Fix bug in openpose whole body

Currently translated at 99.5% (1091 of 1096 strings)

Co-authored-by: Васянатор <ilabulanov339@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ru/
Translation: InvokeAI/Web UI

.github/actions/install-frontend-deps/action.yml

@@ -0,0 +1,33 @@
+name: install frontend dependencies
+description: Installs frontend dependencies with pnpm, with caching
+runs:
+  using: 'composite'
+  steps:
+    - name: setup node 18
+      uses: actions/setup-node@v4
+      with:
+        node-version: '18'
+
+    - name: setup pnpm
+      uses: pnpm/action-setup@v2
+      with:
+        version: 8
+        run_install: false
+
+    - name: get pnpm store directory
+      shell: bash
+      run: |
+        echo "STORE_PATH=$(pnpm store path --silent)" >> $GITHUB_ENV
+
+    - name: setup cache
+      uses: actions/cache@v4
+      with:
+        path: ${{ env.STORE_PATH }}
+        key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/pnpm-lock.yaml') }}
+        restore-keys: |
+          ${{ runner.os }}-pnpm-store-
+
+    - name: install frontend dependencies
+      run: pnpm install --prefer-frozen-lockfile
+      shell: bash
+      working-directory: invokeai/frontend/web

.github/pr_labels.yml

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

.github/workflows/build-container.yml

@@ -11,7 +11,7 @@ on:
       - 'docker/docker-entrypoint.sh'
       - 'workflows/build-container.yml'
     tags:
-      - 'v*'
+      - 'v*.*.*'
   workflow_dispatch:
 
 permissions:

.github/workflows/build-installer.yml

@@ -0,0 +1,45 @@
+# Builds and uploads the installer and python build artifacts.
+
+name: build installer
+
+on:
+  workflow_dispatch:
+  workflow_call:
+
+jobs:
+  build-installer:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <2 min
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: setup python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install pypa/build
+        run: pip install --upgrade build
+
+      - name: setup frontend
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: create installer
+        id: create_installer
+        run: ./create_installer.sh
+        working-directory: installer
+
+      - name: upload python distribution artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: ${{ steps.create_installer.outputs.DIST_PATH }}
+
+      - name: upload installer artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ steps.create_installer.outputs.INSTALLER_FILENAME }}
+          path: ${{ steps.create_installer.outputs.INSTALLER_PATH }}

.github/workflows/frontend-checks.yml

@@ -0,0 +1,80 @@
+# Runs frontend code quality checks.
+#
+# Checks for changes to frontend files before running the checks.
+# If always_run is true, always runs the checks.
+
+name: 'frontend checks'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+
+defaults:
+  run:
+    working-directory: invokeai/frontend/web
+
+jobs:
+  frontend-checks:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10 # expected run time: <2 min
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: check for changed frontend files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            frontend:
+              - 'invokeai/frontend/web/**'
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: tsc
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:tsc'
+        shell: bash
+
+      - name: dpdm
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:dpdm'
+        shell: bash
+
+      - name: eslint
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:eslint'
+        shell: bash
+
+      - name: prettier
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:prettier'
+        shell: bash
+
+      - name: knip
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm lint:knip'
+        shell: bash

.github/workflows/frontend-tests.yml

@@ -0,0 +1,60 @@
+# Runs frontend tests.
+#
+# Checks for changes to frontend files before running the tests.
+# If always_run is true, always runs the tests.
+
+name: 'frontend tests'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+
+defaults:
+  run:
+    working-directory: invokeai/frontend/web
+
+jobs:
+  frontend-tests:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10 # expected run time: <2 min
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: check for changed frontend files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            frontend:
+              - 'invokeai/frontend/web/**'
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        uses: ./.github/actions/install-frontend-deps
+
+      - name: vitest
+        if: ${{ steps.changed-files.outputs.frontend_any_changed == 'true' || inputs.always_run == true }}
+        run: 'pnpm test:no-watch'
+        shell: bash

.github/workflows/label-pr.yml

@@ -1,6 +1,6 @@
-name: "Pull Request Labeler"
+name: 'label PRs'
 on:
-- pull_request_target
+  - pull_request_target
 
 jobs:
   labeler:
@@ -9,8 +9,10 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout
+      - name: checkout
         uses: actions/checkout@v4
-      - uses: actions/labeler@v5
+
+      - name: label PRs
+        uses: actions/labeler@v5
         with:
-          configuration-path: .github/pr_labels.yml
+          configuration-path: .github/pr_labels.yml

.github/workflows/lint-frontend.yml

@@ -1,43 +0,0 @@
-name: Lint frontend
-
-on:
-  pull_request:
-    types:
-      - 'ready_for_review'
-      - 'opened'
-      - 'synchronize'
-  push:
-    branches:
-      - 'main'
-  merge_group:
-  workflow_dispatch:
-
-defaults:
-  run:
-    working-directory: invokeai/frontend/web
-
-jobs:
-  lint-frontend:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-22.04
-    steps:
-      - name: Setup Node 18
-        uses: actions/setup-node@v4
-        with:
-          node-version: '18'
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v2
-        with:
-          version: '8.12.1'
-      - name: Install dependencies
-        run: 'pnpm install --prefer-frozen-lockfile'
-      - name: Typescript
-        run: 'pnpm run lint:tsc'
-      - name: Madge
-        run: 'pnpm run lint:madge'
-      - name: ESLint
-        run: 'pnpm run lint:eslint'
-      - name: Prettier
-        run: 'pnpm run lint:prettier'

.github/workflows/mkdocs-material.yml

@@ -1,51 +1,49 @@
-name: mkdocs-material
+# This is a mostly a copy-paste from https://github.com/squidfunk/mkdocs-material/blob/master/docs/publishing-your-site.md
+
+name: mkdocs
+
 on:
   push:
     branches:
-      - 'refs/heads/main'
+      - main
+  workflow_dispatch:
 
 permissions:
-    contents: write
+  contents: write
 
 jobs:
-  mkdocs-material:
+  deploy:
     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
-        with:
-          fetch-depth: 0
+      - name: checkout
+        uses: actions/checkout@v4
 
       - name: setup python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         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 ".[docs]"
+      - name: set cache id
+        run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
 
-      - name: confirm buildability
-        run: |
-          python -m \
-            mkdocs build \
-            --clean \
-            --verbose
+      - name: use cache
+        uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
 
-      - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/main' }}
-        run: |
-          python -m \
-            mkdocs gh-deploy \
-            --clean \
-            --force
+      - name: install dependencies
+        run: python -m pip install ".[docs]"
+
+      - name: build & deploy
+        run: mkdocs gh-deploy --force

.github/workflows/pypi-release.yml

@@ -1,67 +0,0 @@
-name: PyPI Release
-
-on:
-  workflow_dispatch:
-    inputs:
-      publish_package:
-        description: 'Publish build on PyPi? [true/false]'
-        required: true
-        default: 'false'
-
-jobs:
-  build-and-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
-        uses: actions/checkout@v4
-
-      - name: Setup Node 18
-        uses: actions/setup-node@v4
-        with:
-          node-version: '18'
-
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v2
-        with:
-          version: '8.12.1'
-
-      - name: Install frontend dependencies
-        run: pnpm install --prefer-frozen-lockfile
-        working-directory: invokeai/frontend/web
-
-      - name: Build frontend
-        run: pnpm run build
-        working-directory: invokeai/frontend/web
-
-      - name: Install python dependencies
-        run: pip install --upgrade build twine
-
-      - name: Build python package
-        run: python3 -m build
-
-      - name: Upload build as workflow artifact
-        uses: actions/upload-artifact@v4
-        with:
-          name: dist
-          path: dist
-
-      - name: Check distribution
-        run: twine check dist/*
-
-      - name: Check PyPI versions
-        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
-        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: Publish build on PyPi
-        if: env.PACKAGE_EXISTS == 'False' && env.TWINE_PASSWORD != '' && github.event.inputs.publish_package == 'true'
-        run: twine upload dist/*

.github/workflows/python-checks.yml

@@ -0,0 +1,76 @@
+# Runs python code quality checks.
+#
+# Checks for changes to python files before running the checks.
+# If always_run is true, always runs the checks.
+#
+# TODO: Add mypy or pyright to the checks.
+
+name: 'python checks'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the checks'
+        required: true
+        type: boolean
+        default: true
+
+jobs:
+  python-checks:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check for changed python files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            python:
+              - 'pyproject.toml'
+              - 'invokeai/**'
+              - '!invokeai/frontend/web/**'
+              - 'tests/**'
+
+      - name: setup python
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install ruff
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: pip install ruff
+        shell: bash
+
+      - name: ruff check
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: ruff check --output-format=github .
+        shell: bash
+
+      - name: ruff format
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: ruff format --check .
+        shell: bash

.github/workflows/python-tests.yml

@@ -0,0 +1,106 @@
+# Runs python tests on a matrix of python versions and platforms.
+#
+# Checks for changes to python files before running the tests.
+# If always_run is true, always runs the tests.
+
+name: 'python tests'
+
+on:
+  push:
+    branches:
+      - 'main'
+  pull_request:
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
+  merge_group:
+  workflow_dispatch:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+  workflow_call:
+    inputs:
+      always_run:
+        description: 'Always run the tests'
+        required: true
+        type: boolean
+        default: true
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  matrix:
+    strategy:
+      matrix:
+        python-version:
+          - '3.10'
+          - '3.11'
+        platform:
+          - linux-cuda-11_7
+          - linux-rocm-5_2
+          - linux-cpu
+          - macos-default
+          - windows-cpu
+        include:
+          - platform: linux-cuda-11_7
+            os: ubuntu-22.04
+            github-env: $GITHUB_ENV
+          - platform: linux-rocm-5_2
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
+            github-env: $GITHUB_ENV
+          - platform: linux-cpu
+            os: ubuntu-22.04
+            extra-index-url: 'https://download.pytorch.org/whl/cpu'
+            github-env: $GITHUB_ENV
+          - platform: macos-default
+            os: macOS-12
+            github-env: $GITHUB_ENV
+          - platform: windows-cpu
+            os: windows-2022
+            github-env: $env:GITHUB_ENV
+    name: 'py${{ matrix.python-version }}: ${{ matrix.platform }}'
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15 # expected run time: 2-6 min, depending on platform
+    env:
+      PIP_USE_PEP517: '1'
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check for changed python files
+        if: ${{ inputs.always_run != true }}
+        id: changed-files
+        uses: tj-actions/changed-files@v42
+        with:
+          files_yaml: |
+            python:
+              - 'pyproject.toml'
+              - 'invokeai/**'
+              - '!invokeai/frontend/web/**'
+              - 'tests/**'
+
+      - name: setup python
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+          cache-dependency-path: pyproject.toml
+
+      - name: install dependencies
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        env:
+          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
+        run: >
+          pip3 install --editable=".[test]"
+
+      - name: run pytest
+        if: ${{ steps.changed-files.outputs.python_any_changed == 'true' || inputs.always_run == true }}
+        run: pytest

.github/workflows/release.yml

@@ -0,0 +1,108 @@
+# Main release workflow. Triggered on tag push or manual trigger.
+#
+# - Runs all code checks and tests
+# - Verifies the app version matches the tag version.
+# - Builds the installer and build, uploading them as artifacts.
+# - Publishes to TestPyPI and PyPI. Both are conditional on the previous steps passing and require a manual approval.
+#
+# See docs/RELEASE.md for more information on the release process.
+
+name: release
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  check-version:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: check python version
+        uses: samuelcolvin/check-python-version@v4
+        id: check-python-version
+        with:
+          version_file_path: invokeai/version/invokeai_version.py
+
+  frontend-checks:
+    uses: ./.github/workflows/frontend-checks.yml
+    with:
+      always_run: true
+
+  frontend-tests:
+    uses: ./.github/workflows/frontend-tests.yml
+    with:
+      always_run: true
+
+  python-checks:
+    uses: ./.github/workflows/python-checks.yml
+    with:
+      always_run: true
+
+  python-tests:
+    uses: ./.github/workflows/python-tests.yml
+    with:
+      always_run: true
+
+  build:
+    uses: ./.github/workflows/build-installer.yml
+
+  publish-testpypi:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    needs:
+      [
+        check-version,
+        frontend-checks,
+        frontend-tests,
+        python-checks,
+        python-tests,
+        build,
+      ]
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/invokeai
+    permissions:
+      id-token: write
+    steps:
+      - name: download distribution from build job
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: publish distribution to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  publish-pypi:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5 # expected run time: <1 min
+    needs:
+      [
+        check-version,
+        frontend-checks,
+        frontend-tests,
+        python-checks,
+        python-tests,
+        build,
+      ]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/invokeai
+    permissions:
+      id-token: write
+    steps:
+      - name: download distribution from build job
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: publish distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/style-checks.yml

@@ -1,24 +0,0 @@
-name: style checks
-
-on:
-  pull_request:
-  push:
-    branches: main
-
-jobs:
-  ruff:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-
-      - name: Install dependencies with pip
-        run: |
-          pip install ruff
-
-      - run: ruff check --output-format=github .
-      - run: ruff format --check .

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

@@ -1,129 +0,0 @@
-name: Test invoke.py pip
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    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_7
-          - linux-rocm-5_2
-          - linux-cpu
-          - macos-default
-          - windows-cpu
-        include:
-          - 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
-    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: Check for changed python files
-        id: changed-files
-        uses: tj-actions/changed-files@v41
-        with:
-          files_yaml: |
-            python:
-              - 'pyproject.toml'
-              - 'invokeai/**'
-              - '!invokeai/frontend/web/**'
-              - 'tests/**'
-
-      - name: set test prompt to main branch validation
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
-
-      - name: setup python
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: pip
-          cache-dependency-path: pyproject.toml
-
-      - name: install invokeai
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        env:
-          PIP_EXTRA_INDEX_URL: ${{ matrix.extra-index-url }}
-        run: >
-          pip3 install
-          --editable=".[test]"
-
-      - name: run pytest
-        if: steps.changed-files.outputs.python_any_changed == 'true'
-        id: run-pytest
-        run: pytest
-
-      # - name: run invokeai-configure
-      #   env:
-      #     HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-      #   run: >
-      #     invokeai-configure
-      #     --yes
-      #     --default_only
-      #     --full-precision
-      #   # can't use fp16 weights without a GPU
-
-      # - name: run invokeai
-      #   id: run-invokeai
-      #   env:
-      #     # Set offline mode to make sure configure preloaded successfully.
-      #     HF_HUB_OFFLINE: 1
-      #     HF_DATASETS_OFFLINE: 1
-      #     TRANSFORMERS_OFFLINE: 1
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   run: >
-      #     invokeai
-      #     --no-patchmatch
-      #     --no-nsfw_checker
-      #     --precision=float32
-      #     --always_use_cpu
-      #     --use_memory_db
-      #     --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
-      #     --from_file ${{ env.TEST_PROMPTS }}
-
-      # - name: Archive results
-      #   env:
-      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
-      #   uses: actions/upload-artifact@v3
-      #   with:
-      #     name: results
-      #     path: ${{ env.INVOKEAI_OUTDIR }}

.prettierrc.yaml

@@ -7,7 +7,7 @@ embeddedLanguageFormatting: auto
 overrides:
   - files: '*.md'
     options:
-      proseWrap: always
+      proseWrap: preserve
       printWidth: 80
       parser: markdown
       cursorOffset: -1

Makefile

@@ -6,33 +6,50 @@ default: help
 help:
 	@echo Developer commands:
 	@echo
-	@echo "ruff           Run ruff, fixing any safely-fixable errors and formatting"
-	@echo "ruff-unsafe    Run ruff, fixing all fixable errors and formatting"
-	@echo "mypy           Run mypy using the config in pyproject.toml to identify type mismatches and other coding errors"
-	@echo "mypy-all       Run mypy ignoring the config in pyproject.tom but still ignoring missing imports"
-	@echo "frontend-build Build the frontend in order to run on localhost:9090"
-	@echo "frontend-dev   Run the frontend in developer mode on localhost:5173"
-	@echo "installer-zip  Build the installer .zip file for the current version"
-	@echo "tag-release    Tag the GitHub repository with the current version (use at release time only!)"
+	@echo "ruff                     Run ruff, fixing any safely-fixable errors and formatting"
+	@echo "ruff-unsafe              Run ruff, fixing all fixable errors and formatting"
+	@echo "mypy                     Run mypy using the config in pyproject.toml to identify type mismatches and other coding errors"
+	@echo "mypy-all                 Run mypy ignoring the config in pyproject.tom but still ignoring missing imports"
+	@echo "test                     Run the unit tests."
+	@echo "update-config-docstring  Update the app's config docstring so mkdocs can autogenerate it correctly."
+	@echo "frontend-install         Install the pnpm modules needed for the front end"
+	@echo "frontend-build           Build the frontend in order to run on localhost:9090"
+	@echo "frontend-dev             Run the frontend in developer mode on localhost:5173"
+	@echo "frontend-typegen         Generate types for the frontend from the OpenAPI schema"
+	@echo "installer-zip            Build the installer .zip file for the current version"
+	@echo "tag-release              Tag the GitHub repository with the current version (use at release time only!)"
 
 # Runs ruff, fixing any safely-fixable errors and formatting
 ruff:
-		ruff check . --fix
-		ruff format .
+	ruff check . --fix
+	ruff format .
 
 # Runs ruff, fixing all errors it can fix and formatting
 ruff-unsafe:
-		ruff check . --fix --unsafe-fixes
-		ruff format .
+	ruff check . --fix --unsafe-fixes
+	ruff format .
 
 # Runs mypy, using the config in pyproject.toml
 mypy:
-		mypy scripts/invokeai-web.py
+	mypy scripts/invokeai-web.py
 
 # Runs mypy, ignoring the config in pyproject.toml but still ignoring missing (untyped) imports
 # (many files are ignored by the config, so this is useful for checking all files)
 mypy-all:
-		mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+	mypy scripts/invokeai-web.py --config-file= --ignore-missing-imports
+
+# Run the unit tests
+test:
+	pytest ./tests
+
+# Update config docstring
+update-config-docstring:
+	python scripts/update_config_docstring.py
+
+# Install the pnpm modules needed for the front end
+frontend-install:
+	rm -rf invokeai/frontend/web/node_modules
+	cd invokeai/frontend/web && pnpm install
 
 # Build the frontend
 frontend-build:
@@ -42,6 +59,9 @@ frontend-build:
 frontend-dev:
 	cd invokeai/frontend/web && pnpm dev
 
+frontend-typegen:
+	cd invokeai/frontend/web && python ../../../scripts/generate_openapi_schema.py | pnpm typegen
+
 # Installer zip file
 installer-zip:
 	cd installer && ./create_installer.sh

docs/RELEASE.md

@@ -0,0 +1,142 @@
+# Release Process
+
+The app is published in twice, in different build formats.
+
+- A [PyPI] distribution. This includes both a source distribution and built distribution (a wheel). Users install with `pip install invokeai`. The updater uses this build.
+- An installer on the [InvokeAI Releases Page]. This is a zip file with install scripts and a wheel. This is only used for new installs.
+
+## General Prep
+
+Make a developer call-out for PRs to merge. Merge and test things out.
+
+While the release workflow does not include end-to-end tests, it does pause before publishing so you can download and test the final build.
+
+## Release Workflow
+
+The `release.yml` workflow runs a number of jobs to handle code checks, tests, build and publish on PyPI.
+
+It is triggered on **tag push**, when the tag matches `v*`. It doesn't matter if you've prepped a release branch like `release/v3.5.0` or are releasing from `main` - it works the same.
+
+> Because commits are reference-counted, it is safe to create a release branch, tag it, let the workflow run, then delete the branch. So long as the tag exists, that commit will exist.
+
+### Triggering the Workflow
+
+Run `make tag-release` to tag the current commit and kick off the workflow.
+
+The release may also be dispatched [manually].
+
+### Workflow Jobs and Process
+
+The workflow consists of a number of concurrently-run jobs, and two final publish jobs.
+
+The publish jobs require manual approval and are only run if the other jobs succeed.
+
+#### `check-version` Job
+
+This job checks that the git ref matches the app version. It matches the ref against the `__version__` variable in `invokeai/version/invokeai_version.py`.
+
+When the workflow is triggered by tag push, the ref is the tag. If the workflow is run manually, the ref is the target selected from the **Use workflow from** dropdown.
+
+This job uses [samuelcolvin/check-python-version].
+
+> Any valid [version specifier] works, so long as the tag matches the version. The release workflow works exactly the same for `RC`, `post`, `dev`, etc.
+
+#### Check and Test Jobs
+
+- **`python-tests`**: runs `pytest` on matrix of platforms
+- **`python-checks`**: runs `ruff` (format and lint)
+- **`frontend-tests`**: runs `vitest`
+- **`frontend-checks`**: runs `prettier` (format), `eslint` (lint), `dpdm` (circular refs), `tsc` (static type check) and `knip` (unused imports)
+
+> **TODO** We should add `mypy` or `pyright` to the **`check-python`** job.
+
+> **TODO** We should add an end-to-end test job that generates an image.
+
+#### `build-installer` Job
+
+This sets up both python and frontend dependencies and builds the python package. Internally, this runs `installer/create_installer.sh` and uploads two artifacts:
+
+- **`dist`**: the python distribution, to be published on PyPI
+- **`InvokeAI-installer-${VERSION}.zip`**: the installer to be included in the GitHub release
+
+#### Sanity Check & Smoke Test
+
+At this point, the release workflow pauses as the remaining publish jobs require approval.
+
+A maintainer should go to the **Summary** tab of the workflow, download the installer and test it. Ensure the app loads and generates.
+
+> The same wheel file is bundled in the installer and in the `dist` artifact, which is uploaded to PyPI. You should end up with the exactly the same installation of the `invokeai` package from any of these methods.
+
+#### PyPI Publish Jobs
+
+The publish jobs will run if any of the previous jobs fail.
+
+They use [GitHub environments], which are configured as [trusted publishers] on PyPI.
+
+Both jobs require a maintainer to approve them from the workflow's **Summary** tab.
+
+- Click the **Review deployments** button
+- Select the environment (either `testpypi` or `pypi`)
+- Click **Approve and deploy**
+
+> **If the version already exists on PyPI, the publish jobs will fail.** PyPI only allows a given version to be published once - you cannot change it. If version published on PyPI has a problem, you'll need to "fail forward" by bumping the app version and publishing a followup release.
+
+#### `publish-testpypi` Job
+
+Publishes the distribution on the [Test PyPI] index, using the `testpypi` GitHub environment.
+
+This job is not required for the production PyPI publish, but included just in case you want to test the PyPI release.
+
+If approved and successful, you could try out the test release like this:
+
+```sh
+# Create a new virtual environment
+python -m venv ~/.test-invokeai-dist --prompt test-invokeai-dist
+# Install the distribution from Test PyPI
+pip install --index-url https://test.pypi.org/simple/ invokeai
+# Run and test the app
+invokeai-web
+# Cleanup
+deactivate
+rm -rf ~/.test-invokeai-dist
+```
+
+#### `publish-pypi` Job
+
+Publishes the distribution on the production PyPI index, using the `pypi` GitHub environment.
+
+## Publish the GitHub Release with installer
+
+Once the release is published to PyPI, it's time to publish the GitHub release.
+
+1. [Draft a new release] on GitHub, choosing the tag that triggered the release.
+2. Write the release notes, describing important changes. The **Generate release notes** button automatically inserts the changelog and new contributors, and you can copy/paste the intro from previous releases.
+3. Upload the zip file created in **`build`** job into the Assets section of the release notes. You can also upload the zip into the body of the release notes, since it can be hard for users to find the Assets section.
+4. Check the **Set as a pre-release** and **Create a discussion for this release** checkboxes at the bottom of the release page.
+5. Publish the pre-release.
+6. Announce the pre-release in Discord.
+
+> **TODO** Workflows can create a GitHub release from a template and upload release assets. One popular action to handle this is [ncipollo/release-action]. A future enhancement to the release process could set this up.
+
+## Manual Build
+
+The `build installer` workflow can be dispatched manually. This is useful to test the installer for a given branch or tag.
+
+No checks are run, it just builds.
+
+## Manual Release
+
+The `release` workflow can be dispatched manually. You must dispatch the workflow from the right tag, else it will fail the version check.
+
+This functionality is available as a fallback in case something goes wonky. Typically, releases should be triggered via tag push as described above.
+
+[InvokeAI Releases Page]: https://github.com/invoke-ai/InvokeAI/releases
+[PyPI]: https://pypi.org/
+[Draft a new release]: https://github.com/invoke-ai/InvokeAI/releases/new
+[Test PyPI]: https://test.pypi.org/
+[version specifier]: https://packaging.python.org/en/latest/specifications/version-specifiers/
+[ncipollo/release-action]: https://github.com/ncipollo/release-action
+[GitHub environments]: https://docs.github.com/en/actions/deployment/targeting-different-environments/using-environments-for-deployment
+[trusted publishers]: https://docs.pypi.org/trusted-publishers/
+[samuelcolvin/check-python-version]: https://github.com/samuelcolvin/check-python-version
+[manually]: #manual-release

docs/contributing/frontend/OVERVIEW.md

@@ -0,0 +1,133 @@
+# Invoke UI
+
+Invoke's UI is made possible by many contributors and open-source libraries. Thank you!
+
+## Dev environment
+
+### Setup
+
+1. Install [node] and [pnpm].
+1. Run `pnpm i` to install all packages.
+
+#### Run in dev mode
+
+1. From `invokeai/frontend/web/`, run `pnpm dev`.
+1. From repo root, run `python scripts/invokeai-web.py`.
+1. Point your browser to the dev server address, e.g. <http://localhost:5173/>
+
+### Package scripts
+
+- `dev`: run the frontend in dev mode, enabling hot reloading
+- `build`: run all checks (madge, eslint, prettier, tsc) and then build the frontend
+- `typegen`: generate types from the OpenAPI schema (see [Type generation])
+- `lint:dpdm`: check circular dependencies
+- `lint:eslint`: check code quality
+- `lint:prettier`: check code formatting
+- `lint:tsc`: check type issues
+- `lint:knip`: check for unused exports or objects (failures here are just suggestions, not hard fails)
+- `lint`: run all checks concurrently
+- `fix`: run `eslint` and `prettier`, fixing fixable issues
+
+### Type generation
+
+We use [openapi-typescript] to generate types from the app's OpenAPI schema.
+
+The generated types are committed to the repo in [schema.ts].
+
+```sh
+# from the repo root, start the server
+python scripts/invokeai-web.py
+# from invokeai/frontend/web/, run the script
+pnpm typegen
+```
+
+### Localization
+
+We use [i18next] for localization, but translation to languages other than English happens on our [Weblate] project.
+
+Only the English source strings should be changed on this repo.
+
+### VSCode
+
+#### Example debugger config
+
+```jsonc
+{
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "chrome",
+      "request": "launch",
+      "name": "Invoke UI",
+      "url": "http://localhost:5173",
+      "webRoot": "${workspaceFolder}/invokeai/frontend/web"
+    }
+  ]
+}
+```
+
+#### Remote dev
+
+We've noticed an intermittent timeout issue with the VSCode remote dev port forwarding.
+
+We suggest disabling the editor's port forwarding feature and doing it manually via SSH:
+
+```sh
+ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host
+```
+
+## Contributing Guidelines
+
+Thanks for your interest in contributing to the Invoke Web UI!
+
+Please follow these guidelines when contributing.
+
+### Check in before investing your time
+
+Please check in before you invest your time on anything besides a trivial fix, in case it conflicts with ongoing work or isn't aligned with the vision for the app.
+
+If a feature request or issue doesn't already exist for the thing you want to work on, please create one.
+
+Ping `@psychedelicious` on [discord] in the `#frontend-dev` channel or in the feature request / issue you want to work on - we're happy to chat.
+
+### Code conventions
+
+- This is a fairly complex app with a deep component tree. Please use memoization (`useCallback`, `useMemo`, `memo`) with enthusiasm.
+- If you need to add some global, ephemeral state, please use [nanostores] if possible.
+- Be careful with your redux selectors. If they need to be parameterized, consider creating them inside a `useMemo`.
+- Feel free to use `lodash` (via `lodash-es`) to make the intent of your code clear.
+- Please add comments describing the "why", not the "how" (unless it is really arcane).
+
+### Commit format
+
+Please use the [conventional commits] spec for the web UI, with a scope of "ui":
+
+- `chore(ui): bump deps`
+- `chore(ui): lint`
+- `feat(ui): add some cool new feature`
+- `fix(ui): fix some bug`
+
+### Submitting a PR
+
+- Ensure your branch is tidy. Use an interactive rebase to clean up the commit history and reword the commit messages if they are not descriptive.
+- Run `pnpm lint`. Some issues are auto-fixable with `pnpm fix`.
+- Fill out the PR form when creating the PR.
+  - It doesn't need to be super detailed, but a screenshot or video is nice if you changed something visually.
+  - If a section isn't relevant, delete it. There are no UI tests at this time.
+
+## Other docs
+
+- [Workflows - Design and Implementation]
+- [State Management]
+
+[node]: https://nodejs.org/en/download/
+[pnpm]: https://github.com/pnpm/pnpm
+[discord]: https://discord.gg/ZmtBAhwWhy
+[i18next]: https://github.com/i18next/react-i18next
+[Weblate]: https://hosted.weblate.org/engage/invokeai/
+[openapi-typescript]: https://github.com/drwpow/openapi-typescript
+[Type generation]: #type-generation
+[schema.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/services/api/schema.ts
+[conventional commits]: https://www.conventionalcommits.org/en/v1.0.0/
+[Workflows - Design and Implementation]: ./WORKFLOWS.md
+[State Management]: ./STATE_MGMT.md

docs/contributing/frontend/WORKFLOWS.md

@@ -1,40 +1,5 @@
 # Workflows - Design and Implementation
 
-<!-- @import "[TOC]" {cmd="toc" depthFrom=1 depthTo=6 orderedList=false} -->
-
-<!-- code_chunk_output -->
-
-- [Workflows - Design and Implementation](#workflows---design-and-implementation)
-  - [Design](#design)
-    - [Linear UI](#linear-ui)
-    - [Workflow Editor](#workflow-editor)
-      - [Workflows](#workflows)
-        - [Workflow -> reactflow state -> InvokeAI graph](#workflow---reactflow-state---invokeai-graph)
-        - [Nodes vs Invocations](#nodes-vs-invocations)
-        - [Workflow Linear View](#workflow-linear-view)
-      - [OpenAPI Schema](#openapi-schema)
-        - [Field Instances and Templates](#field-instances-and-templates)
-        - [Stateful vs Stateless Fields](#stateful-vs-stateless-fields)
-        - [Collection and Polymorphic Fields](#collection-and-polymorphic-fields)
-  - [Implementation](#implementation)
-    - [zod Schemas and Types](#zod-schemas-and-types)
-    - [OpenAPI Schema Parsing](#openapi-schema-parsing)
-      - [Parsing Field Types](#parsing-field-types)
-        - [Primitive Types](#primitive-types)
-        - [Complex Types](#complex-types)
-        - [Collection Types](#collection-types)
-        - [Collection or Scalar Types](#collection-or-scalar-types)
-        - [Optional Fields](#optional-fields)
-      - [Building Field Input Templates](#building-field-input-templates)
-      - [Building Field Output Templates](#building-field-output-templates)
-    - [Managing reactflow State](#managing-reactflow-state)
-      - [Building Nodes and Edges](#building-nodes-and-edges)
-      - [Building a Workflow](#building-a-workflow)
-      - [Loading a Workflow](#loading-a-workflow)
-    - [Workflow Migrations](#workflow-migrations)
-
-<!-- /code_chunk_output -->
-
 > This document describes, at a high level, the design and implementation of workflows in the InvokeAI frontend. There are a substantial number of implementation details not included, but which are hopefully clear from the code.
 
 InvokeAI's backend uses graphs, composed of **nodes** and **edges**, to process data and generate images.
@@ -152,13 +117,13 @@ Stateless fields do not store their value in the node, so their field instances
 
 "Custom" fields will always be treated as stateless fields.
 
-##### Collection and Polymorphic Fields
+##### Collection and Scalar Fields
 
-Field types have a name and two flags which may identify it as a **collection** or **polymorphic** field.
+Field types have a name and two flags which may identify it as a **collection** or **collection or scalar** field.
 
-If a field is annotated in python as a list, its field type is parsed and flagged as a collection type (e.g. `list[int]`).
+If a field is annotated in python as a list, its field type is parsed and flagged as a **collection** type (e.g. `list[int]`).
 
-If it is annotated as a union of a type and list, the type will be flagged as a polymorphic type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
+If it is annotated as a union of a type and list, the type will be flagged as a **collection or scalar** type (e.g. `Union[int, list[int]]`). Fields may not be unions of different types (e.g. `Union[int, list[str]]` and `Union[int, str]` are not allowed).
 
 ## Implementation
 
@@ -338,13 +303,13 @@ Migration logic is in [migrations.ts].
 [reactflow]: https://github.com/xyflow/xyflow 'reactflow'
 [reactflow-concepts]: https://reactflow.dev/learn/concepts/terms-and-definitions
 [reactflow-events]: https://reactflow.dev/api-reference/react-flow#event-handlers
-[buildWorkflow.ts]: ../src/features/nodes/util/workflow/buildWorkflow.ts
-[nodesSlice.ts]: ../src/features/nodes/store/nodesSlice.ts
-[buildLinearTextToImageGraph.ts]: ../src/features/nodes/util/graph/buildLinearTextToImageGraph.ts
-[buildNodesGraph.ts]: ../src/features/nodes/util/graph/buildNodesGraph.ts
-[buildInvocationNode.ts]: ../src/features/nodes/util/node/buildInvocationNode.ts
-[validateWorkflow.ts]: ../src/features/nodes/util/workflow/validateWorkflow.ts
-[migrations.ts]: ../src/features/nodes/util/workflow/migrations.ts
-[parseSchema.ts]: ../src/features/nodes/util/schema/parseSchema.ts
-[buildFieldInputTemplate.ts]: ../src/features/nodes/util/schema/buildFieldInputTemplate.ts
-[buildFieldOutputTemplate.ts]: ../src/features/nodes/util/schema/buildFieldOutputTemplate.ts
+[buildWorkflow.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/buildWorkflow.ts
+[nodesSlice.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/store/nodesSlice.ts
+[buildLinearTextToImageGraph.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/graph/buildLinearTextToImageGraph.ts
+[buildNodesGraph.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/graph/buildNodesGraph.ts
+[buildInvocationNode.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/node/buildInvocationNode.ts
+[validateWorkflow.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/validateWorkflow.ts
+[migrations.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/workflow/migrations.ts
+[parseSchema.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/parseSchema.ts
+[buildFieldInputTemplate.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/buildFieldInputTemplate.ts
+[buildFieldOutputTemplate.ts]: https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/frontend/web/src/features/nodes/util/schema/buildFieldOutputTemplate.ts

docs/features/CONFIGURATION.md

@@ -6,259 +6,162 @@ title: Configuration
 
 ## Intro
 
-InvokeAI has numerous runtime settings which can be used to adjust
-many aspects of its operations, including the location of files and
-directories, memory usage, and performance. These settings can be
-viewed and customized in several ways:
+Runtime settings, including the location of files and
+directories, memory usage, and performance, are managed via the
+`invokeai.yaml` config file or environment variables. A subset
+of settings may be set via commandline arguments.
 
-1. By editing settings in the `invokeai.yaml` file.
-2. By setting environment variables.
-3. On the command-line, when InvokeAI is launched.
+Settings sources are used in this order:
 
-In addition, the most commonly changed settings are accessible
+- CLI args
+- Environment variables
+- `invokeai.yaml` settings
+- Fallback: defaults
+
+The most commonly changed settings are also accessible
 graphically via the `invokeai-configure` script.
 
-### How the Configuration System Works
+### InvokeAI Root Directory
 
-When InvokeAI is launched, the very first thing it needs to do is to
-find its "root" directory, which contains its configuration files,
-installed models, its database of images, and the folder(s) of
-generated images themselves. In this document, the root directory will
-be referred to as ROOT.
+On startup, InvokeAI searches for its "root" directory. This is the directory
+that contains models, images, the database, and so on. It also contains
+a configuration file called `invokeai.yaml`.
 
-#### Finding the Root Directory
+InvokeAI searches for the root directory in this order:
 
-To find its root directory, InvokeAI uses the following recipe:
+1. The `--root <path>` CLI arg.
+2. The environment variable INVOKEAI_ROOT.
+3. The directory containing the currently active virtual environment.
+4. Fallback: a directory in the current user's home directory named `invokeai`.
 
-1. It first looks for the argument `--root <path>` on the command line
-it was launched from, and uses the indicated path if present.
+### InvokeAI Configuration File
 
-2. Next it looks for the environment variable INVOKEAI_ROOT, and uses
-the directory path found there if present.
+Inside the root directory, we read settings from the `invokeai.yaml` file.
 
-3. If neither of these are present, then InvokeAI looks for the
-folder containing the `.venv` Python virtual environment directory for
-the currently active environment. This directory is checked for files
-expected inside the InvokeAI root before it is used.
+It has two sections - one for internal use and one for user settings:
 
-4. Finally, InvokeAI looks for a directory in the current user's home
-directory named `invokeai`.
+```yaml
+# Internal metadata - do not edit:
+meta:
+  schema_version: 4
 
-#### Reading the InvokeAI Configuration File
-
-Once the root directory has been located, InvokeAI looks for a file
-named `ROOT/invokeai.yaml`, and if present reads configuration values
-from it. The top of this file looks like this:
-
-```
-InvokeAI:
-  Web Server:
-    host: localhost
-    port: 9090
-    allow_origins: []
-    allow_credentials: true
-    allow_methods:
-    - '*'
-    allow_headers:
-    - '*'
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    patchmatch: true
-    restore: true
-...
+# Put user settings here:
+host: 0.0.0.0 # serve the app on your local network
+models_dir: D:\invokeai\models # store models on an external drive
+precision: float16 # always use fp16 precision
 ```
 
-This lines in this file are used to establish default values for
-Invoke's settings. In the above fragment, the Web Server's listening
-port is set to 9090 by the `port` setting.
+The settings in this file will override the defaults. You only need
+to change this file if the default for a particular setting doesn't
+work for you.
 
-You can edit this file with a text editor such as "Notepad" (do not
-use Word or any other word processor). When editing, be careful to
-maintain the indentation, and do not add extraneous text, as syntax
-errors will prevent InvokeAI from launching. A basic guide to the
-format of YAML files can be found
-[here](https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/).
+Some settings, like [Model Marketplace API Keys], require the YAML
+to be formatted correctly. Here is a [basic guide to YAML files].
 
 You can fix a broken `invokeai.yaml` by deleting it and running the
 configuration script again -- option [6] in the launcher, "Re-run the
 configure script".
 
-#### Reading Environment Variables
+### Environment Variables
 
-Next InvokeAI looks for defined environment variables in the format
-`INVOKEAI_<setting_name>`, for example `INVOKEAI_port`. Environment
-variable values take precedence over configuration file variables. On
-a Macintosh system, for example, you could change the port that the
-web server listens on by setting the environment variable this way:
+All settings may be set via environment variables by prefixing `INVOKEAI_`
+to the variable name. For example, `INVOKEAI_HOST` would set the `host`
+setting.
 
-```
-export INVOKEAI_port=8000
-invokeai-web
+For non-primitive values, pass a JSON-encoded string:
+
+```sh
+export INVOKEAI_REMOTE_API_TOKENS='[{"url_regex":"modelmarketplace", "token": "12345"}]'
 ```
 
-Please check out these
-[Macintosh](https://phoenixnap.com/kb/set-environment-variable-mac)
-and
-[Windows](https://phoenixnap.com/kb/windows-set-environment-variable)
-guides for setting temporary and permanent environment variables.
+We suggest using `invokeai.yaml`, as it is more user-friendly.
 
-#### Reading the Command Line
+### CLI Args
 
-Lastly, InvokeAI takes settings from the command line, which override
-everything else. The command-line settings have the same name as the
-corresponding configuration file settings, preceded by a `--`, for
-example `--port 8000`.
+A subset of settings may be specified using CLI args:
 
-If you are using the launcher (`invoke.sh` or `invoke.bat`) to launch
-InvokeAI, then just pass the command-line arguments to the launcher:
+- `--root`: specify the root directory
+- `--ignore_missing_core-models`: if set, do not check for models needed
+  to convert checkpoint/safetensor models to diffusers
 
-```
-invoke.bat --port 8000 --host 0.0.0.0
+### All Settings
+
+The config is managed by the `InvokeAIAppConfig` class. The below docs are autogenerated from the class.
+
+Following the table are additional explanations for certain settings.
+
+<!-- prettier-ignore-start -->
+::: invokeai.app.services.config.config_default.InvokeAIAppConfig
+    options:
+        heading_level: 4
+        members: false
+        show_docstring_description: false
+        group_by_category: true
+        show_category_heading: false
+<!-- prettier-ignore-end -->
+
+#### Model Marketplace API Keys
+
+Some model marketplaces require an API key to download models. You can provide a URL pattern and appropriate token in your `invokeai.yaml` file to provide that API key.
+
+The pattern can be any valid regex (you may need to surround the pattern with quotes):
+
+```yaml
+remote_api_tokens:
+  # Any URL containing `models.com` will automatically use `your_models_com_token`
+  - url_regex: models.com
+    token: your_models_com_token
+  # Any URL matching this contrived regex will use `some_other_token`
+  - url_regex: '^[a-z]{3}whatever.*\.com$'
+    token: some_other_token
 ```
 
-The arguments will be applied when you select the web server option
-(and the other options as well).
+The provided token will be added as a `Bearer` token to the network requests to download the model files. As far as we know, this works for all model marketplaces that require authorization.
 
-If, on the other hand, you prefer to launch InvokeAI directly from the
-command line, you would first activate the virtual environment (known
-as the "developer's console" in the launcher), and run `invokeai-web`:
+#### Model Hashing
 
-```
-> C:\Users\Fred\invokeai\.venv\scripts\activate
-(.venv) > invokeai-web --port 8000 --host 0.0.0.0
+Models are hashed during installation, providing a stable identifier for models across all platforms. The default algorithm is `blake3`, with a multi-threaded implementation.
+
+If your models are stored on a spinning hard drive, we suggest using `blake3_single`, the single-threaded implementation. The hashes are the same, but it's much faster on spinning disks.
+
+```yaml
+hashing_algorithm: blake3_single
 ```
 
-You can get a listing and brief instructions for each of the
-command-line options by giving the `--help` argument:
+Model hashing is a one-time operation, but it may take a couple minutes to hash a large model collection. You may opt out of model hashing entirely by setting the algorithm to `random`.
 
-```
-(.venv) > invokeai-web --help
-usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials] [--allow_methods [ALLOW_METHODS ...]]
-                [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan] [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
-                [--patchmatch | --no-patchmatch] [--restore | --no-restore]
-                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_loaded_models MAX_LOADED_MODELS] [--max_cache_size MAX_CACHE_SIZE]
-                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--gpu_mem_reserved GPU_MEM_RESERVED] [--precision {auto,float16,float32,autocast}]
-                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled] [--tiled_decode | --no-tiled_decode] [--root ROOT]
-                [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR] [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH]
-                [--models_dir MODELS_DIR] [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
-                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]] [--log_format {plain,color,syslog,legacy}]
-                [--log_level {debug,info,warning,error,critical}] [--version | --no-version]
+```yaml
+hashing_algorithm: random
 ```
 
-## The Configuration Settings
+Most common algorithms are supported, like `md5`, `sha256`, and `sha512`. These are typically much, much slower than `blake3`.
 
-The configuration settings are divided into several distinct
-groups in `invokeia.yaml`:
-
-### Web Server
-
-| Setting             | Default Value | Description                                                                                                                |
-|---------------------|---------------|----------------------------------------------------------------------------------------------------------------------------|
-| `host`              | `localhost`   | Name or IP address of the network interface that the web server will listen on                                             |
-| `port`              | `9090`        | Network port number that the web server will listen on                                                                     |
-| `allow_origins`     | `[]`          | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
-| `allow_credentials` | `true`        | Require credentials for a foreign host to access the InvokeAI API (don't change this)                                      |
-| `allow_methods`     | `*`           | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API                          |
-| `allow_headers`     | `*`           | List of HTTP headers that the web server will accept when accessing the API                                                |
-| `ssl_certfile`      | null          | Path to an SSL certificate file, used to enable HTTPS.                                                                     |
-| `ssl_keyfile`       | null          | Path to an SSL keyfile, if the key is not included in the certificate file.                                                |
-
-The documentation for InvokeAI's API can be accessed by browsing to the following URL: [http://localhost:9090/docs].
-
-### Features
-
-These configuration settings allow you to enable and disable various InvokeAI features:
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `esrgan`     | `true`      | Activate the ESRGAN upscaling options|
-| `internet_available` | `true`     | When a resource is not available locally, try to fetch it via the internet |
-| `log_tokenization` | `false`      | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
-| `patchmatch` | `true`     | Activate the "patchmatch" algorithm for improved inpainting |
-
-### Generation
-
-These options tune InvokeAI's memory and performance characteristics.
-
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `sequential_guidance` | `false`       | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss                                                                                                                                          |
-| `attention_type`      | `auto`        | Select the type of attention to use. One of `auto`,`normal`,`xformers`,`sliced`, or `torch-sdp`                                                                                                                                                                  |
-| `attention_slice_size` | `auto`       | When "sliced" attention is selected, set the slice size. One of `auto`, `balanced`, `max` or the integers 1-8|
-| `force_tiled_decode`  | `false`       | Force the VAE step to decode in tiles, reducing memory consumption at the cost of performance |
-
-### Device
-
-These options configure the generation execution device.
-
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `device`           | `auto`        | Preferred execution device. One of `auto`, `cpu`, `cuda`, `cuda:1`, `mps`. `auto` will choose the device depending on the hardware platform and the installed torch capabilities. |
-| `precision`           | `auto`        | Floating point precision. One of `auto`, `float16` or `float32`. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system |
-
-
-### Paths
+#### Path Settings
 
 These options set the paths of various directories and files used by
-InvokeAI. Relative paths are interpreted relative to INVOKEAI_ROOT, so
-if INVOKEAI_ROOT is `/home/fred/invokeai` and the path is
+InvokeAI. Relative paths are interpreted relative to the root directory, so
+if root is `/home/fred/invokeai` and the path is
 `autoimport/main`, then the corresponding directory will be located at
 `/home/fred/invokeai/autoimport/main`.
 
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `autoimport_dir` | `autoimport/main`     | At startup time, read and import any main model files found in this directory |
-| `lora_dir` | `autoimport/lora`     | At startup time, read and import any LoRA/LyCORIS models found in this directory |
-| `embedding_dir` | `autoimport/embedding`  | At startup time, read and import any textual inversion (embedding) models found in this directory |
-| `controlnet_dir` | `autoimport/controlnet`  | At startup time, read and import any ControlNet models found in this directory |
-| `conf_path` | `configs/models.yaml`  | Location of the `models.yaml` model configuration file |
-| `models_dir` | `models`  | Location of the directory containing models installed by InvokeAI's model manager |
-| `legacy_conf_dir` | `configs/stable-diffusion`  | Location of the directory containing the .yaml configuration files for legacy checkpoint models |
-| `db_dir` | `databases`  | Location of the directory containing InvokeAI's image, schema and session database |
-| `outdir` | `outputs`  | Location of the directory in which the gallery of generated and uploaded images will be stored |
-| `use_memory_db` | `false`  | Keep database information in memory rather than on disk; this will not preserve image gallery information across restarts |
-
-Note that the autoimport directories will be searched recursively,
+Note that the autoimport directory will be searched recursively,
 allowing you to organize the models into folders and subfolders in any
-way you wish. In addition, while we have split up autoimport
-directories by the type of model they contain, this isn't
-necessary. You can combine different model types in the same folder
-and InvokeAI will figure out what they are. So you can easily use just
-one autoimport directory by commenting out the unneeded paths:
+way you wish.
 
-```
-Paths:
-  autoimport_dir: autoimport
-#  lora_dir: null
-#  embedding_dir: null
-#  controlnet_dir: null
-```
-
-### Logging
-
-These settings control the information, warning, and debugging
-messages printed to the console log while InvokeAI is running:
-
-| Setting  | Default Value  |  Description |
-|----------|----------------|--------------|
-| `log_handlers` | `console` | This controls where log messages are sent, and can be a list of one or more destinations. Values include `console`, `file`, `syslog` and `http`. These are described in more detail below |
-| `log_format` | `color` | This controls the formatting of the log messages. Values are `plain`, `color`, `legacy` and `syslog` |
-| `log_level`  | `debug` | This filters messages according to the level of severity and can be one of `debug`, `info`, `warning`, `error` and `critical`. For example, setting to `warning` will display all messages at the warning level or higher, but won't display "debug" or "info" messages |
+#### Logging
 
 Several different log handler destinations are available, and multiple destinations are supported by providing a list:
 
-```
-  log_handlers:
-     - console
-     - syslog=localhost
-     - file=/var/log/invokeai.log
+```yaml
+log_handlers:
+  - console
+  - syslog=localhost
+  - file=/var/log/invokeai.log
 ```
 
-* `console` is the default. It prints log messages to the command-line window from which InvokeAI was launched.
+- `console` is the default. It prints log messages to the command-line window from which InvokeAI was launched.
 
-* `syslog` is only available on Linux and Macintosh systems. It uses
+- `syslog` is only available on Linux and Macintosh systems. It uses
   the operating system's "syslog" facility to write log file entries
   locally or to a remote logging machine. `syslog` offers a variety
   of configuration options:
@@ -271,7 +174,7 @@ Several different log handler destinations are available, and multiple destinati
                         - Log to LAN-connected server "fredserver" using the facility LOG_USER and datagram packets.
 ```
 
-* `http` can be used to log to a remote web server. The server must be
+- `http` can be used to log to a remote web server. The server must be
   properly configured to receive and act on log messages. The option
   accepts the URL to the web server, and a `method` argument
   indicating whether the message should be submitted using the GET or
@@ -283,7 +186,10 @@ Several different log handler destinations are available, and multiple destinati
 
 The `log_format` option provides several alternative formats:
 
-* `color`    - default format providing time, date and a message, using text colors to distinguish different log severities
-* `plain`    - same as above, but monochrome text only
-* `syslog`   - the log level and error message only, allowing the syslog system to attach the time and date
-* `legacy`   - a format similar to the one used by the legacy 2.3 InvokeAI releases.
+- `color` - default format providing time, date and a message, using text colors to distinguish different log severities
+- `plain` - same as above, but monochrome text only
+- `syslog` - the log level and error message only, allowing the syslog system to attach the time and date
+- `legacy` - a format similar to the one used by the legacy 2.3 InvokeAI releases.
+
+[basic guide to yaml files]: https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/
+[Model Marketplace API Keys]: #model-marketplace-api-keys

docs/features/DATABASE.md

@@ -0,0 +1,35 @@
+---
+title: Database
+---
+
+# Invoke's SQLite Database
+
+Invoke uses a SQLite database to store image, workflow, model, and execution data.
+
+We take great care to ensure your data is safe, by utilizing transactions and a database migration system.
+
+Even so, when testing an prerelease version of the app, we strongly suggest either backing up your database or using an in-memory database. This ensures any prelease hiccups or databases schema changes will not cause problems for your data.
+
+## Database Backup
+
+Backing up your database is very simple. Invoke's data is stored in an `$INVOKEAI_ROOT` directory - where your `invoke.sh`/`invoke.bat` and `invokeai.yaml` files live.
+
+To back up your database, copy the `invokeai.db` file from `$INVOKEAI_ROOT/databases/invokeai.db` to somewhere safe.
+
+If anything comes up during prelease testing, you can simply copy your backup back into `$INVOKEAI_ROOT/databases/`.
+
+## In-Memory Database
+
+SQLite can run on an in-memory database. Your existing database is untouched when this mode is enabled, but your existing data won't be accessible.
+
+This is very useful for testing, as there is no chance of a database change modifying your "physical" database.
+
+To run Invoke with a memory database, edit your `invokeai.yaml` file, and add `use_memory_db: true` to the `Paths:` stanza:
+
+```yaml
+InvokeAI:
+  Development:
+    use_memory_db: true
+```
+
+Delete this line (or set it to `false`) to use your main database.

docs/nodes/INVOCATION_API.md

@@ -0,0 +1,63 @@
+# Invocation API
+
+Each invocation's `invoke` method is provided a single arg - the Invocation
+Context.
+
+This object provides access to various methods, used to interact with the
+application. Loading and saving images, logging messages, etc.
+
+!!! warning ""
+
+    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
+
+```py
+class MyInvocation(BaseInvocation):
+  ...
+  def invoke(self, context: InvocationContext) -> ImageOutput:
+      image_pil = context.images.get_pil(image_name)
+      # Do something to the image
+      image_dto = context.images.save(image_pil)
+      # Log a message
+      context.logger.info(f"Did something cool, image saved!")
+      ...
+```
+
+The full API is documented below.
+
+## Invocation Mixins
+
+Two important mixins are provided to facilitate working with metadata and gallery boards.
+
+### `WithMetadata`
+
+Inherit from this class (in addition to `BaseInvocation`) to add a `metadata` input to your node. When you do this, you can access the metadata dict from `self.metadata` in the `invoke()` function.
+
+The dict will be populated via the node's input, and you can add any metadata you'd like to it. When you call `context.images.save()`, if the metadata dict has any data, it be automatically embedded in the image.
+
+### `WithBoard`
+
+Inherit from this class (in addition to `BaseInvocation`) to add a `board` input to your node. This renders as a drop-down to select a board. The user's selection will be accessible from `self.board` in the `invoke()` function.
+
+When you call `context.images.save()`, if a board was selected, the image will added to that board as it is saved.
+
+<!-- prettier-ignore-start -->
+::: invokeai.app.services.shared.invocation_context.InvocationContext
+    options:
+        members: false
+
+::: invokeai.app.services.shared.invocation_context.ImagesInterface
+
+::: invokeai.app.services.shared.invocation_context.TensorsInterface
+
+::: invokeai.app.services.shared.invocation_context.ConditioningInterface
+
+::: invokeai.app.services.shared.invocation_context.ModelsInterface
+
+::: invokeai.app.services.shared.invocation_context.LoggerInterface
+
+::: invokeai.app.services.shared.invocation_context.ConfigInterface
+
+::: invokeai.app.services.shared.invocation_context.UtilInterface
+
+::: invokeai.app.services.shared.invocation_context.BoardsInterface
+<!-- prettier-ignore-end -->

docs/nodes/NODES_MIGRATION_V3_V4.md

@@ -0,0 +1,148 @@
+# Invoke v4.0.0 Nodes API Migration guide
+
+Invoke v4.0.0 is versioned as such due to breaking changes to the API utilized
+by nodes, both core and custom.
+
+## Motivation
+
+Prior to v4.0.0, the `invokeai` python package has not be set up to be utilized
+as a library. That is to say, it didn't have any explicitly public API, and node
+authors had to work with the unstable internal application API.
+
+v4.0.0 introduces a stable public API for nodes.
+
+## Changes
+
+There are two node-author-facing changes:
+
+1. Import Paths
+1. Invocation Context API
+
+### Import Paths
+
+All public objects are now exported from `invokeai.invocation_api`:
+
+```py
+# Old
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    InputField,
+    InvocationContext,
+    invocation,
+)
+from invokeai.app.invocations.primitives import ImageField
+
+# New
+from invokeai.invocation_api import (
+    BaseInvocation,
+    ImageField,
+    InputField,
+    InvocationContext,
+    invocation,
+)
+```
+
+It's possible that we've missed some classes you need in your node. Please let
+us know if that's the case.
+
+### Invocation Context API
+
+Most nodes utilize the Invocation Context, an object that is passed to the
+`invoke` that provides access to data and services a node may need.
+
+Until now, that object and the services it exposed were internal. Exposing them
+to nodes means that changes to our internal implementation could break nodes.
+The methods on the services are also often fairly complicated and allowed nodes
+to footgun.
+
+In v4.0.0, this object has been refactored to be much simpler.
+
+See [INVOCATION_API](./INVOCATION_API.md) for full details of the API.
+
+!!! warning ""
+
+    This API may shift slightly until the release of v4.0.0 as we work through a few final updates to the Model Manager.
+
+#### Improved Service Methods
+
+The biggest offender was the image save method:
+
+```py
+# Old
+image_dto = context.services.images.create(
+    image=image,
+    image_origin=ResourceOrigin.INTERNAL,
+    image_category=ImageCategory.GENERAL,
+    node_id=self.id,
+    session_id=context.graph_execution_state_id,
+    is_intermediate=self.is_intermediate,
+    metadata=self.metadata,
+    workflow=context.workflow,
+)
+
+# New
+image_dto = context.images.save(image=image)
+```
+
+Other methods are simplified, or enhanced with additional functionality:
+
+```py
+# Old
+image = context.services.images.get_pil_image(image_name)
+
+# New
+image = context.images.get_pil(image_name)
+image_cmyk = context.images.get_pil(image_name, "CMYK")
+```
+
+We also had some typing issues around tensors:
+
+```py
+# Old
+# `latents` typed as `torch.Tensor`, but could be `ConditioningFieldData`
+latents = context.services.latents.get(self.latents.latents_name)
+# `data` typed as `torch.Tenssor,` but could be `ConditioningFieldData`
+context.services.latents.save(latents_name, data)
+
+# New - separate methods for tensors and conditioning data w/ correct typing
+# Also, the service generates the names
+tensor_name = context.tensors.save(tensor)
+tensor = context.tensors.load(tensor_name)
+# For conditioning
+cond_name = context.conditioning.save(cond_data)
+cond_data = context.conditioning.load(cond_name)
+```
+
+#### Output Construction
+
+Core Outputs have builder functions right on them - no need to manually
+construct these objects, or use an extra utility:
+
+```py
+# Old
+image_output = ImageOutput(
+    image=ImageField(image_name=image_dto.image_name),
+    width=image_dto.width,
+    height=image_dto.height,
+)
+latents_output = build_latents_output(latents_name=name, latents=latents, seed=None)
+noise_output = NoiseOutput(
+    noise=LatentsField(latents_name=latents_name, seed=seed),
+    width=latents.size()[3] * 8,
+    height=latents.size()[2] * 8,
+)
+cond_output = ConditioningOutput(
+    conditioning=ConditioningField(
+        conditioning_name=conditioning_name,
+    ),
+)
+
+# New
+image_output = ImageOutput.build(image_dto)
+latents_output = LatentsOutput.build(latents_name=name, latents=noise, seed=self.seed)
+noise_output = NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)
+cond_output = ConditioningOutput.build(conditioning_name)
+```
+
+You can still create the objects using constructors if you want, but we suggest
+using the builder methods.

docs/nodes/communityNodes.md

@@ -32,6 +32,7 @@ To use a community workflow, download the the `.json` node graph file and load i
     + [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
     + [Image Picker](#image-picker)
     + [Image Resize Plus](#image-resize-plus)
+    + [Latent Upscale](#latent-upscale)
     + [Load Video Frame](#load-video-frame)
     + [Make 3D](#make-3d)
     + [Mask Operations](#mask-operations)
@@ -290,6 +291,13 @@ View:
 </br><img src="https://raw.githubusercontent.com/VeyDlin/image-resize-plus-node/master/.readme/node.png" width="500" />
 
 
+--------------------------------
+### Latent Upscale
+
+**Description:** This node uses a small (~2.4mb) model to upscale the latents used in a Stable Diffusion 1.5 or Stable Diffusion XL image generation, rather than the typical interpolation method, avoiding the traditional downsides of the latent upscale technique.
+
+**Node Link:** [https://github.com/gogurtenjoyer/latent-upscale](https://github.com/gogurtenjoyer/latent-upscale)
+
 --------------------------------
 ### Load Video Frame
 
@@ -346,12 +354,21 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
 
 **Description:** A set of nodes for Metadata. Collect Metadata from within an `iterate` node & extract metadata from an image.
 
-- `Metadata Item Linked` - Allows collecting of metadata while within an iterate node with no need for a collect node or conversion to metadata node.
-- `Metadata From Image` - Provides Metadata from an image.
-- `Metadata To String` - Extracts a String value of a label from metadata.
-- `Metadata To Integer` - Extracts an Integer value of a label from metadata.
-- `Metadata To Float` - Extracts a Float value of a label from metadata.
-- `Metadata To Scheduler` - Extracts a Scheduler value of a label from metadata.
+- `Metadata Item Linked` - Allows collecting of metadata while within an iterate node with no need for a collect node or conversion to metadata node
+- `Metadata From Image` - Provides Metadata from an image
+- `Metadata To String` - Extracts a String value of a label from metadata
+- `Metadata To Integer` - Extracts an Integer value of a label from metadata
+- `Metadata To Float` - Extracts a Float value of a label from metadata
+- `Metadata To Scheduler` - Extracts a Scheduler value of a label from metadata
+- `Metadata To Bool` - Extracts Bool types from metadata
+- `Metadata To Model` - Extracts model types from metadata
+- `Metadata To SDXL Model` - Extracts SDXL model types from metadata
+- `Metadata To LoRAs` - Extracts Loras from metadata. 
+- `Metadata To SDXL LoRAs` - Extracts SDXL Loras from metadata
+- `Metadata To ControlNets` - Extracts ControNets from metadata
+- `Metadata To IP-Adapters` - Extracts IP-Adapters from metadata
+- `Metadata To T2I-Adapters` - Extracts T2I-Adapters from metadata
+- `Denoise Latents + Metadata` - This is an inherited version of the existing `Denoise Latents` node but with a metadata input and output. 
 
 **Node Link:** https://github.com/skunkworxdark/metadata-linked-nodes
 

docs/nodes/defaultNodes.md

@@ -19,6 +19,8 @@ their descriptions.
 | Conditioning Primitive                                        | A conditioning tensor primitive value                                                                                                                |
 | Content Shuffle Processor                                     | Applies content shuffle processing to image                                                                                                          |
 | ControlNet                                                    | Collects ControlNet info to pass to other nodes                                                                                                      |
+| Create Denoise Mask                                           | Converts a greyscale or transparency image into a mask for denoising.                                                                                |
+| Create Gradient Mask                                          | Creates a mask for Gradient ("soft", "differential") inpainting that gradually expands during denoising. Improves edge coherence.                    |
 | Denoise Latents                                               | Denoises noisy latents to decodable images                                                                                                           |
 | Divide Integers                                               | Divides two numbers                                                                                                                                  |
 | Dynamic Prompt                                                | Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator                                                                      |

docs/requirements-mkdocs.txt

@@ -1,5 +0,0 @@
-mkdocs
-mkdocs-material>=8, <9
-mkdocs-git-revision-date-localized-plugin
-mkdocs-redirects==1.2.0
-

docs/stylesheets/extra.css

@@ -1,5 +0,0 @@
-:root {
-    --md-primary-fg-color:        #35A4DB;
-    --md-primary-fg-color--light: #35A4DB;
-    --md-primary-fg-color--dark:  #35A4DB;
-  }

installer/create_installer.sh

@@ -2,22 +2,18 @@
 
 set -e
 
-BCYAN="\e[1;36m"
-BYELLOW="\e[1;33m"
-BGREEN="\e[1;32m"
-BRED="\e[1;31m"
-RED="\e[31m"
-RESET="\e[0m"
-
-function is_bin_in_path {
-    builtin type -P "$1" &>/dev/null
-}
+BCYAN="\033[1;36m"
+BYELLOW="\033[1;33m"
+BGREEN="\033[1;32m"
+BRED="\033[1;31m"
+RED="\033[31m"
+RESET="\033[0m"
 
 function git_show {
     git show -s --format=oneline --abbrev-commit "$1" | cat
 }
 
-if [[ -v "VIRTUAL_ENV" ]]; then
+if [[ ! -z "${VIRTUAL_ENV}" ]]; then
     # we can't just call 'deactivate' because this function is not exported
     # to the environment of this script from the bash process that runs the script
     echo -e "${BRED}A virtual environment is activated. Please deactivate it before proceeding.${RESET}"
@@ -26,31 +22,63 @@ fi
 
 cd "$(dirname "$0")"
 
-echo
-echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
-echo "The current working directory is $(pwd)"
-read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
-echo
-
-# Some machines only have `python3` in PATH, others have `python` - make an alias.
-# We can use a function to approximate an alias within a non-interactive shell.
-if ! is_bin_in_path python && is_bin_in_path python3; then
-    function python {
-        python3 "$@"
-    }
-fi
-
 VERSION=$(
     cd ..
-    python -c "from invokeai.version import __version__ as version; print(version)"
+    python3 -c "from invokeai.version import __version__ as version; print(version)"
 )
-PATCH=""
-VERSION="v${VERSION}${PATCH}"
+VERSION="v${VERSION}"
+
+if [[ ! -z ${CI} ]]; then
+    echo
+    echo -e "${BCYAN}CI environment detected${RESET}"
+    echo
+else
+    echo
+    echo -e "${BYELLOW}This script must be run from the installer directory!${RESET}"
+    echo "The current working directory is $(pwd)"
+    read -p "If that looks right, press any key to proceed, or CTRL-C to exit..."
+    echo
+fi
 
 echo -e "${BGREEN}HEAD${RESET}:"
 git_show HEAD
 echo
 
+# ---------------------- FRONTEND ----------------------
+
+pushd ../invokeai/frontend/web >/dev/null
+echo "Installing frontend dependencies..."
+echo
+pnpm i --frozen-lockfile
+echo
+if [[ ! -z ${CI} ]]; then
+    echo "Building frontend without checks..."
+    # In CI, we have already done the frontend checks and can just build
+    pnpm vite build
+else
+    echo "Running checks and building frontend..."
+    # This runs all the frontend checks and builds
+    pnpm build
+fi
+echo
+popd
+
+# ---------------------- BACKEND ----------------------
+
+echo
+echo "Building wheel..."
+echo
+
+# install the 'build' package in the user site packages, if needed
+# could be improved by using a temporary venv, but it's tiny and harmless
+if [[ $(python3 -c 'from importlib.util import find_spec; print(find_spec("build") is None)') == "True" ]]; then
+    pip install --user build
+fi
+
+rm -rf ../build
+
+python3 -m build --outdir dist/ ../.
+
 # ----------------------
 
 echo
@@ -78,10 +106,28 @@ chmod a+x InvokeAI-Installer/install.sh
 cp install.bat.in InvokeAI-Installer/install.bat
 cp WinLongPathsEnabled.reg InvokeAI-Installer/
 
-# Zip everything up
-zip -r InvokeAI-installer-$VERSION.zip InvokeAI-Installer
+FILENAME=InvokeAI-installer-$VERSION.zip
 
-# clean up
-rm -rf InvokeAI-Installer tmp dist ../invokeai/frontend/web/dist/
+# Zip everything up
+zip -r ${FILENAME} InvokeAI-Installer
+
+echo
+echo -e "${BGREEN}Built installer: ./${FILENAME}${RESET}"
+echo -e "${BGREEN}Built PyPi distribution: ./dist${RESET}"
+
+# clean up, but only if we are not in a github action
+if [[ -z ${CI} ]]; then
+    echo
+    echo "Cleaning up intermediate build files..."
+    rm -rf InvokeAI-Installer tmp ../invokeai/frontend/web/dist/
+fi
+
+if [[ ! -z ${CI} ]]; then
+    echo
+    echo "Setting GitHub action outputs..."
+    echo "INSTALLER_FILENAME=${FILENAME}" >>$GITHUB_OUTPUT
+    echo "INSTALLER_PATH=installer/${FILENAME}" >>$GITHUB_OUTPUT
+    echo "DIST_PATH=installer/dist/" >>$GITHUB_OUTPUT
+fi
 
 exit 0

installer/tag_release.sh

@@ -2,12 +2,12 @@
 
 set -e
 
-BCYAN="\e[1;36m"
-BYELLOW="\e[1;33m"
-BGREEN="\e[1;32m"
-BRED="\e[1;31m"
-RED="\e[31m"
-RESET="\e[0m"
+BCYAN="\033[1;36m"
+BYELLOW="\033[1;33m"
+BGREEN="\033[1;32m"
+BRED="\033[1;31m"
+RED="\033[31m"
+RESET="\033[0m"
 
 function does_tag_exist {
     git rev-parse --quiet --verify "refs/tags/$1" >/dev/null
@@ -23,49 +23,40 @@ function git_show {
 
 VERSION=$(
     cd ..
-    python -c "from invokeai.version import __version__ as version; print(version)"
+    python3 -c "from invokeai.version import __version__ as version; print(version)"
 )
 PATCH=""
-MAJOR_VERSION=$(echo $VERSION | sed 's/\..*$//')
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v${MAJOR_VERSION}-latest"
 
 if does_tag_exist $VERSION; then
     echo -e "${BCYAN}${VERSION}${RESET} already exists:"
     git_show_ref tags/$VERSION
     echo
 fi
-if does_tag_exist $LATEST_TAG; then
-    echo -e "${BCYAN}${LATEST_TAG}${RESET} already exists:"
-    git_show_ref tags/$LATEST_TAG
-    echo
-fi
 
 echo -e "${BGREEN}HEAD${RESET}:"
 git_show
 echo
 
-echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} and ${BCYAN}${LATEST_TAG}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on remote${RESET}? "
+echo -e "${BGREEN}git remote -v${RESET}:"
+git remote -v
+echo
+
+echo -e -n "Create tags ${BCYAN}${VERSION}${RESET} @ ${BGREEN}HEAD${RESET}, ${RED}deleting existing tags on origin remote${RESET}? "
 read -e -p 'y/n [n]: ' input
 RESPONSE=${input:='n'}
 if [ "$RESPONSE" == 'y' ]; then
     echo
-    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on remote..."
-    git push --delete origin $VERSION
+    echo -e "Deleting ${BCYAN}${VERSION}${RESET} tag on origin remote..."
+    git push origin :refs/tags/$VERSION
 
-    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} locally..."
+    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${VERSION}${RESET} on locally..."
     if ! git tag -fa $VERSION; then
         echo "Existing/invalid tag"
         exit -1
     fi
 
-    echo -e "Deleting ${BCYAN}${LATEST_TAG}${RESET} tag on remote..."
-    git push --delete origin $LATEST_TAG
-
-    echo -e "Tagging ${BGREEN}HEAD${RESET} with ${BCYAN}${LATEST_TAG}${RESET} locally..."
-    git tag -fa $LATEST_TAG
-
-    echo -e "Pushing updated tags to remote..."
+    echo -e "Pushing updated tags to origin remote..."
     git push origin --tags
 fi
 exit 0

invokeai/app/api/dependencies.py

@@ -4,11 +4,9 @@ from logging import Logger
 
 import torch
 
-from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
 from invokeai.app.services.object_serializer.object_serializer_disk import ObjectSerializerDisk
 from invokeai.app.services.object_serializer.object_serializer_forward_cache import ObjectSerializerForwardCache
 from invokeai.app.services.shared.sqlite.sqlite_util import init_db
-from invokeai.backend.model_manager.metadata import ModelMetadataStore
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
@@ -17,24 +15,22 @@ from ..services.board_image_records.board_image_records_sqlite import SqliteBoar
 from ..services.board_images.board_images_default import BoardImagesService
 from ..services.board_records.board_records_sqlite import SqliteBoardRecordStorage
 from ..services.boards.boards_default import BoardService
+from ..services.bulk_download.bulk_download_default import BulkDownloadService
 from ..services.config import InvokeAIAppConfig
 from ..services.download import DownloadQueueService
 from ..services.image_files.image_files_disk import DiskImageFileStorage
 from ..services.image_records.image_records_sqlite import SqliteImageRecordStorage
 from ..services.images.images_default import ImageService
 from ..services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
-from ..services.invocation_processor.invocation_processor_default import DefaultInvocationProcessor
-from ..services.invocation_queue.invocation_queue_memory import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
 from ..services.invocation_stats.invocation_stats_default import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.model_install import ModelInstallService
+from ..services.model_images.model_images_default import ModelImageFileStorageDisk
 from ..services.model_manager.model_manager_default import ModelManagerService
 from ..services.model_records import ModelRecordServiceSQL
 from ..services.names.names_default import SimpleNameService
 from ..services.session_processor.session_processor_default import DefaultSessionProcessor
 from ..services.session_queue.session_queue_sqlite import SqliteSessionQueue
-from ..services.shared.graph import GraphExecutionState
 from ..services.urls.urls_default import LocalUrlService
 from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
 from .events import FastAPIEventService
@@ -68,14 +64,15 @@ class ApiDependencies:
     def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger) -> None:
         logger.info(f"InvokeAI version {__version__}")
         logger.info(f"Root directory = {str(config.root_path)}")
-        logger.debug(f"Internet connectivity is {config.internet_available}")
 
-        output_folder = config.output_path
+        output_folder = config.outputs_path
         if output_folder is None:
             raise ValueError("Output folder is not set")
 
         image_files = DiskImageFileStorage(f"{output_folder}/images")
 
+        model_images_folder = config.models_path
+
         db = init_db(config=config, logger=logger, image_files=image_files)
 
         configuration = config
@@ -86,7 +83,7 @@ class ApiDependencies:
         board_records = SqliteBoardRecordStorage(db=db)
         boards = BoardService()
         events = FastAPIEventService(event_handler_id)
-        graph_execution_manager = ItemStorageMemory[GraphExecutionState]()
+        bulk_download = BulkDownloadService()
         image_records = SqliteImageRecordStorage(db=db)
         images = ImageService()
         invocation_cache = MemoryInvocationCache(max_cache_size=config.node_cache_size)
@@ -96,21 +93,16 @@ class ApiDependencies:
         conditioning = ObjectSerializerForwardCache(
             ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
         )
-        model_manager = ModelManagerService(config, logger)
-        model_record_service = ModelRecordServiceSQL(db=db)
         download_queue_service = DownloadQueueService(event_bus=events)
-        metadata_store = ModelMetadataStore(db=db)
-        model_install_service = ModelInstallService(
-            app_config=config,
-            record_store=model_record_service,
+        model_images_service = ModelImageFileStorageDisk(model_images_folder / "model_images")
+        model_manager = ModelManagerService.build_model_manager(
+            app_config=configuration,
+            model_record_service=ModelRecordServiceSQL(db=db),
             download_queue=download_queue_service,
-            metadata_store=metadata_store,
-            event_bus=events,
+            events=events,
         )
         names = SimpleNameService()
         performance_statistics = InvocationStatsService()
-        processor = DefaultInvocationProcessor()
-        queue = MemoryInvocationQueue()
         session_processor = DefaultSessionProcessor()
         session_queue = SqliteSessionQueue(db=db)
         urls = LocalUrlService()
@@ -121,22 +113,19 @@ class ApiDependencies:
             board_images=board_images,
             board_records=board_records,
             boards=boards,
+            bulk_download=bulk_download,
             configuration=configuration,
             events=events,
-            graph_execution_manager=graph_execution_manager,
             image_files=image_files,
             image_records=image_records,
             images=images,
             invocation_cache=invocation_cache,
             logger=logger,
+            model_images=model_images_service,
             model_manager=model_manager,
-            model_records=model_record_service,
             download_queue=download_queue_service,
-            model_install=model_install_service,
             names=names,
             performance_statistics=performance_statistics,
-            processor=processor,
-            queue=queue,
             session_processor=session_processor,
             session_queue=session_queue,
             urls=urls,

invokeai/app/api/routers/app_info.py

@@ -12,7 +12,6 @@ from pydantic import BaseModel, Field
 
 from invokeai.app.invocations.upscale import ESRGAN_MODELS
 from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
-from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.patchmatch import PatchMatch
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 from invokeai.backend.util.logging import logging
@@ -114,9 +113,7 @@ async def get_config() -> AppConfig:
     if SafetyChecker.safety_checker_available():
         nsfw_methods.append("nsfw_checker")
 
-    watermarking_methods = []
-    if InvisibleWatermark.invisible_watermark_available():
-        watermarking_methods.append("invisible_watermark")
+    watermarking_methods = ["invisible_watermark"]
 
     return AppConfig(
         infill_methods=infill_methods,

invokeai/app/api/routers/download_queue.py

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

invokeai/app/api/routers/images.py

@@ -2,7 +2,7 @@ import io
 import traceback
 from typing import Optional
 
-from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
+from fastapi import BackgroundTasks, Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
@@ -375,16 +375,67 @@ async def unstar_images_in_list(
 
 class ImagesDownloaded(BaseModel):
     response: Optional[str] = Field(
-        description="If defined, the message to display to the user when images begin downloading"
+        default=None, description="The message to display to the user when images begin downloading"
+    )
+    bulk_download_item_name: Optional[str] = Field(
+        default=None, description="The name of the bulk download item for which events will be emitted"
     )
 
 
-@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
+@images_router.post(
+    "/download", operation_id="download_images_from_list", response_model=ImagesDownloaded, status_code=202
+)
 async def download_images_from_list(
-    image_names: list[str] = Body(description="The list of names of images to download", embed=True),
+    background_tasks: BackgroundTasks,
+    image_names: Optional[list[str]] = Body(
+        default=None, description="The list of names of images to download", embed=True
+    ),
     board_id: Optional[str] = Body(
-        default=None, description="The board from which image should be downloaded from", embed=True
+        default=None, description="The board from which image should be downloaded", embed=True
     ),
 ) -> ImagesDownloaded:
-    # return ImagesDownloaded(response="Your images are downloading")
-    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")
+    if (image_names is None or len(image_names) == 0) and board_id is None:
+        raise HTTPException(status_code=400, detail="No images or board id specified.")
+    bulk_download_item_id: str = ApiDependencies.invoker.services.bulk_download.generate_item_id(board_id)
+
+    background_tasks.add_task(
+        ApiDependencies.invoker.services.bulk_download.handler,
+        image_names,
+        board_id,
+        bulk_download_item_id,
+    )
+    return ImagesDownloaded(bulk_download_item_name=bulk_download_item_id + ".zip")
+
+
+@images_router.api_route(
+    "/download/{bulk_download_item_name}",
+    methods=["GET"],
+    operation_id="get_bulk_download_item",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the complete bulk download item",
+            "content": {"application/zip": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_bulk_download_item(
+    background_tasks: BackgroundTasks,
+    bulk_download_item_name: str = Path(description="The bulk_download_item_name of the bulk download item to get"),
+) -> FileResponse:
+    """Gets a bulk download zip file"""
+    try:
+        path = ApiDependencies.invoker.services.bulk_download.get_path(bulk_download_item_name)
+
+        response = FileResponse(
+            path,
+            media_type="application/zip",
+            filename=bulk_download_item_name,
+            content_disposition_type="inline",
+        )
+        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        background_tasks.add_task(ApiDependencies.invoker.services.bulk_download.delete, bulk_download_item_name)
+        return response
+    except Exception:
+        raise HTTPException(status_code=404)

invokeai/app/api/routers/model_manager.py

@@ -0,0 +1,782 @@
+# Copyright (c) 2023 Lincoln D. Stein
+"""FastAPI route for model configuration records."""
+
+import io
+import pathlib
+import shutil
+import traceback
+from typing import Any, Dict, List, Optional
+
+from fastapi import Body, Path, Query, Response, UploadFile
+from fastapi.responses import FileResponse
+from fastapi.routing import APIRouter
+from PIL import Image
+from pydantic import AnyHttpUrl, BaseModel, ConfigDict, Field
+from starlette.exceptions import HTTPException
+from typing_extensions import Annotated
+
+from invokeai.app.services.model_install import ModelInstallJob
+from invokeai.app.services.model_records import (
+    InvalidModelException,
+    UnknownModelException,
+)
+from invokeai.app.services.model_records.model_records_base import DuplicateModelException, ModelRecordChanges
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    MainCheckpointConfig,
+    ModelFormat,
+    ModelType,
+    SubModelType,
+)
+from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
+from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
+from invokeai.backend.model_manager.search import ModelSearch
+
+from ..dependencies import ApiDependencies
+
+model_manager_router = APIRouter(prefix="/v2/models", tags=["model_manager"])
+
+# images are immutable; set a high max-age
+IMAGE_MAX_AGE = 31536000
+
+
+class ModelsList(BaseModel):
+    """Return list of configs."""
+
+    models: List[AnyModelConfig]
+
+    model_config = ConfigDict(use_enum_values=True)
+
+
+##############################################################################
+# These are example inputs and outputs that are used in places where Swagger
+# is unable to generate a correct example.
+##############################################################################
+example_model_config = {
+    "path": "string",
+    "name": "string",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config_path": "string",
+    "key": "string",
+    "hash": "string",
+    "description": "string",
+    "source": "string",
+    "converted_at": 0,
+    "variant": "normal",
+    "prediction_type": "epsilon",
+    "repo_variant": "fp16",
+    "upcast_attention": False,
+}
+
+example_model_input = {
+    "path": "/path/to/model",
+    "name": "model_name",
+    "base": "sd-1",
+    "type": "main",
+    "format": "checkpoint",
+    "config_path": "configs/stable-diffusion/v1-inference.yaml",
+    "description": "Model description",
+    "vae": None,
+    "variant": "normal",
+}
+
+##############################################################################
+# ROUTES
+##############################################################################
+
+
+@model_manager_router.get(
+    "/",
+    operation_id="list_model_records",
+)
+async def list_model_records(
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
+    model_format: Optional[ModelFormat] = Query(
+        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
+    ),
+) -> ModelsList:
+    """Get a list of models."""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    found_models: list[AnyModelConfig] = []
+    if base_models:
+        for base_model in base_models:
+            found_models.extend(
+                record_store.search_by_attr(
+                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
+                )
+            )
+    else:
+        found_models.extend(
+            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
+        )
+    for model in found_models:
+        cover_image = ApiDependencies.invoker.services.model_images.get_url(model.key)
+        model.cover_image = cover_image
+    return ModelsList(models=found_models)
+
+
+@model_manager_router.get(
+    "/get_by_attrs",
+    operation_id="get_model_records_by_attrs",
+    response_model=AnyModelConfig,
+)
+async def get_model_records_by_attrs(
+    name: str = Query(description="The name of the model"),
+    type: ModelType = Query(description="The type of the model"),
+    base: BaseModelType = Query(description="The base model of the model"),
+) -> AnyModelConfig:
+    """Gets a model by its attributes. The main use of this route is to provide backwards compatibility with the old
+    model manager, which identified models by a combination of name, base and type."""
+    configs = ApiDependencies.invoker.services.model_manager.store.search_by_attr(
+        base_model=base, model_type=type, model_name=name
+    )
+    if not configs:
+        raise HTTPException(status_code=404, detail="No model found with these attributes")
+
+    return configs[0]
+
+
+@model_manager_router.get(
+    "/i/{key}",
+    operation_id="get_model_record",
+    responses={
+        200: {
+            "description": "The model configuration was retrieved successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+    },
+)
+async def get_model_record(
+    key: str = Path(description="Key of the model record to fetch."),
+) -> AnyModelConfig:
+    """Get a model record"""
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        config: AnyModelConfig = record_store.get_model(key)
+        cover_image = ApiDependencies.invoker.services.model_images.get_url(key)
+        config.cover_image = cover_image
+        return config
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+# @model_manager_router.get("/summary", operation_id="list_model_summary")
+# async def list_model_summary(
+#     page: int = Query(default=0, description="The page to get"),
+#     per_page: int = Query(default=10, description="The number of models per page"),
+#     order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
+# ) -> PaginatedResults[ModelSummary]:
+#     """Gets a page of model summary data."""
+#     record_store = ApiDependencies.invoker.services.model_manager.store
+#     results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
+#     return results
+
+
+class FoundModel(BaseModel):
+    path: str = Field(description="Path to the model")
+    is_installed: bool = Field(description="Whether or not the model is already installed")
+
+
+@model_manager_router.get(
+    "/scan_folder",
+    operation_id="scan_for_models",
+    responses={
+        200: {"description": "Directory scanned successfully"},
+        400: {"description": "Invalid directory path"},
+    },
+    status_code=200,
+    response_model=List[FoundModel],
+)
+async def scan_for_models(
+    scan_path: str = Query(description="Directory path to search for models", default=None),
+) -> List[FoundModel]:
+    path = pathlib.Path(scan_path)
+    if not scan_path or not path.is_dir():
+        raise HTTPException(
+            status_code=400,
+            detail=f"The search path '{scan_path}' does not exist or is not directory",
+        )
+
+    search = ModelSearch()
+    try:
+        found_model_paths = search.search(path)
+        models_path = ApiDependencies.invoker.services.configuration.models_path
+
+        # If the search path includes the main models directory, we need to exclude core models from the list.
+        # TODO(MM2): Core models should be handled by the model manager so we can determine if they are installed
+        # without needing to crawl the filesystem.
+        core_models_path = pathlib.Path(models_path, "core").resolve()
+        non_core_model_paths = [p for p in found_model_paths if not p.is_relative_to(core_models_path)]
+
+        installed_models = ApiDependencies.invoker.services.model_manager.store.search_by_attr()
+        resolved_installed_model_paths: list[str] = []
+        installed_model_sources: list[str] = []
+
+        # This call lists all installed models.
+        for model in installed_models:
+            path = pathlib.Path(model.path)
+            # If the model has a source, we need to add it to the list of installed sources.
+            if model.source:
+                installed_model_sources.append(model.source)
+            # If the path is not absolute, that means it is in the app models directory, and we need to join it with
+            # the models path before resolving.
+            if not path.is_absolute():
+                resolved_installed_model_paths.append(str(pathlib.Path(models_path, path).resolve()))
+                continue
+            resolved_installed_model_paths.append(str(path.resolve()))
+
+        scan_results: list[FoundModel] = []
+
+        # Check if the model is installed by comparing the resolved paths, appending to the scan result.
+        for p in non_core_model_paths:
+            path = str(p)
+            is_installed = path in resolved_installed_model_paths or path in installed_model_sources
+            found_model = FoundModel(path=path, is_installed=is_installed)
+            scan_results.append(found_model)
+    except Exception as e:
+        raise HTTPException(
+            status_code=500,
+            detail=f"An error occurred while searching the directory: {e}",
+        )
+    return scan_results
+
+
+class HuggingFaceModels(BaseModel):
+    urls: List[AnyHttpUrl] | None = Field(description="URLs for all checkpoint format models in the metadata")
+    is_diffusers: bool = Field(description="Whether the metadata is for a Diffusers format model")
+
+
+@model_manager_router.get(
+    "/hugging_face",
+    operation_id="get_hugging_face_models",
+    responses={
+        200: {"description": "Hugging Face repo scanned successfully"},
+        400: {"description": "Invalid hugging face repo"},
+    },
+    status_code=200,
+    response_model=HuggingFaceModels,
+)
+async def get_hugging_face_models(
+    hugging_face_repo: str = Query(description="Hugging face repo to search for models", default=None),
+) -> HuggingFaceModels:
+    try:
+        metadata = HuggingFaceMetadataFetch().from_id(hugging_face_repo)
+    except UnknownMetadataException:
+        raise HTTPException(
+            status_code=400,
+            detail="No HuggingFace repository found",
+        )
+
+    assert isinstance(metadata, ModelMetadataWithFiles)
+
+    return HuggingFaceModels(
+        urls=metadata.ckpt_urls,
+        is_diffusers=metadata.is_diffusers,
+    )
+
+
+@model_manager_router.patch(
+    "/i/{key}",
+    operation_id="update_model_record",
+    responses={
+        200: {
+            "description": "The model was updated successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+)
+async def update_model_record(
+    key: Annotated[str, Path(description="Unique key of model")],
+    changes: Annotated[ModelRecordChanges, Body(description="Model config", example=example_model_input)],
+) -> AnyModelConfig:
+    """Update a model's config."""
+    logger = ApiDependencies.invoker.services.logger
+    record_store = ApiDependencies.invoker.services.model_manager.store
+    try:
+        model_response: AnyModelConfig = record_store.update_model(key, changes=changes)
+        logger.info(f"Updated model: {key}")
+    except UnknownModelException as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return model_response
+
+
+@model_manager_router.get(
+    "/i/{key}/image",
+    operation_id="get_model_image",
+    responses={
+        200: {
+            "description": "The model image was fetched successfully",
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "The model image could not be found"},
+    },
+    status_code=200,
+)
+async def get_model_image(
+    key: str = Path(description="The name of model image file to get"),
+) -> FileResponse:
+    """Gets an image file that previews the model"""
+
+    try:
+        path = ApiDependencies.invoker.services.model_images.get_path(key)
+
+        response = FileResponse(
+            path,
+            media_type="image/png",
+            filename=key + ".png",
+            content_disposition_type="inline",
+        )
+        response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
+        return response
+    except Exception:
+        raise HTTPException(status_code=404)
+
+
+@model_manager_router.patch(
+    "/i/{key}/image",
+    operation_id="update_model_image",
+    responses={
+        200: {
+            "description": "The model image was updated successfully",
+        },
+        400: {"description": "Bad request"},
+    },
+    status_code=200,
+)
+async def update_model_image(
+    key: Annotated[str, Path(description="Unique key of model")],
+    image: UploadFile,
+) -> None:
+    if not image.content_type or not image.content_type.startswith("image"):
+        raise HTTPException(status_code=415, detail="Not an image")
+
+    contents = await image.read()
+    try:
+        pil_image = Image.open(io.BytesIO(contents))
+
+    except Exception:
+        ApiDependencies.invoker.services.logger.error(traceback.format_exc())
+        raise HTTPException(status_code=415, detail="Failed to read image")
+
+    logger = ApiDependencies.invoker.services.logger
+    model_images = ApiDependencies.invoker.services.model_images
+    try:
+        model_images.save(pil_image, key)
+        logger.info(f"Updated image for model: {key}")
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return
+
+
+@model_manager_router.delete(
+    "/i/{key}",
+    operation_id="delete_model",
+    responses={
+        204: {"description": "Model deleted successfully"},
+        404: {"description": "Model not found"},
+    },
+    status_code=204,
+)
+async def delete_model(
+    key: str = Path(description="Unique key of model to remove from model registry."),
+) -> Response:
+    """
+    Delete model record from database.
+
+    The configuration record will be removed. The corresponding weights files will be
+    deleted as well if they reside within the InvokeAI "models" directory.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        installer.delete(key)
+        logger.info(f"Deleted model: {key}")
+        return Response(status_code=204)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/i/{key}/image",
+    operation_id="delete_model_image",
+    responses={
+        204: {"description": "Model image deleted successfully"},
+        404: {"description": "Model image not found"},
+    },
+    status_code=204,
+)
+async def delete_model_image(
+    key: str = Path(description="Unique key of model image to remove from model_images directory."),
+) -> None:
+    logger = ApiDependencies.invoker.services.logger
+    model_images = ApiDependencies.invoker.services.model_images
+    try:
+        model_images.delete(key)
+        logger.info(f"Deleted model image: {key}")
+        return
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+# @model_manager_router.post(
+#     "/i/",
+#     operation_id="add_model_record",
+#     responses={
+#         201: {
+#             "description": "The model added successfully",
+#             "content": {"application/json": {"example": example_model_config}},
+#         },
+#         409: {"description": "There is already a model corresponding to this path or repo_id"},
+#         415: {"description": "Unrecognized file/folder format"},
+#     },
+#     status_code=201,
+# )
+# async def add_model_record(
+#     config: Annotated[
+#         AnyModelConfig, Body(description="Model config", discriminator="type", example=example_model_input)
+#     ],
+# ) -> AnyModelConfig:
+#     """Add a model using the configuration information appropriate for its type."""
+#     logger = ApiDependencies.invoker.services.logger
+#     record_store = ApiDependencies.invoker.services.model_manager.store
+#     try:
+#         record_store.add_model(config)
+#     except DuplicateModelException as e:
+#         logger.error(str(e))
+#         raise HTTPException(status_code=409, detail=str(e))
+#     except InvalidModelException as e:
+#         logger.error(str(e))
+#         raise HTTPException(status_code=415)
+
+#     # now fetch it out
+#     result: AnyModelConfig = record_store.get_model(config.key)
+#     return result
+
+
+@model_manager_router.post(
+    "/install",
+    operation_id="install_model",
+    responses={
+        201: {"description": "The model imported successfully"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+)
+async def install_model(
+    source: str = Query(description="Model source to install, can be a local path, repo_id, or remote URL"),
+    inplace: Optional[bool] = Query(description="Whether or not to install a local model in place", default=False),
+    # TODO(MM2): Can we type this?
+    config: Optional[Dict[str, Any]] = Body(
+        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
+        default=None,
+        example={"name": "string", "description": "string"},
+    ),
+    access_token: Optional[str] = None,
+) -> ModelInstallJob:
+    """Install a model using a string identifier.
+
+    `source` can be any of the following.
+
+    1. A path on the local filesystem ('C:\\users\\fred\\model.safetensors')
+    2. A Url pointing to a single downloadable model file
+    3. A HuggingFace repo_id with any of the following formats:
+       - model/name
+       - model/name:fp16:vae
+       - model/name::vae          -- use default precision
+       - model/name:fp16:path/to/model.safetensors
+       - model/name::path/to/model.safetensors
+
+    `config` is an optional dict containing model configuration values that will override
+    the ones that are probed automatically.
+
+    `access_token` is an optional access token for use with Urls that require
+    authentication.
+
+    Models will be downloaded, probed, configured and installed in a
+    series of background threads. The return object has `status` attribute
+    that can be used to monitor progress.
+
+    See the documentation for `import_model_record` for more information on
+    interpreting the job information returned by this route.
+    """
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        result: ModelInstallJob = installer.heuristic_import(
+            source=source,
+            config=config,
+            access_token=access_token,
+            inplace=bool(inplace),
+        )
+        logger.info(f"Started installation of {source}")
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
+    except ValueError as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+    return result
+
+
+@model_manager_router.get(
+    "/install",
+    operation_id="list_model_installs",
+)
+async def list_model_installs() -> List[ModelInstallJob]:
+    """Return the list of model install jobs.
+
+    Install jobs have a numeric `id`, a `status`, and other fields that provide information on
+    the nature of the job and its progress. The `status` is one of:
+
+    * "waiting" -- Job is waiting in the queue to run
+    * "downloading" -- Model file(s) are downloading
+    * "running" -- Model has downloaded and the model probing and registration process is running
+    * "completed" -- Installation completed successfully
+    * "error" -- An error occurred. Details will be in the "error_type" and "error" fields.
+    * "cancelled" -- Job was cancelled before completion.
+
+    Once completed, information about the model such as its size, base
+    model and type can be retrieved from the `config_out` field. For multi-file models such as diffusers,
+    information on individual files can be retrieved from `download_parts`.
+
+    See the example and schema below for more information.
+    """
+    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_manager.install.list_jobs()
+    return jobs
+
+
+@model_manager_router.get(
+    "/install/{id}",
+    operation_id="get_model_install_job",
+    responses={
+        200: {"description": "Success"},
+        404: {"description": "No such job"},
+    },
+)
+async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
+    """
+    Return model install job corresponding to the given source. See the documentation for 'List Model Install Jobs'
+    for information on the format of the return value.
+    """
+    try:
+        result: ModelInstallJob = ApiDependencies.invoker.services.model_manager.install.get_job_by_id(id)
+        return result
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+
+
+@model_manager_router.delete(
+    "/install/{id}",
+    operation_id="cancel_model_install_job",
+    responses={
+        201: {"description": "The job was cancelled successfully"},
+        415: {"description": "No such job"},
+    },
+    status_code=201,
+)
+async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
+    """Cancel the model install job(s) corresponding to the given job ID."""
+    installer = ApiDependencies.invoker.services.model_manager.install
+    try:
+        job = installer.get_job_by_id(id)
+    except ValueError as e:
+        raise HTTPException(status_code=415, detail=str(e))
+    installer.cancel_job(job)
+
+
+@model_manager_router.delete(
+    "/install",
+    operation_id="prune_model_install_jobs",
+    responses={
+        204: {"description": "All completed and errored jobs have been pruned"},
+        400: {"description": "Bad request"},
+    },
+)
+async def prune_model_install_jobs() -> Response:
+    """Prune all completed and errored jobs from the install job list."""
+    ApiDependencies.invoker.services.model_manager.install.prune_jobs()
+    return Response(status_code=204)
+
+
+@model_manager_router.patch(
+    "/sync",
+    operation_id="sync_models_to_config",
+    responses={
+        204: {"description": "Model config record database resynced with files on disk"},
+        400: {"description": "Bad request"},
+    },
+)
+async def sync_models_to_config() -> Response:
+    """
+    Traverse the models and autoimport directories.
+
+    Model files without a corresponding
+    record in the database are added. Orphan records without a models file are deleted.
+    """
+    ApiDependencies.invoker.services.model_manager.install.sync_to_config()
+    return Response(status_code=204)
+
+
+@model_manager_router.put(
+    "/convert/{key}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "description": "Model converted successfully",
+            "content": {"application/json": {"example": example_model_config}},
+        },
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
+        409: {"description": "There is already a model registered at this location"},
+    },
+)
+async def convert_model(
+    key: str = Path(description="Unique key of the safetensors main model to convert to diffusers format."),
+) -> AnyModelConfig:
+    """
+    Permanently convert a model into diffusers format, replacing the safetensors version.
+    Note that during the conversion process the key and model hash will change.
+    The return value is the model configuration for the converted model.
+    """
+    model_manager = ApiDependencies.invoker.services.model_manager
+    logger = ApiDependencies.invoker.services.logger
+    loader = ApiDependencies.invoker.services.model_manager.load
+    store = ApiDependencies.invoker.services.model_manager.store
+    installer = ApiDependencies.invoker.services.model_manager.install
+
+    try:
+        model_config = store.get_model(key)
+    except UnknownModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=424, detail=str(e))
+
+    if not isinstance(model_config, MainCheckpointConfig):
+        logger.error(f"The model with key {key} is not a main checkpoint model.")
+        raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
+
+    # loading the model will convert it into a cached diffusers file
+    model_manager.load.load_model(model_config, submodel_type=SubModelType.Scheduler)
+
+    # Get the path of the converted model from the loader
+    cache_path = loader.convert_cache.cache_path(key)
+    assert cache_path.exists()
+
+    # temporarily rename the original safetensors file so that there is no naming conflict
+    original_name = model_config.name
+    model_config.name = f"{original_name}.DELETE"
+    changes = ModelRecordChanges(name=model_config.name)
+    store.update_model(key, changes=changes)
+
+    # install the diffusers
+    try:
+        new_key = installer.install_path(
+            cache_path,
+            config={
+                "name": original_name,
+                "description": model_config.description,
+                "hash": model_config.hash,
+                "source": model_config.source,
+            },
+        )
+    except DuplicateModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=409, detail=str(e))
+
+    # delete the original safetensors file
+    installer.delete(key)
+
+    # delete the cached version
+    shutil.rmtree(cache_path)
+
+    # return the config record for the new diffusers directory
+    new_config: AnyModelConfig = store.get_model(new_key)
+    return new_config
+
+
+# @model_manager_router.put(
+#     "/merge",
+#     operation_id="merge",
+#     responses={
+#         200: {
+#             "description": "Model converted successfully",
+#             "content": {"application/json": {"example": example_model_config}},
+#         },
+#         400: {"description": "Bad request"},
+#         404: {"description": "Model not found"},
+#         409: {"description": "There is already a model registered at this location"},
+#     },
+# )
+# async def merge(
+#     keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
+#     merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
+#     alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+#     force: bool = Body(
+#         description="Force merging of models created with different versions of diffusers",
+#         default=False,
+#     ),
+#     interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
+#     merge_dest_directory: Optional[str] = Body(
+#         description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+#         default=None,
+#     ),
+# ) -> AnyModelConfig:
+#     """
+#     Merge diffusers models. The process is controlled by a set parameters provided in the body of the request.
+#     ```
+#     Argument                Description [default]
+#     --------               ----------------------
+#     keys                   List of 2-3 model keys to merge together. All models must use the same base type.
+#     merged_model_name      Name for the merged model [Concat model names]
+#     alpha                  Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
+#     force                  If true, force the merge even if the models were generated by different versions of the diffusers library [False]
+#     interp                 Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
+#     merge_dest_directory   Specify a directory to store the merged model in [models directory]
+#     ```
+#     """
+#     logger = ApiDependencies.invoker.services.logger
+#     try:
+#         logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
+#         dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
+#         installer = ApiDependencies.invoker.services.model_manager.install
+#         merger = ModelMerger(installer)
+#         model_names = [installer.record_store.get_model(x).name for x in keys]
+#         response = merger.merge_diffusion_models_and_save(
+#             model_keys=keys,
+#             merged_model_name=merged_model_name or "+".join(model_names),
+#             alpha=alpha,
+#             interp=interp,
+#             force=force,
+#             merge_dest_directory=dest,
+#         )
+#     except UnknownModelException:
+#         raise HTTPException(
+#             status_code=404,
+#             detail=f"One or more of the models '{keys}' not found",
+#         )
+#     except ValueError as e:
+#         raise HTTPException(status_code=400, detail=str(e))
+#     return response

invokeai/app/api/routers/model_records.py

@@ -1,472 +0,0 @@
-# Copyright (c) 2023 Lincoln D. Stein
-"""FastAPI route for model configuration records."""
-
-import pathlib
-from hashlib import sha1
-from random import randbytes
-from typing import Any, Dict, List, Optional, Set
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict
-from starlette.exceptions import HTTPException
-from typing_extensions import Annotated
-
-from invokeai.app.services.model_install import ModelInstallJob, ModelSource
-from invokeai.app.services.model_records import (
-    DuplicateModelException,
-    InvalidModelException,
-    ModelRecordOrderBy,
-    ModelSummary,
-    UnknownModelException,
-)
-from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager.config import (
-    AnyModelConfig,
-    BaseModelType,
-    ModelFormat,
-    ModelType,
-)
-from invokeai.backend.model_manager.merge import MergeInterpolationMethod, ModelMerger
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
-
-from ..dependencies import ApiDependencies
-
-model_records_router = APIRouter(prefix="/v1/model/record", tags=["model_manager_v2_unstable"])
-
-
-class ModelsList(BaseModel):
-    """Return list of configs."""
-
-    models: List[AnyModelConfig]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-class ModelTagSet(BaseModel):
-    """Return tags for a set of models."""
-
-    key: str
-    name: str
-    author: str
-    tags: Set[str]
-
-
-@model_records_router.get(
-    "/",
-    operation_id="list_model_records",
-)
-async def list_model_records(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-    model_name: Optional[str] = Query(default=None, description="Exact match on the name of the model"),
-    model_format: Optional[ModelFormat] = Query(
-        default=None, description="Exact match on the format of the model (e.g. 'diffusers')"
-    ),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    found_models: list[AnyModelConfig] = []
-    if base_models:
-        for base_model in base_models:
-            found_models.extend(
-                record_store.search_by_attr(
-                    base_model=base_model, model_type=model_type, model_name=model_name, model_format=model_format
-                )
-            )
-    else:
-        found_models.extend(
-            record_store.search_by_attr(model_type=model_type, model_name=model_name, model_format=model_format)
-        )
-    return ModelsList(models=found_models)
-
-
-@model_records_router.get(
-    "/i/{key}",
-    operation_id="get_model_record",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-    },
-)
-async def get_model_record(
-    key: str = Path(description="Key of the model record to fetch."),
-) -> AnyModelConfig:
-    """Get a model record"""
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        return record_store.get_model(key)
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.get("/meta", operation_id="list_model_summary")
-async def list_model_summary(
-    page: int = Query(default=0, description="The page to get"),
-    per_page: int = Query(default=10, description="The number of models per page"),
-    order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-) -> PaginatedResults[ModelSummary]:
-    """Gets a page of model summary data."""
-    return ApiDependencies.invoker.services.model_records.list_models(page=page, per_page=per_page, order_by=order_by)
-
-
-@model_records_router.get(
-    "/meta/i/{key}",
-    operation_id="get_model_metadata",
-    responses={
-        200: {"description": "Success"},
-        400: {"description": "Bad request"},
-        404: {"description": "No metadata available"},
-    },
-)
-async def get_model_metadata(
-    key: str = Path(description="Key of the model repo metadata to fetch."),
-) -> Optional[AnyModelRepoMetadata]:
-    """Get a model metadata object."""
-    record_store = ApiDependencies.invoker.services.model_records
-    result = record_store.get_metadata(key)
-    if not result:
-        raise HTTPException(status_code=404, detail="No metadata for a model with this key")
-    return result
-
-
-@model_records_router.get(
-    "/tags",
-    operation_id="list_tags",
-)
-async def list_tags() -> Set[str]:
-    """Get a unique set of all the model tags."""
-    record_store = ApiDependencies.invoker.services.model_records
-    return record_store.list_tags()
-
-
-@model_records_router.get(
-    "/tags/search",
-    operation_id="search_by_metadata_tags",
-)
-async def search_by_metadata_tags(
-    tags: Set[str] = Query(default=None, description="Tags to search for"),
-) -> ModelsList:
-    """Get a list of models."""
-    record_store = ApiDependencies.invoker.services.model_records
-    results = record_store.search_by_metadata_tag(tags)
-    return ModelsList(models=results)
-
-
-@model_records_router.patch(
-    "/i/{key}",
-    operation_id="update_model_record",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=AnyModelConfig,
-)
-async def update_model_record(
-    key: Annotated[str, Path(description="Unique key of model")],
-    info: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    try:
-        model_response = record_store.update_model(key, config=info)
-        logger.info(f"Updated model: {key}")
-    except UnknownModelException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return model_response
-
-
-@model_records_router.delete(
-    "/i/{key}",
-    operation_id="del_model_record",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-)
-async def del_model_record(
-    key: str = Path(description="Unique key of model to remove from model registry."),
-) -> Response:
-    """
-    Delete model record from database.
-
-    The configuration record will be removed. The corresponding weights files will be
-    deleted as well if they reside within the InvokeAI "models" directory.
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        installer.delete(key)
-        logger.info(f"Deleted model: {key}")
-        return Response(status_code=204)
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.post(
-    "/i/",
-    operation_id="add_model_record",
-    responses={
-        201: {"description": "The model added successfully"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-        415: {"description": "Unrecognized file/folder format"},
-    },
-    status_code=201,
-)
-async def add_model_record(
-    config: Annotated[AnyModelConfig, Body(description="Model config", discriminator="type")],
-) -> AnyModelConfig:
-    """Add a model using the configuration information appropriate for its type."""
-    logger = ApiDependencies.invoker.services.logger
-    record_store = ApiDependencies.invoker.services.model_records
-    if config.key == "<NOKEY>":
-        config.key = sha1(randbytes(100)).hexdigest()
-        logger.info(f"Created model {config.key} for {config.name}")
-    try:
-        record_store.add_model(config.key, config)
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-
-    # now fetch it out
-    return record_store.get_model(config.key)
-
-
-@model_records_router.post(
-    "/import",
-    operation_id="import_model_record",
-    responses={
-        201: {"description": "The model imported successfully"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-)
-async def import_model(
-    source: ModelSource,
-    config: Optional[Dict[str, Any]] = Body(
-        description="Dict of fields that override auto-probed values in the model config record, such as name, description and prediction_type ",
-        default=None,
-    ),
-) -> ModelInstallJob:
-    """Add a model using its local path, repo_id, or remote URL.
-
-    Models will be downloaded, probed, configured and installed in a
-    series of background threads. The return object has `status` attribute
-    that can be used to monitor progress.
-
-    The source object is a discriminated Union of LocalModelSource,
-    HFModelSource and URLModelSource. Set the "type" field to the
-    appropriate value:
-
-    * To install a local path using LocalModelSource, pass a source of form:
-      `{
-        "type": "local",
-        "path": "/path/to/model",
-        "inplace": false
-      }`
-       The "inplace" flag, if true, will register the model in place in its
-       current filesystem location. Otherwise, the model will be copied
-       into the InvokeAI models directory.
-
-    * To install a HuggingFace repo_id using HFModelSource, pass a source of form:
-      `{
-        "type": "hf",
-        "repo_id": "stabilityai/stable-diffusion-2.0",
-        "variant": "fp16",
-        "subfolder": "vae",
-        "access_token": "f5820a918aaf01"
-      }`
-     The `variant`, `subfolder` and `access_token` fields are optional.
-
-    * To install a remote model using an arbitrary URL, pass:
-      `{
-        "type": "url",
-        "url": "http://www.civitai.com/models/123456",
-        "access_token": "f5820a918aaf01"
-      }`
-    The `access_token` field is optonal
-
-    The model's configuration record will be probed and filled in
-    automatically.  To override the default guesses, pass "metadata"
-    with a Dict containing the attributes you wish to override.
-
-    Installation occurs in the background. Either use list_model_install_jobs()
-    to poll for completion, or listen on the event bus for the following events:
-
-      "model_install_running"
-      "model_install_completed"
-      "model_install_error"
-
-    On successful completion, the event's payload will contain the field "key"
-    containing the installed ID of the model. On an error, the event's payload
-    will contain the fields "error_type" and "error" describing the nature of the
-    error and its traceback, respectively.
-
-    """
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installer = ApiDependencies.invoker.services.model_install
-        result: ModelInstallJob = installer.import_model(
-            source=source,
-            config=config,
-        )
-        logger.info(f"Started installation of {source}")
-    except UnknownModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=424, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    return result
-
-
-@model_records_router.get(
-    "/import",
-    operation_id="list_model_install_jobs",
-)
-async def list_model_install_jobs() -> List[ModelInstallJob]:
-    """Return list of model install jobs."""
-    jobs: List[ModelInstallJob] = ApiDependencies.invoker.services.model_install.list_jobs()
-    return jobs
-
-
-@model_records_router.get(
-    "/import/{id}",
-    operation_id="get_model_install_job",
-    responses={
-        200: {"description": "Success"},
-        404: {"description": "No such job"},
-    },
-)
-async def get_model_install_job(id: int = Path(description="Model install id")) -> ModelInstallJob:
-    """Return model install job corresponding to the given source."""
-    try:
-        return ApiDependencies.invoker.services.model_install.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@model_records_router.delete(
-    "/import/{id}",
-    operation_id="cancel_model_install_job",
-    responses={
-        201: {"description": "The job was cancelled successfully"},
-        415: {"description": "No such job"},
-    },
-    status_code=201,
-)
-async def cancel_model_install_job(id: int = Path(description="Model install job ID")) -> None:
-    """Cancel the model install job(s) corresponding to the given job ID."""
-    installer = ApiDependencies.invoker.services.model_install
-    try:
-        job = installer.get_job_by_id(id)
-    except ValueError as e:
-        raise HTTPException(status_code=415, detail=str(e))
-    installer.cancel_job(job)
-
-
-@model_records_router.patch(
-    "/import",
-    operation_id="prune_model_install_jobs",
-    responses={
-        204: {"description": "All completed and errored jobs have been pruned"},
-        400: {"description": "Bad request"},
-    },
-)
-async def prune_model_install_jobs() -> Response:
-    """Prune all completed and errored jobs from the install job list."""
-    ApiDependencies.invoker.services.model_install.prune_jobs()
-    return Response(status_code=204)
-
-
-@model_records_router.patch(
-    "/sync",
-    operation_id="sync_models_to_config",
-    responses={
-        204: {"description": "Model config record database resynced with files on disk"},
-        400: {"description": "Bad request"},
-    },
-)
-async def sync_models_to_config() -> Response:
-    """
-    Traverse the models and autoimport directories.
-
-    Model files without a corresponding
-    record in the database are added. Orphan records without a models file are deleted.
-    """
-    ApiDependencies.invoker.services.model_install.sync_to_config()
-    return Response(status_code=204)
-
-
-@model_records_router.put(
-    "/merge",
-    operation_id="merge",
-)
-async def merge(
-    keys: List[str] = Body(description="Keys for two to three models to merge", min_length=2, max_length=3),
-    merged_model_name: Optional[str] = Body(description="Name of destination model", default=None),
-    alpha: float = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-    force: bool = Body(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    ),
-    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method", default=None),
-    merge_dest_directory: Optional[str] = Body(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    ),
-) -> AnyModelConfig:
-    """
-    Merge diffusers models.
-
-        keys: List of 2-3 model keys to merge together. All models must use the same base type.
-        merged_model_name: Name for the merged model [Concat model names]
-        alpha: Alpha value (0.0-1.0). Higher values give more weight to the second model [0.5]
-        force: If true, force the merge even if the models were generated by different versions of the diffusers library [False]
-        interp: Interpolation method. One of "weighted_sum", "sigmoid", "inv_sigmoid" or "add_difference" [weighted_sum]
-        merge_dest_directory: Specify a directory to store the merged model in [models directory]
-    """
-    print(f"here i am, keys={keys}")
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Merging models: {keys} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
-        dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-        installer = ApiDependencies.invoker.services.model_install
-        merger = ModelMerger(installer)
-        model_names = [installer.record_store.get_model(x).name for x in keys]
-        response = merger.merge_diffusion_models_and_save(
-            model_keys=keys,
-            merged_model_name=merged_model_name or "+".join(model_names),
-            alpha=alpha,
-            interp=interp,
-            force=force,
-            merge_dest_directory=dest,
-        )
-    except UnknownModelException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{keys}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/routers/models.py

@@ -1,427 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2023 Lincoln D. Stein
-
-import pathlib
-from typing import Annotated, List, Literal, Optional, Union
-
-from fastapi import Body, Path, Query, Response
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
-from starlette.exceptions import HTTPException
-
-from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management import MergeInterpolationMethod
-from invokeai.backend.model_management.models import (
-    OPENAPI_MODEL_CONFIGS,
-    InvalidModelException,
-    ModelNotFoundException,
-    SchedulerPredictionType,
-)
-
-from ..dependencies import ApiDependencies
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
-
-ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
-
-ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
-
-MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
-
-
-class ModelsList(BaseModel):
-    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
-
-    model_config = ConfigDict(use_enum_values=True)
-
-
-ModelsListValidator = TypeAdapter(ModelsList)
-
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList}},
-)
-async def list_models(
-    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
-    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
-) -> ModelsList:
-    """Gets a list of models"""
-    if base_models and len(base_models) > 0:
-        models_raw = []
-        for base_model in base_models:
-            models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
-    else:
-        models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
-    models = ModelsListValidator.validate_python({"models": models_raw})
-    return models
-
-
-@models_router.patch(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="update_model",
-    responses={
-        200: {"description": "The model was updated successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "The model could not be found"},
-        409: {"description": "There is already a model corresponding to the new name"},
-    },
-    status_code=200,
-    response_model=UpdateModelResponse,
-)
-async def update_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> UpdateModelResponse:
-    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        previous_info = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-
-        # rename operation requested
-        if info.model_name != model_name or info.base_model != base_model:
-            ApiDependencies.invoker.services.model_manager.rename_model(
-                base_model=base_model,
-                model_type=model_type,
-                model_name=model_name,
-                new_name=info.model_name,
-                new_base=info.base_model,
-            )
-            logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
-            # update information to support an update of attributes
-            model_name = info.model_name
-            base_model = info.base_model
-            new_info = ApiDependencies.invoker.services.model_manager.list_model(
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-            )
-            if new_info.get("path") != previous_info.get(
-                "path"
-            ):  # model manager moved model path during rename - don't overwrite it
-                info.path = new_info.get("path")
-
-        # replace empty string values with None/null to avoid phenomenon of vae: ''
-        info_dict = info.model_dump()
-        info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
-
-        ApiDependencies.invoker.services.model_manager.update_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-            model_attributes=info_dict,
-        )
-
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        )
-        model_response = UpdateModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-    except Exception as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=400, detail=str(e))
-
-    return model_response
-
-
-@models_router.post(
-    "/import",
-    operation_id="import_model",
-    responses={
-        201: {"description": "The model imported successfully"},
-        404: {"description": "The model could not be found"},
-        415: {"description": "Unrecognized file/folder format"},
-        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def import_model(
-    location: str = Body(description="A model path, repo_id or URL to import"),
-    prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
-        default=None,
-    ),
-) -> ImportModelResponse:
-    """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
-
-    location = location.strip("\"' ")
-    items_to_import = {location}
-    prediction_types = {x.value: x for x in SchedulerPredictionType}
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-            items_to_import=items_to_import,
-            prediction_type_helper=lambda x: prediction_types.get(prediction_type),
-        )
-        info = installed_models.get(location)
-
-        if not info:
-            logger.error("Import failed")
-            raise HTTPException(status_code=415)
-
-        logger.info(f"Successfully imported {location}, got {info}")
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.name, base_model=info.base_model, model_type=info.model_type
-        )
-        return ImportModelResponseValidator.validate_python(model_raw)
-
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except InvalidModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=415)
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.post(
-    "/add",
-    operation_id="add_model",
-    responses={
-        201: {"description": "The model added successfully"},
-        404: {"description": "The model could not be found"},
-        424: {"description": "The model appeared to add successfully, but could not be found in the model manager"},
-        409: {"description": "There is already a model corresponding to this path or repo_id"},
-    },
-    status_code=201,
-    response_model=ImportModelResponse,
-)
-async def add_model(
-    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
-) -> ImportModelResponse:
-    """Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
-
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name,
-            info.base_model,
-            info.model_type,
-            model_attributes=info.model_dump(),
-        )
-        logger.info(f"Successfully added {info.model_name}")
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.model_name,
-            base_model=info.base_model,
-            model_type=info.model_type,
-        )
-        return ImportModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-    except ValueError as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
-
-
-@models_router.delete(
-    "/{base_model}/{model_type}/{model_name}",
-    operation_id="del_model",
-    responses={
-        204: {"description": "Model deleted successfully"},
-        404: {"description": "Model not found"},
-    },
-    status_code=204,
-    response_model=None,
-)
-async def delete_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-) -> Response:
-    """Delete Model"""
-    logger = ApiDependencies.invoker.services.logger
-
-    try:
-        ApiDependencies.invoker.services.model_manager.del_model(
-            model_name, base_model=base_model, model_type=model_type
-        )
-        logger.info(f"Deleted model: {model_name}")
-        return Response(status_code=204)
-    except ModelNotFoundException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=404, detail=str(e))
-
-
-@models_router.put(
-    "/convert/{base_model}/{model_type}/{model_name}",
-    operation_id="convert_model",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Bad request"},
-        404: {"description": "Model not found"},
-    },
-    status_code=200,
-    response_model=ConvertModelResponse,
-)
-async def convert_model(
-    base_model: BaseModelType = Path(description="Base model"),
-    model_type: ModelType = Path(description="The type of model"),
-    model_name: str = Path(description="model name"),
-    convert_dest_directory: Optional[str] = Query(
-        default=None, description="Save the converted model to the designated directory"
-    ),
-) -> ConvertModelResponse:
-    """Convert a checkpoint model into a diffusers model, optionally saving to the indicated destination directory, or `models` if none."""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(f"Converting model: {model_name}")
-        dest = pathlib.Path(convert_dest_directory) if convert_dest_directory else None
-        ApiDependencies.invoker.services.model_manager.convert_model(
-            model_name,
-            base_model=base_model,
-            model_type=model_type,
-            convert_dest_directory=dest,
-        )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name, base_model=base_model, model_type=model_type
-        )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException as e:
-        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response
-
-
-@models_router.get(
-    "/search",
-    operation_id="search_for_models",
-    responses={
-        200: {"description": "Directory searched successfully"},
-        404: {"description": "Invalid directory path"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def search_for_models(
-    search_path: pathlib.Path = Query(description="Directory path to search for models"),
-) -> List[pathlib.Path]:
-    if not search_path.is_dir():
-        raise HTTPException(
-            status_code=404,
-            detail=f"The search path '{search_path}' does not exist or is not directory",
-        )
-    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
-
-
-@models_router.get(
-    "/ckpt_confs",
-    operation_id="list_ckpt_configs",
-    responses={
-        200: {"description": "paths retrieved successfully"},
-    },
-    status_code=200,
-    response_model=List[pathlib.Path],
-)
-async def list_ckpt_configs() -> List[pathlib.Path]:
-    """Return a list of the legacy checkpoint configuration files stored in `ROOT/configs/stable-diffusion`, relative to ROOT."""
-    return ApiDependencies.invoker.services.model_manager.list_checkpoint_configs()
-
-
-@models_router.post(
-    "/sync",
-    operation_id="sync_to_config",
-    responses={
-        201: {"description": "synchronization successful"},
-    },
-    status_code=201,
-    response_model=bool,
-)
-async def sync_to_config() -> bool:
-    """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
-    in-memory data structures with disk data structures."""
-    ApiDependencies.invoker.services.model_manager.sync_to_config()
-    return True
-
-
-# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
-# TODO: After a few updates, see if it works inside the route operation handler?
-class MergeModelsBody(BaseModel):
-    model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
-    merged_model_name: Optional[str] = Field(description="Name of destination model")
-    alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
-    interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
-    force: Optional[bool] = Field(
-        description="Force merging of models created with different versions of diffusers",
-        default=False,
-    )
-
-    merge_dest_directory: Optional[str] = Field(
-        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
-        default=None,
-    )
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-@models_router.put(
-    "/merge/{base_model}",
-    operation_id="merge_models",
-    responses={
-        200: {"description": "Model converted successfully"},
-        400: {"description": "Incompatible models"},
-        404: {"description": "One or more models not found"},
-    },
-    status_code=200,
-    response_model=MergeModelResponse,
-)
-async def merge_models(
-    body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
-    base_model: BaseModelType = Path(description="Base model"),
-) -> MergeModelResponse:
-    """Convert a checkpoint model into a diffusers model"""
-    logger = ApiDependencies.invoker.services.logger
-    try:
-        logger.info(
-            f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
-        )
-        dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
-        result = ApiDependencies.invoker.services.model_manager.merge_models(
-            model_names=body.model_names,
-            base_model=base_model,
-            merged_model_name=body.merged_model_name or "+".join(body.model_names),
-            alpha=body.alpha,
-            interp=body.interp,
-            force=body.force,
-            merge_dest_directory=dest,
-        )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            result.name,
-            base_model=base_model,
-            model_type=ModelType.Main,
-        )
-        response = ConvertModelResponseValidator.validate_python(model_raw)
-    except ModelNotFoundException:
-        raise HTTPException(
-            status_code=404,
-            detail=f"One or more of the models '{body.model_names}' not found",
-        )
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))
-    return response

invokeai/app/api/routers/sessions.py

@@ -1,276 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-
-from fastapi import HTTPException, Path
-from fastapi.routing import APIRouter
-
-from ...services.shared.graph import GraphExecutionState
-from ..dependencies import ApiDependencies
-
-session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
-
-
-# @session_router.post(
-#     "/",
-#     operation_id="create_session",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid json"},
-#     },
-#     deprecated=True,
-# )
-# async def create_session(
-#     queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
-#     graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
-# ) -> GraphExecutionState:
-#     """Creates a new session, optionally initializing it with an invocation graph"""
-#     session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
-#     return session
-
-
-# @session_router.get(
-#     "/",
-#     operation_id="list_sessions",
-#     responses={200: {"model": PaginatedResults[GraphExecutionState]}},
-#     deprecated=True,
-# )
-# async def list_sessions(
-#     page: int = Query(default=0, description="The page of results to get"),
-#     per_page: int = Query(default=10, description="The number of results per page"),
-#     query: str = Query(default="", description="The query string to search for"),
-# ) -> PaginatedResults[GraphExecutionState]:
-#     """Gets a list of sessions, optionally searching"""
-#     if query == "":
-#         result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
-#     else:
-#         result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
-#     return result
-
-
-@session_router.get(
-    "/{session_id}",
-    operation_id="get_session",
-    responses={
-        200: {"model": GraphExecutionState},
-        404: {"description": "Session not found"},
-    },
-)
-async def get_session(
-    session_id: str = Path(description="The id of the session to get"),
-) -> GraphExecutionState:
-    """Gets a session"""
-    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-    if session is None:
-        raise HTTPException(status_code=404)
-    else:
-        return session
-
-
-# @session_router.post(
-#     "/{session_id}/nodes",
-#     operation_id="add_node",
-#     responses={
-#         200: {"model": str},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def add_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-#         description="The node to add"
-#     ),
-# ) -> str:
-#     """Adds a node to the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.add_node(node)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session.id
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.put(
-#     "/{session_id}/nodes/{node_path}",
-#     operation_id="update_node",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def update_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node_path: str = Path(description="The path to the node in the graph"),
-#     node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
-#         description="The new node"
-#     ),
-# ) -> GraphExecutionState:
-#     """Updates a node in the graph and removes all linked edges"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.update_node(node_path, node)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.delete(
-#     "/{session_id}/nodes/{node_path}",
-#     operation_id="delete_node",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def delete_node(
-#     session_id: str = Path(description="The id of the session"),
-#     node_path: str = Path(description="The path to the node to delete"),
-# ) -> GraphExecutionState:
-#     """Deletes a node in the graph and removes all linked edges"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.delete_node(node_path)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.post(
-#     "/{session_id}/edges",
-#     operation_id="add_edge",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def add_edge(
-#     session_id: str = Path(description="The id of the session"),
-#     edge: Edge = Body(description="The edge to add"),
-# ) -> GraphExecutionState:
-#     """Adds an edge to the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         session.add_edge(edge)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# # TODO: the edge being in the path here is really ugly, find a better solution
-# @session_router.delete(
-#     "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
-#     operation_id="delete_edge",
-#     responses={
-#         200: {"model": GraphExecutionState},
-#         400: {"description": "Invalid node or link"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def delete_edge(
-#     session_id: str = Path(description="The id of the session"),
-#     from_node_id: str = Path(description="The id of the node the edge is coming from"),
-#     from_field: str = Path(description="The field of the node the edge is coming from"),
-#     to_node_id: str = Path(description="The id of the node the edge is going to"),
-#     to_field: str = Path(description="The field of the node the edge is going to"),
-# ) -> GraphExecutionState:
-#     """Deletes an edge from the graph"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     try:
-#         edge = Edge(
-#             source=EdgeConnection(node_id=from_node_id, field=from_field),
-#             destination=EdgeConnection(node_id=to_node_id, field=to_field),
-#         )
-#         session.delete_edge(edge)
-#         ApiDependencies.invoker.services.graph_execution_manager.set(
-#             session
-#         )  # TODO: can this be done automatically, or add node through an API?
-#         return session
-#     except NodeAlreadyExecutedError:
-#         raise HTTPException(status_code=400)
-#     except IndexError:
-#         raise HTTPException(status_code=400)
-
-
-# @session_router.put(
-#     "/{session_id}/invoke",
-#     operation_id="invoke_session",
-#     responses={
-#         200: {"model": None},
-#         202: {"description": "The invocation is queued"},
-#         400: {"description": "The session has no invocations ready to invoke"},
-#         404: {"description": "Session not found"},
-#     },
-#     deprecated=True,
-# )
-# async def invoke_session(
-#     queue_id: str = Query(description="The id of the queue to associate the session with"),
-#     session_id: str = Path(description="The id of the session to invoke"),
-#     all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
-# ) -> Response:
-#     """Invokes a session"""
-#     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
-#     if session is None:
-#         raise HTTPException(status_code=404)
-
-#     if session.is_complete():
-#         raise HTTPException(status_code=400)
-
-#     ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
-#     return Response(status_code=202)
-
-
-# @session_router.delete(
-#     "/{session_id}/invoke",
-#     operation_id="cancel_session_invoke",
-#     responses={202: {"description": "The invocation is canceled"}},
-#     deprecated=True,
-# )
-# async def cancel_session_invoke(
-#     session_id: str = Path(description="The id of the session to cancel"),
-# ) -> Response:
-#     """Invokes a session"""
-#     ApiDependencies.invoker.cancel(session_id)
-#     return Response(status_code=202)

invokeai/app/api/sockets.py

@@ -12,16 +12,26 @@ class SocketIO:
     __sio: AsyncServer
     __app: ASGIApp
 
+    __sub_queue: str = "subscribe_queue"
+    __unsub_queue: str = "unsubscribe_queue"
+
+    __sub_bulk_download: str = "subscribe_bulk_download"
+    __unsub_bulk_download: str = "unsubscribe_bulk_download"
+
     def __init__(self, app: FastAPI):
         self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
         self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="/ws/socket.io")
         app.mount("/ws", self.__app)
 
-        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
-        self.__sio.on("unsubscribe_queue", handler=self._handle_unsub_queue)
+        self.__sio.on(self.__sub_queue, handler=self._handle_sub_queue)
+        self.__sio.on(self.__unsub_queue, handler=self._handle_unsub_queue)
         local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
         local_handler.register(event_name=EventServiceBase.model_event, _func=self._handle_model_event)
 
+        self.__sio.on(self.__sub_bulk_download, handler=self._handle_sub_bulk_download)
+        self.__sio.on(self.__unsub_bulk_download, handler=self._handle_unsub_bulk_download)
+        local_handler.register(event_name=EventServiceBase.bulk_download_event, _func=self._handle_bulk_download_event)
+
     async def _handle_queue_event(self, event: Event):
         await self.__sio.emit(
             event=event[1]["event"],
@@ -39,3 +49,18 @@ class SocketIO:
 
     async def _handle_model_event(self, event: Event) -> None:
         await self.__sio.emit(event=event[1]["event"], data=event[1]["data"])
+
+    async def _handle_bulk_download_event(self, event: Event):
+        await self.__sio.emit(
+            event=event[1]["event"],
+            data=event[1]["data"],
+            room=event[1]["data"]["bulk_download_id"],
+        )
+
+    async def _handle_sub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.enter_room(sid, data["bulk_download_id"])
+
+    async def _handle_unsub_bulk_download(self, sid, data, *args, **kwargs):
+        if "bulk_download_id" in data:
+            await self.__sio.leave_room(sid, data["bulk_download_id"])

invokeai/app/api_app.py

@@ -1,81 +1,84 @@
-# parse_args() must be called before any other imports. if it is not called first, consumers of the config
-# which are imported/used before parse_args() is called will get the default config values instead of the
-# values from the command line or config file.
-import sys
+import asyncio
+import mimetypes
+import socket
+from contextlib import asynccontextmanager
+from inspect import signature
+from pathlib import Path
+from typing import Any
 
+import uvicorn
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.middleware.gzip import GZipMiddleware
+from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
+from fastapi.openapi.utils import get_openapi
+from fastapi.responses import HTMLResponse
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.middleware import EventHandlerASGIMiddleware
+from pydantic.json_schema import models_json_schema
+from torch.backends.mps import is_available as is_mps_available
+
+# for PyCharm:
+# noinspection PyUnresolvedReferences
+import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
+import invokeai.frontend.web as web_dir
 from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
-from invokeai.version.invokeai_version import __version__
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.services.config.config_default import get_config
+from invokeai.app.services.session_processor.session_processor_common import ProgressImage
 
+from ..backend.util.logging import InvokeAILogger
+from .api.dependencies import ApiDependencies
+from .api.routers import (
+    app_info,
+    board_images,
+    boards,
+    download_queue,
+    images,
+    model_manager,
+    session_queue,
+    utilities,
+    workflows,
+)
+from .api.sockets import SocketIO
+from .invocations.baseinvocation import (
+    BaseInvocation,
+    UIConfigBase,
+)
 from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
-from .services.config import InvokeAIAppConfig
 
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
-if app_config.version:
-    print(f"InvokeAI version {__version__}")
-    sys.exit(0)
-
-if True:  # hack to make flake8 happy with imports coming after setting up the config
-    import asyncio
-    import mimetypes
-    import socket
-    from inspect import signature
-    from pathlib import Path
-    from typing import Any
-
-    import uvicorn
-    from fastapi import FastAPI
-    from fastapi.middleware.cors import CORSMiddleware
-    from fastapi.middleware.gzip import GZipMiddleware
-    from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
-    from fastapi.openapi.utils import get_openapi
-    from fastapi.responses import HTMLResponse
-    from fastapi_events.handlers.local import local_handler
-    from fastapi_events.middleware import EventHandlerASGIMiddleware
-    from pydantic.json_schema import models_json_schema
-    from torch.backends.mps import is_available as is_mps_available
-
-    # for PyCharm:
-    # noinspection PyUnresolvedReferences
-    import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
-    import invokeai.frontend.web as web_dir
-
-    from ..backend.util.logging import InvokeAILogger
-    from .api.dependencies import ApiDependencies
-    from .api.routers import (
-        app_info,
-        board_images,
-        boards,
-        download_queue,
-        images,
-        model_records,
-        models,
-        session_queue,
-        sessions,
-        utilities,
-        workflows,
-    )
-    from .api.sockets import SocketIO
-    from .invocations.baseinvocation import (
-        BaseInvocation,
-        UIConfigBase,
-    )
-
-    if is_mps_available():
-        import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
+app_config = get_config()
+
+
+if is_mps_available():
+    import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
 
 
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
 logger = InvokeAILogger.get_logger(config=app_config)
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # Add startup event to load dependencies
+    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
+    yield
+    # Shut down threads
+    ApiDependencies.shutdown()
+
+
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
-app = FastAPI(title="Invoke - Community Edition", docs_url=None, redoc_url=None, separate_input_output_schemas=False)
+app = FastAPI(
+    title="Invoke - Community Edition",
+    docs_url=None,
+    redoc_url=None,
+    separate_input_output_schemas=False,
+    lifespan=lifespan,
+)
 
 # Add event handler
 event_handler_id: int = id(app)
@@ -98,24 +101,9 @@ app.add_middleware(
 app.add_middleware(GZipMiddleware, minimum_size=1000)
 
 
-# Add startup event to load dependencies
-@app.on_event("startup")
-async def startup_event() -> None:
-    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
-
-
-# Shut down threads
-@app.on_event("shutdown")
-async def shutdown_event() -> None:
-    ApiDependencies.shutdown()
-
-
 # Include all routers
-app.include_router(sessions.session_router, prefix="/api")
-
 app.include_router(utilities.utilities_router, prefix="/api")
-app.include_router(models.models_router, prefix="/api")
-app.include_router(model_records.model_records_router, prefix="/api")
+app.include_router(model_manager.model_manager_router, prefix="/api")
 app.include_router(download_queue.download_queue_router, prefix="/api")
 app.include_router(images.images_router, prefix="/api")
 app.include_router(boards.boards_router, prefix="/api")
@@ -153,18 +141,22 @@ def custom_openapi() -> dict[str, Any]:
         # TODO: note that we assume the schema_key here is the TYPE.__name__
         # This could break in some cases, figure out a better way to do it
         output_type_titles[schema_key] = output_schema["title"]
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
+        openapi_schema["components"]["schemas"][schema_key]["class"] = "output"
 
-    # Add Node Editor UI helper schemas
-    ui_config_schemas = models_json_schema(
+    # Some models don't end up in the schemas as standalone definitions
+    additional_schemas = models_json_schema(
         [
             (UIConfigBase, "serialization"),
             (InputFieldJSONSchemaExtra, "serialization"),
             (OutputFieldJSONSchemaExtra, "serialization"),
+            (ModelIdentifierField, "serialization"),
+            (ProgressImage, "serialization"),
         ],
         ref_template="#/components/schemas/{model}",
     )
-    for schema_key, ui_config_schema in ui_config_schemas[1]["$defs"].items():
-        openapi_schema["components"]["schemas"][schema_key] = ui_config_schema
+    for schema_key, schema_json in additional_schemas[1]["$defs"].items():
+        openapi_schema["components"]["schemas"][schema_key] = schema_json
 
     # Add a reference to the output type to additionalProperties of the invoker schema
     for invoker in all_invocations:
@@ -175,23 +167,24 @@ def custom_openapi() -> dict[str, Any]:
         outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
         invoker_schema["output"] = outputs_ref
         invoker_schema["class"] = "invocation"
-        openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
 
-    from invokeai.backend.model_management.models import get_model_config_enums
+    # This code no longer seems to be necessary?
+    # Leave it here just in case
+    #
+    # from invokeai.backend.model_manager import get_model_config_formats
+    # formats = get_model_config_formats()
+    # for model_config_name, enum_set in formats.items():
 
-    for model_config_format_enum in set(get_model_config_enums()):
-        name = model_config_format_enum.__qualname__
+    #     if model_config_name in openapi_schema["components"]["schemas"]:
+    #         # print(f"Config with name {name} already defined")
+    #         continue
 
-        if name in openapi_schema["components"]["schemas"]:
-            # print(f"Config with name {name} already defined")
-            continue
-
-        openapi_schema["components"]["schemas"][name] = {
-            "title": name,
-            "description": "An enumeration.",
-            "type": "string",
-            "enum": [v.value for v in model_config_format_enum],
-        }
+    #     openapi_schema["components"]["schemas"][model_config_name] = {
+    #         "title": model_config_name,
+    #         "description": "An enumeration.",
+    #         "type": "string",
+    #         "enum": [v.value for v in enum_set],
+    #     }
 
     app.openapi_schema = openapi_schema
     return app.openapi_schema
@@ -240,9 +233,9 @@ def invoke_api() -> None:
             else:
                 return port
 
-    from invokeai.backend.install.check_root import check_invokeai_root
+    from invokeai.backend.install.check_directories import check_directories
 
-    check_invokeai_root(app_config)  # note, may exit with an exception if root not set up
+    check_directories(app_config)  # note, may exit with an exception if root not set up
 
     if app_config.dev_reload:
         try:

invokeai/app/invocations/__init__.py

@@ -3,9 +3,9 @@ import sys
 from importlib.util import module_from_spec, spec_from_file_location
 from pathlib import Path
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.config.config_default import get_config
 
-custom_nodes_path = Path(InvokeAIAppConfig.get_config().custom_nodes_path.resolve())
+custom_nodes_path = Path(get_config().custom_nodes_path)
 custom_nodes_path.mkdir(parents=True, exist_ok=True)
 
 custom_nodes_init_path = str(custom_nodes_path / "__init__.py")

invokeai/app/invocations/baseinvocation.py

@@ -8,19 +8,32 @@ import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
-from types import UnionType
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union, cast
+from typing import (
+    TYPE_CHECKING,
+    Annotated,
+    Any,
+    Callable,
+    ClassVar,
+    Iterable,
+    Literal,
+    Optional,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
 
 import semver
-from pydantic import BaseModel, ConfigDict, Field, create_model
+from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, create_model
 from pydantic.fields import FieldInfo
 from pydantic_core import PydanticUndefined
+from typing_extensions import TypeAliasType
 
 from invokeai.app.invocations.fields import (
     FieldKind,
     Input,
 )
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.services.config.config_default import get_config
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
@@ -84,6 +97,7 @@ class BaseInvocationOutput(BaseModel):
     """
 
     _output_classes: ClassVar[set[BaseInvocationOutput]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def register_output(cls, output: BaseInvocationOutput) -> None:
@@ -96,10 +110,14 @@ class BaseInvocationOutput(BaseModel):
         return cls._output_classes
 
     @classmethod
-    def get_outputs_union(cls) -> UnionType:
-        """Gets a union of all invocation outputs."""
-        outputs_union = Union[tuple(cls._output_classes)]  # type: ignore [valid-type]
-        return outputs_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation output types."""
+        if not cls._typeadapter:
+            InvocationOutputsUnion = TypeAliasType(
+                "InvocationOutputsUnion", Annotated[Union[tuple(cls._output_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationOutputsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_output_types(cls) -> Iterable[str]:
@@ -148,6 +166,7 @@ class BaseInvocation(ABC, BaseModel):
     """
 
     _invocation_classes: ClassVar[set[BaseInvocation]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def get_type(cls) -> str:
@@ -160,15 +179,19 @@ class BaseInvocation(ABC, BaseModel):
         cls._invocation_classes.add(invocation)
 
     @classmethod
-    def get_invocations_union(cls) -> UnionType:
-        """Gets a union of all invocation types."""
-        invocations_union = Union[tuple(cls._invocation_classes)]  # type: ignore [valid-type]
-        return invocations_union  # type: ignore [return-value]
+    def get_typeadapter(cls) -> TypeAdapter[Any]:
+        """Gets a pydantc TypeAdapter for the union of all invocation types."""
+        if not cls._typeadapter:
+            InvocationsUnion = TypeAliasType(
+                "InvocationsUnion", Annotated[Union[tuple(cls._invocation_classes)], Field(discriminator="type")]
+            )
+            cls._typeadapter = TypeAdapter(InvocationsUnion)
+        return cls._typeadapter
 
     @classmethod
     def get_invocations(cls) -> Iterable[BaseInvocation]:
         """Gets all invocations, respecting the allowlist and denylist."""
-        app_config = InvokeAIAppConfig.get_config()
+        app_config = get_config()
         allowed_invocations: set[BaseInvocation] = set()
         for sc in cls._invocation_classes:
             invocation_type = sc.get_type()

invokeai/app/invocations/compel.py

@@ -1,36 +1,26 @@
-from typing import List, Optional, Union
+from typing import Iterator, List, Optional, Tuple, Union, cast
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
+from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
-from invokeai.app.invocations.fields import (
-    FieldDescriptions,
-    Input,
-    InputField,
-    OutputField,
-    UIComponent,
-)
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIComponent
 from invokeai.app.invocations.primitives import ConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.ti_utils import generate_ti_list
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ConditioningFieldData,
     ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
+from invokeai.backend.util.devices import torch_dtype
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
-from ...backend.util.devices import torch_dtype
-from ..util.ti_utils import extract_ti_triggers_from_prompt
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
-from .model import ClipField
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from .model import CLIPField
 
 # unconditioned: Optional[torch.Tensor]
 
@@ -56,7 +46,7 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.compel_prompt,
         ui_component=UIComponent.Textarea,
     )
-    clip: ClipField = InputField(
+    clip: CLIPField = InputField(
         title="CLIP",
         description=FieldDescriptions.clip,
         input=Input.Connection,
@@ -64,40 +54,27 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.models.load(**self.clip.tokenizer.model_dump())
-        text_encoder_info = context.models.load(**self.clip.text_encoder.model_dump())
+        tokenizer_info = context.models.load(self.clip.tokenizer)
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(self.clip.text_encoder)
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, CLIPTextModel)
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
-                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(lora.lora)
+                assert isinstance(lora_info.model, LoRAModelRaw)
+                yield (lora_info.model, lora.weight)
                 del lora_info
             return
 
         # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in extract_ti_triggers_from_prompt(self.prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.models.load(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(self.prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -105,8 +82,9 @@ class CompelInvocation(BaseInvocation):
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, self.clip.skipped_layers),
         ):
+            assert isinstance(text_encoder, CLIPTextModel)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -144,28 +122,35 @@ class CompelInvocation(BaseInvocation):
 
 
 class SDXLPromptInvocationBase:
+    """Prompt processor for SDXL models."""
+
     def run_clip_compel(
         self,
         context: InvocationContext,
-        clip_field: ClipField,
+        clip_field: CLIPField,
         prompt: str,
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ):
-        tokenizer_info = context.models.load(**clip_field.tokenizer.model_dump())
-        text_encoder_info = context.models.load(**clip_field.text_encoder.model_dump())
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+        tokenizer_info = context.models.load(clip_field.tokenizer)
+        tokenizer_model = tokenizer_info.model
+        assert isinstance(tokenizer_model, CLIPTokenizer)
+        text_encoder_info = context.models.load(clip_field.text_encoder)
+        text_encoder_model = text_encoder_info.model
+        assert isinstance(text_encoder_model, (CLIPTextModel, CLIPTextModelWithProjection))
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.context.model
+            cpu_text_encoder = text_encoder_info.model
+            assert isinstance(cpu_text_encoder, torch.nn.Module)
             c = torch.zeros(
                 (
                     1,
                     cpu_text_encoder.config.max_position_embeddings,
                     cpu_text_encoder.config.hidden_size,
                 ),
-                dtype=text_encoder_info.context.cache.precision,
+                dtype=cpu_text_encoder.dtype,
             )
             if get_pooled:
                 c_pooled = torch.zeros(
@@ -176,37 +161,21 @@ class SDXLPromptInvocationBase:
                 c_pooled = None
             return c, c_pooled, None
 
-        def _lora_loader():
+        def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
-                lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
-                yield (lora_info.context.model, lora.weight)
+                lora_info = context.models.load(lora.lora)
+                lora_model = lora_info.model
+                assert isinstance(lora_model, LoRAModelRaw)
+                yield (lora_model, lora.weight)
                 del lora_info
             return
 
         # loras = [(context.models.get(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
-        ti_list = []
-        for trigger in extract_ti_triggers_from_prompt(prompt):
-            name = trigger[1:-1]
-            try:
-                ti_list.append(
-                    (
-                        name,
-                        context.models.load(
-                            model_name=name,
-                            base_model=clip_field.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        ti_list = generate_ti_list(prompt, text_encoder_info.config.base, context)
 
         with (
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            ModelPatcher.apply_ti(tokenizer_model, text_encoder_model, ti_list) as (
                 tokenizer,
                 ti_manager,
             ),
@@ -214,8 +183,10 @@ class SDXLPromptInvocationBase:
             # Apply the LoRA after text_encoder has been moved to its target device for faster patching.
             ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
+            ModelPatcher.apply_clip_skip(text_encoder_model, clip_field.skipped_layers),
         ):
+            assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
+            text_encoder = cast(CLIPTextModel, text_encoder)
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -282,8 +253,8 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     crop_left: int = InputField(default=0, description="")
     target_width: int = InputField(default=1024, description="")
     target_height: int = InputField(default=1024, description="")
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
+    clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -332,6 +303,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -368,7 +340,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     crop_top: int = InputField(default=0, description="")
     crop_left: int = InputField(default=0, description="")
     aesthetic_score: float = InputField(default=6.0, description=FieldDescriptions.sdxl_aesthetic)
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
+    clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -380,6 +352,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -397,10 +370,10 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
 
 @invocation_output("clip_skip_output")
-class ClipSkipInvocationOutput(BaseInvocationOutput):
-    """Clip skip node output"""
+class CLIPSkipInvocationOutput(BaseInvocationOutput):
+    """CLIP skip node output"""
 
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
 @invocation(
@@ -410,23 +383,23 @@ class ClipSkipInvocationOutput(BaseInvocationOutput):
     category="conditioning",
     version="1.0.0",
 )
-class ClipSkipInvocation(BaseInvocation):
+class CLIPSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
-    skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
+    clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
+    skipped_layers: int = InputField(default=0, ge=0, description=FieldDescriptions.skipped_layers)
 
-    def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
+    def invoke(self, context: InvocationContext) -> CLIPSkipInvocationOutput:
         self.clip.skipped_layers += self.skipped_layers
-        return ClipSkipInvocationOutput(
+        return CLIPSkipInvocationOutput(
             clip=self.clip,
         )
 
 
 def get_max_token_count(
-    tokenizer,
+    tokenizer: CLIPTokenizer,
     prompt: Union[FlattenedPrompt, Blend, Conjunction],
-    truncate_if_too_long=False,
+    truncate_if_too_long: bool = False,
 ) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
@@ -438,7 +411,9 @@ def get_max_token_count(
         return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> List[str]:
+def get_tokens_for_prompt_object(
+    tokenizer: CLIPTokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long: bool = True
+) -> List[str]:
     if type(parsed_prompt) is Blend:
         raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
@@ -451,24 +426,29 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
-    tokens = tokenizer.tokenize(text)
+    tokens: List[str] = tokenizer.tokenize(text)
     if truncate_if_too_long:
         max_tokens_length = tokenizer.model_max_length - 2  # typically 75
         tokens = tokens[0:max_tokens_length]
     return tokens
 
 
-def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
+def log_tokenization_for_conjunction(
+    c: Conjunction, tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
+            assert display_label_prefix is not None
             this_display_label_prefix = display_label_prefix
         log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer: CLIPTokenizer, display_label_prefix: Optional[str] = None
+) -> None:
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -508,7 +488,12 @@ def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokeniz
             log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(
+    text: str,
+    tokenizer: CLIPTokenizer,
+    display_label: Optional[str] = None,
+    truncate_if_too_long: Optional[bool] = False,
+) -> None:
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/constants.py

@@ -12,3 +12,6 @@ The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
 
 SCHEDULER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
 """A literal type representing the valid scheduler names."""
+
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+"""A literal type for PIL image modes supported by Invoke"""

invokeai/app/invocations/controlnet_image_processors.py

@@ -23,7 +23,7 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
@@ -31,22 +31,18 @@ from invokeai.app.invocations.fields import (
     Input,
     InputField,
     OutputField,
+    UIType,
     WithBoard,
     WithMetadata,
 )
+from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
 from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
-from invokeai.backend.model_management.models.base import BaseModelType
 
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -57,18 +53,9 @@ CONTROLNET_RESIZE_VALUES = Literal[
 ]
 
 
-class ControlNetModelField(BaseModel):
-    """ControlNet model field"""
-
-    model_name: str = Field(description="Name of the ControlNet model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
 class ControlField(BaseModel):
     image: ImageField = Field(description="The control image")
-    control_model: ControlNetModelField = Field(description="The ControlNet model to use")
+    control_model: ModelIdentifierField = Field(description="The ControlNet model to use")
     control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
@@ -104,7 +91,9 @@ class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
     image: ImageField = InputField(description="The control image")
-    control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
+    control_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.controlnet_model, input=Input.Direct, ui_type=UIType.ControlNetModel
+    )
     control_weight: Union[float, List[float]] = InputField(
         default=1.0, ge=-1, le=2, description="The weight given to the ControlNet"
     )
@@ -152,8 +141,12 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
         # superclass just passes through image without processing
         return image
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # allows override for any special formatting specific to the preprocessor
+        return context.images.get_pil(self.image.image_name, "RGB")
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        raw_image = context.images.get_pil(self.image.image_name)
+        raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
@@ -183,6 +176,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
 
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
     low_threshold: int = InputField(
         default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)"
     )
@@ -190,9 +184,18 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)"
     )
 
+    def load_image(self, context: InvocationContext) -> Image.Image:
+        # Keep alpha channel for Canny processing to detect edges of transparent areas
+        return context.images.get_pil(self.image.image_name, "RGBA")
+
     def run_processor(self, image):
         canny_processor = CannyDetector()
-        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
+        processed_image = canny_processor(
+            image,
+            self.low_threshold,
+            self.high_threshold,
+            image_resolution=self.image_resolution,
+        )
         return processed_image
 
 
@@ -282,6 +285,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
 
     a_mult: float = InputField(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
     bg_th: float = InputField(default=0.1, ge=0, description="Midas parameter `bg_th`")
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
     # depth_and_normal not supported in controlnet_aux v0.0.3
     # depth_and_normal: bool = InputField(default=False, description="whether to use depth and normal mode")
 
@@ -291,6 +295,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
             image,
             a=np.pi * self.a_mult,
             bg_th=self.bg_th,
+            image_resolution=self.image_resolution,
             # dept_and_normal not supported in controlnet_aux v0.0.3
             # depth_and_normal=self.depth_and_normal,
         )
@@ -422,14 +427,13 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
 
     max_faces: int = InputField(default=1, ge=1, description="Maximum number of faces to detect")
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
     def run_processor(self, image):
-        # MediaPipeFaceDetector throws an error if image has alpha channel
-        #     so convert to RGB if needed
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
         mediapipe_face_processor = MediapipeFaceDetector()
-        processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
+        processed_image = mediapipe_face_processor(
+            image, max_faces=self.max_faces, min_confidence=self.min_confidence, image_resolution=self.image_resolution
+        )
         return processed_image
 
 
@@ -512,13 +516,15 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
 
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
             "ybelkada/segment-anything", subfolder="checkpoints"
         )
         np_img = np.array(image, dtype=np.uint8)
-        processed_image = segment_anything_processor(np_img)
+        processed_image = segment_anything_processor(np_img, image_resolution=self.image_resolution)
         return processed_image
 
 
@@ -557,7 +563,6 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
 
     def run_processor(self, image: Image.Image):
-        image = image.convert("RGB")
         np_image = np.array(image, dtype=np.uint8)
         height, width = np_image.shape[:2]
 
@@ -582,7 +587,7 @@ DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
     title="Depth Anything Processor",
     tags=["controlnet", "depth", "depth anything"],
     category="controlnet",
-    version="1.0.0",
+    version="1.0.1",
 )
 class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a depth map based on the Depth Anything algorithm"""
@@ -591,16 +596,12 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
         default="small", description="The size of the depth model to use"
     )
     resolution: int = InputField(default=512, ge=64, multiple_of=64, description=FieldDescriptions.image_res)
-    offload: bool = InputField(default=False)
 
     def run_processor(self, image: Image.Image):
         depth_anything_detector = DepthAnythingDetector()
         depth_anything_detector.load_model(model_size=self.model_size)
 
-        if image.mode == "RGBA":
-            image = image.convert("RGB")
-
-        processed_image = depth_anything_detector(image=image, resolution=self.resolution, offload=self.offload)
+        processed_image = depth_anything_detector(image=image, resolution=self.resolution)
         return processed_image
 
 
@@ -619,7 +620,7 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     draw_hands: bool = InputField(default=False)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image):
         dw_openpose = DWOpenposeDetector()
         processed_image = dw_openpose(
             image,

invokeai/app/invocations/fields.py

@@ -39,13 +39,15 @@ class UIType(str, Enum, metaclass=MetaEnum):
     """
 
     # region Model Field Types
+    MainModel = "MainModelField"
     SDXLMainModel = "SDXLMainModelField"
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
+    VAEModel = "VAEModelField"
     LoRAModel = "LoRAModelField"
     ControlNetModel = "ControlNetModelField"
     IPAdapterModel = "IPAdapterModelField"
+    T2IAdapterModel = "T2IAdapterModelField"
     # endregion
 
     # region Misc Field Types
@@ -86,7 +88,6 @@ class UIType(str, Enum, metaclass=MetaEnum):
     IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
     LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
     StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
     UNet = "DEPRECATED_UNet"
     Vae = "DEPRECATED_Vae"
     CLIP = "DEPRECATED_CLIP"
@@ -199,6 +200,7 @@ class DenoiseMaskField(BaseModel):
 
     mask_name: str = Field(description="The name of the mask image")
     masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
+    gradient: bool = Field(default=False, description="Used for gradient inpainting")
 
 
 class LatentsField(BaseModel):
@@ -227,7 +229,7 @@ class ConditioningField(BaseModel):
     # endregion
 
 
-class MetadataField(RootModel):
+class MetadataField(RootModel[dict[str, Any]]):
     """
     Pydantic model for metadata with custom root of type dict[str, Any].
     Metadata is stored without a strict schema.

invokeai/app/invocations/image.py

@@ -7,6 +7,7 @@ import cv2
 import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
+from invokeai.app.invocations.constants import IMAGE_MODES
 from invokeai.app.invocations.fields import (
     ColorField,
     FieldDescriptions,
@@ -21,11 +22,7 @@ from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
-from .baseinvocation import (
-    BaseInvocation,
-    Classification,
-    invocation,
-)
+from .baseinvocation import BaseInvocation, Classification, invocation
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.1")
@@ -263,9 +260,6 @@ class ImageChannelInvocation(BaseInvocation, WithMetadata, WithBoard):
         return ImageOutput.build(image_dto)
 
 
-IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
-
-
 @invocation(
     "img_conv",
     title="Convert Image Mode",
@@ -936,3 +930,40 @@ class SaveImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         image_dto = context.images.save(image=image)
 
         return ImageOutput.build(image_dto)
+
+
+@invocation(
+    "canvas_paste_back",
+    title="Canvas Paste Back",
+    tags=["image", "combine"],
+    category="image",
+    version="1.0.0",
+)
+class CanvasPasteBackInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Combines two images by using the mask provided. Intended for use on the Unified Canvas."""
+
+    source_image: ImageField = InputField(description="The source image")
+    target_image: ImageField = InputField(default=None, description="The target image")
+    mask: ImageField = InputField(
+        description="The mask to use when pasting",
+    )
+    mask_blur: int = InputField(default=0, ge=0, description="The amount to blur the mask by")
+
+    def _prepare_mask(self, mask: Image.Image) -> Image.Image:
+        mask_array = numpy.array(mask)
+        kernel = numpy.ones((self.mask_blur, self.mask_blur), numpy.uint8)
+        dilated_mask_array = cv2.erode(mask_array, kernel, iterations=3)
+        dilated_mask = Image.fromarray(dilated_mask_array)
+        if self.mask_blur > 0:
+            mask = dilated_mask.filter(ImageFilter.GaussianBlur(self.mask_blur))
+        return ImageOps.invert(mask.convert("L"))
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        source_image = context.images.get_pil(self.source_image.image_name)
+        target_image = context.images.get_pil(self.target_image.image_name)
+        mask = self._prepare_mask(context.images.get_pil(self.mask.image_name))
+
+        source_image.paste(target_image, (0, 0), mask)
+
+        image_dto = context.images.save(image=source_image)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -1,8 +1,8 @@
-import os
 from builtins import float
 from typing import List, Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
+from typing_extensions import Self
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -10,32 +10,18 @@ from invokeai.app.invocations.baseinvocation import (
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
-
-
-class IPAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the IP-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-class CLIPVisionModelField(BaseModel):
-    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
-    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
-
-    model_config = ConfigDict(protected_namespaces=())
+from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, IPAdapterConfig, ModelType
 
 
 class IPAdapterField(BaseModel):
     image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
-    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
-    image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
+    ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model to use.")
+    image_encoder_model: ModelIdentifierField = Field(description="The name of the CLIP image encoder model.")
     weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
@@ -46,12 +32,12 @@ class IPAdapterField(BaseModel):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
@@ -68,8 +54,12 @@ class IPAdapterInvocation(BaseInvocation):
 
     # Inputs
     image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
-    ip_adapter_model: IPAdapterModelField = InputField(
-        description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
+    ip_adapter_model: ModelIdentifierField = InputField(
+        description="The IP-Adapter model.",
+        title="IP-Adapter Model",
+        input=Input.Direct,
+        ui_order=-1,
+        ui_type=UIType.IPAdapterModel,
     )
 
     weight: Union[float, List[float]] = InputField(
@@ -84,40 +74,47 @@ class IPAdapterInvocation(BaseInvocation):
 
     @field_validator("weight")
     @classmethod
-    def validate_ip_adapter_weight(cls, v):
+    def validate_ip_adapter_weight(cls, v: float) -> float:
         validate_weights(v)
         return v
 
     @model_validator(mode="after")
-    def validate_begin_end_step_percent(self):
+    def validate_begin_end_step_percent(self) -> Self:
         validate_begin_end_step(self.begin_step_percent, self.end_step_percent)
         return self
 
     def invoke(self, context: InvocationContext) -> IPAdapterOutput:
         # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.models.get_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.config.get().models_path, ip_adapter_info["path"])
-        )
+        ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
+        assert isinstance(ip_adapter_info, IPAdapterConfig)
+        image_encoder_model_id = ip_adapter_info.image_encoder_model_id
         image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_model = CLIPVisionModelField(
-            model_name=image_encoder_model_name,
-            base_model=BaseModelType.Any,
-        )
+        image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,
                 ip_adapter_model=self.ip_adapter_model,
-                image_encoder_model=image_encoder_model,
+                image_encoder_model=ModelIdentifierField.from_config(image_encoder_model),
                 weight=self.weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
             ),
         )
+
+    def _get_image_encoder(self, context: InvocationContext, image_encoder_model_name: str) -> AnyModelConfig:
+        found = False
+        while not found:
+            image_encoder_models = context.models.search_by_attrs(
+                name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
+            )
+            found = len(image_encoder_models) > 0
+            if not found:
+                context.logger.warning(
+                    f"The image encoder required by this IP Adapter ({image_encoder_model_name}) is not installed."
+                )
+                context.logger.warning("Downloading and installing now. This may take a while.")
+                installer = context._services.model_manager.install
+                job = installer.heuristic_import(f"InvokeAI/{image_encoder_model_name}")
+                installer.wait_for_job(job, timeout=600)  # wait up to 10 minutes - then raise a TimeoutException
+        assert len(image_encoder_models) == 1
+        return image_encoder_models[0]

invokeai/app/invocations/latent.py

@@ -3,13 +3,15 @@
 import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
-from typing import List, Literal, Optional, Union
+from typing import Any, Iterator, List, Literal, Optional, Tuple, Union
 
 import einops
 import numpy as np
+import numpy.typing as npt
 import torch
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
+from diffusers.configuration_utils import ConfigMixin
 from diffusers.image_processor import VaeImageProcessor
 from diffusers.models.adapter import T2IAdapter
 from diffusers.models.attention_processor import (
@@ -18,10 +20,13 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
 from diffusers.schedulers import DPMSolverSDEScheduler
 from diffusers.schedulers import SchedulerMixin as Scheduler
+from PIL import Image, ImageFilter
 from pydantic import field_validator
 from torchvision.transforms.functional import resize as tv_resize
+from transformers import CLIPVisionModelWithProjection
 
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR, SCHEDULER_NAME_VALUES
 from invokeai.app.invocations.fields import (
@@ -47,13 +52,13 @@ from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-from invokeai.backend.model_management.models import ModelType, SilenceWarnings
+from invokeai.backend.lora import LoRAModelRaw
+from invokeai.backend.model_manager import BaseModelType, LoadedModel
+from invokeai.backend.model_patcher import ModelPatcher
+from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
+from invokeai.backend.util.silence_warnings import SilenceWarnings
 
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import BaseModelType
-from ...backend.model_management.seamless import set_seamless
-from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
     IPAdapterData,
@@ -61,7 +66,6 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
     T2IAdapterData,
     image_resized_to_grid_as_tensor,
 )
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from ...backend.util.devices import choose_precision, choose_torch_device
 from .baseinvocation import (
@@ -71,7 +75,7 @@ from .baseinvocation import (
     invocation_output,
 )
 from .controlnet_image_processors import ControlField
-from .model import ModelInfo, UNetField, VaeField
+from .model import ModelIdentifierField, UNetField, VAEField
 
 if choose_torch_device() == torch.device("mps"):
     from torch import mps
@@ -114,7 +118,7 @@ class SchedulerInvocation(BaseInvocation):
 class CreateDenoiseMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
 
-    vae: VaeField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
+    vae: VAEField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
     image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
     mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
     tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
@@ -124,10 +128,10 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         ui_order=4,
     )
 
-    def prep_mask_tensor(self, mask_image):
+    def prep_mask_tensor(self, mask_image: Image.Image) -> torch.Tensor:
         if mask_image.mode != "L":
             mask_image = mask_image.convert("L")
-        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
         if mask_tensor.dim() == 3:
             mask_tensor = mask_tensor.unsqueeze(0)
         # if shape is not None:
@@ -138,21 +142,21 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
             image = context.images.get_pil(self.image.image_name)
-            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image.dim() == 3:
-                image = image.unsqueeze(0)
+            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image_tensor.dim() == 3:
+                image_tensor = image_tensor.unsqueeze(0)
         else:
-            image = None
+            image_tensor = None
 
         mask = self.prep_mask_tensor(
             context.images.get_pil(self.mask.image_name),
         )
 
-        if image is not None:
-            vae_info = context.models.load(**self.vae.vae.model_dump())
+        if image_tensor is not None:
+            vae_info = context.models.load(self.vae.vae)
 
-            img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-            masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
+            img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+            masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
             # TODO:
             masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
 
@@ -165,17 +169,87 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         return DenoiseMaskOutput.build(
             mask_name=mask_name,
             masked_latents_name=masked_latents_name,
+            gradient=False,
+        )
+
+
+@invocation_output("gradient_mask_output")
+class GradientMaskOutput(BaseInvocationOutput):
+    """Outputs a denoise mask and an image representing the total gradient of the mask."""
+
+    denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
+    expanded_mask_area: ImageField = OutputField(
+        description="Image representing the total gradient area of the mask. For paste-back purposes."
+    )
+
+
+@invocation(
+    "create_gradient_mask",
+    title="Create Gradient Mask",
+    tags=["mask", "denoise"],
+    category="latents",
+    version="1.0.0",
+)
+class CreateGradientMaskInvocation(BaseInvocation):
+    """Creates mask for denoising model run."""
+
+    mask: ImageField = InputField(default=None, description="Image which will be masked", ui_order=1)
+    edge_radius: int = InputField(
+        default=16, ge=0, description="How far to blur/expand the edges of the mask", ui_order=2
+    )
+    coherence_mode: Literal["Gaussian Blur", "Box Blur", "Staged"] = InputField(default="Gaussian Blur", ui_order=3)
+    minimum_denoise: float = InputField(
+        default=0.0, ge=0, le=1, description="Minimum denoise level for the coherence region", ui_order=4
+    )
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> GradientMaskOutput:
+        mask_image = context.images.get_pil(self.mask.image_name, mode="L")
+        if self.edge_radius > 0:
+            if self.coherence_mode == "Box Blur":
+                blur_mask = mask_image.filter(ImageFilter.BoxBlur(self.edge_radius))
+            else:  # Gaussian Blur OR Staged
+                # Gaussian Blur uses standard deviation. 1/2 radius is a good approximation
+                blur_mask = mask_image.filter(ImageFilter.GaussianBlur(self.edge_radius / 2))
+
+            blur_tensor: torch.Tensor = image_resized_to_grid_as_tensor(blur_mask, normalize=False)
+
+            # redistribute blur so that the original edges are 0 and blur outwards to 1
+            blur_tensor = (blur_tensor - 0.5) * 2
+
+            threshold = 1 - self.minimum_denoise
+
+            if self.coherence_mode == "Staged":
+                # wherever the blur_tensor is less than fully masked, convert it to threshold
+                blur_tensor = torch.where((blur_tensor < 1) & (blur_tensor > 0), threshold, blur_tensor)
+            else:
+                # wherever the blur_tensor is above threshold but less than 1, drop it to threshold
+                blur_tensor = torch.where((blur_tensor > threshold) & (blur_tensor < 1), threshold, blur_tensor)
+
+        else:
+            blur_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+
+        mask_name = context.tensors.save(tensor=blur_tensor.unsqueeze(1))
+
+        # compute a [0, 1] mask from the blur_tensor
+        expanded_mask = torch.where((blur_tensor < 1), 0, 1)
+        expanded_mask_image = Image.fromarray((expanded_mask.squeeze(0).numpy() * 255).astype(np.uint8), mode="L")
+        expanded_image_dto = context.images.save(expanded_mask_image)
+
+        return GradientMaskOutput(
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=None, gradient=True),
+            expanded_mask_area=ImageField(image_name=expanded_image_dto.image_name),
         )
 
 
 def get_scheduler(
     context: InvocationContext,
-    scheduler_info: ModelInfo,
+    scheduler_info: ModelIdentifierField,
     scheduler_name: str,
     seed: int,
 ) -> Scheduler:
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.models.load(**scheduler_info.model_dump())
+    orig_scheduler_info = context.models.load(scheduler_info)
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -183,7 +257,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,
+        **scheduler_extra_config,  # FIXME
         "_backup": scheduler_config,
     }
 
@@ -196,6 +270,7 @@ def get_scheduler(
     # hack copied over from generate.py
     if not hasattr(scheduler, "uses_inpainting_model"):
         scheduler.uses_inpainting_model = lambda: False
+    assert isinstance(scheduler, Scheduler)
     return scheduler
 
 
@@ -279,7 +354,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
 
     @field_validator("cfg_scale")
-    def ge_one(cls, v):
+    def ge_one(cls, v: Union[List[float], float]) -> Union[List[float], float]:
         """validate that all cfg_scale values are >= 1"""
         if isinstance(v, list):
             for i in v:
@@ -293,13 +368,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler,
-        unet,
-        seed,
+        scheduler: Scheduler,
+        unet: UNet2DConditionModel,
+        seed: int,
     ) -> ConditioningData:
         positive_cond_data = context.conditioning.load(self.positive_conditioning.conditioning_name)
         c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
-        extra_conditioning_info = c.extra_conditioning
 
         negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
@@ -309,16 +383,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
             text_embeddings=c,
             guidance_scale=self.cfg_scale,
             guidance_rescale_multiplier=self.cfg_rescale_multiplier,
-            extra=extra_conditioning_info,
-            postprocessing_settings=PostprocessingSettings(
-                threshold=0.0,  # threshold,
-                warmup=0.2,  # warmup,
-                h_symmetry_time_pct=None,  # h_symmetry_time_pct,
-                v_symmetry_time_pct=None,  # v_symmetry_time_pct,
-            ),
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
+        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
             scheduler,
             # for ddim scheduler
             eta=0.0,  # ddim_eta
@@ -330,8 +397,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     def create_pipeline(
         self,
-        unet,
-        scheduler,
+        unet: UNet2DConditionModel,
+        scheduler: Scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -342,10 +409,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         class FakeVae:
             class FakeVaeConfig:
-                def __init__(self):
+                def __init__(self) -> None:
                     self.block_out_channels = [0]
 
-            def __init__(self):
+            def __init__(self) -> None:
                 self.config = FakeVae.FakeVaeConfig()
 
         return StableDiffusionGeneratorPipeline(
@@ -362,11 +429,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
     def prep_control_data(
         self,
         context: InvocationContext,
-        control_input: Union[ControlField, List[ControlField]],
+        control_input: Optional[Union[ControlField, List[ControlField]]],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
-    ) -> List[ControlNetData]:
+    ) -> Optional[List[ControlNetData]]:
         # Assuming fixed dimensional scaling of LATENT_SCALE_FACTOR.
         control_height_resize = latents_shape[2] * LATENT_SCALE_FACTOR
         control_width_resize = latents_shape[3] * LATENT_SCALE_FACTOR
@@ -388,13 +455,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         #        and if weight is None, populate with default 1.0?
         controlnet_data = []
         for control_info in control_list:
-            control_model = exit_stack.enter_context(
-                context.models.load(
-                    model_name=control_info.control_model.model_name,
-                    model_type=ModelType.ControlNet,
-                    base_model=control_info.control_model.base_model,
-                )
-            )
+            control_model = exit_stack.enter_context(context.models.load(control_info.control_model))
 
             # control_models.append(control_model)
             control_image_field = control_info.image
@@ -456,29 +517,21 @@ class DenoiseLatentsInvocation(BaseInvocation):
         conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
-                context.models.load(
-                    model_name=single_ip_adapter.ip_adapter_model.model_name,
-                    model_type=ModelType.IPAdapter,
-                    base_model=single_ip_adapter.ip_adapter_model.base_model,
-                )
-            )
-
-            image_encoder_model_info = context.models.load(
-                model_name=single_ip_adapter.image_encoder_model.model_name,
-                model_type=ModelType.CLIPVision,
-                base_model=single_ip_adapter.image_encoder_model.base_model,
+                context.models.load(single_ip_adapter.ip_adapter_model)
             )
 
+            image_encoder_model_info = context.models.load(single_ip_adapter.image_encoder_model)
             # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
-            single_ipa_images = single_ip_adapter.image
-            if not isinstance(single_ipa_images, list):
-                single_ipa_images = [single_ipa_images]
+            single_ipa_image_fields = single_ip_adapter.image
+            if not isinstance(single_ipa_image_fields, list):
+                single_ipa_image_fields = [single_ipa_image_fields]
 
-            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_images]
+            single_ipa_images = [context.images.get_pil(image.image_name) for image in single_ipa_image_fields]
 
             # TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
             # models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
             with image_encoder_model_info as image_encoder_model:
+                assert isinstance(image_encoder_model, CLIPVisionModelWithProjection)
                 # Get image embeddings from CLIP and ImageProjModel.
                 image_prompt_embeds, uncond_image_prompt_embeds = ip_adapter_model.get_image_embeds(
                     single_ipa_images, image_encoder_model
@@ -518,25 +571,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.models.load(
-                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
-                model_type=ModelType.T2IAdapter,
-                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
-            )
+            t2i_adapter_model_config = context.models.get_config(t2i_adapter_field.t2i_adapter_model.key)
+            t2i_adapter_loaded_model = context.models.load(t2i_adapter_field.t2i_adapter_model)
             image = context.images.get_pil(t2i_adapter_field.image.image_name)
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
-            if t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusion1:
+            if t2i_adapter_model_config.base == BaseModelType.StableDiffusion1:
                 max_unet_downscale = 8
-            elif t2i_adapter_field.t2i_adapter_model.base_model == BaseModelType.StableDiffusionXL:
+            elif t2i_adapter_model_config.base == BaseModelType.StableDiffusionXL:
                 max_unet_downscale = 4
             else:
-                raise ValueError(
-                    f"Unexpected T2I-Adapter base model type: '{t2i_adapter_field.t2i_adapter_model.base_model}'."
-                )
+                raise ValueError(f"Unexpected T2I-Adapter base model type: '{t2i_adapter_model_config.base}'.")
 
             t2i_adapter_model: T2IAdapter
-            with t2i_adapter_model_info as t2i_adapter_model:
+            with t2i_adapter_loaded_model as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
 
                 # Resize the T2I-Adapter input image.
@@ -556,7 +604,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     do_classifier_free_guidance=False,
                     width=t2i_input_width,
                     height=t2i_input_height,
-                    num_channels=t2i_adapter_model.config.in_channels,
+                    num_channels=t2i_adapter_model.config["in_channels"],  # mypy treats this as a FrozenDict
                     device=t2i_adapter_model.device,
                     dtype=t2i_adapter_model.dtype,
                     resize_mode=t2i_adapter_field.resize_mode,
@@ -581,7 +629,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
-    def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
+    def init_scheduler(
+        self,
+        scheduler: Union[Scheduler, ConfigMixin],
+        device: torch.device,
+        steps: int,
+        denoising_start: float,
+        denoising_end: float,
+    ) -> Tuple[int, List[int], int]:
+        assert isinstance(scheduler, ConfigMixin)
         if scheduler.config.get("cpu_only", False):
             scheduler.set_timesteps(steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
@@ -593,11 +649,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
         _timesteps = timesteps[:: scheduler.order]
 
         # get start timestep index
-        t_start_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_start)))
+        t_start_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_start)))
         t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, _timesteps)))
 
         # get end timestep index
-        t_end_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_end)))
+        t_end_val = int(round(scheduler.config["num_train_timesteps"] * (1 - denoising_end)))
         t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, _timesteps[t_start_idx:])))
 
         # apply order to indexes
@@ -610,18 +666,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context: InvocationContext, latents):
+    def prep_inpaint_mask(
+        self, context: InvocationContext, latents: torch.Tensor
+    ) -> Tuple[Optional[torch.Tensor], Optional[torch.Tensor], bool]:
         if self.denoise_mask is None:
-            return None, None
+            return None, None, False
 
         mask = context.tensors.load(self.denoise_mask.mask_name)
         mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
         if self.denoise_mask.masked_latents_name is not None:
             masked_latents = context.tensors.load(self.denoise_mask.masked_latents_name)
         else:
-            masked_latents = None
+            masked_latents = torch.where(mask < 0.5, 0.0, latents)
 
-        return 1 - mask, masked_latents
+        return 1 - mask, masked_latents, self.denoise_mask.gradient
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -648,7 +706,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if seed is None:
                 seed = 0
 
-            mask, masked_latents = self.prep_inpaint_mask(context, latents)
+            mask, masked_latents, gradient_mask = self.prep_inpaint_mask(context, latents)
 
             # TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
             # below. Investigate whether this is appropriate.
@@ -659,25 +717,31 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 do_classifier_free_guidance=True,
             )
 
-            def step_callback(state: PipelineIntermediateState):
-                context.util.sd_step_callback(state, self.unet.unet.base_model)
+            # get the unet's config so that we can pass the base to dispatch_progress()
+            unet_config = context.models.get_config(self.unet.unet.key)
 
-            def _lora_loader():
+            def step_callback(state: PipelineIntermediateState) -> None:
+                context.util.sd_step_callback(state, unet_config.base)
+
+            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
                 for lora in self.unet.loras:
-                    lora_info = context.models.load(**lora.model_dump(exclude={"weight"}))
-                    yield (lora_info.context.model, lora.weight)
+                    lora_info = context.models.load(lora.lora)
+                    assert isinstance(lora_info.model, LoRAModelRaw)
+                    yield (lora_info.model, lora.weight)
                     del lora_info
                 return
 
-            unet_info = context.models.load(**self.unet.unet.model_dump())
+            unet_info = context.models.load(self.unet.unet)
+            assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 ExitStack() as exit_stack,
-                ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
-                set_seamless(unet_info.context.model, self.unet.seamless_axes),
+                ModelPatcher.apply_freeu(unet_info.model, self.unet.freeu_config),
+                set_seamless(unet_info.model, self.unet.seamless_axes),  # FIXME
                 unet_info as unet,
                 # Apply the LoRA after unet has been moved to its target device for faster patching.
                 ModelPatcher.apply_lora_unet(unet, _lora_loader()),
             ):
+                assert isinstance(unet, UNet2DConditionModel)
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
@@ -720,10 +784,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     denoising_end=self.denoising_end,
                 )
 
-                (
-                    result_latents,
-                    result_attention_map_saver,
-                ) = pipeline.latents_from_embeddings(
+                result_latents = pipeline.latents_from_embeddings(
                     latents=latents,
                     timesteps=timesteps,
                     init_timestep=init_timestep,
@@ -731,6 +792,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     seed=seed,
                     mask=mask,
                     masked_latents=masked_latents,
+                    gradient_mask=gradient_mask,
                     num_inference_steps=num_inference_steps,
                     conditioning_data=conditioning_data,
                     control_data=controlnet_data,
@@ -763,7 +825,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         description=FieldDescriptions.latents,
         input=Input.Connection,
     )
-    vae: VaeField = InputField(
+    vae: VAEField = InputField(
         description=FieldDescriptions.vae,
         input=Input.Connection,
     )
@@ -774,14 +836,15 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.tensors.load(self.latents.latents_name)
 
-        vae_info = context.models.load(**self.vae.vae.model_dump())
-
-        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
+        vae_info = context.models.load(self.vae.vae)
+        assert isinstance(vae_info.model, (UNet2DConditionModel, AutoencoderKL, AutoencoderTiny))
+        with set_seamless(vae_info.model, self.vae.seamless_axes), vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
 
-                use_torch_2_0_or_xformers = isinstance(
+                use_torch_2_0_or_xformers = hasattr(vae.decoder, "mid_block") and isinstance(
                     vae.decoder.mid_block.attentions[0].processor,
                     (
                         AttnProcessor2_0,
@@ -803,7 +866,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.config.get().tiled_decode:
+            if self.tiled or context.config.get().force_tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -940,7 +1003,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     image: ImageField = InputField(
         description="The image to encode",
     )
-    vae: VaeField = InputField(
+    vae: VAEField = InputField(
         description=FieldDescriptions.vae,
         input=Input.Connection,
     )
@@ -948,13 +1011,14 @@ class ImageToLatentsInvocation(BaseInvocation):
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
     @staticmethod
-    def vae_encode(vae_info, upcast, tiled, image_tensor):
+    def vae_encode(vae_info: LoadedModel, upcast: bool, tiled: bool, image_tensor: torch.Tensor) -> torch.Tensor:
         with vae_info as vae:
+            assert isinstance(vae, torch.nn.Module)
             orig_dtype = vae.dtype
             if upcast:
                 vae.to(dtype=torch.float32)
 
-                use_torch_2_0_or_xformers = isinstance(
+                use_torch_2_0_or_xformers = hasattr(vae.decoder, "mid_block") and isinstance(
                     vae.decoder.mid_block.attentions[0].processor,
                     (
                         AttnProcessor2_0,
@@ -995,7 +1059,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.models.load(**self.vae.vae.model_dump())
+        vae_info = context.models.load(self.vae.vae)
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
         if image_tensor.dim() == 3:
@@ -1010,14 +1074,19 @@ class ImageToLatentsInvocation(BaseInvocation):
     @singledispatchmethod
     @staticmethod
     def _encode_to_tensor(vae: AutoencoderKL, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
+        assert isinstance(vae, torch.nn.Module)
         image_tensor_dist = vae.encode(image_tensor).latent_dist
-        latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
+        latents: torch.Tensor = image_tensor_dist.sample().to(
+            dtype=vae.dtype
+        )  # FIXME: uses torch.randn. make reproducible!
         return latents
 
     @_encode_to_tensor.register
     @staticmethod
     def _(vae: AutoencoderTiny, image_tensor: torch.FloatTensor) -> torch.FloatTensor:
-        return vae.encode(image_tensor).latents
+        assert isinstance(vae, torch.nn.Module)
+        latents: torch.FloatTensor = vae.encode(image_tensor).latents
+        return latents
 
 
 @invocation(
@@ -1050,7 +1119,12 @@ class BlendLatentsInvocation(BaseInvocation):
         # TODO:
         device = choose_torch_device()
 
-        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
+        def slerp(
+            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
+            v0: Union[torch.Tensor, npt.NDArray[Any]],
+            v1: Union[torch.Tensor, npt.NDArray[Any]],
+            DOT_THRESHOLD: float = 0.9995,
+        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
             """
             Spherical linear interpolation
             Args:
@@ -1083,12 +1157,16 @@ class BlendLatentsInvocation(BaseInvocation):
                 v2 = s0 * v0 + s1 * v1
 
             if inputs_are_torch:
-                v2 = torch.from_numpy(v2).to(device)
-
-            return v2
+                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
+                return v2_torch
+            else:
+                assert isinstance(v2, np.ndarray)
+                return v2
 
         # blend
-        blended_latents = slerp(self.alpha, latents_a, latents_b)
+        bl = slerp(self.alpha, latents_a, latents_b)
+        assert isinstance(bl, torch.Tensor)
+        blended_latents: torch.Tensor = bl  # for type checking convenience
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
@@ -1181,15 +1259,16 @@ class IdealSizeInvocation(BaseInvocation):
         description="Amount to multiply the model's dimensions by when calculating the ideal size (may result in initial generation artifacts if too large)",
     )
 
-    def trim_to_multiple_of(self, *args, multiple_of=LATENT_SCALE_FACTOR):
+    def trim_to_multiple_of(self, *args: int, multiple_of: int = LATENT_SCALE_FACTOR) -> Tuple[int, ...]:
         return tuple((x - x % multiple_of) for x in args)
 
     def invoke(self, context: InvocationContext) -> IdealSizeOutput:
+        unet_config = context.models.get_config(**self.unet.unet.model_dump())
         aspect = self.width / self.height
-        dimension = 512
-        if self.unet.unet.base_model == BaseModelType.StableDiffusion2:
+        dimension: float = 512
+        if unet_config.base == BaseModelType.StableDiffusion2:
             dimension = 768
-        elif self.unet.unet.base_model == BaseModelType.StableDiffusionXL:
+        elif unet_config.base == BaseModelType.StableDiffusionXL:
             dimension = 1024
         dimension = dimension * self.multiplier
         min_dimension = math.floor(dimension * 0.5)

invokeai/app/invocations/metadata.py

@@ -8,7 +8,10 @@ from invokeai.app.invocations.baseinvocation import (
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.controlnet_image_processors import ControlField
+from invokeai.app.invocations.controlnet_image_processors import (
+    CONTROLNET_MODE_VALUES,
+    CONTROLNET_RESIZE_VALUES,
+)
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
     ImageField,
@@ -17,9 +20,7 @@ from invokeai.app.invocations.fields import (
     OutputField,
     UIType,
 )
-from invokeai.app.invocations.ip_adapter import IPAdapterModelField
-from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.t2i_adapter import T2IAdapterField
+from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
@@ -33,7 +34,7 @@ class MetadataItemField(BaseModel):
 class LoRAMetadataField(BaseModel):
     """LoRA Metadata Field"""
 
-    lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
+    model: ModelIdentifierField = Field(description=FieldDescriptions.lora_model)
     weight: float = Field(description=FieldDescriptions.lora_weight)
 
 
@@ -41,16 +42,41 @@ class IPAdapterMetadataField(BaseModel):
     """IP Adapter Field, minus the CLIP Vision Encoder model"""
 
     image: ImageField = Field(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = Field(
-        description="The IP-Adapter model.",
-    )
-    weight: Union[float, list[float]] = Field(
-        description="The weight given to the IP-Adapter",
-    )
+    ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
+    weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
     end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")
 
 
+class T2IAdapterMetadataField(BaseModel):
+    image: ImageField = Field(description="The control image.")
+    processed_image: Optional[ImageField] = Field(default=None, description="The control image, after processing.")
+    t2i_adapter_model: ModelIdentifierField = Field(description="The T2I-Adapter model to use.")
+    weight: Union[float, list[float]] = Field(default=1, description="The weight given to the T2I-Adapter")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the T2I-Adapter is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the T2I-Adapter is last applied (% of total steps)"
+    )
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
+class ControlNetMetadataField(BaseModel):
+    image: ImageField = Field(description="The control image")
+    processed_image: Optional[ImageField] = Field(default=None, description="The control image, after processing.")
+    control_model: ModelIdentifierField = Field(description="The ControlNet model to use")
+    control_weight: Union[float, list[float]] = Field(default=1, description="The weight given to the ControlNet")
+    begin_step_percent: float = Field(
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
+    )
+    end_step_percent: float = Field(
+        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
+    )
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+
+
 @invocation_output("metadata_item_output")
 class MetadataItemOutput(BaseInvocationOutput):
     """Metadata Item Output"""
@@ -114,7 +140,7 @@ GENERATION_MODES = Literal[
 ]
 
 
-@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.1")
+@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.1.1")
 class CoreMetadataInvocation(BaseInvocation):
     """Collects core generation metadata into a MetadataField"""
 
@@ -140,14 +166,14 @@ class CoreMetadataInvocation(BaseInvocation):
         default=None,
         description="The number of skipped CLIP layers",
     )
-    model: Optional[MainModelField] = InputField(default=None, description="The main model used for inference")
-    controlnets: Optional[list[ControlField]] = InputField(
+    model: Optional[ModelIdentifierField] = InputField(default=None, description="The main model used for inference")
+    controlnets: Optional[list[ControlNetMetadataField]] = InputField(
         default=None, description="The ControlNets used for inference"
     )
     ipAdapters: Optional[list[IPAdapterMetadataField]] = InputField(
         default=None, description="The IP Adapters used for inference"
     )
-    t2iAdapters: Optional[list[T2IAdapterField]] = InputField(
+    t2iAdapters: Optional[list[T2IAdapterMetadataField]] = InputField(
         default=None, description="The IP Adapters used for inference"
     )
     loras: Optional[list[LoRAMetadataField]] = InputField(default=None, description="The LoRAs used for inference")
@@ -159,7 +185,7 @@ class CoreMetadataInvocation(BaseInvocation):
         default=None,
         description="The name of the initial image",
     )
-    vae: Optional[VAEModelField] = InputField(
+    vae: Optional[ModelIdentifierField] = InputField(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
@@ -190,7 +216,7 @@ class CoreMetadataInvocation(BaseInvocation):
     )
 
     # SDXL Refiner
-    refiner_model: Optional[MainModelField] = InputField(
+    refiner_model: Optional[ModelIdentifierField] = InputField(
         default=None,
         description="The SDXL Refiner model used",
     )
@@ -222,10 +248,9 @@ class CoreMetadataInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> MetadataOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataOutput(
-            metadata=MetadataField.model_validate(
-                self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
-            )
-        )
+        as_dict = self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
+        as_dict["app_version"] = __version__
+
+        return MetadataOutput(metadata=MetadataField.model_validate(as_dict))
 
     model_config = ConfigDict(extra="allow")

invokeai/app/invocations/model.py

@@ -1,13 +1,13 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
+from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelType, SubModelType
 
-from ...backend.model_management import BaseModelType, ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -16,43 +16,58 @@ from .baseinvocation import (
 )
 
 
-class ModelInfo(BaseModel):
-    model_name: str = Field(description="Info to load submodel")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Info to load submodel")
-    submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
+class ModelIdentifierField(BaseModel):
+    key: str = Field(description="The model's unique key")
+    hash: str = Field(description="The model's BLAKE3 hash")
+    name: str = Field(description="The model's name")
+    base: BaseModelType = Field(description="The model's base model type")
+    type: ModelType = Field(description="The model's type")
+    submodel_type: Optional[SubModelType] = Field(
+        description="The submodel to load, if this is a main model", default=None
+    )
 
-    model_config = ConfigDict(protected_namespaces=())
+    @classmethod
+    def from_config(
+        cls, config: "AnyModelConfig", submodel_type: Optional[SubModelType] = None
+    ) -> "ModelIdentifierField":
+        return cls(
+            key=config.key,
+            hash=config.hash,
+            name=config.name,
+            base=config.base,
+            type=config.type,
+            submodel_type=submodel_type,
+        )
 
 
-class LoraInfo(ModelInfo):
-    weight: float = Field(description="Lora's weight which to use when apply to model")
+class LoRAField(BaseModel):
+    lora: ModelIdentifierField = Field(description="Info to load lora model")
+    weight: float = Field(description="Weight to apply to lora model")
 
 
 class UNetField(BaseModel):
-    unet: ModelInfo = Field(description="Info to load unet submodel")
-    scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
-    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
+    unet: ModelIdentifierField = Field(description="Info to load unet submodel")
+    scheduler: ModelIdentifierField = Field(description="Info to load scheduler submodel")
+    loras: List[LoRAField] = Field(description="LoRAs to apply on model loading")
     seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
     freeu_config: Optional[FreeUConfig] = Field(default=None, description="FreeU configuration")
 
 
-class ClipField(BaseModel):
-    tokenizer: ModelInfo = Field(description="Info to load tokenizer submodel")
-    text_encoder: ModelInfo = Field(description="Info to load text_encoder submodel")
+class CLIPField(BaseModel):
+    tokenizer: ModelIdentifierField = Field(description="Info to load tokenizer submodel")
+    text_encoder: ModelIdentifierField = Field(description="Info to load text_encoder submodel")
     skipped_layers: int = Field(description="Number of skipped layers in text_encoder")
-    loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
+    loras: List[LoRAField] = Field(description="LoRAs to apply on model loading")
 
 
-class VaeField(BaseModel):
-    # TODO: better naming?
-    vae: ModelInfo = Field(description="Info to load vae submodel")
+class VAEField(BaseModel):
+    vae: ModelIdentifierField = Field(description="Info to load vae submodel")
     seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
 
 
 @invocation_output("unet_output")
 class UNetOutput(BaseInvocationOutput):
-    """Base class for invocations that output a UNet field"""
+    """Base class for invocations that output a UNet field."""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
 
@@ -61,14 +76,14 @@ class UNetOutput(BaseInvocationOutput):
 class VAEOutput(BaseInvocationOutput):
     """Base class for invocations that output a VAE field"""
 
-    vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
 @invocation_output("clip_output")
 class CLIPOutput(BaseInvocationOutput):
     """Base class for invocations that output a CLIP field"""
 
-    clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP")
+    clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP")
 
 
 @invocation_output("model_loader_output")
@@ -78,25 +93,6 @@ class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
     pass
 
 
-class MainModelField(BaseModel):
-    """Main model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-    model_type: ModelType = Field(description="Model Type")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
-class LoRAModelField(BaseModel):
-    """LoRA model field"""
-
-    model_name: str = Field(description="Name of the LoRA model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
 @invocation(
     "main_model_loader",
     title="Main Model",
@@ -107,107 +103,44 @@ class LoRAModelField(BaseModel):
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
-    model: MainModelField = InputField(description=FieldDescriptions.main_model, input=Input.Direct)
+    model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.main_model, input=Input.Direct, ui_type=UIType.MainModel
+    )
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
-
         # TODO: not found exceptions
-        if not context.models.exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.models.exists(self.model.key):
+            raise Exception(f"Unknown model {self.model.key}")
 
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
+        unet = self.model.model_copy(update={"submodel_type": SubModelType.UNet})
+        scheduler = self.model.model_copy(update={"submodel_type": SubModelType.Scheduler})
+        tokenizer = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
+        text_encoder = self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+        vae = self.model.model_copy(update={"submodel_type": SubModelType.VAE})
 
         return ModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
-                ),
-            ),
+            unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
+            clip=CLIPField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
+            vae=VAEField(vae=vae),
         )
 
 
 @invocation_output("lora_loader_output")
-class LoraLoaderOutput(BaseInvocationOutput):
+class LoRALoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
     unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
 @invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
-class LoraLoaderInvocation(BaseInvocation):
+class LoRALoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
-    lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
+    lora: ModelIdentifierField = InputField(
+        description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA", ui_type=UIType.LoRAModel
+    )
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
         default=None,
@@ -215,55 +148,41 @@ class LoraLoaderInvocation(BaseInvocation):
         input=Input.Connection,
         title="UNet",
     )
-    clip: Optional[ClipField] = InputField(
+    clip: Optional[CLIPField] = InputField(
         default=None,
         description=FieldDescriptions.clip,
         input=Input.Connection,
         title="CLIP",
     )
 
-    def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
-        if self.lora is None:
-            raise Exception("No LoRA provided")
+    def invoke(self, context: InvocationContext) -> LoRALoaderOutput:
+        lora_key = self.lora.key
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unkown lora: {lora_key}!")
 
-        if not context.models.exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unkown lora name: {lora_name}!")
+        if self.unet is not None and any(lora.lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'LoRA "{lora_key}" already applied to unet')
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.clip is not None and any(lora.lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'LoRA "{lora_key}" already applied to clip')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
-
-        output = LoraLoaderOutput()
+        output = LoRALoaderOutput()
 
         if self.unet is not None:
-            output.unet = copy.deepcopy(self.unet)
+            output.unet = self.unet.model_copy(deep=True)
             output.unet.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                LoRAField(
+                    lora=self.lora,
                     weight=self.weight,
                 )
             )
 
         if self.clip is not None:
-            output.clip = copy.deepcopy(self.clip)
+            output.clip = self.clip.model_copy(deep=True)
             output.clip.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                LoRAField(
+                    lora=self.lora,
                     weight=self.weight,
                 )
             )
@@ -272,12 +191,12 @@ class LoraLoaderInvocation(BaseInvocation):
 
 
 @invocation_output("sdxl_lora_loader_output")
-class SDXLLoraLoaderOutput(BaseInvocationOutput):
+class SDXLLoRALoaderOutput(BaseInvocationOutput):
     """SDXL LoRA Loader Output"""
 
     unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
-    clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
+    clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
+    clip2: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
 
 
 @invocation(
@@ -287,10 +206,12 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     category="model",
     version="1.0.1",
 )
-class SDXLLoraLoaderInvocation(BaseInvocation):
+class SDXLLoRALoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
-    lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
+    lora: ModelIdentifierField = InputField(
+        description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA", ui_type=UIType.LoRAModel
+    )
     weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
     unet: Optional[UNetField] = InputField(
         default=None,
@@ -298,76 +219,59 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         input=Input.Connection,
         title="UNet",
     )
-    clip: Optional[ClipField] = InputField(
+    clip: Optional[CLIPField] = InputField(
         default=None,
         description=FieldDescriptions.clip,
         input=Input.Connection,
         title="CLIP 1",
     )
-    clip2: Optional[ClipField] = InputField(
+    clip2: Optional[CLIPField] = InputField(
         default=None,
         description=FieldDescriptions.clip,
         input=Input.Connection,
         title="CLIP 2",
     )
 
-    def invoke(self, context: InvocationContext) -> SDXLLoraLoaderOutput:
-        if self.lora is None:
-            raise Exception("No LoRA provided")
+    def invoke(self, context: InvocationContext) -> SDXLLoRALoaderOutput:
+        lora_key = self.lora.key
 
-        base_model = self.lora.base_model
-        lora_name = self.lora.model_name
+        if not context.models.exists(lora_key):
+            raise Exception(f"Unknown lora: {lora_key}!")
 
-        if not context.models.exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unknown lora name: {lora_name}!")
+        if self.unet is not None and any(lora.lora.key == lora_key for lora in self.unet.loras):
+            raise Exception(f'LoRA "{lora_key}" already applied to unet')
 
-        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to unet')
+        if self.clip is not None and any(lora.lora.key == lora_key for lora in self.clip.loras):
+            raise Exception(f'LoRA "{lora_key}" already applied to clip')
 
-        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip')
+        if self.clip2 is not None and any(lora.lora.key == lora_key for lora in self.clip2.loras):
+            raise Exception(f'LoRA "{lora_key}" already applied to clip2')
 
-        if self.clip2 is not None and any(lora.model_name == lora_name for lora in self.clip2.loras):
-            raise Exception(f'Lora "{lora_name}" already applied to clip2')
-
-        output = SDXLLoraLoaderOutput()
+        output = SDXLLoRALoaderOutput()
 
         if self.unet is not None:
-            output.unet = copy.deepcopy(self.unet)
+            output.unet = self.unet.model_copy(deep=True)
             output.unet.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                LoRAField(
+                    lora=self.lora,
                     weight=self.weight,
                 )
             )
 
         if self.clip is not None:
-            output.clip = copy.deepcopy(self.clip)
+            output.clip = self.clip.model_copy(deep=True)
             output.clip.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                LoRAField(
+                    lora=self.lora,
                     weight=self.weight,
                 )
             )
 
         if self.clip2 is not None:
-            output.clip2 = copy.deepcopy(self.clip2)
+            output.clip2 = self.clip2.model_copy(deep=True)
             output.clip2.loras.append(
-                LoraInfo(
-                    base_model=base_model,
-                    model_name=lora_name,
-                    model_type=ModelType.Lora,
-                    submodel=None,
+                LoRAField(
+                    lora=self.lora,
                     weight=self.weight,
                 )
             )
@@ -375,45 +279,21 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
         return output
 
 
-class VAEModelField(BaseModel):
-    """Vae model field"""
-
-    model_name: str = Field(description="Name of the model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
-
-
 @invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
-class VaeLoaderInvocation(BaseInvocation):
+class VAELoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
-    vae_model: VAEModelField = InputField(
-        description=FieldDescriptions.vae_model,
-        input=Input.Direct,
-        title="VAE",
+    vae_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.vae_model, input=Input.Direct, title="VAE", ui_type=UIType.VAEModel
     )
 
     def invoke(self, context: InvocationContext) -> VAEOutput:
-        base_model = self.vae_model.base_model
-        model_name = self.vae_model.model_name
-        model_type = ModelType.Vae
+        key = self.vae_model.key
 
-        if not context.models.exists(
-            base_model=base_model,
-            model_name=model_name,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unkown vae name: {model_name}!")
-        return VAEOutput(
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                )
-            )
-        )
+        if not context.models.exists(key):
+            raise Exception(f"Unkown vae: {key}!")
+
+        return VAEOutput(vae=VAEField(vae=self.vae_model))
 
 
 @invocation_output("seamless_output")
@@ -421,7 +301,7 @@ class SeamlessModeOutput(BaseInvocationOutput):
     """Modified Seamless Model output"""
 
     unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    vae: Optional[VaeField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
+    vae: Optional[VAEField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
 
 
 @invocation(
@@ -440,7 +320,7 @@ class SeamlessModeInvocation(BaseInvocation):
         input=Input.Connection,
         title="UNet",
     )
-    vae: Optional[VaeField] = InputField(
+    vae: Optional[VAEField] = InputField(
         default=None,
         description=FieldDescriptions.vae_model,
         input=Input.Connection,

invokeai/app/invocations/primitives.py

@@ -299,9 +299,13 @@ class DenoiseMaskOutput(BaseInvocationOutput):
     denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
 
     @classmethod
-    def build(cls, mask_name: str, masked_latents_name: Optional[str] = None) -> "DenoiseMaskOutput":
+    def build(
+        cls, mask_name: str, masked_latents_name: Optional[str] = None, gradient: bool = False
+    ) -> "DenoiseMaskOutput":
         return cls(
-            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name),
+            denoise_mask=DenoiseMaskField(
+                mask_name=mask_name, masked_latents_name=masked_latents_name, gradient=gradient
+            ),
         )
 
 

invokeai/app/invocations/sdxl.py

@@ -1,14 +1,14 @@
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager import SubModelType
 
-from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     invocation,
     invocation_output,
 )
-from .model import ClipField, MainModelField, ModelInfo, UNetField, VaeField
+from .model import CLIPField, ModelIdentifierField, UNetField, VAEField
 
 
 @invocation_output("sdxl_model_loader_output")
@@ -16,9 +16,9 @@ class SDXLModelLoaderOutput(BaseInvocationOutput):
     """SDXL base model loader output"""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 1")
-    clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
-    vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 1")
+    clip2: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
+    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
 @invocation_output("sdxl_refiner_model_loader_output")
@@ -26,88 +26,39 @@ class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
     """SDXL refiner model loader output"""
 
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
-    clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
-    vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    clip2: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
+    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
 @invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.1")
 class SDXLModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl base model, outputting its submodels."""
 
-    model: MainModelField = InputField(
+    model: ModelIdentifierField = InputField(
         description=FieldDescriptions.sdxl_main_model, input=Input.Direct, ui_type=UIType.SDXLMainModel
     )
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        model_key = self.model.key
 
         # TODO: not found exceptions
-        if not context.models.exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.models.exists(model_key):
+            raise Exception(f"Unknown model: {model_key}")
+
+        unet = self.model.model_copy(update={"submodel_type": SubModelType.UNet})
+        scheduler = self.model.model_copy(update={"submodel_type": SubModelType.Scheduler})
+        tokenizer = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
+        text_encoder = self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+        tokenizer2 = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer2})
+        text_encoder2 = self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
+        vae = self.model.model_copy(update={"submodel_type": SubModelType.VAE})
 
         return SDXLModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            clip2=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer2,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder2,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
-                ),
-            ),
+            unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
+            clip=CLIPField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
+            clip2=CLIPField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
+            vae=VAEField(vae=vae),
         )
 
 
@@ -121,64 +72,26 @@ class SDXLModelLoaderInvocation(BaseInvocation):
 class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl refiner model, outputting its submodels."""
 
-    model: MainModelField = InputField(
-        description=FieldDescriptions.sdxl_refiner_model,
-        input=Input.Direct,
-        ui_type=UIType.SDXLRefinerModel,
+    model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.sdxl_refiner_model, input=Input.Direct, ui_type=UIType.SDXLRefinerModel
     )
     # TODO: precision?
 
     def invoke(self, context: InvocationContext) -> SDXLRefinerModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.Main
+        model_key = self.model.key
 
         # TODO: not found exceptions
-        if not context.models.exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.models.exists(model_key):
+            raise Exception(f"Unknown model: {model_key}")
+
+        unet = self.model.model_copy(update={"submodel_type": SubModelType.UNet})
+        scheduler = self.model.model_copy(update={"submodel_type": SubModelType.Scheduler})
+        tokenizer2 = self.model.model_copy(update={"submodel_type": SubModelType.Tokenizer2})
+        text_encoder2 = self.model.model_copy(update={"submodel_type": SubModelType.TextEncoder2})
+        vae = self.model.model_copy(update={"submodel_type": SubModelType.VAE})
 
         return SDXLRefinerModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.UNet,
-                ),
-                scheduler=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Scheduler,
-                ),
-                loras=[],
-            ),
-            clip2=ClipField(
-                tokenizer=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Tokenizer2,
-                ),
-                text_encoder=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.TextEncoder2,
-                ),
-                loras=[],
-                skipped_layers=0,
-            ),
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.Vae,
-                ),
-            ),
+            unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
+            clip2=CLIPField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
+            vae=VAEField(vae=vae),
         )

invokeai/app/invocations/t2i_adapter.py

@@ -1,6 +1,6 @@
 from typing import Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, field_validator, model_validator
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -9,22 +9,15 @@ from invokeai.app.invocations.baseinvocation import (
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
-from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.model_management.models.base import BaseModelType
-
-
-class T2IAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the T2I-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-    model_config = ConfigDict(protected_namespaces=())
 
 
 class T2IAdapterField(BaseModel):
     image: ImageField = Field(description="The T2I-Adapter image prompt.")
-    t2i_adapter_model: T2IAdapterModelField = Field(description="The T2I-Adapter model to use.")
+    t2i_adapter_model: ModelIdentifierField = Field(description="The T2I-Adapter model to use.")
     weight: Union[float, list[float]] = Field(default=1, description="The weight given to the T2I-Adapter")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the T2I-Adapter is first applied (% of total steps)"
@@ -59,11 +52,12 @@ class T2IAdapterInvocation(BaseInvocation):
 
     # Inputs
     image: ImageField = InputField(description="The IP-Adapter image prompt.")
-    t2i_adapter_model: T2IAdapterModelField = InputField(
+    t2i_adapter_model: ModelIdentifierField = InputField(
         description="The T2I-Adapter model.",
         title="T2I-Adapter Model",
         input=Input.Direct,
         ui_order=-1,
+        ui_type=UIType.T2IAdapterModel,
     )
     weight: Union[float, list[float]] = InputField(
         default=1, ge=0, description="The weight given to the T2I-Adapter", title="Weight"

invokeai/app/run_app.py

@@ -0,0 +1,12 @@
+"""This is a wrapper around the main app entrypoint, to allow for CLI args to be parsed before running the app."""
+
+
+def run_app() -> None:
+    # Before doing _anything_, parse CLI args!
+    from invokeai.frontend.cli.arg_parser import InvokeAIArgs
+
+    InvokeAIArgs.parse_args()
+
+    from invokeai.app.api_app import invoke_api
+
+    invoke_api()

invokeai/app/services/bulk_download/bulk_download_base.py

@@ -0,0 +1,44 @@
+from abc import ABC, abstractmethod
+from typing import Optional
+
+
+class BulkDownloadBase(ABC):
+    """Responsible for creating a zip file containing the images specified by the given image names or board id."""
+
+    @abstractmethod
+    def handler(
+        self, image_names: Optional[list[str]], board_id: Optional[str], bulk_download_item_id: Optional[str]
+    ) -> None:
+        """
+        Create a zip file containing the images specified by the given image names or board id.
+
+        :param image_names: A list of image names to include in the zip file.
+        :param board_id: The ID of the board. If provided, all images associated with the board will be included in the zip file.
+        :param bulk_download_item_id: The bulk_download_item_id that will be used to retrieve the bulk download item when it is prepared, if none is provided a uuid will be generated.
+        """
+
+    @abstractmethod
+    def get_path(self, bulk_download_item_name: str) -> str:
+        """
+        Get the path to the bulk download file.
+
+        :param bulk_download_item_name: The name of the bulk download item.
+        :return: The path to the bulk download file.
+        """
+
+    @abstractmethod
+    def generate_item_id(self, board_id: Optional[str]) -> str:
+        """
+        Generate an item ID for a bulk download item.
+
+        :param board_id: The ID of the board whose name is to be included in the item id.
+        :return: The generated item ID.
+        """
+
+    @abstractmethod
+    def delete(self, bulk_download_item_name: str) -> None:
+        """
+        Delete the bulk download file.
+
+        :param bulk_download_item_name: The name of the bulk download item.
+        """

invokeai/app/services/bulk_download/bulk_download_common.py

@@ -0,0 +1,25 @@
+DEFAULT_BULK_DOWNLOAD_ID = "default"
+
+
+class BulkDownloadException(Exception):
+    """Exception raised when a bulk download fails."""
+
+    def __init__(self, message="Bulk download failed"):
+        super().__init__(message)
+        self.message = message
+
+
+class BulkDownloadTargetException(BulkDownloadException):
+    """Exception raised when a bulk download target is not found."""
+
+    def __init__(self, message="The bulk download target was not found"):
+        super().__init__(message)
+        self.message = message
+
+
+class BulkDownloadParametersException(BulkDownloadException):
+    """Exception raised when a bulk download parameter is invalid."""
+
+    def __init__(self, message="No image names or board ID provided"):
+        super().__init__(message)
+        self.message = message

invokeai/app/services/bulk_download/bulk_download_default.py

@@ -0,0 +1,157 @@
+from pathlib import Path
+from tempfile import TemporaryDirectory
+from typing import Optional, Union
+from zipfile import ZipFile
+
+from invokeai.app.services.board_records.board_records_common import BoardRecordNotFoundException
+from invokeai.app.services.bulk_download.bulk_download_common import (
+    DEFAULT_BULK_DOWNLOAD_ID,
+    BulkDownloadException,
+    BulkDownloadParametersException,
+    BulkDownloadTargetException,
+)
+from invokeai.app.services.image_records.image_records_common import ImageRecordNotFoundException
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.util.misc import uuid_string
+
+from .bulk_download_base import BulkDownloadBase
+
+
+class BulkDownloadService(BulkDownloadBase):
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+
+    def __init__(self):
+        self._temp_directory = TemporaryDirectory()
+        self._bulk_downloads_folder = Path(self._temp_directory.name) / "bulk_downloads"
+        self._bulk_downloads_folder.mkdir(parents=True, exist_ok=True)
+
+    def handler(
+        self, image_names: Optional[list[str]], board_id: Optional[str], bulk_download_item_id: Optional[str]
+    ) -> None:
+        bulk_download_id: str = DEFAULT_BULK_DOWNLOAD_ID
+        bulk_download_item_id = bulk_download_item_id or uuid_string()
+        bulk_download_item_name = bulk_download_item_id + ".zip"
+
+        self._signal_job_started(bulk_download_id, bulk_download_item_id, bulk_download_item_name)
+
+        try:
+            image_dtos: list[ImageDTO] = []
+
+            if board_id:
+                image_dtos = self._board_handler(board_id)
+            elif image_names:
+                image_dtos = self._image_handler(image_names)
+            else:
+                raise BulkDownloadParametersException()
+
+            bulk_download_item_name: str = self._create_zip_file(image_dtos, bulk_download_item_id)
+            self._signal_job_completed(bulk_download_id, bulk_download_item_id, bulk_download_item_name)
+        except (
+            ImageRecordNotFoundException,
+            BoardRecordNotFoundException,
+            BulkDownloadException,
+            BulkDownloadParametersException,
+        ) as e:
+            self._signal_job_failed(bulk_download_id, bulk_download_item_id, bulk_download_item_name, e)
+        except Exception as e:
+            self._signal_job_failed(bulk_download_id, bulk_download_item_id, bulk_download_item_name, e)
+            self._invoker.services.logger.error("Problem bulk downloading images.")
+            raise e
+
+    def _image_handler(self, image_names: list[str]) -> list[ImageDTO]:
+        return [self._invoker.services.images.get_dto(image_name) for image_name in image_names]
+
+    def _board_handler(self, board_id: str) -> list[ImageDTO]:
+        image_names = self._invoker.services.board_image_records.get_all_board_image_names_for_board(board_id)
+        return self._image_handler(image_names)
+
+    def generate_item_id(self, board_id: Optional[str]) -> str:
+        return uuid_string() if board_id is None else self._get_clean_board_name(board_id) + "_" + uuid_string()
+
+    def _get_clean_board_name(self, board_id: str) -> str:
+        if board_id == "none":
+            return "Uncategorized"
+
+        return self._clean_string_to_path_safe(self._invoker.services.board_records.get(board_id).board_name)
+
+    def _create_zip_file(self, image_dtos: list[ImageDTO], bulk_download_item_id: str) -> str:
+        """
+        Create a zip file containing the images specified by the given image names or board id.
+        If download with the same bulk_download_id already exists, it will be overwritten.
+
+        :return: The name of the zip file.
+        """
+        zip_file_name = bulk_download_item_id + ".zip"
+        zip_file_path = self._bulk_downloads_folder / (zip_file_name)
+
+        with ZipFile(zip_file_path, "w") as zip_file:
+            for image_dto in image_dtos:
+                image_zip_path = Path(image_dto.image_category.value) / image_dto.image_name
+                image_disk_path = self._invoker.services.images.get_path(image_dto.image_name)
+                zip_file.write(image_disk_path, arcname=image_zip_path)
+
+        return str(zip_file_name)
+
+    # from https://stackoverflow.com/questions/7406102/create-sane-safe-filename-from-any-unsafe-string
+    def _clean_string_to_path_safe(self, s: str) -> str:
+        """Clean a string to be path safe."""
+        return "".join([c for c in s if c.isalpha() or c.isdigit() or c == " " or c == "_" or c == "-"]).rstrip()
+
+    def _signal_job_started(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> None:
+        """Signal that a bulk download job has started."""
+        if self._invoker:
+            assert bulk_download_id is not None
+            self._invoker.services.events.emit_bulk_download_started(
+                bulk_download_id=bulk_download_id,
+                bulk_download_item_id=bulk_download_item_id,
+                bulk_download_item_name=bulk_download_item_name,
+            )
+
+    def _signal_job_completed(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> None:
+        """Signal that a bulk download job has completed."""
+        if self._invoker:
+            assert bulk_download_id is not None
+            assert bulk_download_item_name is not None
+            self._invoker.services.events.emit_bulk_download_completed(
+                bulk_download_id=bulk_download_id,
+                bulk_download_item_id=bulk_download_item_id,
+                bulk_download_item_name=bulk_download_item_name,
+            )
+
+    def _signal_job_failed(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, exception: Exception
+    ) -> None:
+        """Signal that a bulk download job has failed."""
+        if self._invoker:
+            assert bulk_download_id is not None
+            assert exception is not None
+            self._invoker.services.events.emit_bulk_download_failed(
+                bulk_download_id=bulk_download_id,
+                bulk_download_item_id=bulk_download_item_id,
+                bulk_download_item_name=bulk_download_item_name,
+                error=str(exception),
+            )
+
+    def stop(self, *args, **kwargs):
+        self._temp_directory.cleanup()
+
+    def delete(self, bulk_download_item_name: str) -> None:
+        path = self.get_path(bulk_download_item_name)
+        Path(path).unlink()
+
+    def get_path(self, bulk_download_item_name: str) -> str:
+        path = str(self._bulk_downloads_folder / bulk_download_item_name)
+        if not self._is_valid_path(path):
+            raise BulkDownloadTargetException()
+        return path
+
+    def _is_valid_path(self, path: Union[str, Path]) -> bool:
+        """Validates the path given for a bulk download."""
+        path = path if isinstance(path, Path) else Path(path)
+        return path.exists()

invokeai/app/services/config/__init__.py

@@ -2,6 +2,6 @@
 
 from invokeai.app.services.config.config_common import PagingArgumentParser
 
-from .config_default import InvokeAIAppConfig, get_invokeai_config
+from .config_default import InvokeAIAppConfig, get_config
 
-__all__ = ["InvokeAIAppConfig", "get_invokeai_config", "PagingArgumentParser"]
+__all__ = ["InvokeAIAppConfig", "get_config", "PagingArgumentParser"]

invokeai/app/services/config/config_base.py

@@ -1,222 +0,0 @@
-# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
-
-"""
-Base class for the InvokeAI configuration system.
-It defines a type of pydantic BaseSettings object that
-is able to read and write from an omegaconf-based config file,
-with overriding of settings from environment variables and/or
-the command line.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import sys
-from argparse import ArgumentParser
-from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional, Union, get_args, get_origin, get_type_hints
-
-from omegaconf import DictConfig, ListConfig, OmegaConf
-from pydantic_settings import BaseSettings, SettingsConfigDict
-
-from invokeai.app.services.config.config_common import PagingArgumentParser, int_or_float_or_str
-
-
-class InvokeAISettings(BaseSettings):
-    """Runtime configuration settings in which default values are read from an omegaconf .yaml file."""
-
-    initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict] = {}
-
-    model_config = SettingsConfigDict(env_file_encoding="utf-8", arbitrary_types_allowed=True, case_sensitive=True)
-
-    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
-        """Call to parse command-line arguments."""
-        parser = self.get_parser()
-        opt, unknown_opts = parser.parse_known_args(argv)
-        if len(unknown_opts) > 0:
-            print("Unknown args:", unknown_opts)
-        for name in self.model_fields:
-            if name not in self._excluded():
-                value = getattr(opt, name)
-                if isinstance(value, ListConfig):
-                    value = list(value)
-                elif isinstance(value, DictConfig):
-                    value = dict(value)
-                setattr(self, name, value)
-
-    def to_yaml(self) -> str:
-        """Return a YAML string representing our settings. This can be used as the contents of `invokeai.yaml` to restore settings later."""
-        cls = self.__class__
-        type = get_args(get_type_hints(cls)["type"])[0]
-        field_dict: Dict[str, Dict[str, Any]] = {type: {}}
-        for name, field in self.model_fields.items():
-            if name in cls._excluded_from_yaml():
-                continue
-            assert isinstance(field.json_schema_extra, dict)
-            category = (
-                field.json_schema_extra.get("category", "Uncategorized") if field.json_schema_extra else "Uncategorized"
-            )
-            value = getattr(self, name)
-            assert isinstance(category, str)
-            if category not in field_dict[type]:
-                field_dict[type][category] = {}
-            # keep paths as strings to make it easier to read
-            field_dict[type][category][name] = str(value) if isinstance(value, Path) else value
-        conf = OmegaConf.create(field_dict)
-        return OmegaConf.to_yaml(conf)
-
-    @classmethod
-    def add_parser_arguments(cls, parser):
-        """Dynamically create arguments for a settings parser."""
-        if "type" in get_type_hints(cls):
-            settings_stanza = get_args(get_type_hints(cls)["type"])[0]
-        else:
-            settings_stanza = "Uncategorized"
-
-        env_prefix = getattr(cls.model_config, "env_prefix", None)
-        env_prefix = env_prefix if env_prefix is not None else settings_stanza.upper()
-
-        initconf = (
-            cls.initconf.get(settings_stanza)
-            if cls.initconf and settings_stanza in cls.initconf
-            else OmegaConf.create()
-        )
-
-        # create an upcase version of the environment in
-        # order to achieve case-insensitive environment
-        # variables (the way Windows does)
-        upcase_environ = {}
-        for key, value in os.environ.items():
-            upcase_environ[key.upper()] = value
-
-        fields = cls.model_fields
-        cls.argparse_groups = {}
-
-        for name, field in fields.items():
-            if name not in cls._excluded():
-                current_default = field.default
-
-                category = (
-                    field.json_schema_extra.get("category", "Uncategorized")
-                    if field.json_schema_extra
-                    else "Uncategorized"
-                )
-                env_name = env_prefix + "_" + name
-                if category in initconf and name in initconf.get(category):
-                    field.default = initconf.get(category).get(name)
-                if env_name.upper() in upcase_environ:
-                    field.default = upcase_environ[env_name.upper()]
-                cls.add_field_argument(parser, name, field)
-
-                field.default = current_default
-
-    @classmethod
-    def cmd_name(cls, command_field: str = "type") -> str:
-        """Return the category of a setting."""
-        hints = get_type_hints(cls)
-        if command_field in hints:
-            return get_args(hints[command_field])[0]
-        else:
-            return "Uncategorized"
-
-    @classmethod
-    def get_parser(cls) -> ArgumentParser:
-        """Get the command-line parser for a setting."""
-        parser = PagingArgumentParser(
-            prog=cls.cmd_name(),
-            description=cls.__doc__,
-        )
-        cls.add_parser_arguments(parser)
-        return parser
-
-    @classmethod
-    def _excluded(cls) -> List[str]:
-        # internal fields that shouldn't be exposed as command line options
-        return ["type", "initconf"]
-
-    @classmethod
-    def _excluded_from_yaml(cls) -> List[str]:
-        # combination of deprecated parameters and internal ones that shouldn't be exposed as invokeai.yaml options
-        return [
-            "type",
-            "initconf",
-            "version",
-            "from_file",
-            "model",
-            "root",
-            "max_cache_size",
-            "max_vram_cache_size",
-            "always_use_cpu",
-            "free_gpu_mem",
-            "xformers_enabled",
-            "tiled_decode",
-            "lora_dir",
-            "embedding_dir",
-            "controlnet_dir",
-        ]
-
-    @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
-        """Add the argparse arguments for a setting parser."""
-        field_type = get_type_hints(cls).get(name)
-        default = (
-            default_override
-            if default_override is not None
-            else field.default
-            if field.default_factory is None
-            else field.default_factory()
-        )
-        if category := (field.json_schema_extra.get("category", None) if field.json_schema_extra else None):
-            if category not in cls.argparse_groups:
-                cls.argparse_groups[category] = command_parser.add_argument_group(category)
-            argparse_group = cls.argparse_groups[category]
-        else:
-            argparse_group = command_parser
-
-        if get_origin(field_type) == Literal:
-            allowed_values = get_args(field.annotation)
-            allowed_types = set()
-            for val in allowed_values:
-                allowed_types.add(type(val))
-            allowed_types_list = list(allowed_types)
-            field_type = allowed_types_list[0] if len(allowed_types) == 1 else int_or_float_or_str
-
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field_type,
-                default=default,
-                choices=allowed_values,
-                help=field.description,
-            )
-
-        elif get_origin(field_type) == Union:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=int_or_float_or_str,
-                default=default,
-                help=field.description,
-            )
-
-        elif get_origin(field_type) == list:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                nargs="*",
-                type=field.annotation,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.annotation == bool else "store",
-                help=field.description,
-            )
-        else:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field.annotation,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.annotation == bool else "store",
-                help=field.description,
-            )

invokeai/app/services/config/config_common.py

@@ -12,7 +12,6 @@ from __future__ import annotations
 
 import argparse
 import pydoc
-from typing import Union
 
 
 class PagingArgumentParser(argparse.ArgumentParser):
@@ -21,21 +20,6 @@ class PagingArgumentParser(argparse.ArgumentParser):
     It also supports reading defaults from an init file.
     """
 
-    def print_help(self, file=None):
+    def print_help(self, file=None) -> None:
         text = self.format_help()
         pydoc.pager(text)
-
-
-def int_or_float_or_str(value: str) -> Union[int, float, str]:
-    """
-    Workaround for argparse type checking.
-    """
-    try:
-        return int(value)
-    except Exception as e:  # noqa F841
-        pass
-    try:
-        return float(value)
-    except Exception as e:  # noqa F841
-        pass
-    return str(value)

invokeai/app/services/config/config_default.py

@@ -1,480 +1,431 @@
-# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
+# TODO(psyche): pydantic-settings supports YAML settings sources. If we can figure out a way to integrate the YAML
+# migration logic, we could use that for simpler config loading.
 
-"""Invokeai configuration system.
-
-Arguments and fields are taken from the pydantic definition of the
-model.  Defaults can be set by creating a yaml configuration file that
-has a top-level key of "InvokeAI" and subheadings for each of the
-categories returned by `invokeai --help`. The file looks like this:
-
-[file: invokeai.yaml]
-
-InvokeAI:
-  Web Server:
-    host: 127.0.0.1
-    port: 9090
-    allow_origins: []
-    allow_credentials: true
-    allow_methods:
-    - '*'
-    allow_headers:
-    - '*'
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    patchmatch: true
-    ignore_missing_core_models: false
-  Paths:
-    autoimport_dir: autoimport
-    lora_dir: null
-    embedding_dir: null
-    controlnet_dir: null
-    conf_path: configs/models.yaml
-    models_dir: models
-    legacy_conf_dir: configs/stable-diffusion
-    db_dir: databases
-    outdir: /home/lstein/invokeai-main/outputs
-    use_memory_db: false
-  Logging:
-    log_handlers:
-    - console
-    log_format: plain
-    log_level: info
-  Model Cache:
-    ram: 13.5
-    vram: 0.25
-    lazy_offload: true
-    log_memory_usage: false
-  Device:
-    device: auto
-    precision: auto
-  Generation:
-    sequential_guidance: false
-    attention_type: xformers
-    attention_slice_size: auto
-    force_tiled_decode: false
-
-The default name of the configuration file is `invokeai.yaml`, located
-in INVOKEAI_ROOT. You can replace supersede this by providing any
-OmegaConf dictionary object initialization time:
-
- omegaconf = OmegaConf.load('/tmp/init.yaml')
- conf = InvokeAIAppConfig()
- conf.parse_args(conf=omegaconf)
-
-InvokeAIAppConfig.parse_args() will parse the contents of `sys.argv`
-at initialization time. You may pass a list of strings in the optional
-`argv` argument to use instead of the system argv:
-
- conf.parse_args(argv=['--log_tokenization'])
-
-It is also possible to set a value at initialization time. However, if
-you call parse_args() it may be overwritten.
-
- conf = InvokeAIAppConfig(log_tokenization=True)
- conf.parse_args(argv=['--no-log_tokenization'])
- conf.log_tokenization
- # False
-
-To avoid this, use `get_config()` to retrieve the application-wide
-configuration object. This will retain any properties set at object
-creation time:
-
- conf = InvokeAIAppConfig.get_config(log_tokenization=True)
- conf.parse_args(argv=['--no-log_tokenization'])
- conf.log_tokenization
- # True
-
-Any setting can be overwritten by setting an environment variable of
-form: "INVOKEAI_<setting>", as in:
-
-  export INVOKEAI_port=8080
-
-Order of precedence (from highest):
-   1) initialization options
-   2) command line options
-   3) environment variable options
-   4) config file options
-   5) pydantic defaults
-
-Typical usage at the top level file:
-
- from invokeai.app.services.config import InvokeAIAppConfig
-
- # get global configuration and print its cache size
- conf = InvokeAIAppConfig.get_config()
- conf.parse_args()
- print(conf.ram_cache_size)
-
-Typical usage in a backend module:
-
- from invokeai.app.services.config import InvokeAIAppConfig
-
- # get global configuration and print its cache size value
- conf = InvokeAIAppConfig.get_config()
- print(conf.ram_cache_size)
-
-Computed properties:
-
-The InvokeAIAppConfig object has a series of properties that
-resolve paths relative to the runtime root directory. They each return
-a Path object:
-
- root_path          - path to InvokeAI root
- output_path        - path to default outputs directory
- model_conf_path    - path to models.yaml
- conf               - alias for the above
- embedding_path     - path to the embeddings directory
- lora_path          - path to the LoRA directory
-
-In most cases, you will want to create a single InvokeAIAppConfig
-object for the entire application. The InvokeAIAppConfig.get_config() function
-does this:
-
-  config = InvokeAIAppConfig.get_config()
-  config.parse_args()   # read values from the command line/config file
-  print(config.root)
-
-# Subclassing
-
-If you wish to create a similar class, please subclass the
-`InvokeAISettings` class and define a Literal field named "type",
-which is set to the desired top-level name.  For example, to create a
-"InvokeBatch" configuration, define like this:
-
-  class InvokeBatch(InvokeAISettings):
-     type: Literal["InvokeBatch"] = "InvokeBatch"
-     node_count : int = Field(default=1, description="Number of nodes to run on", json_schema_extra=dict(category='Resources'))
-     cpu_count  : int = Field(default=8, description="Number of GPUs to run on per node", json_schema_extra=dict(category='Resources'))
-
-This will now read and write from the "InvokeBatch" section of the
-config file, look for environment variables named INVOKEBATCH_*, and
-accept the command-line arguments `--node_count` and `--cpu_count`. The
-two configs are kept in separate sections of the config file:
-
-  # invokeai.yaml
-
-  InvokeBatch:
-     Resources:
-        node_count: 1
-        cpu_count: 8
-
-  InvokeAI:
-     Paths:
-        root: /home/lstein/invokeai-main
-        conf_path: configs/models.yaml
-        legacy_conf_dir: configs/stable-diffusion
-        outdir: outputs
-     ...
-
-"""
 from __future__ import annotations
 
 import os
+import re
+import shutil
+from functools import lru_cache
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional, Union
+from typing import Any, Literal, Optional
 
-from omegaconf import DictConfig, OmegaConf
-from pydantic import Field
-from pydantic.config import JsonDict
-from pydantic_settings import SettingsConfigDict
+import yaml
+from pydantic import BaseModel, Field, PrivateAttr, field_validator
+from pydantic_settings import BaseSettings, SettingsConfigDict
 
-from .config_base import InvokeAISettings
+from invokeai.backend.model_hash.model_hash import HASHING_ALGORITHMS
+from invokeai.frontend.cli.arg_parser import InvokeAIArgs
 
 INIT_FILE = Path("invokeai.yaml")
 DB_FILE = Path("invokeai.db")
 LEGACY_INIT_FILE = Path("invokeai.init")
-DEFAULT_MAX_VRAM = 0.5
+DEFAULT_RAM_CACHE = 10.0
+DEFAULT_VRAM_CACHE = 0.25
+DEFAULT_CONVERT_CACHE = 20.0
+DEVICE = Literal["auto", "cpu", "cuda", "cuda:1", "mps"]
+PRECISION = Literal["auto", "float16", "bfloat16", "float32", "autocast"]
+ATTENTION_TYPE = Literal["auto", "normal", "xformers", "sliced", "torch-sdp"]
+ATTENTION_SLICE_SIZE = Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8]
+LOG_FORMAT = Literal["plain", "color", "syslog", "legacy"]
+LOG_LEVEL = Literal["debug", "info", "warning", "error", "critical"]
+CONFIG_SCHEMA_VERSION = 4
 
 
-class Categories(object):
-    """Category headers for configuration variable groups."""
+class URLRegexTokenPair(BaseModel):
+    url_regex: str = Field(description="Regular expression to match against the URL")
+    token: str = Field(description="Token to use when the URL matches the regex")
 
-    WebServer: JsonDict = {"category": "Web Server"}
-    Features: JsonDict = {"category": "Features"}
-    Paths: JsonDict = {"category": "Paths"}
-    Logging: JsonDict = {"category": "Logging"}
-    Development: JsonDict = {"category": "Development"}
-    Other: JsonDict = {"category": "Other"}
-    ModelCache: JsonDict = {"category": "Model Cache"}
-    Device: JsonDict = {"category": "Device"}
-    Generation: JsonDict = {"category": "Generation"}
-    Queue: JsonDict = {"category": "Queue"}
-    Nodes: JsonDict = {"category": "Nodes"}
-    MemoryPerformance: JsonDict = {"category": "Memory/Performance"}
+    @field_validator("url_regex")
+    @classmethod
+    def validate_url_regex(cls, v: str) -> str:
+        """Validate that the value is a valid regex."""
+        try:
+            re.compile(v)
+        except re.error as e:
+            raise ValueError(f"Invalid regex: {e}")
+        return v
 
 
-class InvokeAIAppConfig(InvokeAISettings):
-    """Configuration object for InvokeAI App."""
+class InvokeAIAppConfig(BaseSettings):
+    """Invoke's global app configuration.
 
-    singleton_config: ClassVar[Optional[InvokeAIAppConfig]] = None
-    singleton_init: ClassVar[Optional[Dict[str, Any]]] = None
+    Typically, you won't need to interact with this class directly. Instead, use the `get_config` function from `invokeai.app.services.config` to get a singleton config object.
+
+    Attributes:
+        host: IP address to bind to. Use `0.0.0.0` to serve to your local network.
+        port: Port to bind to.
+        allow_origins: Allowed CORS origins.
+        allow_credentials: Allow CORS credentials.
+        allow_methods: Methods allowed for CORS.
+        allow_headers: Headers allowed for CORS.
+        ssl_certfile: SSL certificate file for HTTPS. See https://www.uvicorn.org/settings/#https.
+        ssl_keyfile: SSL key file for HTTPS. See https://www.uvicorn.org/settings/#https.
+        log_tokenization: Enable logging of parsed prompt tokens.
+        patchmatch: Enable patchmatch inpaint code.
+        ignore_missing_core_models: Ignore missing core models on startup. If `True`, the app will attempt to download missing models on startup.
+        autoimport_dir: Path to a directory of models files to be imported on startup.
+        models_dir: Path to the models directory.
+        convert_cache_dir: Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.
+        legacy_conf_dir: Path to directory of legacy checkpoint config files.
+        db_dir: Path to InvokeAI databases directory.
+        outputs_dir: Path to directory for outputs.
+        custom_nodes_dir: Path to directory for custom nodes.
+        log_handlers: Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>".
+        log_format: Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style.<br>Valid values: `plain`, `color`, `syslog`, `legacy`
+        log_level: Emit logging messages at this level or higher.<br>Valid values: `debug`, `info`, `warning`, `error`, `critical`
+        log_sql: Log SQL queries. `log_level` must be `debug` for this to do anything. Extremely verbose.
+        use_memory_db: Use in-memory database. Useful for development.
+        dev_reload: Automatically reload when Python sources are changed. Does not reload node definitions.
+        profile_graphs: Enable graph profiling using `cProfile`.
+        profile_prefix: An optional prefix for profile output files.
+        profiles_dir: Path to profiles output directory.
+        ram: Maximum memory amount used by memory model cache for rapid switching (GB).
+        vram: Amount of VRAM reserved for model storage (GB).
+        convert_cache: Maximum size of on-disk converted models cache (GB).
+        lazy_offload: Keep models in VRAM until their space is needed.
+        log_memory_usage: If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.
+        device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `cuda:1`, `mps`
+        precision: Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.<br>Valid values: `auto`, `float16`, `bfloat16`, `float32`, `autocast`
+        sequential_guidance: Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.
+        attention_type: Attention type.<br>Valid values: `auto`, `normal`, `xformers`, `sliced`, `torch-sdp`
+        attention_slice_size: Slice size, valid when attention_type=="sliced".<br>Valid values: `auto`, `balanced`, `max`, `1`, `2`, `3`, `4`, `5`, `6`, `7`, `8`
+        force_tiled_decode: Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty).
+        pil_compress_level: The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = no compression, 1 = fastest with slightly larger filesize, 9 = slowest with smallest filesize. 1 is typically the best setting.
+        max_queue_size: Maximum number of items in the session queue.
+        allow_nodes: List of nodes to allow. Omit to allow all.
+        deny_nodes: List of nodes to deny. Omit to deny none.
+        node_cache_size: How many cached nodes to keep in memory.
+        hashing_algorithm: Model hashing algorthim for model installs. 'blake3' is best for SSDs. 'blake3_single' is best for spinning disk HDDs. 'random' disables hashing, instead assigning a UUID to models. Useful when using a memory db to reduce model installation time, or if you don't care about storing stable hashes for models. Alternatively, any other hashlib algorithm is accepted, though these are not nearly as performant as blake3.<br>Valid values: `md5`, `sha1`, `sha224`, `sha256`, `sha384`, `sha512`, `blake2b`, `blake2s`, `sha3_224`, `sha3_256`, `sha3_384`, `sha3_512`, `shake_128`, `shake_256`, `blake3`, `blake3_single`, `random`
+        remote_api_tokens: List of regular expression and token pairs used when downloading models from URLs. The download URL is tested against the regex, and if it matches, the token is provided in as a Bearer token.
+    """
+
+    _root: Optional[Path] = PrivateAttr(default=None)
 
     # fmt: off
-    type: Literal["InvokeAI"] = "InvokeAI"
+
+    # INTERNAL
+    schema_version:                 int = Field(default=CONFIG_SCHEMA_VERSION, description="Schema version of the config file. This is not a user-configurable setting.")
+    legacy_models_yaml_path: Optional[Path] = Field(default=None,           description="Path to the legacy models.yaml file. This is not a user-configurable setting.")
 
     # WEB
-    host                : str = Field(default="127.0.0.1", description="IP address to bind to", json_schema_extra=Categories.WebServer)
-    port                : int = Field(default=9090, description="Port to bind to", json_schema_extra=Categories.WebServer)
-    allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", json_schema_extra=Categories.WebServer)
-    allow_credentials   : bool = Field(default=True, description="Allow CORS credentials", json_schema_extra=Categories.WebServer)
-    allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", json_schema_extra=Categories.WebServer)
-    allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", json_schema_extra=Categories.WebServer)
-    # SSL options correspond to https://www.uvicorn.org/settings/#https
-    ssl_certfile        : Optional[Path] = Field(default=None, description="SSL certificate file (for HTTPS)", json_schema_extra=Categories.WebServer)
-    ssl_keyfile         : Optional[Path] = Field(default=None, description="SSL key file", json_schema_extra=Categories.WebServer)
+    host:                           str = Field(default="127.0.0.1",        description="IP address to bind to. Use `0.0.0.0` to serve to your local network.")
+    port:                           int = Field(default=9090,               description="Port to bind to.")
+    allow_origins:            list[str] = Field(default=[],                 description="Allowed CORS origins.")
+    allow_credentials:             bool = Field(default=True,               description="Allow CORS credentials.")
+    allow_methods:            list[str] = Field(default=["*"],              description="Methods allowed for CORS.")
+    allow_headers:            list[str] = Field(default=["*"],              description="Headers allowed for CORS.")
+    ssl_certfile:        Optional[Path] = Field(default=None,               description="SSL certificate file for HTTPS. See https://www.uvicorn.org/settings/#https.")
+    ssl_keyfile:         Optional[Path] = Field(default=None,               description="SSL key file for HTTPS. See https://www.uvicorn.org/settings/#https.")
 
-    # FEATURES
-    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", json_schema_extra=Categories.Features)
-    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", json_schema_extra=Categories.Features)
-    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", json_schema_extra=Categories.Features)
-    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", json_schema_extra=Categories.Features)
-    ignore_missing_core_models : bool = Field(default=False, description='Ignore missing models in models/core/convert', json_schema_extra=Categories.Features)
+    # MISC FEATURES
+    log_tokenization:              bool = Field(default=False,              description="Enable logging of parsed prompt tokens.")
+    patchmatch:                    bool = Field(default=True,               description="Enable patchmatch inpaint code.")
+    ignore_missing_core_models:    bool = Field(default=False,              description="Ignore missing core models on startup. If `True`, the app will attempt to download missing models on startup.")
 
     # PATHS
-    root                : Optional[Path] = Field(default=None, description='InvokeAI runtime root directory', json_schema_extra=Categories.Paths)
-    autoimport_dir      : Path = Field(default=Path('autoimport'), description='Path to a directory of models files to be imported on startup.', json_schema_extra=Categories.Paths)
-    conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
-    models_dir          : Path = Field(default=Path('models'), description='Path to the models directory', json_schema_extra=Categories.Paths)
-    legacy_conf_dir     : Path = Field(default=Path('configs/stable-diffusion'), description='Path to directory of legacy checkpoint config files', json_schema_extra=Categories.Paths)
-    db_dir              : Path = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
-    outdir              : Path = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
-    use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', json_schema_extra=Categories.Paths)
-    custom_nodes_dir    : Path = Field(default=Path('nodes'), description='Path to directory for custom nodes', json_schema_extra=Categories.Paths)
-    from_file           : Optional[Path] = Field(default=None, description='Take command input from the indicated file (command-line client only)', json_schema_extra=Categories.Paths)
+    autoimport_dir:                Path = Field(default=Path("autoimport"), description="Path to a directory of models files to be imported on startup.")
+    models_dir:                    Path = Field(default=Path("models"),     description="Path to the models directory.")
+    convert_cache_dir:             Path = Field(default=Path("models/.cache"), description="Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.")
+    legacy_conf_dir:               Path = Field(default=Path("configs/stable-diffusion"), description="Path to directory of legacy checkpoint config files.")
+    db_dir:                        Path = Field(default=Path("databases"),  description="Path to InvokeAI databases directory.")
+    outputs_dir:                   Path = Field(default=Path("outputs"),    description="Path to directory for outputs.")
+    custom_nodes_dir:              Path = Field(default=Path("nodes"),      description="Path to directory for custom nodes.")
 
     # LOGGING
-    log_handlers        : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', json_schema_extra=Categories.Logging)
+    log_handlers:             list[str] = Field(default=["console"],        description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>".')
     # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
-    log_format          : Literal['plain', 'color', 'syslog', 'legacy'] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', json_schema_extra=Categories.Logging)
-    log_level           : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or  higher", json_schema_extra=Categories.Logging)
-    log_sql             : bool = Field(default=False, description="Log SQL queries", json_schema_extra=Categories.Logging)
+    log_format:              LOG_FORMAT = Field(default="color",            description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style.')
+    log_level:                LOG_LEVEL = Field(default="info",             description="Emit logging messages at this level or higher.")
+    log_sql:                       bool = Field(default=False,              description="Log SQL queries. `log_level` must be `debug` for this to do anything. Extremely verbose.")
 
     # Development
-    dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", json_schema_extra=Categories.Development)
-    profile_graphs      : bool = Field(default=False, description="Enable graph profiling", json_schema_extra=Categories.Development)
-    profile_prefix      : Optional[str] = Field(default=None, description="An optional prefix for profile output files.", json_schema_extra=Categories.Development)
-    profiles_dir        : Path = Field(default=Path('profiles'), description="Directory for graph profiles", json_schema_extra=Categories.Development)
-
-    version             : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
+    use_memory_db:                 bool = Field(default=False,              description="Use in-memory database. Useful for development.")
+    dev_reload:                    bool = Field(default=False,              description="Automatically reload when Python sources are changed. Does not reload node definitions.")
+    profile_graphs:                bool = Field(default=False,              description="Enable graph profiling using `cProfile`.")
+    profile_prefix:       Optional[str] = Field(default=None,               description="An optional prefix for profile output files.")
+    profiles_dir:                  Path = Field(default=Path("profiles"),   description="Path to profiles output directory.")
 
     # CACHE
-    ram                 : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    vram                : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
-    lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", json_schema_extra=Categories.ModelCache, )
-    log_memory_usage    : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
+    ram:                          float = Field(default=DEFAULT_RAM_CACHE, gt=0, description="Maximum memory amount used by memory model cache for rapid switching (GB).")
+    vram:                         float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (GB).")
+    convert_cache:                float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB).")
+    lazy_offload:                  bool = Field(default=True,               description="Keep models in VRAM until their space is needed.")
+    log_memory_usage:              bool = Field(default=False,              description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.")
 
     # DEVICE
-    device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", json_schema_extra=Categories.Device)
-    precision           : Literal["auto", "float16", "bfloat16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
+    device:                      DEVICE = Field(default="auto",             description="Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.")
+    precision:                PRECISION = Field(default="auto",             description="Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.")
 
     # GENERATION
-    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", json_schema_extra=Categories.Generation)
-    attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", json_schema_extra=Categories.Generation)
-    attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', json_schema_extra=Categories.Generation)
-    force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Generation)
-    png_compress_level  : int = Field(default=1, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
-
-    # QUEUE
-    max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", json_schema_extra=Categories.Queue)
+    sequential_guidance:           bool = Field(default=False,              description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.")
+    attention_type:      ATTENTION_TYPE = Field(default="auto",             description="Attention type.")
+    attention_slice_size: ATTENTION_SLICE_SIZE = Field(default="auto",      description='Slice size, valid when attention_type=="sliced".')
+    force_tiled_decode:            bool = Field(default=False,              description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty).")
+    pil_compress_level:             int = Field(default=1,                  description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = no compression, 1 = fastest with slightly larger filesize, 9 = slowest with smallest filesize. 1 is typically the best setting.")
+    max_queue_size:                 int = Field(default=10000, gt=0,        description="Maximum number of items in the session queue.")
 
     # NODES
-    allow_nodes         : Optional[List[str]] = Field(default=None, description="List of nodes to allow. Omit to allow all.", json_schema_extra=Categories.Nodes)
-    deny_nodes          : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", json_schema_extra=Categories.Nodes)
-    node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory", json_schema_extra=Categories.Nodes)
+    allow_nodes:    Optional[list[str]] = Field(default=None,               description="List of nodes to allow. Omit to allow all.")
+    deny_nodes:     Optional[list[str]] = Field(default=None,               description="List of nodes to deny. Omit to deny none.")
+    node_cache_size:                int = Field(default=512,                description="How many cached nodes to keep in memory.")
 
-    # MODEL IMPORT
-    civitai_api_key       : Optional[str] = Field(default=os.environ.get("CIVITAI_API_KEY"), description="API key for CivitAI", json_schema_extra=Categories.Other)
+    # MODEL INSTALL
+    hashing_algorithm: HASHING_ALGORITHMS = Field(default="blake3",         description="Model hashing algorthim for model installs. 'blake3' is best for SSDs. 'blake3_single' is best for spinning disk HDDs. 'random' disables hashing, instead assigning a UUID to models. Useful when using a memory db to reduce model installation time, or if you don't care about storing stable hashes for models. Alternatively, any other hashlib algorithm is accepted, though these are not nearly as performant as blake3.")
+    remote_api_tokens: Optional[list[URLRegexTokenPair]] = Field(default=None, description="List of regular expression and token pairs used when downloading models from URLs. The download URL is tested against the regex, and if it matches, the token is provided in as a Bearer token.")
 
-    # DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
-    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", json_schema_extra=Categories.MemoryPerformance)
-    max_cache_size      : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", json_schema_extra=Categories.MemoryPerformance)
-    max_vram_cache_size : Optional[float] = Field(default=None, ge=0, description="Amount of VRAM reserved for model storage", json_schema_extra=Categories.MemoryPerformance)
-    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", json_schema_extra=Categories.MemoryPerformance)
-    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.MemoryPerformance)
-    lora_dir            : Optional[Path] = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', json_schema_extra=Categories.Paths)
-    embedding_dir       : Optional[Path] = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
-    controlnet_dir      : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
-
-    # this is not referred to in the source code and can be removed entirely
-    #free_gpu_mem        : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", json_schema_extra=Categories.MemoryPerformance)
-
-    # See InvokeAIAppConfig subclass below for CACHE and DEVICE categories
     # fmt: on
 
-    model_config = SettingsConfigDict(validate_assignment=True, env_prefix="INVOKEAI")
+    model_config = SettingsConfigDict(env_prefix="INVOKEAI_", env_ignore_empty=True)
 
-    def parse_args(
-        self,
-        argv: Optional[list[str]] = None,
-        conf: Optional[DictConfig] = None,
-        clobber: Optional[bool] = False,
-    ) -> None:
+    def update_config(self, config: dict[str, Any] | InvokeAIAppConfig, clobber: bool = True) -> None:
+        """Updates the config, overwriting existing values.
+
+        Args:
+            config: A dictionary of config settings, or instance of `InvokeAIAppConfig`. If an instance of \
+                `InvokeAIAppConfig`, only the explicitly set fields will be merged into the singleton config.
+            clobber: If `True`, overwrite existing values. If `False`, only update fields that are not already set.
         """
-        Update settings with contents of init file, environment, and command-line settings.
 
-        :param conf: alternate Omegaconf dictionary object
-        :param argv: aternate sys.argv list
-        :param clobber: ovewrite any initialization parameters passed during initialization
+        if isinstance(config, dict):
+            new_config = self.model_validate(config)
+        else:
+            new_config = config
+
+        for field_name in new_config.model_fields_set:
+            new_value = getattr(new_config, field_name)
+            current_value = getattr(self, field_name)
+
+            if field_name in self.model_fields_set and not clobber:
+                continue
+
+            if new_value != current_value:
+                setattr(self, field_name, new_value)
+
+    def write_file(self, dest_path: Path) -> None:
+        """Write the current configuration to file. This will overwrite the existing file.
+
+        A `meta` stanza is added to the top of the file, containing metadata about the config file. This is not stored in the config object.
+
+        Args:
+            dest_path: Path to write the config to.
         """
-        # Set the runtime root directory. We parse command-line switches here
-        # in order to pick up the --root_dir option.
-        super().parse_args(argv)
-        loaded_conf = None
-        if conf is None:
-            try:
-                loaded_conf = OmegaConf.load(self.root_dir / INIT_FILE)
-            except Exception:
-                pass
-        if isinstance(loaded_conf, DictConfig):
-            InvokeAISettings.initconf = loaded_conf
-        else:
-            InvokeAISettings.initconf = conf
+        with open(dest_path, "w") as file:
+            # Meta fields should be written in a separate stanza
+            meta_dict = self.model_dump(mode="json", include={"schema_version"})
+            # Only include the legacy_models_yaml_path if it's set
+            if self.legacy_models_yaml_path:
+                meta_dict.update(self.model_dump(mode="json", include={"legacy_models_yaml_path"}))
 
-        # parse args again in order to pick up settings in configuration file
-        super().parse_args(argv)
+            # User settings
+            config_dict = self.model_dump(
+                mode="json",
+                exclude_unset=True,
+                exclude_defaults=True,
+                exclude={"schema_version", "legacy_models_yaml_path"},
+            )
 
-        if self.singleton_init and not clobber:
-            # When setting values in this way, set validate_assignment to true if you want to validate the value.
-            for k, v in self.singleton_init.items():
-                setattr(self, k, v)
+            file.write("# Internal metadata - do not edit:\n")
+            file.write(yaml.dump(meta_dict, sort_keys=False))
+            file.write("\n")
+            file.write("# Put user settings here:\n")
+            if len(config_dict) > 0:
+                file.write(yaml.dump(config_dict, sort_keys=False))
 
-    @classmethod
-    def get_config(cls, **kwargs: Any) -> InvokeAIAppConfig:
-        """Return a singleton InvokeAIAppConfig configuration object."""
-        if (
-            cls.singleton_config is None
-            or type(cls.singleton_config) is not cls
-            or (kwargs and cls.singleton_init != kwargs)
-        ):
-            cls.singleton_config = cls(**kwargs)
-            cls.singleton_init = kwargs
-        return cls.singleton_config
+    def merge_from_file(self, source_path: Optional[Path] = None) -> None:
+        """Read the config from the `invokeai.yaml` file, migrating it if necessary and merging it into the singleton config.
 
-    @property
-    def root_path(self) -> Path:
-        """Path to the runtime root directory."""
-        if self.root:
-            root = Path(self.root).expanduser().absolute()
-        else:
-            root = self.find_root().expanduser().absolute()
-        self.root = root  # insulate ourselves from relative paths that may change
-        return root.resolve()
+        This function will write to the `invokeai.yaml` file if the config is migrated.
 
-    @property
-    def root_dir(self) -> Path:
-        """Alias for above."""
-        return self.root_path
+        Args:
+            source_path: Path to the config file. If not provided, the default path is used.
+        """
+        path = source_path or self.init_file_path
+        config_from_file = load_and_migrate_config(path)
+        # Clobbering here will overwrite any settings that were set via environment variables
+        self.update_config(config_from_file, clobber=False)
+
+    def set_root(self, root: Path) -> None:
+        """Set the runtime root directory. This is typically set using a CLI arg."""
+        assert isinstance(root, Path)
+        self._root = root
 
     def _resolve(self, partial_path: Path) -> Path:
         return (self.root_path / partial_path).resolve()
 
+    @property
+    def root_path(self) -> Path:
+        """Path to the runtime root directory, resolved to an absolute path."""
+        if self._root:
+            root = Path(self._root).expanduser().absolute()
+        else:
+            root = self.find_root().expanduser().absolute()
+        self._root = root  # insulate ourselves from relative paths that may change
+        return root.resolve()
+
     @property
     def init_file_path(self) -> Path:
-        """Path to invokeai.yaml."""
+        """Path to invokeai.yaml, resolved to an absolute path.."""
         resolved_path = self._resolve(INIT_FILE)
         assert resolved_path is not None
         return resolved_path
 
     @property
-    def output_path(self) -> Optional[Path]:
-        """Path to defaults outputs directory."""
-        return self._resolve(self.outdir)
+    def autoimport_path(self) -> Path:
+        """Path to the autoimports directory, resolved to an absolute path.."""
+        return self._resolve(self.autoimport_dir)
+
+    @property
+    def outputs_path(self) -> Optional[Path]:
+        """Path to the outputs directory, resolved to an absolute path.."""
+        return self._resolve(self.outputs_dir)
 
     @property
     def db_path(self) -> Path:
-        """Path to the invokeai.db file."""
+        """Path to the invokeai.db file, resolved to an absolute path.."""
         db_dir = self._resolve(self.db_dir)
         assert db_dir is not None
         return db_dir / DB_FILE
 
-    @property
-    def model_conf_path(self) -> Path:
-        """Path to models configuration file."""
-        return self._resolve(self.conf_path)
-
     @property
     def legacy_conf_path(self) -> Path:
-        """Path to directory of legacy configuration files (e.g. v1-inference.yaml)."""
+        """Path to directory of legacy configuration files (e.g. v1-inference.yaml), resolved to an absolute path.."""
         return self._resolve(self.legacy_conf_dir)
 
     @property
     def models_path(self) -> Path:
-        """Path to the models directory."""
+        """Path to the models directory, resolved to an absolute path.."""
         return self._resolve(self.models_dir)
 
+    @property
+    def convert_cache_path(self) -> Path:
+        """Path to the converted cache models directory, resolved to an absolute path.."""
+        return self._resolve(self.convert_cache_dir)
+
     @property
     def custom_nodes_path(self) -> Path:
-        """Path to the custom nodes directory."""
+        """Path to the custom nodes directory, resolved to an absolute path.."""
         custom_nodes_path = self._resolve(self.custom_nodes_dir)
         assert custom_nodes_path is not None
         return custom_nodes_path
 
-    # the following methods support legacy calls leftover from the Globals era
-    @property
-    def full_precision(self) -> bool:
-        """Return true if precision set to float32."""
-        return self.precision == "float32"
-
-    @property
-    def try_patchmatch(self) -> bool:
-        """Return true if patchmatch true."""
-        return self.patchmatch
-
-    @property
-    def nsfw_checker(self) -> bool:
-        """Return value for NSFW checker. The NSFW node is always active and disabled from Web UI."""
-        return True
-
-    @property
-    def invisible_watermark(self) -> bool:
-        """Return value of invisible watermark. It is always active and disabled from Web UI."""
-        return True
-
-    @property
-    def ram_cache_size(self) -> Union[Literal["auto"], float]:
-        """Return the ram cache size using the legacy or modern setting."""
-        return self.max_cache_size or self.ram
-
-    @property
-    def vram_cache_size(self) -> Union[Literal["auto"], float]:
-        """Return the vram cache size using the legacy or modern setting."""
-        return self.max_vram_cache_size or self.vram
-
-    @property
-    def use_cpu(self) -> bool:
-        """Return true if the device is set to CPU or the always_use_cpu flag is set."""
-        return self.always_use_cpu or self.device == "cpu"
-
-    @property
-    def disable_xformers(self) -> bool:
-        """Return true if enable_xformers is false (reversed logic) and attention type is not set to xformers."""
-        disabled_in_config = not self.xformers_enabled
-        return disabled_in_config and self.attention_type != "xformers"
-
     @property
     def profiles_path(self) -> Path:
-        """Path to the graph profiles directory."""
+        """Path to the graph profiles directory, resolved to an absolute path.."""
         return self._resolve(self.profiles_dir)
 
     @staticmethod
     def find_root() -> Path:
         """Choose the runtime root directory when not specified on command line or init file."""
-        return _find_root()
+        venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
+        if os.environ.get("INVOKEAI_ROOT"):
+            root = Path(os.environ["INVOKEAI_ROOT"])
+        elif any((venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]):
+            root = (venv.parent).resolve()
+        else:
+            root = Path("~/invokeai").expanduser().resolve()
+        return root
 
 
-def get_invokeai_config(**kwargs: Any) -> InvokeAIAppConfig:
-    """Legacy function which returns InvokeAIAppConfig.get_config()."""
-    return InvokeAIAppConfig.get_config(**kwargs)
+def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
+    """Migrate a v3 config dictionary to a current config object.
+
+    Args:
+        config_dict: A dictionary of settings from a v3 config file.
+
+    Returns:
+        An instance of `InvokeAIAppConfig` with the migrated settings.
+
+    """
+    parsed_config_dict: dict[str, Any] = {}
+    for _category_name, category_dict in config_dict["InvokeAI"].items():
+        for k, v in category_dict.items():
+            # `outdir` was renamed to `outputs_dir` in v4
+            if k == "outdir":
+                parsed_config_dict["outputs_dir"] = v
+            # `max_cache_size` was renamed to `ram` some time in v3, but both names were used
+            if k == "max_cache_size" and "ram" not in category_dict:
+                parsed_config_dict["ram"] = v
+            # `max_vram_cache_size` was renamed to `vram` some time in v3, but both names were used
+            if k == "max_vram_cache_size" and "vram" not in category_dict:
+                parsed_config_dict["vram"] = v
+            if k == "conf_path":
+                parsed_config_dict["legacy_models_yaml_path"] = v
+            elif k in InvokeAIAppConfig.model_fields:
+                # skip unknown fields
+                parsed_config_dict[k] = v
+    config = InvokeAIAppConfig.model_validate(parsed_config_dict)
+
+    return config
 
 
-def _find_root() -> Path:
-    venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
-    if os.environ.get("INVOKEAI_ROOT"):
-        root = Path(os.environ["INVOKEAI_ROOT"])
-    elif any((venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]):
-        root = (venv.parent).resolve()
+def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
+    """Load and migrate a config file to the latest version.
+
+    Args:
+        config_path: Path to the config file.
+
+    Returns:
+        An instance of `InvokeAIAppConfig` with the loaded and migrated settings.
+    """
+    assert config_path.suffix == ".yaml"
+    with open(config_path) as file:
+        loaded_config_dict = yaml.safe_load(file)
+
+    assert isinstance(loaded_config_dict, dict)
+
+    if "InvokeAI" in loaded_config_dict:
+        # This is a v3 config file, attempt to migrate it
+        shutil.copy(config_path, config_path.with_suffix(".yaml.bak"))
+        try:
+            config = migrate_v3_config_dict(loaded_config_dict)
+        except Exception as e:
+            shutil.copy(config_path.with_suffix(".yaml.bak"), config_path)
+            raise RuntimeError(f"Failed to load and migrate v3 config file {config_path}: {e}") from e
+        # By excluding defaults, we ensure that the new config file only contains the settings that were explicitly set
+        config.write_file(config_path)
+        return config
     else:
-        root = Path("~/invokeai").expanduser().resolve()
-    return root
+        # Attempt to load as a v4 config file
+        try:
+            # Meta is not included in the model fields, so we need to validate it separately
+            config = InvokeAIAppConfig.model_validate(loaded_config_dict)
+            assert (
+                config.schema_version == CONFIG_SCHEMA_VERSION
+            ), f"Invalid schema version, expected {CONFIG_SCHEMA_VERSION}: {config.schema_version}"
+            return config
+        except Exception as e:
+            raise RuntimeError(f"Failed to load config file {config_path}: {e}") from e
+
+
+@lru_cache(maxsize=1)
+def get_config() -> InvokeAIAppConfig:
+    """Return the global singleton app config.
+
+    When called, this function will parse the CLI args and merge in config from the `invokeai.yaml` config file.
+    """
+    config = InvokeAIAppConfig()
+
+    args = InvokeAIArgs.args
+
+    # CLI args trump environment variables
+    if root := getattr(args, "root", None):
+        config.set_root(Path(root))
+    if ignore_missing_core_models := getattr(args, "ignore_missing_core_models", None):
+        config.ignore_missing_core_models = ignore_missing_core_models
+
+    # TODO(psyche): This shouldn't be wrapped in a try/catch. The configuration script imports a number of classes
+    # from throughout the app, which in turn call get_config(). At that time, there may not be a config file to
+    # read from, and this raises.
+    #
+    # Once we move all* model installation to the web app, the configure script will not be reaching into the main app
+    # and we can make this an unhandled error, which feels correct.
+    #
+    # *all user-facing models. Core model installation will still be handled by the configure/install script.
+
+    try:
+        config.merge_from_file()
+    except FileNotFoundError:
+        pass
+
+    return config

invokeai/app/services/download/__init__.py

@@ -1,4 +1,5 @@
 """Init file for download queue."""
+
 from .download_base import DownloadJob, DownloadJobStatus, DownloadQueueServiceBase, UnknownJobIDException
 from .download_default import DownloadQueueService, TqdmProgress
 

invokeai/app/services/download/download_base.py

@@ -260,3 +260,16 @@ class DownloadQueueServiceBase(ABC):
     def join(self) -> None:
         """Wait until all jobs are off the queue."""
         pass
+
+    @abstractmethod
+    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
+        """Wait until the indicated download job has reached a terminal state.
+
+        This will block until the indicated install job has completed,
+        been cancelled, or errored out.
+
+        :param job: The job to wait on.
+        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
+        the job hasn't completed within the indicated time.
+        """
+        pass

invokeai/app/services/download/download_default.py

@@ -4,10 +4,11 @@
 import os
 import re
 import threading
+import time
 import traceback
 from pathlib import Path
 from queue import Empty, PriorityQueue
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Set
 
 import requests
 from pydantic.networks import AnyHttpUrl
@@ -48,11 +49,12 @@ class DownloadQueueService(DownloadQueueServiceBase):
         :param max_parallel_dl: Number of simultaneous downloads allowed [5].
         :param requests_session: Optional requests.sessions.Session object, for unit tests.
         """
-        self._jobs = {}
+        self._jobs: Dict[int, DownloadJob] = {}
         self._next_job_id = 0
-        self._queue = PriorityQueue()
+        self._queue: PriorityQueue[DownloadJob] = PriorityQueue()
         self._stop_event = threading.Event()
-        self._worker_pool = set()
+        self._job_completed_event = threading.Event()
+        self._worker_pool: Set[threading.Thread] = set()
         self._lock = threading.Lock()
         self._logger = InvokeAILogger.get_logger("DownloadQueueService")
         self._event_bus = event_bus
@@ -188,6 +190,16 @@ class DownloadQueueService(DownloadQueueServiceBase):
             if not job.in_terminal_state:
                 self.cancel_job(job)
 
+    def wait_for_job(self, job: DownloadJob, timeout: int = 0) -> DownloadJob:
+        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
+        start = time.time()
+        while not job.in_terminal_state:
+            if self._job_completed_event.wait(timeout=0.25):  # in case we miss an event
+                self._job_completed_event.clear()
+            if timeout > 0 and time.time() - start > timeout:
+                raise TimeoutError("Timeout exceeded")
+        return job
+
     def _start_workers(self, max_workers: int) -> None:
         """Start the requested number of worker threads."""
         self._stop_event.clear()
@@ -212,7 +224,6 @@ class DownloadQueueService(DownloadQueueServiceBase):
                 job.job_started = get_iso_timestamp()
                 self._do_download(job)
                 self._signal_job_complete(job)
-
             except (OSError, HTTPError) as excp:
                 job.error_type = excp.__class__.__name__ + f"({str(excp)})"
                 job.error = traceback.format_exc()
@@ -223,6 +234,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
             finally:
                 job.job_ended = get_iso_timestamp()
+                self._job_completed_event.set()  # signal a change to terminal state
                 self._queue.task_done()
         self._logger.debug(f"Download queue worker thread {threading.current_thread().name} exiting.")
 
@@ -407,11 +419,11 @@ class DownloadQueueService(DownloadQueueServiceBase):
 
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
-#   download_service.download('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().job_update
+#   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))
 class TqdmProgress(object):
     """TQDM-based progress bar object to use in on_progress handlers."""
 
-    _bars: Dict[int, tqdm]  # the tqdm object
+    _bars: Dict[int, tqdm]  # type: ignore
     _last: Dict[int, int]  # last bytes downloaded
 
     def __init__(self) -> None:  # noqa D107

invokeai/app/services/events/events_base.py

@@ -3,7 +3,7 @@
 
 from typing import Any, Dict, List, Optional, Union
 
-from invokeai.app.services.invocation_processor.invocation_processor_common import ProgressImage
+from invokeai.app.services.session_processor.session_processor_common import ProgressImage
 from invokeai.app.services.session_queue.session_queue_common import (
     BatchStatus,
     EnqueueBatchResult,
@@ -11,12 +11,13 @@ from invokeai.app.services.session_queue.session_queue_common import (
     SessionQueueStatus,
 )
 from invokeai.app.util.misc import get_timestamp
-from invokeai.backend.model_management.model_manager import LoadedModelInfo
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
+from invokeai.backend.model_manager import AnyModelConfig
+from invokeai.backend.model_manager.config import SubModelType
 
 
 class EventServiceBase:
     queue_event: str = "queue_event"
+    bulk_download_event: str = "bulk_download_event"
     download_event: str = "download_event"
     model_event: str = "model_event"
 
@@ -25,6 +26,14 @@ class EventServiceBase:
     def dispatch(self, event_name: str, payload: Any) -> None:
         pass
 
+    def _emit_bulk_download_event(self, event_name: str, payload: dict) -> None:
+        """Bulk download events are emitted to a room with queue_id as the room name"""
+        payload["timestamp"] = get_timestamp()
+        self.dispatch(
+            event_name=EventServiceBase.bulk_download_event,
+            payload={"event": event_name, "data": payload},
+        )
+
     def __emit_queue_event(self, event_name: str, payload: dict) -> None:
         """Queue events are emitted to a room with queue_id as the room name"""
         payload["timestamp"] = get_timestamp()
@@ -72,7 +81,7 @@ class EventServiceBase:
                 "graph_execution_state_id": graph_execution_state_id,
                 "node_id": node_id,
                 "source_node_id": source_node_id,
-                "progress_image": progress_image.model_dump() if progress_image is not None else None,
+                "progress_image": progress_image.model_dump(mode="json") if progress_image is not None else None,
                 "step": step,
                 "order": order,
                 "total_steps": total_steps,
@@ -171,10 +180,8 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
     ) -> None:
         """Emitted when a model is requested"""
         self.__emit_queue_event(
@@ -184,10 +191,8 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_name": model_name,
-                "base_model": base_model,
-                "model_type": model_type,
-                "submodel": submodel,
+                "model_config": model_config.model_dump(mode="json"),
+                "submodel_type": submodel_type,
             },
         )
 
@@ -197,11 +202,8 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
-        loaded_model_info: LoadedModelInfo,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
         self.__emit_queue_event(
@@ -211,59 +213,8 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "model_name": model_name,
-                "base_model": base_model,
-                "model_type": model_type,
-                "submodel": submodel,
-                "hash": loaded_model_info.hash,
-                "location": str(loaded_model_info.location),
-                "precision": str(loaded_model_info.precision),
-            },
-        )
-
-    def emit_session_retrieval_error(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        error_type: str,
-        error: str,
-    ) -> None:
-        """Emitted when session retrieval fails"""
-        self.__emit_queue_event(
-            event_name="session_retrieval_error",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "error_type": error_type,
-                "error": error,
-            },
-        )
-
-    def emit_invocation_retrieval_error(
-        self,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        node_id: str,
-        error_type: str,
-        error: str,
-    ) -> None:
-        """Emitted when invocation retrieval fails"""
-        self.__emit_queue_event(
-            event_name="invocation_retrieval_error",
-            payload={
-                "queue_id": queue_id,
-                "queue_item_id": queue_item_id,
-                "queue_batch_id": queue_batch_id,
-                "graph_execution_state_id": graph_execution_state_id,
-                "node_id": node_id,
-                "error_type": error_type,
-                "error": error,
+                "model_config": model_config.model_dump(mode="json"),
+                "submodel_type": submodel_type,
             },
         )
 
@@ -308,8 +259,8 @@ class EventServiceBase:
                     "started_at": str(session_queue_item.started_at) if session_queue_item.started_at else None,
                     "completed_at": str(session_queue_item.completed_at) if session_queue_item.completed_at else None,
                 },
-                "batch_status": batch_status.model_dump(),
-                "queue_status": queue_status.model_dump(),
+                "batch_status": batch_status.model_dump(mode="json"),
+                "queue_status": queue_status.model_dump(mode="json"),
             },
         )
 
@@ -411,6 +362,7 @@ class EventServiceBase:
         bytes: int,
         total_bytes: int,
         parts: List[Dict[str, Union[str, int]]],
+        id: int,
     ) -> None:
         """
         Emit at intervals while the install job is in progress (remote models only).
@@ -430,6 +382,7 @@ class EventServiceBase:
                 "bytes": bytes,
                 "total_bytes": total_bytes,
                 "parts": parts,
+                "id": id,
             },
         )
 
@@ -444,7 +397,7 @@ class EventServiceBase:
             payload={"source": source},
         )
 
-    def emit_model_install_completed(self, source: str, key: str, total_bytes: Optional[int] = None) -> None:
+    def emit_model_install_completed(self, source: str, key: str, id: int, total_bytes: Optional[int] = None) -> None:
         """
         Emit when an install job is completed successfully.
 
@@ -454,14 +407,10 @@ class EventServiceBase:
         """
         self.__emit_model_event(
             event_name="model_install_completed",
-            payload={
-                "source": source,
-                "total_bytes": total_bytes,
-                "key": key,
-            },
+            payload={"source": source, "total_bytes": total_bytes, "key": key, "id": id},
         )
 
-    def emit_model_install_cancelled(self, source: str) -> None:
+    def emit_model_install_cancelled(self, source: str, id: int) -> None:
         """
         Emit when an install job is cancelled.
 
@@ -469,15 +418,10 @@ class EventServiceBase:
         """
         self.__emit_model_event(
             event_name="model_install_cancelled",
-            payload={"source": source},
+            payload={"source": source, "id": id},
         )
 
-    def emit_model_install_error(
-        self,
-        source: str,
-        error_type: str,
-        error: str,
-    ) -> None:
+    def emit_model_install_error(self, source: str, error_type: str, error: str, id: int) -> None:
         """
         Emit when an install job encounters an exception.
 
@@ -487,9 +431,45 @@ class EventServiceBase:
         """
         self.__emit_model_event(
             event_name="model_install_error",
+            payload={"source": source, "error_type": error_type, "error": error, "id": id},
+        )
+
+    def emit_bulk_download_started(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> None:
+        """Emitted when a bulk download starts"""
+        self._emit_bulk_download_event(
+            event_name="bulk_download_started",
             payload={
-                "source": source,
-                "error_type": error_type,
+                "bulk_download_id": bulk_download_id,
+                "bulk_download_item_id": bulk_download_item_id,
+                "bulk_download_item_name": bulk_download_item_name,
+            },
+        )
+
+    def emit_bulk_download_completed(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str
+    ) -> None:
+        """Emitted when a bulk download completes"""
+        self._emit_bulk_download_event(
+            event_name="bulk_download_completed",
+            payload={
+                "bulk_download_id": bulk_download_id,
+                "bulk_download_item_id": bulk_download_item_id,
+                "bulk_download_item_name": bulk_download_item_name,
+            },
+        )
+
+    def emit_bulk_download_failed(
+        self, bulk_download_id: str, bulk_download_item_id: str, bulk_download_item_name: str, error: str
+    ) -> None:
+        """Emitted when a bulk download fails"""
+        self._emit_bulk_download_event(
+            event_name="bulk_download_failed",
+            payload={
+                "bulk_download_id": bulk_download_id,
+                "bulk_download_item_id": bulk_download_item_id,
+                "bulk_download_item_name": bulk_download_item_name,
                 "error": error,
             },
         )

invokeai/app/services/image_files/image_files_disk.py

@@ -82,7 +82,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
                 image_path,
                 "PNG",
                 pnginfo=pnginfo,
-                compress_level=self.__invoker.services.configuration.png_compress_level,
+                compress_level=self.__invoker.services.configuration.pil_compress_level,
             )
 
             thumbnail_name = get_thumbnail_name(image_name)

invokeai/app/services/invocation_cache/invocation_cache_base.py

@@ -41,8 +41,9 @@ class InvocationCacheBase(ABC):
         """Clears the cache"""
         pass
 
+    @staticmethod
     @abstractmethod
-    def create_key(self, invocation: BaseInvocation) -> int:
+    def create_key(invocation: BaseInvocation) -> int:
         """Gets the key for the invocation's cache item"""
         pass
 

invokeai/app/services/invocation_cache/invocation_cache_memory.py

@@ -61,9 +61,7 @@ class MemoryInvocationCache(InvocationCacheBase):
             self._delete_oldest_access(number_to_delete)
             self._cache[key] = CachedItem(
                 invocation_output,
-                invocation_output.model_dump_json(
-                    warnings=False, exclude_defaults=True, exclude_unset=True, include={"type"}
-                ),
+                invocation_output.model_dump_json(warnings=False, exclude_defaults=True, exclude_unset=True),
             )
 
     def _delete_oldest_access(self, number_to_delete: int) -> None:
@@ -81,7 +79,7 @@ class MemoryInvocationCache(InvocationCacheBase):
         with self._lock:
             return self._delete(key)
 
-    def clear(self, *args, **kwargs) -> None:
+    def clear(self) -> None:
         with self._lock:
             if self._max_cache_size == 0:
                 return

invokeai/app/services/invocation_processor/invocation_processor_base.py

@@ -1,5 +0,0 @@
-from abc import ABC
-
-
-class InvocationProcessorABC(ABC):  # noqa: B024
-    pass

invokeai/app/services/invocation_processor/invocation_processor_common.py

@@ -1,15 +0,0 @@
-from pydantic import BaseModel, Field
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")
-
-
-class CanceledException(Exception):
-    """Execution canceled by user."""
-
-    pass

invokeai/app/services/invocation_processor/invocation_processor_default.py

@@ -1,241 +0,0 @@
-import time
-import traceback
-from contextlib import suppress
-from threading import BoundedSemaphore, Event, Thread
-from typing import Optional
-
-import invokeai.backend.util.logging as logger
-from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
-from invokeai.app.services.invocation_stats.invocation_stats_common import (
-    GESStatsNotFoundError,
-)
-from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
-from invokeai.app.util.profiler import Profiler
-
-from ..invoker import Invoker
-from .invocation_processor_base import InvocationProcessorABC
-from .invocation_processor_common import CanceledException
-
-
-class DefaultInvocationProcessor(InvocationProcessorABC):
-    __invoker_thread: Thread
-    __stop_event: Event
-    __invoker: Invoker
-    __threadLimit: BoundedSemaphore
-
-    def start(self, invoker: Invoker) -> None:
-        # if we do want multithreading at some point, we could make this configurable
-        self.__threadLimit = BoundedSemaphore(1)
-        self.__invoker = invoker
-        self.__stop_event = Event()
-        self.__invoker_thread = Thread(
-            name="invoker_processor",
-            target=self.__process,
-            kwargs={"stop_event": self.__stop_event},
-        )
-        self.__invoker_thread.daemon = True  # TODO: make async and do not use threads
-        self.__invoker_thread.start()
-
-    def stop(self, *args, **kwargs) -> None:
-        self.__stop_event.set()
-
-    def __process(self, stop_event: Event):
-        try:
-            self.__threadLimit.acquire()
-            queue_item: Optional[InvocationQueueItem] = None
-
-            profiler = (
-                Profiler(
-                    logger=self.__invoker.services.logger,
-                    output_dir=self.__invoker.services.configuration.profiles_path,
-                    prefix=self.__invoker.services.configuration.profile_prefix,
-                )
-                if self.__invoker.services.configuration.profile_graphs
-                else None
-            )
-
-            def stats_cleanup(graph_execution_state_id: str) -> None:
-                if profiler:
-                    profile_path = profiler.stop()
-                    stats_path = profile_path.with_suffix(".json")
-                    self.__invoker.services.performance_statistics.dump_stats(
-                        graph_execution_state_id=graph_execution_state_id, output_path=stats_path
-                    )
-                with suppress(GESStatsNotFoundError):
-                    self.__invoker.services.performance_statistics.log_stats(graph_execution_state_id)
-                    self.__invoker.services.performance_statistics.reset_stats(graph_execution_state_id)
-
-            while not stop_event.is_set():
-                try:
-                    queue_item = self.__invoker.services.queue.get()
-                except Exception as e:
-                    self.__invoker.services.logger.error("Exception while getting from queue:\n%s" % e)
-
-                if not queue_item:  # Probably stopping
-                    # do not hammer the queue
-                    time.sleep(0.5)
-                    continue
-
-                if profiler and profiler.profile_id != queue_item.graph_execution_state_id:
-                    profiler.start(profile_id=queue_item.graph_execution_state_id)
-
-                try:
-                    graph_execution_state = self.__invoker.services.graph_execution_manager.get(
-                        queue_item.graph_execution_state_id
-                    )
-                except Exception as e:
-                    self.__invoker.services.logger.error("Exception while retrieving session:\n%s" % e)
-                    self.__invoker.services.events.emit_session_retrieval_error(
-                        queue_batch_id=queue_item.session_queue_batch_id,
-                        queue_item_id=queue_item.session_queue_item_id,
-                        queue_id=queue_item.session_queue_id,
-                        graph_execution_state_id=queue_item.graph_execution_state_id,
-                        error_type=e.__class__.__name__,
-                        error=traceback.format_exc(),
-                    )
-                    continue
-
-                try:
-                    invocation = graph_execution_state.execution_graph.get_node(queue_item.invocation_id)
-                except Exception as e:
-                    self.__invoker.services.logger.error("Exception while retrieving invocation:\n%s" % e)
-                    self.__invoker.services.events.emit_invocation_retrieval_error(
-                        queue_batch_id=queue_item.session_queue_batch_id,
-                        queue_item_id=queue_item.session_queue_item_id,
-                        queue_id=queue_item.session_queue_id,
-                        graph_execution_state_id=queue_item.graph_execution_state_id,
-                        node_id=queue_item.invocation_id,
-                        error_type=e.__class__.__name__,
-                        error=traceback.format_exc(),
-                    )
-                    continue
-
-                # get the source node id to provide to clients (the prepared node id is not as useful)
-                source_node_id = graph_execution_state.prepared_source_mapping[invocation.id]
-
-                # Send starting event
-                self.__invoker.services.events.emit_invocation_started(
-                    queue_batch_id=queue_item.session_queue_batch_id,
-                    queue_item_id=queue_item.session_queue_item_id,
-                    queue_id=queue_item.session_queue_id,
-                    graph_execution_state_id=graph_execution_state.id,
-                    node=invocation.model_dump(),
-                    source_node_id=source_node_id,
-                )
-
-                # Invoke
-                try:
-                    graph_id = graph_execution_state.id
-                    with self.__invoker.services.performance_statistics.collect_stats(invocation, graph_id):
-                        # use the internal invoke_internal(), which wraps the node's invoke() method,
-                        # which handles a few things:
-                        # - nodes that require a value, but get it only from a connection
-                        # - referencing the invocation cache instead of executing the node
-                        context_data = InvocationContextData(
-                            invocation=invocation,
-                            session_id=graph_id,
-                            workflow=queue_item.workflow,
-                            source_node_id=source_node_id,
-                            queue_id=queue_item.session_queue_id,
-                            queue_item_id=queue_item.session_queue_item_id,
-                            batch_id=queue_item.session_queue_batch_id,
-                        )
-                        context = build_invocation_context(
-                            services=self.__invoker.services,
-                            context_data=context_data,
-                        )
-                        outputs = invocation.invoke_internal(context=context, services=self.__invoker.services)
-
-                        # Check queue to see if this is canceled, and skip if so
-                        if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
-                            continue
-
-                        # Save outputs and history
-                        graph_execution_state.complete(invocation.id, outputs)
-
-                        # Save the state changes
-                        self.__invoker.services.graph_execution_manager.set(graph_execution_state)
-
-                        # Send complete event
-                        self.__invoker.services.events.emit_invocation_complete(
-                            queue_batch_id=queue_item.session_queue_batch_id,
-                            queue_item_id=queue_item.session_queue_item_id,
-                            queue_id=queue_item.session_queue_id,
-                            graph_execution_state_id=graph_execution_state.id,
-                            node=invocation.model_dump(),
-                            source_node_id=source_node_id,
-                            result=outputs.model_dump(),
-                        )
-
-                except KeyboardInterrupt:
-                    pass
-
-                except CanceledException:
-                    stats_cleanup(graph_execution_state.id)
-                    pass
-
-                except Exception as e:
-                    error = traceback.format_exc()
-                    logger.error(error)
-
-                    # Save error
-                    graph_execution_state.set_node_error(invocation.id, error)
-
-                    # Save the state changes
-                    self.__invoker.services.graph_execution_manager.set(graph_execution_state)
-
-                    self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
-                    # Send error event
-                    self.__invoker.services.events.emit_invocation_error(
-                        queue_batch_id=queue_item.session_queue_batch_id,
-                        queue_item_id=queue_item.session_queue_item_id,
-                        queue_id=queue_item.session_queue_id,
-                        graph_execution_state_id=graph_execution_state.id,
-                        node=invocation.model_dump(),
-                        source_node_id=source_node_id,
-                        error_type=e.__class__.__name__,
-                        error=error,
-                    )
-                    pass
-
-                # Check queue to see if this is canceled, and skip if so
-                if self.__invoker.services.queue.is_canceled(graph_execution_state.id):
-                    continue
-
-                # Queue any further commands if invoking all
-                is_complete = graph_execution_state.is_complete()
-                if queue_item.invoke_all and not is_complete:
-                    try:
-                        self.__invoker.invoke(
-                            session_queue_batch_id=queue_item.session_queue_batch_id,
-                            session_queue_item_id=queue_item.session_queue_item_id,
-                            session_queue_id=queue_item.session_queue_id,
-                            graph_execution_state=graph_execution_state,
-                            workflow=queue_item.workflow,
-                            invoke_all=True,
-                        )
-                    except Exception as e:
-                        self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
-                        self.__invoker.services.events.emit_invocation_error(
-                            queue_batch_id=queue_item.session_queue_batch_id,
-                            queue_item_id=queue_item.session_queue_item_id,
-                            queue_id=queue_item.session_queue_id,
-                            graph_execution_state_id=graph_execution_state.id,
-                            node=invocation.model_dump(),
-                            source_node_id=source_node_id,
-                            error_type=e.__class__.__name__,
-                            error=traceback.format_exc(),
-                        )
-                elif is_complete:
-                    self.__invoker.services.events.emit_graph_execution_complete(
-                        queue_batch_id=queue_item.session_queue_batch_id,
-                        queue_item_id=queue_item.session_queue_item_id,
-                        queue_id=queue_item.session_queue_id,
-                        graph_execution_state_id=graph_execution_state.id,
-                    )
-                    stats_cleanup(graph_execution_state.id)
-
-        except KeyboardInterrupt:
-            pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor
-        finally:
-            self.__threadLimit.release()

invokeai/app/services/invocation_queue/invocation_queue_base.py

@@ -1,26 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-from abc import ABC, abstractmethod
-from typing import Optional
-
-from .invocation_queue_common import InvocationQueueItem
-
-
-class InvocationQueueABC(ABC):
-    """Abstract base class for all invocation queues"""
-
-    @abstractmethod
-    def get(self) -> InvocationQueueItem:
-        pass
-
-    @abstractmethod
-    def put(self, item: Optional[InvocationQueueItem]) -> None:
-        pass
-
-    @abstractmethod
-    def cancel(self, graph_execution_state_id: str) -> None:
-        pass
-
-    @abstractmethod
-    def is_canceled(self, graph_execution_state_id: str) -> bool:
-        pass

invokeai/app/services/invocation_queue/invocation_queue_common.py

@@ -1,23 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-import time
-from typing import Optional
-
-from pydantic import BaseModel, Field
-
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-
-
-class InvocationQueueItem(BaseModel):
-    graph_execution_state_id: str = Field(description="The ID of the graph execution state")
-    invocation_id: str = Field(description="The ID of the node being invoked")
-    session_queue_id: str = Field(description="The ID of the session queue from which this invocation queue item came")
-    session_queue_item_id: int = Field(
-        description="The ID of session queue item from which this invocation queue item came"
-    )
-    session_queue_batch_id: str = Field(
-        description="The ID of the session batch from which this invocation queue item came"
-    )
-    workflow: Optional[WorkflowWithoutID] = Field(description="The workflow associated with this queue item")
-    invoke_all: bool = Field(default=False)
-    timestamp: float = Field(default_factory=time.time)

invokeai/app/services/invocation_queue/invocation_queue_memory.py

@@ -1,44 +0,0 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
-import time
-from queue import Queue
-from typing import Optional
-
-from .invocation_queue_base import InvocationQueueABC
-from .invocation_queue_common import InvocationQueueItem
-
-
-class MemoryInvocationQueue(InvocationQueueABC):
-    __queue: Queue
-    __cancellations: dict[str, float]
-
-    def __init__(self):
-        self.__queue = Queue()
-        self.__cancellations = {}
-
-    def get(self) -> InvocationQueueItem:
-        item = self.__queue.get()
-
-        while (
-            isinstance(item, InvocationQueueItem)
-            and item.graph_execution_state_id in self.__cancellations
-            and self.__cancellations[item.graph_execution_state_id] > item.timestamp
-        ):
-            item = self.__queue.get()
-
-        # Clear old items
-        for graph_execution_state_id in list(self.__cancellations.keys()):
-            if self.__cancellations[graph_execution_state_id] < item.timestamp:
-                del self.__cancellations[graph_execution_state_id]
-
-        return item
-
-    def put(self, item: Optional[InvocationQueueItem]) -> None:
-        self.__queue.put(item)
-
-    def cancel(self, graph_execution_state_id: str) -> None:
-        if graph_execution_state_id not in self.__cancellations:
-            self.__cancellations[graph_execution_state_id] = time.time()
-
-    def is_canceled(self, graph_execution_state_id: str) -> bool:
-        return graph_execution_state_id in self.__cancellations

invokeai/app/services/invocation_services.py

@@ -16,6 +16,7 @@ if TYPE_CHECKING:
     from .board_images.board_images_base import BoardImagesServiceABC
     from .board_records.board_records_base import BoardRecordStorageBase
     from .boards.boards_base import BoardServiceABC
+    from .bulk_download.bulk_download_base import BulkDownloadBase
     from .config import InvokeAIAppConfig
     from .download import DownloadQueueServiceBase
     from .events.events_base import EventServiceBase
@@ -23,17 +24,12 @@ if TYPE_CHECKING:
     from .image_records.image_records_base import ImageRecordStorageBase
     from .images.images_base import ImageServiceABC
     from .invocation_cache.invocation_cache_base import InvocationCacheBase
-    from .invocation_processor.invocation_processor_base import InvocationProcessorABC
-    from .invocation_queue.invocation_queue_base import InvocationQueueABC
     from .invocation_stats.invocation_stats_base import InvocationStatsServiceBase
-    from .item_storage.item_storage_base import ItemStorageABC
-    from .model_install import ModelInstallServiceBase
+    from .model_images.model_images_base import ModelImageFileStorageBase
     from .model_manager.model_manager_base import ModelManagerServiceBase
-    from .model_records import ModelRecordServiceBase
     from .names.names_base import NameServiceBase
     from .session_processor.session_processor_base import SessionProcessorBase
     from .session_queue.session_queue_base import SessionQueueBase
-    from .shared.graph import GraphExecutionState
     from .urls.urls_base import UrlServiceBase
     from .workflow_records.workflow_records_base import WorkflowRecordsStorageBase
 
@@ -47,20 +43,17 @@ class InvocationServices:
         board_image_records: "BoardImageRecordStorageBase",
         boards: "BoardServiceABC",
         board_records: "BoardRecordStorageBase",
+        bulk_download: "BulkDownloadBase",
         configuration: "InvokeAIAppConfig",
         events: "EventServiceBase",
-        graph_execution_manager: "ItemStorageABC[GraphExecutionState]",
         images: "ImageServiceABC",
         image_files: "ImageFileStorageBase",
         image_records: "ImageRecordStorageBase",
         logger: "Logger",
+        model_images: "ModelImageFileStorageBase",
         model_manager: "ModelManagerServiceBase",
-        model_records: "ModelRecordServiceBase",
         download_queue: "DownloadQueueServiceBase",
-        model_install: "ModelInstallServiceBase",
-        processor: "InvocationProcessorABC",
         performance_statistics: "InvocationStatsServiceBase",
-        queue: "InvocationQueueABC",
         session_queue: "SessionQueueBase",
         session_processor: "SessionProcessorBase",
         invocation_cache: "InvocationCacheBase",
@@ -74,20 +67,17 @@ class InvocationServices:
         self.board_image_records = board_image_records
         self.boards = boards
         self.board_records = board_records
+        self.bulk_download = bulk_download
         self.configuration = configuration
         self.events = events
-        self.graph_execution_manager = graph_execution_manager
         self.images = images
         self.image_files = image_files
         self.image_records = image_records
         self.logger = logger
+        self.model_images = model_images
         self.model_manager = model_manager
-        self.model_records = model_records
         self.download_queue = download_queue
-        self.model_install = model_install
-        self.processor = processor
         self.performance_statistics = performance_statistics
-        self.queue = queue
         self.session_queue = session_queue
         self.session_processor = session_processor
         self.invocation_cache = invocation_cache

invokeai/app/services/invocation_stats/invocation_stats_base.py

@@ -3,7 +3,7 @@
 
 Usage:
 
-statistics = InvocationStatsService(graph_execution_manager)
+statistics = InvocationStatsService()
 with statistics.collect_stats(invocation, graph_execution_state.id):
       ... execute graphs...
 statistics.log_stats()
@@ -29,8 +29,8 @@ writes to the system log is stored in InvocationServices.performance_statistics.
 """
 
 from abc import ABC, abstractmethod
-from contextlib import AbstractContextManager
 from pathlib import Path
+from typing import ContextManager
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invocation_stats.invocation_stats_common import InvocationStatsSummary
@@ -40,18 +40,17 @@ class InvocationStatsServiceBase(ABC):
     "Abstract base class for recording node memory/time performance statistics"
 
     @abstractmethod
-    def __init__(self):
+    def __init__(self) -> None:
         """
         Initialize the InvocationStatsService and reset counters to zero
         """
-        pass
 
     @abstractmethod
     def collect_stats(
         self,
         invocation: BaseInvocation,
         graph_execution_state_id: str,
-    ) -> AbstractContextManager:
+    ) -> ContextManager[None]:
         """
         Return a context object that will capture the statistics on the execution
         of invocaation. Use with: to place around the part of the code that executes the invocation.
@@ -61,16 +60,12 @@ class InvocationStatsServiceBase(ABC):
         pass
 
     @abstractmethod
-    def reset_stats(self, graph_execution_state_id: str):
-        """
-        Reset all statistics for the indicated graph.
-        :param graph_execution_state_id: The id of the session whose stats to reset.
-        :raises GESStatsNotFoundError: if the graph isn't tracked in the stats.
-        """
+    def reset_stats(self):
+        """Reset all stored statistics."""
         pass
 
     @abstractmethod
-    def log_stats(self, graph_execution_state_id: str):
+    def log_stats(self, graph_execution_state_id: str) -> None:
         """
         Write out the accumulated statistics to the log or somewhere else.
         :param graph_execution_state_id: The id of the session whose stats to log.

invokeai/app/services/invocation_stats/invocation_stats_default.py

@@ -2,6 +2,7 @@ import json
 import time
 from contextlib import contextmanager
 from pathlib import Path
+from typing import Generator
 
 import psutil
 import torch
@@ -9,8 +10,7 @@ import torch
 import invokeai.backend.util.logging as logger
 from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.item_storage.item_storage_common import ItemNotFoundError
-from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.backend.model_manager.load.model_cache import CacheStats
 
 from .invocation_stats_base import InvocationStatsServiceBase
 from .invocation_stats_common import (
@@ -41,22 +41,23 @@ class InvocationStatsService(InvocationStatsServiceBase):
         self._invoker = invoker
 
     @contextmanager
-    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str):
+    def collect_stats(self, invocation: BaseInvocation, graph_execution_state_id: str) -> Generator[None, None, None]:
+        # This is to handle case of the model manager not being initialized, which happens
+        # during some tests.
+        services = self._invoker.services
         if not self._stats.get(graph_execution_state_id):
             # First time we're seeing this graph_execution_state_id.
             self._stats[graph_execution_state_id] = GraphExecutionStats()
             self._cache_stats[graph_execution_state_id] = CacheStats()
 
-            # Prune stale stats. There should be none since we're starting a new graph, but just in case.
-            self._prune_stale_stats()
-
         # Record state before the invocation.
         start_time = time.time()
         start_ram = psutil.Process().memory_info().rss
         if torch.cuda.is_available():
             torch.cuda.reset_peak_memory_stats()
-        if self._invoker.services.model_manager:
-            self._invoker.services.model_manager.collect_cache_stats(self._cache_stats[graph_execution_state_id])
+
+        assert services.model_manager.load is not None
+        services.model_manager.load.ram_cache.stats = self._cache_stats[graph_execution_state_id]
 
         try:
             # Let the invocation run.
@@ -73,42 +74,9 @@ class InvocationStatsService(InvocationStatsServiceBase):
             )
             self._stats[graph_execution_state_id].add_node_execution_stats(node_stats)
 
-    def _prune_stale_stats(self):
-        """Check all graphs being tracked and prune any that have completed/errored.
-
-        This shouldn't be necessary, but we don't have totally robust upstream handling of graph completions/errors, so
-        for now we call this function periodically to prevent them from accumulating.
-        """
-        to_prune: list[str] = []
-        for graph_execution_state_id in self._stats:
-            try:
-                graph_execution_state = self._invoker.services.graph_execution_manager.get(graph_execution_state_id)
-            except ItemNotFoundError:
-                # TODO(ryand): What would cause this? Should this exception just be allowed to propagate?
-                logger.warning(f"Failed to get graph state for {graph_execution_state_id}.")
-                continue
-
-            if not graph_execution_state.is_complete():
-                # The graph is still running, don't prune it.
-                continue
-
-            to_prune.append(graph_execution_state_id)
-
-        for graph_execution_state_id in to_prune:
-            del self._stats[graph_execution_state_id]
-            del self._cache_stats[graph_execution_state_id]
-
-        if len(to_prune) > 0:
-            logger.info(f"Pruned stale graph stats for {to_prune}.")
-
-    def reset_stats(self, graph_execution_state_id: str):
-        try:
-            del self._stats[graph_execution_state_id]
-            del self._cache_stats[graph_execution_state_id]
-        except KeyError as e:
-            raise GESStatsNotFoundError(
-                f"Attempted to clear statistics for unknown graph {graph_execution_state_id}: {e}."
-            ) from e
+    def reset_stats(self):
+        self._stats = {}
+        self._cache_stats = {}
 
     def get_stats(self, graph_execution_state_id: str) -> InvocationStatsSummary:
         graph_stats_summary = self._get_graph_summary(graph_execution_state_id)

invokeai/app/services/invoker.py

@@ -1,12 +1,7 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional
 
-from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
-
-from .invocation_queue.invocation_queue_common import InvocationQueueItem
 from .invocation_services import InvocationServices
-from .shared.graph import Graph, GraphExecutionState
 
 
 class Invoker:
@@ -18,51 +13,6 @@ class Invoker:
         self.services = services
         self._start()
 
-    def invoke(
-        self,
-        session_queue_id: str,
-        session_queue_item_id: int,
-        session_queue_batch_id: str,
-        graph_execution_state: GraphExecutionState,
-        workflow: Optional[WorkflowWithoutID] = None,
-        invoke_all: bool = False,
-    ) -> Optional[str]:
-        """Determines the next node to invoke and enqueues it, preparing if needed.
-        Returns the id of the queued node, or `None` if there are no nodes left to enqueue."""
-
-        # Get the next invocation
-        invocation = graph_execution_state.next()
-        if not invocation:
-            return None
-
-        # Save the execution state
-        self.services.graph_execution_manager.set(graph_execution_state)
-
-        # Queue the invocation
-        self.services.queue.put(
-            InvocationQueueItem(
-                session_queue_id=session_queue_id,
-                session_queue_item_id=session_queue_item_id,
-                session_queue_batch_id=session_queue_batch_id,
-                graph_execution_state_id=graph_execution_state.id,
-                invocation_id=invocation.id,
-                workflow=workflow,
-                invoke_all=invoke_all,
-            )
-        )
-
-        return invocation.id
-
-    def create_execution_state(self, graph: Optional[Graph] = None) -> GraphExecutionState:
-        """Creates a new execution state for the given graph"""
-        new_state = GraphExecutionState(graph=Graph() if graph is None else graph)
-        self.services.graph_execution_manager.set(new_state)
-        return new_state
-
-    def cancel(self, graph_execution_state_id: str) -> None:
-        """Cancels the given execution state"""
-        self.services.queue.cancel(graph_execution_state_id)
-
     def __start_service(self, service) -> None:
         # Call start() method on any services that have it
         start_op = getattr(service, "start", None)
@@ -85,5 +35,3 @@ class Invoker:
         # First stop all services
         for service in vars(self.services):
             self.__stop_service(getattr(self.services, service))
-
-        self.services.queue.put(None)

invokeai/app/services/model_images/model_images_base.py

@@ -0,0 +1,33 @@
+from abc import ABC, abstractmethod
+from pathlib import Path
+
+from PIL.Image import Image as PILImageType
+
+
+class ModelImageFileStorageBase(ABC):
+    """Low-level service responsible for storing and retrieving image files."""
+
+    @abstractmethod
+    def get(self, model_key: str) -> PILImageType:
+        """Retrieves a model image as PIL Image."""
+        pass
+
+    @abstractmethod
+    def get_path(self, model_key: str) -> Path:
+        """Gets the internal path to a model image."""
+        pass
+
+    @abstractmethod
+    def get_url(self, model_key: str) -> str | None:
+        """Gets the URL to fetch a model image."""
+        pass
+
+    @abstractmethod
+    def save(self, image: PILImageType, model_key: str) -> None:
+        """Saves a model image."""
+        pass
+
+    @abstractmethod
+    def delete(self, model_key: str) -> None:
+        """Deletes a model image."""
+        pass

invokeai/app/services/model_images/model_images_common.py

@@ -0,0 +1,20 @@
+# TODO: Should these excpetions subclass existing python exceptions?
+class ModelImageFileNotFoundException(Exception):
+    """Raised when an image file is not found in storage."""
+
+    def __init__(self, message="Model image file not found"):
+        super().__init__(message)
+
+
+class ModelImageFileSaveException(Exception):
+    """Raised when an image cannot be saved."""
+
+    def __init__(self, message="Model image file not saved"):
+        super().__init__(message)
+
+
+class ModelImageFileDeleteException(Exception):
+    """Raised when an image cannot be deleted."""
+
+    def __init__(self, message="Model image file not deleted"):
+        super().__init__(message)

invokeai/app/services/model_images/model_images_default.py

@@ -0,0 +1,85 @@
+from pathlib import Path
+
+from PIL import Image
+from PIL.Image import Image as PILImageType
+from send2trash import send2trash
+
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.util.misc import uuid_string
+from invokeai.app.util.thumbnails import make_thumbnail
+
+from .model_images_base import ModelImageFileStorageBase
+from .model_images_common import (
+    ModelImageFileDeleteException,
+    ModelImageFileNotFoundException,
+    ModelImageFileSaveException,
+)
+
+
+class ModelImageFileStorageDisk(ModelImageFileStorageBase):
+    """Stores images on disk"""
+
+    def __init__(self, model_images_folder: Path):
+        self._model_images_folder = model_images_folder
+        self._validate_storage_folders()
+
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+
+    def get(self, model_key: str) -> PILImageType:
+        try:
+            path = self.get_path(model_key)
+
+            if not self._validate_path(path):
+                raise ModelImageFileNotFoundException
+
+            return Image.open(path)
+        except FileNotFoundError as e:
+            raise ModelImageFileNotFoundException from e
+
+    def save(self, image: PILImageType, model_key: str) -> None:
+        try:
+            self._validate_storage_folders()
+            image_path = self._model_images_folder / (model_key + ".webp")
+            thumbnail = make_thumbnail(image, 256)
+            thumbnail.save(image_path, format="webp")
+
+        except Exception as e:
+            raise ModelImageFileSaveException from e
+
+    def get_path(self, model_key: str) -> Path:
+        path = self._model_images_folder / (model_key + ".webp")
+
+        return path
+
+    def get_url(self, model_key: str) -> str | None:
+        path = self.get_path(model_key)
+        if not self._validate_path(path):
+            return
+
+        url = self._invoker.services.urls.get_model_image_url(model_key)
+
+        # The image URL never changes, so we must add random query string to it to prevent caching
+        url += f"?{uuid_string()}"
+
+        return url
+
+    def delete(self, model_key: str) -> None:
+        try:
+            path = self.get_path(model_key)
+
+            if not self._validate_path(path):
+                raise ModelImageFileNotFoundException
+
+            send2trash(path)
+
+        except Exception as e:
+            raise ModelImageFileDeleteException from e
+
+    def _validate_path(self, path: Path) -> bool:
+        """Validates the path given for an image."""
+        return path.exists()
+
+    def _validate_storage_folders(self) -> None:
+        """Checks if the required folders exist and create them if they don't"""
+        self._model_images_folder.mkdir(parents=True, exist_ok=True)

invokeai/app/services/model_install/__init__.py

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

invokeai/app/services/model_install/model_install_base.py

@@ -14,11 +14,12 @@ from typing_extensions import Annotated
 
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
-from invokeai.app.services.events import EventServiceBase
+from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.model_records import ModelRecordServiceBase
 from invokeai.backend.model_manager import AnyModelConfig, ModelRepoVariant
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore
+from invokeai.backend.model_manager.config import ModelSourceType
+from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata
 
 
 class InstallStatus(str, Enum):
@@ -26,6 +27,7 @@ class InstallStatus(str, Enum):
 
     WAITING = "waiting"  # waiting to be dequeued
     DOWNLOADING = "downloading"  # downloading of model files in process
+    DOWNLOADS_DONE = "downloads_done"  # downloading done, waiting to run
     RUNNING = "running"  # being processed
     COMPLETED = "completed"  # finished running
     ERROR = "error"  # terminated with an error message
@@ -89,21 +91,6 @@ class LocalModelSource(StringLikeSource):
         return Path(self.path).as_posix()
 
 
-class CivitaiModelSource(StringLikeSource):
-    """A Civitai version id, with optional variant and access token."""
-
-    version_id: int
-    variant: Optional[ModelRepoVariant] = None
-    access_token: Optional[str] = None
-    type: Literal["civitai"] = "civitai"
-
-    def __str__(self) -> str:
-        """Return string version of repoid when string rep needed."""
-        base: str = str(self.version_id)
-        base += f" ({self.variant})" if self.variant else ""
-        return base
-
-
 class HFModelSource(StringLikeSource):
     """
     A HuggingFace repo_id with optional variant, sub-folder and access token.
@@ -127,8 +114,8 @@ class HFModelSource(StringLikeSource):
     def __str__(self) -> str:
         """Return string version of repoid when string rep needed."""
         base: str = self.repo_id
+        base += f":{self.variant or ''}"
         base += f":{self.subfolder}" if self.subfolder else ""
-        base += f" ({self.variant})" if self.variant else ""
         return base
 
 
@@ -144,9 +131,13 @@ class URLModelSource(StringLikeSource):
         return str(self.url)
 
 
-ModelSource = Annotated[
-    Union[LocalModelSource, HFModelSource, CivitaiModelSource, URLModelSource], Field(discriminator="type")
-]
+ModelSource = Annotated[Union[LocalModelSource, HFModelSource, URLModelSource], Field(discriminator="type")]
+
+MODEL_SOURCE_TO_TYPE_MAP = {
+    URLModelSource: ModelSourceType.Url,
+    HFModelSource: ModelSourceType.HFRepoID,
+    LocalModelSource: ModelSourceType.Path,
+}
 
 
 class ModelInstallJob(BaseModel):
@@ -154,6 +145,7 @@ class ModelInstallJob(BaseModel):
 
     id: int = Field(description="Unique ID for this job")
     status: InstallStatus = Field(default=InstallStatus.WAITING, description="Current status of install process")
+    error_reason: Optional[str] = Field(default=None, description="Information about why the job failed")
     config_in: Dict[str, Any] = Field(
         default_factory=dict, description="Configuration information (e.g. 'description') to apply to model."
     )
@@ -175,6 +167,12 @@ class ModelInstallJob(BaseModel):
     download_parts: Set[DownloadJob] = Field(
         default_factory=set, description="Download jobs contributing to this install"
     )
+    error: Optional[str] = Field(
+        default=None, description="On an error condition, this field will contain the text of the exception"
+    )
+    error_traceback: Optional[str] = Field(
+        default=None, description="On an error condition, this field will contain the exception traceback"
+    )
     # internal flags and transitory settings
     _install_tmpdir: Optional[Path] = PrivateAttr(default=None)
     _exception: Optional[Exception] = PrivateAttr(default=None)
@@ -182,7 +180,10 @@ class ModelInstallJob(BaseModel):
     def set_error(self, e: Exception) -> None:
         """Record the error and traceback from an exception."""
         self._exception = e
+        self.error = str(e)
+        self.error_traceback = self._format_error(e)
         self.status = InstallStatus.ERROR
+        self.error_reason = self._exception.__class__.__name__ if self._exception else None
 
     def cancel(self) -> None:
         """Call to cancel the job."""
@@ -193,10 +194,9 @@ class ModelInstallJob(BaseModel):
         """Class name of the exception that led to status==ERROR."""
         return self._exception.__class__.__name__ if self._exception else None
 
-    @property
-    def error(self) -> Optional[str]:
+    def _format_error(self, exception: Exception) -> str:
         """Error traceback."""
-        return "".join(traceback.format_exception(self._exception)) if self._exception else None
+        return "".join(traceback.format_exception(exception))
 
     @property
     def cancelled(self) -> bool:
@@ -218,6 +218,11 @@ class ModelInstallJob(BaseModel):
         """Return true if job is downloading."""
         return self.status == InstallStatus.DOWNLOADING
 
+    @property
+    def downloads_done(self) -> bool:
+        """Return true if job's downloads ae done."""
+        return self.status == InstallStatus.DOWNLOADS_DONE
+
     @property
     def running(self) -> bool:
         """Return true if job is running."""
@@ -243,7 +248,6 @@ class ModelInstallServiceBase(ABC):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        metadata_store: ModelMetadataStore,
         event_bus: Optional["EventServiceBase"] = None,
     ):
         """
@@ -324,6 +328,44 @@ class ModelInstallServiceBase(ABC):
         :returns id: The string ID of the registered model.
         """
 
+    @abstractmethod
+    def heuristic_import(
+        self,
+        source: str,
+        config: Optional[Dict[str, Any]] = None,
+        access_token: Optional[str] = None,
+        inplace: Optional[bool] = False,
+    ) -> ModelInstallJob:
+        r"""Install the indicated model using heuristics to interpret user intentions.
+
+        :param source: String source
+        :param config: Optional dict. Any fields in this dict
+         will override corresponding autoassigned probe fields in the
+         model's config record as described in `import_model()`.
+        :param access_token: Optional access token for remote sources.
+
+        The source can be:
+        1. A local file path in posix() format (`/foo/bar` or `C:\foo\bar`)
+        2. An http or https URL (`https://foo.bar/foo`)
+        3. A HuggingFace repo_id (`foo/bar`, `foo/bar:fp16`, `foo/bar:fp16:vae`)
+
+        We extend the HuggingFace repo_id syntax to include the variant and the
+        subfolder or path. The following are acceptable alternatives:
+            stabilityai/stable-diffusion-v4
+            stabilityai/stable-diffusion-v4:fp16
+            stabilityai/stable-diffusion-v4:fp16:vae
+            stabilityai/stable-diffusion-v4::/checkpoints/sd4.safetensors
+            stabilityai/stable-diffusion-v4:onnx:vae
+
+        Because a local file path can look like a huggingface repo_id, the logic
+        first checks whether the path exists on disk, and if not, it is treated as
+        a parseable huggingface repo.
+
+        The previous support for recursing into a local folder and loading all model-like files
+        has been removed.
+        """
+        pass
+
     @abstractmethod
     def import_model(
         self,
@@ -338,7 +380,7 @@ class ModelInstallServiceBase(ABC):
          will override corresponding autoassigned probe fields in the
          model's config record. Use it to override
          `name`, `description`, `base_type`, `model_type`, `format`,
-         `prediction_type`, `image_size`, and/or `ztsnr_training`.
+         `prediction_type`, and/or `image_size`.
 
         This will download the model located at `source`,
         probe it, and install it into the models directory.
@@ -385,6 +427,18 @@ class ModelInstallServiceBase(ABC):
     def cancel_job(self, job: ModelInstallJob) -> None:
         """Cancel the indicated job."""
 
+    @abstractmethod
+    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
+        """Wait for the indicated job to reach a terminal state.
+
+        This will block until the indicated install job has completed,
+        been cancelled, or errored out.
+
+        :param job: The job to wait on.
+        :param timeout: Wait up to indicated number of seconds. Raise a TimeoutError if
+        the job hasn't completed within the indicated time.
+        """
+
     @abstractmethod
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:
         """
@@ -394,7 +448,8 @@ class ModelInstallServiceBase(ABC):
         completed, been cancelled, or errored out.
 
         :param timeout: Wait up to indicated number of seconds. Raise an Exception('timeout') if
-        installs do not complete within the indicated time.
+        installs do not complete within the indicated time. A timeout of zero (the default)
+        will block indefinitely until the installs complete.
         """
 
     @abstractmethod
@@ -410,3 +465,22 @@ class ModelInstallServiceBase(ABC):
     @abstractmethod
     def sync_to_config(self) -> None:
         """Synchronize models on disk to those in the model record database."""
+
+    @abstractmethod
+    def download_and_cache(self, source: Union[str, AnyHttpUrl], access_token: Optional[str] = None) -> Path:
+        """
+        Download the model file located at source to the models cache and return its Path.
+
+        :param source: A Url or a string that can be converted into one.
+        :param access_token: Optional access token to access restricted resources.
+
+        The model file will be downloaded into the system-wide model cache
+        (`models/.cache`) if it isn't already there. Note that the model cache
+        is periodically cleared of infrequently-used entries when the model
+        converter runs.
+
+        Note that this doesn't automaticallly install or register the model, but is
+        intended for use by nodes that need access to models that aren't directly
+        supported by InvokeAI. The downloading process takes advantage of the download queue
+        to avoid interrupting other operations.
+        """

invokeai/app/services/model_install/model_install_default.py

@@ -7,49 +7,51 @@ import time
 from hashlib import sha256
 from pathlib import Path
 from queue import Empty, Queue
-from random import randbytes
 from shutil import copyfile, copytree, move, rmtree
 from tempfile import mkdtemp
 from typing import Any, Dict, List, Optional, Set, Union
 
+import yaml
 from huggingface_hub import HfFolder
 from pydantic.networks import AnyHttpUrl
 from requests import Session
 
 from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase
+from invokeai.app.services.download import DownloadJob, DownloadQueueServiceBase, TqdmProgress
 from invokeai.app.services.events.events_base import EventServiceBase
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase, ModelRecordServiceSQL
+from invokeai.app.services.model_records import DuplicateModelException, ModelRecordServiceBase
+from invokeai.app.services.model_records.model_records_base import ModelRecordChanges
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
+    CheckpointConfigBase,
     InvalidModelConfigException,
     ModelRepoVariant,
+    ModelSourceType,
     ModelType,
 )
-from invokeai.backend.model_manager.hash import FastModelHash
 from invokeai.backend.model_manager.metadata import (
     AnyModelRepoMetadata,
-    CivitaiMetadataFetch,
     HuggingFaceMetadataFetch,
-    ModelMetadataStore,
     ModelMetadataWithFiles,
     RemoteModelFile,
 )
+from invokeai.backend.model_manager.metadata.metadata_base import HuggingFaceMetadata
 from invokeai.backend.model_manager.probe import ModelProbe
 from invokeai.backend.model_manager.search import ModelSearch
 from invokeai.backend.util import Chdir, InvokeAILogger
 from invokeai.backend.util.devices import choose_precision, choose_torch_device
 
 from .model_install_base import (
-    CivitaiModelSource,
+    MODEL_SOURCE_TO_TYPE_MAP,
     HFModelSource,
     InstallStatus,
     LocalModelSource,
     ModelInstallJob,
     ModelInstallServiceBase,
     ModelSource,
+    StringLikeSource,
     URLModelSource,
 )
 
@@ -64,7 +66,6 @@ class ModelInstallService(ModelInstallServiceBase):
         app_config: InvokeAIAppConfig,
         record_store: ModelRecordServiceBase,
         download_queue: DownloadQueueServiceBase,
-        metadata_store: Optional[ModelMetadataStore] = None,
         event_bus: Optional[EventServiceBase] = None,
         session: Optional[Session] = None,
     ):
@@ -86,19 +87,12 @@ class ModelInstallService(ModelInstallServiceBase):
         self._lock = threading.Lock()
         self._stop_event = threading.Event()
         self._downloads_changed_event = threading.Event()
+        self._install_completed_event = threading.Event()
         self._download_queue = download_queue
         self._download_cache: Dict[AnyHttpUrl, ModelInstallJob] = {}
         self._running = False
         self._session = session
         self._next_job_id = 0
-        # There may not necessarily be a metadata store initialized
-        # so we create one and initialize it with the same sql database
-        # used by the record store service.
-        if metadata_store:
-            self._metadata_store = metadata_store
-        else:
-            assert isinstance(record_store, ModelRecordServiceSQL)
-            self._metadata_store = ModelMetadataStore(record_store.db)
 
     @property
     def app_config(self) -> InvokeAIAppConfig:  # noqa D102
@@ -121,6 +115,7 @@ class ModelInstallService(ModelInstallServiceBase):
                 raise Exception("Attempt to start the installer service twice")
             self._start_installer_thread()
             self._remove_dangling_install_dirs()
+            self._migrate_yaml()
             self.sync_to_config()
 
     def stop(self, invoker: Optional[Invoker] = None) -> None:
@@ -145,8 +140,9 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if config.get("source") is None:
+        if not config.get("source"):
             config["source"] = model_path.resolve().as_posix()
+        config["source_type"] = ModelSourceType.Path
         return self._register(model_path, config)
 
     def install_path(
@@ -156,20 +152,21 @@ class ModelInstallService(ModelInstallServiceBase):
     ) -> str:  # noqa D102
         model_path = Path(model_path)
         config = config or {}
-        if config.get("source") is None:
-            config["source"] = model_path.resolve().as_posix()
 
-        info: AnyModelConfig = self._probe_model(Path(model_path), config)
-        old_hash = info.original_hash
-        dest_path = self.app_config.models_path / info.base.value / info.type.value / model_path.name
+        info: AnyModelConfig = ModelProbe.probe(Path(model_path), config, hash_algo=self._app_config.hashing_algorithm)
+
+        if preferred_name := config.get("name"):
+            preferred_name = Path(preferred_name).with_suffix(model_path.suffix)
+
+        dest_path = (
+            self.app_config.models_path / info.base.value / info.type.value / (preferred_name or model_path.name)
+        )
         try:
             new_path = self._copy_model(model_path, dest_path)
         except FileExistsError as excp:
             raise DuplicateModelException(
                 f"A model named {model_path.name} is already installed at {dest_path.as_posix()}"
             ) from excp
-        new_hash = FastModelHash.hash(new_path)
-        assert new_hash == old_hash, f"{model_path}: Model hash changed during installation, possibly corrupted."
 
         return self._register(
             new_path,
@@ -177,12 +174,51 @@ class ModelInstallService(ModelInstallServiceBase):
             info,
         )
 
+    def heuristic_import(
+        self,
+        source: str,
+        config: Optional[Dict[str, Any]] = None,
+        access_token: Optional[str] = None,
+        inplace: Optional[bool] = False,
+    ) -> ModelInstallJob:
+        variants = "|".join(ModelRepoVariant.__members__.values())
+        hf_repoid_re = f"^([^/:]+/[^/:]+)(?::({variants})?(?::/?([^:]+))?)?$"
+        source_obj: Optional[StringLikeSource] = None
+
+        if Path(source).exists():  # A local file or directory
+            source_obj = LocalModelSource(path=Path(source), inplace=inplace)
+        elif match := re.match(hf_repoid_re, source):
+            source_obj = HFModelSource(
+                repo_id=match.group(1),
+                variant=match.group(2) if match.group(2) else None,  # pass None rather than ''
+                subfolder=Path(match.group(3)) if match.group(3) else None,
+                access_token=access_token,
+            )
+        elif re.match(r"^https?://[^/]+", source):
+            # Pull the token from config if it exists and matches the URL
+            _token = access_token
+            if _token is None:
+                for pair in self.app_config.remote_api_tokens or []:
+                    if re.search(pair.url_regex, source):
+                        _token = pair.token
+                        break
+            source_obj = URLModelSource(
+                url=AnyHttpUrl(source),
+                access_token=_token,
+            )
+        else:
+            raise ValueError(f"Unsupported model source: '{source}'")
+        return self.import_model(source_obj, config)
+
     def import_model(self, source: ModelSource, config: Optional[Dict[str, Any]] = None) -> ModelInstallJob:  # noqa D102
+        similar_jobs = [x for x in self.list_jobs() if x.source == source and not x.in_terminal_state]
+        if similar_jobs:
+            self._logger.warning(f"There is already an active install job for {source}. Not enqueuing.")
+            return similar_jobs[0]
+
         if isinstance(source, LocalModelSource):
             install_job = self._import_local_model(source, config)
             self._install_queue.put(install_job)  # synchronously install
-        elif isinstance(source, CivitaiModelSource):
-            install_job = self._import_from_civitai(source, config)
         elif isinstance(source, HFModelSource):
             install_job = self._import_from_hf(source, config)
         elif isinstance(source, URLModelSource):
@@ -207,14 +243,25 @@ class ModelInstallService(ModelInstallServiceBase):
         assert isinstance(jobs[0], ModelInstallJob)
         return jobs[0]
 
+    def wait_for_job(self, job: ModelInstallJob, timeout: int = 0) -> ModelInstallJob:
+        """Block until the indicated job has reached terminal state, or when timeout limit reached."""
+        start = time.time()
+        while not job.in_terminal_state:
+            if self._install_completed_event.wait(timeout=5):  # in case we miss an event
+                self._install_completed_event.clear()
+            if timeout > 0 and time.time() - start > timeout:
+                raise TimeoutError("Timeout exceeded")
+        return job
+
+    # TODO: Better name? Maybe wait_for_jobs()? Maybe too easily confused with above
     def wait_for_installs(self, timeout: int = 0) -> List[ModelInstallJob]:  # noqa D102
         """Block until all installation jobs are done."""
         start = time.time()
         while len(self._download_cache) > 0:
-            if self._downloads_changed_event.wait(timeout=5):  # in case we miss an event
+            if self._downloads_changed_event.wait(timeout=0.25):  # in case we miss an event
                 self._downloads_changed_event.clear()
             if timeout > 0 and time.time() - start > timeout:
-                raise Exception("Timeout exceeded")
+                raise TimeoutError("Timeout exceeded")
         self._install_queue.join()
         return self._install_jobs
 
@@ -232,14 +279,62 @@ class ModelInstallService(ModelInstallServiceBase):
     def sync_to_config(self) -> None:
         """Synchronize models on disk to those in the config record store database."""
         self._scan_models_directory()
-        if autoimport := self._app_config.autoimport_dir:
+        if self._app_config.autoimport_path:
             self._logger.info("Scanning autoimport directory for new models")
-            installed = self.scan_directory(self._app_config.root_path / autoimport)
+            installed = self.scan_directory(self._app_config.autoimport_path)
             self._logger.info(f"{len(installed)} new models registered")
         self._logger.info("Model installer (re)initialized")
 
+    def _migrate_yaml(self) -> None:
+        db_models = self.record_store.all_models()
+
+        legacy_models_yaml_path = (
+            self._app_config.legacy_models_yaml_path or self._app_config.root_path / "configs" / "models.yaml"
+        )
+
+        if legacy_models_yaml_path.exists():
+            legacy_models_yaml = yaml.safe_load(legacy_models_yaml_path.read_text())
+
+            yaml_metadata = legacy_models_yaml.pop("__metadata__")
+            yaml_version = yaml_metadata.get("version")
+
+            if yaml_version != "3.0.0":
+                raise ValueError(
+                    f"Attempted migration of unsupported `models.yaml` v{yaml_version}. Only v3.0.0 is supported. Exiting."
+                )
+
+            self._logger.info(
+                f"Starting one-time migration of {len(legacy_models_yaml.items())} models from {str(legacy_models_yaml_path)}. This may take a few minutes."
+            )
+
+            if len(db_models) == 0 and len(legacy_models_yaml.items()) != 0:
+                for model_key, stanza in legacy_models_yaml.items():
+                    _, _, model_name = str(model_key).split("/")
+                    model_path = Path(stanza["path"])
+                    if not model_path.is_absolute():
+                        model_path = self._app_config.models_path / model_path
+                    model_path = model_path.resolve()
+
+                    config: dict[str, Any] = {}
+                    config["name"] = model_name
+                    config["description"] = stanza.get("description")
+                    config["config_path"] = stanza.get("config")
+
+                    try:
+                        id = self.register_path(model_path=model_path, config=config)
+                        self._logger.info(f"Migrated {model_name} with id {id}")
+                    except Exception as e:
+                        self._logger.warning(f"Model at {model_path} could not be migrated: {e}")
+
+            # Rename `models.yaml` to `models.yaml.bak` to prevent re-migration
+            legacy_models_yaml_path.rename(legacy_models_yaml_path.with_suffix(".yaml.bak"))
+
+        # Remove `legacy_models_yaml_path` from the config file - we are done with it either way
+        self._app_config.legacy_models_yaml_path = None
+        self._app_config.write_file(self._app_config.init_file_path)
+
     def scan_directory(self, scan_dir: Path, install: bool = False) -> List[str]:  # noqa D102
-        self._cached_model_paths = {Path(x.path) for x in self.record_store.all_models()}
+        self._cached_model_paths = {Path(x.path).resolve() for x in self.record_store.all_models()}
         callback = self._scan_install if install else self._scan_register
         search = ModelSearch(on_model_found=callback)
         self._models_installed.clear()
@@ -253,7 +348,7 @@ class ModelInstallService(ModelInstallServiceBase):
         """Unregister the model. Delete its files only if they are within our models directory."""
         model = self.record_store.get_model(key)
         models_dir = self.app_config.models_path
-        model_path = models_dir / model.path
+        model_path = models_dir / Path(model.path)  # handle legacy relative model paths
         if model_path.is_relative_to(models_dir):
             self.unconditionally_delete(key)
         else:
@@ -261,13 +356,45 @@ class ModelInstallService(ModelInstallServiceBase):
 
     def unconditionally_delete(self, key: str) -> None:  # noqa D102
         model = self.record_store.get_model(key)
-        path = self.app_config.models_path / model.path
-        if path.is_dir():
-            rmtree(path)
+        model_path = self.app_config.models_path / model.path
+        if model_path.is_dir():
+            rmtree(model_path)
         else:
-            path.unlink()
+            model_path.unlink()
         self.unregister(key)
 
+    def download_and_cache(
+        self,
+        source: Union[str, AnyHttpUrl],
+        access_token: Optional[str] = None,
+        timeout: int = 0,
+    ) -> Path:
+        """Download the model file located at source to the models cache and return its Path."""
+        model_hash = sha256(str(source).encode("utf-8")).hexdigest()[0:32]
+        model_path = self._app_config.convert_cache_path / model_hash
+
+        # We expect the cache directory to contain one and only one downloaded file.
+        # We don't know the file's name in advance, as it is set by the download
+        # content-disposition header.
+        if model_path.exists():
+            contents = [x for x in model_path.iterdir() if x.is_file()]
+            if len(contents) > 0:
+                return contents[0]
+
+        model_path.mkdir(parents=True, exist_ok=True)
+        job = self._download_queue.download(
+            source=AnyHttpUrl(str(source)),
+            dest=model_path,
+            access_token=access_token,
+            on_progress=TqdmProgress().update,
+        )
+        self._download_queue.wait_for_job(job, timeout)
+        if job.complete:
+            assert job.download_path is not None
+            return job.download_path
+        else:
+            raise Exception(job.error)
+
     # --------------------------------------------------------------------------------------------
     # Internal functions that manage the installer threads
     # --------------------------------------------------------------------------------------------
@@ -295,20 +422,22 @@ class ModelInstallService(ModelInstallServiceBase):
                     self._signal_job_errored(job)
 
                 elif (
-                    job.waiting or job.downloading
+                    job.waiting or job.downloads_done
                 ):  # local jobs will be in waiting state, remote jobs will be downloading state
                     job.total_bytes = self._stat_size(job.local_path)
                     job.bytes = job.total_bytes
                     self._signal_job_running(job)
+                    job.config_in["source"] = str(job.source)
+                    job.config_in["source_type"] = MODEL_SOURCE_TO_TYPE_MAP[job.source.__class__]
+                    # enter the metadata, if there is any
+                    if isinstance(job.source_metadata, (HuggingFaceMetadata)):
+                        job.config_in["source_api_response"] = job.source_metadata.api_response
+
                     if job.inplace:
                         key = self.register_path(job.local_path, job.config_in)
                     else:
                         key = self.install_path(job.local_path, job.config_in)
                     job.config_out = self.record_store.get_model(key)
-
-                    # enter the metadata, if there is any
-                    if job.source_metadata:
-                        self._metadata_store.add_metadata(key, job.source_metadata)
                     self._signal_job_completed(job)
 
             except InvalidModelConfigException as excp:
@@ -330,6 +459,7 @@ class ModelInstallService(ModelInstallServiceBase):
                 # if this is an install of a remote file, then clean up the temporary directory
                 if job._install_tmpdir is not None:
                     rmtree(job._install_tmpdir)
+                self._install_completed_event.set()
                 self._install_queue.task_done()
 
         self._logger.info("Install thread exiting")
@@ -367,11 +497,13 @@ class ModelInstallService(ModelInstallServiceBase):
             self._logger.info(f"Scanning {self._app_config.models_path} for new and orphaned models")
             for cur_base_model in BaseModelType:
                 for cur_model_type in ModelType:
-                    models_dir = Path(cur_base_model.value, cur_model_type.value)
+                    models_dir = self._app_config.models_path / Path(cur_base_model.value, cur_model_type.value)
+                    if not models_dir.exists():
+                        continue
                     installed.update(self.scan_directory(models_dir))
             self._logger.info(f"{len(installed)} new models registered; {len(defunct_models)} unregistered")
 
-    def _sync_model_path(self, key: str, ignore_hash_change: bool = False) -> AnyModelConfig:
+    def _sync_model_path(self, key: str) -> AnyModelConfig:
         """
         Move model into the location indicated by its basetype, type and name.
 
@@ -386,21 +518,21 @@ class ModelInstallService(ModelInstallServiceBase):
         old_path = Path(model.path)
         models_dir = self.app_config.models_path
 
-        if not old_path.is_relative_to(models_dir):
+        try:
+            old_path.relative_to(models_dir)
+            return model
+        except ValueError:
+            pass
+
+        new_path = models_dir / model.base.value / model.type.value / old_path.name
+
+        if old_path == new_path or new_path.exists() and old_path == new_path.resolve():
             return model
 
-        new_path = models_dir / model.base.value / model.type.value / model.name
         self._logger.info(f"Moving {model.name} to {new_path}.")
         new_path = self._move_model(old_path, new_path)
-        new_hash = FastModelHash.hash(new_path)
-        model.path = new_path.relative_to(models_dir).as_posix()
-        if model.current_hash != new_hash:
-            assert (
-                ignore_hash_change
-            ), f"{model.name}: Model hash changed during installation, model is possibly corrupted"
-            model.current_hash = new_hash
-            self._logger.info(f"Model has new hash {model.current_hash}, but will continue to be identified by {key}")
-        self.record_store.update_model(key, model)
+        model.path = new_path.as_posix()
+        self.record_store.update_model(key, ModelRecordChanges(path=model.path))
         return model
 
     def _scan_register(self, model: Path) -> bool:
@@ -452,35 +584,23 @@ class ModelInstallService(ModelInstallServiceBase):
         move(old_path, new_path)
         return new_path
 
-    def _probe_model(self, model_path: Path, config: Optional[Dict[str, Any]] = None) -> AnyModelConfig:
-        info: AnyModelConfig = ModelProbe.probe(Path(model_path))
-        if config:  # used to override probe fields
-            for key, value in config.items():
-                setattr(info, key, value)
-        return info
-
-    def _create_key(self) -> str:
-        return sha256(randbytes(100)).hexdigest()[0:32]
-
     def _register(
         self, model_path: Path, config: Optional[Dict[str, Any]] = None, info: Optional[AnyModelConfig] = None
     ) -> str:
-        info = info or ModelProbe.probe(model_path, config)
-        key = self._create_key()
+        config = config or {}
 
-        model_path = model_path.absolute()
-        if model_path.is_relative_to(self.app_config.models_path):
-            model_path = model_path.relative_to(self.app_config.models_path)
+        info = info or ModelProbe.probe(model_path, config, hash_algo=self._app_config.hashing_algorithm)
+
+        model_path = model_path.resolve()
 
         info.path = model_path.as_posix()
 
         # add 'main' specific fields
-        if hasattr(info, "config"):
-            # make config relative to our root
-            legacy_conf = (self.app_config.root_dir / self.app_config.legacy_conf_dir / info.config).resolve()
-            info.config = legacy_conf.relative_to(self.app_config.root_dir).as_posix()
-        self.record_store.add_model(key, info)
-        return key
+        if isinstance(info, CheckpointConfigBase):
+            legacy_conf = (self.app_config.legacy_conf_path / info.config_path).resolve()
+            info.config_path = legacy_conf.as_posix()
+        self.record_store.add_model(info)
+        return info.key
 
     def _next_id(self) -> int:
         with self._lock:
@@ -489,10 +609,10 @@ class ModelInstallService(ModelInstallServiceBase):
         return id
 
     @staticmethod
-    def _guess_variant() -> ModelRepoVariant:
+    def _guess_variant() -> Optional[ModelRepoVariant]:
         """Guess the best HuggingFace variant type to download."""
         precision = choose_precision(choose_torch_device())
-        return ModelRepoVariant.FP16 if precision == "float16" else ModelRepoVariant.DEFAULT
+        return ModelRepoVariant.FP16 if precision == "float16" else None
 
     def _import_local_model(self, source: LocalModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         return ModelInstallJob(
@@ -500,24 +620,16 @@ class ModelInstallService(ModelInstallServiceBase):
             source=source,
             config_in=config or {},
             local_path=Path(source.path),
-            inplace=source.inplace,
+            inplace=source.inplace or False,
         )
 
-    def _import_from_civitai(self, source: CivitaiModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        if not source.access_token:
-            self._logger.info("No Civitai access token provided; some models may not be downloadable.")
-        metadata = CivitaiMetadataFetch(self._session).from_id(str(source.version_id))
-        assert isinstance(metadata, ModelMetadataWithFiles)
-        remote_files = metadata.download_urls(session=self._session)
-        return self._import_remote_model(source=source, config=config, metadata=metadata, remote_files=remote_files)
-
     def _import_from_hf(self, source: HFModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
         # Add user's cached access token to HuggingFace requests
         source.access_token = source.access_token or HfFolder.get_token()
         if not source.access_token:
             self._logger.info("No HuggingFace access token present; some models may not be downloadable.")
 
-        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id)
+        metadata = HuggingFaceMetadataFetch(self._session).from_id(source.repo_id, source.variant)
         assert isinstance(metadata, ModelMetadataWithFiles)
         remote_files = metadata.download_urls(
             variant=source.variant or self._guess_variant(),
@@ -533,16 +645,16 @@ class ModelInstallService(ModelInstallServiceBase):
         )
 
     def _import_from_url(self, source: URLModelSource, config: Optional[Dict[str, Any]]) -> ModelInstallJob:
-        # URLs from Civitai or HuggingFace will be handled specially
-        url_patterns = {
-            r"^https?://civitai.com/": CivitaiMetadataFetch,
-            r"^https?://huggingface.co/[^/]+/[^/]+$": HuggingFaceMetadataFetch,
-        }
+        # URLs from HuggingFace will be handled specially
         metadata = None
-        for pattern, fetcher in url_patterns.items():
-            if re.match(pattern, str(source.url), re.IGNORECASE):
-                metadata = fetcher(self._session).from_url(source.url)
-                break
+        fetcher = None
+        try:
+            fetcher = self.get_fetcher_from_url(str(source.url))
+        except ValueError:
+            pass
+        kwargs: dict[str, Any] = {"session": self._session}
+        if fetcher is not None:
+            metadata = fetcher(**kwargs).from_url(source.url)
         self._logger.debug(f"metadata={metadata}")
         if metadata and isinstance(metadata, ModelMetadataWithFiles):
             remote_files = metadata.download_urls(session=self._session)
@@ -557,7 +669,7 @@ class ModelInstallService(ModelInstallServiceBase):
 
     def _import_remote_model(
         self,
-        source: ModelSource,
+        source: HFModelSource | URLModelSource,
         remote_files: List[RemoteModelFile],
         metadata: Optional[AnyModelRepoMetadata],
         config: Optional[Dict[str, Any]],
@@ -565,6 +677,8 @@ class ModelInstallService(ModelInstallServiceBase):
         # TODO: Replace with tempfile.tmpdir() when multithreading is cleaned up.
         # Currently the tmpdir isn't automatically removed at exit because it is
         # being held in a daemon thread.
+        if len(remote_files) == 0:
+            raise ValueError(f"{source}: No downloadable files found")
         tmpdir = Path(
             mkdtemp(
                 dir=self._app_config.models_path,
@@ -580,6 +694,16 @@ class ModelInstallService(ModelInstallServiceBase):
             bytes=0,
             total_bytes=0,
         )
+        # In the event that there is a subfolder specified in the source,
+        # we need to remove it from the destination path in order to avoid
+        # creating unwanted subfolders
+        if isinstance(source, HFModelSource) and source.subfolder:
+            root = Path(remote_files[0].path.parts[0])
+            subfolder = root / source.subfolder
+        else:
+            root = Path(".")
+            subfolder = Path(".")
+
         # we remember the path up to the top of the tmpdir so that it may be
         # removed safely at the end of the install process.
         install_job._install_tmpdir = tmpdir
@@ -589,7 +713,7 @@ class ModelInstallService(ModelInstallServiceBase):
         self._logger.debug(f"remote_files={remote_files}")
         for model_file in remote_files:
             url = model_file.url
-            path = model_file.path
+            path = root / model_file.path.relative_to(subfolder)
             self._logger.info(f"Downloading {url} => {path}")
             install_job.total_bytes += model_file.size
             assert hasattr(source, "access_token")
@@ -652,13 +776,14 @@ class ModelInstallService(ModelInstallServiceBase):
                 self._signal_job_downloading(install_job)
 
     def _download_complete_callback(self, download_job: DownloadJob) -> None:
+        self._logger.info(f"{download_job.source}: model download complete")
         with self._lock:
             install_job = self._download_cache[download_job.source]
             self._download_cache.pop(download_job.source, None)
 
             # are there any more active jobs left in this task?
-            if all(x.complete for x in install_job.download_parts):
-                #  now enqueue job for actual installation into the models directory
+            if install_job.downloading and all(x.complete for x in install_job.download_parts):
+                install_job.status = InstallStatus.DOWNLOADS_DONE
                 self._install_queue.put(install_job)
 
             # Let other threads know that the number of downloads has changed
@@ -684,7 +809,7 @@ class ModelInstallService(ModelInstallServiceBase):
             if not install_job:
                 return
             self._downloads_changed_event.set()
-            self._logger.warning(f"Download {download_job.source} cancelled.")
+            self._logger.warning(f"{download_job.source}: model download cancelled")
             # if install job has already registered an error, then do not replace its status with cancelled
             if not install_job.errored:
                 install_job.cancel()
@@ -731,6 +856,7 @@ class ModelInstallService(ModelInstallServiceBase):
                 parts=parts,
                 bytes=job.bytes,
                 total_bytes=job.total_bytes,
+                id=job.id,
             )
 
     def _signal_job_completed(self, job: ModelInstallJob) -> None:
@@ -743,7 +869,7 @@ class ModelInstallService(ModelInstallServiceBase):
             assert job.local_path is not None
             assert job.config_out is not None
             key = job.config_out.key
-            self._event_bus.emit_model_install_completed(str(job.source), key)
+            self._event_bus.emit_model_install_completed(str(job.source), key, id=job.id)
 
     def _signal_job_errored(self, job: ModelInstallJob) -> None:
         self._logger.info(f"{job.source}: model installation encountered an exception: {job.error_type}\n{job.error}")
@@ -752,9 +878,15 @@ class ModelInstallService(ModelInstallServiceBase):
             error = job.error
             assert error_type is not None
             assert error is not None
-            self._event_bus.emit_model_install_error(str(job.source), error_type, error)
+            self._event_bus.emit_model_install_error(str(job.source), error_type, error, id=job.id)
 
     def _signal_job_cancelled(self, job: ModelInstallJob) -> None:
         self._logger.info(f"{job.source}: model installation was cancelled")
         if self._event_bus:
-            self._event_bus.emit_model_install_cancelled(str(job.source))
+            self._event_bus.emit_model_install_cancelled(str(job.source), id=job.id)
+
+    @staticmethod
+    def get_fetcher_from_url(url: str):
+        if re.match(r"^https?://huggingface.co/[^/]+/[^/]+$", url.lower()):
+            return HuggingFaceMetadataFetch
+        raise ValueError(f"Unsupported model source: '{url}'")

invokeai/app/services/model_load/__init__.py

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

invokeai/app/services/model_load/model_load_base.py

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

invokeai/app/services/model_load/model_load_default.py

@@ -0,0 +1,118 @@
+# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Team
+"""Implementation of model loader service."""
+
+from typing import Optional, Type
+
+from invokeai.app.services.config import InvokeAIAppConfig
+from invokeai.app.services.invoker import Invoker
+from invokeai.app.services.shared.invocation_context import InvocationContextData
+from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
+from invokeai.backend.model_manager.load import (
+    LoadedModel,
+    ModelLoaderRegistry,
+    ModelLoaderRegistryBase,
+)
+from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
+from invokeai.backend.util.logging import InvokeAILogger
+
+from .model_load_base import ModelLoadServiceBase
+
+
+class ModelLoadService(ModelLoadServiceBase):
+    """Wrapper around ModelLoaderRegistry."""
+
+    def __init__(
+        self,
+        app_config: InvokeAIAppConfig,
+        ram_cache: ModelCacheBase[AnyModel],
+        convert_cache: ModelConvertCacheBase,
+        registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
+    ):
+        """Initialize the model load service."""
+        logger = InvokeAILogger.get_logger(self.__class__.__name__)
+        logger.setLevel(app_config.log_level.upper())
+        self._logger = logger
+        self._app_config = app_config
+        self._ram_cache = ram_cache
+        self._convert_cache = convert_cache
+        self._registry = registry
+
+    def start(self, invoker: Invoker) -> None:
+        self._invoker = invoker
+
+    @property
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
+        """Return the RAM cache used by this loader."""
+        return self._ram_cache
+
+    @property
+    def convert_cache(self) -> ModelConvertCacheBase:
+        """Return the checkpoint convert cache used by this loader."""
+        return self._convert_cache
+
+    def load_model(
+        self,
+        model_config: AnyModelConfig,
+        submodel_type: Optional[SubModelType] = None,
+        context_data: Optional[InvocationContextData] = None,
+    ) -> LoadedModel:
+        """
+        Given a model's configuration, load it and return the LoadedModel object.
+
+        :param model_config: Model configuration record (as returned by ModelRecordBase.get_model())
+        :param submodel: For main (pipeline models), the submodel to fetch.
+        :param context: Invocation context used for event reporting
+        """
+        if context_data:
+            self._emit_load_event(
+                context_data=context_data,
+                model_config=model_config,
+                submodel_type=submodel_type,
+            )
+
+        implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
+        loaded_model: LoadedModel = implementation(
+            app_config=self._app_config,
+            logger=self._logger,
+            ram_cache=self._ram_cache,
+            convert_cache=self._convert_cache,
+        ).load_model(model_config, submodel_type)
+
+        if context_data:
+            self._emit_load_event(
+                context_data=context_data,
+                model_config=model_config,
+                submodel_type=submodel_type,
+                loaded=True,
+            )
+        return loaded_model
+
+    def _emit_load_event(
+        self,
+        context_data: InvocationContextData,
+        model_config: AnyModelConfig,
+        loaded: Optional[bool] = False,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> None:
+        if not self._invoker:
+            return
+
+        if not loaded:
+            self._invoker.services.events.emit_model_load_started(
+                queue_id=context_data.queue_item.queue_id,
+                queue_item_id=context_data.queue_item.item_id,
+                queue_batch_id=context_data.queue_item.batch_id,
+                graph_execution_state_id=context_data.queue_item.session_id,
+                model_config=model_config,
+                submodel_type=submodel_type,
+            )
+        else:
+            self._invoker.services.events.emit_model_load_completed(
+                queue_id=context_data.queue_item.queue_id,
+                queue_item_id=context_data.queue_item.item_id,
+                queue_batch_id=context_data.queue_item.batch_id,
+                graph_execution_state_id=context_data.queue_item.session_id,
+                model_config=model_config,
+                submodel_type=submodel_type,
+            )

invokeai/app/services/model_manager/__init__.py

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

invokeai/app/services/model_manager/model_manager_base.py

@@ -1,283 +1,68 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
 
-from __future__ import annotations
-
 from abc import ABC, abstractmethod
-from logging import Logger
-from pathlib import Path
-from typing import Callable, List, Literal, Optional, Tuple, Union
 
-from pydantic import Field
+import torch
+from typing_extensions import Self
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_management import (
-    AddModelResult,
-    BaseModelType,
-    LoadedModelInfo,
-    MergeInterpolationMethod,
-    ModelType,
-    SchedulerPredictionType,
-    SubModelType,
-)
-from invokeai.backend.model_management.model_cache import CacheStats
+from invokeai.app.services.invoker import Invoker
+
+from ..config import InvokeAIAppConfig
+from ..download import DownloadQueueServiceBase
+from ..events.events_base import EventServiceBase
+from ..model_install import ModelInstallServiceBase
+from ..model_load import ModelLoadServiceBase
+from ..model_records import ModelRecordServiceBase
 
 
 class ModelManagerServiceBase(ABC):
-    """Responsible for managing models on disk and in memory"""
+    """Abstract base class for the model manager service."""
 
-    @abstractmethod
-    def __init__(
-        self,
-        config: InvokeAIAppConfig,
-        logger: Logger,
-    ):
-        """
-        Initialize with the path to the models.yaml config file.
-        Optional parameters are the torch device type, precision, max_models,
-        and sequential_offload boolean. Note that the default device
-        type and precision are set up for a CUDA system running at half precision.
-        """
-        pass
+    # attributes:
+    # store: ModelRecordServiceBase = Field(description="An instance of the model record configuration service.")
+    # install: ModelInstallServiceBase = Field(description="An instance of the model install service.")
+    # load: ModelLoadServiceBase = Field(description="An instance of the model load service.")
 
+    @classmethod
     @abstractmethod
-    def get_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModelInfo:
-        """Retrieve the indicated model with name and type.
-        submodel can be used to get a part (such as the vae)
-        of a diffusers pipeline."""
+    def build_model_manager(
+        cls,
+        app_config: InvokeAIAppConfig,
+        model_record_service: ModelRecordServiceBase,
+        download_queue: DownloadQueueServiceBase,
+        events: EventServiceBase,
+        execution_device: torch.device,
+    ) -> Self:
+        """
+        Construct the model manager service instance.
+
+        Use it rather than the __init__ constructor. This class
+        method simplifies the construction considerably.
+        """
         pass
 
     @property
     @abstractmethod
-    def logger(self):
+    def store(self) -> ModelRecordServiceBase:
+        """Return the ModelRecordServiceBase used to store and retrieve configuration records."""
+        pass
+
+    @property
+    @abstractmethod
+    def load(self) -> ModelLoadServiceBase:
+        """Return the ModelLoadServiceBase used to load models from their configuration records."""
+        pass
+
+    @property
+    @abstractmethod
+    def install(self) -> ModelInstallServiceBase:
+        """Return the ModelInstallServiceBase used to download and manipulate model files."""
         pass
 
     @abstractmethod
-    def model_exists(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ) -> bool:
+    def start(self, invoker: Invoker) -> None:
         pass
 
     @abstractmethod
-    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
-        """
-        Given a model name returns a dict-like (OmegaConf) object describing it.
-        Uses the exact format as the omegaconf stanza.
-        """
-        pass
-
-    @abstractmethod
-    def list_models(self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None) -> dict:
-        """
-        Return a dict of models in the format:
-        { model_type1:
-          { model_name1: {'status': 'active'|'cached'|'not loaded',
-                         'model_name' : name,
-                         'model_type' : SDModelType,
-                         'description': description,
-                         'format': 'folder'|'safetensors'|'ckpt'
-                         },
-            model_name2: { etc }
-          },
-          model_type2:
-            { model_name_n: etc
-        }
-        """
-        pass
-
-    @abstractmethod
-    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> dict:
-        """
-        Return information about the model using the same format as list_models()
-        """
-        pass
-
-    @abstractmethod
-    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
-        """
-        Returns a list of all the model names known.
-        """
-        pass
-
-    @abstractmethod
-    def add_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-        clobber: bool = False,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with an
-        assertion error if the name already exists. Pass clobber=True to overwrite.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        pass
-
-    @abstractmethod
-    def update_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with a
-        ModelNotFoundException if the name does not already exist.
-
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        pass
-
-    @abstractmethod
-    def del_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ):
-        """
-        Delete the named model from configuration. If delete_files is true,
-        then the underlying weight file or diffusers directory will be deleted
-        as well. Call commit() to write to disk.
-        """
-        pass
-
-    @abstractmethod
-    def rename_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        new_name: str,
-    ):
-        """
-        Rename the indicated model.
-        """
-        pass
-
-    @abstractmethod
-    def list_checkpoint_configs(self) -> List[Path]:
-        """
-        List the checkpoint config paths from ROOT/configs/stable-diffusion.
-        """
-        pass
-
-    @abstractmethod
-    def convert_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: Literal[ModelType.Main, ModelType.Vae],
-    ) -> AddModelResult:
-        """
-        Convert a checkpoint file into a diffusers folder, deleting the cached
-        version and deleting the original checkpoint file if it is in the models
-        directory.
-        :param model_name: Name of the model to convert
-        :param base_model: Base model type
-        :param model_type: Type of model ['vae' or 'main']
-
-        This will raise a ValueError unless the model is not a checkpoint. It will
-        also raise a ValueError in the event that there is a similarly-named diffusers
-        directory already in place.
-        """
-        pass
-
-    @abstractmethod
-    def heuristic_import(
-        self,
-        items_to_import: set[str],
-        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
-    ) -> dict[str, AddModelResult]:
-        """Import a list of paths, repo_ids or URLs. Returns the set of
-        successfully imported items.
-        :param items_to_import: Set of strings corresponding to models to be imported.
-        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
-
-        The prediction type helper is necessary to distinguish between
-        models based on Stable Diffusion 2 Base (requiring
-        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
-        (requiring SchedulerPredictionType.VPrediction). It is
-        generally impossible to do this programmatically, so the
-        prediction_type_helper usually asks the user to choose.
-
-        The result is a set of successfully installed models. Each element
-        of the set is a dict corresponding to the newly-created OmegaConf stanza for
-        that model.
-        """
-        pass
-
-    @abstractmethod
-    def merge_models(
-        self,
-        model_names: List[str] = Field(
-            default=None, min_length=2, max_length=3, description="List of model names to merge"
-        ),
-        base_model: Union[BaseModelType, str] = Field(
-            default=None, description="Base model shared by all models to be merged"
-        ),
-        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
-        alpha: Optional[float] = 0.5,
-        interp: Optional[MergeInterpolationMethod] = None,
-        force: Optional[bool] = False,
-        merge_dest_directory: Optional[Path] = None,
-    ) -> AddModelResult:
-        """
-        Merge two to three diffusrs pipeline models and save as a new model.
-        :param model_names: List of 2-3 models to merge
-        :param base_model: Base model to use for all models
-        :param merged_model_name: Name of destination merged model
-        :param alpha: Alpha strength to apply to 2d and 3d model
-        :param interp: Interpolation method. None (default)
-        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
-        """
-        pass
-
-    @abstractmethod
-    def search_for_models(self, directory: Path) -> List[Path]:
-        """
-        Return list of all models found in the designated directory.
-        """
-        pass
-
-    @abstractmethod
-    def sync_to_config(self):
-        """
-        Re-read models.yaml, rescan the models directory, and reimport models
-        in the autoimport directories. Call after making changes outside the
-        model manager API.
-        """
-        pass
-
-    @abstractmethod
-    def collect_cache_stats(self, cache_stats: CacheStats):
-        """
-        Reset model cache statistics for graph with graph_id.
-        """
-        pass
-
-    @abstractmethod
-    def commit(self, conf_file: Optional[Path] = None) -> None:
-        """
-        Write current configuration out to the indicated file.
-        If no conf_file is provided, then replaces the
-        original file/database used to initialize the object.
-        """
+    def stop(self, invoker: Invoker) -> None:
         pass

invokeai/app/services/model_manager/model_manager_default.py

@@ -1,421 +1,99 @@
 # Copyright (c) 2023 Lincoln D. Stein and the InvokeAI Team
-
-from __future__ import annotations
-
-from logging import Logger
-from pathlib import Path
-from typing import TYPE_CHECKING, Callable, List, Literal, Optional, Tuple, Union
+"""Implementation of ModelManagerServiceBase."""
 
 import torch
-from pydantic import Field
+from typing_extensions import Self
 
-from invokeai.app.services.config.config_default import InvokeAIAppConfig
-from invokeai.app.services.invocation_processor.invocation_processor_common import CanceledException
 from invokeai.app.services.invoker import Invoker
-from invokeai.app.services.shared.invocation_context import InvocationContextData
-from invokeai.backend.model_management import (
-    AddModelResult,
-    BaseModelType,
-    LoadedModelInfo,
-    MergeInterpolationMethod,
-    ModelManager,
-    ModelMerger,
-    ModelNotFoundException,
-    ModelType,
-    SchedulerPredictionType,
-    SubModelType,
-)
-from invokeai.backend.model_management.model_cache import CacheStats
-from invokeai.backend.model_management.model_search import FindModels
-from invokeai.backend.util import choose_precision, choose_torch_device
+from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
+from invokeai.backend.util.devices import choose_torch_device
+from invokeai.backend.util.logging import InvokeAILogger
 
+from ..config import InvokeAIAppConfig
+from ..download import DownloadQueueServiceBase
+from ..events.events_base import EventServiceBase
+from ..model_install import ModelInstallService, ModelInstallServiceBase
+from ..model_load import ModelLoadService, ModelLoadServiceBase
+from ..model_records import ModelRecordServiceBase
 from .model_manager_base import ModelManagerServiceBase
 
-if TYPE_CHECKING:
-    pass
 
-
-# simple implementation
 class ModelManagerService(ModelManagerServiceBase):
-    """Responsible for managing models on disk and in memory"""
+    """
+    The ModelManagerService handles various aspects of model installation, maintenance and loading.
+
+    It bundles three distinct services:
+    model_manager.store   -- Routines to manage the database of model configuration records.
+    model_manager.install -- Routines to install, move and delete models.
+    model_manager.load    -- Routines to load models into memory.
+    """
 
     def __init__(
         self,
-        config: InvokeAIAppConfig,
-        logger: Logger,
+        store: ModelRecordServiceBase,
+        install: ModelInstallServiceBase,
+        load: ModelLoadServiceBase,
     ):
-        """
-        Initialize with the path to the models.yaml config file.
-        Optional parameters are the torch device type, precision, max_models,
-        and sequential_offload boolean. Note that the default device
-        type and precision are set up for a CUDA system running at half precision.
-        """
-        if config.model_conf_path and config.model_conf_path.exists():
-            config_file = config.model_conf_path
-        else:
-            config_file = config.root_dir / "configs/models.yaml"
-
-        logger.debug(f"Config file={config_file}")
-
-        device = torch.device(choose_torch_device())
-        device_name = torch.cuda.get_device_name() if device == torch.device("cuda") else ""
-        logger.info(f"GPU device = {device} {device_name}")
-
-        precision = config.precision
-        if precision == "auto":
-            precision = choose_precision(device)
-        dtype = torch.float32 if precision == "float32" else torch.float16
-
-        # this is transitional backward compatibility
-        # support for the deprecated `max_loaded_models`
-        # configuration value. If present, then the
-        # cache size is set to 2.5 GB times
-        # the number of max_loaded_models. Otherwise
-        # use new `ram_cache_size` config setting
-        max_cache_size = config.ram_cache_size
-
-        logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
-
-        sequential_offload = config.sequential_guidance
-
-        self.mgr = ModelManager(
-            config=config_file,
-            device_type=device,
-            precision=dtype,
-            max_cache_size=max_cache_size,
-            sequential_offload=sequential_offload,
-            logger=logger,
-        )
-        logger.info("Model manager service initialized")
-
-    def start(self, invoker: Invoker) -> None:
-        self._invoker: Optional[Invoker] = invoker
-
-    def get_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: Optional[SubModelType] = None,
-        context_data: Optional[InvocationContextData] = None,
-    ) -> LoadedModelInfo:
-        """
-        Retrieve the indicated model. submodel can be used to get a
-        part (such as the vae) of a diffusers mode.
-        """
-
-        # we can emit model loading events if we are executing with access to the invocation context
-        if context_data is not None:
-            self._emit_load_event(
-                context_data=context_data,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-            )
-
-        loaded_model_info = self.mgr.get_model(
-            model_name,
-            base_model,
-            model_type,
-            submodel,
-        )
-
-        if context_data is not None:
-            self._emit_load_event(
-                context_data=context_data,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-                loaded_model_info=loaded_model_info,
-            )
-
-        return loaded_model_info
-
-    def model_exists(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ) -> bool:
-        """
-        Given a model name, returns True if it is a valid
-        identifier.
-        """
-        return self.mgr.model_exists(
-            model_name,
-            base_model,
-            model_type,
-        )
-
-    def model_info(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
-        """
-        Given a model name returns a dict-like (OmegaConf) object describing it.
-        """
-        return self.mgr.model_info(model_name, base_model, model_type)
-
-    def model_names(self) -> List[Tuple[str, BaseModelType, ModelType]]:
-        """
-        Returns a list of all the model names known.
-        """
-        return self.mgr.model_names()
-
-    def list_models(
-        self, base_model: Optional[BaseModelType] = None, model_type: Optional[ModelType] = None
-    ) -> list[dict]:
-        """
-        Return a list of models.
-        """
-        return self.mgr.list_models(base_model, model_type)
-
-    def list_model(self, model_name: str, base_model: BaseModelType, model_type: ModelType) -> Union[dict, None]:
-        """
-        Return information about the model using the same format as list_models()
-        """
-        return self.mgr.list_model(model_name=model_name, base_model=base_model, model_type=model_type)
-
-    def add_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-        clobber: bool = False,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with an
-        assertion error if the name already exists. Pass clobber=True to overwrite.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        self.logger.debug(f"add/update model {model_name}")
-        return self.mgr.add_model(model_name, base_model, model_type, model_attributes, clobber)
-
-    def update_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        model_attributes: dict,
-    ) -> AddModelResult:
-        """
-        Update the named model with a dictionary of attributes. Will fail with a
-        ModelNotFoundException exception if the name does not already exist.
-        On a successful update, the config will be changed in memory. Will fail
-        with an assertion error if provided attributes are incorrect or
-        the model name is missing. Call commit() to write changes to disk.
-        """
-        self.logger.debug(f"update model {model_name}")
-        if not self.model_exists(model_name, base_model, model_type):
-            raise ModelNotFoundException(f"Unknown model {model_name}")
-        return self.add_model(model_name, base_model, model_type, model_attributes, clobber=True)
-
-    def del_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-    ):
-        """
-        Delete the named model from configuration. If delete_files is true,
-        then the underlying weight file or diffusers directory will be deleted
-        as well.
-        """
-        self.logger.debug(f"delete model {model_name}")
-        self.mgr.del_model(model_name, base_model, model_type)
-        self.mgr.commit()
-
-    def convert_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: Literal[ModelType.Main, ModelType.Vae],
-        convert_dest_directory: Optional[Path] = Field(
-            default=None, description="Optional directory location for merged model"
-        ),
-    ) -> AddModelResult:
-        """
-        Convert a checkpoint file into a diffusers folder, deleting the cached
-        version and deleting the original checkpoint file if it is in the models
-        directory.
-        :param model_name: Name of the model to convert
-        :param base_model: Base model type
-        :param model_type: Type of model ['vae' or 'main']
-        :param convert_dest_directory: Save the converted model to the designated directory (`models/etc/etc` by default)
-
-        This will raise a ValueError unless the model is not a checkpoint. It will
-        also raise a ValueError in the event that there is a similarly-named diffusers
-        directory already in place.
-        """
-        self.logger.debug(f"convert model {model_name}")
-        return self.mgr.convert_model(model_name, base_model, model_type, convert_dest_directory)
-
-    def collect_cache_stats(self, cache_stats: CacheStats):
-        """
-        Reset model cache statistics for graph with graph_id.
-        """
-        self.mgr.cache.stats = cache_stats
-
-    def commit(self, conf_file: Optional[Path] = None):
-        """
-        Write current configuration out to the indicated file.
-        If no conf_file is provided, then replaces the
-        original file/database used to initialize the object.
-        """
-        return self.mgr.commit(conf_file)
-
-    def _emit_load_event(
-        self,
-        context_data: InvocationContextData,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: Optional[SubModelType] = None,
-        loaded_model_info: Optional[LoadedModelInfo] = None,
-    ):
-        if self._invoker is None:
-            return
-
-        if self._invoker.services.queue.is_canceled(context_data.session_id):
-            raise CanceledException()
-
-        if loaded_model_info:
-            self._invoker.services.events.emit_model_load_completed(
-                queue_id=context_data.queue_id,
-                queue_item_id=context_data.queue_item_id,
-                queue_batch_id=context_data.batch_id,
-                graph_execution_state_id=context_data.session_id,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-                loaded_model_info=loaded_model_info,
-            )
-        else:
-            self._invoker.services.events.emit_model_load_started(
-                queue_id=context_data.queue_id,
-                queue_item_id=context_data.queue_item_id,
-                queue_batch_id=context_data.batch_id,
-                graph_execution_state_id=context_data.session_id,
-                model_name=model_name,
-                base_model=base_model,
-                model_type=model_type,
-                submodel=submodel,
-            )
+        self._store = store
+        self._install = install
+        self._load = load
 
     @property
-    def logger(self):
-        return self.mgr.logger
+    def store(self) -> ModelRecordServiceBase:
+        return self._store
 
-    def heuristic_import(
-        self,
-        items_to_import: set[str],
-        prediction_type_helper: Optional[Callable[[Path], SchedulerPredictionType]] = None,
-    ) -> dict[str, AddModelResult]:
-        """Import a list of paths, repo_ids or URLs. Returns the set of
-        successfully imported items.
-        :param items_to_import: Set of strings corresponding to models to be imported.
-        :param prediction_type_helper: A callback that receives the Path of a Stable Diffusion 2 checkpoint model and returns a SchedulerPredictionType.
+    @property
+    def install(self) -> ModelInstallServiceBase:
+        return self._install
 
-        The prediction type helper is necessary to distinguish between
-        models based on Stable Diffusion 2 Base (requiring
-        SchedulerPredictionType.Epsilson) and Stable Diffusion 768
-        (requiring SchedulerPredictionType.VPrediction). It is
-        generally impossible to do this programmatically, so the
-        prediction_type_helper usually asks the user to choose.
+    @property
+    def load(self) -> ModelLoadServiceBase:
+        return self._load
 
-        The result is a set of successfully installed models. Each element
-        of the set is a dict corresponding to the newly-created OmegaConf stanza for
-        that model.
-        """
-        return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
+    def start(self, invoker: Invoker) -> None:
+        for service in [self._store, self._install, self._load]:
+            if hasattr(service, "start"):
+                service.start(invoker)
 
-    def merge_models(
-        self,
-        model_names: List[str] = Field(
-            default=None, min_length=2, max_length=3, description="List of model names to merge"
-        ),
-        base_model: Union[BaseModelType, str] = Field(
-            default=None, description="Base model shared by all models to be merged"
-        ),
-        merged_model_name: str = Field(default=None, description="Name of destination model after merging"),
-        alpha: float = 0.5,
-        interp: Optional[MergeInterpolationMethod] = None,
-        force: bool = False,
-        merge_dest_directory: Optional[Path] = Field(
-            default=None, description="Optional directory location for merged model"
-        ),
-    ) -> AddModelResult:
-        """
-        Merge two to three diffusrs pipeline models and save as a new model.
-        :param model_names: List of 2-3 models to merge
-        :param base_model: Base model to use for all models
-        :param merged_model_name: Name of destination merged model
-        :param alpha: Alpha strength to apply to 2d and 3d model
-        :param interp: Interpolation method. None (default)
-        :param merge_dest_directory: Save the merged model to the designated directory (with 'merged_model_name' appended)
-        """
-        merger = ModelMerger(self.mgr)
-        try:
-            result = merger.merge_diffusion_models_and_save(
-                model_names=model_names,
-                base_model=base_model,
-                merged_model_name=merged_model_name,
-                alpha=alpha,
-                interp=interp,
-                force=force,
-                merge_dest_directory=merge_dest_directory,
-            )
-        except AssertionError as e:
-            raise ValueError(e)
-        return result
+    def stop(self, invoker: Invoker) -> None:
+        for service in [self._store, self._install, self._load]:
+            if hasattr(service, "stop"):
+                service.stop(invoker)
 
-    def search_for_models(self, directory: Path) -> List[Path]:
+    @classmethod
+    def build_model_manager(
+        cls,
+        app_config: InvokeAIAppConfig,
+        model_record_service: ModelRecordServiceBase,
+        download_queue: DownloadQueueServiceBase,
+        events: EventServiceBase,
+        execution_device: torch.device = choose_torch_device(),
+    ) -> Self:
         """
-        Return list of all models found in the designated directory.
-        """
-        search = FindModels([directory], self.logger)
-        return search.list_models()
+        Construct the model manager service instance.
 
-    def sync_to_config(self):
+        For simplicity, use this class method rather than the __init__ constructor.
         """
-        Re-read models.yaml, rescan the models directory, and reimport models
-        in the autoimport directories. Call after making changes outside the
-        model manager API.
-        """
-        return self.mgr.sync_to_config()
+        logger = InvokeAILogger.get_logger(cls.__name__)
+        logger.setLevel(app_config.log_level.upper())
 
-    def list_checkpoint_configs(self) -> List[Path]:
-        """
-        List the checkpoint config paths from ROOT/configs/stable-diffusion.
-        """
-        config = self.mgr.app_config
-        conf_path = config.legacy_conf_path
-        root_path = config.root_path
-        return [(conf_path / x).relative_to(root_path) for x in conf_path.glob("**/*.yaml")]
-
-    def rename_model(
-        self,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        new_name: Optional[str] = None,
-        new_base: Optional[BaseModelType] = None,
-    ):
-        """
-        Rename the indicated model. Can provide a new name and/or a new base.
-        :param model_name: Current name of the model
-        :param base_model: Current base of the model
-        :param model_type: Model type (can't be changed)
-        :param new_name: New name for the model
-        :param new_base: New base for the model
-        """
-        self.mgr.rename_model(
-            base_model=base_model,
-            model_type=model_type,
-            model_name=model_name,
-            new_name=new_name,
-            new_base=new_base,
+        ram_cache = ModelCache(
+            max_cache_size=app_config.ram,
+            max_vram_cache_size=app_config.vram,
+            logger=logger,
+            execution_device=execution_device,
         )
+        convert_cache = ModelConvertCache(cache_path=app_config.convert_cache_path, max_size=app_config.convert_cache)
+        loader = ModelLoadService(
+            app_config=app_config,
+            ram_cache=ram_cache,
+            convert_cache=convert_cache,
+            registry=ModelLoaderRegistry,
+        )
+        installer = ModelInstallService(
+            app_config=app_config,
+            record_store=model_record_service,
+            download_queue=download_queue,
+            event_bus=events,
+        )
+        return cls(store=model_record_service, install=installer, load=loader)

invokeai/app/services/model_records/__init__.py

@@ -1,4 +1,5 @@
 """Init file for model record services."""
+
 from .model_records_base import (  # noqa F401
     DuplicateModelException,
     InvalidModelException,

invokeai/app/services/model_records/model_records_base.py

@@ -6,13 +6,24 @@ Abstract base class for storing and retrieving model configuration records.
 from abc import ABC, abstractmethod
 from enum import Enum
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import List, Optional, Set, Union
 
 from pydantic import BaseModel, Field
 
 from invokeai.app.services.shared.pagination import PaginatedResults
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelFormat, ModelType
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore
+from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
+from invokeai.backend.model_manager import (
+    AnyModelConfig,
+    BaseModelType,
+    ModelFormat,
+    ModelType,
+)
+from invokeai.backend.model_manager.config import (
+    ControlAdapterDefaultSettings,
+    MainModelDefaultSettings,
+    ModelVariantType,
+    SchedulerPredictionType,
+)
 
 
 class DuplicateModelException(Exception):
@@ -53,11 +64,34 @@ class ModelSummary(BaseModel):
     tags: Set[str] = Field(description="tags associated with model")
 
 
+class ModelRecordChanges(BaseModelExcludeNull):
+    """A set of changes to apply to a model."""
+
+    # Changes applicable to all models
+    name: Optional[str] = Field(description="Name of the model.", default=None)
+    path: Optional[str] = Field(description="Path to the model.", default=None)
+    description: Optional[str] = Field(description="Model description", default=None)
+    base: Optional[BaseModelType] = Field(description="The base model.", default=None)
+    trigger_phrases: Optional[set[str]] = Field(description="Set of trigger phrases for this model", default=None)
+    default_settings: Optional[MainModelDefaultSettings | ControlAdapterDefaultSettings] = Field(
+        description="Default settings for this model", default=None
+    )
+
+    # Checkpoint-specific changes
+    # TODO(MM2): Should we expose these? Feels footgun-y...
+    variant: Optional[ModelVariantType] = Field(description="The variant of the model.", default=None)
+    prediction_type: Optional[SchedulerPredictionType] = Field(
+        description="The prediction type of the model.", default=None
+    )
+    upcast_attention: Optional[bool] = Field(description="Whether to upcast attention.", default=None)
+    config_path: Optional[str] = Field(description="Path to config file for model", default=None)
+
+
 class ModelRecordServiceBase(ABC):
     """Abstract base class for storage and retrieval of model configs."""
 
     @abstractmethod
-    def add_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def add_model(self, config: AnyModelConfig) -> AnyModelConfig:
         """
         Add a model to the database.
 
@@ -81,13 +115,12 @@ class ModelRecordServiceBase(ABC):
         pass
 
     @abstractmethod
-    def update_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def update_model(self, key: str, changes: ModelRecordChanges) -> AnyModelConfig:
         """
         Update the model, returning the updated version.
 
-        :param key: Unique key for the model to be updated
-        :param config: Model configuration record. Either a dict with the
-         required fields, or a ModelConfigBase instance.
+        :param key: Unique key for the model to be updated.
+        :param changes: A set of changes to apply to this model. Changes are validated before being written.
         """
         pass
 
@@ -102,40 +135,17 @@ class ModelRecordServiceBase(ABC):
         """
         pass
 
-    @property
     @abstractmethod
-    def metadata_store(self) -> ModelMetadataStore:
-        """Return a ModelMetadataStore initialized on the same database."""
-        pass
-
-    @abstractmethod
-    def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
+    def get_model_by_hash(self, hash: str) -> AnyModelConfig:
         """
-        Retrieve metadata (if any) from when model was downloaded from a repo.
+        Retrieve the configuration for the indicated model.
 
-        :param key: Model key
+        :param hash: Hash of model config to be fetched.
+
+        Exceptions: UnknownModelException
         """
         pass
 
-    @abstractmethod
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:
-        """List metadata for all models that have it."""
-        pass
-
-    @abstractmethod
-    def search_by_metadata_tag(self, tags: Set[str]) -> List[AnyModelConfig]:
-        """
-        Search model metadata for ones with all listed tags and return their corresponding configs.
-
-        :param tags: Set of tags to search for. All tags must be present.
-        """
-        pass
-
-    @abstractmethod
-    def list_tags(self) -> Set[str]:
-        """Return a unique set of all the model tags in the metadata database."""
-        pass
-
     @abstractmethod
     def list_models(
         self, page: int = 0, per_page: int = 10, order_by: ModelRecordOrderBy = ModelRecordOrderBy.Default
@@ -146,7 +156,7 @@ class ModelRecordServiceBase(ABC):
     @abstractmethod
     def exists(self, key: str) -> bool:
         """
-        Return True if a model with the indicated key exists in the databse.
+        Return True if a model with the indicated key exists in the database.
 
         :param key: Unique key for the model to be deleted
         """
@@ -210,21 +220,3 @@ class ModelRecordServiceBase(ABC):
                 f"More than one model matched the search criteria: base_model='{base_model}', model_type='{model_type}', model_name='{model_name}'."
             )
         return model_configs[0]
-
-    def rename_model(
-        self,
-        key: str,
-        new_name: str,
-    ) -> AnyModelConfig:
-        """
-        Rename the indicated model. Just a special case of update_model().
-
-        In some implementations, renaming the model may involve changing where
-        it is stored on the filesystem. So this is broken out.
-
-        :param key: Model key
-        :param new_name: New name for model
-        """
-        config = self.get_model(key)
-        config.name = new_name
-        return self.update_model(key, config)

invokeai/app/services/model_records/model_records_sql.py

@@ -39,12 +39,11 @@ Typical usage:
   configs = store.search_by_attr(base_model='sd-2', model_type='main')
 """
 
-
 import json
 import sqlite3
 from math import ceil
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple, Union
+from typing import List, Optional, Union
 
 from invokeai.app.services.shared.pagination import PaginatedResults
 from invokeai.backend.model_manager.config import (
@@ -54,11 +53,11 @@ from invokeai.backend.model_manager.config import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.metadata import AnyModelRepoMetadata, ModelMetadataStore, UnknownMetadataException
 
 from ..shared.sqlite.sqlite_database import SqliteDatabase
 from .model_records_base import (
     DuplicateModelException,
+    ModelRecordChanges,
     ModelRecordOrderBy,
     ModelRecordServiceBase,
     ModelSummary,
@@ -73,19 +72,18 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         """
         Initialize a new object from preexisting sqlite3 connection and threading lock objects.
 
-        :param conn: sqlite3 connection object
-        :param lock: threading Lock object
+        :param db: Sqlite connection object
         """
         super().__init__()
         self._db = db
-        self._cursor = self._db.conn.cursor()
+        self._cursor = db.conn.cursor()
 
     @property
     def db(self) -> SqliteDatabase:
         """Return the underlying database."""
         return self._db
 
-    def add_model(self, key: str, config: Union[Dict[str, Any], AnyModelConfig]) -> AnyModelConfig:
+    def add_model(self, config: AnyModelConfig) -> AnyModelConfig:
         """
         Add a model to the database.
 
@@ -95,23 +93,19 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
 
         Can raise DuplicateModelException and InvalidModelConfigException exceptions.
         """
-        record = ModelConfigFactory.make_config(config, key=key)  # ensure it is a valid config obect.
-        json_serialized = record.model_dump_json()  # and turn it into a json string.
         with self._db.lock:
             try:
                 self._cursor.execute(
                     """--sql
-                    INSERT INTO model_config (
+                    INSERT INTO models (
                        id,
-                       original_hash,
                        config
                       )
-                    VALUES (?,?,?);
+                    VALUES (?,?);
                     """,
                     (
-                        key,
-                        record.original_hash,
-                        json_serialized,
+                        config.key,
+                        config.model_dump_json(),
                     ),
                 )
                 self._db.conn.commit()
@@ -119,12 +113,12 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
             except sqlite3.IntegrityError as e:
                 self._db.conn.rollback()
                 if "UNIQUE constraint failed" in str(e):
-                    if "model_config.path" in str(e):
-                        msg = f"A model with path '{record.path}' is already installed"
-                    elif "model_config.name" in str(e):
-                        msg = f"A model with name='{record.name}', type='{record.type}', base='{record.base}' is already installed"
+                    if "models.path" in str(e):
+                        msg = f"A model with path '{config.path}' is already installed"
+                    elif "models.name" in str(e):
+                        msg = f"A model with name='{config.name}', type='{config.type}', base='{config.base}' is already installed"
                     else:
-                        msg = f"A model with key '{key}' is already installed"
+                        msg = f"A model with key '{config.key}' is already installed"
                     raise DuplicateModelException(msg) from e
                 else:
                     raise e
@@ -132,7 +126,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 self._db.conn.rollback()
                 raise e
 
-        return self.get_model(key)
+        return self.get_model(config.key)
 
     def del_model(self, key: str) -> None:
         """
@@ -146,7 +140,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
             try:
                 self._cursor.execute(
                     """--sql
-                    DELETE FROM model_config
+                    DELETE FROM models
                     WHERE id=?;
                     """,
                     (key,),
@@ -158,21 +152,20 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 self._db.conn.rollback()
                 raise e
 
-    def update_model(self, key: str, config: Union[dict, AnyModelConfig]) -> AnyModelConfig:
-        """
-        Update the model, returning the updated version.
+    def update_model(self, key: str, changes: ModelRecordChanges) -> AnyModelConfig:
+        record = self.get_model(key)
+
+        # Model configs use pydantic's `validate_assignment`, so each change is validated by pydantic.
+        for field_name in changes.model_fields_set:
+            setattr(record, field_name, getattr(changes, field_name))
+
+        json_serialized = record.model_dump_json()
 
-        :param key: Unique key for the model to be updated
-        :param config: Model configuration record. Either a dict with the
-         required fields, or a ModelConfigBase instance.
-        """
-        record = ModelConfigFactory.make_config(config, key=key)  # ensure it is a valid config obect
-        json_serialized = record.model_dump_json()  # and turn it into a json string.
         with self._db.lock:
             try:
                 self._cursor.execute(
                     """--sql
-                    UPDATE model_config
+                    UPDATE models
                     SET
                         config=?
                     WHERE id=?;
@@ -199,7 +192,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config FROM model_config
+                SELECT config, strftime('%s',updated_at) FROM models
                 WHERE id=?;
                 """,
                 (key,),
@@ -207,7 +200,22 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
             rows = self._cursor.fetchone()
             if not rows:
                 raise UnknownModelException("model not found")
-            model = ModelConfigFactory.make_config(json.loads(rows[0]))
+            model = ModelConfigFactory.make_config(json.loads(rows[0]), timestamp=rows[1])
+        return model
+
+    def get_model_by_hash(self, hash: str) -> AnyModelConfig:
+        with self._db.lock:
+            self._cursor.execute(
+                """--sql
+                SELECT config, strftime('%s',updated_at) FROM models
+                WHERE hash=?;
+                """,
+                (hash,),
+            )
+            rows = self._cursor.fetchone()
+            if not rows:
+                raise UnknownModelException("model not found")
+            model = ModelConfigFactory.make_config(json.loads(rows[0]), timestamp=rows[1])
         return model
 
     def exists(self, key: str) -> bool:
@@ -220,7 +228,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                select count(*) FROM model_config
+                select count(*) FROM models
                 WHERE id=?;
                 """,
                 (key,),
@@ -234,6 +242,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         base_model: Optional[BaseModelType] = None,
         model_type: Optional[ModelType] = None,
         model_format: Optional[ModelFormat] = None,
+        order_by: ModelRecordOrderBy = ModelRecordOrderBy.Default,
     ) -> List[AnyModelConfig]:
         """
         Return models matching name, base and/or type.
@@ -242,13 +251,23 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         :param base_model: Filter by base model (optional)
         :param model_type: Filter by type of model (optional)
         :param model_format: Filter by model format (e.g. "diffusers") (optional)
+        :param order_by: Result order
 
         If none of the optional filters are passed, will return all
         models in the database.
         """
-        results = []
-        where_clause = []
-        bindings = []
+
+        assert isinstance(order_by, ModelRecordOrderBy)
+        ordering = {
+            ModelRecordOrderBy.Default: "type, base, name, format",
+            ModelRecordOrderBy.Type: "type",
+            ModelRecordOrderBy.Base: "base",
+            ModelRecordOrderBy.Name: "name",
+            ModelRecordOrderBy.Format: "format",
+        }
+
+        where_clause: list[str] = []
+        bindings: list[str] = []
         if model_name:
             where_clause.append("name=?")
             bindings.append(model_name)
@@ -265,12 +284,15 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 f"""--sql
-                select config FROM model_config
-                {where};
+                SELECT config, strftime('%s',updated_at)
+                FROM models
+                {where}
+                ORDER BY {ordering[order_by]} -- using ? to bind doesn't work here for some reason;
                 """,
                 tuple(bindings),
             )
-            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
+            result = self._cursor.fetchall()
+            results = [ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in result]
         return results
 
     def search_by_path(self, path: Union[str, Path]) -> List[AnyModelConfig]:
@@ -279,105 +301,61 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config FROM model_config
+                SELECT config, strftime('%s',updated_at) FROM models
                 WHERE path=?;
                 """,
                 (str(path),),
             )
-            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
+            results = [
+                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
+            ]
         return results
 
     def search_by_hash(self, hash: str) -> List[AnyModelConfig]:
-        """Return models with the indicated original_hash."""
+        """Return models with the indicated hash."""
         results = []
         with self._db.lock:
             self._cursor.execute(
                 """--sql
-                SELECT config FROM model_config
-                WHERE original_hash=?;
+                SELECT config, strftime('%s',updated_at) FROM models
+                WHERE hash=?;
                 """,
                 (hash,),
             )
-            results = [ModelConfigFactory.make_config(json.loads(x[0])) for x in self._cursor.fetchall()]
+            results = [
+                ModelConfigFactory.make_config(json.loads(x[0]), timestamp=x[1]) for x in self._cursor.fetchall()
+            ]
         return results
 
-    @property
-    def metadata_store(self) -> ModelMetadataStore:
-        """Return a ModelMetadataStore initialized on the same database."""
-        return ModelMetadataStore(self._db)
-
-    def get_metadata(self, key: str) -> Optional[AnyModelRepoMetadata]:
-        """
-        Retrieve metadata (if any) from when model was downloaded from a repo.
-
-        :param key: Model key
-        """
-        store = self.metadata_store
-        try:
-            metadata = store.get_metadata(key)
-            return metadata
-        except UnknownMetadataException:
-            return None
-
-    def search_by_metadata_tag(self, tags: Set[str]) -> List[AnyModelConfig]:
-        """
-        Search model metadata for ones with all listed tags and return their corresponding configs.
-
-        :param tags: Set of tags to search for. All tags must be present.
-        """
-        store = ModelMetadataStore(self._db)
-        keys = store.search_by_tag(tags)
-        return [self.get_model(x) for x in keys]
-
-    def list_tags(self) -> Set[str]:
-        """Return a unique set of all the model tags in the metadata database."""
-        store = ModelMetadataStore(self._db)
-        return store.list_tags()
-
-    def list_all_metadata(self) -> List[Tuple[str, AnyModelRepoMetadata]]:
-        """List metadata for all models that have it."""
-        store = ModelMetadataStore(self._db)
-        return store.list_all_metadata()
-
     def list_models(
         self, page: int = 0, per_page: int = 10, order_by: ModelRecordOrderBy = ModelRecordOrderBy.Default
     ) -> PaginatedResults[ModelSummary]:
         """Return a paginated summary listing of each model in the database."""
+        assert isinstance(order_by, ModelRecordOrderBy)
         ordering = {
-            ModelRecordOrderBy.Default: "a.type, a.base, a.format, a.name",
-            ModelRecordOrderBy.Type: "a.type",
-            ModelRecordOrderBy.Base: "a.base",
-            ModelRecordOrderBy.Name: "a.name",
-            ModelRecordOrderBy.Format: "a.format",
+            ModelRecordOrderBy.Default: "type, base, name, format",
+            ModelRecordOrderBy.Type: "type",
+            ModelRecordOrderBy.Base: "base",
+            ModelRecordOrderBy.Name: "name",
+            ModelRecordOrderBy.Format: "format",
         }
 
-        def _fixup(summary: Dict[str, str]) -> Dict[str, Union[str, int, Set[str]]]:
-            """Fix up results so that there are no null values."""
-            result: Dict[str, Union[str, int, Set[str]]] = {}
-            for key, item in summary.items():
-                result[key] = item or ""
-            result["tags"] = set(json.loads(summary["tags"] or "[]"))
-            return result
-
         # Lock so that the database isn't updated while we're doing the two queries.
         with self._db.lock:
             # query1: get the total number of model configs
             self._cursor.execute(
                 """--sql
-                select count(*) from model_config;
+                select count(*) from models;
                 """,
                 (),
             )
             total = int(self._cursor.fetchone()[0])
 
-            # query2: fetch key fields from the join of model_config and model_metadata
+            # query2: fetch key fields
             self._cursor.execute(
                 f"""--sql
-                SELECT a.id as key, a.type, a.base, a.format, a.name,
-                       json_extract(a.config, '$.description') as description,
-                       json_extract(b.metadata, '$.tags') as tags
-                FROM model_config AS a
-                LEFT JOIN model_metadata AS b on a.id=b.id
+                SELECT config
+                FROM models
                 ORDER BY {ordering[order_by]} -- using ? to bind doesn't work here for some reason
                 LIMIT ?
                 OFFSET ?;
@@ -388,7 +366,7 @@ class ModelRecordServiceSQL(ModelRecordServiceBase):
                 ),
             )
             rows = self._cursor.fetchall()
-            items = [ModelSummary.model_validate(_fixup(dict(x))) for x in rows]
+            items = [ModelSummary.model_validate(dict(x)) for x in rows]
             return PaginatedResults(
                 page=page, pages=ceil(total / per_page), per_page=per_page, total=total, items=items
             )

invokeai/app/services/session_processor/session_processor_common.py

@@ -4,3 +4,17 @@ from pydantic import BaseModel, Field
 class SessionProcessorStatus(BaseModel):
     is_started: bool = Field(description="Whether the session processor is started")
     is_processing: bool = Field(description="Whether a session is being processed")
+
+
+class CanceledException(Exception):
+    """Execution canceled by user."""
+
+    pass
+
+
+class ProgressImage(BaseModel):
+    """The progress image sent intermittently during processing"""
+
+    width: int = Field(description="The effective width of the image in pixels")
+    height: int = Field(description="The effective height of the image in pixels")
+    dataURL: str = Field(description="The image data as a b64 data URL")

invokeai/app/services/session_processor/session_processor_default.py

@@ -1,4 +1,5 @@
 import traceback
+from contextlib import suppress
 from threading import BoundedSemaphore, Thread
 from threading import Event as ThreadEvent
 from typing import Optional
@@ -6,136 +7,271 @@ from typing import Optional
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.typing import Event as FastAPIEvent
 
+from invokeai.app.invocations.baseinvocation import BaseInvocation
 from invokeai.app.services.events.events_base import EventServiceBase
+from invokeai.app.services.invocation_stats.invocation_stats_common import GESStatsNotFoundError
+from invokeai.app.services.session_processor.session_processor_common import CanceledException
 from invokeai.app.services.session_queue.session_queue_common import SessionQueueItem
+from invokeai.app.services.shared.invocation_context import InvocationContextData, build_invocation_context
+from invokeai.app.util.profiler import Profiler
 
 from ..invoker import Invoker
 from .session_processor_base import SessionProcessorBase
 from .session_processor_common import SessionProcessorStatus
 
-POLLING_INTERVAL = 1
-THREAD_LIMIT = 1
-
 
 class DefaultSessionProcessor(SessionProcessorBase):
-    def start(self, invoker: Invoker) -> None:
-        self.__invoker: Invoker = invoker
-        self.__queue_item: Optional[SessionQueueItem] = None
+    def start(self, invoker: Invoker, thread_limit: int = 1, polling_interval: int = 1) -> None:
+        self._invoker: Invoker = invoker
+        self._queue_item: Optional[SessionQueueItem] = None
+        self._invocation: Optional[BaseInvocation] = None
 
-        self.__resume_event = ThreadEvent()
-        self.__stop_event = ThreadEvent()
-        self.__poll_now_event = ThreadEvent()
+        self._resume_event = ThreadEvent()
+        self._stop_event = ThreadEvent()
+        self._poll_now_event = ThreadEvent()
+        self._cancel_event = ThreadEvent()
 
         local_handler.register(event_name=EventServiceBase.queue_event, _func=self._on_queue_event)
 
-        self.__threadLimit = BoundedSemaphore(THREAD_LIMIT)
-        self.__thread = Thread(
+        self._thread_limit = thread_limit
+        self._thread_semaphore = BoundedSemaphore(thread_limit)
+        self._polling_interval = polling_interval
+
+        # If profiling is enabled, create a profiler. The same profiler will be used for all sessions. Internally,
+        # the profiler will create a new profile for each session.
+        self._profiler = (
+            Profiler(
+                logger=self._invoker.services.logger,
+                output_dir=self._invoker.services.configuration.profiles_path,
+                prefix=self._invoker.services.configuration.profile_prefix,
+            )
+            if self._invoker.services.configuration.profile_graphs
+            else None
+        )
+
+        self._thread = Thread(
             name="session_processor",
-            target=self.__process,
+            target=self._process,
             kwargs={
-                "stop_event": self.__stop_event,
-                "poll_now_event": self.__poll_now_event,
-                "resume_event": self.__resume_event,
+                "stop_event": self._stop_event,
+                "poll_now_event": self._poll_now_event,
+                "resume_event": self._resume_event,
+                "cancel_event": self._cancel_event,
             },
         )
-        self.__thread.start()
+        self._thread.start()
 
     def stop(self, *args, **kwargs) -> None:
-        self.__stop_event.set()
+        self._stop_event.set()
 
     def _poll_now(self) -> None:
-        self.__poll_now_event.set()
+        self._poll_now_event.set()
 
     async def _on_queue_event(self, event: FastAPIEvent) -> None:
         event_name = event[1]["event"]
 
-        # This was a match statement, but match is not supported on python 3.9
-        if event_name in [
-            "graph_execution_state_complete",
-            "invocation_error",
-            "session_retrieval_error",
-            "invocation_retrieval_error",
-        ]:
-            self.__queue_item = None
-            self._poll_now()
-        elif (
-            event_name == "session_canceled"
-            and self.__queue_item is not None
-            and self.__queue_item.session_id == event[1]["data"]["graph_execution_state_id"]
-        ):
-            self.__queue_item = None
+        if event_name == "session_canceled" or event_name == "queue_cleared":
+            # These both mean we should cancel the current session.
+            self._cancel_event.set()
             self._poll_now()
         elif event_name == "batch_enqueued":
             self._poll_now()
-        elif event_name == "queue_cleared":
-            self.__queue_item = None
-            self._poll_now()
 
     def resume(self) -> SessionProcessorStatus:
-        if not self.__resume_event.is_set():
-            self.__resume_event.set()
+        if not self._resume_event.is_set():
+            self._resume_event.set()
         return self.get_status()
 
     def pause(self) -> SessionProcessorStatus:
-        if self.__resume_event.is_set():
-            self.__resume_event.clear()
+        if self._resume_event.is_set():
+            self._resume_event.clear()
         return self.get_status()
 
     def get_status(self) -> SessionProcessorStatus:
         return SessionProcessorStatus(
-            is_started=self.__resume_event.is_set(),
-            is_processing=self.__queue_item is not None,
+            is_started=self._resume_event.is_set(),
+            is_processing=self._queue_item is not None,
         )
 
-    def __process(
+    def _process(
         self,
         stop_event: ThreadEvent,
         poll_now_event: ThreadEvent,
         resume_event: ThreadEvent,
+        cancel_event: ThreadEvent,
     ):
+        # Outermost processor try block; any unhandled exception is a fatal processor error
         try:
+            self._thread_semaphore.acquire()
             stop_event.clear()
             resume_event.set()
-            self.__threadLimit.acquire()
-            queue_item: Optional[SessionQueueItem] = None
+            cancel_event.clear()
+
             while not stop_event.is_set():
                 poll_now_event.clear()
+                # Middle processor try block; any unhandled exception is a non-fatal processor error
                 try:
-                    # do not dequeue if there is already a session running
-                    if self.__queue_item is None and resume_event.is_set():
-                        queue_item = self.__invoker.services.session_queue.dequeue()
+                    # Get the next session to process
+                    self._queue_item = self._invoker.services.session_queue.dequeue()
+                    if self._queue_item is not None and resume_event.is_set():
+                        self._invoker.services.logger.debug(f"Executing queue item {self._queue_item.item_id}")
+                        cancel_event.clear()
 
-                        if queue_item is not None:
-                            self.__invoker.services.logger.debug(f"Executing queue item {queue_item.item_id}")
-                            self.__queue_item = queue_item
-                            self.__invoker.services.graph_execution_manager.set(queue_item.session)
-                            self.__invoker.invoke(
-                                session_queue_batch_id=queue_item.batch_id,
-                                session_queue_id=queue_item.queue_id,
-                                session_queue_item_id=queue_item.item_id,
-                                graph_execution_state=queue_item.session,
-                                workflow=queue_item.workflow,
-                                invoke_all=True,
+                        # If profiling is enabled, start the profiler
+                        if self._profiler is not None:
+                            self._profiler.start(profile_id=self._queue_item.session_id)
+
+                        # Prepare invocations and take the first
+                        self._invocation = self._queue_item.session.next()
+
+                        # Loop over invocations until the session is complete or canceled
+                        while self._invocation is not None and not cancel_event.is_set():
+                            # get the source node id to provide to clients (the prepared node id is not as useful)
+                            source_invocation_id = self._queue_item.session.prepared_source_mapping[self._invocation.id]
+
+                            # Send starting event
+                            self._invoker.services.events.emit_invocation_started(
+                                queue_batch_id=self._queue_item.batch_id,
+                                queue_item_id=self._queue_item.item_id,
+                                queue_id=self._queue_item.queue_id,
+                                graph_execution_state_id=self._queue_item.session_id,
+                                node=self._invocation.model_dump(),
+                                source_node_id=source_invocation_id,
                             )
-                            queue_item = None
 
-                    if queue_item is None:
-                        self.__invoker.services.logger.debug("Waiting for next polling interval or event")
-                        poll_now_event.wait(POLLING_INTERVAL)
+                            # Innermost processor try block; any unhandled exception is an invocation error & will fail the graph
+                            try:
+                                with self._invoker.services.performance_statistics.collect_stats(
+                                    self._invocation, self._queue_item.session.id
+                                ):
+                                    # Build invocation context (the node-facing API)
+                                    data = InvocationContextData(
+                                        invocation=self._invocation,
+                                        source_invocation_id=source_invocation_id,
+                                        queue_item=self._queue_item,
+                                    )
+                                    context = build_invocation_context(
+                                        data=data,
+                                        services=self._invoker.services,
+                                        cancel_event=self._cancel_event,
+                                    )
+
+                                    # Invoke the node
+                                    outputs = self._invocation.invoke_internal(
+                                        context=context, services=self._invoker.services
+                                    )
+
+                                    # Save outputs and history
+                                    self._queue_item.session.complete(self._invocation.id, outputs)
+
+                                    # Send complete event
+                                    self._invoker.services.events.emit_invocation_complete(
+                                        queue_batch_id=self._queue_item.batch_id,
+                                        queue_item_id=self._queue_item.item_id,
+                                        queue_id=self._queue_item.queue_id,
+                                        graph_execution_state_id=self._queue_item.session.id,
+                                        node=self._invocation.model_dump(),
+                                        source_node_id=source_invocation_id,
+                                        result=outputs.model_dump(),
+                                    )
+
+                            except KeyboardInterrupt:
+                                # TODO(MM2): Create an event for this
+                                pass
+
+                            except CanceledException:
+                                # When the user cancels the graph, we first set the cancel event. The event is checked
+                                # between invocations, in this loop. Some invocations are long-running, and we need to
+                                # be able to cancel them mid-execution.
+                                #
+                                # For example, denoising is a long-running invocation with many steps. A step callback
+                                # is executed after each step. This step callback checks if the canceled event is set,
+                                # then raises a CanceledException to stop execution immediately.
+                                #
+                                # When we get a CanceledException, we don't need to do anything - just pass and let the
+                                # loop go to its next iteration, and the cancel event will be handled correctly.
+                                pass
+
+                            except Exception as e:
+                                error = traceback.format_exc()
+
+                                # Save error
+                                self._queue_item.session.set_node_error(self._invocation.id, error)
+                                self._invoker.services.logger.error(
+                                    f"Error while invoking session {self._queue_item.session_id}, invocation {self._invocation.id} ({self._invocation.get_type()}):\n{e}"
+                                )
+                                self._invoker.services.logger.error(error)
+
+                                # Send error event
+                                self._invoker.services.events.emit_invocation_error(
+                                    queue_batch_id=self._queue_item.session_id,
+                                    queue_item_id=self._queue_item.item_id,
+                                    queue_id=self._queue_item.queue_id,
+                                    graph_execution_state_id=self._queue_item.session.id,
+                                    node=self._invocation.model_dump(),
+                                    source_node_id=source_invocation_id,
+                                    error_type=e.__class__.__name__,
+                                    error=error,
+                                )
+                                pass
+
+                            # The session is complete if the all invocations are complete or there was an error
+                            if self._queue_item.session.is_complete() or cancel_event.is_set():
+                                # Send complete event
+                                self._invoker.services.events.emit_graph_execution_complete(
+                                    queue_batch_id=self._queue_item.batch_id,
+                                    queue_item_id=self._queue_item.item_id,
+                                    queue_id=self._queue_item.queue_id,
+                                    graph_execution_state_id=self._queue_item.session.id,
+                                )
+                                # If we are profiling, stop the profiler and dump the profile & stats
+                                if self._profiler:
+                                    profile_path = self._profiler.stop()
+                                    stats_path = profile_path.with_suffix(".json")
+                                    self._invoker.services.performance_statistics.dump_stats(
+                                        graph_execution_state_id=self._queue_item.session.id, output_path=stats_path
+                                    )
+                                # We'll get a GESStatsNotFoundError if we try to log stats for an untracked graph, but in the processor
+                                # we don't care about that - suppress the error.
+                                with suppress(GESStatsNotFoundError):
+                                    self._invoker.services.performance_statistics.log_stats(self._queue_item.session.id)
+                                    self._invoker.services.performance_statistics.reset_stats()
+
+                                # Set the invocation to None to prepare for the next session
+                                self._invocation = None
+                            else:
+                                # Prepare the next invocation
+                                self._invocation = self._queue_item.session.next()
+
+                        # The session is complete, immediately poll for next session
+                        self._queue_item = None
+                        poll_now_event.set()
+                    else:
+                        # The queue was empty, wait for next polling interval or event to try again
+                        self._invoker.services.logger.debug("Waiting for next polling interval or event")
+                        poll_now_event.wait(self._polling_interval)
                         continue
-                except Exception as e:
-                    self.__invoker.services.logger.error(f"Error in session processor: {e}")
-                    if queue_item is not None:
-                        self.__invoker.services.session_queue.cancel_queue_item(
-                            queue_item.item_id, error=traceback.format_exc()
+                except Exception:
+                    # Non-fatal error in processor
+                    self._invoker.services.logger.error(
+                        f"Non-fatal error in session processor:\n{traceback.format_exc()}"
+                    )
+                    # Cancel the queue item
+                    if self._queue_item is not None:
+                        self._invoker.services.session_queue.cancel_queue_item(
+                            self._queue_item.item_id, error=traceback.format_exc()
                         )
-                    poll_now_event.wait(POLLING_INTERVAL)
+                    # Reset the invocation to None to prepare for the next session
+                    self._invocation = None
+                    # Immediately poll for next queue item
+                    poll_now_event.wait(self._polling_interval)
                     continue
-        except Exception as e:
-            self.__invoker.services.logger.error(f"Fatal Error in session processor: {e}")
+        except Exception:
+            # Fatal error in processor, log and pass - we're done here
+            self._invoker.services.logger.error(f"Fatal Error in session processor:\n{traceback.format_exc()}")
             pass
         finally:
             stop_event.clear()
             poll_now_event.clear()
-            self.__queue_item = None
-            self.__threadLimit.release()
+            self._queue_item = None
+            self._thread_semaphore.release()