Run typegen, update version to 4.0.0rc2

- Add helper functions to build metadata for control adapters, including the processed images
- Update parses to parse the new metadata

.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

docker/Dockerfile

@@ -18,8 +18,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
 ENV VIRTUAL_ENV=/opt/venv/invokeai
 
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-ARG TORCH_VERSION=2.1.0
-ARG TORCHVISION_VERSION=0.16
+ARG TORCH_VERSION=2.1.2
+ARG TORCHVISION_VERSION=0.16.2
 ARG GPU_DRIVER=cuda
 ARG TARGETPLATFORM="linux/amd64"
 # unused but available
@@ -35,7 +35,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
     elif [ "$GPU_DRIVER" = "rocm" ]; then \
-        extra_index_url_arg="--index-url https://download.pytorch.org/whl/rocm5.6"; \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.6"; \
     else \
         extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
     fi &&\
@@ -54,7 +54,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
         pip install -e ".[xformers]"; \
     else \
-        pip install -e "."; \
+        pip install $extra_index_url_arg -e "."; \
     fi
 
 # #### Build the Web UI ------------------------------------

docker/run.sh

@@ -21,7 +21,7 @@ run() {
     printf "%s\n" "$build_args"
   fi
 
-  docker compose build $build_args
+  docker compose build $build_args $service_name
   unset build_args
 
   printf "%s\n" "starting service $service_name"

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/INVOCATIONS.md

@@ -9,11 +9,15 @@ complex functionality.
 
 ## Invocations Directory
 
-InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These can be used as examples to create your own nodes.
+InvokeAI Nodes can be found in the `invokeai/app/invocations` directory. These
+can be used as examples to create your own nodes.
 
-New nodes should be added to a subfolder in `nodes` direction found at the root level of the InvokeAI installation location. Nodes added to this folder will be able to be used upon application startup. 
+New nodes should be added to a subfolder in `nodes` direction found at the root
+level of the InvokeAI installation location. Nodes added to this folder will be
+able to be used upon application startup.
+
+Example `nodes` subfolder structure:
 
-Example `nodes`  subfolder structure:
 ```py
 ├── __init__.py # Invoke-managed custom node loader
 │
@@ -30,14 +34,14 @@ Example `nodes`  subfolder structure:
         └── fancy_node.py
 ```
 
-Each node folder must have an `__init__.py` file that imports its nodes. Only nodes imported in the `__init__.py` file are loaded.
- See the README in the nodes folder for more examples: 
+Each node folder must have an `__init__.py` file that imports its nodes. Only
+nodes imported in the `__init__.py` file are loaded. See the README in the nodes
+folder for more examples:
 
 ```py
 from .cool_node import CoolInvocation
 ```
 
-
 ## Creating A New Invocation
 
 In order to understand the process of creating a new Invocation, let us actually
@@ -131,7 +135,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -167,7 +170,6 @@ from invokeai.app.invocations.primitives import ImageField
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -197,7 +199,6 @@ from invokeai.app.invocations.image import ImageOutput
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
 
-    # Inputs
     image: ImageField = InputField(description="The input image")
     width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
@@ -229,30 +230,17 @@ class ResizeInvocation(BaseInvocation):
     height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service. Returns the PIL image.
-        image = context.services.images.get_pil_image(self.image.image_name)
+        # Load the input image as a PIL image
+        image = context.images.get_pil(self.image.image_name)
 
-        # Resizing the image
+        # Resize the image
         resized_image = image.resize((self.width, self.height))
 
-        # Save the image using InvokeAI's predefined Image Service. Returns the prepared PIL image.
-        output_image = context.services.images.create(
-            image=resized_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,
-        )
+        # Save the image
+        image_dto = context.images.save(image=resized_image)
 
-        # Returning the Image
-        return ImageOutput(
-            image=ImageField(
-                image_name=output_image.image_name,
-            ),
-            width=output_image.width,
-            height=output_image.height,
-        )
+        # Return an ImageOutput
+        return ImageOutput.build(image_dto)
 ```
 
 **Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
@@ -343,27 +331,25 @@ class ImageColorStringOutput(BaseInvocationOutput):
 
 That's all there is to it.
 
-<!-- TODO: DANGER - we probably do not want people to create their own field types, because this requires a lot of work on the frontend to accomodate.
-
 ### Custom Input Fields
 
 Now that you know how to create your own Invocations, let us dive into slightly
 more advanced topics.
 
 While creating your own Invocations, you might run into a scenario where the
-existing input types in InvokeAI do not meet your requirements. In such cases,
-you can create your own input types.
+existing fields in InvokeAI do not meet your requirements. In such cases, you
+can create your own fields.
 
 Let us create one as an example. Let us say we want to create a color input
 field that represents a color code. But before we start on that here are some
 general good practices to keep in mind.
 
-**Good Practices**
+### Best Practices
 
 - There is no naming convention for input fields but we highly recommend that
   you name it something appropriate like `ColorField`.
 - It is not mandatory but it is heavily recommended to add a relevant
-  `docstring` to describe your input field.
+  `docstring` to describe your field.
 - Keep your field in the same file as the Invocation that it is made for or in
   another file where it is relevant.
 
@@ -378,10 +364,13 @@ class ColorField(BaseModel):
     pass
 ```
 
-Perfect. Now let us create our custom inputs for our field. This is exactly
-similar how you created input fields for your Invocation. All the same rules
-apply. Let us create four fields representing the _red(r)_, _blue(b)_,
-_green(g)_ and _alpha(a)_ channel of the color.
+Perfect. Now let us create the properties for our field. This is similar to how
+you created input fields for your Invocation. All the same rules apply. Let us
+create four fields representing the _red(r)_, _blue(b)_, _green(g)_ and
+_alpha(a)_ channel of the color.
+
+> Technically, the properties are _also_ called fields - but in this case, it
+> refers to a `pydantic` field.
 
 ```python
 class ColorField(BaseModel):
@@ -396,25 +385,11 @@ That's it. We now have a new input field type that we can use in our Invocations
 like this.
 
 ```python
-color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
+color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
 ```
 
-### Custom Components For Frontend
+### Using the custom field
 
-Every backend input type should have a corresponding frontend component so the
-UI knows what to render when you use a particular field type.
+When you start the UI, your custom field will be automatically recognized.
 
-If you are using existing field types, we already have components for those. So
-you don't have to worry about creating anything new. But this might not always
-be the case. Sometimes you might want to create new field types and have the
-frontend UI deal with it in a different way.
-
-This is where we venture into the world of React and Javascript and create our
-own new components for our Invocations. Do not fear the world of JS. It's
-actually pretty straightforward.
-
-Let us create a new component for our custom color field we created above. When
-we use a color field, let us say we want the UI to display a color picker for
-the user to pick from rather than entering values. That is what we will build
-now.
--->
+Custom fields only support connection inputs in the Workflow Editor.

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

@@ -31,18 +31,18 @@ be referred to as ROOT.
 To find its root directory, InvokeAI uses the following recipe:
 
 1. It first looks for the argument `--root <path>` on the command line
-it was launched from, and uses the indicated path if present.
+   it was launched from, and uses the indicated path if present.
 
 2. Next it looks for the environment variable INVOKEAI_ROOT, and uses
-the directory path found there if present.
+   the directory path found there if present.
 
 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.
+   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.
 
 4. Finally, InvokeAI looks for a directory in the current user's home
-directory named `invokeai`.
+   directory named `invokeai`.
 
 #### Reading the InvokeAI Configuration File
 
@@ -149,104 +149,75 @@ usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS
 
 ## The Configuration Settings
 
-The configuration settings are divided into several distinct
-groups in `invokeia.yaml`:
+The config is managed by the `InvokeAIAppConfig` class, which is a pydantic model. The below docs are autogenerated from the class.
 
-### Web Server
+When editing your `invokeai.yaml` file, you'll need to put settings under their appropriate group. The group for each setting is denoted in the table below.
 
-| 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.                                                |
+Following the table are additional explanations for certain settings.
 
-The documentation for InvokeAI's API can be accessed by browsing to the following URL: [http://localhost:9090/docs].
+<!-- prettier-ignore-start -->
+::: invokeai.app.services.config.config_default.InvokeAIAppConfig
+    options:
+        heading_level: 3
+        members: false
+<!-- prettier-ignore-end -->
 
-### Features
+### Model Marketplace API Keys
 
-These configuration settings allow you to enable and disable various InvokeAI features:
+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.
 
-| 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 |
+The pattern can be any valid regex (you may need to surround the pattern with quotes):
 
-### Generation
+```yaml
+InvokeAI:
+  Model Install:
+    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
+```
 
-These options tune InvokeAI's memory and performance characteristics.
+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.
 
-| 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 |
+### Model Hashing
 
-### Device
+Models are hashed during installation, providing a stable identifier for models across all platforms. The default algorithm is `blake3`, with a multi-threaded implementation.
 
-These options configure the generation execution device.
+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.
 
-| 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 |
+```yaml
+InvokeAI:
+  Model Install:
+    hashing_algorithm: blake3_single
+```
 
+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`.
+
+```yaml
+InvokeAI:
+  Model Install:
+    hashing_algorithm: random
+```
+
+Most common algorithms are supported, like `md5`, `sha256`, and `sha512`. These are typically much, much slower than `blake3`.
 
 ### Paths
 
 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:
-
-```
-Paths:
-  autoimport_dir: autoimport
-#  lora_dir: null
-#  embedding_dir: null
-#  controlnet_dir: null
-```
+way you wish.
 
 ### 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 |
-
 Several different log handler destinations are available, and multiple destinations are supported by providing a list:
 
 ```
@@ -256,9 +227,9 @@ Several different log handler destinations are available, and multiple destinati
      - 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 +242,7 @@ 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 +254,7 @@ 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.

docs/features/CONTROLNET.md

@@ -94,6 +94,8 @@ A model that helps generate creative QR codes that still scan. Can also be used
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
 
+*Note:* The DWPose Processor has replaced the OpenPose processor in Invoke. Workflows and generations that relied on the OpenPose Processor will need to be updated to use the DWPose Processor instead.
+
 **Mediapipe Face**:
 
 The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.

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/installation/020_INSTALL_MANUAL.md

@@ -230,13 +230,13 @@ manager, please follow these steps:
         === "local Webserver"
 
             ```bash
-            invokeai --web
+            invokeai-web
             ```
 
         === "Public Webserver"
 
             ```bash
-            invokeai --web --host 0.0.0.0
+            invokeai-web --host 0.0.0.0
             ```
 
         === "CLI"
@@ -402,4 +402,4 @@ environment variable INVOKEAI_ROOT to point to the installation directory.
 Note that if you run into problems with the Conda installation, the InvokeAI
 staff will **not** be able to help you out. Caveat Emptor!
 
-[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939
+[dev-chat]: https://discord.com/channels/1020123559063990373/1049495067846524939

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                                                                      |
@@ -81,7 +83,7 @@ their descriptions.
 | ONNX Text to Latents                                          | Generates latents from conditionings.                                                                                                                |
 | ONNX Model Loader                                             | Loads a main model, outputting its submodels.                                                                                                        |
 | OpenCV Inpaint                                                | Simple inpaint using opencv.                                                                                                                         |
-| Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
+| DW Openpose Processor                                            | Applies Openpose processing to image                                                                                                                 |
 | PIDI Processor                                                | Applies PIDI processing to image                                                                                                                     |
 | Prompts from File                                             | Loads prompts from a text file                                                                                                                       |
 | Random Integer                                                | Outputs a single random integer.                                                                                                                     |

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

@@ -2,9 +2,12 @@
 
 from logging import Logger
 
-from invokeai.app.services.item_storage.item_storage_memory import ItemStorageMemory
+import torch
+
+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__
 
@@ -12,26 +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.latents_storage.latents_storage_disk import DiskLatentsStorage
-from ..services.latents_storage.latents_storage_forward_cache import ForwardCacheLatentsStorage
-from ..services.model_install import ModelInstallService
+from ..services.model_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
@@ -68,8 +67,13 @@ class ApiDependencies:
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
         output_folder = config.output_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
@@ -80,26 +84,26 @@ 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)
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
-        model_manager = ModelManagerService(config, logger)
-        model_record_service = ModelRecordServiceSQL(db=db)
+        tensors = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[torch.Tensor](output_folder / "tensors", ephemeral=True)
+        )
+        conditioning = ObjectSerializerForwardCache(
+            ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
+        )
         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()
@@ -110,27 +114,25 @@ 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,
-            latents=latents,
             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,
             workflow_records=workflow_records,
+            tensors=tensors,
+            conditioning=conditioning,
         )
 
         ApiDependencies.invoker = Invoker(services)

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

@@ -2,13 +2,13 @@ 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
 from pydantic import BaseModel, Field, ValidationError
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
 from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
@@ -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

@@ -3,7 +3,8 @@
 # values from the command line or config file.
 import sys
 
-from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.services.session_processor.session_processor_common import ProgressImage
 from invokeai.version.invokeai_version import __version__
 
 from .services.config import InvokeAIAppConfig
@@ -18,6 +19,7 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     import asyncio
     import mimetypes
     import socket
+    from contextlib import asynccontextmanager
     from inspect import signature
     from pathlib import Path
     from typing import Any
@@ -38,6 +40,7 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
     # 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 ..backend.util.logging import InvokeAILogger
     from .api.dependencies import ApiDependencies
@@ -47,20 +50,17 @@ if True:  # hack to make flake8 happy with imports coming after setting up the c
         boards,
         download_queue,
         images,
-        model_records,
-        models,
+        model_manager,
         session_queue,
-        sessions,
         utilities,
         workflows,
     )
     from .api.sockets import SocketIO
     from .invocations.baseinvocation import (
         BaseInvocation,
-        InputFieldJSONSchemaExtra,
-        OutputFieldJSONSchemaExtra,
         UIConfigBase,
     )
+    from .invocations.fields import InputFieldJSONSchemaExtra, OutputFieldJSONSchemaExtra
 
     if is_mps_available():
         import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
@@ -74,9 +74,25 @@ logger = InvokeAILogger.get_logger(config=app_config)
 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)
@@ -99,24 +115,9 @@ 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")
@@ -154,18 +155,22 @@ 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:
@@ -176,23 +181,24 @@ 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

invokeai/app/invocations/baseinvocation.py

@@ -8,17 +8,33 @@ 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, RootModel, TypeAdapter, create_model
-from pydantic.fields import FieldInfo, _Unset
+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.workflow_records.workflow_records_common import WorkflowWithoutID
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.metaenum import MetaEnum
 from invokeai.app.util.misc import uuid_string
 from invokeai.backend.util.logging import InvokeAILogger
@@ -52,393 +68,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
 
 
-class Input(str, Enum, metaclass=MetaEnum):
-    """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
-    """
-
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class FieldKind(str, Enum, metaclass=MetaEnum):
-    """
-    The kind of field.
-    - `Input`: An input field on a node.
-    - `Output`: An output field on a node.
-    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
-    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
-    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
-    allowing "metadata" for that field.
-    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
-    but which are used to store information about the node. For example, the `id` and `type` fields are node
-    attributes.
-
-    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
-    startup, and when generating the OpenAPI schema for the workflow editor.
-    """
-
-    Input = "input"
-    Output = "output"
-    Internal = "internal"
-    NodeAttribute = "node_attribute"
-
-
-class UIType(str, Enum, metaclass=MetaEnum):
-    """
-    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
-
-    - Model Fields
-    The most common node-author-facing use will be for model fields. Internally, there is no difference
-    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
-    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
-    the field is an SDXL main model field.
-
-    - Any Field
-    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
-    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
-
-    - Scheduler Field
-    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
-
-    - Internal Fields
-    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
-    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
-    should not be used by node authors.
-
-    - DEPRECATED Fields
-    These types are deprecated and should not be used by node authors. A warning will be logged if one is
-    used, and the type will be ignored. They are included here for backwards compatibility.
-    """
-
-    # region Model Field Types
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VAEModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    # endregion
-
-    # region Misc Field Types
-    Scheduler = "SchedulerField"
-    Any = "AnyField"
-    # endregion
-
-    # region Internal Field Types
-    _Collection = "CollectionField"
-    _CollectionItem = "CollectionItemField"
-    # endregion
-
-    # region DEPRECATED
-    Boolean = "DEPRECATED_Boolean"
-    Color = "DEPRECATED_Color"
-    Conditioning = "DEPRECATED_Conditioning"
-    Control = "DEPRECATED_Control"
-    Float = "DEPRECATED_Float"
-    Image = "DEPRECATED_Image"
-    Integer = "DEPRECATED_Integer"
-    Latents = "DEPRECATED_Latents"
-    String = "DEPRECATED_String"
-    BooleanCollection = "DEPRECATED_BooleanCollection"
-    ColorCollection = "DEPRECATED_ColorCollection"
-    ConditioningCollection = "DEPRECATED_ConditioningCollection"
-    ControlCollection = "DEPRECATED_ControlCollection"
-    FloatCollection = "DEPRECATED_FloatCollection"
-    ImageCollection = "DEPRECATED_ImageCollection"
-    IntegerCollection = "DEPRECATED_IntegerCollection"
-    LatentsCollection = "DEPRECATED_LatentsCollection"
-    StringCollection = "DEPRECATED_StringCollection"
-    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
-    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
-    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
-    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
-    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
-    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
-    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
-    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
-    StringPolymorphic = "DEPRECATED_StringPolymorphic"
-    MainModel = "DEPRECATED_MainModel"
-    UNet = "DEPRECATED_UNet"
-    Vae = "DEPRECATED_Vae"
-    CLIP = "DEPRECATED_CLIP"
-    Collection = "DEPRECATED_Collection"
-    CollectionItem = "DEPRECATED_CollectionItem"
-    Enum = "DEPRECATED_Enum"
-    WorkflowField = "DEPRECATED_WorkflowField"
-    IsIntermediate = "DEPRECATED_IsIntermediate"
-    BoardField = "DEPRECATED_BoardField"
-    MetadataItem = "DEPRECATED_MetadataItem"
-    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
-    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
-    MetadataDict = "DEPRECATED_MetadataDict"
-    # endregion
-
-
-class UIComponent(str, Enum, metaclass=MetaEnum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class InputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
-    and by the workflow editor during schema parsing and UI rendering.
-    """
-
-    input: Input
-    orig_required: bool
-    field_kind: FieldKind
-    default: Optional[Any] = None
-    orig_default: Optional[Any] = None
-    ui_hidden: bool = False
-    ui_type: Optional[UIType] = None
-    ui_component: Optional[UIComponent] = None
-    ui_order: Optional[int] = None
-    ui_choice_labels: Optional[dict[str, str]] = None
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-class OutputFieldJSONSchemaExtra(BaseModel):
-    """
-    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
-    during schema parsing and UI rendering.
-    """
-
-    field_kind: FieldKind
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-    model_config = ConfigDict(
-        validate_assignment=True,
-        json_schema_serialization_defaults_required=True,
-    )
-
-
-def InputField(
-    # copied from pydantic's Field
-    # TODO: Can we support default_factory?
-    default: Any = _Unset,
-    default_factory: Callable[[], Any] | None = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
-
-    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
-    """
-
-    json_schema_extra_ = InputFieldJSONSchemaExtra(
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        ui_choice_labels=ui_choice_labels,
-        field_kind=FieldKind.Input,
-        orig_required=True,
-    )
-
-    """
-    There is a conflict between the typing of invocation definitions and the typing of an invocation's
-    `invoke()` function.
-
-    On instantiation of a node, the invocation definition is used to create the python class. At this time,
-    any number of fields may be optional, because they may be provided by connections.
-
-    On calling of `invoke()`, however, those fields may be required.
-
-    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
-
-    `image` is required during the call to `invoke()`, but when the python class is instantiated,
-    the field may not be present. This is fine, because that image field will be provided by a
-    connection from an ancestor node, which outputs an image.
-
-    This means we want to type the `image` field as optional for the node class definition, but required
-    for the `invoke()` function.
-
-    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
-    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
-    any static type analysis tools will complain.
-
-    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
-    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
-    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
-    """
-
-    if default_factory is not _Unset and default_factory is not None:
-        default = default_factory()
-        logger.warn('"default_factory" is not supported, calling it now to set "default"')
-
-    # These are the args we may wish pass to the pydantic `Field()` function
-    field_args = {
-        "default": default,
-        "title": title,
-        "description": description,
-        "pattern": pattern,
-        "strict": strict,
-        "gt": gt,
-        "ge": ge,
-        "lt": lt,
-        "le": le,
-        "multiple_of": multiple_of,
-        "allow_inf_nan": allow_inf_nan,
-        "max_digits": max_digits,
-        "decimal_places": decimal_places,
-        "min_length": min_length,
-        "max_length": max_length,
-    }
-
-    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
-    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
-
-    # Because we are manually making fields optional, we need to store the original required bool for reference later
-    json_schema_extra_.orig_required = default is PydanticUndefined
-
-    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
-    if input is Input.Any or input is Input.Connection:
-        default_ = None if default is PydanticUndefined else default
-        provided_args.update({"default": default_})
-        if default is not PydanticUndefined:
-            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
-            json_schema_extra_.default = default
-            json_schema_extra_.orig_default = default
-    elif default is not PydanticUndefined:
-        default_ = default
-        provided_args.update({"default": default_})
-        json_schema_extra_.orig_default = default_
-
-    return Field(
-        **provided_args,
-        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
-    )
-
-
-def OutputField(
-    # copied from pydantic's Field
-    default: Any = _Unset,
-    title: str | None = _Unset,
-    description: str | None = _Unset,
-    pattern: str | None = _Unset,
-    strict: bool | None = _Unset,
-    gt: float | None = _Unset,
-    ge: float | None = _Unset,
-    lt: float | None = _Unset,
-    le: float | None = _Unset,
-    multiple_of: float | None = _Unset,
-    allow_inf_nan: bool | None = _Unset,
-    max_digits: int | None = _Unset,
-    decimal_places: int | None = _Unset,
-    min_length: int | None = _Unset,
-    max_length: int | None = _Unset,
-    # custom
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        default=default,
-        title=title,
-        description=description,
-        pattern=pattern,
-        strict=strict,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_length=min_length,
-        max_length=max_length,
-        json_schema_extra=OutputFieldJSONSchemaExtra(
-            ui_type=ui_type,
-            ui_hidden=ui_hidden,
-            ui_order=ui_order,
-            field_kind=FieldKind.Output,
-        ).model_dump(exclude_none=True),
-    )
-
-
 class UIConfigBase(BaseModel):
     """
     Provides additional node configuration to the UI.
@@ -460,33 +89,6 @@ class UIConfigBase(BaseModel):
     )
 
 
-class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
-    services: InvocationServices
-    graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
-    workflow: Optional[WorkflowWithoutID]
-
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        graph_execution_state_id: str,
-        workflow: Optional[WorkflowWithoutID],
-    ):
-        self.services = services
-        self.graph_execution_state_id = graph_execution_state_id
-        self.queue_id = queue_id
-        self.queue_item_id = queue_item_id
-        self.queue_batch_id = queue_batch_id
-        self.workflow = workflow
-
-
 class BaseInvocationOutput(BaseModel):
     """
     Base class for all invocation outputs.
@@ -495,6 +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:
@@ -507,10 +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]:
@@ -559,6 +166,7 @@ class BaseInvocation(ABC, BaseModel):
     """
 
     _invocation_classes: ClassVar[set[BaseInvocation]] = set()
+    _typeadapter: ClassVar[Optional[TypeAdapter[Any]]] = None
 
     @classmethod
     def get_type(cls) -> str:
@@ -571,10 +179,14 @@ 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]:
@@ -632,7 +244,7 @@ class BaseInvocation(ABC, BaseModel):
         """Invoke with provided context and return outputs."""
         pass
 
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
+    def invoke_internal(self, context: InvocationContext, services: "InvocationServices") -> BaseInvocationOutput:
         """
         Internal invoke method, calls `invoke()` after some prep.
         Handles optional fields that are required to call `invoke()` and invocation cache.
@@ -657,23 +269,23 @@ class BaseInvocation(ABC, BaseModel):
                     raise MissingInputException(self.model_fields["type"].default, field_name)
 
         # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
+        if services.configuration.node_cache_size == 0:
             return self.invoke(context)
 
         output: BaseInvocationOutput
         if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
+            key = services.invocation_cache.create_key(self)
+            cached_value = services.invocation_cache.get(key)
             if cached_value is None:
-                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
                 output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
+                services.invocation_cache.save(key, output)
                 return output
             else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
+                services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
                 return cached_value
         else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
+            services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
             return self.invoke(context)
 
     id: str = Field(
@@ -714,9 +326,7 @@ RESERVED_NODE_ATTRIBUTE_FIELD_NAMES = {
     "workflow",
 }
 
-RESERVED_INPUT_FIELD_NAMES = {
-    "metadata",
-}
+RESERVED_INPUT_FIELD_NAMES = {"metadata", "board"}
 
 RESERVED_OUTPUT_FIELD_NAMES = {"type"}
 
@@ -926,37 +536,3 @@ def invocation_output(
         return cls
 
     return wrapper
-
-
-class MetadataField(RootModel):
-    """
-    Pydantic model for metadata with custom root of type dict[str, Any].
-    Metadata is stored without a strict schema.
-    """
-
-    root: dict[str, Any] = Field(description="The metadata")
-
-
-MetadataFieldValidator = TypeAdapter(MetadataField)
-
-
-class WithMetadata(BaseModel):
-    metadata: Optional[MetadataField] = Field(
-        default=None,
-        description=FieldDescriptions.metadata,
-        json_schema_extra=InputFieldJSONSchemaExtra(
-            field_kind=FieldKind.Internal,
-            input=Input.Connection,
-            orig_required=False,
-        ).model_dump(exclude_none=True),
-    )
-
-
-class WithWorkflow:
-    workflow = None
-
-    def __init_subclass__(cls) -> None:
-        logger.warn(
-            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
-        )
-        super().__init_subclass__()

invokeai/app/invocations/collections.py

@@ -5,9 +5,11 @@ import numpy as np
 from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(

invokeai/app/invocations/compel.py

@@ -1,40 +1,28 @@
-from dataclasses import dataclass
-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.primitives import ConditioningField, ConditioningOutput
-from invokeai.app.shared.fields import FieldDescriptions
+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,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    invocation,
-    invocation_output,
-)
-from .model import ClipField
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from .model import CLIPField
 
-
-@dataclass
-class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
-    # unconditioned: Optional[torch.Tensor]
+# unconditioned: Optional[torch.Tensor]
 
 
 # class ConditioningAlgo(str, Enum):
@@ -48,7 +36,7 @@ class ConditioningFieldData:
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -58,7 +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,
@@ -66,49 +54,27 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-            context=context,
-        )
+        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.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                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.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # 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.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=self.clip.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                print(f'Warn: trigger: "{trigger}" not found')
+        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,
             ),
@@ -116,8 +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,
@@ -128,7 +95,7 @@ class CompelInvocation(BaseInvocation):
 
             conjunction = Compel.parse_prompt_string(self.prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -149,45 +116,41 @@ class CompelInvocation(BaseInvocation):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 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.services.model_manager.get_model(
-            **clip_field.tokenizer.model_dump(),
-            context=context,
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.model_dump(),
-            context=context,
-        )
+    ) -> 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(
@@ -198,40 +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.services.model_manager.get_model(
-                    **lora.model_dump(exclude={"weight"}), context=context
-                )
-                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.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # 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.services.model_manager.get_model(
-                            model_name=name,
-                            base_model=clip_field.text_encoder.base_model,
-                            model_type=ModelType.TextualInversion,
-                            context=context,
-                        ).context.model,
-                    )
-                )
-            except ModelNotFoundException:
-                # print(e)
-                # import traceback
-                # print(traceback.format_exc())
-                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,
             ),
@@ -239,8 +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,
@@ -253,7 +199,7 @@ class SDXLPromptInvocationBase:
 
             conjunction = Compel.parse_prompt_string(prompt)
 
-            if context.services.configuration.log_tokenization:
+            if context.config.get().log_tokenization:
                 # TODO: better logging for and syntax
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
@@ -286,7 +232,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -307,8 +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:
@@ -357,6 +303,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                 dim=1,
             )
 
+        assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -368,14 +315,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @invocation(
@@ -383,7 +325,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     title="SDXL Refiner Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.0.0",
+    version="1.0.1",
 )
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -398,7 +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:
@@ -410,6 +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(
@@ -421,21 +364,16 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ]
         )
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-        context.services.latents.save(conditioning_name, conditioning_data)
+        conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
+        return ConditioningOutput.build(conditioning_name)
 
 
 @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(
@@ -445,23 +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
@@ -473,7 +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")
 
@@ -486,24 +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
@@ -543,7 +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

@@ -0,0 +1,17 @@
+from typing import Literal
+
+from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
+
+LATENT_SCALE_FACTOR = 8
+"""
+HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
+be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
+factor is hard-coded to a literal '8' rather than using this constant.
+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

@@ -17,33 +17,32 @@ from controlnet_aux import (
     MidasDetector,
     MLSDdetector,
     NormalBaeDetector,
-    OpenposeDetector,
     PidiNetDetector,
     SamDetector,
     ZoeDetector,
 )
 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.primitives import ImageField, ImageOutput
-from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
-
-from ...backend.model_management import BaseModelType
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
     Input,
     InputField,
-    InvocationContext,
     OutputField,
+    UIType,
+    WithBoard,
     WithMetadata,
-    invocation,
-    invocation_output,
 )
+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 .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
@@ -54,18 +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)"
@@ -101,7 +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"
     )
@@ -140,7 +132,7 @@ class ControlNetInvocation(BaseInvocation):
 
 
 # This invocation exists for other invocations to subclass it - do not register with @invocation!
-class ImageProcessorInvocation(BaseInvocation, WithMetadata):
+class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Base class for invocations that preprocess images for ControlNet"""
 
     image: ImageField = InputField(description="The image to process")
@@ -149,23 +141,18 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
         # 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.services.images.get_pil_image(self.image.image_name)
+        raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
-        image_dto = context.services.images.create(
-            image=processed_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.CONTROL,
-            session_id=context.graph_execution_state_id,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            metadata=self.metadata,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=processed_image)
 
         """Builds an ImageOutput and its ImageField"""
         processed_image_field = ImageField(image_name=image_dto.image_name)
@@ -184,7 +171,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata):
     title="Canny Processor",
     tags=["controlnet", "canny"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
@@ -196,6 +183,10 @@ 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)
@@ -207,7 +198,7 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
     title="HED (softedge) Processor",
     tags=["controlnet", "hed", "softedge"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
@@ -236,7 +227,7 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Processor",
     tags=["controlnet", "lineart"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
@@ -258,7 +249,7 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
     title="Lineart Anime Processor",
     tags=["controlnet", "lineart", "anime"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
@@ -276,37 +267,12 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.2.0",
-)
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
-    """Applies Openpose processing to image"""
-
-    hand_and_face: bool = InputField(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-
-    def run_processor(self, image):
-        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = openpose_processor(
-            image,
-            detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution,
-            hand_and_face=self.hand_and_face,
-        )
-        return processed_image
-
-
 @invocation(
     "midas_depth_image_processor",
     title="Midas Depth Processor",
     tags=["controlnet", "midas"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
@@ -333,7 +299,7 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Normal BAE Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
@@ -350,7 +316,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.0"
+    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.2.1"
 )
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
@@ -373,7 +339,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
 
 
 @invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.0"
+    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.2.1"
 )
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
@@ -400,7 +366,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     title="Content Shuffle Processor",
     tags=["controlnet", "contentshuffle"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
@@ -430,7 +396,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     title="Zoe (Depth) Processor",
     tags=["controlnet", "zoe", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
@@ -446,7 +412,7 @@ class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     title="Mediapipe Face Processor",
     tags=["controlnet", "mediapipe", "face"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
@@ -455,10 +421,6 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
 
     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)
         return processed_image
@@ -469,7 +431,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     title="Leres (Depth) Processor",
     tags=["controlnet", "leres", "depth"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
@@ -498,7 +460,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     title="Tile Resample Processor",
     tags=["controlnet", "tile"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
@@ -538,7 +500,7 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     title="Segment Anything Processor",
     tags=["controlnet", "segmentanything"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
@@ -580,7 +542,7 @@ class SamDetectorReproducibleColors(SamDetector):
     title="Color Map Processor",
     tags=["controlnet"],
     category="controlnet",
-    version="1.2.0",
+    version="1.2.1",
 )
 class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a color map from the provided image"""
@@ -588,7 +550,6 @@ 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]
 
@@ -613,7 +574,7 @@ 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"""
@@ -622,14 +583,37 @@ 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):
+    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
+
+
+@invocation(
+    "dw_openpose_image_processor",
+    title="DW Openpose Image Processor",
+    tags=["controlnet", "dwpose", "openpose"],
+    category="controlnet",
+    version="1.0.0",
+)
+class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
+    """Generates an openpose pose from an image using DWPose"""
+
+    draw_body: bool = InputField(default=True)
+    draw_face: bool = InputField(default=False)
+    draw_hands: bool = InputField(default=False)
+    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+
+    def run_processor(self, image: Image.Image):
+        dw_openpose = DWOpenposeDetector()
+        processed_image = dw_openpose(
+            image,
+            draw_face=self.draw_face,
+            draw_hands=self.draw_hands,
+            draw_body=self.draw_body,
+            resolution=self.image_resolution,
+        )
         return processed_image

invokeai/app/invocations/cv.py

@@ -5,22 +5,24 @@ import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.0")
-class CvInpaintInvocation(BaseInvocation, WithMetadata):
+@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.2.1")
+class CvInpaintInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Simple inpaint using opencv."""
 
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        mask = context.services.images.get_pil_image(self.mask.image_name)
+        image = context.images.get_pil(self.image.image_name)
+        mask = context.images.get_pil(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
@@ -34,18 +36,6 @@ class CvInpaintInvocation(BaseInvocation, WithMetadata):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_dto = context.services.images.create(
-            image=image_inpainted,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=image_inpainted)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/facetools.py

@@ -13,15 +13,13 @@ from pydantic import field_validator
 import invokeai.assets.fonts as font_assets
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.image_records.image_records_common import ImageCategory
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 @invocation_output("face_mask_output")
@@ -306,37 +304,37 @@ def extract_face(
 
     # Adjust the crop boundaries to stay within the original image's dimensions
     if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -X-axis padding reached image edge.")
         x_max -= x_min
         x_min = 0
     elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +X-axis padding reached image edge.")
         x_min -= x_max - mask.width
         x_max = mask.width
 
     if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
         y_max -= y_min
         y_min = 0
     elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
+        context.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
         y_min -= y_max - mask.height
         y_max = mask.height
 
     # Ensure the crop is square and adjust the boundaries if needed
     if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
         diff = crop_size - (x_max - x_min)
         x_min -= diff // 2
         x_max += diff - diff // 2
 
     if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
+        context.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
         diff = crop_size - (y_max - y_min)
         y_min -= diff // 2
         y_max += diff - diff // 2
 
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
+    context.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
 
     # Crop the output image to the specified size with the center of the face mesh as the center.
     mask = mask.crop((x_min, y_min, x_max, y_max))
@@ -368,7 +366,7 @@ def get_faces_list(
 
     # Generate the face box mask and get the center of the face.
     if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
+        context.logger.info("FaceTools --> Attempting full image face detection.")
         result = generate_face_box_mask(
             context=context,
             minimum_confidence=minimum_confidence,
@@ -380,7 +378,7 @@ def get_faces_list(
             draw_mesh=draw_mesh,
         )
     if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
+        context.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
         width, height = image.size
         image_chunks = []
         x_offsets = []
@@ -399,7 +397,7 @@ def get_faces_list(
                 x_offsets.append(x)
                 y_offsets.append(0)
                 fx += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
+                context.logger.info(f"FaceTools --> Chunk starting at x = {x}")
         elif height > width:
             # Portrait - slice the image vertically
             fy = 0.0
@@ -411,10 +409,10 @@ def get_faces_list(
                 x_offsets.append(0)
                 y_offsets.append(y)
                 fy += increment
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
+                context.logger.info(f"FaceTools --> Chunk starting at y = {y}")
 
         for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
+            context.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
             result = result + generate_face_box_mask(
                 context=context,
                 minimum_confidence=minimum_confidence,
@@ -428,7 +426,7 @@ def get_faces_list(
 
         if len(result) == 0:
             # Give up
-            context.services.logger.warning(
+            context.logger.warning(
                 "FaceTools --> No face detected in chunked input image. Passing through original image."
             )
 
@@ -437,7 +435,7 @@ def get_faces_list(
     return all_faces
 
 
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.2.1")
 class FaceOffInvocation(BaseInvocation, WithMetadata):
     """Bound, extract, and mask a face from an image using MediaPipe detection"""
 
@@ -470,11 +468,11 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         )
 
         if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
+            context.logger.warning("FaceOff --> No faces detected. Passing through original image.")
             return None
 
         if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
+            context.logger.warning(
                 f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
             )
             return None
@@ -486,7 +484,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return face_data
 
     def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.faceoff(context=context, image=image)
 
         if result is None:
@@ -500,24 +498,9 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
             x = result["x_min"]
             y = result["y_min"]
 
-        image_dto = context.services.images.create(
-            image=result_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,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result_mask, image_category=ImageCategory.MASK)
 
         output = FaceOffOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -531,7 +514,7 @@ class FaceOffInvocation(BaseInvocation, WithMetadata):
         return output
 
 
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.0")
+@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.2.1")
 class FaceMaskInvocation(BaseInvocation, WithMetadata):
     """Face mask creation using mediapipe face detection"""
 
@@ -580,7 +563,7 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
             if len(intersected_face_ids) == 0:
                 id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
+                context.logger.warning(
                     f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
                 )
                 return FaceMaskResult(
@@ -616,27 +599,12 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
         )
 
     def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result = self.facemask(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result["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,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result["image"])
 
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
+        mask_dto = context.images.save(image=result["mask"], image_category=ImageCategory.MASK)
 
         output = FaceMaskOutput(
             image=ImageField(image_name=image_dto.image_name),
@@ -649,9 +617,9 @@ class FaceMaskInvocation(BaseInvocation, WithMetadata):
 
 
 @invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.0"
+    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.2.1"
 )
-class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
+class FaceIdentifierInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
 
     image: ImageField = InputField(description="Image to face detect")
@@ -705,21 +673,9 @@ class FaceIdentifierInvocation(BaseInvocation, WithMetadata):
         return image
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
         result_image = self.faceidentifier(context=context, image=image)
 
-        image_dto = context.services.images.create(
-            image=result_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,
-            workflow=context.workflow,
-        )
+        image_dto = context.images.save(image=result_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/fields.py

@@ -0,0 +1,567 @@
+from enum import Enum
+from typing import Any, Callable, Optional, Tuple
+
+from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter
+from pydantic.fields import _Unset
+from pydantic_core import PydanticUndefined
+
+from invokeai.app.util.metaenum import MetaEnum
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.get_logger()
+
+
+class UIType(str, Enum, metaclass=MetaEnum):
+    """
+    Type hints for the UI for situations in which the field type is not enough to infer the correct UI type.
+
+    - Model Fields
+    The most common node-author-facing use will be for model fields. Internally, there is no difference
+    between SD-1, SD-2 and SDXL model fields - they all use the class `MainModelField`. To ensure the
+    base-model-specific UI is rendered, use e.g. `ui_type=UIType.SDXLMainModelField` to indicate that
+    the field is an SDXL main model field.
+
+    - Any Field
+    We cannot infer the usage of `typing.Any` via schema parsing, so you *must* use `ui_type=UIType.Any` to
+    indicate that the field accepts any type. Use with caution. This cannot be used on outputs.
+
+    - Scheduler Field
+    Special handling in the UI is needed for this field, which otherwise would be parsed as a plain enum field.
+
+    - Internal Fields
+    Similar to the Any Field, the `collect` and `iterate` nodes make use of `typing.Any`. To facilitate
+    handling these types in the client, we use `UIType._Collection` and `UIType._CollectionItem`. These
+    should not be used by node authors.
+
+    - DEPRECATED Fields
+    These types are deprecated and should not be used by node authors. A warning will be logged if one is
+    used, and the type will be ignored. They are included here for backwards compatibility.
+    """
+
+    # region Model Field Types
+    MainModel = "MainModelField"
+    SDXLMainModel = "SDXLMainModelField"
+    SDXLRefinerModel = "SDXLRefinerModelField"
+    ONNXModel = "ONNXModelField"
+    VAEModel = "VAEModelField"
+    LoRAModel = "LoRAModelField"
+    ControlNetModel = "ControlNetModelField"
+    IPAdapterModel = "IPAdapterModelField"
+    T2IAdapterModel = "T2IAdapterModelField"
+    # endregion
+
+    # region Misc Field Types
+    Scheduler = "SchedulerField"
+    Any = "AnyField"
+    # endregion
+
+    # region Internal Field Types
+    _Collection = "CollectionField"
+    _CollectionItem = "CollectionItemField"
+    # endregion
+
+    # region DEPRECATED
+    Boolean = "DEPRECATED_Boolean"
+    Color = "DEPRECATED_Color"
+    Conditioning = "DEPRECATED_Conditioning"
+    Control = "DEPRECATED_Control"
+    Float = "DEPRECATED_Float"
+    Image = "DEPRECATED_Image"
+    Integer = "DEPRECATED_Integer"
+    Latents = "DEPRECATED_Latents"
+    String = "DEPRECATED_String"
+    BooleanCollection = "DEPRECATED_BooleanCollection"
+    ColorCollection = "DEPRECATED_ColorCollection"
+    ConditioningCollection = "DEPRECATED_ConditioningCollection"
+    ControlCollection = "DEPRECATED_ControlCollection"
+    FloatCollection = "DEPRECATED_FloatCollection"
+    ImageCollection = "DEPRECATED_ImageCollection"
+    IntegerCollection = "DEPRECATED_IntegerCollection"
+    LatentsCollection = "DEPRECATED_LatentsCollection"
+    StringCollection = "DEPRECATED_StringCollection"
+    BooleanPolymorphic = "DEPRECATED_BooleanPolymorphic"
+    ColorPolymorphic = "DEPRECATED_ColorPolymorphic"
+    ConditioningPolymorphic = "DEPRECATED_ConditioningPolymorphic"
+    ControlPolymorphic = "DEPRECATED_ControlPolymorphic"
+    FloatPolymorphic = "DEPRECATED_FloatPolymorphic"
+    ImagePolymorphic = "DEPRECATED_ImagePolymorphic"
+    IntegerPolymorphic = "DEPRECATED_IntegerPolymorphic"
+    LatentsPolymorphic = "DEPRECATED_LatentsPolymorphic"
+    StringPolymorphic = "DEPRECATED_StringPolymorphic"
+    UNet = "DEPRECATED_UNet"
+    Vae = "DEPRECATED_Vae"
+    CLIP = "DEPRECATED_CLIP"
+    Collection = "DEPRECATED_Collection"
+    CollectionItem = "DEPRECATED_CollectionItem"
+    Enum = "DEPRECATED_Enum"
+    WorkflowField = "DEPRECATED_WorkflowField"
+    IsIntermediate = "DEPRECATED_IsIntermediate"
+    BoardField = "DEPRECATED_BoardField"
+    MetadataItem = "DEPRECATED_MetadataItem"
+    MetadataItemCollection = "DEPRECATED_MetadataItemCollection"
+    MetadataItemPolymorphic = "DEPRECATED_MetadataItemPolymorphic"
+    MetadataDict = "DEPRECATED_MetadataDict"
+
+
+class UIComponent(str, Enum, metaclass=MetaEnum):
+    """
+    The type of UI component to use for a field, used to override the default components, which are
+    inferred from the field type.
+    """
+
+    None_ = "none"
+    Textarea = "textarea"
+    Slider = "slider"
+
+
+class FieldDescriptions:
+    denoising_start = "When to start denoising, expressed a percentage of total steps"
+    denoising_end = "When to stop denoising, expressed a percentage of total steps"
+    cfg_scale = "Classifier-Free Guidance scale"
+    cfg_rescale_multiplier = "Rescale multiplier for CFG guidance, used for models trained with zero-terminal SNR"
+    scheduler = "Scheduler to use during inference"
+    positive_cond = "Positive conditioning tensor"
+    negative_cond = "Negative conditioning tensor"
+    noise = "Noise tensor"
+    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    unet = "UNet (scheduler, LoRAs)"
+    vae = "VAE"
+    cond = "Conditioning tensor"
+    controlnet_model = "ControlNet model to load"
+    vae_model = "VAE model to load"
+    lora_model = "LoRA model to load"
+    main_model = "Main model (UNet, VAE, CLIP) to load"
+    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
+    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
+    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
+    lora_weight = "The weight at which the LoRA is applied to each model"
+    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
+    raw_prompt = "Raw prompt text (no parsing)"
+    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
+    skipped_layers = "Number of layers to skip in text encoder"
+    seed = "Seed for random number generation"
+    steps = "Number of steps to run"
+    width = "Width of output (px)"
+    height = "Height of output (px)"
+    control = "ControlNet(s) to apply"
+    ip_adapter = "IP-Adapter to apply"
+    t2i_adapter = "T2I-Adapter(s) to apply"
+    denoised_latents = "Denoised latents tensor"
+    latents = "Latents tensor"
+    strength = "Strength of denoising (proportional to steps)"
+    metadata = "Optional metadata to be saved with the image"
+    metadata_collection = "Collection of Metadata"
+    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
+    metadata_item_label = "Label for this metadata item"
+    metadata_item_value = "The value for this metadata item (may be any type)"
+    workflow = "Optional workflow to be saved with the image"
+    interp_mode = "Interpolation mode"
+    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
+    fp32 = "Whether or not to use full float32 precision"
+    precision = "Precision to use"
+    tiled = "Processing using overlapping tiles (reduce memory consumption)"
+    detect_res = "Pixel resolution for detection"
+    image_res = "Pixel resolution for output image"
+    safe_mode = "Whether or not to use safe mode"
+    scribble_mode = "Whether or not to use scribble mode"
+    scale_factor = "The factor by which to scale"
+    blend_alpha = (
+        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
+    )
+    num_1 = "The first number"
+    num_2 = "The second number"
+    mask = "The mask to use for the operation"
+    board = "The board to save the image to"
+    image = "The image to process"
+    tile_size = "Tile size"
+    inclusive_low = "The inclusive low value"
+    exclusive_high = "The exclusive high value"
+    decimal_places = "The number of decimal places to round to"
+    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
+    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
+    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
+
+
+class ImageField(BaseModel):
+    """An image primitive field"""
+
+    image_name: str = Field(description="The name of the image")
+
+
+class BoardField(BaseModel):
+    """A board primitive field"""
+
+    board_id: str = Field(description="The id of the board")
+
+
+class DenoiseMaskField(BaseModel):
+    """An inpaint mask field"""
+
+    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):
+    """A latents tensor primitive field"""
+
+    latents_name: str = Field(description="The name of the latents")
+    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
+
+
+class ColorField(BaseModel):
+    """A color primitive field"""
+
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+    # endregion
+
+
+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.
+    """
+
+    root: dict[str, Any] = Field(description="The metadata")
+
+
+MetadataFieldValidator = TypeAdapter(MetadataField)
+
+
+class Input(str, Enum, metaclass=MetaEnum):
+    """
+    The type of input a field accepts.
+    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
+      are instantiated.
+    - `Input.Connection`: The field must have its value provided by a connection.
+    - `Input.Any`: The field may have its value provided either directly or by a connection.
+    """
+
+    Connection = "connection"
+    Direct = "direct"
+    Any = "any"
+
+
+class FieldKind(str, Enum, metaclass=MetaEnum):
+    """
+    The kind of field.
+    - `Input`: An input field on a node.
+    - `Output`: An output field on a node.
+    - `Internal`: A field which is treated as an input, but cannot be used in node definitions. Metadata is
+    one example. It is provided to nodes via the WithMetadata class, and we want to reserve the field name
+    "metadata" for this on all nodes. `FieldKind` is used to short-circuit the field name validation logic,
+    allowing "metadata" for that field.
+    - `NodeAttribute`: The field is a node attribute. These are fields which are not inputs or outputs,
+    but which are used to store information about the node. For example, the `id` and `type` fields are node
+    attributes.
+
+    The presence of this in `json_schema_extra["field_kind"]` is used when initializing node schemas on app
+    startup, and when generating the OpenAPI schema for the workflow editor.
+    """
+
+    Input = "input"
+    Output = "output"
+    Internal = "internal"
+    NodeAttribute = "node_attribute"
+
+
+class InputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used during graph execution,
+    and by the workflow editor during schema parsing and UI rendering.
+    """
+
+    input: Input
+    orig_required: bool
+    field_kind: FieldKind
+    default: Optional[Any] = None
+    orig_default: Optional[Any] = None
+    ui_hidden: bool = False
+    ui_type: Optional[UIType] = None
+    ui_component: Optional[UIComponent] = None
+    ui_order: Optional[int] = None
+    ui_choice_labels: Optional[dict[str, str]] = None
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+class WithMetadata(BaseModel):
+    """
+    Inherit from this class if your node needs a metadata input field.
+    """
+
+    metadata: Optional[MetadataField] = Field(
+        default=None,
+        description=FieldDescriptions.metadata,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Connection,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class WithWorkflow:
+    workflow = None
+
+    def __init_subclass__(cls) -> None:
+        logger.warn(
+            f"{cls.__module__.split('.')[0]}.{cls.__name__}: WithWorkflow is deprecated. Use `context.workflow` to access the workflow."
+        )
+        super().__init_subclass__()
+
+
+class WithBoard(BaseModel):
+    """
+    Inherit from this class if your node needs a board input field.
+    """
+
+    board: Optional[BoardField] = Field(
+        default=None,
+        description=FieldDescriptions.board,
+        json_schema_extra=InputFieldJSONSchemaExtra(
+            field_kind=FieldKind.Internal,
+            input=Input.Direct,
+            orig_required=False,
+        ).model_dump(exclude_none=True),
+    )
+
+
+class OutputFieldJSONSchemaExtra(BaseModel):
+    """
+    Extra attributes to be added to input fields and their OpenAPI schema. Used by the workflow editor
+    during schema parsing and UI rendering.
+    """
+
+    field_kind: FieldKind
+    ui_hidden: bool
+    ui_type: Optional[UIType]
+    ui_order: Optional[int]
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        json_schema_serialization_defaults_required=True,
+    )
+
+
+def InputField(
+    # copied from pydantic's Field
+    # TODO: Can we support default_factory?
+    default: Any = _Unset,
+    default_factory: Callable[[], Any] | None = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    input: Input = Input.Any,
+    ui_type: Optional[UIType] = None,
+    ui_component: Optional[UIComponent] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+    ui_choice_labels: Optional[dict[str, str]] = None,
+) -> Any:
+    """
+    Creates an input field for an invocation.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/latest/api/fields/#pydantic.fields.Field) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param Input input: [Input.Any] The kind of input this field requires. \
+      `Input.Direct` means a value must be provided on instantiation. \
+      `Input.Connection` means the value must be provided by a connection. \
+      `Input.Any` means either will do.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
+      The UI will always render a suitable component, but sometimes you want something different than the default. \
+      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
+      For this case, you could provide `UIComponent.Textarea`.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI.
+
+    :param dict[str, str] ui_choice_labels: [None] Specifies the labels to use for the choices in an enum field.
+    """
+
+    json_schema_extra_ = InputFieldJSONSchemaExtra(
+        input=input,
+        ui_type=ui_type,
+        ui_component=ui_component,
+        ui_hidden=ui_hidden,
+        ui_order=ui_order,
+        ui_choice_labels=ui_choice_labels,
+        field_kind=FieldKind.Input,
+        orig_required=True,
+    )
+
+    """
+    There is a conflict between the typing of invocation definitions and the typing of an invocation's
+    `invoke()` function.
+
+    On instantiation of a node, the invocation definition is used to create the python class. At this time,
+    any number of fields may be optional, because they may be provided by connections.
+
+    On calling of `invoke()`, however, those fields may be required.
+
+    For example, consider an ResizeImageInvocation with an `image: ImageField` field.
+
+    `image` is required during the call to `invoke()`, but when the python class is instantiated,
+    the field may not be present. This is fine, because that image field will be provided by a
+    connection from an ancestor node, which outputs an image.
+
+    This means we want to type the `image` field as optional for the node class definition, but required
+    for the `invoke()` function.
+
+    If we use `typing.Optional` in the node class definition, the field will be typed as optional in the
+    `invoke()` method, and we'll have to do a lot of runtime checks to ensure the field is present - or
+    any static type analysis tools will complain.
+
+    To get around this, in node class definitions, we type all fields correctly for the `invoke()` function,
+    but secretly make them optional in `InputField()`. We also store the original required bool and/or default
+    value. When we call `invoke()`, we use this stored information to do an additional check on the class.
+    """
+
+    if default_factory is not _Unset and default_factory is not None:
+        default = default_factory()
+        logger.warn('"default_factory" is not supported, calling it now to set "default"')
+
+    # These are the args we may wish pass to the pydantic `Field()` function
+    field_args = {
+        "default": default,
+        "title": title,
+        "description": description,
+        "pattern": pattern,
+        "strict": strict,
+        "gt": gt,
+        "ge": ge,
+        "lt": lt,
+        "le": le,
+        "multiple_of": multiple_of,
+        "allow_inf_nan": allow_inf_nan,
+        "max_digits": max_digits,
+        "decimal_places": decimal_places,
+        "min_length": min_length,
+        "max_length": max_length,
+    }
+
+    # We only want to pass the args that were provided, otherwise the `Field()`` function won't work as expected
+    provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
+
+    # Because we are manually making fields optional, we need to store the original required bool for reference later
+    json_schema_extra_.orig_required = default is PydanticUndefined
+
+    # Make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
+    if input is Input.Any or input is Input.Connection:
+        default_ = None if default is PydanticUndefined else default
+        provided_args.update({"default": default_})
+        if default is not PydanticUndefined:
+            # Before invoking, we'll check for the original default value and set it on the field if the field has no value
+            json_schema_extra_.default = default
+            json_schema_extra_.orig_default = default
+    elif default is not PydanticUndefined:
+        default_ = default
+        provided_args.update({"default": default_})
+        json_schema_extra_.orig_default = default_
+
+    return Field(
+        **provided_args,
+        json_schema_extra=json_schema_extra_.model_dump(exclude_none=True),
+    )
+
+
+def OutputField(
+    # copied from pydantic's Field
+    default: Any = _Unset,
+    title: str | None = _Unset,
+    description: str | None = _Unset,
+    pattern: str | None = _Unset,
+    strict: bool | None = _Unset,
+    gt: float | None = _Unset,
+    ge: float | None = _Unset,
+    lt: float | None = _Unset,
+    le: float | None = _Unset,
+    multiple_of: float | None = _Unset,
+    allow_inf_nan: bool | None = _Unset,
+    max_digits: int | None = _Unset,
+    decimal_places: int | None = _Unset,
+    min_length: int | None = _Unset,
+    max_length: int | None = _Unset,
+    # custom
+    ui_type: Optional[UIType] = None,
+    ui_hidden: bool = False,
+    ui_order: Optional[int] = None,
+) -> Any:
+    """
+    Creates an output field for an invocation output.
+
+    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
+    that adds a few extra parameters to support graph execution and the node editor UI.
+
+    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
+      In some situations, the field's type is not enough to infer the correct UI type. \
+      For example, model selection fields should render a dropdown UI component to select a model. \
+      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
+      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
+      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
+
+    :param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
+
+    :param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
+    """
+    return Field(
+        default=default,
+        title=title,
+        description=description,
+        pattern=pattern,
+        strict=strict,
+        gt=gt,
+        ge=ge,
+        lt=lt,
+        le=le,
+        multiple_of=multiple_of,
+        allow_inf_nan=allow_inf_nan,
+        max_digits=max_digits,
+        decimal_places=decimal_places,
+        min_length=min_length,
+        max_length=max_length,
+        json_schema_extra=OutputFieldJSONSchemaExtra(
+            ui_type=ui_type,
+            ui_hidden=ui_hidden,
+            ui_order=ui_order,
+            field_kind=FieldKind.Output,
+        ).model_dump(exclude_none=True),
+    )

invokeai/app/invocations/infill.py

@@ -6,14 +6,16 @@ from typing import Literal, Optional, get_args
 import numpy as np
 from PIL import Image, ImageOps
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ColorField, ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
 from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
 
 
@@ -118,8 +120,8 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
     return si
 
 
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class InfillColorInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class InfillColorInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with a solid color"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -129,33 +131,20 @@ class InfillColorInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
 
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            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,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
-class InfillTileInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.2")
+class InfillTileInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image with tiles of the image"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -168,33 +157,20 @@ class InfillTileInvocation(BaseInvocation, WithMetadata):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
         infilled.paste(image, (0, 0), image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            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,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 @invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0"
+    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1"
 )
-class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
+class InfillPatchMatchInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
     image: ImageField = InputField(description="The image to infill")
@@ -202,7 +178,7 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
+        image = context.images.get_pil(self.image.image_name).convert("RGBA")
 
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
@@ -227,77 +203,38 @@ class InfillPatchMatchInvocation(BaseInvocation, WithMetadata):
         infilled.paste(image, (0, 0), mask=image.split()[-1])
         # image.paste(infilled, (0, 0), mask=image.split()[-1])
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            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,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class LaMaInfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class LaMaInfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using the LaMa model"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_lama(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            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,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.0")
-class CV2InfillInvocation(BaseInvocation, WithMetadata):
+@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.2.1")
+class CV2InfillInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
     image: ImageField = InputField(description="The image to infill")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         infilled = infill_cv2(image.copy())
 
-        image_dto = context.services.images.create(
-            image=infilled,
-            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,
-        )
+        image_dto = context.images.save(image=infilled)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/ip_adapter.py

@@ -1,44 +1,27 @@
-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,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
+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.shared.fields import FieldDescriptions
-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.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.model_manager.config import 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)"
@@ -49,12 +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
 
@@ -65,14 +48,18 @@ class IPAdapterOutput(BaseInvocationOutput):
     ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.1")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.2")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
     # 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(
@@ -87,38 +74,30 @@ 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.services.model_manager.model_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
-        )
+        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_models = context.models.search_by_attrs(
+            name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
         )
+        assert len(image_encoder_models) == 1
         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_models[0]),
                 weight=self.weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,

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 (
@@ -18,34 +20,45 @@ 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 (
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIType,
+    WithBoard,
+    WithMetadata,
+)
 from invokeai.app.invocations.ip_adapter import IPAdapterField
 from invokeai.app.invocations.primitives import (
-    DenoiseMaskField,
     DenoiseMaskOutput,
-    ImageField,
     ImageOutput,
-    LatentsField,
     LatentsOutput,
-    build_latents_output,
 )
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import prepare_control_image
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
-from invokeai.backend.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,
@@ -53,42 +66,26 @@ 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 (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from .compel import ConditioningField
 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
 
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
-SAMPLER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
-
-# HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
-# be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
-# factor is hard-coded to a literal '8' rather than using this constant.
-# The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
-LATENT_SCALE_FACTOR = 8
-
 
 @invocation_output("scheduler_output")
 class SchedulerOutput(BaseInvocationOutput):
-    scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
+    scheduler: SCHEDULER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
 
 
 @invocation(
@@ -101,7 +98,7 @@ class SchedulerOutput(BaseInvocationOutput):
 class SchedulerInvocation(BaseInvocation):
     """Selects a scheduler."""
 
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -116,12 +113,12 @@ class SchedulerInvocation(BaseInvocation):
     title="Create Denoise Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 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)
@@ -131,10 +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:
@@ -144,55 +141,115 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
         if self.image is not None:
-            image = context.services.images.get_pil_image(self.image.image_name)
-            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image.dim() == 3:
-                image = image.unsqueeze(0)
+            image = context.images.get_pil(self.image.image_name)
+            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image_tensor.dim() == 3:
+                image_tensor = image_tensor.unsqueeze(0)
         else:
-            image = None
+            image_tensor = None
 
         mask = self.prep_mask_tensor(
-            context.services.images.get_pil_image(self.mask.image_name),
+            context.images.get_pil(self.mask.image_name),
         )
 
-        if image is not None:
-            vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.model_dump(),
-                context=context,
-            )
+        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())
 
-            masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
-            context.services.latents.save(masked_latents_name, masked_latents)
+            masked_latents_name = context.tensors.save(tensor=masked_latents)
         else:
             masked_latents_name = None
 
-        mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
-        context.services.latents.save(mask_name, mask)
+        mask_name = context.tensors.save(tensor=mask)
 
-        return DenoiseMaskOutput(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name,
-                masked_latents_name=masked_latents_name,
-            ),
+        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.services.model_manager.get_model(
-        **scheduler_info.model_dump(),
-        context=context,
-    )
+    orig_scheduler_info = context.models.load(scheduler_info)
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -200,7 +257,7 @@ def get_scheduler(
         scheduler_config = scheduler_config["_backup"]
     scheduler_config = {
         **scheduler_config,
-        **scheduler_extra_config,
+        **scheduler_extra_config,  # FIXME
         "_backup": scheduler_config,
     }
 
@@ -213,6 +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
 
 
@@ -221,7 +279,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.5.1",
+    version="1.5.2",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -249,7 +307,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    scheduler: SAMPLER_NAME_VALUES = InputField(
+    scheduler: SCHEDULER_NAME_VALUES = InputField(
         default="euler",
         description=FieldDescriptions.scheduler,
         ui_type=UIType.Scheduler,
@@ -296,7 +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:
@@ -307,34 +365,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self,
-        context: InvocationContext,
-        source_node_id: str,
-        intermediate_state: PipelineIntermediateState,
-        base_model: BaseModelType,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.model_dump(),
-            source_node_id=source_node_id,
-            base_model=base_model,
-        )
-
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler,
-        unet,
-        seed,
+        scheduler: Scheduler,
+        unet: UNet2DConditionModel,
+        seed: int,
     ) -> ConditioningData:
-        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        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.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
         uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
 
         conditioning_data = ConditioningData(
@@ -342,16 +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
@@ -363,8 +397,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
     def create_pipeline(
         self,
-        unet,
-        scheduler,
+        unet: UNet2DConditionModel,
+        scheduler: Scheduler,
     ) -> StableDiffusionGeneratorPipeline:
         # TODO:
         # configure_model_padding(
@@ -375,10 +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(
@@ -395,11 +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
@@ -421,18 +455,11 @@ 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.services.model_manager.get_model(
-                    model_name=control_info.control_model.model_name,
-                    model_type=ModelType.ControlNet,
-                    base_model=control_info.control_model.base_model,
-                    context=context,
-                )
-            )
+            control_model = exit_stack.enter_context(context.models.load(control_info.control_model))
 
             # control_models.append(control_model)
             control_image_field = control_info.image
-            input_image = context.services.images.get_pil_image(control_image_field.image_name)
+            input_image = context.images.get_pil(control_image_field.image_name)
             # self.image.image_type, self.image.image_name
             # FIXME: still need to test with different widths, heights, devices, dtypes
             #        and add in batch_size, num_images_per_prompt?
@@ -490,31 +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.services.model_manager.get_model(
-                    model_name=single_ip_adapter.ip_adapter_model.model_name,
-                    model_type=ModelType.IPAdapter,
-                    base_model=single_ip_adapter.ip_adapter_model.base_model,
-                    context=context,
-                )
-            )
-
-            image_encoder_model_info = context.services.model_manager.get_model(
-                model_name=single_ip_adapter.image_encoder_model.model_name,
-                model_type=ModelType.CLIPVision,
-                base_model=single_ip_adapter.image_encoder_model.base_model,
-                context=context,
+                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.services.images.get_pil_image(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
@@ -554,26 +571,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
-            t2i_adapter_model_info = context.services.model_manager.get_model(
-                model_name=t2i_adapter_field.t2i_adapter_model.model_name,
-                model_type=ModelType.T2IAdapter,
-                base_model=t2i_adapter_field.t2i_adapter_model.base_model,
-                context=context,
-            )
-            image = context.services.images.get_pil_image(t2i_adapter_field.image.image_name)
+            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.
@@ -593,7 +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,
@@ -618,7 +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)
@@ -630,11 +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
@@ -647,18 +666,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context, 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.services.latents.get(self.denoise_mask.mask_name)
+        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.services.latents.get(self.denoise_mask.masked_latents_name)
+            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:
@@ -666,11 +687,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
             seed = None
             noise = None
             if self.noise is not None:
-                noise = context.services.latents.get(self.noise.latents_name)
+                noise = context.tensors.load(self.noise.latents_name)
                 seed = self.noise.seed
 
             if self.latents is not None:
-                latents = context.services.latents.get(self.latents.latents_name)
+                latents = context.tensors.load(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
 
@@ -685,7 +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.
@@ -696,35 +717,31 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 do_classifier_free_guidance=True,
             )
 
-            # Get the source node id (we are invoking the prepared node)
-            graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-            source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+            # get the unet's config so that we can pass the base to dispatch_progress()
+            unet_config = context.models.get_config(self.unet.unet.key)
 
-            def step_callback(state: PipelineIntermediateState):
-                self.dispatch_progress(context, source_node_id, state, self.unet.unet.base_model)
+            def step_callback(state: PipelineIntermediateState) -> None:
+                context.util.sd_step_callback(state, unet_config.base)
 
-            def _lora_loader():
+            def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
                 for lora in self.unet.loras:
-                    lora_info = context.services.model_manager.get_model(
-                        **lora.model_dump(exclude={"weight"}),
-                        context=context,
-                    )
-                    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.services.model_manager.get_model(
-                **self.unet.unet.model_dump(),
-                context=context,
-            )
+            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)
@@ -767,10 +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,
@@ -778,6 +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,
@@ -792,9 +807,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
             if choose_torch_device() == torch.device("mps"):
                 mps.empty_cache()
 
-            name = f"{context.graph_execution_state_id}__{self.id}"
-            context.services.latents.save(name, result_latents)
-        return build_latents_output(latents_name=name, latents=result_latents, seed=seed)
+            name = context.tensors.save(tensor=result_latents)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
 
 
 @invocation(
@@ -802,16 +816,16 @@ class DenoiseLatentsInvocation(BaseInvocation):
     title="Latents to Image",
     tags=["latents", "image", "vae", "l2i"],
     category="latents",
-    version="1.2.0",
+    version="1.2.1",
 )
-class LatentsToImageInvocation(BaseInvocation, WithMetadata):
+class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Generates an image from latents."""
 
     latents: LatentsField = InputField(
         description=FieldDescriptions.latents,
         input=Input.Connection,
     )
-    vae: VaeField = InputField(
+    vae: VAEField = InputField(
         description=FieldDescriptions.vae,
         input=Input.Connection,
     )
@@ -820,19 +834,17 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
-
-        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,
@@ -854,7 +866,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
                 vae.to(dtype=torch.float16)
                 latents = latents.half()
 
-            if self.tiled or context.services.configuration.tiled_decode:
+            if self.tiled or context.config.get().tiled_decode:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -878,22 +890,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        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,
-        )
+        image_dto = context.images.save(image=image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)
 
 
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
@@ -904,7 +903,7 @@ LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic",
     title="Resize Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
@@ -927,7 +926,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -945,10 +944,8 @@ class ResizeLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -956,7 +953,7 @@ class ResizeLatentsInvocation(BaseInvocation):
     title="Scale Latents",
     tags=["latents", "resize"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
@@ -970,7 +967,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     antialias: bool = InputField(default=False, description=FieldDescriptions.torch_antialias)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         # TODO:
         device = choose_torch_device()
@@ -989,10 +986,8 @@ class ScaleLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, resized_latents)
-        return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
+        name = context.tensors.save(tensor=resized_latents)
+        return LatentsOutput.build(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
 @invocation(
@@ -1000,7 +995,7 @@ class ScaleLatentsInvocation(BaseInvocation):
     title="Image to Latents",
     tags=["latents", "image", "vae", "i2l"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
@@ -1008,7 +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,
     )
@@ -1016,13 +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,
@@ -1061,12 +1057,9 @@ class ImageToLatentsInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-            context=context,
-        )
+        vae_info = context.models.load(self.vae.vae)
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
         if image_tensor.dim() == 3:
@@ -1074,22 +1067,26 @@ class ImageToLatentsInvocation(BaseInvocation):
 
         latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
         latents = latents.to("cpu")
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=latents, seed=None)
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
     @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(
@@ -1097,7 +1094,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     title="Blend Latents",
     tags=["latents", "blend"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 class BlendLatentsInvocation(BaseInvocation):
     """Blend two latents using a given alpha. Latents must have same size."""
@@ -1113,8 +1110,8 @@ class BlendLatentsInvocation(BaseInvocation):
     alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents_a = context.services.latents.get(self.latents_a.latents_name)
-        latents_b = context.services.latents.get(self.latents_b.latents_name)
+        latents_a = context.tensors.load(self.latents_a.latents_name)
+        latents_b = context.tensors.load(self.latents_b.latents_name)
 
         if latents_a.shape != latents_b.shape:
             raise Exception("Latents to blend must be the same size.")
@@ -1122,7 +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:
@@ -1155,12 +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")
@@ -1168,10 +1174,8 @@ class BlendLatentsInvocation(BaseInvocation):
         if device == torch.device("mps"):
             mps.empty_cache()
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, blended_latents)
-        return build_latents_output(latents_name=name, latents=blended_latents)
+        name = context.tensors.save(tensor=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents)
 
 
 # The Crop Latents node was copied from @skunkworxdark's implementation here:
@@ -1181,7 +1185,7 @@ class BlendLatentsInvocation(BaseInvocation):
     title="Crop Latents",
     tags=["latents", "crop"],
     category="latents",
-    version="1.0.0",
+    version="1.0.1",
 )
 # TODO(ryand): Named `CropLatentsCoreInvocation` to prevent a conflict with custom node `CropLatentsInvocation`.
 # Currently, if the class names conflict then 'GET /openapi.json' fails.
@@ -1216,7 +1220,7 @@ class CropLatentsCoreInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
         x1 = self.x // LATENT_SCALE_FACTOR
         y1 = self.y // LATENT_SCALE_FACTOR
@@ -1225,10 +1229,9 @@ class CropLatentsCoreInvocation(BaseInvocation):
 
         cropped_latents = latents[..., y1:y2, x1:x2]
 
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, cropped_latents)
+        name = context.tensors.save(tensor=cropped_latents)
 
-        return build_latents_output(latents_name=name, latents=cropped_latents)
+        return LatentsOutput.build(latents_name=name, latents=cropped_latents)
 
 
 @invocation_output("ideal_size_output")
@@ -1256,15 +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/math.py

@@ -5,10 +5,11 @@ from typing import Literal
 import numpy as np
 from pydantic import ValidationInfo, field_validator
 
+from invokeai.app.invocations.fields import FieldDescriptions, InputField
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
 
 
 @invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")

invokeai/app/invocations/metadata.py

@@ -5,20 +5,23 @@ from pydantic import BaseModel, ConfigDict, Field
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    MetadataField,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.controlnet_image_processors import ControlField
-from invokeai.app.invocations.ip_adapter import IPAdapterModelField
-from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.primitives import ImageField
-from invokeai.app.invocations.t2i_adapter import T2IAdapterField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.controlnet_image_processors import (
+    CONTROLNET_MODE_VALUES,
+    CONTROLNET_RESIZE_VALUES,
+)
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    ImageField,
+    InputField,
+    MetadataField,
+    OutputField,
+    UIType,
+)
+from invokeai.app.invocations.model import ModelIdentifierField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from ...version import __version__
 
@@ -31,7 +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)
 
 
@@ -39,16 +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"""
@@ -112,7 +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"""
 
@@ -138,14 +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")
@@ -157,7 +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",
     )
@@ -188,7 +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",
     )
@@ -220,10 +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

@@ -1,61 +1,73 @@
 import copy
 from typing import List, Optional
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+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,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 
 
-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")
 
@@ -64,14 +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")
@@ -81,136 +93,54 @@ 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",
     tags=["model"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 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.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.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="1.0.0")
-class LoraLoaderInvocation(BaseInvocation):
+@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
+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,
@@ -218,55 +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.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unkown lora name: {lora_name}!")
+        if self.unet is not None and any(lora.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,
                 )
             )
@@ -275,12 +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(
@@ -288,12 +204,14 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
     title="SDXL LoRA",
     tags=["lora", "model"],
     category="model",
-    version="1.0.0",
+    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,
@@ -301,76 +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.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=lora_name,
-            model_type=ModelType.Lora,
-        ):
-            raise Exception(f"Unknown lora name: {lora_name}!")
+        if self.unet is not None and any(lora.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,
                 )
             )
@@ -378,45 +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="1.0.0")
-class VaeLoaderInvocation(BaseInvocation):
+@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
+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.services.model_manager.model_exists(
-            base_model=base_model,
-            model_name=model_name,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unkown vae name: {model_name}!")
-        return VAEOutput(
-            vae=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                )
-            )
-        )
+        if not context.models.exists(key):
+            raise Exception(f"Unkown vae: {key}!")
+
+        return VAEOutput(vae=VAEField(vae=self.vae_model))
 
 
 @invocation_output("seamless_output")
@@ -424,7 +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(
@@ -443,7 +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/noise.py

@@ -4,17 +4,15 @@
 import torch
 from pydantic import field_validator
 
-from invokeai.app.invocations.latent import LatentsField
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import FieldDescriptions, InputField, LatentsField, OutputField
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.misc import SEED_MAX
 
 from ...backend.util.devices import choose_torch_device, torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
@@ -69,13 +67,13 @@ class NoiseOutput(BaseInvocationOutput):
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
-
-def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
-    return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: int) -> "NoiseOutput":
+        return cls(
+            noise=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
 
 
 @invocation(
@@ -96,13 +94,13 @@ class NoiseInvocation(BaseInvocation):
     )
     width: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.width,
     )
     height: int = InputField(
         default=512,
-        multiple_of=8,
+        multiple_of=LATENT_SCALE_FACTOR,
         gt=0,
         description=FieldDescriptions.height,
     )
@@ -124,6 +122,5 @@ class NoiseInvocation(BaseInvocation):
             seed=self.seed,
             use_cpu=self.use_cpu,
         )
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise, seed=self.seed)
+        name = context.tensors.save(tensor=noise)
+        return NoiseOutput.build(latents_name=name, latents=noise, seed=self.seed)

invokeai/app/invocations/onnx.py

@@ -1,508 +0,0 @@
-# Copyright (c) 2023 Borisov Sergey (https://github.com/StAlKeR7779)
-
-import inspect
-
-# from contextlib import ExitStack
-from typing import List, Literal, Union
-
-import numpy as np
-import torch
-from diffusers.image_processor import VaeImageProcessor
-from pydantic import BaseModel, ConfigDict, Field, field_validator
-from tqdm import tqdm
-
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
-from invokeai.app.shared.fields import FieldDescriptions
-from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend import BaseModelType, ModelType, SubModelType
-
-from ...backend.model_management import ONNXModelPatcher
-from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.util import choose_torch_device
-from ..util.ti_utils import extract_ti_triggers_from_prompt
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    UIType,
-    WithMetadata,
-    invocation,
-    invocation_output,
-)
-from .controlnet_image_processors import ControlField
-from .latent import SAMPLER_NAME_VALUES, LatentsField, LatentsOutput, build_latents_output, get_scheduler
-from .model import ClipField, ModelInfo, UNetField, VaeField
-
-ORT_TO_NP_TYPE = {
-    "tensor(bool)": np.bool_,
-    "tensor(int8)": np.int8,
-    "tensor(uint8)": np.uint8,
-    "tensor(int16)": np.int16,
-    "tensor(uint16)": np.uint16,
-    "tensor(int32)": np.int32,
-    "tensor(uint32)": np.uint32,
-    "tensor(int64)": np.int64,
-    "tensor(uint64)": np.uint64,
-    "tensor(float16)": np.float16,
-    "tensor(float)": np.float32,
-    "tensor(double)": np.float64,
-}
-
-PRECISION_VALUES = Literal[tuple(ORT_TO_NP_TYPE.keys())]
-
-
-@invocation("prompt_onnx", title="ONNX Prompt (Raw)", tags=["prompt", "onnx"], category="conditioning", version="1.0.0")
-class ONNXPromptInvocation(BaseInvocation):
-    prompt: str = InputField(default="", description=FieldDescriptions.raw_prompt, ui_component=UIComponent.Textarea)
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
-
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.model_dump(),
-        )
-        text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.model_dump(),
-        )
-        with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder:  # , ExitStack() as stack:
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(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.services.model_manager.get_model(
-                                model_name=name,
-                                base_model=self.clip.text_encoder.base_model,
-                                model_type=ModelType.TextualInversion,
-                            ).context.model,
-                        )
-                    )
-                except Exception:
-                    # print(e)
-                    # import traceback
-                    # print(traceback.format_exc())
-                    print(f'Warn: trigger: "{trigger}" not found')
-            if loras or ti_list:
-                text_encoder.release_session()
-            with (
-                ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras),
-                ONNXModelPatcher.apply_ti(orig_tokenizer, text_encoder, ti_list) as (tokenizer, ti_manager),
-            ):
-                text_encoder.create_session()
-
-                # copy from
-                # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L153
-                text_inputs = tokenizer(
-                    self.prompt,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="np",
-                )
-                text_input_ids = text_inputs.input_ids
-                """
-                untruncated_ids = tokenizer(prompt, padding="max_length", return_tensors="np").input_ids
-
-                if not np.array_equal(text_input_ids, untruncated_ids):
-                    removed_text = self.tokenizer.batch_decode(
-                        untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                    )
-                    logger.warning(
-                        "The following part of your input was truncated because CLIP can only handle sequences up to"
-                        f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                    )
-                """
-
-                prompt_embeds = text_encoder(input_ids=text_input_ids.astype(np.int32))[0]
-
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
-
-        # TODO: hacky but works ;D maybe rename latents somehow?
-        context.services.latents.save(conditioning_name, (prompt_embeds, None))
-
-        return ConditioningOutput(
-            conditioning=ConditioningField(
-                conditioning_name=conditioning_name,
-            ),
-        )
-
-
-# Text to image
-@invocation(
-    "t2l_onnx",
-    title="ONNX Text to Latents",
-    tags=["latents", "inference", "txt2img", "onnx"],
-    category="latents",
-    version="1.0.0",
-)
-class ONNXTextToLatentsInvocation(BaseInvocation):
-    """Generates latents from conditionings."""
-
-    positive_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.positive_cond,
-        input=Input.Connection,
-    )
-    negative_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.negative_cond,
-        input=Input.Connection,
-    )
-    noise: LatentsField = InputField(
-        description=FieldDescriptions.noise,
-        input=Input.Connection,
-    )
-    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
-    cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5,
-        ge=1,
-        description=FieldDescriptions.cfg_scale,
-    )
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
-    )
-    precision: PRECISION_VALUES = InputField(default="tensor(float16)", description=FieldDescriptions.precision)
-    unet: UNetField = InputField(
-        description=FieldDescriptions.unet,
-        input=Input.Connection,
-    )
-    control: Union[ControlField, list[ControlField]] = InputField(
-        default=None,
-        description=FieldDescriptions.control,
-    )
-    # seamless:   bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
-    # seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-
-    @field_validator("cfg_scale")
-    def ge_one(cls, v):
-        """validate that all cfg_scale values are >= 1"""
-        if isinstance(v, list):
-            for i in v:
-                if i < 1:
-                    raise ValueError("cfg_scale must be greater than 1")
-        else:
-            if v < 1:
-                raise ValueError("cfg_scale must be greater than 1")
-        return v
-
-    # based on
-    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        c, _ = context.services.latents.get(self.positive_conditioning.conditioning_name)
-        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
-        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
-        if isinstance(c, torch.Tensor):
-            c = c.cpu().numpy()
-        if isinstance(uc, torch.Tensor):
-            uc = uc.cpu().numpy()
-        device = torch.device(choose_torch_device())
-        prompt_embeds = np.concatenate([uc, c])
-
-        latents = context.services.latents.get(self.noise.latents_name)
-        if isinstance(latents, torch.Tensor):
-            latents = latents.cpu().numpy()
-
-        # TODO: better execution device handling
-        latents = latents.astype(ORT_TO_NP_TYPE[self.precision])
-
-        # get the initial random noise unless the user supplied it
-        do_classifier_free_guidance = True
-        # latents_dtype = prompt_embeds.dtype
-        # latents_shape = (batch_size * num_images_per_prompt, 4, height // 8, width // 8)
-        # if latents.shape != latents_shape:
-        #    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
-
-        scheduler = get_scheduler(
-            context=context,
-            scheduler_info=self.unet.scheduler,
-            scheduler_name=self.scheduler,
-            seed=0,  # TODO: refactor this node
-        )
-
-        def torch2numpy(latent: torch.Tensor):
-            return latent.cpu().numpy()
-
-        def numpy2torch(latent, device):
-            return torch.from_numpy(latent).to(device)
-
-        def dispatch_progress(
-            self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
-        ) -> None:
-            stable_diffusion_step_callback(
-                context=context,
-                intermediate_state=intermediate_state,
-                node=self.model_dump(),
-                source_node_id=source_node_id,
-            )
-
-        scheduler.set_timesteps(self.steps)
-        latents = latents * np.float64(scheduler.init_noise_sigma)
-
-        extra_step_kwargs = {}
-        if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
-            extra_step_kwargs.update(
-                eta=0.0,
-            )
-
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
-
-        with unet_info as unet:  # , ExitStack() as stack:
-            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
-            loras = [
-                (
-                    context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
-                    lora.weight,
-                )
-                for lora in self.unet.loras
-            ]
-
-            if loras:
-                unet.release_session()
-            with ONNXModelPatcher.apply_lora_unet(unet, loras):
-                # TODO:
-                _, _, h, w = latents.shape
-                unet.create_session(h, w)
-
-                timestep_dtype = next(
-                    (input.type for input in unet.session.get_inputs() if input.name == "timestep"), "tensor(float16)"
-                )
-                timestep_dtype = ORT_TO_NP_TYPE[timestep_dtype]
-                for i in tqdm(range(len(scheduler.timesteps))):
-                    t = scheduler.timesteps[i]
-                    # expand the latents if we are doing classifier free guidance
-                    latent_model_input = np.concatenate([latents] * 2) if do_classifier_free_guidance else latents
-                    latent_model_input = scheduler.scale_model_input(numpy2torch(latent_model_input, device), t)
-                    latent_model_input = latent_model_input.cpu().numpy()
-
-                    # predict the noise residual
-                    timestep = np.array([t], dtype=timestep_dtype)
-                    noise_pred = unet(sample=latent_model_input, timestep=timestep, encoder_hidden_states=prompt_embeds)
-                    noise_pred = noise_pred[0]
-
-                    # perform guidance
-                    if do_classifier_free_guidance:
-                        noise_pred_uncond, noise_pred_text = np.split(noise_pred, 2)
-                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
-
-                    # compute the previous noisy sample x_t -> x_t-1
-                    scheduler_output = scheduler.step(
-                        numpy2torch(noise_pred, device), t, numpy2torch(latents, device), **extra_step_kwargs
-                    )
-                    latents = torch2numpy(scheduler_output.prev_sample)
-
-                    state = PipelineIntermediateState(
-                        run_id="test", step=i, timestep=timestep, latents=scheduler_output.prev_sample
-                    )
-                    dispatch_progress(self, context=context, source_node_id=source_node_id, intermediate_state=state)
-
-                    # call the callback, if provided
-                    # if callback is not None and i % callback_steps == 0:
-                    #    callback(i, t, latents)
-
-        torch.cuda.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        context.services.latents.save(name, latents)
-        return build_latents_output(latents_name=name, latents=torch.from_numpy(latents))
-
-
-# Latent to image
-@invocation(
-    "l2i_onnx",
-    title="ONNX Latents to Image",
-    tags=["latents", "image", "vae", "onnx"],
-    category="image",
-    version="1.2.0",
-)
-class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata):
-    """Generates an image from latents."""
-
-    latents: LatentsField = InputField(
-        description=FieldDescriptions.denoised_latents,
-        input=Input.Connection,
-    )
-    vae: VaeField = InputField(
-        description=FieldDescriptions.vae,
-        input=Input.Connection,
-    )
-    # tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        if self.vae.vae.submodel != SubModelType.VaeDecoder:
-            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
-
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.model_dump(),
-        )
-
-        # clear memory as vae decode can request a lot
-        torch.cuda.empty_cache()
-
-        with vae_info as vae:
-            vae.create_session()
-
-            # copied from
-            # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L427
-            latents = 1 / 0.18215 * latents
-            # image = self.vae_decoder(latent_sample=latents)[0]
-            # it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
-            image = np.concatenate([vae(latent_sample=latents[i : i + 1])[0] for i in range(latents.shape[0])])
-
-            image = np.clip(image / 2 + 0.5, 0, 1)
-            image = image.transpose((0, 2, 3, 1))
-            image = VaeImageProcessor.numpy_to_pil(image)[0]
-
-        torch.cuda.empty_cache()
-
-        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,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation_output("model_loader_output_onnx")
-class ONNXModelLoaderOutput(BaseInvocationOutput):
-    """Model loader output"""
-
-    unet: UNetField = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
-    vae_decoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Decoder")
-    vae_encoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Encoder")
-
-
-class OnnxModelField(BaseModel):
-    """Onnx 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=())
-
-
-@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
-class OnnxModelLoaderInvocation(BaseInvocation):
-    """Loads a main model, outputting its submodels."""
-
-    model: OnnxModelField = InputField(
-        description=FieldDescriptions.onnx_main_model, input=Input.Direct, ui_type=UIType.ONNXModel
-    )
-
-    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
-        base_model = self.model.base_model
-        model_name = self.model.model_name
-        model_type = ModelType.ONNX
-
-        # TODO: not found exceptions
-        if not context.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
-
-        """
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.Tokenizer,
-        ):
-            raise Exception(
-                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.TextEncoder,
-        ):
-            raise Exception(
-                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
-            )
-
-        if not context.services.model_manager.model_exists(
-            model_name=self.model_name,
-            model_type=SDModelType.Diffusers,
-            submodel=SDModelType.UNet,
-        ):
-            raise Exception(
-                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
-            )
-        """
-
-        return ONNXModelLoaderOutput(
-            unet=UNetField(
-                unet=ModelInfo(
-                    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_decoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeDecoder,
-                ),
-            ),
-            vae_encoder=VaeField(
-                vae=ModelInfo(
-                    model_name=model_name,
-                    base_model=base_model,
-                    model_type=model_type,
-                    submodel=SubModelType.VaeEncoder,
-                ),
-            ),
-        )

invokeai/app/invocations/param_easing.py

@@ -40,8 +40,10 @@ from easing_functions import (
 from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.primitives import FloatCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField
 
 
 @invocation(
@@ -109,7 +111,7 @@ EASING_FUNCTION_KEYS = Literal[tuple(EASING_FUNCTIONS_MAP.keys())]
     title="Step Param Easing",
     tags=["step", "easing"],
     category="step",
-    version="1.0.0",
+    version="1.0.1",
 )
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
@@ -148,19 +150,19 @@ class StepParamEasingInvocation(BaseInvocation):
         postlist = list(num_poststeps * [self.post_end_value])
 
         if log_diagnostics:
-            context.services.logger.debug("start_step: " + str(start_step))
-            context.services.logger.debug("end_step: " + str(end_step))
-            context.services.logger.debug("num_easing_steps: " + str(num_easing_steps))
-            context.services.logger.debug("num_presteps: " + str(num_presteps))
-            context.services.logger.debug("num_poststeps: " + str(num_poststeps))
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
-            context.services.logger.debug("prelist: " + str(prelist))
-            context.services.logger.debug("postlist: " + str(postlist))
+            context.logger.debug("start_step: " + str(start_step))
+            context.logger.debug("end_step: " + str(end_step))
+            context.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.logger.debug("num_presteps: " + str(num_presteps))
+            context.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist: " + str(prelist))
+            context.logger.debug("postlist: " + str(postlist))
 
         easing_class = EASING_FUNCTIONS_MAP[self.easing]
         if log_diagnostics:
-            context.services.logger.debug("easing class: " + str(easing_class))
+            context.logger.debug("easing class: " + str(easing_class))
         easing_list = []
         if self.mirror:  # "expected" mirroring
             # if number of steps is even, squeeze duration down to (number_of_steps)/2
@@ -171,7 +173,7 @@ class StepParamEasingInvocation(BaseInvocation):
 
             base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
             if log_diagnostics:
-                context.services.logger.debug("base easing duration: " + str(base_easing_duration))
+                context.logger.debug("base easing duration: " + str(base_easing_duration))
             even_num_steps = num_easing_steps % 2 == 0  # even number of steps
             easing_function = easing_class(
                 start=self.start_value,
@@ -183,14 +185,14 @@ class StepParamEasingInvocation(BaseInvocation):
                 easing_val = easing_function.ease(step_index)
                 base_easing_vals.append(easing_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
             if even_num_steps:
                 mirror_easing_vals = list(reversed(base_easing_vals))
             else:
                 mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
             if log_diagnostics:
-                context.services.logger.debug("base easing vals: " + str(base_easing_vals))
-                context.services.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+                context.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
             easing_list = base_easing_vals + mirror_easing_vals
 
         # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
@@ -225,12 +227,12 @@ class StepParamEasingInvocation(BaseInvocation):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
                 if log_diagnostics:
-                    context.services.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
 
         if log_diagnostics:
-            context.services.logger.debug("prelist size: " + str(len(prelist)))
-            context.services.logger.debug("easing_list size: " + str(len(easing_list)))
-            context.services.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
 
         param_list = prelist + easing_list + postlist
 

invokeai/app/invocations/primitives.py

@@ -1,20 +1,28 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import torch
-from pydantic import BaseModel, Field
 
-from invokeai.app.shared.fields import FieldDescriptions
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    ColorField,
+    ConditioningField,
+    DenoiseMaskField,
+    FieldDescriptions,
+    ImageField,
+    Input,
+    InputField,
+    LatentsField,
+    OutputField,
+    UIComponent,
+)
+from invokeai.app.services.images.images_common import ImageDTO
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
@@ -221,18 +229,6 @@ class StringCollectionInvocation(BaseInvocation):
 # region Image
 
 
-class ImageField(BaseModel):
-    """An image primitive field"""
-
-    image_name: str = Field(description="The name of the image")
-
-
-class BoardField(BaseModel):
-    """A board primitive field"""
-
-    board_id: str = Field(description="The id of the board")
-
-
 @invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
@@ -241,6 +237,14 @@ class ImageOutput(BaseInvocationOutput):
     width: int = OutputField(description="The width of the image in pixels")
     height: int = OutputField(description="The height of the image in pixels")
 
+    @classmethod
+    def build(cls, image_dto: ImageDTO) -> "ImageOutput":
+        return cls(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 
 @invocation_output("image_collection_output")
 class ImageCollectionOutput(BaseInvocationOutput):
@@ -251,16 +255,14 @@ class ImageCollectionOutput(BaseInvocationOutput):
     )
 
 
-@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
-class ImageInvocation(
-    BaseInvocation,
-):
+@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.1")
+class ImageInvocation(BaseInvocation):
     """An image primitive value"""
 
     image: ImageField = InputField(description="The image to load")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        image = context.images.get_pil(self.image.image_name)
 
         return ImageOutput(
             image=ImageField(image_name=self.image.image_name),
@@ -290,42 +292,44 @@ class ImageCollectionInvocation(BaseInvocation):
 # region DenoiseMask
 
 
-class DenoiseMaskField(BaseModel):
-    """An inpaint mask field"""
-
-    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")
-
-
 @invocation_output("denoise_mask_output")
 class DenoiseMaskOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
 
     denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
 
+    @classmethod
+    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, gradient=gradient
+            ),
+        )
+
 
 # endregion
 
 # region Latents
 
 
-class LatentsField(BaseModel):
-    """A latents tensor primitive field"""
-
-    latents_name: str = Field(description="The name of the latents")
-    seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
-
-
 @invocation_output("latents_output")
 class LatentsOutput(BaseInvocationOutput):
     """Base class for nodes that output a single latents tensor"""
 
-    latents: LatentsField = OutputField(
-        description=FieldDescriptions.latents,
-    )
+    latents: LatentsField = OutputField(description=FieldDescriptions.latents)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
 
+    @classmethod
+    def build(cls, latents_name: str, latents: torch.Tensor, seed: Optional[int] = None) -> "LatentsOutput":
+        return cls(
+            latents=LatentsField(latents_name=latents_name, seed=seed),
+            width=latents.size()[3] * LATENT_SCALE_FACTOR,
+            height=latents.size()[2] * LATENT_SCALE_FACTOR,
+        )
+
 
 @invocation_output("latents_collection_output")
 class LatentsCollectionOutput(BaseInvocationOutput):
@@ -337,7 +341,7 @@ class LatentsCollectionOutput(BaseInvocationOutput):
 
 
 @invocation(
-    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.0"
+    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.1"
 )
 class LatentsInvocation(BaseInvocation):
     """A latents tensor primitive value"""
@@ -345,9 +349,9 @@ class LatentsInvocation(BaseInvocation):
     latents: LatentsField = InputField(description="The latents tensor", input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
+        latents = context.tensors.load(self.latents.latents_name)
 
-        return build_latents_output(self.latents.latents_name, latents)
+        return LatentsOutput.build(self.latents.latents_name, latents)
 
 
 @invocation(
@@ -368,31 +372,11 @@ class LatentsCollectionInvocation(BaseInvocation):
         return LatentsCollectionOutput(collection=self.collection)
 
 
-def build_latents_output(latents_name: str, latents: torch.Tensor, seed: Optional[int] = None):
-    return LatentsOutput(
-        latents=LatentsField(latents_name=latents_name, seed=seed),
-        width=latents.size()[3] * 8,
-        height=latents.size()[2] * 8,
-    )
-
-
 # endregion
 
 # region Color
 
 
-class ColorField(BaseModel):
-    """A color primitive field"""
-
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
 @invocation_output("color_output")
 class ColorOutput(BaseInvocationOutput):
     """Base class for nodes that output a single color"""
@@ -424,18 +408,16 @@ class ColorInvocation(BaseInvocation):
 # region Conditioning
 
 
-class ConditioningField(BaseModel):
-    """A conditioning tensor primitive value"""
-
-    conditioning_name: str = Field(description="The name of conditioning tensor")
-
-
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
 
     conditioning: ConditioningField = OutputField(description=FieldDescriptions.cond)
 
+    @classmethod
+    def build(cls, conditioning_name: str) -> "ConditioningOutput":
+        return cls(conditioning=ConditioningField(conditioning_name=conditioning_name))
+
 
 @invocation_output("conditioning_collection_output")
 class ConditioningCollectionOutput(BaseInvocationOutput):

invokeai/app/invocations/prompt.py

@@ -6,8 +6,10 @@ from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPrompt
 from pydantic import field_validator
 
 from invokeai.app.invocations.primitives import StringCollectionOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, UIComponent
 
 
 @invocation(

invokeai/app/invocations/sdxl.py

@@ -1,18 +1,14 @@
-from invokeai.app.shared.fields import FieldDescriptions
+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,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
     invocation,
     invocation_output,
 )
-from .model import ClipField, MainModelField, ModelInfo, UNetField, VaeField
+from .model import CLIPField, ModelIdentifierField, UNetField, VAEField
 
 
 @invocation_output("sdxl_model_loader_output")
@@ -20,9 +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")
@@ -30,88 +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="1.0.0")
+@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.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.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),
         )
 
 
@@ -120,69 +67,31 @@ class SDXLModelLoaderInvocation(BaseInvocation):
     title="SDXL Refiner Model",
     tags=["model", "sdxl", "refiner"],
     category="model",
-    version="1.0.0",
+    version="1.0.1",
 )
 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.services.model_manager.model_exists(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-        ):
-            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+        if not context.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/strings.py

@@ -2,16 +2,15 @@
 
 import re
 
+from invokeai.app.services.shared.invocation_context import InvocationContext
+
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
     invocation,
     invocation_output,
 )
+from .fields import InputField, OutputField, UIComponent
 from .primitives import StringOutput
 
 

invokeai/app/invocations/t2i_adapter.py

@@ -1,34 +1,23 @@
 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,
     BaseInvocationOutput,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
     invocation,
     invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
-from invokeai.app.invocations.primitives import ImageField
+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.shared.fields import FieldDescriptions
-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=())
+from invokeai.app.services.shared.invocation_context import InvocationContext
 
 
 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)"
@@ -63,11 +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/invocations/tiles.py

@@ -8,16 +8,12 @@ from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     Classification,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    WithMetadata,
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField, Input, InputField, OutputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.tiles.tiles import (
     calc_tiles_even_split,
     calc_tiles_min_overlap,
@@ -236,7 +232,7 @@ BLEND_MODES = Literal["Linear", "Seam"]
     version="1.1.0",
     classification=Classification.Beta,
 )
-class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
+class MergeTilesToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Merge multiple tile images into a single image."""
 
     # Inputs
@@ -268,7 +264,7 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # existed in memory at an earlier point in the graph.
         tile_np_images: list[np.ndarray] = []
         for image in images:
-            pil_image = context.services.images.get_pil_image(image.image_name)
+            pil_image = context.images.get_pil(image.image_name)
             pil_image = pil_image.convert("RGB")
             tile_np_images.append(np.array(pil_image))
 
@@ -291,18 +287,5 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata):
         # Convert into a PIL image and save
         pil_image = Image.fromarray(np_image)
 
-        image_dto = context.services.images.create(
-            image=pil_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,
-        )
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        image_dto = context.images.save(image=pil_image)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/upscale.py

@@ -8,13 +8,15 @@ import torch
 from PIL import Image
 from pydantic import ConfigDict
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.invocations.fields import ImageField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.image_util.basicsr.rrdbnet_arch import RRDBNet
 from invokeai.backend.image_util.realesrgan.realesrgan import RealESRGAN
 from invokeai.backend.util.devices import choose_torch_device
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, invocation
+from .baseinvocation import BaseInvocation, invocation
+from .fields import InputField, WithBoard, WithMetadata
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -29,8 +31,8 @@ if choose_torch_device() == torch.device("mps"):
     from torch import mps
 
 
-@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.0")
-class ESRGANInvocation(BaseInvocation, WithMetadata):
+@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.3.1")
+class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
     """Upscales an image using RealESRGAN."""
 
     image: ImageField = InputField(description="The input image")
@@ -42,8 +44,8 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
     model_config = ConfigDict(protected_namespaces=())
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        models_path = context.services.configuration.models_path
+        image = context.images.get_pil(self.image.image_name)
+        models_path = context.config.get().models_path
 
         rrdbnet_model = None
         netscale = None
@@ -87,7 +89,7 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
             netscale = 2
         else:
             msg = f"Invalid RealESRGAN model: {self.model_name}"
-            context.services.logger.error(msg)
+            context.logger.error(msg)
             raise ValueError(msg)
 
         esrgan_model_path = Path(f"core/upscaling/realesrgan/{self.model_name}")
@@ -110,19 +112,6 @@ class ESRGANInvocation(BaseInvocation, WithMetadata):
         if choose_torch_device() == torch.device("mps"):
             mps.empty_cache()
 
-        image_dto = context.services.images.create(
-            image=pil_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,
-        )
+        image_dto = context.images.save(image=pil_image)
 
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
+        return ImageOutput.build(image_dto)

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/config_base.py

@@ -17,7 +17,8 @@ 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 omegaconf import DictConfig, DictKeyType, ListConfig, OmegaConf
+from pydantic import BaseModel
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 from invokeai.app.services.config.config_common import PagingArgumentParser, int_or_float_or_str
@@ -27,11 +28,11 @@ class InvokeAISettings(BaseSettings):
     """Runtime configuration settings in which default values are read from an omegaconf .yaml file."""
 
     initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict] = {}
+    argparse_groups: ClassVar[Dict[str, Any]] = {}
 
     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:]):
+    def parse_args(self, argv: Optional[List[str]] = sys.argv[1:]) -> None:
         """Call to parse command-line arguments."""
         parser = self.get_parser()
         opt, unknown_opts = parser.parse_known_args(argv)
@@ -62,13 +63,29 @@ class InvokeAISettings(BaseSettings):
             assert isinstance(category, str)
             if category not in field_dict[type]:
                 field_dict[type][category] = {}
+            if isinstance(value, BaseModel):
+                dump = value.model_dump(exclude_defaults=True, exclude_unset=True, exclude_none=True)
+                field_dict[type][category][name] = dump
+                continue
+            if isinstance(value, list):
+                if not value or len(value) == 0:
+                    continue
+                primitive = isinstance(value[0], get_args(DictKeyType))
+                if not primitive:
+                    val_list: List[Dict[str, Any]] = []
+                    for list_val in value:
+                        if isinstance(list_val, BaseModel):
+                            dump = list_val.model_dump(exclude_defaults=True, exclude_unset=True, exclude_none=True)
+                            val_list.append(dump)
+                    field_dict[type][category][name] = val_list
+                    continue
             # 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):
+    def add_parser_arguments(cls, parser: ArgumentParser) -> None:
         """Dynamically create arguments for a settings parser."""
         if "type" in get_type_hints(cls):
             settings_stanza = get_args(get_type_hints(cls)["type"])[0]
@@ -117,7 +134,8 @@ class InvokeAISettings(BaseSettings):
         """Return the category of a setting."""
         hints = get_type_hints(cls)
         if command_field in hints:
-            return get_args(hints[command_field])[0]
+            result: str = get_args(hints[command_field])[0]
+            return result
         else:
             return "Uncategorized"
 
@@ -155,10 +173,11 @@ class InvokeAISettings(BaseSettings):
             "lora_dir",
             "embedding_dir",
             "controlnet_dir",
+            "conf_path",
         ]
 
     @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
+    def add_field_argument(cls, command_parser, name: str, field, default_override=None) -> None:
         """Add the argparse arguments for a setting parser."""
         field_type = get_type_hints(cls).get(name)
         default = (

invokeai/app/services/config/config_common.py

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

invokeai/app/services/config/config_default.py

@@ -30,7 +30,6 @@ InvokeAI:
     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
@@ -123,7 +122,6 @@ 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
@@ -163,29 +161,34 @@ two configs are kept in separate sections of the config file:
   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
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, Literal, Optional, Union
+from typing import Any, ClassVar, Dict, List, Literal, Optional
 
 from omegaconf import DictConfig, OmegaConf
-from pydantic import Field
+from pydantic import BaseModel, Field, field_validator
 from pydantic.config import JsonDict
 from pydantic_settings import SettingsConfigDict
 
+from invokeai.backend.model_hash.model_hash import HASHING_ALGORITHMS
+
 from .config_base import InvokeAISettings
 
 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
 
 
 class Categories(object):
@@ -196,17 +199,87 @@ class Categories(object):
     Paths: JsonDict = {"category": "Paths"}
     Logging: JsonDict = {"category": "Logging"}
     Development: JsonDict = {"category": "Development"}
-    Other: JsonDict = {"category": "Other"}
+    CLIArgs: JsonDict = {"category": "CLIArgs"}
+    ModelInstall: JsonDict = {"category": "Model Install"}
     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"}
+    Deprecated: JsonDict = {"category": "Deprecated"}
+
+
+class URLRegexToken(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")
+
+    @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."""
+    """Invoke App Configuration
+
+    Attributes:
+        host: **Web Server**: IP address to bind to. Use `0.0.0.0` to serve to your local network.
+        port: **Web Server**: Port to bind to.
+        allow_origins: **Web Server**: Allowed CORS origins.
+        allow_credentials: **Web Server**: Allow CORS credentials.
+        allow_methods: **Web Server**: Methods allowed for CORS.
+        allow_headers: **Web Server**: Headers allowed for CORS.
+        ssl_certfile: **Web Server**: SSL certificate file for HTTPS.
+        ssl_keyfile: **Web Server**: SSL key file for HTTPS.
+        esrgan: **Features**: Enables or disables the upscaling code.
+        internet_available: **Features**: If true, attempt to download models on the fly; otherwise only use local models.
+        log_tokenization: **Features**: Enable logging of parsed prompt tokens.
+        patchmatch: **Features**: Enable patchmatch inpaint code.
+        ignore_missing_core_models: **Features**: Ignore missing core models on startup. If `True`, the app will attempt to download missing models on startup.
+        root: **Paths**: The InvokeAI runtime root directory.
+        autoimport_dir: **Paths**: Path to a directory of models files to be imported on startup.
+        models_dir: **Paths**: Path to the models directory.
+        convert_cache_dir: **Paths**: 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: **Paths**: Path to directory of legacy checkpoint config files.
+        db_dir: **Paths**: Path to InvokeAI databases directory.
+        outdir: **Paths**: Path to directory for outputs.
+        custom_nodes_dir: **Paths**: Path to directory for custom nodes.
+        from_file: **Paths**: Take command input from the indicated file (command-line client only).
+        log_handlers: **Logging**: Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>".
+        log_format: **Logging**: Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style.
+        log_level: **Logging**: Emit logging messages at this level or higher.
+        log_sql: **Logging**: Log SQL queries. `log_level` must be `debug` for this to do anything. Extremely verbose.
+        use_memory_db: **Development**: Use in-memory database. Useful for development.
+        dev_reload: **Development**: Automatically reload when Python sources are changed. Does not reload node definitions.
+        profile_graphs: **Development**: Enable graph profiling using `cProfile`.
+        profile_prefix: **Development**: An optional prefix for profile output files.
+        profiles_dir: **Development**: Path to profiles output directory.
+        version: **CLIArgs**: CLI arg - show InvokeAI version and exit.
+        hashing_algorithm: **Model Install**: 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: **Model Install**: 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.
+        ram: **Model Cache**: Maximum memory amount used by memory model cache for rapid switching (GB).
+        vram: **Model Cache**: Amount of VRAM reserved for model storage (GB)
+        convert_cache: **Model Cache**: Maximum size of on-disk converted models cache (GB)
+        lazy_offload: **Model Cache**: Keep models in VRAM until their space is needed.
+        log_memory_usage: **Model Cache**: 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**: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.
+        precision: **Device**: 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.
+        sequential_guidance: **Generation**: Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.
+        attention_type: **Generation**: Attention type.
+        attention_slice_size: **Generation**: Slice size, valid when attention_type=="sliced".
+        force_tiled_decode: **Generation**: Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty).
+        png_compress_level: **Generation**: 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: **Queue**: Maximum number of items in the session queue.
+        allow_nodes: **Nodes**: List of nodes to allow. Omit to allow all.
+        deny_nodes: **Nodes**: List of nodes to deny. Omit to deny none.
+        node_cache_size: **Nodes**: How many cached nodes to keep in memory.
+    """
 
     singleton_config: ClassVar[Optional[InvokeAIAppConfig]] = None
     singleton_init: ClassVar[Optional[Dict[str, Any]]] = None
@@ -215,87 +288,98 @@ class InvokeAIAppConfig(InvokeAISettings):
     type: Literal["InvokeAI"] = "InvokeAI"
 
     # 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)
+    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.", 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)
+    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 for HTTPS.", json_schema_extra=Categories.WebServer)
 
     # 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)
+    esrgan              : bool = Field(default=True, description="Enables or disables the upscaling code.", json_schema_extra=Categories.Features)
+    # TODO(psyche): This is not used anywhere.
+    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)
+    patchmatch          : bool = Field(default=True, description="Enable patchmatch inpaint code.", json_schema_extra=Categories.Features)
+    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.', json_schema_extra=Categories.Features)
 
     # PATHS
-    root                : Optional[Path] = Field(default=None, description='InvokeAI runtime root directory', json_schema_extra=Categories.Paths)
+    root                : Optional[Path] = Field(default=None, description='The 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)
+    models_dir          : Path = Field(default=Path('models'), description='Path to the models directory.', json_schema_extra=Categories.Paths)
+    convert_cache_dir   : Path = Field(default=Path('models/.cache'), description='Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.', 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='Path to directory for outputs.', 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)
+    # TODO(psyche): This is not used anywhere.
+    from_file           : Optional[Path] = Field(default=None, description='Take command input from the indicated file (command-line client only).', json_schema_extra=Categories.Paths)
 
     # 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>".', json_schema_extra=Categories.Logging)
     # 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          : 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. `log_level` must be `debug` for this to do anything. Extremely verbose.", json_schema_extra=Categories.Logging)
 
     # Development
-    dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", json_schema_extra=Categories.Development)
-    profile_graphs      : bool = Field(default=False, description="Enable graph profiling", json_schema_extra=Categories.Development)
+    use_memory_db       : bool = Field(default=False, description='Use in-memory database. Useful for development.', json_schema_extra=Categories.Development)
+    dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed. Does not reload node definitions.", json_schema_extra=Categories.Development)
+    profile_graphs      : bool = Field(default=False, description="Enable graph profiling using `cProfile`.", 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)
+    profiles_dir        : Path = Field(default=Path('profiles'), description="Path to profiles output directory.", json_schema_extra=Categories.Development)
 
-    version             : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
+    version             : bool = Field(default=False, description="CLI arg - show InvokeAI version and exit.", json_schema_extra=Categories.CLIArgs)
 
     # 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, )
+    ram                 : float = Field(default=DEFAULT_RAM_CACHE, gt=0, description="Maximum memory amount used by memory model cache for rapid switching (GB).", json_schema_extra=Categories.ModelCache, )
+    vram                : float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (GB)", json_schema_extra=Categories.ModelCache, )
+    convert_cache       : float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB)", json_schema_extra=Categories.ModelCache)
+
+    lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed.", json_schema_extra=Categories.ModelCache, )
     log_memory_usage    : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
 
     # DEVICE
-    device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", json_schema_extra=Categories.Device)
-    precision           : Literal["auto", "float16", "bfloat16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
+    device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.", json_schema_extra=Categories.Device)
+    precision           : Literal["auto", "float16", "bfloat16", "float32", "autocast"] = 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.", json_schema_extra=Categories.Device)
 
     # GENERATION
-    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", json_schema_extra=Categories.Generation)
-    attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", json_schema_extra=Categories.Generation)
-    attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', json_schema_extra=Categories.Generation)
-    force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Generation)
-    png_compress_level  : int = Field(default=1, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
+    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 = no compression, 1 = fastest with slightly larger filesize, 9 = slowest with smallest filesize. 1 is typically the best setting.", 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)
+    max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue.", json_schema_extra=Categories.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)
+    node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory.", json_schema_extra=Categories.Nodes)
 
-    # MODEL IMPORT
-    civitai_api_key       : Optional[str] = Field(default=os.environ.get("CIVITAI_API_KEY"), description="API key for CivitAI", json_schema_extra=Categories.Other)
+    # 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.", json_schema_extra=Categories.ModelInstall)
+    remote_api_tokens   : Optional[list[URLRegexToken]] = 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.",
+        json_schema_extra=Categories.ModelInstall
+    )
 
+    # TODO(psyche): Can we just remove these then?
     # 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)
+    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.Deprecated)
+    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.Deprecated)
+    max_vram_cache_size : Optional[float] = Field(default=None, ge=0, description="Amount of VRAM reserved for model storage", json_schema_extra=Categories.Deprecated)
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", json_schema_extra=Categories.Deprecated)
+    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Deprecated)
+    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.Deprecated)
+    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.Deprecated)
+    controlnet_dir      : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Deprecated)
+    conf_path           : Path = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Deprecated)
 
     # 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)
@@ -404,6 +488,11 @@ class InvokeAIAppConfig(InvokeAISettings):
         """Path to the models directory."""
         return self._resolve(self.models_dir)
 
+    @property
+    def models_convert_cache_path(self) -> Path:
+        """Path to the converted cache models directory."""
+        return self._resolve(self.convert_cache_dir)
+
     @property
     def custom_nodes_path(self) -> Path:
         """Path to the custom nodes directory."""
@@ -433,15 +522,20 @@ class InvokeAIAppConfig(InvokeAISettings):
         return True
 
     @property
-    def ram_cache_size(self) -> Union[Literal["auto"], float]:
-        """Return the ram cache size using the legacy or modern setting."""
+    def ram_cache_size(self) -> float:
+        """Return the ram cache size using the legacy or modern setting (GB)."""
         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."""
+    def vram_cache_size(self) -> float:
+        """Return the vram cache size using the legacy or modern setting (GB)."""
         return self.max_vram_cache_size or self.vram
 
+    @property
+    def convert_cache_size(self) -> float:
+        """Return the convert cache size on disk (GB)."""
+        return self.convert_cache
+
     @property
     def use_cpu(self) -> bool:
         """Return true if the device is set to CPU or the always_use_cpu flag is set."""
@@ -463,6 +557,53 @@ class InvokeAIAppConfig(InvokeAISettings):
         """Choose the runtime root directory when not specified on command line or init file."""
         return _find_root()
 
+    @staticmethod
+    def generate_docstrings() -> str:
+        """Helper function for mkdocs. Generates a docstring for the InvokeAIAppConfig class.
+
+        You shouldn't run this manually. Instead, run `scripts/update-config-docstring.py` to update the docstring.
+        A makefile target is also available: `make update-config-docstring`.
+
+        See that script for more information about why this is necessary.
+        """
+        docstring = '    """Invoke App Configuration\n\n'
+        docstring += "    Attributes:"
+
+        field_descriptions: dict[str, list[str]] = {}
+
+        for k, v in InvokeAIAppConfig.model_fields.items():
+            if not isinstance(v.json_schema_extra, dict):
+                # Should never happen
+                continue
+
+            category = v.json_schema_extra.get("category", None)
+            if not isinstance(category, str) or category == "Deprecated":
+                continue
+            if not field_descriptions.get(category):
+                field_descriptions[category] = []
+            field_descriptions[category].append(f"        {k}: **{category}**: {v.description}")
+
+        for c in [
+            "Web Server",
+            "Features",
+            "Paths",
+            "Logging",
+            "Development",
+            "CLIArgs",
+            "Model Install",
+            "Model Cache",
+            "Device",
+            "Generation",
+            "Queue",
+            "Nodes",
+        ]:
+            docstring += "\n"
+            docstring += "\n".join(field_descriptions[c])
+
+        docstring += '\n    """'
+
+        return docstring
+
 
 def get_invokeai_config(**kwargs: Any) -> InvokeAIAppConfig:
     """Legacy function which returns InvokeAIAppConfig.get_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 ModelInfo
-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()
@@ -55,7 +64,7 @@ class EventServiceBase:
         queue_item_id: int,
         queue_batch_id: str,
         graph_execution_state_id: str,
-        node: dict,
+        node_id: str,
         source_node_id: str,
         progress_image: Optional[ProgressImage],
         step: int,
@@ -70,9 +79,9 @@ class EventServiceBase:
                 "queue_item_id": queue_item_id,
                 "queue_batch_id": queue_batch_id,
                 "graph_execution_state_id": graph_execution_state_id,
-                "node_id": node.get("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,
-        model_info: ModelInfo,
+        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": model_info.hash,
-                "location": str(model_info.location),
-                "precision": str(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_base.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 
 

invokeai/app/services/image_files/image_files_disk.py

@@ -7,7 +7,7 @@ from PIL import Image, PngImagePlugin
 from PIL.Image import Image as PILImageType
 from send2trash import send2trash
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail

invokeai/app/services/image_records/image_records_base.py

@@ -2,7 +2,7 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from typing import Optional
 
-from invokeai.app.invocations.metadata import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 
 from .image_records_common import ImageCategory, ImageRecord, ImageRecordChanges, ResourceOrigin

invokeai/app/services/image_records/image_records_sqlite.py

@@ -3,7 +3,7 @@ import threading
 from datetime import datetime
 from typing import Optional, Union, cast
 
-from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator
+from invokeai.app.invocations.fields import MetadataField, MetadataFieldValidator
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.shared.sqlite.sqlite_database import SqliteDatabase
 

invokeai/app/services/images/images_base.py

@@ -3,7 +3,7 @@ from typing import Callable, Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.image_records.image_records_common import (
     ImageCategory,
     ImageRecord,

invokeai/app/services/images/images_default.py

@@ -2,7 +2,7 @@ from typing import Optional
 
 from PIL.Image import Image as PILImageType
 
-from invokeai.app.invocations.baseinvocation import MetadataField
+from invokeai.app.invocations.fields import MetadataField
 from invokeai.app.services.invoker import Invoker
 from invokeai.app.services.shared.pagination import OffsetPaginatedResults
 from invokeai.app.services.workflow_records.workflow_records_common import WorkflowWithoutID
@@ -154,7 +154,7 @@ class ImageService(ImageServiceABC):
             self.__invoker.services.logger.error("Image record not found")
             raise
         except Exception as e:
-            self.__invoker.services.logger.error("Problem getting image DTO")
+            self.__invoker.services.logger.error("Problem getting image metadata")
             raise e
 
     def get_workflow(self, image_name: str) -> Optional[WorkflowWithoutID]:

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

@@ -37,7 +37,8 @@ class MemoryInvocationCache(InvocationCacheBase):
         if self._max_cache_size == 0:
             return
         self._invoker.services.images.on_deleted(self._delete_by_match)
-        self._invoker.services.latents.on_deleted(self._delete_by_match)
+        self._invoker.services.tensors.on_deleted(self._delete_by_match)
+        self._invoker.services.conditioning.on_deleted(self._delete_by_match)
 
     def get(self, key: Union[int, str]) -> Optional[BaseInvocationOutput]:
         with self._lock:
@@ -60,9 +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:
@@ -80,7 +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

@@ -1,237 +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.invocations.baseinvocation import InvocationContext
-from invokeai.app.services.invocation_queue.invocation_queue_common import InvocationQueueItem
-from invokeai.app.services.invocation_stats.invocation_stats_common import (
-    GESStatsNotFoundError,
-)
-from invokeai.app.util.profiler import Profiler
-
-from ..invoker import Invoker
-from .invocation_processor_base import InvocationProcessorABC
-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
-                        outputs = invocation.invoke_internal(
-                            InvocationContext(
-                                services=self.__invoker.services,
-                                graph_execution_state_id=graph_execution_state.id,
-                                queue_item_id=queue_item.session_queue_item_id,
-                                queue_id=queue_item.session_queue_id,
-                                queue_batch_id=queue_item.session_queue_batch_id,
-                                workflow=queue_item.workflow,
-                            )
-                        )
-
-                        # 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

@@ -3,13 +3,20 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
+from invokeai.app.services.object_serializer.object_serializer_base import ObjectSerializerBase
+
 if TYPE_CHECKING:
     from logging import Logger
 
+    import torch
+
+    from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData
+
     from .board_image_records.board_image_records_base import BoardImageRecordStorageBase
     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
@@ -17,18 +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 .latents_storage.latents_storage_base import LatentsStorageBase
-    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
 
@@ -36,83 +37,52 @@ if TYPE_CHECKING:
 class InvocationServices:
     """Services that can be used by invocations"""
 
-    # TODO: Just forward-declared everything due to circular dependencies. Fix structure.
-    board_images: "BoardImagesServiceABC"
-    board_image_record_storage: "BoardImageRecordStorageBase"
-    boards: "BoardServiceABC"
-    board_records: "BoardRecordStorageBase"
-    configuration: "InvokeAIAppConfig"
-    events: "EventServiceBase"
-    graph_execution_manager: "ItemStorageABC[GraphExecutionState]"
-    images: "ImageServiceABC"
-    image_records: "ImageRecordStorageBase"
-    image_files: "ImageFileStorageBase"
-    latents: "LatentsStorageBase"
-    logger: "Logger"
-    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"
-    names: "NameServiceBase"
-    urls: "UrlServiceBase"
-    workflow_records: "WorkflowRecordsStorageBase"
-
     def __init__(
         self,
         board_images: "BoardImagesServiceABC",
         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",
-        latents: "LatentsStorageBase",
         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",
         names: "NameServiceBase",
         urls: "UrlServiceBase",
         workflow_records: "WorkflowRecordsStorageBase",
+        tensors: "ObjectSerializerBase[torch.Tensor]",
+        conditioning: "ObjectSerializerBase[ConditioningFieldData]",
     ):
         self.board_images = board_images
         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.latents = latents
         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
         self.names = names
         self.urls = urls
         self.workflow_records = workflow_records
+        self.tensors = tensors
+        self.conditioning = conditioning

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)