: After installation completes, the
+    installer will launch the configuration form, which will guide you
+    through the first-time process of adjusting some of InvokeAI's
+    startup settings. To move around this form use ctrl-N for
+    &lt;N&gt;ext and ctrl-P for &lt;P&gt;revious, or use &lt;tab&gt;
+    and shift-&lt;tab&gt; to move forward and back. Once you are in a
+    multi-checkbox field use the up and down cursor keys to select the
+    item you want, and &lt;space&gt; to toggle it on and off.  Within
+    a directory field, pressing &lt;tab&gt; will provide autocomplete
+    options.
+
+    Generally the defaults are fine, and you can come back to this screen at
+    any time to tweak your system. Here are the options you can adjust:
+
+    - ***Output directory for images***
+      This is the path to a directory in which InvokeAI will store all its
+      generated images.
+
+    - ***NSFW checker***
+      If checked, InvokeAI will test images for potential sexual content
+      and blur them out if found. Note that the NSFW checker consumes
+      an additional 0.6 GB of VRAM on top of the 2-3 GB of VRAM used
+      by most image models. If you have a low VRAM GPU (4-6 GB), you
+      can reduce out of memory errors by disabling the checker.
+
+    - ***HuggingFace Access Token***
+      InvokeAI has the ability to download embedded styles and subjects
+      from the HuggingFace Concept Library on-demand. However, some of
+      the concept library files are password protected. To make download
+      smoother, you can set up an account at huggingface.co, obtain an
+      access token, and paste it into this field. Note that you paste
+      to this screen using ctrl-shift-V
+
+    - ***Free GPU memory after each generation***
+        This is useful for low-memory machines and helps minimize the
+	amount of GPU VRAM used by InvokeAI.
+
+    - ***Enable xformers support if available***
+        If the xformers library was successfully installed, this will activate
+	it to reduce memory consumption and increase rendering speed noticeably.
+	Note that xformers has the side effect of generating slightly different
+	images even when presented with the same seed and other settings.
+
+    - ***Force CPU to be used on GPU systems***
+        This will use the (slow) CPU rather than the accelerated GPU. This
+	can be used to generate images on systems that don't have a compatible
+	GPU.
+
+    - ***Precision***
+        This controls whether to use float32 or float16 arithmetic.
+	float16 uses less memory but is also slightly less accurate.
+	Ordinarily the right arithmetic is picked automatically ("auto"),
+	but you may have to use float32 to get images on certain systems
+	and graphics cards. The "autocast" option is deprecated and
+	shouldn't be used unless you are asked to by a member of the team.
+
+    - ***Number of models to cache in CPU memory***
+        This allows you to keep models in memory and switch rapidly among
+	them rather than having them load from disk each time. This slider
+	controls how many models to keep loaded at once. Each
+	model will use 2-4 GB of RAM, so use this cautiously
+
+    - ***Directory containing embedding/textual inversion files***
+        This is the directory in which you can place custom embedding
+	files (.pt or .bin). During startup, this directory will be
+	scanned and InvokeAI will print out the text terms that
+	are available to trigger the embeddings.
+
+    At the bottom of the screen you will see a checkbox for accepting
+    the CreativeML Responsible AI License. You need to accept the license
+    in order to download Stable Diffusion models from the next screen.
+
+    _You can come back to the startup options form_ as many times as you like.
+    From the `invoke.sh` or `invoke.bat` launcher, select option (6) to relaunch
+    this script. On the command line, it is named `invokeai-configure`.
+
+11. **Downloading Models**: After you press `[NEXT]` on the screen, you will be taken
+    to another screen that prompts you to download a series of starter models. The ones
+    we recommend are preselected for you, but you are encouraged to use the checkboxes to
+    pick and choose.
+    You will probably wish to download `autoencoder-840000` for use with models that
+    were trained with an older version of the Stability VAE.
+
+    <figure markdown>
+    ![select-models-screenshot](../assets/installer-walkthrough/installing-models.png)
+    </figure>
+    
+    Below the preselected list of starter models is a large text field which you can use
+    to specify a series of models to import. You can specify models in a variety of formats,
+    each separated by a space or newline. The formats accepted are:
+
+    - The path to a .ckpt or .safetensors file. On most systems, you can drag a file from
+      the file browser to the textfield to automatically paste the path. Be sure to remove
+      extraneous quotation marks and other things that come along for the ride.
+
+    - The path to a directory containing a combination of `.ckpt` and `.safetensors` files.
+      The directory will be scanned from top to bottom (including subfolders) and any
+      file that can be imported will be.
+
+    - A URL pointing to a `.ckpt` or `.safetensors` file. You can cut
+      and paste directly from a web page, or simply drag the link from the web page
+      or navigation bar. (You can also use ctrl-shift-V to paste into this field)
+      The file will be downloaded and installed.
+      
+    - The HuggingFace repository ID (repo_id) for a `diffusers` model. These IDs have
+       the format _author_name/model_name_, as in `andite/anything-v4.0`
+      
+    - The path to a local directory containing a `diffusers`
+      model. These directories always have the file `model_index.json`
+      at their top level.
+
+    _Select a directory for models to import_ You may select a local
+    directory for autoimporting at startup time. If you select this
+    option, the directory you choose will be scanned for new
+    .ckpt/.safetensors files each time InvokeAI starts up, and any new
+    files will be automatically imported and made available for your
+    use.
+
+    _Convert imported models into diffusers_ When legacy checkpoint
+    files are imported, you may select to use them unmodified (the
+    default) or to convert them into `diffusers` models. The latter
+    load much faster and have slightly better rendering performance,
+    but not all checkpoint files can be converted. Note that Stable Diffusion
+    Version 2.X files are **only** supported in `diffusers` format and will
+    be converted regardless.
+     
+     _You can come back to the model install form_ as many times as you like.
+     From the `invoke.sh` or `invoke.bat` launcher, select option (5) to relaunch
+     this script. On the command line, it is named `invokeai-model-install`.
+
+12. **Running InvokeAI for the first time**: The script will now exit and you'll be ready to generate some images. Look
+    for the directory `invokeai` installed in the location you chose at the
+    beginning of the install session. Look for a shell script named `invoke.sh`
+    (Linux/Mac) or `invoke.bat` (Windows). Launch the script by double-clicking
+    it or typing its name at the command-line:
+
+    ```cmd
+    C:\Documents\Linco> cd invokeai
+    C:\Documents\Linco\invokeAI> invoke.bat
+    ```
+
+    - The `invoke.bat` (`invoke.sh`) script will give you the choice
+      of starting (1) the command-line interface, (2) the web GUI, (3)
+      textual inversion training, and (4) model merging.
+
+    - By default, the script will launch the web interface. When you
+      do this, you'll see a series of startup messages ending with
+      instructions to point your browser at
+      http://localhost:9090. Click on this link to open up a browser
+      and start exploring InvokeAI's features.
+
+12. **InvokeAI Options**: You can launch InvokeAI with several different command-line arguments that
+    customize its behavior. For example, you can change the location of the
+    image output directory, or select your favorite sampler. See the
+    [Command-Line Interface](../features/CLI.md) for a full list of the options.
+
+    - To set defaults that will take effect every time you launch InvokeAI,
+      use a text editor (e.g. Notepad) to exit the file
+      `invokeai\invokeai.init`. It contains a variety of examples that you can
+      follow to add and modify launch options.
+
+    - The launcher script also offers you an option labeled "open the developer
+      console". If you choose this option, you will be dropped into a
+      command-line interface in which you can run python commands directly,
+      access developer tools, and launch InvokeAI with customized options.
+
+
+    !!! warning "Do not move or remove the `invokeai` directory"
+      
+        The `invokeai` directory contains the `invokeai` application, its
+        configuration files, the model weight files, and outputs of image generation.
+        Once InvokeAI is installed, do not move or remove this directory."
+
+
+## Troubleshooting
+
+### _Package dependency conflicts_
+
+If you have previously installed InvokeAI or another Stable Diffusion
+package, the installer may occasionally pick up outdated libraries and
+either the installer or `invoke` will fail with complaints about
+library conflicts. In this case, run the `invoke.sh`/`invoke.bat`
+command and enter the Developer's Console by picking option (5). This
+will take you to a command-line prompt.
+
+Then give this command:
+
+`pip install InvokeAI --force-reinstall`
+
+This should fix the issues.
+
+### InvokeAI runs extremely slowly on Linux or Windows systems
+
+The most frequent cause of this problem is when the installation
+process installed the CPU-only version of the torch machine-learning
+library, rather than a version that takes advantage of GPU
+acceleration. To confirm this issue, look at the InvokeAI startup
+messages. If you see a message saying ">> Using device CPU", then
+this is what happened.
+
+To fix this problem, first determine whether you have an NVidia or an
+AMD GPU. The former uses the CUDA driver, and the latter uses ROCm
+(only available on Linux). Then run the `invoke.sh`/`invoke.bat`
+command and enter the Developer's Console by picking option (5). This
+will take you to a command-line prompt.
+
+Then type the following commands:
+
+=== "NVIDIA System"
+    ```bash
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install xformers
+    ```
+
+=== "AMD System"
+    ```bash
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    ```
+
+### Corrupted configuration file
+
+Everything seems to install ok, but `invokeai` complains of a corrupted
+configuration file and goes back into the configuration process (asking you to
+download models, etc), but this doesn't fix the problem.
+
+This issue is often caused by a misconfigured configuration directive in the
+`invokeai\invokeai.init` initialization file that contains startup settings. The
+easiest way to fix the problem is to move the file out of the way and re-run
+`invokeai-configure`. Enter the developer's console (option 3 of the launcher
+script) and run this command:
+
+```cmd
+invokeai-configure --root=.
+```
+
+Note the dot (.) after `--root`. It is part of the command.
+
+_If none of these maneuvers fixes the problem_ then please report the problem to
+the [InvokeAI Issues](https://github.com/invoke-ai/InvokeAI/issues) section, or
+visit our [Discord Server](https://discord.gg/ZmtBAhwWhy) for interactive
+assistance.
+
+### Out of Memory Issues
+
+The models are large, VRAM is expensive, and you may find yourself
+faced with Out of Memory errors when generating images. Here are some
+tips to reduce the problem:
+
+* **4 GB of VRAM**
+
+This should be adequate for 512x512 pixel images using Stable Diffusion 1.5
+and derived models, provided that you **disable** the NSFW checker. To
+disable the filter, do one of the following:
+
+   * Select option (6) "_change InvokeAI startup options_" from the
+     launcher. This will bring up the console-based startup settings
+     dialogue and allow you to unselect the "NSFW Checker" option.
+   * Start the startup settings dialogue directly by running
+     `invokeai-configure --skip-sd-weights --skip-support-models`
+     from the command line.
+   * Find the `invokeai.init` initialization file in the InvokeAI root
+     directory, open it in a text editor, and change `--nsfw_checker`
+     to `--no-nsfw_checker`
+
+If you are on a CUDA system, you can realize significant memory
+savings by activating the `xformers` library as described above. The
+downside is `xformers` introduces non-deterministic behavior, such
+that images generated with exactly the same prompt and settings will
+be slightly different from each other. See above for more information.
+
+* **6 GB of VRAM**
+
+This is a border case. Using the SD 1.5 series you should be able to
+generate images up to 640x640 with the NSFW checker enabled, and up to
+1024x1024 with it disabled and `xformers` activated. 
+
+If you run into persistent memory issues there are a series of
+environment variables that you can set before launching InvokeAI that
+alter how the PyTorch machine learning library manages memory.  See
+https://pytorch.org/docs/stable/notes/cuda.html#memory-management for
+a list of these tweaks.
+
+* **12 GB of VRAM**
+
+This should be sufficient to generate larger images up to about
+1280x1280. If you wish to push further, consider activating
+`xformers`.
+
+### Other Problems
+
+If you run into problems during or after installation, the InvokeAI team is
+available to help you. Either create an
+[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
+make a request for help on the "bugs-and-support" channel of our
+[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
+organization, but typically somebody will be available to help you within 24
+hours, and often much sooner.
+
+## Updating to newer versions
+
+This distribution is changing rapidly, and we add new features
+regularly. Releases are announced at
+http://github.com/invoke-ai/InvokeAI/releases, and at
+https://pypi.org/project/InvokeAI/ To update to the latest released
+version (recommended), follow these steps:
+
+1. Start the `invoke.sh`/`invoke.bat` launch script from within the
+   `invokeai` root directory.
+
+2. Choose menu item (10) "Update InvokeAI".
+
+3. This will launch a menu that gives you the option of:
+
+   1. Updating to the latest official release;
+   2. Updating to the bleeding-edge development version; or
+   3. Manually entering the tag or branch name of a version of
+      InvokeAI you wish to try out.

docs/installation/020_INSTALL_MANUAL.md

@@ -0,0 +1,369 @@
+---
+title: Installing Manually
+---
+
+<figure markdown>
+
+# :fontawesome-brands-linux: Linux | :fontawesome-brands-apple: macOS | :fontawesome-brands-windows: Windows
+
+</figure>
+
+!!! warning "This is for advanced Users"
+
+    **python experience is mandatory**
+
+## Introduction
+
+!!! tip "Conda"
+    As of InvokeAI v2.3.0 installation using the `conda` package manager is no longer being supported. It will likely still work, but we are not testing this installation method.
+
+On Windows systems, you are encouraged to install and use the
+[PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
+which provides compatibility with Linux and Mac shells and nice
+features such as command-line completion.
+
+### Prerequisites
+
+Before you start, make sure you have the following preqrequisites
+installed.  These are described in more detail in [Automated
+Installation](010_INSTALL_AUTOMATED.md), and in many cases will
+already be installed (if, for example, you have used your system for
+gaming):
+
+* **Python**
+
+    version 3.9 or 3.10 (3.11 is not recommended).
+
+* **CUDA Tools**
+
+    For those with _NVidia GPUs_, you will need to
+    install the [CUDA toolkit and optionally the XFormers library](070_INSTALL_XFORMERS.md).
+
+* **ROCm Tools**
+
+    For _Linux users with AMD GPUs_, you will need
+    to install the [ROCm toolkit](./030_INSTALL_CUDA_AND_ROCM.md). Note that
+    InvokeAI does not support AMD GPUs on Windows systems due to
+    lack of a Windows ROCm library.
+
+* **Visual C++ Libraries**
+
+    _Windows users_ must install the free
+    [Visual C++ libraries from Microsoft](https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170)
+
+* **The Xcode command line tools**
+
+    for _Macintosh users_. Instructions are available at
+    [Free Code Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
+
+    * _Macintosh users_ may also need to run the `Install Certificates` command
+      if model downloads give lots of certificate errors. Run:
+      `/Applications/Python\ 3.10/Install\ Certificates.command`
+
+### Installation Walkthrough
+
+To install InvokeAI with virtual environments and the PIP package
+manager, please follow these steps:
+
+1.  Please make sure you are using Python 3.9 or 3.10. The rest of the install
+    procedure depends on this and will not work with other versions:
+
+    ```bash
+    python -V
+    ```
+
+2.  Create a directory to contain your InvokeAI library, configuration
+    files, and models. This is known as the "runtime" or "root"
+    directory, and often lives in your home directory under the name `invokeai`.
+
+    Please keep in mind the disk space requirements - you will need at
+    least 20GB for the models and the virtual environment.  From now
+    on we will refer to this directory as `INVOKEAI_ROOT`. For convenience,
+    the steps below create a shell variable of that name which contains the
+    path to `HOME/invokeai`.
+
+    === "Linux/Mac"
+
+        ```bash
+        export INVOKEAI_ROOT=~/invokeai
+        mkdir $INVOKEAI_ROOT
+        ```
+
+    === "Windows (Powershell)"
+
+        ```bash
+        Set-Variable -Name INVOKEAI_ROOT -Value $Home/invokeai
+        mkdir $INVOKEAI_ROOT
+        ```
+
+3. Enter the root (invokeai) directory and create a virtual Python
+   environment within it named `.venv`. If the command `python`
+   doesn't work, try `python3`. Note that while you may create the
+   virtual environment anywhere in the file system, we recommend that
+   you create it within the root directory as shown here. This makes
+   it possible for the InvokeAI applications to find the model data
+   and configuration. If you do not choose to install the virtual
+   environment inside the root directory, then you **must** set the
+   `INVOKEAI_ROOT` environment variable in your shell environment, for
+   example, by editing `~/.bashrc` or `~/.zshrc` files, or setting the
+   Windows environment variable using the Advanced System Settings dialogue.
+   Refer to your operating system documentation for details.
+
+    ```terminal
+    cd $INVOKEAI_ROOT
+    python -m venv .venv --prompt InvokeAI
+    ```
+
+4.  Activate the new environment:
+
+    === "Linux/Mac"
+
+        ```bash
+        source .venv/bin/activate
+        ```
+
+    === "Windows"
+
+        ```ps
+        .venv\Scripts\activate
+        ```
+
+        If you get a permissions error at this point, run this command and try again
+
+        `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
+
+    The command-line prompt should change to to show `(InvokeAI)` at the
+    beginning of the prompt. Note that all the following steps should be
+    run while inside the INVOKEAI_ROOT directory
+
+5.  Make sure that pip is installed in your virtual environment and up to date:
+
+    ```bash
+    python -m pip install --upgrade pip
+    ```
+
+6. Install the InvokeAI Package. The `--extra-index-url` option is used to select among
+   CUDA, ROCm and CPU/MPS drivers as shown below:
+
+    === "CUDA (NVidia)"
+
+        ```bash
+        pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+        ```
+
+    === "ROCm (AMD)"
+
+        ```bash
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        ```
+
+    === "CPU (Intel Macs & non-GPU systems)"
+
+        ```bash
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+        ```
+
+    === "MPS (M1 and M2 Macs)"
+
+        ```bash
+        pip install InvokeAI --use-pep517
+        ```
+
+7.  Deactivate and reactivate your runtime directory so that the invokeai-specific commands
+    become available in the environment
+
+    === "Linux/Macintosh"
+
+        ```bash
+        deactivate && source .venv/bin/activate
+        ```
+
+    === "Windows"
+
+        ```ps
+        deactivate
+        .venv\Scripts\activate
+        ```
+
+8.  Set up the runtime directory
+
+    In this step you will initialize your runtime directory with the downloaded
+    models, model config files, directory for textual inversion embeddings, and
+    your outputs.
+
+    ```terminal
+    invokeai-configure
+    ```
+
+    The script `invokeai-configure` will interactively guide you through the
+    process of downloading and installing the weights files needed for InvokeAI.
+    Note that the main Stable Diffusion weights file is protected by a license
+    agreement that you have to agree to. The script will list the steps you need
+    to take to create an account on the site that hosts the weights files,
+    accept the agreement, and provide an access token that allows InvokeAI to
+    legally download and install the weights files.
+
+    If you get an error message about a module not being installed, check that
+    the `invokeai` environment is active and if not, repeat step 5.
+
+    !!! tip
+
+        If you have already downloaded the weights file(s) for another Stable
+        Diffusion distribution, you may skip this step (by selecting "skip" when
+        prompted) and configure InvokeAI to use the previously-downloaded files. The
+        process for this is described in [Installing Models](050_INSTALLING_MODELS.md).
+
+9.  Run the command-line- or the web- interface:
+
+    From within INVOKEAI_ROOT, activate the environment
+    (with `source .venv/bin/activate` or `.venv\scripts\activate), and then run
+    the script `invokeai`. If the virtual environment you selected is NOT inside
+    INVOKEAI_ROOT, then you must specify the path to the root directory by adding
+    `--root_dir \path\to\invokeai` to the commands below:
+
+    !!! example ""
+
+        !!! warning "Make sure that the virtual environment is activated, which should create `(.venv)` in front of your prompt!"
+
+        === "CLI"
+
+            ```bash
+            invokeai
+            ```
+
+        === "local Webserver"
+
+            ```bash
+            invokeai --web
+            ```
+
+        === "Public Webserver"
+
+            ```bash
+            invokeai --web --host 0.0.0.0
+            ```
+
+        If you choose the run the web interface, point your browser at
+        http://localhost:9090 in order to load the GUI.
+
+    !!! tip
+
+        You can permanently set the location of the runtime directory
+        by setting the environment variable `INVOKEAI_ROOT` to the
+        path of the directory. As mentioned previously, this is
+        *highly recommended** if your virtual environment is located outside of
+        your runtime directory.
+
+10.  Render away!
+
+    Browse the [features](../features/CLI.md) section to learn about all the
+    things you can do with InvokeAI.
+
+
+11.  Subsequently, to relaunch the script, activate the virtual environment, and
+    then launch `invokeai` command. If you forget to activate the virtual
+    environment you will most likeley receive a `command not found` error.
+
+    !!! warning
+
+        Do not move the runtime directory after installation. The virtual environment will get confused if the directory is moved.
+
+12. Other scripts
+
+    The [Textual Inversion](../features/TEXTUAL_INVERSION.md) script can be launched with the command:
+
+    ```bash
+    invokeai-ti --gui
+    ```
+
+    Similarly, the [Model Merging](../features/MODEL_MERGING.md) script can be launched with the command:
+
+    ```bash
+    invokeai-merge --gui
+    ```
+
+    Leave off the `--gui` option to run the script using command-line arguments. Pass the `--help` argument
+    to get usage instructions.
+
+### Developer Install
+
+If you have an interest in how InvokeAI works, or you would like to
+add features or bugfixes, you are encouraged to install the source
+code for InvokeAI. For this to work, you will need to install the
+`git` source code management program. If it is not already installed
+on your system, please see the [Git Installation
+Guide](https://github.com/git-guides/install-git)
+
+1. From the command line, run this command:
+   ```bash
+   git clone https://github.com/invoke-ai/InvokeAI.git
+   ```
+
+    This will create a directory named `InvokeAI` and populate it with the
+    full source code from the InvokeAI repository.
+
+2. Activate the InvokeAI virtual environment as per step (4) of the manual
+installation protocol (important!)
+
+3. Enter the InvokeAI repository directory and run one of these
+   commands, based on your GPU:
+
+    === "CUDA (NVidia)"
+        ```bash
+        pip install -e .[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+        ```
+
+    === "ROCm (AMD)"
+        ```bash
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        ```
+
+    === "CPU (Intel Macs & non-GPU systems)"
+        ```bash
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+        ```
+
+    === "MPS (M1 and M2 Macs)"
+        ```bash
+        pip install -e . --use-pep517
+        ```
+
+    Be sure to pass `-e` (for an editable install) and don't forget the
+    dot ("."). It is part of the command.
+
+    You can now run `invokeai` and its related commands. The code will be
+    read from the repository, so that you can edit the .py source files
+    and watch the code's behavior change.
+
+4.  If you wish to contribute to the InvokeAI project, you are
+    encouraged to establish a GitHub account and "fork"
+    https://github.com/invoke-ai/InvokeAI into your own copy of the
+    repository. You can then use GitHub functions to create and submit
+    pull requests to contribute improvements to the project.
+
+    Please see [Contributing](../index.md#contributing) for hints
+    on getting started.
+
+### Unsupported Conda Install
+
+Congratulations, you found the "secret" Conda installation
+instructions. If you really **really** want to use Conda with InvokeAI
+you can do so using this unsupported recipe:
+
+```
+mkdir ~/invokeai
+conda create -n invokeai python=3.10
+conda activate invokeai
+pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+invokeai-configure --root ~/invokeai
+invokeai --root ~/invokeai --web
+```
+
+The `pip install` command shown in this recipe is for Linux/Windows
+systems with an NVIDIA GPU. See step (6) above for the command to use
+with other platforms/GPU combinations. If you don't wish to pass the
+`--root` argument to `invokeai` with each launch, you may set the
+environment variable INVOKEAI_ROOT to point to the installation directory.
+
+Note that if you run into problems with the Conda installation, the InvokeAI
+staff will **not** be able to help you out. Caveat Emptor!

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -0,0 +1,133 @@
+---
+title: NVIDIA Cuda / AMD ROCm
+---
+
+<figure markdown>
+
+# :simple-nvidia: CUDA | :simple-amd: ROCm
+
+</figure>
+
+In order for InvokeAI to run at full speed, you will need a graphics
+card with a supported GPU. InvokeAI supports NVidia cards via the CUDA
+driver on Windows and Linux, and AMD cards via the ROCm driver on Linux.
+
+## :simple-nvidia: CUDA
+
+### Linux and Windows Install
+
+If you have used your system for other graphics-intensive tasks, such
+as gaming, you may very well already have the CUDA drivers
+installed. To confirm, open up a command-line window and type:
+
+```
+nvidia-smi
+```
+
+If this command produces a status report on the GPU(s) installed on
+your system, CUDA is installed and you have no more work to do. If
+instead you get "command not found", or similar, then the driver will
+need to be installed.
+
+We strongly recommend that you install the CUDA Toolkit package
+directly from NVIDIA. **Do not try to install Ubuntu's
+nvidia-cuda-toolkit package. It is out of date and will cause
+conflicts among the NVIDIA driver and binaries.**
+
+Go to [CUDA Toolkit 11.7
+Downloads](https://developer.nvidia.com/cuda-11-7-0-download-archive),
+and use the target selection wizard to choose your operating system,
+hardware platform, and preferred installation method (e.g. "local"
+versus "network").
+
+This will provide you with a downloadable install file or, depending
+on your choices, a recipe for downloading and running a install shell
+script. Be sure to read and follow the full installation instructions.
+
+After an install that seems successful, you can confirm by again
+running `nvidia-smi` from the command line.
+
+### Linux Install with a Runtime Container
+
+On Linux systems, an alternative to installing CUDA Toolkit directly on
+your system is to run an NVIDIA software container that has the CUDA
+libraries already in place. This is recommended if you are already 
+familiar with containerization technologies such as Docker.
+
+For downloads and instructions, visit the [NVIDIA CUDA Container
+Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
+
+### Torch Installation
+
+When installing torch and torchvision manually with `pip`, remember to provide
+the argument `--extra-index-url
+https://download.pytorch.org/whl/cu117` as described in the [Manual
+Installation Guide](020_INSTALL_MANUAL.md).
+
+## :simple-amd: ROCm
+
+### Linux Install
+
+AMD GPUs are only supported on Linux platforms due to the lack of a
+Windows ROCm driver at the current time. Also be aware that support
+for newer AMD GPUs is spotty. Your mileage may vary.
+
+It is possible that the ROCm driver is already installed on your
+machine. To test, open up a terminal window and issue the following
+command:
+
+```
+rocminfo
+```
+
+If you get a table labeled "ROCm System Management Interface" the
+driver is installed and you are done. If you get "command not found,"
+then the driver needs to be installed.
+
+Go to AMD's [ROCm Downloads
+Guide](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html#installation-methods)
+and scroll to the _Installation Methods_ section. Find the subsection
+for the install method for your preferred Linux distribution, and
+issue the commands given in the recipe.
+
+Annoyingly, the official AMD site does not have a recipe for the most
+recent version of Ubuntu, 22.04. However, this [community-contributed
+recipe](https://novaspirit.github.io/amdgpu-rocm-ubu22/) is reported
+to work well.
+
+After installation, please run `rocminfo` a second time to confirm
+that the driver is present and the GPU is recognized. You may need to
+do a reboot in order to load the driver. In addition, if you see
+errors relating to your username not being a member of the `render`
+group, you may fix this by adding yourself to this group with the command:
+
+```
+sudo usermod -a -G render myUserName
+```
+
+(Thanks to @EgoringKosmos for the usermod recipe.)
+
+### Linux Install with a ROCm-docker Container
+
+If you are comfortable with the Docker containerization system, then
+you can build a ROCm docker file. The source code and installation
+recipes are available
+[Here](https://github.com/RadeonOpenCompute/ROCm-docker/blob/master/quick-start.md)
+
+### Torch Installation
+
+When installing torch and torchvision manually with `pip`, remember to provide
+the argument `--extra-index-url
+https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
+Installation Guide](020_INSTALL_MANUAL.md).
+
+This will be done automatically for you if you use the installer
+script.
+
+Be aware that the torch machine learning library does not seamlessly
+interoperate with all AMD GPUs and you may experience garbled images,
+black images, or long startup delays before rendering commences. Most
+of these issues can be solved by Googling for workarounds. If you have
+a problem and find a solution, please post an
+[Issue](https://github.com/invoke-ai/InvokeAI/issues) so that other
+users benefit and we can update this document.

docs/installation/040_INSTALL_DOCKER.md

@@ -0,0 +1,279 @@
+---
+title: Installing with Docker
+---
+
+# :fontawesome-brands-docker: Docker
+
+!!! warning "For end users"
+
+    We highly recommend to Install InvokeAI locally using [these instructions](index.md)
+
+!!! tip "For developers"
+
+    For container-related development tasks or for enabling easy
+    deployment to other environments (on-premises or cloud), follow these
+    instructions.
+
+    For general use, install locally to leverage your machine's GPU.
+
+## Why containers?
+
+They provide a flexible, reliable way to build and deploy InvokeAI. You'll also
+use a Docker volume to store the largest model files and image outputs as a
+first step in decoupling storage and compute. Future enhancements can do this
+for other assets. See [Processes](https://12factor.net/processes) under the
+Twelve-Factor App methodology for details on why running applications in such a
+stateless fashion is important.
+
+You can specify the target platform when building the image and running the
+container. You'll also need to specify the InvokeAI requirements file that
+matches the container's OS and the architecture it will run on.
+
+Developers on Apple silicon (M1/M2): You
+[can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224)
+and performance is reduced compared with running it directly on macOS but for
+development purposes it's fine. Once you're done with development tasks on your
+laptop you can build for the target platform and architecture and deploy to
+another environment with NVIDIA GPUs on-premises or in the cloud.
+
+## Installation in a Linux container (desktop)
+
+### Prerequisites
+
+#### Install [Docker](https://github.com/santisbon/guides#docker)
+
+On the [Docker Desktop app](https://docs.docker.com/get-docker/), go to
+Preferences, Resources, Advanced. Increase the CPUs and Memory to avoid this
+[Issue](https://github.com/invoke-ai/InvokeAI/issues/342). You may need to
+increase Swap and Disk image size too.
+
+#### Get a Huggingface-Token
+
+Besides the Docker Agent you will need an Account on
+[huggingface.co](https://huggingface.co/join).
+
+After you succesfully registered your account, go to
+[huggingface.co/settings/tokens](https://huggingface.co/settings/tokens), create
+a token and copy it, since you will need in for the next step.
+
+### Setup
+
+Set the fork you want to use and other variables.
+
+!!! tip
+
+    I preffer to save my env vars
+    in the repository root in a `.env` (or `.envrc`) file to automatically re-apply
+    them when I come back.
+
+The build- and run- scripts contain default values for almost everything,
+besides the [Hugging Face Token](https://huggingface.co/settings/tokens) you
+created in the last step.
+
+Some Suggestions of variables you may want to change besides the Token:
+
+<figure markdown>
+
+| Environment-Variable <img width="220" align="right"/> | Default value <img width="360" align="right"/> | Description                                                                                                                                                                                       |
+| ----------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `HUGGING_FACE_HUB_TOKEN`                              | No default, but **required**!                  | This is the only **required** variable, without it you can't download the huggingface models                                                                                                      |
+| `REPOSITORY_NAME`                                     | The Basename of the Repo folder                | This name will used as the container repository/image name                                                                                                                                        |
+| `VOLUMENAME`                                          | `${REPOSITORY_NAME,,}_data`                    | Name of the Docker Volume where model files will be stored                                                                                                                                        |
+| `ARCH`                                                | arch of the build machine                      | Can be changed if you want to build the image for another arch                                                                                                                                    |
+| `CONTAINER_REGISTRY`                                  | ghcr.io                                        | Name of the Container Registry to use for the full tag                                                                                                                                            |
+| `CONTAINER_REPOSITORY`                                | `$(whoami)/${REPOSITORY_NAME}`                 | Name of the Container Repository                                                                                                                                                                  |
+| `CONTAINER_FLAVOR`                                    | `cuda`                                         | The flavor of the image to built, available options are `cuda`, `rocm` and `cpu`. If you choose `rocm` or `cpu`, the extra-index-url will be selected automatically, unless you set one yourself. |
+| `CONTAINER_TAG`                                       | `${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}`   | The Container Repository / Tag which will be used                                                                                                                                                 |
+| `INVOKE_DOCKERFILE`                                   | `Dockerfile`                                   | The Dockerfile which should be built, handy for development                                                                                                                                       |
+| `PIP_EXTRA_INDEX_URL`                                 |                                                | If you want to use a custom pip-extra-index-url                                                                                                                                                   |
+
+</figure>
+
+#### Build the Image
+
+I provided a build script, which is located next to the Dockerfile in
+`docker/build.sh`. It can be executed from repository root like this:
+
+```bash
+./docker/build.sh
+```
+
+The build Script not only builds the container, but also creates the docker
+volume if not existing yet.
+
+#### Run the Container
+
+After the build process is done, you can run the container via the provided
+`docker/run.sh` script
+
+```bash
+./docker/run.sh
+```
+
+When used without arguments, the container will start the webserver and provide
+you the link to open it. But if you want to use some other parameters you can
+also do so.
+
+!!! example "run script example"
+
+    ```bash
+    ./docker/run.sh "banana sushi" -Ak_lms -S42 -s10
+    ```
+
+    This would generate the legendary "banana sushi" with Seed 42, k_lms Sampler and 10 steps.
+
+    Find out more about available CLI-Parameters at [features/CLI.md](../../features/CLI/#arguments)
+
+---
+
+## Running the container on your GPU
+
+If you have an Nvidia GPU, you can enable InvokeAI to run on the GPU by running
+the container with an extra environment variable to enable GPU usage and have
+the process run much faster:
+
+```bash
+GPU_FLAGS=all ./docker/run.sh
+```
+
+This passes the `--gpus all` to docker and uses the GPU.
+
+If you don't have a GPU (or your host is not yet setup to use it) you will see a
+message like this:
+
+`docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]].`
+
+You can use the full set of GPU combinations documented here:
+
+https://docs.docker.com/config/containers/resource_constraints/#gpu
+
+For example, use `GPU_FLAGS=device=GPU-3a23c669-1f69-c64e-cf85-44e9b07e7a2a` to
+choose a specific device identified by a UUID.
+
+---
+
+!!! warning "Deprecated"
+
+    From here on you will find the the previous Docker-Docs, which will still
+    provide some usefull informations.
+
+## Usage (time to have fun)
+
+### Startup
+
+If you're on a **Linux container** the `invoke` script is **automatically
+started** and the output dir set to the Docker volume you created earlier.
+
+If you're **directly on macOS follow these startup instructions**. With the
+Conda environment activated (`conda activate ldm`), run the interactive
+interface that combines the functionality of the original scripts `txt2img` and
+`img2img`: Use the more accurate but VRAM-intensive full precision math because
+half-precision requires autocast and won't work. By default the images are saved
+in `outputs/img-samples/`.
+
+```Shell
+python3 scripts/invoke.py --full_precision
+```
+
+You'll get the script's prompt. You can see available options or quit.
+
+```Shell
+invoke> -h
+invoke> q
+```
+
+### Text to Image
+
+For quick (but bad) image results test with 5 steps (default 50) and 1 sample
+image. This will let you know that everything is set up correctly. Then increase
+steps to 100 or more for good (but slower) results. The prompt can be in quotes
+or not.
+
+```Shell
+invoke> The hulk fighting with sheldon cooper -s5 -n1
+invoke> "woman closeup highly detailed"  -s 150
+# Reuse previous seed and apply face restoration
+invoke> "woman closeup highly detailed"  --steps 150 --seed -1 -G 0.75
+```
+
+You'll need to experiment to see if face restoration is making it better or
+worse for your specific prompt.
+
+If you're on a container the output is set to the Docker volume. You can copy it
+wherever you want. You can download it from the Docker Desktop app, Volumes,
+my-vol, data. Or you can copy it from your Mac terminal. Keep in mind
+`docker cp` can't expand `*.png` so you'll need to specify the image file name.
+
+On your host Mac (you can use the name of any container that mounted the
+volume):
+
+```Shell
+docker cp dummy:/data/000001.928403745.png /Users/<your-user>/Pictures
+```
+
+### Image to Image
+
+You can also do text-guided image-to-image translation. For example, turning a
+sketch into a detailed drawing.
+
+`strength` is a value between 0.0 and 1.0 that controls the amount of noise that
+is added to the input image. Values that approach 1.0 allow for lots of
+variations but will also produce images that are not semantically consistent
+with the input. 0.0 preserves image exactly, 1.0 replaces it completely.
+
+Make sure your input image size dimensions are multiples of 64 e.g. 512x512.
+Otherwise you'll get `Error: product of dimension sizes > 2**31'`. If you still
+get the error
+[try a different size](https://support.apple.com/guide/preview/resize-rotate-or-flip-an-image-prvw2015/mac#:~:text=image's%20file%20size-,In%20the%20Preview%20app%20on%20your%20Mac%2C%20open%20the%20file,is%20shown%20at%20the%20bottom.)
+like 512x256.
+
+If you're on a Docker container, copy your input image into the Docker volume
+
+```Shell
+docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
+```
+
+Try it out generating an image (or more). The `invoke` script needs absolute
+paths to find the image so don't use `~`.
+
+If you're on your Mac
+
+```Shell
+invoke> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75  --steps 100 -n4
+```
+
+If you're on a Linux container on your Mac
+
+```Shell
+invoke> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75  --steps 50 -n1
+```
+
+### Web Interface
+
+You can use the `invoke` script with a graphical web interface. Start the web
+server with:
+
+```Shell
+python3 scripts/invoke.py --full_precision --web
+```
+
+If it's running on your Mac point your Mac web browser to
+<http://127.0.0.1:9090>
+
+Press Control-C at the command line to stop the web server.
+
+### Notes
+
+Some text you can add at the end of the prompt to make it very pretty:
+
+```Shell
+cinematic photo, highly detailed, cinematic lighting, ultra-detailed, ultrarealistic, photorealism, Octane Rendering, cyberpunk lights, Hyper Detail, 8K, HD, Unreal Engine, V-Ray, full hd, cyberpunk, abstract, 3d octane render + 4k UHD + immense detail + dramatic lighting + well lit + black, purple, blue, pink, cerulean, teal, metallic colours, + fine details, ultra photoreal, photographic, concept art, cinematic composition, rule of thirds, mysterious, eerie, photorealism, breathtaking detailed, painting art deco pattern, by hsiao, ron cheng, john james audubon, bizarre compositions, exquisite detail, extremely moody lighting, painted by greg rutkowski makoto shinkai takashi takeuchi studio ghibli, akihiko yoshida
+```
+
+The original scripts should work as well.
+
+```Shell
+python3 scripts/orig_scripts/txt2img.py --help
+python3 scripts/orig_scripts/txt2img.py --ddim_steps 100 --n_iter 1 --n_samples 1  --plms --prompt "new born baby kitten. Hyper Detail, Octane Rendering, Unreal Engine, V-Ray"
+python3 scripts/orig_scripts/txt2img.py --ddim_steps 5   --n_iter 1 --n_samples 1  --plms --prompt "ocean" # or --klms
+```

docs/installation/050_INSTALLING_MODELS.md

@@ -0,0 +1,459 @@
+---
+title: Installing Models
+---
+
+# :octicons-paintbrush-16: Installing Models
+
+## Checkpoint and Diffusers Models
+
+The model checkpoint files ('\*.ckpt') are the Stable Diffusion
+"secret sauce". They are the product of training the AI on millions of
+captioned images gathered from multiple sources.
+
+Originally there was only a single Stable Diffusion weights file,
+which many people named `model.ckpt`. Now there are hundreds
+that have been fine tuned to provide particulary styles, genres, or
+other features. In addition, there are several new formats that
+improve on the original checkpoint format: a `.safetensors` format
+which prevents malware from masquerading as a model, and `diffusers`
+models, the most recent innovation.
+
+InvokeAI supports all three formats but strongly prefers the
+`diffusers` format. These are distributed as directories containing
+multiple subfolders, each of which contains a different aspect of the
+model. The advantage of this is that the models load from disk really
+fast. Another advantage is that `diffusers` models are supported by a
+large and active set of open source developers working at and with
+HuggingFace organization, and improvements in both rendering quality
+and performance are being made at a rapid pace. Among other features
+is the ability to download and install a `diffusers` model just by
+providing its HuggingFace repository ID.
+
+While InvokeAI will continue to support legacy `.ckpt` and `.safetensors`
+models for the near future, these are deprecated and support will
+be withdrawn in version 3.0, after which all legacy models will be
+converted into diffusers at the time they are loaded.
+
+This manual will guide you through installing and configuring model
+weight files and converting legacy `.ckpt` and `.safetensors` files
+into performant `diffusers` models.
+
+## Base Models
+
+InvokeAI comes with support for a good set of starter models. You'll
+find them listed in the master models file
+`configs/INITIAL_MODELS.yaml` in the InvokeAI root directory. The
+subset that are currently installed are found in
+`configs/models.yaml`. As of v2.3.1, the list of starter models is:
+
+|Model Name | HuggingFace Repo ID | Description | URL |
+|---------- | ---------- | ----------- | --- |
+|stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
+|sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
+|stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
+|deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
+|d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |
+|dreamlike-photoreal-2.0|dreamlike-art/dreamlike-photoreal-2.0|A photorealistic model trained on 768 pixel images based on SD 1.5 (2.13 GB)|https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0 |
+|inkpunk-1.0|Envvi/Inkpunk-Diffusion|Stylized illustrations inspired by Gorillaz, FLCL and Shinkawa; prompt with "nvinkpunk" (4.27 GB)|https://huggingface.co/Envvi/Inkpunk-Diffusion |
+|openjourney-4.0|prompthero/openjourney|An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)|https://huggingface.co/prompthero/openjourney |
+|portrait-plus-1.0|wavymulder/portraitplus|An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)|https://huggingface.co/wavymulder/portraitplus |
+|seek-art-mega-1.0|coreco/seek.art_MEGA|A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)|https://huggingface.co/coreco/seek.art_MEGA |
+|trinart-2.0|naclbit/trinart_stable_diffusion_v2|An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)|https://huggingface.co/naclbit/trinart_stable_diffusion_v2 |
+|waifu-diffusion-1.4|hakurei/waifu-diffusion|An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)|https://huggingface.co/hakurei/waifu-diffusion |
+
+Note that these files are covered by an "Ethical AI" license which
+forbids certain uses. When you initially download them, you are asked
+to accept the license terms. In addition, some of these models carry
+additional license terms that limit their use in commercial
+applications or on public servers. Be sure to familiarize yourself
+with the model terms by visiting the URLs in the table above.
+
+## Community-Contributed Models
+
+There are too many to list here and more are being contributed every
+day.  [HuggingFace](https://huggingface.co/models?library=diffusers)
+is a great resource for diffusers models, and is also the home of a
+[fast-growing repository](https://huggingface.co/sd-concepts-library)
+of embedding (".bin") models that add subjects and/or styles to your
+images. The latter are automatically installed on the fly when you
+include the text `<concept-name>` in your prompt. See [Concepts
+Library](../features/CONCEPTS.md) for more information.
+
+Another popular site for community-contributed models is
+[CIVITAI](https://civitai.com). This extensive site currently supports
+only `.safetensors` and `.ckpt` models, but they can be easily loaded
+into InvokeAI and/or converted into optimized `diffusers` models. Be
+aware that CIVITAI hosts many models that generate NSFW content.
+
+!!! note
+
+    InvokeAI 2.3.x does not support directly importing and
+    running Stable Diffusion version 2 checkpoint models. If you
+    try to import them, they will be automatically
+    converted into `diffusers` models on the fly. This adds about 20s
+    to loading time. To avoid this overhead, you are encouraged to
+    use one of the conversion methods described below to convert them
+    permanently.
+
+## Installation
+
+There are multiple ways to install and manage models:
+
+1. The `invokeai-model-install` script which will download and install them for you.
+
+2. The command-line tool (CLI) has commands that allows you to import, configure and modify
+   models files.
+
+3. The web interface (WebUI) has a GUI for importing and managing
+   models.
+
+### Installation via `invokeai-model-install`
+
+From the `invoke` launcher, choose option (5) "Download and install
+models."  This will launch the same script that prompted you to select
+models at install time. You can use this to add models that you
+skipped the first time around. It is all right to specify a model that
+was previously downloaded; the script will just confirm that the files
+are complete.
+
+This script allows you to load 3d party models. Look for a large text
+entry box labeled "IMPORT LOCAL AND REMOTE MODELS." In this box, you
+can cut and paste one or more of any of the following:
+
+1. A URL that points to a downloadable .ckpt or .safetensors file.
+2. A file path pointing to a .ckpt or .safetensors  file.
+3. A diffusers model repo_id (from HuggingFace) in the format
+   "owner/repo_name".
+4. A directory path pointing to a diffusers model directory.
+5. A directory path pointing to a directory containing a bunch of
+   .ckpt and .safetensors files. All will be imported.
+
+You can enter multiple items into the textbox, each one on a separate
+line. You can paste into the textbox using ctrl-shift-V or by dragging
+and dropping a file/directory from the desktop into the box.
+
+The script also lets you designate a directory that will be scanned
+for new model files each time InvokeAI starts up. These models will be
+added automatically.
+
+Lastly, the script gives you a checkbox option to convert legacy models
+into diffusers, or to run the legacy model directly. If you choose to
+convert, the original .ckpt/.safetensors file will **not** be deleted,
+but a new diffusers directory will be created, using twice your disk
+space. However, the diffusers version will load faster, and will be
+compatible with InvokeAI 3.0.
+
+### Installation via the CLI
+
+You can install a new model, including any of the community-supported ones, via
+the command-line client's `!import_model` command.
+
+#### Installing individual `.ckpt` and `.safetensors` models
+
+If the model is already downloaded to your local disk, use
+`!import_model /path/to/file.ckpt` to load it. For example:
+
+```bash
+invoke> !import_model C:/Users/fred/Downloads/martians.safetensors
+```
+
+!!! tip "Forward Slashes"
+    On Windows systems, use forward slashes rather than backslashes
+    in your file paths.
+    If you do use backslashes,
+    you must double them like this:
+    `C:\\Users\\fred\\Downloads\\martians.safetensors`
+
+Alternatively you can directly import the file using its URL:
+
+```bash
+invoke> !import_model https://example.org/sd_models/martians.safetensors
+```
+
+For this to work, the URL must not be password-protected. Otherwise
+you will receive a 404 error.
+
+When you import a legacy model, the CLI will try to figure out what
+type of model it is and select the correct load configuration file.
+However, one thing it can't do is to distinguish between Stable
+Diffusion 2.x models trained on 512x512 vs 768x768 images. In this
+case, the CLI will pop up a menu of choices, asking you to select
+which type of model it is. Please consult the model documentation to
+identify the correct answer, as loading with the wrong configuration
+will lead to black images. You can correct the model type after the
+fact using the `!edit_model` command.
+
+After importing, the model will load. If this is successful, you will
+be asked if you want to keep the model loaded in memory to start
+generating immediately. You'll also be asked if you wish to make this
+the default model on startup. You can change this later using
+`!edit_model`.
+
+#### Importing a batch of `.ckpt` and `.safetensors` models from a directory
+
+You may also point `!import_model` to a directory containing a set of
+`.ckpt` or `.safetensors` files. They will be imported _en masse_.
+
+!!! example
+
+    ```console
+    invoke> !import_model C:/Users/fred/Downloads/civitai_models/
+    ```
+
+You will be given the option to import all models found in the
+directory, or select which ones to import. If there are subfolders
+within the directory, they will be searched for models to import.
+
+#### Installing `diffusers` models
+
+You can install a `diffusers` model from the HuggingFace site using
+`!import_model` and the HuggingFace repo_id for the model:
+
+```bash
+invoke> !import_model andite/anything-v4.0
+```
+
+Alternatively, you can download the model to disk and import it from
+there. The model may be distributed as a ZIP file, or as a Git
+repository:
+
+```bash
+invoke> !import_model C:/Users/fred/Downloads/andite--anything-v4.0
+```
+
+!!! tip "The CLI supports file path autocompletion"
+         Type a bit of the path name and hit ++tab++ in order to get a choice of
+         possible completions.
+
+!!! tip "On Windows, you can drag model files onto the command-line"
+         Once you have typed in `!import_model `, you can drag the
+         model  file or directory onto the command-line to insert the model path. This way, you don't need to
+         type it or copy/paste. However, you will need to reverse or
+         double backslashes as noted above.
+
+Before installing, the CLI will ask you for a short name and
+description for the model, whether to make this the default model that
+is loaded at InvokeAI startup time, and whether to replace its
+VAE. Generally the answer to the latter question is "no".
+
+### Installation via the WebUI
+
+To access the WebUI Model Manager, click on the button that looks like
+a cube in the upper right side of the browser screen. This will bring
+up a dialogue that lists the models you have already installed, and
+allows you to load, delete or edit them:
+
+<figure markdown>
+
+![model-manager](../assets/installing-models/webui-models-1.png)
+
+</figure>
+
+To add a new model, click on **+ Add New** and select to either a
+checkpoint/safetensors model, or a diffusers model:
+
+<figure markdown>
+
+![model-manager-add-new](../assets/installing-models/webui-models-2.png)
+
+</figure>
+
+In this example, we chose **Add Diffusers**. As shown in the figure
+below, a new dialogue prompts you to enter the name to use for the
+model, its description, and either the location of the `diffusers`
+model on disk, or its Repo ID on the HuggingFace web site. If you
+choose to enter a path to disk, the system will autocomplete for you
+as you type:
+
+<figure markdown>
+
+![model-manager-add-diffusers](../assets/installing-models/webui-models-3.png)
+
+</figure>
+
+Press **Add Model** at the bottom of the dialogue (scrolled out of
+site in the figure), and the model will be downloaded, imported, and
+registered in `models.yaml`.
+
+The **Add Checkpoint/Safetensor Model** option is similar, except that
+in this case you can choose to scan an entire folder for
+checkpoint/safetensors files to import. Simply type in the path of the
+directory and press the "Search" icon. This will display the
+`.ckpt` and `.safetensors` found inside the directory and its
+subfolders, and allow you to choose which ones to import:
+
+<figure markdown>
+
+![model-manager-add-checkpoint](../assets/installing-models/webui-models-4.png)
+
+</figure>
+
+## Model Management Startup Options
+
+The `invoke` launcher and the `invokeai` script accept a series of
+command-line arguments that modify InvokeAI's behavior when loading
+models. These can be provided on the command line, or added to the
+InvokeAI root directory's `invokeai.init` initialization file.
+
+The arguments are:
+
+* `--model <model name>` -- Start up with the indicated model loaded
+* `--ckpt_convert` -- When a checkpoint/safetensors model is loaded, convert it into a `diffusers` model in memory. This does not permanently save the converted model to disk.
+* `--autoconvert <path/to/directory>` -- Scan the indicated directory path for new checkpoint/safetensors files, convert them into `diffusers` models, and import them into InvokeAI.
+
+Here is an example of providing an argument on the command line using
+the `invoke.sh` launch script:
+
+```bash
+invoke.sh --autoconvert /home/fred/stable-diffusion-checkpoints
+```
+
+And here is what the same argument looks like in `invokeai.init`:
+
+```bash
+--outdir="/home/fred/invokeai/outputs
+--no-nsfw_checker
+--autoconvert /home/fred/stable-diffusion-checkpoints
+```
+
+### Specifying a configuration file for legacy checkpoints
+
+Some checkpoint files come with instructions to use a specific .yaml
+configuration file. For InvokeAI load this file correctly, please put
+the config file in the same directory as the corresponding `.ckpt` or
+`.safetensors` file and make sure the file has the same basename as
+the model file. Here is an example:
+
+```bash
+wonderful-model-v2.ckpt
+wonderful-model-v2.yaml
+```
+
+This is not needed for `diffusers` models, which come with their own
+pre-packaged configuration.
+
+### Specifying a custom VAE file for legacy checkpoints
+
+To associate a custom VAE with a legacy file, place the VAE file in
+the same directory as the corresponding `.ckpt` or
+`.safetensors` file and make sure the file has the same basename as
+the model file. Use the suffix `.vae.pt` for VAE checkpoint files, and
+`.vae.safetensors` for VAE safetensors files. There is no requirement
+that both the model and the VAE follow the same format.
+
+Example:
+
+```bash
+wonderful-model-v2.pt
+wonderful-model-v2.vae.safetensors
+```
+
+### Converting legacy models into `diffusers`
+
+The CLI `!convert_model` will convert a `.safetensors` or `.ckpt`
+models file into `diffusers` and install it.This will enable the model
+to load and run faster without loss of image quality.
+
+The usage is identical to `!import_model`. You may point the command
+to either a downloaded model file on disk, or to a (non-password
+protected) URL:
+
+```bash
+invoke> !convert_model C:/Users/fred/Downloads/martians.safetensors
+```
+
+After a successful conversion, the CLI will offer you the option of
+deleting the original `.ckpt` or `.safetensors` file.
+
+### Optimizing a previously-installed model
+
+Lastly, if you have previously installed a `.ckpt` or `.safetensors`
+file and wish to convert it into a `diffusers` model, you can do this
+without re-downloading and converting the original file using the
+`!optimize_model` command. Simply pass the short name of an existing
+installed model:
+
+```bash
+invoke> !optimize_model martians-v1.0
+```
+
+The model will be converted into `diffusers` format and replace the
+previously installed version. You will again be offered the
+opportunity to delete the original `.ckpt` or `.safetensors` file.
+
+Alternatively you can use the WebUI's model manager to handle diffusers
+optimization. Select the legacy model you wish to convert, and then
+look for a button labeled "Convert to Diffusers" in the upper right of
+the window.
+
+### Related CLI Commands
+
+There are a whole series of additional model management commands in
+the CLI that you can read about in [Command-Line
+Interface](../features/CLI.md). These include:
+
+* `!models` - List all installed models
+* `!switch <model name>` - Switch to the indicated model
+* `!edit_model <model name>` - Edit the indicated model to change its name, description or other properties
+* `!del_model <model name>` - Delete the indicated model
+
+### Manually editing `configs/models.yaml`
+
+If you are comfortable with a text editor then you may simply edit `models.yaml`
+directly.
+
+You will need to download the desired `.ckpt/.safetensors` file and
+place it somewhere on your machine's filesystem. Alternatively, for a
+`diffusers` model, record the repo_id or download the whole model
+directory. Then using a **text** editor (e.g. the Windows Notepad
+application), open the file `configs/models.yaml`, and add a new
+stanza that follows this model:
+
+#### A legacy model
+
+A legacy `.ckpt` or `.safetensors` entry will look like this:
+
+```yaml
+arabian-nights-1.0:
+  description: A great fine-tune in Arabian Nights style
+  weights: ./path/to/arabian-nights-1.0.ckpt
+  config: ./configs/stable-diffusion/v1-inference.yaml
+  format: ckpt
+  width: 512
+  height: 512
+  default: false
+```
+
+Note that `format` is `ckpt` for both `.ckpt` and `.safetensors` files.
+
+#### A diffusers model
+
+A stanza for a `diffusers` model will look like this for a HuggingFace
+model with a repository ID:
+
+```yaml
+arabian-nights-1.1:
+  description: An even better fine-tune of the Arabian Nights
+  repo_id: captahab/arabian-nights-1.1
+  format: diffusers
+  default: true
+```
+
+And for a downloaded directory:
+
+```yaml
+arabian-nights-1.1:
+  description: An even better fine-tune of the Arabian Nights
+  path: /path/to/captahab-arabian-nights-1.1
+  format: diffusers
+  default: true
+```
+
+There is additional syntax for indicating an external VAE to use with
+this model. See `INITIAL_MODELS.yaml` and `models.yaml` for examples.
+
+After you save the modified `models.yaml` file relaunch
+`invokeai`. The new model will now be available for your use.
+