wip attempt to rewrite to use no adapter

will squash and describe all changes later sry

.dockerignore

@@ -1,25 +1,9 @@
-# use this file as a whitelist
 *
 !invokeai
-!ldm
 !pyproject.toml
+!docker/docker-entrypoint.sh
+!LICENSE
 
-# ignore frontend/web but whitelist dist
-invokeai/frontend/web/
-!invokeai/frontend/web/dist/
-
-# ignore invokeai/assets but whitelist invokeai/assets/web
-invokeai/assets/
-!invokeai/assets/web/
-
-# Guard against pulling in any models that might exist in the directory tree
-**/*.pt*
-**/*.ckpt
-
-# Byte-compiled / optimized / DLL files
-**/__pycache__/
-**/*.py[cod]
-
-# Distribution / packaging
-**/*.egg-info/
-**/*.egg
+**/node_modules
+**/__pycache__
+**/*.egg-info

.github/CODEOWNERS

@@ -2,7 +2,7 @@
 /.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein  @tildebyte @blessedcoolant
+/docs/ @lstein @blessedcoolant @hipsterusername
 /mkdocs.yml @lstein  @blessedcoolant
 
 # nodes
@@ -18,17 +18,17 @@
 /invokeai/version @lstein @blessedcoolant
 
 # web ui
-/invokeai/frontend @blessedcoolant @psychedelicious @lstein
-/invokeai/backend @blessedcoolant @psychedelicious @lstein
+/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp
+/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp
 
 # generation, model management, postprocessing
-/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2 @StAlKeR7779
 
 # front ends
 /invokeai/frontend/CLI @lstein
 /invokeai/frontend/install @lstein @ebr  
-/invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/web @psychedelicious @blessedcoolant
+/invokeai/frontend/merge @lstein @blessedcoolant 
+/invokeai/frontend/training @lstein @blessedcoolant 
+/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp 
 
 

.github/workflows/build-container.yml

@@ -3,17 +3,15 @@ on:
   push:
     branches:
       - 'main'
-      - 'update/ci/docker/*'
-      - 'update/docker/*'
-      - 'dev/ci/docker/*'
-      - 'dev/docker/*'
     paths:
       - 'pyproject.toml'
       - '.dockerignore'
       - 'invokeai/**'
       - 'docker/Dockerfile'
+      - 'docker/docker-entrypoint.sh'
+      - 'workflows/build-container.yml'
     tags:
-      - 'v*.*.*'
+      - 'v*'
   workflow_dispatch:
 
 permissions:
@@ -26,23 +24,27 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        flavor:
-          - rocm
-          - cuda
-          - cpu
-        include:
-          - flavor: rocm
-            pip-extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-          - flavor: cuda
-            pip-extra-index-url: ''
-          - flavor: cpu
-            pip-extra-index-url: 'https://download.pytorch.org/whl/cpu'
+        gpu-driver:
+        - cuda
+        - cpu
+        - rocm
     runs-on: ubuntu-latest
-    name: ${{ matrix.flavor }}
+    name: ${{ matrix.gpu-driver }}
     env:
-      PLATFORMS: 'linux/amd64,linux/arm64'
-      DOCKERFILE: 'docker/Dockerfile'
+      # torch/arm64 does not support GPU currently, so arm64 builds
+      # would not be GPU-accelerated.
+      # re-enable arm64 if there is sufficient demand.
+      # PLATFORMS: 'linux/amd64,linux/arm64'
+      PLATFORMS: 'linux/amd64'
     steps:
+      - name: Free up more disk space on the runner
+        # https://github.com/actions/runner-images/issues/2840#issuecomment-1284059930
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+          sudo swapoff /mnt/swapfile
+          sudo rm -rf /mnt/swapfile
+
       - name: Checkout
         uses: actions/checkout@v3
 
@@ -53,7 +55,7 @@ jobs:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           images: |
             ghcr.io/${{ github.repository }}
-            ${{ vars.DOCKERHUB_REPOSITORY }}
+            ${{ env.DOCKERHUB_REPOSITORY }}
           tags: |
             type=ref,event=branch
             type=ref,event=tag
@@ -62,8 +64,8 @@ jobs:
             type=pep440,pattern={{major}}
             type=sha,enable=true,prefix=sha-,format=short
           flavor: |
-            latest=${{ matrix.flavor == 'cuda' && github.ref == 'refs/heads/main' }}
-            suffix=-${{ matrix.flavor }},onlatest=false
+            latest=${{ matrix.gpu-driver == 'cuda' && github.ref == 'refs/heads/main' }}
+            suffix=-${{ matrix.gpu-driver }},onlatest=false
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v2
@@ -81,34 +83,33 @@ jobs:
           username: ${{ github.repository_owner }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Login to Docker Hub
-        if: github.event_name != 'pull_request' && vars.DOCKERHUB_REPOSITORY != ''
-        uses: docker/login-action@v2
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      # - name: Login to Docker Hub
+      #   if: github.event_name != 'pull_request' && vars.DOCKERHUB_REPOSITORY != ''
+      #   uses: docker/login-action@v2
+      #   with:
+      #     username: ${{ secrets.DOCKERHUB_USERNAME }}
+      #     password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Build container
         id: docker_build
         uses: docker/build-push-action@v4
         with:
           context: .
-          file: ${{ env.DOCKERFILE }}
+          file: docker/Dockerfile
           platforms: ${{ env.PLATFORMS }}
           push: ${{ github.ref == 'refs/heads/main' || github.ref_type == 'tag' }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
-          build-args: PIP_EXTRA_INDEX_URL=${{ matrix.pip-extra-index-url }}
           cache-from: |
-            type=gha,scope=${{ github.ref_name }}-${{ matrix.flavor }}
-            type=gha,scope=main-${{ matrix.flavor }}
-          cache-to: type=gha,mode=max,scope=${{ github.ref_name }}-${{ matrix.flavor }}
+            type=gha,scope=${{ github.ref_name }}-${{ matrix.gpu-driver }}
+            type=gha,scope=main-${{ matrix.gpu-driver }}
+          cache-to: type=gha,mode=max,scope=${{ github.ref_name }}-${{ matrix.gpu-driver }}
 
-      - name: Docker Hub Description
-        if: github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' && vars.DOCKERHUB_REPOSITORY != ''
-        uses: peter-evans/dockerhub-description@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-          repository: ${{ vars.DOCKERHUB_REPOSITORY }}
-          short-description: ${{ github.event.repository.description }}
+      # - name: Docker Hub Description
+      #   if: github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' && vars.DOCKERHUB_REPOSITORY != ''
+      #   uses: peter-evans/dockerhub-description@v3
+      #   with:
+      #     username: ${{ secrets.DOCKERHUB_USERNAME }}
+      #     password: ${{ secrets.DOCKERHUB_TOKEN }}
+      #     repository: ${{ vars.DOCKERHUB_REPOSITORY }}
+      #     short-description: ${{ github.event.repository.description }}

.github/workflows/mkdocs-material.yml

@@ -2,8 +2,7 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'main'
-      - 'development'
+      - 'refs/heads/v2.3'
 
 permissions:
     contents: write
@@ -12,6 +11,10 @@ jobs:
   mkdocs-material:
     if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
+    env:
+      REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
+      REPO_NAME: '${{ github.repository }}'
+      SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
     steps:
       - name: checkout sources
         uses: actions/checkout@v3
@@ -22,11 +25,15 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
 
       - name: install requirements
+        env:
+          PIP_USE_PEP517: 1
         run: |
           python -m \
-            pip install -r docs/requirements-mkdocs.txt
+            pip install ".[docs]"
 
       - name: confirm buildability
         run: |
@@ -36,7 +43,7 @@ jobs:
             --verbose
 
       - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/main' }}
+        if: ${{ github.ref == 'refs/heads/v2.3' }}
         run: |
           python -m \
             mkdocs gh-deploy \

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

@@ -1,10 +1,16 @@
 name: Test invoke.py pip
+
+# This is a dummy stand-in for the actual tests
+# we don't need to run python tests on non-Python changes
+# But PRs require passing tests to be mergeable
+
 on:
   pull_request:
     paths:
       - '**'
       - '!pyproject.toml'
       - '!invokeai/**'
+      - '!tests/**'
       - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
@@ -19,48 +25,26 @@ jobs:
     strategy:
       matrix:
         python-version:
-          # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
-            github-env: $GITHUB_ENV
           - pytorch: linux-rocm-5_2
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
-            github-env: $GITHUB_ENV
           - pytorch: linux-cpu
             os: ubuntu-22.04
-            extra-index-url: 'https://download.pytorch.org/whl/cpu'
-            github-env: $GITHUB_ENV
           - pytorch: macos-default
             os: macOS-12
-            github-env: $GITHUB_ENV
           - pytorch: windows-cpu
             os: windows-2022
-            github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     steps:
-      - run: 'echo "No build required"'
+      - name: skip
+        run: echo "no build required"

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

@@ -11,6 +11,7 @@ on:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
+      - 'tests/**'
       - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
@@ -32,19 +33,12 @@ jobs:
           # - '3.9'
           - '3.10'
         pytorch:
-          # - linux-cuda-11_6
           - linux-cuda-11_7
           - linux-rocm-5_2
           - linux-cpu
           - macos-default
           - windows-cpu
-          # - windows-cuda-11_6
-          # - windows-cuda-11_7
         include:
-          # - pytorch: linux-cuda-11_6
-          #   os: ubuntu-22.04
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $GITHUB_ENV
           - pytorch: linux-cuda-11_7
             os: ubuntu-22.04
             github-env: $GITHUB_ENV
@@ -62,14 +56,6 @@ jobs:
           - pytorch: windows-cpu
             os: windows-2022
             github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_6
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu116'
-          #   github-env: $env:GITHUB_ENV
-          # - pytorch: windows-cuda-11_7
-          #   os: windows-2022
-          #   extra-index-url: 'https://download.pytorch.org/whl/cu117'
-          #   github-env: $env:GITHUB_ENV
     name: ${{ matrix.pytorch }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     env:
@@ -80,11 +66,6 @@ jobs:
         uses: actions/checkout@v3
 
       - name: set test prompt to main branch validation
-        if: ${{ github.ref == 'refs/heads/main' }}
-        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
-
-      - name: set test prompt to Pull Request validation
-        if: ${{ github.ref != 'refs/heads/main' }}
         run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
@@ -105,40 +86,38 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: set INVOKEAI_OUTDIR
-        run: >
-          python -c
-          "import os;from invokeai.backend.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
-          >> ${{ matrix.github-env }}
+      # - 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-configure
-        id: run-preload-models
-        env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGINGFACE_TOKEN }}
-        run: >
-          invokeai-configure
-          --yes
-          --default_only
-          --full-precision
-        # can't use fp16 weights without a GPU
+      # - name: run invokeai
+      #   id: run-invokeai
+      #   env:
+      #     # Set offline mode to make sure configure preloaded successfully.
+      #     HF_HUB_OFFLINE: 1
+      #     HF_DATASETS_OFFLINE: 1
+      #     TRANSFORMERS_OFFLINE: 1
+      #     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: run invokeai
-        id: run-invokeai
-        env:
-          # Set offline mode to make sure configure preloaded successfully.
-          HF_HUB_OFFLINE: 1
-          HF_DATASETS_OFFLINE: 1
-          TRANSFORMERS_OFFLINE: 1
-        run: >
-          invokeai
-          --no-patchmatch
-          --no-nsfw_checker
-          --from_file ${{ env.TEST_PROMPTS }}
-          --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
-
-      - name: Archive results
-        id: archive-results
-        uses: actions/upload-artifact@v3
-        with:
-          name: results
-          path: ${{ env.INVOKEAI_OUTDIR }}
+      # - name: Archive results
+      #   env:
+      #     INVOKEAI_OUTDIR: ${{ github.workspace }}/results
+      #   uses: actions/upload-artifact@v3
+      #   with:
+      #     name: results
+      #     path: ${{ env.INVOKEAI_OUTDIR }}

.gitignore

@@ -34,7 +34,7 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-dist/
+# dist/
 downloads/
 eggs/
 .eggs/
@@ -79,6 +79,7 @@ cov.xml
 .pytest.ini
 cover/
 junit/
+notes/
 
 # Translations
 *.mo
@@ -201,6 +202,9 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
+invokeai/frontend/yarn.lock
+invokeai/frontend/node_modules
+
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*
 

LICENSE

@@ -1,21 +1,176 @@
-MIT License
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
 
-Copyright (c) 2022 InvokeAI Team
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+   1. Definitions.
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   

README.md

@@ -1,8 +1,11 @@
 <div align="center">
 
-![project logo](https://github.com/invoke-ai/InvokeAI/raw/main/docs/assets/invoke_ai_banner.png)
+![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
+
+# Invoke AI - Generative AI for Professional Creatives
+## Professional Creative Tools for Stable Diffusion, Custom-Trained Models, and more. 
+  To learn more about Invoke AI, get started instantly, or implement our Business solutions, visit [invoke.ai](https://invoke.ai)
 
-# InvokeAI: A Stable Diffusion Toolkit
 
 [![discord badge]][discord link]
 
@@ -33,13 +36,32 @@
 
 </div>
 
-InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
+_**Note: This is an alpha release. Bugs are expected and not all
+features are fully implemented. Please use the GitHub [Issues
+pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
+to report unexpected problems. Also note that InvokeAI root directory
+which contains models, outputs and configuration files, has changed
+between the 2.x and 3.x release. If you wish to use your v2.3 root
+directory with v3.0, please follow the directions in [Migrating a 2.3
+root directory to 3.0](#migrating-to-3).**_
 
-**Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
+InvokeAI is a leading creative engine built to empower professionals
+and enthusiasts alike. Generate and create stunning visual media using
+the latest AI-driven technologies. InvokeAI offers an industry leading
+Web Interface, interactive Command Line Interface, and also serves as
+the foundation for multiple commercial products.
 
-_Note: InvokeAI is rapidly evolving. Please use the
-[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
-requests. Be sure to use the provided templates. They will help us diagnose issues faster._
+**Quick links**: [[How to
+  Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a
+  href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a
+  href="https://invoke-ai.github.io/InvokeAI/">Documentation and
+  Tutorials</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/">Code and
+  Downloads</a>] [<a
+  href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>]
+  [<a
+  href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion,
+  Ideas & Q&A</a>]
 
 <div align="center">
 
@@ -49,22 +71,30 @@ requests. Be sure to use the provided templates. They will help us diagnose issu
 
 ## Table of Contents
 
-1. [Quick Start](#getting-started-with-invokeai)
-2. [Installation](#detailed-installation-instructions)
-3. [Hardware Requirements](#hardware-requirements)
-4. [Features](#features)
-5. [Latest Changes](#latest-changes)
-6. [Troubleshooting](#troubleshooting)
-7. [Contributing](#contributing)
-8. [Contributors](#contributors)
-9. [Support](#support)
-10. [Further Reading](#further-reading)
+Table of Contents 📝
 
-## Getting Started with InvokeAI
+**Getting Started**
+1. 🏁 [Quick Start](#quick-start) 
+3. 🖥️ [Hardware Requirements](#hardware-requirements) 
+
+**More About Invoke**
+1. 🌟 [Features](#features) 
+2. 📣 [Latest Changes](#latest-changes) 
+3. 🛠️ [Troubleshooting](#troubleshooting) 
+
+**Supporting the Project**
+1. 🤝 [Contributing](#contributing) 
+2. 👥 [Contributors](#contributors) 
+3. 💕 [Support](#support) 
+
+## Quick Start
 
 For full installation and upgrade instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
+If upgrading from version 2.3, please read [Migrating a 2.3 root
+directory to 3.0](#migrating-to-3) first.
+
 ### Automatic Installer (suggested for 1st time users)
 
 1. Go to the bottom of the [Latest Release Page](https://github.com/invoke-ai/InvokeAI/releases/latest)
@@ -73,9 +103,8 @@ For full installation and upgrade instructions, please see:
 
 3. Unzip the file.
 
-4. If you are on Windows, double-click on the `install.bat` script. On
-macOS, open a Terminal window, drag the file `install.sh` from Finder
-into the Terminal, and press return. On Linux, run `install.sh`.
+4. **Windows:** double-click on the `install.bat` script. **macOS:** Open a Terminal window, drag the file `install.sh` from Finder
+into the Terminal, and press return. **Linux:** run `install.sh`.
 
 5. You'll be asked to confirm the location of the folder in which
 to install InvokeAI and its image generation model files. Pick a
@@ -101,7 +130,7 @@ and go to http://localhost:9090.
 
 10. Type `banana sushi` in the box on the top left and click `Invoke`
 
-### Command-Line Installation (for users familiar with Terminals)
+### Command-Line Installation (for developers and users familiar with Terminals)
 
 You must have Python 3.9 or 3.10 installed on your machine. Earlier or later versions are
 not supported.
@@ -177,7 +206,7 @@ not supported.
 Be sure to activate the virtual environment each time before re-launching InvokeAI,
 using `source .venv/bin/activate` or `.venv\Scripts\activate`.
 
-### Detailed Installation Instructions
+## Detailed Installation Instructions
 
 This fork is supported across Linux, Windows and Macintosh. Linux
 users can use either an Nvidia-based card (with CUDA support) or an
@@ -185,6 +214,87 @@ AMD card (using the ROCm driver). For full installation and upgrade
 instructions, please see:
 [InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALL_SOURCE/)
 
+<a name="migrating-to-3"></a>
+### Migrating a v2.3 InvokeAI root directory
+
+The InvokeAI root directory is where the InvokeAI startup file,
+installed models, and generated images are stored. It is ordinarily
+named `invokeai` and located in your home directory. The contents and
+layout of this directory has changed between versions 2.3 and 3.0 and
+cannot be used directly.
+
+We currently recommend that you use the installer to create a new root
+directory named differently from the 2.3 one, e.g. `invokeai-3` and
+then use a migration script to copy your 2.3 models into the new
+location. However, if you choose, you can upgrade this directory in
+place.  This section gives both recipes.
+
+#### Creating a new root directory and migrating old models
+
+This is the safer recipe because it leaves your old root directory in
+place to fall back on.
+
+1. Follow the instructions above to create and install InvokeAI in a
+directory that has a different name from the 2.3 invokeai directory.
+In this example, we will use "invokeai-3"
+
+2. When you are prompted to select models to install, select a minimal
+set of models, such as stable-diffusion-v1.5 only.
+
+3. After installation is complete launch `invokeai.sh` (Linux/Mac) or
+`invokeai.bat` and select option 8 "Open the developers console". This
+will take you to the command line.
+
+4. Issue the command `invokeai-migrate3 --from /path/to/v2.3-root --to
+/path/to/invokeai-3-root`. Provide the correct `--from` and `--to`
+paths for your v2.3 and v3.0 root directories respectively.
+
+This will copy and convert your old models from 2.3 format to 3.0
+format and create a new `models` directory in the 3.0 directory. The
+old models directory (which contains the models selected at install
+time) will be renamed `models.orig` and can be deleted once you have
+confirmed that the migration was successful.
+
+#### Migrating in place
+
+For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
+without touching the command line. The recipe is as follows>
+
+1. Launch the InvokeAI launcher script in your current v2.3 root directory.
+
+2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
+
+3a. During the alpha release phase, select option [3] and manually
+enter the tag name `v3.0.0+a2`.
+
+3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
+
+4. Once the upgrade is finished you will be returned to the launcher
+menu. Select option [7] "Re-run the configure script to fix a broken
+install or to complete a major upgrade".
+
+This will run the configure script against the v2.3 directory and
+update it to the 3.0 format. The following files will be replaced:
+
+  - The invokeai.init file, replaced by invokeai.yaml
+  - The models directory
+  - The configs/models.yaml model index
+  
+The original versions of these files will be saved with the suffix
+".orig" appended to the end. Once you have confirmed that the upgrade
+worked, you can safely remove these files. Alternatively you can
+restore a working v2.3 directory by removing the new files and
+restoring the ".orig" files' original names.
+
+#### Migration Caveats
+
+The migration script will migrate your invokeai settings and models,
+including textual inversion models, LoRAs and merges that you may have
+installed previously. However it does **not** migrate the generated
+images stored in your 2.3-format outputs directory. The released
+version of 3.0 is expected to have an interface for importing an
+entire directory of image files as a batch.
+
 ## Hardware Requirements
 
 InvokeAI is supported across Linux, Windows and macOS. Linux
@@ -203,13 +313,9 @@ We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
 to render 512x512 images.
 
-### Memory
+**Memory** - At least 12 GB Main Memory RAM.
 
-- At least 12 GB Main Memory RAM.
-
-### Disk
-
-- At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
+**Disk** - At least 12 GB of free disk space for the machine learning model, Python, and all its dependencies.
 
 ## Features
 
@@ -223,28 +329,24 @@ InvokeAI offers a locally hosted Web Server & React Frontend, with an industry l
 
 The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
 
-### *Advanced Prompt Syntax*
+### *Node Architecture & Editor (Beta)*
 
-InvokeAI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
+Invoke AI's backend is built on a graph-based execution architecture. This allows for customizable generation pipelines to be developed by professional users looking to create specific workflows to support their production use-cases, and will be extended in the future with additional capabilities.
 
-### *Command Line Interface*
+### *Board & Gallery Management*
 
-For users utilizing a terminal-based environment, or who want to take advantage of CLI features, InvokeAI offers an extensive and actively supported command-line interface that provides the full suite of generation functionality available in the tool.
+Invoke AI provides an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow. 
 
 ### Other features
 
 - *Support for both ckpt and diffusers models*
 - *SD 2.0, 2.1 support*
-- *Noise Control & Tresholding*
-- *Popular Sampler Support*
-- *Upscaling & Face Restoration Tools*
+- *Upscaling Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-
-### Coming Soon
-
-- *Node-Based Architecture & UI*
-- And more...
+- *Node-Based Architecture*
+- *Node-Based Plug-&-Play UI (Beta)*
+- *SDXL Support* (Coming soon)
 
 ### Latest Changes
 
@@ -252,7 +354,7 @@ For our latest changes, view our [Release
 Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 [CHANGELOG](docs/CHANGELOG.md).
 
-## Troubleshooting
+### Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
 problems and other issues.
@@ -282,8 +384,6 @@ This fork is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for
 their time, hard work and effort.
 
-Thanks to [Weblate](https://weblate.org/) for generously providing translation services to this project.
-
 ### Support
 
 For support, please use this repository's GitHub Issues tracking service, or join the Discord.

binary_installer/install.bat.in

@@ -1,164 +0,0 @@
-@echo off
-
-@rem This script will install git (if not found on the PATH variable)
-@rem  using micromamba (an 8mb static-linked single-file binary, conda replacement).
-@rem For users who already have git, this step will be skipped.
-
-@rem Next, it'll download the project's source code.
-@rem Then it will download a self-contained, standalone Python and unpack it.
-@rem Finally, it'll create the Python virtual environment and preload the models.
-
-@rem This enables a user to install this project without manually installing git or Python
-
-@rem change to the script's directory
-PUSHD "%~dp0"
-
-set "no_cache_dir=--no-cache-dir"
-if "%1" == "use-cache" (
-    set "no_cache_dir="
-)
-
-echo ***** Installing InvokeAI.. *****
-@rem Config
-set INSTALL_ENV_DIR=%cd%\installer_files\env
-@rem https://mamba.readthedocs.io/en/latest/installation.html
-set MICROMAMBA_DOWNLOAD_URL=https://github.com/cmdr2/stable-diffusion-ui/releases/download/v1.1/micromamba.exe
-set RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-set RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-set PYTHON_BUILD_STANDALONE_URL=https://github.com/indygreg/python-build-standalone/releases/download
-set PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-x86_64-pc-windows-msvc-shared-install_only.tar.gz
-
-set PACKAGES_TO_INSTALL=
-
-call git --version >.tmp1 2>.tmp2
-if "%ERRORLEVEL%" NEQ "0" set PACKAGES_TO_INSTALL=%PACKAGES_TO_INSTALL% git
-
-@rem Cleanup
-del /q .tmp1 .tmp2
-
-@rem (if necessary) install git into a contained environment
-if "%PACKAGES_TO_INSTALL%" NEQ "" (
-    @rem download micromamba
-    echo ***** Downloading micromamba from %MICROMAMBA_DOWNLOAD_URL% to micromamba.exe *****
-
-    call curl -L "%MICROMAMBA_DOWNLOAD_URL%" > micromamba.exe
-
-    @rem test the mamba binary
-    echo ***** Micromamba version:  *****
-    call micromamba.exe --version
-
-    @rem create the installer env
-    if not exist "%INSTALL_ENV_DIR%" (
-        call micromamba.exe create -y --prefix "%INSTALL_ENV_DIR%"
-    )
-
-    echo ***** Packages to install:%PACKAGES_TO_INSTALL% *****
-
-    call micromamba.exe install -y --prefix "%INSTALL_ENV_DIR%" -c conda-forge %PACKAGES_TO_INSTALL%
-
-    if not exist "%INSTALL_ENV_DIR%" (
-        echo ----- There was a problem while installing "%PACKAGES_TO_INSTALL%" using micromamba. Cannot continue. -----
-        pause
-        exit /b
-    )
-)
-
-del /q micromamba.exe
-
-@rem For 'git' only
-set PATH=%INSTALL_ENV_DIR%\Library\bin;%PATH%
-
-@rem Download/unpack/clean up InvokeAI release sourceball
-set err_msg=----- InvokeAI source download failed -----
-echo Trying to download "%RELEASE_URL%%RELEASE_SOURCEBALL%"
-curl -L %RELEASE_URL%%RELEASE_SOURCEBALL% --output InvokeAI.tgz
-if %errorlevel% neq 0 goto err_exit
-
-set err_msg=----- InvokeAI source unpack failed -----
-tar -zxf InvokeAI.tgz
-if %errorlevel% neq 0 goto err_exit
-
-del /q InvokeAI.tgz
-
-set err_msg=----- InvokeAI source copy failed -----
-cd InvokeAI-*
-xcopy . .. /e /h
-if %errorlevel% neq 0 goto err_exit
-cd ..
-
-@rem cleanup
-for /f %%i in ('dir /b InvokeAI-*') do rd /s /q %%i
-rd /s /q .dev_scripts .github docker-build tests
-del /q requirements.in requirements-mkdocs.txt shell.nix
-
-echo ***** Unpacked InvokeAI source *****
-
-@rem Download/unpack/clean up python-build-standalone
-set err_msg=----- Python download failed -----
-curl -L %PYTHON_BUILD_STANDALONE_URL%/%PYTHON_BUILD_STANDALONE% --output python.tgz
-if %errorlevel% neq 0 goto err_exit
-
-set err_msg=----- Python unpack failed -----
-tar -zxf python.tgz
-if %errorlevel% neq 0 goto err_exit
-
-del /q python.tgz
-
-echo ***** Unpacked python-build-standalone *****
-
-@rem create venv
-set err_msg=----- problem creating venv -----
-.\python\python -E -s -m venv .venv
-if %errorlevel% neq 0 goto err_exit
-call .venv\Scripts\activate.bat
-
-echo ***** Created Python virtual environment *****
-
-@rem Print venv's Python version
-set err_msg=----- problem calling venv's python -----
-echo We're running under
-.venv\Scripts\python --version
-if %errorlevel% neq 0 goto err_exit
-
-set err_msg=----- pip update failed -----
-.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location --upgrade pip wheel
-if %errorlevel% neq 0 goto err_exit
-
-echo ***** Updated pip and wheel *****
-
-set err_msg=----- requirements file copy failed -----
-copy binary_installer\py3.10-windows-x86_64-cuda-reqs.txt requirements.txt
-if %errorlevel% neq 0 goto err_exit
-
-set err_msg=----- main pip install failed -----
-.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location -r requirements.txt
-if %errorlevel% neq 0 goto err_exit
-
-echo ***** Installed Python dependencies *****
-
-set err_msg=----- InvokeAI setup failed -----
-.venv\Scripts\python -m pip install %no_cache_dir% --no-warn-script-location -e .
-if %errorlevel% neq 0 goto err_exit
-
-copy binary_installer\invoke.bat.in .\invoke.bat
-echo ***** Installed invoke launcher script ******
-
-@rem more cleanup
-rd /s /q binary_installer installer_files
-
-@rem preload the models
-call .venv\Scripts\python ldm\invoke\config\invokeai_configure.py
-set err_msg=----- model download clone failed -----
-if %errorlevel% neq 0 goto err_exit
-deactivate
-
-echo ***** Finished downloading models *****
-
-echo All done! Execute the file invoke.bat in this directory to start InvokeAI
-pause
-exit
-
-:err_exit
-    echo %err_msg%
-    pause
-    exit

binary_installer/install.sh.in

@@ -1,235 +0,0 @@
-#!/usr/bin/env bash
-
-# ensure we're in the correct folder in case user's CWD is somewhere else
-scriptdir=$(dirname "$0")
-cd "$scriptdir"
-
-set -euo pipefail
-IFS=$'\n\t'
-
-function _err_exit {
-    if test "$1" -ne 0
-    then
-        echo -e "Error code $1; Error caught was '$2'"
-        read -p "Press any key to exit..."
-        exit
-    fi
-}
-
-# This script will install git (if not found on the PATH variable)
-#  using micromamba (an 8mb static-linked single-file binary, conda replacement).
-# For users who already have git, this step will be skipped.
-
-# Next, it'll download the project's source code.
-# Then it will download a self-contained, standalone Python and unpack it.
-# Finally, it'll create the Python virtual environment and preload the models.
-
-# This enables a user to install this project without manually installing git or Python
-
-echo -e "\n***** Installing InvokeAI into $(pwd)... *****\n"
-
-export no_cache_dir="--no-cache-dir"
-if [ $# -ge 1 ]; then
-    if [ "$1" = "use-cache" ]; then
-        export no_cache_dir=""
-    fi
-fi
-
-
-OS_NAME=$(uname -s)
-case "${OS_NAME}" in
-    Linux*)     OS_NAME="linux";;
-    Darwin*)    OS_NAME="darwin";;
-    *)          echo -e "\n----- Unknown OS: $OS_NAME! This script runs only on Linux or macOS -----\n" && exit
-esac
-
-OS_ARCH=$(uname -m)
-case "${OS_ARCH}" in
-    x86_64*)    ;;
-    arm64*)     ;;
-    *)          echo -e "\n----- Unknown system architecture: $OS_ARCH! This script runs only on x86_64 or arm64 -----\n" && exit
-esac
-
-# https://mamba.readthedocs.io/en/latest/installation.html
-MAMBA_OS_NAME=$OS_NAME
-MAMBA_ARCH=$OS_ARCH
-if [ "$OS_NAME" == "darwin" ]; then
-    MAMBA_OS_NAME="osx"
-fi
-
-if [ "$OS_ARCH" == "linux" ]; then
-    MAMBA_ARCH="aarch64"
-fi
-
-if [ "$OS_ARCH" == "x86_64" ]; then
-    MAMBA_ARCH="64"
-fi
-
-PY_ARCH=$OS_ARCH
-if [ "$OS_ARCH" == "arm64" ]; then
-    PY_ARCH="aarch64"
-fi
-
-# Compute device ('cd' segment of reqs files) detect goes here
-# This needs a ton of work
-# Suggestions:
-#   - lspci
-#   - check $PATH for nvidia-smi, gtt CUDA/GPU version from output
-#   - Surely there's a similar utility for AMD?
-CD="cuda"
-if [ "$OS_NAME" == "darwin" ] && [ "$OS_ARCH" == "arm64" ]; then
-    CD="mps"
-fi
-
-# config
-INSTALL_ENV_DIR="$(pwd)/installer_files/env"
-MICROMAMBA_DOWNLOAD_URL="https://micro.mamba.pm/api/micromamba/${MAMBA_OS_NAME}-${MAMBA_ARCH}/latest"
-RELEASE_URL=https://github.com/invoke-ai/InvokeAI
-RELEASE_SOURCEBALL=/archive/refs/heads/main.tar.gz
-PYTHON_BUILD_STANDALONE_URL=https://github.com/indygreg/python-build-standalone/releases/download
-if [ "$OS_NAME" == "darwin" ]; then
-    PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-${PY_ARCH}-apple-darwin-install_only.tar.gz
-elif [ "$OS_NAME" == "linux" ]; then
-    PYTHON_BUILD_STANDALONE=20221002/cpython-3.10.7+20221002-${PY_ARCH}-unknown-linux-gnu-install_only.tar.gz
-fi
-echo "INSTALLING $RELEASE_SOURCEBALL FROM $RELEASE_URL"
-
-PACKAGES_TO_INSTALL=""
-
-if ! hash "git" &>/dev/null; then PACKAGES_TO_INSTALL="$PACKAGES_TO_INSTALL git"; fi
-
-# (if necessary) install git and conda into a contained environment
-if [ "$PACKAGES_TO_INSTALL" != "" ]; then
-    # download micromamba
-    echo -e "\n***** Downloading micromamba from $MICROMAMBA_DOWNLOAD_URL to micromamba *****\n"
-
-    curl -L "$MICROMAMBA_DOWNLOAD_URL" | tar -xvjO bin/micromamba > micromamba
-
-    chmod u+x ./micromamba
-
-    # test the mamba binary
-    echo -e "\n***** Micromamba version: *****\n"
-    ./micromamba --version
-
-    # create the installer env
-    if [ ! -e "$INSTALL_ENV_DIR" ]; then
-        ./micromamba create -y --prefix "$INSTALL_ENV_DIR"
-    fi
-
-    echo -e "\n***** Packages to install:$PACKAGES_TO_INSTALL *****\n"
-
-    ./micromamba install -y --prefix "$INSTALL_ENV_DIR" -c conda-forge "$PACKAGES_TO_INSTALL"
-
-    if [ ! -e "$INSTALL_ENV_DIR" ]; then
-        echo -e "\n----- There was a problem while initializing micromamba. Cannot continue. -----\n"
-        exit
-    fi
-fi
-
-rm -f micromamba.exe
-
-export PATH="$INSTALL_ENV_DIR/bin:$PATH"
-
-# Download/unpack/clean up InvokeAI release sourceball
-_err_msg="\n----- InvokeAI source download failed -----\n"
-curl -L $RELEASE_URL/$RELEASE_SOURCEBALL --output InvokeAI.tgz
-_err_exit $? _err_msg
-_err_msg="\n----- InvokeAI source unpack failed -----\n"
-tar -zxf InvokeAI.tgz
-_err_exit $? _err_msg
-
-rm -f InvokeAI.tgz
-
-_err_msg="\n----- InvokeAI source copy failed -----\n"
-cd InvokeAI-*
-cp -r . ..
-_err_exit $? _err_msg
-cd ..
-
-# cleanup
-rm -rf InvokeAI-*/
-rm -rf .dev_scripts/ .github/ docker-build/ tests/ requirements.in requirements-mkdocs.txt shell.nix
-
-echo -e "\n***** Unpacked InvokeAI source *****\n"
-
-# Download/unpack/clean up python-build-standalone
-_err_msg="\n----- Python download failed -----\n"
-curl -L $PYTHON_BUILD_STANDALONE_URL/$PYTHON_BUILD_STANDALONE --output python.tgz
-_err_exit $? _err_msg
-_err_msg="\n----- Python unpack failed -----\n"
-tar -zxf python.tgz
-_err_exit $? _err_msg
-
-rm -f python.tgz
-
-echo -e "\n***** Unpacked python-build-standalone *****\n"
-
-# create venv
-_err_msg="\n----- problem creating venv -----\n"
-
-if [ "$OS_NAME" == "darwin" ]; then
-    # patch sysconfig so that extensions can build properly
-    # adapted from https://github.com/cashapp/hermit-packages/commit/fcba384663892f4d9cfb35e8639ff7a28166ee43
-    PYTHON_INSTALL_DIR="$(pwd)/python"
-    SYSCONFIG="$(echo python/lib/python*/_sysconfigdata_*.py)"
-    TMPFILE="$(mktemp)"
-    chmod +w "${SYSCONFIG}"
-    cp "${SYSCONFIG}" "${TMPFILE}"
-    sed "s,'/install,'${PYTHON_INSTALL_DIR},g" "${TMPFILE}" > "${SYSCONFIG}"
-    rm -f "${TMPFILE}"
-fi
-
-./python/bin/python3 -E -s -m venv .venv
-_err_exit $? _err_msg
-source .venv/bin/activate
-
-echo -e "\n***** Created Python virtual environment *****\n"
-
-# Print venv's Python version
-_err_msg="\n----- problem calling venv's python -----\n"
-echo -e "We're running under"
-.venv/bin/python3 --version
-_err_exit $? _err_msg
-
-_err_msg="\n----- pip update failed -----\n"
-.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location --upgrade pip
-_err_exit $? _err_msg
-
-echo -e "\n***** Updated pip *****\n"
-
-_err_msg="\n----- requirements file copy failed -----\n"
-cp binary_installer/py3.10-${OS_NAME}-"${OS_ARCH}"-${CD}-reqs.txt requirements.txt
-_err_exit $? _err_msg
-
-_err_msg="\n----- main pip install failed -----\n"
-.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location -r requirements.txt
-_err_exit $? _err_msg
-
-echo -e "\n***** Installed Python dependencies *****\n"
-
-_err_msg="\n----- InvokeAI setup failed -----\n"
-.venv/bin/python3 -m pip install $no_cache_dir --no-warn-script-location -e .
-_err_exit $? _err_msg
-
-echo -e "\n***** Installed InvokeAI *****\n"
-
-cp binary_installer/invoke.sh.in ./invoke.sh
-chmod a+rx ./invoke.sh
-echo -e "\n***** Installed invoke launcher script ******\n"
-
-# more cleanup
-rm -rf binary_installer/ installer_files/
-
-# preload the models
-.venv/bin/python3 scripts/configure_invokeai.py
-_err_msg="\n----- model download clone failed -----\n"
-_err_exit $? _err_msg
-deactivate
-
-echo -e "\n***** Finished downloading models *****\n"
-
-echo "All done! Run the command"
-echo "  $scriptdir/invoke.sh"
-echo "to start InvokeAI."
-read -p "Press any key to exit..."
-exit

binary_installer/invoke.bat.in

@@ -1,36 +0,0 @@
-@echo off
-
-PUSHD "%~dp0"
-call .venv\Scripts\activate.bat
-
-echo Do you want to generate images using the
-echo 1. command-line
-echo 2. browser-based UI
-echo OR
-echo 3. open the developer console
-set /p choice="Please enter 1, 2 or 3: "
-if /i "%choice%" == "1" (
-    echo Starting the InvokeAI command-line.
-    .venv\Scripts\python scripts\invoke.py %*
-) else if /i "%choice%" == "2" (
-    echo Starting the InvokeAI browser-based UI.
-    .venv\Scripts\python scripts\invoke.py --web %*
-) else if /i "%choice%" == "3" (
-    echo Developer Console
-    echo Python command is:
-    where python
-    echo Python version is:
-    python --version
-    echo *************************
-    echo You are now in the system shell, with the local InvokeAI Python virtual environment activated,
-    echo so that you can troubleshoot this InvokeAI installation as necessary.
-    echo *************************
-    echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
-    call cmd /k
-) else (
-    echo Invalid selection
-    pause
-    exit /b
-)
-
-deactivate

binary_installer/invoke.sh.in

@@ -1,46 +0,0 @@
-#!/usr/bin/env sh
-
-set -eu
-
-. .venv/bin/activate
-
-# set required env var for torch on mac MPS
- if [ "$(uname -s)" == "Darwin" ]; then
-     export PYTORCH_ENABLE_MPS_FALLBACK=1
- fi
-
-echo "Do you want to generate images using the"
-echo "1. command-line"
-echo "2. browser-based UI"
-echo "OR"
-echo "3. open the developer console"
-echo "Please enter 1, 2, or 3:"
-read choice
-
-case $choice in
-    1)
-        printf "\nStarting the InvokeAI command-line..\n";
-        .venv/bin/python scripts/invoke.py $*;
-    ;;
-    2)
-        printf "\nStarting the InvokeAI browser-based UI..\n";
-        .venv/bin/python scripts/invoke.py --web $*;
-    ;;
-    3)
-        printf "\nDeveloper Console:\n";
-        printf "Python command is:\n\t";
-        which python;
-        printf "Python version is:\n\t";
-        python --version;
-        echo "*************************"
-        echo "You are now in your user shell ($SHELL) with the local InvokeAI Python virtual environment activated,";
-        echo "so that you can troubleshoot this InvokeAI installation as necessary.";
-        printf "*************************\n"
-        echo "*** Type \`exit\` to quit this shell and deactivate the Python virtual environment *** ";
-        /usr/bin/env "$SHELL";
-    ;;
-    *)
-        echo "Invalid selection";
-        exit
-    ;;
-esac

binary_installer/readme.txt

@@ -1,17 +0,0 @@
-InvokeAI
-
-Project homepage: https://github.com/invoke-ai/InvokeAI
-
-Installation on Windows:
-    NOTE: You might need to enable Windows Long Paths. If you're not sure,
-    then you almost certainly need to. Simply double-click the 'WinLongPathsEnabled.reg'
-    file. Note that you will need to have admin privileges in order to
-    do this.
-
-    Please double-click the 'install.bat' file (while keeping it inside the invokeAI folder).
-
-Installation on Linux and Mac:
-    Please open the terminal, and run './install.sh' (while keeping it inside the invokeAI folder).
-
-After installation, please run the 'invoke.bat' file (on Windows) or 'invoke.sh'
-file (on Linux/Mac) to start InvokeAI.

binary_installer/requirements.in

@@ -1,33 +0,0 @@
---prefer-binary
---extra-index-url https://download.pytorch.org/whl/torch_stable.html
---extra-index-url https://download.pytorch.org/whl/cu116
---trusted-host https://download.pytorch.org
-accelerate~=0.15
-albumentations
-diffusers[torch]~=0.11
-einops
-eventlet
-flask_cors
-flask_socketio
-flaskwebgui==1.0.3
-getpass_asterisk
-imageio-ffmpeg
-pyreadline3
-realesrgan
-send2trash
-streamlit
-taming-transformers-rom1504
-test-tube
-torch-fidelity
-torch==1.12.1 ; platform_system == 'Darwin'
-torch==1.12.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
-torchvision==0.13.1 ; platform_system == 'Darwin'
-torchvision==0.13.0+cu116 ; platform_system == 'Linux' or platform_system == 'Windows'
-transformers
-picklescan
-https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip
-https://github.com/invoke-ai/clipseg/archive/1f754751c85d7d4255fa681f4491ff5711c1c288.zip
-https://github.com/invoke-ai/GFPGAN/archive/3f5d2397361199bc4a91c08bb7d80f04d7805615.zip ; platform_system=='Windows'
-https://github.com/invoke-ai/GFPGAN/archive/c796277a1cf77954e5fc0b288d7062d162894248.zip ; platform_system=='Linux' or platform_system=='Darwin'
-https://github.com/Birch-san/k-diffusion/archive/363386981fee88620709cf8f6f2eea167bd6cd74.zip
-https://github.com/invoke-ai/PyPatchMatch/archive/129863937a8ab37f6bbcec327c994c0f932abdbc.zip

docker/.env.sample

@@ -0,0 +1,13 @@
+## Make a copy of this file named `.env` and fill in the values below.
+## Any environment variables supported by InvokeAI can be specified here.
+
+# INVOKEAI_ROOT is the path to a path on the local filesystem where InvokeAI will store data.
+# Outputs will also be stored here by default.
+# This **must** be an absolute path.
+INVOKEAI_ROOT=
+
+HUGGINGFACE_TOKEN=
+
+## optional variables specific to the docker setup
+# GPU_DRIVER=cuda
+# CONTAINER_UID=1000

docker/Dockerfile

@@ -1,107 +1,129 @@
-# syntax=docker/dockerfile:1
+# syntax=docker/dockerfile:1.4
 
-ARG PYTHON_VERSION=3.9
-##################
-##  base image  ##
-##################
-FROM --platform=${TARGETPLATFORM} python:${PYTHON_VERSION}-slim AS python-base
+## Builder stage
 
-LABEL org.opencontainers.image.authors="mauwii@outlook.de"
+FROM library/ubuntu:22.04 AS builder
 
-# Prepare apt for buildkit cache
-RUN rm -f /etc/apt/apt.conf.d/docker-clean \
-  && echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' >/etc/apt/apt.conf.d/keep-cache
+ARG DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt update && apt-get install -y \
+        git \
+        python3.10-venv \
+        python3-pip \
+        build-essential
 
-# Install dependencies
-RUN \
-  --mount=type=cache,target=/var/cache/apt,sharing=locked \
-  --mount=type=cache,target=/var/lib/apt,sharing=locked \
-  apt-get update \
-  && apt-get install -y \
-    --no-install-recommends \
-    libgl1-mesa-glx=20.3.* \
-    libglib2.0-0=2.66.* \
-    libopencv-dev=4.5.*
+ENV INVOKEAI_SRC=/opt/invokeai
+ENV VIRTUAL_ENV=/opt/venv/invokeai
 
-# Set working directory and env
-ARG APPDIR=/usr/src
-ARG APPNAME=InvokeAI
-WORKDIR ${APPDIR}
-ENV PATH ${APPDIR}/${APPNAME}/bin:$PATH
-# Keeps Python from generating .pyc files in the container
-ENV PYTHONDONTWRITEBYTECODE 1
-# Turns off buffering for easier container logging
-ENV PYTHONUNBUFFERED 1
-# Don't fall back to legacy build system
-ENV PIP_USE_PEP517=1
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+ARG TORCH_VERSION=2.0.1
+ARG TORCHVISION_VERSION=0.15.2
+ARG GPU_DRIVER=cuda
+ARG TARGETPLATFORM="linux/amd64"
+# unused but available
+ARG BUILDPLATFORM
 
-#######################
-##  build pyproject  ##
-#######################
-FROM python-base AS pyproject-builder
+WORKDIR ${INVOKEAI_SRC}
 
-# Install build dependencies
-RUN \
-  --mount=type=cache,target=/var/cache/apt,sharing=locked \
-  --mount=type=cache,target=/var/lib/apt,sharing=locked \
-  apt-get update \
-  && apt-get install -y \
-    --no-install-recommends \
-    build-essential=12.9 \
-    gcc=4:10.2.* \
-    python3-dev=3.9.*
+# Install pytorch before all other pip packages
+# NOTE: there are no pytorch builds for arm64 + cuda, only cpu
+# x86_64/CUDA is default
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python3 -m venv ${VIRTUAL_ENV} &&\
+    if [ "$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="--extra-index-url https://download.pytorch.org/whl/rocm5.4.2"; \
+    else \
+        extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu118"; \
+    fi &&\
+    pip install $extra_index_url_arg \
+        torch==$TORCH_VERSION \
+        torchvision==$TORCHVISION_VERSION
 
-# Prepare pip for buildkit cache
-ARG PIP_CACHE_DIR=/var/cache/buildkit/pip
-ENV PIP_CACHE_DIR ${PIP_CACHE_DIR}
-RUN mkdir -p ${PIP_CACHE_DIR}
+# Install the local package.
+# Editable mode helps use the same image for development:
+# the local working copy can be bind-mounted into the image
+# at path defined by ${INVOKEAI_SRC}
+COPY invokeai ./invokeai
+COPY pyproject.toml ./
+RUN --mount=type=cache,target=/root/.cache/pip \
+    # xformers + triton fails to install on arm64
+    if [ "$GPU_DRIVER" = "cuda" ] && [ "$TARGETPLATFORM" = "linux/amd64" ]; then \
+        pip install -e ".[xformers]"; \
+    else \
+        pip install -e "."; \
+    fi
 
-# Create virtual environment
-RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
-  python3 -m venv "${APPNAME}" \
-  --upgrade-deps
+# #### Build the Web UI ------------------------------------
 
-# Install requirements
-COPY --link pyproject.toml .
-COPY --link invokeai/version/invokeai_version.py invokeai/version/__init__.py invokeai/version/
-ARG PIP_EXTRA_INDEX_URL
-ENV PIP_EXTRA_INDEX_URL ${PIP_EXTRA_INDEX_URL}
-RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
-  "${APPNAME}"/bin/pip install .
+FROM node:18 AS web-builder
+WORKDIR /build
+COPY invokeai/frontend/web/ ./
+RUN --mount=type=cache,target=/usr/lib/node_modules \
+    npm install --include dev
+RUN --mount=type=cache,target=/usr/lib/node_modules \
+    yarn vite build
 
-# Install pyproject.toml
-COPY --link . .
-RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
-  "${APPNAME}/bin/pip" install .
 
-# Build patchmatch
+#### Runtime stage ---------------------------------------
+
+FROM library/ubuntu:22.04 AS runtime
+
+ARG DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
+RUN apt update && apt install -y --no-install-recommends \
+        git \
+        curl \
+        vim \
+        tmux \
+        ncdu \
+        iotop \
+        bzip2 \
+        gosu \
+        libglib2.0-0 \
+        libgl1-mesa-glx \
+        python3-venv \
+        python3-pip \
+        build-essential \
+        libopencv-dev \
+        libstdc++-10-dev &&\
+    apt-get clean && apt-get autoclean
+
+# globally add magic-wormhole
+# for ease of transferring data to and from the container
+# when running in sandboxed cloud environments; e.g. Runpod etc.
+RUN pip install magic-wormhole
+
+ENV INVOKEAI_SRC=/opt/invokeai
+ENV VIRTUAL_ENV=/opt/venv/invokeai
+ENV INVOKEAI_ROOT=/invokeai
+ENV PATH="$VIRTUAL_ENV/bin:$INVOKEAI_SRC:$PATH"
+
+# --link requires buldkit w/ dockerfile syntax 1.4
+COPY --link --from=builder ${INVOKEAI_SRC} ${INVOKEAI_SRC}
+COPY --link --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --link --from=web-builder /build/dist ${INVOKEAI_SRC}/invokeai/frontend/web/dist
+
+# Link amdgpu.ids for ROCm builds
+# contributed by https://github.com/Rubonnek
+RUN mkdir -p "/opt/amdgpu/share/libdrm" &&\
+  ln -s "/usr/share/libdrm/amdgpu.ids" "/opt/amdgpu/share/libdrm/amdgpu.ids"
+
+WORKDIR ${INVOKEAI_SRC}
+
+# build patchmatch
+RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
 RUN python3 -c "from patchmatch import patch_match"
 
-#####################
-##  runtime image  ##
-#####################
-FROM python-base AS runtime
+# Create unprivileged user and make the local dir
+RUN useradd --create-home --shell /bin/bash -u 1000 --comment "container local user" invoke
+RUN mkdir -p ${INVOKEAI_ROOT} && chown -R invoke:invoke ${INVOKEAI_ROOT}
 
-# Create a new user
-ARG UNAME=appuser
-RUN useradd \
-  --no-log-init \
-  -m \
-  -U \
-  "${UNAME}"
-
-# Create volume directory
-ARG VOLUME_DIR=/data
-RUN mkdir -p "${VOLUME_DIR}" \
-  && chown -hR "${UNAME}:${UNAME}" "${VOLUME_DIR}"
-
-# Setup runtime environment
-USER ${UNAME}:${UNAME}
-COPY --chown=${UNAME}:${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
-ENV INVOKEAI_ROOT ${VOLUME_DIR}
-ENV TRANSFORMERS_CACHE ${VOLUME_DIR}/.cache
-ENV INVOKE_MODEL_RECONFIGURE "--yes --default_only"
-EXPOSE 9090
-ENTRYPOINT [ "invokeai" ]
-CMD [ "--web", "--host", "0.0.0.0", "--port", "9090" ]
-VOLUME [ "${VOLUME_DIR}" ]
+COPY docker/docker-entrypoint.sh ./
+ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]
+CMD ["invokeai-web", "--host", "0.0.0.0"]

docker/README.md

@@ -0,0 +1,77 @@
+# InvokeAI Containerized
+
+All commands are to be run from the `docker` directory: `cd docker`
+
+#### Linux
+
+1. Ensure builkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
+2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://www.digitalocean.com/community/tutorials/how-to-install-and-use-docker-compose-on-ubuntu-22-04).
+    - The deprecated `docker-compose` (hyphenated) CLI continues to work for now.
+3. Ensure docker daemon is able to access the GPU.
+    - You may need to install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
+
+#### macOS
+
+1. Ensure Docker has at least 16GB RAM
+2. Enable VirtioFS for file sharing
+3. Enable `docker compose` V2 support
+
+This is done via Docker Desktop preferences
+
+## Quickstart
+
+
+1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
+    a. the desired location of the InvokeAI runtime directory, or
+    b. an existing, v3.0.0 compatible runtime directory.
+1. `docker compose up`
+
+The image will be built automatically if needed.
+
+The runtime directory (holding models and outputs) will be created in the location specified by `INVOKEAI_ROOT`. The default location is `~/invokeai`. The runtime directory will be populated with the base configs and models necessary to start generating.
+
+### Use a GPU
+
+- Linux is *recommended* for GPU support in Docker.
+- WSL2 is *required* for Windows.
+- only `x86_64` architecture is supported.
+
+The Docker daemon on the system must be already set up to use the GPU. In case of Linux, this involves installing `nvidia-docker-runtime` and configuring the `nvidia` runtime as default. Steps will be different for AMD. Please see Docker documentation for the most up-to-date instructions for using your GPU with Docker.
+
+## Customize
+
+Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `docker compose up`, your custom values will be used.
+
+You can also set these values in `docker compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
+
+Example (most values are optional):
+
+```
+INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
+HUGGINGFACE_TOKEN=the_actual_token
+CONTAINER_UID=1000
+GPU_DRIVER=cuda
+```
+
+## Even Moar Customizing!
+
+See the `docker compose.yaml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
+
+### Reconfigure the runtime directory
+
+Can be used to download additional models from the supported model list
+
+In conjunction with `INVOKEAI_ROOT` can be also used to initialize a runtime directory
+
+```
+command:
+  - invokeai-configure
+  - --yes
+```
+
+Or install models:
+
+```
+command:
+  - invokeai-model-install
+```

docker/build.sh

@@ -1,51 +1,11 @@
 #!/usr/bin/env bash
 set -e
 
-# If you want to build a specific flavor, set the CONTAINER_FLAVOR environment variable
-#   e.g. CONTAINER_FLAVOR=cpu ./build.sh
-#   Possible Values are:
-#     - cpu
-#     - cuda
-#     - rocm
-#   Don't forget to also set it when executing run.sh
-#   if it is not set, the script will try to detect the flavor by itself.
-#
-# Doc can be found here:
-#   https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
+build_args=""
 
-SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
-cd "$SCRIPTDIR" || exit 1
+[[ -f ".env" ]] && build_args=$(awk '$1 ~ /\=[^$]/ {print "--build-arg " $0 " "}' .env)
 
-source ./env.sh
+echo "docker-compose build args:"
+echo $build_args
 
-DOCKERFILE=${INVOKE_DOCKERFILE:-./Dockerfile}
-
-# print the settings
-echo -e "You are using these values:\n"
-echo -e "Dockerfile:\t\t${DOCKERFILE}"
-echo -e "index-url:\t\t${PIP_EXTRA_INDEX_URL:-none}"
-echo -e "Volumename:\t\t${VOLUMENAME}"
-echo -e "Platform:\t\t${PLATFORM}"
-echo -e "Container Registry:\t${CONTAINER_REGISTRY}"
-echo -e "Container Repository:\t${CONTAINER_REPOSITORY}"
-echo -e "Container Tag:\t\t${CONTAINER_TAG}"
-echo -e "Container Flavor:\t${CONTAINER_FLAVOR}"
-echo -e "Container Image:\t${CONTAINER_IMAGE}\n"
-
-# Create docker volume
-if [[ -n "$(docker volume ls -f name="${VOLUMENAME}" -q)" ]]; then
-    echo -e "Volume already exists\n"
-else
-    echo -n "creating docker volume "
-    docker volume create "${VOLUMENAME}"
-fi
-
-# Build Container
-docker build \
-    --platform="${PLATFORM:-linux/amd64}" \
-    --tag="${CONTAINER_IMAGE:-invokeai}" \
-    ${CONTAINER_FLAVOR:+--build-arg="CONTAINER_FLAVOR=${CONTAINER_FLAVOR}"} \
-    ${PIP_EXTRA_INDEX_URL:+--build-arg="PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}"} \
-    ${PIP_PACKAGE:+--build-arg="PIP_PACKAGE=${PIP_PACKAGE}"} \
-    --file="${DOCKERFILE}" \
-    ..
+docker-compose build $build_args

docker/docker-compose.yml

@@ -0,0 +1,48 @@
+# Copyright (c) 2023 Eugene Brodsky https://github.com/ebr
+
+version: '3.8'
+
+services:
+  invokeai:
+    image: "local/invokeai:latest"
+    # edit below to run on a container runtime other than nvidia-container-runtime.
+    # not yet tested with rocm/AMD GPUs
+    # Comment out the "deploy" section to run on CPU only
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile
+
+    # variables without a default will automatically inherit from the host environment
+    environment:
+      - INVOKEAI_ROOT
+      - HF_HOME
+
+    # Create a .env file in the same directory as this docker-compose.yml file
+    # and populate it with environment variables. See .env.sample
+    env_file:
+      - .env
+
+    ports:
+      - "${INVOKEAI_PORT:-9090}:9090"
+    volumes:
+      - ${INVOKEAI_ROOT:-~/invokeai}:${INVOKEAI_ROOT:-/invokeai}
+      - ${HF_HOME:-~/.cache/huggingface}:${HF_HOME:-/invokeai/.cache/huggingface}
+      # - ${INVOKEAI_MODELS_DIR:-${INVOKEAI_ROOT:-/invokeai/models}}
+      # - ${INVOKEAI_MODELS_CONFIG_PATH:-${INVOKEAI_ROOT:-/invokeai/configs/models.yaml}}
+    tty: true
+    stdin_open: true
+
+    # # Example of running alternative commands/scripts in the container
+    # command:
+    #   - bash
+    #   - -c
+    #   - |
+    #     invokeai-model-install --yes --default-only --config_file ${INVOKEAI_ROOT}/config_custom.yaml
+    #     invokeai-nodes-web --host 0.0.0.0

docker/docker-entrypoint.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+set -e -o pipefail
+
+### Container entrypoint
+# Runs the CMD as defined by the Dockerfile or passed to `docker run`
+# Can be used to configure the runtime dir
+# Bypass by using ENTRYPOINT or `--entrypoint`
+
+### Set INVOKEAI_ROOT pointing to a valid runtime directory
+# Otherwise configure the runtime dir first.
+
+### Configure the InvokeAI runtime directory (done by default)):
+# docker run --rm -it <this image> --configure
+# or skip with --no-configure
+
+### Set the CONTAINER_UID envvar to match your user.
+# Ensures files created in the container are owned by you:
+#   docker run --rm -it -v /some/path:/invokeai -e CONTAINER_UID=$(id -u) <this image>
+# Default UID: 1000 chosen due to popularity on Linux systems. Possibly 501 on MacOS.
+
+USER_ID=${CONTAINER_UID:-1000}
+USER=invoke
+usermod -u ${USER_ID} ${USER} 1>/dev/null
+
+configure() {
+    # Configure the runtime directory
+    if [[ -f ${INVOKEAI_ROOT}/invokeai.yaml ]]; then
+        echo "${INVOKEAI_ROOT}/invokeai.yaml exists. InvokeAI is already configured."
+        echo "To reconfigure InvokeAI, delete the above file."
+        echo "======================================================================"
+    else
+        mkdir -p ${INVOKEAI_ROOT}
+        chown --recursive ${USER} ${INVOKEAI_ROOT}
+        gosu ${USER} invokeai-configure --yes --default_only
+    fi
+}
+
+## Skip attempting to configure.
+## Must be passed first, before any other args.
+if [[ $1 != "--no-configure" ]]; then
+    configure
+else
+    shift
+fi
+
+### Set the $PUBLIC_KEY env var to enable SSH access.
+# We do not install openssh-server in the image by default to avoid bloat.
+# but it is useful to have the full SSH server e.g. on Runpod.
+# (use SCP to copy files to/from the image, etc)
+if [[ -v "PUBLIC_KEY" ]] && [[ ! -d "${HOME}/.ssh" ]]; then
+    apt-get update
+    apt-get install -y openssh-server
+    pushd $HOME
+    mkdir -p .ssh
+    echo ${PUBLIC_KEY} > .ssh/authorized_keys
+    chmod -R 700 .ssh
+    popd
+    service ssh start
+fi
+
+
+cd ${INVOKEAI_ROOT}
+
+# Run the CMD as the Container User (not root).
+exec gosu ${USER} "$@"

docker/env.sh

@@ -1,54 +0,0 @@
-#!/usr/bin/env bash
-
-# This file is used to set environment variables for the build.sh and run.sh scripts.
-
-# Try to detect the container flavor if no PIP_EXTRA_INDEX_URL got specified
-if [[ -z "$PIP_EXTRA_INDEX_URL" ]]; then
-
-  # Activate virtual environment if not already activated and exists
-  if [[ -z $VIRTUAL_ENV ]]; then
-    [[ -e "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" ]] \
-      && source "$(dirname "${BASH_SOURCE[0]}")/../.venv/bin/activate" \
-      && echo "Activated virtual environment: $VIRTUAL_ENV"
-  fi
-
-  # Decide which container flavor to build if not specified
-  if [[ -z "$CONTAINER_FLAVOR" ]] && python -c "import torch" &>/dev/null; then
-    # Check for CUDA and ROCm
-    CUDA_AVAILABLE=$(python -c "import torch;print(torch.cuda.is_available())")
-    ROCM_AVAILABLE=$(python -c "import torch;print(torch.version.hip is not None)")
-    if [[ "${CUDA_AVAILABLE}" == "True" ]]; then
-      CONTAINER_FLAVOR="cuda"
-    elif [[ "${ROCM_AVAILABLE}" == "True" ]]; then
-      CONTAINER_FLAVOR="rocm"
-    else
-      CONTAINER_FLAVOR="cpu"
-    fi
-  fi
-
-  # Set PIP_EXTRA_INDEX_URL based on container flavor
-  if [[ "$CONTAINER_FLAVOR" == "rocm" ]]; then
-    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/rocm"
-  elif [[ "$CONTAINER_FLAVOR" == "cpu" ]]; then
-    PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
-  # elif [[ -z "$CONTAINER_FLAVOR" || "$CONTAINER_FLAVOR" == "cuda" ]]; then
-  #   PIP_PACKAGE=${PIP_PACKAGE-".[xformers]"}
-  fi
-fi
-
-# Variables shared by build.sh and run.sh
-REPOSITORY_NAME="${REPOSITORY_NAME-$(basename "$(git rev-parse --show-toplevel)")}"
-REPOSITORY_NAME="${REPOSITORY_NAME,,}"
-VOLUMENAME="${VOLUMENAME-"${REPOSITORY_NAME}_data"}"
-ARCH="${ARCH-$(uname -m)}"
-PLATFORM="${PLATFORM-linux/${ARCH}}"
-INVOKEAI_BRANCH="${INVOKEAI_BRANCH-$(git branch --show)}"
-CONTAINER_REGISTRY="${CONTAINER_REGISTRY-"ghcr.io"}"
-CONTAINER_REPOSITORY="${CONTAINER_REPOSITORY-"$(whoami)/${REPOSITORY_NAME}"}"
-CONTAINER_FLAVOR="${CONTAINER_FLAVOR-cuda}"
-CONTAINER_TAG="${CONTAINER_TAG-"${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}"}"
-CONTAINER_IMAGE="${CONTAINER_REGISTRY}/${CONTAINER_REPOSITORY}:${CONTAINER_TAG}"
-CONTAINER_IMAGE="${CONTAINER_IMAGE,,}"
-
-# enable docker buildkit
-export DOCKER_BUILDKIT=1

docker/run.sh

@@ -1,41 +1,8 @@
 #!/usr/bin/env bash
 set -e
 
-# How to use: https://invoke-ai.github.io/InvokeAI/installation/040_INSTALL_DOCKER/
-
 SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
 cd "$SCRIPTDIR" || exit 1
 
-source ./env.sh
-
-# Create outputs directory if it does not exist
-[[ -d ./outputs ]] || mkdir ./outputs
-
-echo -e "You are using these values:\n"
-echo -e "Volumename:\t${VOLUMENAME}"
-echo -e "Invokeai_tag:\t${CONTAINER_IMAGE}"
-echo -e "local Models:\t${MODELSPATH:-unset}\n"
-
-docker run \
-  --interactive \
-  --tty \
-  --rm \
-  --platform="${PLATFORM}" \
-  --name="${REPOSITORY_NAME}" \
-  --hostname="${REPOSITORY_NAME}" \
-  --mount type=volume,volume-driver=local,source="${VOLUMENAME}",target=/data \
-  --mount type=bind,source="$(pwd)"/outputs/,target=/data/outputs/ \
-  ${MODELSPATH:+--mount="type=bind,source=${MODELSPATH},target=/data/models"} \
-  ${HUGGING_FACE_HUB_TOKEN:+--env="HUGGING_FACE_HUB_TOKEN=${HUGGING_FACE_HUB_TOKEN}"} \
-  --publish=9090:9090 \
-  --cap-add=sys_nice \
-  ${GPU_FLAGS:+--gpus="${GPU_FLAGS}"} \
-  "${CONTAINER_IMAGE}" ${@:+$@}
-
-echo -e "\nCleaning trash folder ..."
-for f in outputs/.Trash*; do
-  if [ -e "$f" ]; then
-    rm -Rf "$f"
-    break
-  fi
-done
+docker-compose up --build -d
+docker-compose logs -f

docker/runpod-readme.md

@@ -0,0 +1,60 @@
+# InvokeAI - A Stable Diffusion Toolkit
+
+Stable Diffusion distribution by InvokeAI: https://github.com/invoke-ai
+
+The Docker image tracks the `main` branch of the InvokeAI project, which means it includes the latest features, but may contain some bugs.
+
+Your working directory is mounted under the `/workspace` path inside the pod. The models are in `/workspace/invokeai/models`, and outputs are in `/workspace/invokeai/outputs`.
+
+> **Only the /workspace directory will persist between pod restarts!**
+
+> **If you _terminate_ (not just _stop_) the pod, the /workspace will be lost.**
+
+## Quickstart
+
+1. Launch a pod from this template. **It will take about 5-10 minutes to run through the initial setup**. Be patient.
+1. Wait for the application to load.
+    - TIP: you know it's ready when the CPU usage goes idle
+    - You can also check the logs for a line that says "_Point your browser at..._"
+1. Open the Invoke AI web UI: click the `Connect` => `connect over  HTTP` button.
+1. Generate some art!
+
+## Other things you can do
+
+At any point you may edit the pod configuration and set an arbitrary Docker command. For example, you could run a command to downloads some models using `curl`, or fetch some images and place them into your outputs to continue a working session.
+
+If you need to run *multiple commands*, define them in the Docker Command field like this:
+
+`bash -c "cd ${INVOKEAI_ROOT}/outputs; wormhole receive 2-foo-bar; invoke.py --web --host 0.0.0.0"`
+
+### Copying your data in and out of the pod
+
+This image includes a couple of handy tools to help you get the data into the pod (such as your custom models or embeddings), and out of the pod (such as downloading your outputs). Here are your options for getting your data in and out of the pod:
+
+- **SSH server**:
+    1. Make sure to create and set your Public Key in the RunPod settings (follow the official instructions)
+    1. Add an exposed port 22 (TCP) in the pod settings!
+    1. When your pod restarts, you will see a new entry in the `Connect` dialog. Use this SSH server to `scp` or `sftp` your files as necessary, or SSH into the pod using the fully fledged SSH server.
+
+- [**Magic Wormhole**](https://magic-wormhole.readthedocs.io/en/latest/welcome.html):
+    1. On your computer, `pip install magic-wormhole` (see above instructions for details)
+    1. Connect to the command line **using the "light" SSH client** or the browser-based console. _Currently there's a bug where `wormhole` isn't available when connected to "full" SSH server, as described above_.
+    1. `wormhole send /workspace/invokeai/outputs` will send the entire `outputs` directory. You can also send individual files.
+    1. Once packaged, you will see a `wormhole receive <123-some-words>` command. Copy it
+    1. Paste this command into the terminal on your local machine to securely download the payload.
+    1. It works the same in reverse: you can `wormhole send` some models from your computer to the pod. Again, save your files somewhere in `/workspace` or they will be lost when the pod is stopped.
+
+- **RunPod's Cloud Sync feature** may be used to sync the persistent volume to cloud storage. You could, for example, copy the entire `/workspace` to S3, add some custom models to it, and copy it back from S3 when launching new pod configurations. Follow the Cloud Sync instructions.
+
+
+### Disable the NSFW checker
+
+The NSFW checker is enabled by default. To disable it, edit the pod configuration and set the following command:
+
+```
+invoke --web --host 0.0.0.0 --no-nsfw_checker
+```
+
+---
+
+Template ©2023 Eugene Brodsky [ebr](https://github.com/ebr)

docs/CHANGELOG.md

@@ -4,6 +4,236 @@ title: Changelog
 
 # :octicons-log-16: **Changelog**
 
+## v2.3.5 <small>(22 May 2023)</small>
+
+This release (along with the post1 and post2 follow-on releases) expands support for additional LoRA and LyCORIS models, upgrades diffusers versions, and fixes a few bugs.
+
+### LoRA and LyCORIS Support Improvement
+
+    A number of LoRA/LyCORIS fine-tune files (those which alter the text encoder as well as the unet model) were not having the desired effect in InvokeAI. This bug has now been fixed. Full documentation of LoRA support is available at InvokeAI LoRA Support.
+    Previously, InvokeAI did not distinguish between LoRA/LyCORIS models based on Stable Diffusion v1.5 vs those based on v2.0 and 2.1, leading to a crash when an incompatible model was loaded. This has now been fixed. In addition, the web pulldown menus for LoRA and Textual Inversion selection have been enhanced to show only those files that are compatible with the currently-selected Stable Diffusion model.
+    Support for the newer LoKR LyCORIS files has been added.
+
+### Library Updates and Speed/Reproducibility Advancements
+The major enhancement in this version is that NVIDIA users no longer need to decide between speed and reproducibility. Previously, if you activated the Xformers library, you would see improvements in speed and memory usage, but multiple images generated with the same seed and other parameters would be slightly different from each other. This is no longer the case. Relative to 2.3.5 you will see improved performance when running without Xformers, and even better performance when Xformers is activated. In both cases, images generated with the same settings will be identical.
+
+Here are the new library versions:
+Library 	Version
+Torch 	2.0.0
+Diffusers 	0.16.1
+Xformers 	0.0.19
+Compel 	1.1.5
+Other Improvements
+
+### Performance Improvements
+
+    When a model is loaded for the first time, InvokeAI calculates its checksum for incorporation into the PNG metadata. This process could take up to a minute on network-mounted disks and WSL mounts. This release noticeably speeds up the process.
+
+### Bug Fixes
+
+    The "import models from directory" and "import from URL" functionality in the console-based model installer has now been fixed.
+    When running the WebUI, we have reduced the number of times that InvokeAI reaches out to HuggingFace to fetch the list of embeddable Textual Inversion models. We have also caught and fixed a problem with the updater not correctly detecting when another instance of the updater is running 
+
+
+## v2.3.4 <small>(7 April 2023)</small>
+
+What's New in 2.3.4
+
+This features release adds support for LoRA (Low-Rank Adaptation) and LyCORIS (Lora beYond Conventional) models, as well as some minor bug fixes.
+### LoRA and LyCORIS Support
+
+LoRA files contain fine-tuning weights that enable particular styles, subjects or concepts to be applied to generated images. LyCORIS files are an extended variant of LoRA. InvokeAI supports the most common LoRA/LyCORIS format, which ends in the suffix .safetensors. You will find numerous LoRA and LyCORIS models for download at Civitai, and a small but growing number at Hugging Face. Full documentation of LoRA support is available at InvokeAI LoRA Support.( Pre-release note: this page will only be available after release)
+
+To use LoRA/LyCORIS models in InvokeAI:
+
+    Download the .safetensors files of your choice and place in /path/to/invokeai/loras. This directory was not present in earlier version of InvokeAI but will be created for you the first time you run the command-line or web client. You can also create the directory manually.
+
+    Add withLora(lora-file,weight) to your prompts. The weight is optional and will default to 1.0. A few examples, assuming that a LoRA file named loras/sushi.safetensors is present:
+
+family sitting at dinner table eating sushi withLora(sushi,0.9)
+family sitting at dinner table eating sushi withLora(sushi, 0.75)
+family sitting at dinner table eating sushi withLora(sushi)
+
+Multiple withLora() prompt fragments are allowed. The weight can be arbitrarily large, but the useful range is roughly 0.5 to 1.0. Higher weights make the LoRA's influence stronger. Negative weights are also allowed, which can lead to some interesting effects.
+
+    Generate as you usually would! If you find that the image is too "crisp" try reducing the overall CFG value or reducing individual LoRA weights. As is the case with all fine-tunes, you'll get the best results when running the LoRA on top of the model similar to, or identical with, the one that was used during the LoRA's training. Don't try to load a SD 1.x-trained LoRA into a SD 2.x model, and vice versa. This will trigger a non-fatal error message and generation will not proceed.
+
+    You can change the location of the loras directory by passing the --lora_directory option to `invokeai.
+
+### New WebUI LoRA and Textual Inversion Buttons
+
+This version adds two new web interface buttons for inserting LoRA and Textual Inversion triggers into the prompt as shown in the screenshot below.
+
+Clicking on one or the other of the buttons will bring up a menu of available LoRA/LyCORIS or Textual Inversion trigger terms. Select a menu item to insert the properly-formatted withLora() or <textual-inversion> prompt fragment into the positive prompt. The number in parentheses indicates the number of trigger terms currently in the prompt. You may click the button again and deselect the LoRA or trigger to remove it from the prompt, or simply edit the prompt directly.
+
+Currently terms are inserted into the positive prompt textbox only. However, some textual inversion embeddings are designed to be used with negative prompts. To move a textual inversion trigger into the negative prompt, simply cut and paste it.
+
+By default the Textual Inversion menu only shows locally installed models found at startup time in /path/to/invokeai/embeddings. However, InvokeAI has the ability to dynamically download and install additional Textual Inversion embeddings from the HuggingFace Concepts Library. You may choose to display the most popular of these (with five or more likes) in the Textual Inversion menu by going to Settings and turning on "Show Textual Inversions from HF Concepts Library." When this option is activated, the locally-installed TI embeddings will be shown first, followed by uninstalled terms from Hugging Face. See The Hugging Face Concepts Library and Importing Textual Inversion files for more information.
+### Minor features and fixes
+
+This release changes model switching behavior so that the command-line and Web UIs save the last model used and restore it the next time they are launched. It also improves the behavior of the installer so that the pip utility is kept up to date.
+  
+### Known Bugs in 2.3.4
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.3 <small>(28 March 2023)</small>
+
+This is a bugfix and minor feature release.
+### Bugfixes
+
+Since version 2.3.2 the following bugs have been fixed:
+Bugs
+
+    When using legacy checkpoints with an external VAE, the VAE file is now scanned for malware prior to loading. Previously only the main model weights file was scanned.
+    Textual inversion will select an appropriate batchsize based on whether xformers is active, and will default to xformers enabled if the library is detected.
+    The batch script log file names have been fixed to be compatible with Windows.
+    Occasional corruption of the .next_prefix file (which stores the next output file name in sequence) on Windows systems is now detected and corrected.
+    Support loading of legacy config files that have no personalization (textual inversion) section.
+    An infinite loop when opening the developer's console from within the invoke.sh script has been corrected.
+    Documentation fixes, including a recipe for detecting and fixing problems with the AMD GPU ROCm driver.
+
+Enhancements
+
+    It is now possible to load and run several community-contributed SD-2.0 based models, including the often-requested "Illuminati" model.
+    The "NegativePrompts" embedding file, and others like it, can now be loaded by placing it in the InvokeAI embeddings directory.
+    If no --model is specified at launch time, InvokeAI will remember the last model used and restore it the next time it is launched.
+    On Linux systems, the invoke.sh launcher now uses a prettier console-based interface. To take advantage of it, install the dialog package using your package manager (e.g. sudo apt install dialog).
+    When loading legacy models (safetensors/ckpt) you can specify a custom config file and/or a VAE by placing like-named files in the same directory as the model following this example:
+
+my-favorite-model.ckpt
+my-favorite-model.yaml
+my-favorite-model.vae.pt      # or my-favorite-model.vae.safetensors
+
+### Known Bugs in 2.3.3
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise Trojan or backdoor alerts for the codeformer.pth face restoration model, as well as the CIDAS/clipseg and runwayml/stable-diffusion-v1.5 models. These are false positives and can be safely ignored. InvokeAI performs a malware scan on all models as they are loaded. For additional security, you should use safetensors models whenever they are available.
+
+
+## v2.3.2 <small>(11 March 2023)</small>
+This is a bugfix and minor feature release.
+
+### Bugfixes
+
+Since version 2.3.1 the following bugs have been fixed:
+
+    Black images appearing for potential NSFW images when generating with legacy checkpoint models and both --no-nsfw_checker and --ckpt_convert turned on.
+    Black images appearing when generating from models fine-tuned on Stable-Diffusion-2-1-base. When importing V2-derived models, you may be asked to select whether the model was derived from a "base" model (512 pixels) or the 768-pixel SD-2.1 model.
+    The "Use All" button was not restoring the Hi-Res Fix setting on the WebUI
+    When using the model installer console app, models failed to import correctly when importing from directories with spaces in their names. A similar issue with the output directory was also fixed.
+    Crashes that occurred during model merging.
+    Restore previous naming of Stable Diffusion base and 768 models.
+    Upgraded to latest versions of diffusers, transformers, safetensors and accelerate libraries upstream. We hope that this will fix the assertion NDArray > 2**32 issue that MacOS users have had when generating images larger than 768x768 pixels. Please report back.
+
+As part of the upgrade to diffusers, the location of the diffusers-based models has changed from models/diffusers to models/hub. When you launch InvokeAI for the first time, it will prompt you to OK a one-time move. This should be quick and harmless, but if you have modified your models/diffusers directory in some way, for example using symlinks, you may wish to cancel the migration and make appropriate adjustments.
+New "Invokeai-batch" script
+
+### Invoke AI Batch
+2.3.2 introduces a new command-line only script called invokeai-batch that can be used to generate hundreds of images from prompts and settings that vary systematically. This can be used to try the same prompt across multiple combinations of models, steps, CFG settings and so forth. It also allows you to template prompts and generate a combinatorial list like:
+
+a shack in the mountains, photograph
+a shack in the mountains, watercolor
+a shack in the mountains, oil painting
+a chalet in the mountains, photograph
+a chalet in the mountains, watercolor
+a chalet in the mountains, oil painting
+a shack in the desert, photograph
+...
+
+If you have a system with multiple GPUs, or a single GPU with lots of VRAM, you can parallelize generation across the combinatorial set, reducing wait times and using your system's resources efficiently (make sure you have good GPU cooling).
+
+To try invokeai-batch out. Launch the "developer's console" using the invoke launcher script, or activate the invokeai virtual environment manually. From the console, give the command invokeai-batch --help in order to learn how the script works and create your first template file for dynamic prompt generation.
+
+
+### Known Bugs in 2.3.2
+
+These are known bugs in the release.
+
+    The Ancestral DPMSolverMultistepScheduler (k_dpmpp_2a) sampler is not yet implemented for diffusers models and will disappear from the WebUI Sampler menu when a diffusers model is selected.
+    Windows Defender will sometimes raise a Trojan alert for the codeformer.pth face restoration model. As far as we have been able to determine, this is a false positive and can be safely whitelisted.
+
+
+## v2.3.1 <small>(22 February 2023)</small>
+This is primarily a bugfix release, but it does provide several new features that will improve the user experience.
+
+### Enhanced support for model management
+
+InvokeAI now makes it convenient to add, remove and modify models. You can individually import models that are stored on your local system, scan an entire folder and its subfolders for models and import them automatically, and even directly import models from the internet by providing their download URLs. You also have the option of designating a local folder to scan for new models each time InvokeAI is restarted.
+
+There are three ways of accessing the model management features:
+
+    From the WebUI, click on the cube to the right of the model selection menu. This will bring up a form that allows you to import models individually from your local disk or scan a directory for models to import.
+
+    Using the Model Installer App
+
+Choose option (5) download and install models from the invoke launcher script to start a new console-based application for model management. You can use this to select from a curated set of starter models, or import checkpoint, safetensors, and diffusers models from a local disk or the internet. The example below shows importing two checkpoint URLs from popular SD sites and a HuggingFace diffusers model using its Repository ID. It also shows how to designate a folder to be scanned at startup time for new models to import.
+
+Command-line users can start this app using the command invokeai-model-install.
+
+    Using the Command Line Client (CLI)
+
+The !install_model and !convert_model commands have been enhanced to allow entering of URLs and local directories to scan and import. The first command installs .ckpt and .safetensors files as-is. The second one converts them into the faster diffusers format before installation.
+
+Internally InvokeAI is able to probe the contents of a .ckpt or .safetensors file to distinguish among v1.x, v2.x and inpainting models. This means that you do not need to include "inpaint" in your model names to use an inpainting model. Note that Stable Diffusion v2.x models will be autoconverted into a diffusers model the first time you use it.
+
+Please see INSTALLING MODELS for more information on model management.
+
+### An Improved Installer Experience
+
+The installer now launches a console-based UI for setting and changing commonly-used startup options:
+
+After selecting the desired options, the installer installs several support models needed by InvokeAI's face reconstruction and upscaling features and then launches the interface for selecting and installing models shown earlier. At any time, you can edit the startup options by launching invoke.sh/invoke.bat and entering option (6) change InvokeAI startup options
+
+Command-line users can launch the new configure app using invokeai-configure.
+
+This release also comes with a renewed updater. To do an update without going through a whole reinstallation, launch invoke.sh or invoke.bat and choose option (9) update InvokeAI . This will bring you to a screen that prompts you to update to the latest released version, to the most current development version, or any released or unreleased version you choose by selecting the tag or branch of the desired version.
+
+Command-line users can run this interface by typing invokeai-configure
+
+### Image Symmetry Options
+
+There are now features to generate horizontal and vertical symmetry during generation. The way these work is to wait until a selected step in the generation process and then to turn on a mirror image effect. In addition to generating some cool images, you can also use this to make side-by-side comparisons of how an image will look with more or fewer steps. Access this option from the WebUI by selecting Symmetry from the image generation settings, or within the CLI by using the options --h_symmetry_time_pct and --v_symmetry_time_pct (these can be abbreviated to --h_sym and --v_sym like all other options).
+
+### A New Unified Canvas Look
+
+This release introduces a beta version of the WebUI Unified Canvas. To try it out, open up the settings dialogue in the WebUI (gear icon) and select Use Canvas Beta Layout:
+
+Refresh the screen and go to to Unified Canvas (left side of screen, third icon from the top). The new layout is designed to provide more space to work in and to keep the image controls close to the image itself:
+
+Model conversion and merging within the WebUI
+
+The WebUI now has an intuitive interface for model merging, as well as for permanent conversion of models from legacy .ckpt/.safetensors formats into diffusers format. These options are also available directly from the invoke.sh/invoke.bat scripts.
+An easier way to contribute translations to the WebUI
+
+We have migrated our translation efforts to Weblate, a FOSS translation product. Maintaining the growing project's translations is now far simpler for the maintainers and community. Please review our brief translation guide for more information on how to contribute.
+Numerous internal bugfixes and performance issues
+
+### Bug Fixes
+This releases quashes multiple bugs that were reported in 2.3.0. Major internal changes include upgrading to diffusers 0.13.0, and using the compel library for prompt parsing. See Detailed Change Log for a detailed list of bugs caught and squished.
+Summary of InvokeAI command line scripts (all accessible via the launcher menu)
+Command 	Description
+invokeai 	Command line interface
+invokeai --web 	Web interface
+invokeai-model-install 	Model installer with console forms-based front end
+invokeai-ti --gui 	Textual inversion, with a console forms-based front end
+invokeai-merge --gui 	Model merging, with a console forms-based front end
+invokeai-configure 	Startup configuration; can also be used to reinstall support models
+invokeai-update 	InvokeAI software updater
+
+### Known Bugs in 2.3.1
+
+These are known bugs in the release.
+    MacOS users generating 768x768 pixel images or greater using diffusers models may experience a hard crash with assertion NDArray > 2**32 This appears to be an issu...
+
+
+
 ## v2.3.0 <small>(15 January 2023)</small>
 
 **Transition to diffusers
@@ -264,7 +494,7 @@ sections describe what's new for InvokeAI.
   [Manual Installation](installation/020_INSTALL_MANUAL.md).
 - The ability to save frequently-used startup options (model to load, steps,
   sampler, etc) in a `.invokeai` file. See
-  [Client](features/CLI.md)
+  [Client](deprecated/CLI.md)
 - Support for AMD GPU cards (non-CUDA) on Linux machines.
 - Multiple bugs and edge cases squashed.
 
@@ -387,7 +617,7 @@ sections describe what's new for InvokeAI.
 - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
   backward compatibility.
 - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
-- Support for [inpainting](features/INPAINTING.md) and
+- Support for [inpainting](deprecated/INPAINTING.md) and
   [outpainting](features/OUTPAINTING.md)
 - img2img runs on all k\* samplers
 - Support for
@@ -399,7 +629,7 @@ sections describe what's new for InvokeAI.
   using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
   infinite canvas), and "embiggen" upscaling. See the `!fix` command.
 - New `--hires` option on `invoke>` line allows
-  [larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img),
+  [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
   at the cost of some performance.
 - New `--perlin` and `--threshold` options allow you to add and control
   variation during image generation (see
@@ -408,7 +638,7 @@ sections describe what's new for InvokeAI.
   of images and tweaking of previous settings.
 - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
   platforms.
-- Improved [command-line completion behavior](features/CLI.md) New commands
+- Improved [command-line completion behavior](deprecated/CLI.md) New commands
   added:
   - List command-line history with `!history`
   - Search command-line history with `!search`

docs/contributing/CONTRIBUTING.md

@@ -0,0 +1,54 @@
+## Welcome to Invoke AI
+
+We're thrilled to have you here and we're excited for you to contribute. 
+
+Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
+
+Here are some guidelines to help you get started:
+
+### Technical Prerequisites
+
+Front-end: You'll need a working knowledge of React and TypeScript.
+
+Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
+
+### How to Submit Contributions
+
+To start contributing, please follow these steps:
+
+1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
+2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
+3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
+
+### Types of Contributions We're Looking For
+
+We welcome all contributions that improve the project. Right now, we're especially looking for:
+
+1. Quality of life (QOL) enhancements on the front-end.
+2. New backend capabilities added through nodes.
+3. Incorporating additional optimizations from the broader open-source software community.
+
+### Communication and Decision-making Process
+
+Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
+
+For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
+
+### Code of Conduct and Contribution Expectations
+
+We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
+
+By making a contribution to this project, you certify that:
+
+1. The contribution was created in whole or in part by you and you have the right to submit it under the open-source license indicated in this project’s GitHub repository; or
+2. The contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open-source license and you have the right under that license to submit that work with modifications, whether created in whole or in part by you, under the same open-source license (unless you are permitted to submit under a different license); or
+3. The contribution was provided directly to you by some other person who certified (1) or (2) and you have not modified it; or
+4. You understand and agree that this project and the contribution are public and that a record of the contribution (including all personal information you submit with it, including your sign-off) is maintained indefinitely and may be redistributed consistent with this project or the open-source license(s) involved.
+
+This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
+
+This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
+
+---
+
+Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/contributing/INVOCATIONS.md

@@ -1,8 +1,521 @@
 # Invocations
 
-Invocations represent a single operation, its inputs, and its outputs. These
-operations and their outputs can be chained together to generate and modify
-images.
+Features in InvokeAI are added in the form of modular node-like systems called
+**Invocations**.
+
+An Invocation is simply a single operation that takes in some inputs and gives
+out some outputs. We can then chain multiple Invocations together to create more
+complex functionality.
+
+## Invocations Directory
+
+InvokeAI Invocations can be found in the `invokeai/app/invocations` directory.
+
+You can add your new functionality to one of the existing Invocations in this
+directory or create a new file in this directory as per your needs.
+
+**Note:** _All Invocations must be inside this directory for InvokeAI to
+recognize them as valid Invocations._
+
+## Creating A New Invocation
+
+In order to understand the process of creating a new Invocation, let us actually
+create one.
+
+In our example, let us create an Invocation that will take in an image, resize
+it and output the resized image.
+
+The first set of things we need to do when creating a new Invocation are -
+
+- Create a new class that derives from a predefined parent class called
+  `BaseInvocation`.
+- The name of every Invocation must end with the word `Invocation` in order for
+  it to be recognized as an Invocation.
+- Every Invocation must have a `docstring` that describes what this Invocation
+  does.
+- Every Invocation must have a unique `type` field defined which becomes its
+  indentifier.
+- Invocations are strictly typed. We make use of the native
+  [typing](https://docs.python.org/3/library/typing.html) library and the
+  installed [pydantic](https://pydantic-docs.helpmanual.io/) library for
+  validation.
+
+So let us do that.
+
+```python
+from typing import Literal
+from .baseinvocation import BaseInvocation
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+```
+
+That's great.
+
+Now we have setup the base of our new Invocation. Let us think about what inputs
+our Invocation takes.
+
+- We need an `image` that we are going to resize.
+- We will need new `width` and `height` values to which we need to resize the
+  image to.
+
+### **Inputs**
+
+Every Invocation input is a pydantic `Field` and like everything else should be
+strictly typed and defined.
+
+So let us create these inputs for our Invocation. First up, the `image` input we
+need. Generally, we can use standard variable types in Python but InvokeAI
+already has a custom `ImageField` type that handles all the stuff that is needed
+for image inputs.
+
+But what is this `ImageField` ..? It is a special class type specifically
+written to handle how images are dealt with in InvokeAI. We will cover how to
+create your own custom field types later in this guide. For now, let's go ahead
+and use it.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation
+from ..models.image import ImageField
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+```
+
+Let us break down our input code.
+
+```python
+image: Union[ImageField, None] = Field(description="The input image", default=None)
+```
+
+| Part      | Value                                                | Description                                                                                        |
+| --------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
+| Name      | `image`                                              | The variable that will hold our image                                                              |
+| Type Hint | `Union[ImageField, None]`                            | The types for our field. Indicates that the image can either be an `ImageField` type or `None`     |
+| Field     | `Field(description="The input image", default=None)` | The image variable is a field which needs a description and a default value that we set to `None`. |
+
+Great. Now let us create our other inputs for `width` and `height`
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation
+from ..models.image import ImageField
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
+```
+
+As you might have noticed, we added two new parameters to the field type for
+`width` and `height` called `gt` and `le`. These basically stand for _greater
+than or equal to_ and _less than or equal to_. There are various other param
+types for field that you can find on the **pydantic** documentation.
+
+**Note:** _Any time it is possible to define constraints for our field, we
+should do it so the frontend has more information on how to parse this field._
+
+Perfect. We now have our inputs. Let us do something with these.
+
+### **Invoke Function**
+
+The `invoke` function is where all the magic happens. This function provides you
+the `context` parameter that is of the type `InvocationContext` which will give
+you access to the current context of the generation and all the other services
+that are provided by it by InvokeAI.
+
+Let us create this function first.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
+
+    def invoke(self, context: InvocationContext):
+        pass
+```
+
+### **Outputs**
+
+The output of our Invocation will be whatever is returned by this `invoke`
+function. Like with our inputs, we need to strongly type and define our outputs
+too.
+
+What is our output going to be? Another image. Normally you'd have to create a
+type for this but InvokeAI already offers you an `ImageOutput` type that handles
+all the necessary info related to image outputs. So let us use that.
+
+We will cover how to create your own output types later in this guide.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField
+from .image import ImageOutput
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        pass
+```
+
+Perfect. Now that we have our Invocation setup, let us do what we want to do.
+
+- We will first load the image. Generally we do this using the `PIL` library but
+  we can use one of the services provided by InvokeAI to load the image.
+- We will resize the image using `PIL` to our input data.
+- We will output this image in the format we set above.
+
+So let's do that.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField, ResourceOrigin, ImageCategory
+from .image import ImageOutput
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(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.
+        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
+
+        # Resizing the image
+        # Because we used the above service, we already have a PIL image. So we can simply resize.
+        resized_image = image.resize((self.width, self.height))
+
+        # Preparing the image for output using InvokeAI's predefined Image Service.
+        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,
+        )
+
+        # Returning the Image
+        return ImageOutput(
+            image=ImageField(
+                image_name=output_image.image_name,
+                image_origin=output_image.image_origin,
+            ),
+            width=output_image.width,
+            height=output_image.height,
+        )
+```
+
+**Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
+certain way that the images need to be dispatched in order to be stored and read
+correctly. In 99% of the cases when dealing with an image output, you can simply
+copy-paste the template above.
+
+That's it. You made your own **Resize Invocation**.
+
+## Result
+
+Once you make your Invocation correctly, the rest of the process is fully
+automated for you.
+
+When you launch InvokeAI, you can go to `http://localhost:9090/docs` and see
+your new Invocation show up there with all the relevant info.
+
+![resize invocation](../assets/contributing/resize_invocation.png)
+
+When you launch the frontend UI, you can go to the Node Editor tab and find your
+new Invocation ready to be used.
+
+![resize node editor](../assets/contributing/resize_node_editor.png)
+
+# Advanced
+
+## 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.
+
+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**
+
+- 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.
+- Keep your field in the same file as the Invocation that it is made for or in
+  another file where it is relevant.
+
+All input types a class that derive from the `BaseModel` type from `pydantic`.
+So let's create one.
+
+```python
+from pydantic import BaseModel
+
+class ColorField(BaseModel):
+    '''A field that holds the rgba values of a color'''
+    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.
+
+```python
+class ColorField(BaseModel):
+    '''A field that holds the rgba values of a color'''
+    r: int = Field(ge=0, le=255, description="The red channel")
+    g: int = Field(ge=0, le=255, description="The green channel")
+    b: int = Field(ge=0, le=255, description="The blue channel")
+    a: int = Field(ge=0, le=255, description="The alpha channel")
+```
+
+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')
+```
+
+**Extra Config**
+
+All input fields also take an additional `Config` class that you can use to do
+various advanced things like setting required parameters and etc.
+
+Let us do that for our _ColorField_ and enforce all the values because we did
+not define any defaults for our fields.
+
+```python
+class ColorField(BaseModel):
+    '''A field that holds the rgba values of a color'''
+    r: int = Field(ge=0, le=255, description="The red channel")
+    g: int = Field(ge=0, le=255, description="The green channel")
+    b: int = Field(ge=0, le=255, description="The blue channel")
+    a: int = Field(ge=0, le=255, description="The alpha channel")
+
+    class Config:
+        schema_extra = {"required": ["r", "g", "b", "a"]}
+```
+
+Now it becomes mandatory for the user to supply all the values required by our
+input field.
+
+We will discuss the `Config` class in extra detail later in this guide and how
+you can use it to make your Invocations more robust.
+
+## Custom Output Types
+
+Like with custom inputs, sometimes you might find yourself needing custom
+outputs that InvokeAI does not provide. We can easily set one up.
+
+Now that you are familiar with Invocations and Inputs, let us use that knowledge
+to put together a custom output type for an Invocation that returns _width_,
+_height_ and _background_color_ that we need to create a blank image.
+
+- A custom output type is a class that derives from the parent class of
+  `BaseInvocationOutput`.
+- It is not mandatory but we recommend using names ending with `Output` for
+  output types. So we'll call our class `BlankImageOutput`
+- It is not mandatory but we highly recommend adding a `docstring` to describe
+  what your output type is for.
+- Like Invocations, each output type should have a `type` variable that is
+  **unique**
+
+Now that we know the basic rules for creating a new output type, let us go ahead
+and make it.
+
+```python
+from typing import Literal
+from pydantic import Field
+
+from .baseinvocation import BaseInvocationOutput
+
+class BlankImageOutput(BaseInvocationOutput):
+    '''Base output type for creating a blank image'''
+    type: Literal['blank_image_output'] = 'blank_image_output'
+
+    # Inputs
+    width: int = Field(description='Width of blank image')
+    height: int = Field(description='Height of blank image')
+    bg_color: ColorField = Field(description='Background color of blank image')
+
+    class Config:
+        schema_extra = {"required": ["type", "width", "height", "bg_color"]}
+```
+
+All set. We now have an output type that requires what we need to create a
+blank_image. And if you noticed it, we even used the `Config` class to ensure
+the fields are required.
+
+## Custom Configuration
+
+As you might have noticed when making inputs and outputs, we used a class called
+`Config` from _pydantic_ to further customize them. Because our inputs and
+outputs essentially inherit from _pydantic_'s `BaseModel` class, all
+[configuration options](https://docs.pydantic.dev/latest/usage/schema/#schema-customization)
+that are valid for _pydantic_ classes are also valid for our inputs and outputs.
+You can do the same for your Invocations too but InvokeAI makes our life a
+little bit easier on that end.
+
+InvokeAI provides a custom configuration class called `InvocationConfig`
+particularly for configuring Invocations. This is exactly the same as the raw
+`Config` class from _pydantic_ with some extra stuff on top to help faciliate
+parsing of the scheme in the frontend UI.
+
+At the current moment, tihs `InvocationConfig` class is further improved with
+the following features related the `ui`.
+
+| Config Option | Field Type                                                                                                    | Example                                                                                                               |
+| ------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
+| type_hints    | `Dict[str, Literal["integer", "float", "boolean", "string", "enum", "image", "latents", "model", "control"]]` | `type_hint: "model"` provides type hints related to the model like displaying a list of available models              |
+| tags          | `List[str]`                                                                                                   | `tags: ['resize', 'image']` will classify your invocation under the tags of resize and image.                         |
+| title         | `str`                                                                                                         | `title: 'Resize Image` will rename your to this custom title rather than infer from the name of the Invocation class. |
+
+So let us update your `ResizeInvocation` with some extra configuration and see
+how that works.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from ..models.image import ImageField, ResourceOrigin, ImageCategory
+from .image import ImageOutput
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
+
+    class Config(InvocationConfig):
+        schema_extra: {
+            ui: {
+                tags: ['resize', 'image'],
+                title: ['My Custom Resize']
+            }
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Load the image using InvokeAI's predefined Image Service.
+        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
+
+        # Resizing the image
+        # Because we used the above service, we already have a PIL image. So we can simply resize.
+        resized_image = image.resize((self.width, self.height))
+
+        # Preparing the image for output using InvokeAI's predefined Image Service.
+        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,
+        )
+
+        # Returning the Image
+        return ImageOutput(
+            image=ImageField(
+                image_name=output_image.image_name,
+                image_origin=output_image.image_origin,
+            ),
+            width=output_image.width,
+            height=output_image.height,
+        )
+```
+
+We now customized our code to let the frontend know that our Invocation falls
+under `resize` and `image` categories. So when the user searches for these
+particular words, our Invocation will show up too.
+
+We also set a custom title for our Invocation. So instead of being called
+`Resize`, it will be called `My Custom Resize`.
+
+As simple as that.
+
+As time goes by, InvokeAI will further improve and add more customizability for
+Invocation configuration. We will have more documentation regarding this at a
+later time.
+
+# **[TODO]**
+
+## Custom Components For Frontend
+
+Every backend input type should have a corresponding frontend component so the
+UI knows what to render when you use a particular field type.
+
+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.
+
+---
+
+# OLD -- TO BE DELETED OR MOVED LATER
+
+---
 
 ## Creating a new invocation
 
@@ -19,31 +532,56 @@ An invocation looks like this:
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-    type: Literal['upscale'] = 'upscale'
+
+    # fmt: off
+    type: Literal["upscale"] = "upscale"
 
     # Inputs
-    image: Union[ImageField,None] = Field(description="The input image")
-    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
-    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    strength: float                = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2, 4]           = Field(default=2, description="The upscale level")
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(self.image.image_type, self.image.image_name)
-        results = context.services.generate.upscale_and_reconstruct(
-            image_list     = [[image, 0]],
-            upscale        = (self.level, self.strength),
-            strength       = 0.0, # GFPGAN strength
-            save_original  = False,
-            image_callback = None,
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
         )
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
-        context.services.images.save(image_type, image_name, results[0][0])
-        return ImageOutput(
-            image = ImageField(image_type = image_type, image_name = image_name)
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
         )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
 ```
 
 Each portion is important to implement correctly.
@@ -95,25 +633,67 @@ Finally, note that for all linking, the `type` of the linked fields must match.
 If the `name` also matches, then the field can be **automatically linked** to a
 previous invocation by name and matching.
 
+### Config
+
+```py
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
+```
+
+This is an optional configuration for the invocation. It inherits from
+pydantic's model `Config` class, and it used primarily to customize the
+autogenerated OpenAPI schema.
+
+The UI relies on the OpenAPI schema in two ways:
+
+- An API client & Typescript types are generated from it. This happens at build
+  time.
+- The node editor parses the schema into a template used by the UI to create the
+  node editor UI. This parsing happens at runtime.
+
+In this example, a `ui` key has been added to the `schema_extra` dict to provide
+some tags for the UI, to facilitate filtering nodes.
+
+See the Schema Generation section below for more information.
+
 ### Invoke Function
 
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(self.image.image_type, self.image.image_name)
-        results = context.services.generate.upscale_and_reconstruct(
-            image_list     = [[image, 0]],
-            upscale        = (self.level, self.strength),
-            strength       = 0.0, # GFPGAN strength
-            save_original  = False,
-            image_callback = None,
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
         )
 
         # Results are image and seed, unwrap for now
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
-        context.services.images.save(image_type, image_name, results[0][0])
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
         return ImageOutput(
-            image = ImageField(image_type = image_type, image_name = image_name)
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 ```
 
@@ -135,9 +715,16 @@ scenarios. If you need functionality, please provide it as a service in the
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
-    type: Literal['image'] = 'image'
 
-    image: ImageField = Field(default=None, description="The output image")
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
 ```
 
 Output classes look like an invocation class without the invoke method. Prefer
@@ -168,35 +755,36 @@ Here's that `ImageOutput` class, without the needed schema customisation:
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
-    type: Literal["image"] = "image"
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
     image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
 ```
 
-The generated OpenAPI schema, and all clients/types generated from it, will have
-the `type` and `image` properties marked as optional, even though we know they
-will always have a value by the time we can interact with them via the API.
-
-Here's the same class, but with the schema customisation added:
+The OpenAPI schema that results from this `ImageOutput` will have the `type`,
+`image`, `width` and `height` properties marked as optional, even though we know
+they will always have a value.
 
 ```python
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
-    type: Literal["image"] = "image"
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
     image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
 
+    # Add schema customization
     class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
-        }
+        schema_extra = {"required": ["type", "image", "width", "height"]}
 ```
 
-The resultant schema (and any API client or types generated from it) will now
-have see `type` as string literal `"image"` and `image` as an `ImageField`
-object.
+With the customization in place, the schema will now show these properties as
+required, obviating the need for extensive null checks in client code.
 
 See this `pydantic` issue for discussion on this solution:
 <https://github.com/pydantic/pydantic/discussions/4577>

docs/deprecated/CLI.md

@@ -0,0 +1,589 @@
+---
+title: Command-Line Interface
+---
+
+# :material-bash: CLI
+
+## **Interactive Command Line Interface**
+
+The InvokeAI command line interface (CLI) provides scriptable access
+to InvokeAI's features.Some advanced features are only available
+through the CLI, though they eventually find their way into the WebUI.
+
+The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
+selecting option (1). Alternatively, it can be launched directly from
+the command line by activating the InvokeAI environment and giving the
+command:
+
+```bash
+invokeai
+```
+
+After some startup messages, you will be presented with the `invoke> `
+prompt. Here you can type prompts to generate images and issue other
+commands to load and manipulate generative models. The CLI has a large
+number of command-line options that control its behavior. To get a
+concise summary of the options, call `invokeai` with the `--help` argument:
+
+```bash
+invokeai --help
+```
+
+The script uses the readline library to allow for in-line editing, command
+history (++up++ and ++down++), autocompletion, and more. To help keep track of
+which prompts generated which images, the script writes a log file of image
+names and prompts to the selected output directory.
+
+Here is a typical session
+
+```bash
+PS1:C:\Users\fred> invokeai
+* Initializing, be patient...
+* Initializing, be patient...
+>> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
+>> Internet connectivity is True
+>> InvokeAI, version 2.3.0-rc5
+>> InvokeAI runtime directory is "/home/lstein/invokeai"
+>> GFPGAN Initialized
+>> CodeFormer Initialized
+>> ESRGAN Initialized
+>> Using device_type cuda
+>> xformers memory-efficient attention is available and enabled
+     (...more initialization messages...)
+* Initialization done! Awaiting your command (-h for help, 'q' to quit)
+invoke> ashley judd riding a camel -n2 -s150
+Outputs:
+   outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
+   outputs/img-samples/00010.png: "ashley judd riding a camel" -n2 -s150 -S 1362479620
+
+invoke> "there's a fly in my soup" -n6 -g
+    outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
+    seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
+invoke> q
+```
+
+![invoke-py-demo](../assets/dream-py-demo.png)
+
+## Arguments
+
+The script recognizes a series of command-line switches that will
+change important global defaults, such as the directory for image
+outputs and the location of the model weight files.
+
+### List of arguments recognized at the command line
+
+These command-line arguments can be passed to `invoke.py` when you first run it
+from the Windows, Mac or Linux command line. Some set defaults that can be
+overridden on a per-prompt basis (see
+[List of prompt arguments](#list-of-prompt-arguments). Others
+
+| Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/>       | Description                                                                                          |
+| ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
+| `--help`                                  | `-h`                                      |                                                | Print a concise help message.                                                                        |
+| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                          | Location for generated images.                                                                       |
+| `--prompt_as_dir`                         | `-p`                                      | `False`                                        | Name output directories using the prompt text.                                                       |
+| `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
+| `--model <modelname>`                     |                                           | `stable-diffusion-1.5`                         | Loads the initial model specified in configs/models.yaml. |
+| `--ckpt_convert `           |                                                         | `False`                                        | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
+| `--autoconvert <path>`                    |                          | `None`                                        | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
+| `--precision`                             |                                           | `fp16`                                         | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
+| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                            | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
+| `--safety-checker`                        |                                           | `False`                                        | Activate safety checker for NSFW and other potentially disturbing imagery                            |
+| `--patchmatch`, `--no-patchmatch`                 |                                   | `--patchmatch`                                        | Load/Don't load the PatchMatch inpainting extension    |
+| `--xformers`, `--no-xformers`                 |                                   | `--xformers`                                        | Load/Don't load the Xformers memory-efficient attention module (CUDA only)    |
+| `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
+| `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
+| `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
+| `--config <path>`                         |                                           | `configs/models.yaml`                          | Configuration file for models and their weights.                                                     |
+| `--iterations <int>`                      | `-n<int>`                                 | `1`                                            | How many images to generate per prompt.                                                              |
+| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
+| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                        | `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
+| `--strength <float>`                      | `-s<float>` | `0.75`  | For img2img: how hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
+| `--fit`                                   | `-F`        | `False` | For img2img: scale the init image to fit into the specified -H and -W dimensions                                                                             |
+| `--grid`                                  | `-g`                                      | `False`                                        | Save all image series as a grid rather than individually.                                            |
+| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                        | Sampler to use. Use `-h` to get list of available samplers.                                          |
+| `--seamless`                              |                                           | `False`                                        | Create interesting effects by tiling elements of the image.                                          |
+| `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
+| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file.                                              |
+| `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
+| `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
+
+!!! warning "These arguments are deprecated but still work"
+
+    <div align="center" markdown>
+
+    | Argument           |  Shortcut  |  Default            |  Description |
+    |--------------------|------------|---------------------|--------------|
+    | `--full_precision`  |             | `False`                | Same as `--precision=fp32`|
+    | `--weights <path>`   |            | `None`                | Path to weights file; use `--model stable-diffusion-1.4` instead |
+    | `--laion400m`        | `-l`         | `False`               | Use older LAION400m weights; use `--model=laion400m` instead |
+
+    </div>
+
+!!! tip
+
+      On Windows systems, you may run into
+      problems when passing the invoke script standard backslashed path
+      names because the Python interpreter treats "\" as an escape.
+      You can either double your slashes (ick): `C:\\path\\to\\my\\file`, or
+      use Linux/Mac style forward slashes (better): `C:/path/to/my/file`.
+
+## The .invokeai initialization file
+
+To start up invoke.py with your preferred settings, place your desired
+startup options in a file in your home directory named `.invokeai` The
+file should contain the startup options as you would type them on the
+command line (`--steps=10 --grid`), one argument per line, or a
+mixture of both using any of the accepted command switch formats:
+
+!!! example "my unmodified initialization file"
+
+    ```bash title="~/.invokeai" linenums="1"
+    # InvokeAI initialization file
+    # This is the InvokeAI initialization file, which contains command-line default values.
+    # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
+    # or renaming it and then running invokeai-configure again.
+
+    # The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
+    --root="/Users/mauwii/invokeai"
+
+    # the --outdir option controls the default location of image files.
+    --outdir="/Users/mauwii/invokeai/outputs"
+
+    # You may place other  frequently-used startup commands here, one or more per line.
+    # Examples:
+    # --web --host=0.0.0.0
+    # --steps=20
+    # -Ak_euler_a -C10.0
+    ```
+
+!!! note
+
+    The  initialization file only accepts the command line arguments.
+    There are additional arguments that you can provide on the `invoke>` command
+    line (such as `-n` or `--iterations`) that cannot be entered into this file.
+    Also be alert for empty blank lines at the end of the file, which will cause
+    an arguments error at startup time.
+
+## List of prompt arguments
+
+After the invoke.py script initializes, it will present you with a `invoke>`
+prompt. Here you can enter information to generate images from text
+([txt2img](#txt2img)), to embellish an existing image or sketch
+([img2img](#img2img)), or to selectively alter chosen regions of the image
+([inpainting](#inpainting)).
+
+### txt2img
+
+!!! example ""
+
+    ```bash
+    invoke> waterfall and rainbow -W640 -H480
+    ```
+
+    This will create the requested image with the dimensions 640 (width)
+    and 480 (height).
+
+Here are the invoke> command that apply to txt2img:
+
+| Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description                                                                                                                                                                                                                                      |
+| ----------------------------------------- | ----------------------------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| "my prompt"                               |                                           |                                          | Text prompt to use. The quotation marks are optional.                                                                                                                                                                                            |
+| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
+| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                                                                                                                                        |
+| `--iterations <int>`                      | `-n<int>`                                 | `1`                                      | How many images to generate from this prompt                                                                                                                                                                                                     |
+| `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
+| `--cfg_scale <float>`                     | `-C<float>`                               | `7.5`                                    | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0                                                                                                       |
+| `--seed <int>`                            | `-S<int>`                                 | `None`                                   | Set the random seed for the next series of images. This can be used to recreate an image generated previously.                                                                                                                                   |
+| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                  | Sampler to use. Use -h to get list of available samplers.                                                                                                                                                                                        |
+| `--karras_max <int>`                      |                                           | `29`                                     | When using k\_\* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29]          |
+| `--hires_fix`                             |                                           |                                          | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution                                                                          |
+| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                      | Select level of compression for output files, from 0 (no compression) to 9 (max compression)                                                                                                                                                     |
+| `--grid`                                  | `-g`                                      | `False`                                  | Turn on grid mode to return a single image combining all the images generated by this prompt                                                                                                                                                     |
+| `--individual`                            | `-i`                                      | `True`                                   | Turn off grid mode (deprecated; leave off --grid instead)                                                                                                                                                                                        |
+| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                    | Temporarily change the location of these images                                                                                                                                                                                                  |
+| `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
+| `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
+| `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
+| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/OTHER.md#weighted-prompts)                                                                                                                                                  |
+| `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
+| `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
+| `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
+| `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
+| `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
+| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
+| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this.                                                                                                                                                           |
+| `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
+| `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
+| `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
+
+!!! note
+
+    the width and height of the image must be multiples of 64. You can
+    provide different values, but they will be rounded down to the nearest multiple
+    of 64.
+
+!!! example "This is a example of img2img"
+
+    ```bash
+    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
+    ```
+
+This will modify the indicated vacation photograph by making it more like the
+prompt. Results will vary greatly depending on what is in the image. We also ask
+to --fit the image into a box no bigger than 640x480. Otherwise the image size
+will be identical to the provided photo and you may run out of memory if it is
+large.
+
+In addition to the command-line options recognized by txt2img, img2img accepts
+additional options:
+
+| Argument <img width="160" align="right"/> | Shortcut    | Default | Description                                                                                                                                |
+| ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| `--init_img <path>`                       | `-I<path>`  | `None`  | Path to the initialization image                                                                                                           |
+| `--fit`                                   | `-F`        | `False` | Scale the image to fit into the specified -H and -W dimensions                                                                             |
+| `--strength <float>`                      | `-s<float>` | `0.75`  | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
+
+### inpainting
+
+!!! example ""
+
+    ```bash
+    invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
+    ```
+
+    This will do the same thing as img2img, but image alterations will
+    only occur within transparent areas defined by the mask file specified
+    by `-M`. You may also supply just a single initial image with the areas
+    to overpaint made transparent, but you must be careful not to destroy
+    the pixels underneath when you create the transparent areas. See
+    [Inpainting](INPAINTING.md) for details.
+
+inpainting accepts all the arguments used for txt2img and img2img, as well as
+the --mask (-M) and --text_mask (-tm) arguments:
+
+| Argument <img width="100" align="right"/> | Shortcut                 | Default | Description                                                                                      |
+| ----------------------------------------- | ------------------------ | ------- | ------------------------------------------------------------------------------------------------ |
+| `--init_mask <path>`                      | `-M<path>`               | `None`  | Path to an image the same size as the initial_image, with areas for inpainting made transparent. |
+| `--invert_mask `                          |                          | False   | If true, invert the mask so that transparent areas are opaque and vice versa.                    |
+| `--text_mask <prompt> [<float>]`          | `-tm <prompt> [<float>]` | <none>  | Create a mask from a text prompt describing part of the image                                    |
+
+The mask may either be an image with transparent areas, in which case the
+inpainting will occur in the transparent areas only, or a black and white image,
+in which case all black areas will be painted into.
+
+`--text_mask` (short form `-tm`) is a way to generate a mask using a text
+description of the part of the image to replace. For example, if you have an
+image of a breakfast plate with a bagel, toast and scrambled eggs, you can
+selectively mask the bagel and replace it with a piece of cake this way:
+
+```bash
+invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
+```
+
+The algorithm uses <a
+href="https://github.com/timojl/clipseg">clipseg</a> to classify different
+regions of the image. The classifier puts out a confidence score for each region
+it identifies. Generally regions that score above 0.5 are reliable, but if you
+are getting too much or too little masking you can adjust the threshold down (to
+get more mask), or up (to get less). In this example, by passing `-tm` a higher
+value, we are insisting on a more stringent classification.
+
+```bash
+invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
+```
+
+### Custom Styles and Subjects
+
+You can load and use hundreds of community-contributed Textual
+Inversion models just by typing the appropriate trigger phrase. Please
+see [Concepts Library](../features/CONCEPTS.md) for more details.
+
+## Other Commands
+
+The CLI offers a number of commands that begin with "!".
+
+### Postprocessing images
+
+To postprocess a file using face restoration or upscaling, use the `!fix`
+command.
+
+#### `!fix`
+
+This command runs a post-processor on a previously-generated image. It takes a
+PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
+switches in order to fix faces or upscale. If you provide a filename, the script
+will look for it in the current output directory. Otherwise you can provide a
+full or partial path to the desired file.
+
+Some examples:
+
+!!! example "Upscale to 4X its original size and fix faces using codeformer"
+
+    ```bash
+    invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
+    ```
+
+!!! example "Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen"
+
+    ```bash
+    invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
+    >> fixing outputs/img-samples/0000045.4829112.png
+    >> retrieved seed 4829112 and prompt "boy enjoying a banana split"
+    >> GFPGAN - Restoring Faces for image seed:4829112
+    Outputs:
+    [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
+    ```
+
+#### `!mask`
+
+This command takes an image, a text prompt, and uses the `clipseg` algorithm to
+automatically generate a mask of the area that matches the text prompt. It is
+useful for debugging the text masking process prior to inpainting with the
+`--text_mask` argument. See [INPAINTING.md] for details.
+
+### Model selection and importation
+
+The CLI allows you to add new models on the fly, as well as to switch
+among them rapidly without leaving the script. There are several
+different model formats, each described in the [Model Installation
+Guide](../installation/050_INSTALLING_MODELS.md).
+
+#### `!models`
+
+This prints out a list of the models defined in `config/models.yaml'. The active
+model is bold-faced
+
+Example:
+
+<pre>
+inpainting-1.5            not loaded  Stable Diffusion inpainting model
+<b>stable-diffusion-1.5          active  Stable Diffusion v1.5</b>
+waifu-diffusion           not loaded  Waifu Diffusion v1.4
+</pre>
+
+#### `!switch <model>`
+
+This quickly switches from one model to another without leaving the CLI script.
+`invoke.py` uses a memory caching system; once a model has been loaded,
+switching back and forth is quick. The following example shows this in action.
+Note how the second column of the `!models` table changes to `cached` after a
+model is first loaded, and that the long initialization step is not needed when
+loading a cached model.
+
+#### `!import_model <hugging_face_repo_ID>`
+
+This imports and installs a `diffusers`-style model that is stored on
+the [HuggingFace Web Site](https://huggingface.co). You can look up
+any [Stable Diffusion diffusers
+model](https://huggingface.co/models?library=diffusers) and install it
+with a command like the following:
+
+```bash
+!import_model prompthero/openjourney
+```
+
+#### `!import_model <path/to/diffusers/directory>`
+
+If you have a copy of a `diffusers`-style model saved to disk, you can
+import it by passing the path to model's top-level directory.
+
+#### `!import_model <url>`
+
+For a `.ckpt` or `.safetensors` file, if you have a direct download
+URL for the file, you can provide it to `!import_model` and the file
+will be downloaded and installed for you.
+
+#### `!import_model <path/to/model/weights.ckpt>`
+
+This command imports a new model weights file into InvokeAI, makes it available
+for image generation within the script, and writes out the configuration for the
+model into `config/models.yaml` for use in subsequent sessions.
+
+Provide `!import_model` with the path to a weights file ending in `.ckpt`. If
+you type a partial path and press tab, the CLI will autocomplete. Although it
+will also autocomplete to `.vae` files, these are not currenty supported (but
+will be soon).
+
+When you hit return, the CLI will prompt you to fill in additional information
+about the model, including the short name you wish to use for it with the
+`!switch` command, a brief description of the model, the default image width and
+height to use with this model, and the model's configuration file. The latter
+three fields are automatically filled with reasonable defaults. In the example
+below, the bold-faced text shows what the user typed in with the exception of
+the width, height and configuration file paths, which were filled in
+automatically.
+
+#### `!import_model <path/to/directory_of_models>`
+
+If you provide the path of a directory that contains one or more
+`.ckpt` or `.safetensors` files, the CLI will scan the directory and
+interactively offer to import the models it finds there. Also see the
+`--autoconvert` command-line option.
+
+#### `!edit_model <name_of_model>`
+
+The `!edit_model` command can be used to modify a model that is already defined
+in `config/models.yaml`. Call it with the short name of the model you wish to
+modify, and it will allow you to modify the model's `description`, `weights` and
+other fields.
+
+Example:
+
+<pre>
+invoke> <b>!edit_model waifu-diffusion</b>
+>> Editing model waifu-diffusion from configuration file ./configs/models.yaml
+description: <b>Waifu diffusion v1.4beta</b>
+weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
+config: configs/stable-diffusion/v1-inference.yaml
+width: 512
+height: 512
+
+>> New configuration:
+waifu-diffusion:
+  config: configs/stable-diffusion/v1-inference.yaml
+  description: Waifu diffusion v1.4beta
+  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+  height: 512
+  width: 512
+
+OK to import [n]? y
+>> Caching model stable-diffusion-1.4 in system RAM
+>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
+...
+</pre>
+
+### History processing
+
+The CLI provides a series of convenient commands for reviewing previous actions,
+retrieving them, modifying them, and re-running them.
+
+#### `!history`
+
+The invoke script keeps track of all the commands you issue during a session,
+allowing you to re-run them. On Mac and Linux systems, it also writes the
+command-line history out to disk, giving you access to the most recent 1000
+commands issued.
+
+The `!history` command will return a numbered list of all the commands issued
+during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
+can then repeat a command by using the command `!NNN`, where "NNN" is the
+history line number. For example:
+
+!!! example ""
+
+    ```bash
+    invoke> !history
+    ...
+    [14] happy woman sitting under tree wearing broad hat and flowing garment
+    [15] beautiful woman sitting under tree wearing broad hat and flowing garment
+    [18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
+    [20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    ...
+    invoke> !20
+    invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+    ```
+
+####`!fetch`
+
+This command retrieves the generation parameters from a previously generated
+image and either loads them into the command line (Linux|Mac), or prints them
+out in a comment for copy-and-paste (Windows). You may provide either the name
+of a file in the current output directory, or a full file path. Specify path to
+a folder with image png files, and wildcard \*.png to retrieve the dream command
+used to generate the images, and save them to a file commands.txt for further
+processing.
+
+!!! example "load the generation command for a single png file"
+
+    ```bash
+    invoke> !fetch 0000015.8929913.png
+    # the script returns the next line, ready for editing and running:
+    invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
+    ```
+
+!!! example "fetch the generation commands from a batch of files and store them into `selected.txt`"
+
+    ```bash
+    invoke> !fetch outputs\selected-imgs\*.png selected.txt
+    ```
+
+#### `!replay`
+
+This command replays a text file generated by !fetch or created manually
+
+!!! example
+
+    ```bash
+    invoke> !replay outputs\selected-imgs\selected.txt
+    ```
+
+!!! note
+
+    These commands may behave unexpectedly if given a PNG file that was
+    not generated by InvokeAI.
+
+#### `!search <search string>`
+
+This is similar to !history but it only returns lines that contain
+`search string`. For example:
+
+```bash
+invoke> !search surreal
+[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
+```
+
+#### `!clear`
+
+This clears the search history from memory and disk. Be advised that this
+operation is irreversible and does not issue any warnings!
+
+## Command-line editing and completion
+
+The command-line offers convenient history tracking, editing, and command
+completion.
+
+- To scroll through previous commands and potentially edit/reuse them, use the
+  ++up++ and ++down++ keys.
+- To edit the current command, use the ++left++ and ++right++ keys to position
+  the cursor, and then ++backspace++, ++delete++ or insert characters.
+- To move to the very beginning of the command, type ++ctrl+a++ (or
+  ++command+a++ on the Mac)
+- To move to the end of the command, type ++ctrl+e++.
+- To cut a section of the command, position the cursor where you want to start
+  cutting and type ++ctrl+k++
+- To paste a cut section back in, position the cursor where you want to paste,
+  and type ++ctrl+y++
+
+Windows users can get similar, but more limited, functionality if they launch
+`invoke.py` with the `winpty` program and have the `pyreadline3` library
+installed:
+
+```batch
+> winpty python scripts\invoke.py
+```
+
+On the Mac and Linux platforms, when you exit invoke.py, the last 1000 lines of
+your command-line history will be saved. When you restart `invoke.py`, you can
+access the saved history using the ++up++ key.
+
+In addition, limited command-line completion is installed. In various contexts,
+you can start typing your command and press ++tab++. A list of potential
+completions will be presented to you. You can then type a little more, hit
+++tab++ again, and eventually autocomplete what you want.
+
+When specifying file paths using the one-letter shortcuts, the CLI will attempt
+to complete pathnames for you. This is most handy for the `-I` (init image) and
+`-M` (init mask) paths. To initiate completion, start the path with a slash
+(`/`) or `./`. For example:
+
+```bash
+invoke> zebra with a mustache -I./test-pictures<TAB>
+-I./test-pictures/Lincoln-and-Parrot.png  -I./test-pictures/zebra.jpg        -I./test-pictures/madonna.png
+-I./test-pictures/bad-sketch.png          -I./test-pictures/man_with_eagle/
+```
+
+You can then type ++z++, hit ++tab++ again, and it will autofill to `zebra.jpg`.
+
+More text completion features (such as autocompleting seeds) are on their way.

docs/features/CLI.md

@@ -1,589 +0,0 @@
----
-title: Command-Line Interface
----
-
-# :material-bash: CLI
-
-## **Interactive Command Line Interface**
-
-The InvokeAI command line interface (CLI) provides scriptable access
-to InvokeAI's features.Some advanced features are only available
-through the CLI, though they eventually find their way into the WebUI.
-
-The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
-selecting option (1). Alternatively, it can be launched directly from
-the command line by activating the InvokeAI environment and giving the
-command:
-
-```bash
-invokeai
-```
-
-After some startup messages, you will be presented with the `invoke> `
-prompt. Here you can type prompts to generate images and issue other
-commands to load and manipulate generative models. The CLI has a large
-number of command-line options that control its behavior. To get a
-concise summary of the options, call `invokeai` with the `--help` argument:
-
-```bash
-invokeai --help
-```
-
-The script uses the readline library to allow for in-line editing, command
-history (++up++ and ++down++), autocompletion, and more. To help keep track of
-which prompts generated which images, the script writes a log file of image
-names and prompts to the selected output directory.
-
-Here is a typical session
-
-```bash
-PS1:C:\Users\fred> invokeai
-* Initializing, be patient...
-* Initializing, be patient...
->> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
->> Internet connectivity is True
->> InvokeAI, version 2.3.0-rc5
->> InvokeAI runtime directory is "/home/lstein/invokeai"
->> GFPGAN Initialized
->> CodeFormer Initialized
->> ESRGAN Initialized
->> Using device_type cuda
->> xformers memory-efficient attention is available and enabled
-     (...more initialization messages...)
-* Initialization done! Awaiting your command (-h for help, 'q' to quit)
-invoke> ashley judd riding a camel -n2 -s150
-Outputs:
-   outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
-   outputs/img-samples/00010.png: "ashley judd riding a camel" -n2 -s150 -S 1362479620
-
-invoke> "there's a fly in my soup" -n6 -g
-    outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
-    seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
-invoke> q
-```
-
-![invoke-py-demo](../assets/dream-py-demo.png)
-
-## Arguments
-
-The script recognizes a series of command-line switches that will
-change important global defaults, such as the directory for image
-outputs and the location of the model weight files.
-
-### List of arguments recognized at the command line
-
-These command-line arguments can be passed to `invoke.py` when you first run it
-from the Windows, Mac or Linux command line. Some set defaults that can be
-overridden on a per-prompt basis (see
-[List of prompt arguments](#list-of-prompt-arguments). Others
-
-| Argument <img width="240" align="right"/> | Shortcut <img width="100" align="right"/> | Default <img width="320" align="right"/>       | Description                                                                                          |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
-| `--help`                                  | `-h`                                      |                                                | Print a concise help message.                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                          | Location for generated images.                                                                       |
-| `--prompt_as_dir`                         | `-p`                                      | `False`                                        | Name output directories using the prompt text.                                                       |
-| `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
-| `--model <modelname>`                     |                                           | `stable-diffusion-1.5`                         | Loads the initial model specified in configs/models.yaml. |
-| `--ckpt_convert `           |                                                         | `False`                                        | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
-| `--autoconvert <path>`                    |                          | `None`                                        | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
-| `--precision`                             |                                           | `fp16`                                         | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                            | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
-| `--safety-checker`                        |                                           | `False`                                        | Activate safety checker for NSFW and other potentially disturbing imagery                            |
-| `--patchmatch`, `--no-patchmatch`                 |                                   | `--patchmatch`                                        | Load/Don't load the PatchMatch inpainting extension    |
-| `--xformers`, `--no-xformers`                 |                                   | `--xformers`                                        | Load/Don't load the Xformers memory-efficient attention module (CUDA only)    |
-| `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
-| `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
-| `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
-| `--config <path>`                         |                                           | `configs/models.yaml`                          | Configuration file for models and their weights.                                                     |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                            | How many images to generate per prompt.                                                              |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                        | `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | For img2img: how hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-| `--fit`                                   | `-F`        | `False` | For img2img: scale the init image to fit into the specified -H and -W dimensions                                                                             |
-| `--grid`                                  | `-g`                                      | `False`                                        | Save all image series as a grid rather than individually.                                            |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                        | Sampler to use. Use `-h` to get list of available samplers.                                          |
-| `--seamless`                              |                                           | `False`                                        | Create interesting effects by tiling elements of the image.                                          |
-| `--embedding_path <path>`                 |                                           | `None`                                         | Path to pre-trained embedding manager checkpoints, for custom models                                 |
-| `--gfpgan_model_path`                     |                                           | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file.                                              |
-| `--free_gpu_mem`                          |                                           | `False`                                        | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions            |
-| `--precision`                             |                                           | `auto`                                         | Set model precision, default is selected by device. Options: auto, float32, float16, autocast        |
-
-!!! warning "These arguments are deprecated but still work"
-
-    <div align="center" markdown>
-
-    | Argument           |  Shortcut  |  Default            |  Description |
-    |--------------------|------------|---------------------|--------------|
-    | `--full_precision`  |             | `False`                | Same as `--precision=fp32`|
-    | `--weights <path>`   |            | `None`                | Path to weights file; use `--model stable-diffusion-1.4` instead |
-    | `--laion400m`        | `-l`         | `False`               | Use older LAION400m weights; use `--model=laion400m` instead |
-
-    </div>
-
-!!! tip
-
-      On Windows systems, you may run into
-      problems when passing the invoke script standard backslashed path
-      names because the Python interpreter treats "\" as an escape.
-      You can either double your slashes (ick): `C:\\path\\to\\my\\file`, or
-      use Linux/Mac style forward slashes (better): `C:/path/to/my/file`.
-
-## The .invokeai initialization file
-
-To start up invoke.py with your preferred settings, place your desired
-startup options in a file in your home directory named `.invokeai` The
-file should contain the startup options as you would type them on the
-command line (`--steps=10 --grid`), one argument per line, or a
-mixture of both using any of the accepted command switch formats:
-
-!!! example "my unmodified initialization file"
-
-    ```bash title="~/.invokeai" linenums="1"
-    # InvokeAI initialization file
-    # This is the InvokeAI initialization file, which contains command-line default values.
-    # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
-    # or renaming it and then running invokeai-configure again.
-
-    # The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
-    --root="/Users/mauwii/invokeai"
-
-    # the --outdir option controls the default location of image files.
-    --outdir="/Users/mauwii/invokeai/outputs"
-
-    # You may place other  frequently-used startup commands here, one or more per line.
-    # Examples:
-    # --web --host=0.0.0.0
-    # --steps=20
-    # -Ak_euler_a -C10.0
-    ```
-
-!!! note
-
-    The  initialization file only accepts the command line arguments.
-    There are additional arguments that you can provide on the `invoke>` command
-    line (such as `-n` or `--iterations`) that cannot be entered into this file.
-    Also be alert for empty blank lines at the end of the file, which will cause
-    an arguments error at startup time.
-
-## List of prompt arguments
-
-After the invoke.py script initializes, it will present you with a `invoke>`
-prompt. Here you can enter information to generate images from text
-([txt2img](#txt2img)), to embellish an existing image or sketch
-([img2img](#img2img)), or to selectively alter chosen regions of the image
-([inpainting](#inpainting)).
-
-### txt2img
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -W640 -H480
-    ```
-
-    This will create the requested image with the dimensions 640 (width)
-    and 480 (height).
-
-Here are the invoke> command that apply to txt2img:
-
-| Argument <img width="680" align="right"/> | Shortcut <img width="420" align="right"/> | Default <img width="480" align="right"/> | Description                                                                                                                                                                                                                                      |
-| ----------------------------------------- | ----------------------------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| "my prompt"                               |                                           |                                          | Text prompt to use. The quotation marks are optional.                                                                                                                                                                                            |
-| `--width <int>`                           | `-W<int>`                                 | `512`                                    | Width of generated image                                                                                                                                                                                                                         |
-| `--height <int>`                          | `-H<int>`                                 | `512`                                    | Height of generated image                                                                                                                                                                                                                        |
-| `--iterations <int>`                      | `-n<int>`                                 | `1`                                      | How many images to generate from this prompt                                                                                                                                                                                                     |
-| `--steps <int>`                           | `-s<int>`                                 | `50`                                     | How many steps of refinement to apply                                                                                                                                                                                                            |
-| `--cfg_scale <float>`                     | `-C<float>`                               | `7.5`                                    | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0                                                                                                       |
-| `--seed <int>`                            | `-S<int>`                                 | `None`                                   | Set the random seed for the next series of images. This can be used to recreate an image generated previously.                                                                                                                                   |
-| `--sampler <sampler>`                     | `-A<sampler>`                             | `k_lms`                                  | Sampler to use. Use -h to get list of available samplers.                                                                                                                                                                                        |
-| `--karras_max <int>`                      |                                           | `29`                                     | When using k\_\* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29]          |
-| `--hires_fix`                             |                                           |                                          | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution                                                                          |
-| `--png_compression <0-9>`                 | `-z<0-9>`                                 | `6`                                      | Select level of compression for output files, from 0 (no compression) to 9 (max compression)                                                                                                                                                     |
-| `--grid`                                  | `-g`                                      | `False`                                  | Turn on grid mode to return a single image combining all the images generated by this prompt                                                                                                                                                     |
-| `--individual`                            | `-i`                                      | `True`                                   | Turn off grid mode (deprecated; leave off --grid instead)                                                                                                                                                                                        |
-| `--outdir <path>`                         | `-o<path>`                                | `outputs/img_samples`                    | Temporarily change the location of these images                                                                                                                                                                                                  |
-| `--seamless`                              |                                           | `False`                                  | Activate seamless tiling for interesting effects                                                                                                                                                                                                 |
-| `--seamless_axes`                         |                                           | `x,y`                                    | Specify which axes to use circular convolution on.                                                                                                                                                                                               |
-| `--log_tokenization`                      | `-t`                                      | `False`                                  | Display a color-coded list of the parsed tokens derived from the prompt                                                                                                                                                                          |
-| `--skip_normalization`                    | `-x`                                      | `False`                                  | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts)                                                                                                                                                  |
-| `--upscale <int> <float>`                 | `-U <int> <float>`                        | `-U 1 0.75`                              | Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75.                                                                                                                |
-| `--facetool_strength <float>`             | `-G <float> `                             | `-G0`                                    | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0)                                                                                                                               |
-| `--facetool <name>`                       | `-ft <name>`                              | `-ft gfpgan`                             | Select face restoration algorithm to use: gfpgan, codeformer                                                                                                                                                                                     |
-| `--codeformer_fidelity`                   | `-cf <float>`                             | `0.75`                                   | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality                                                                                                     |
-| `--save_original`                         | `-save_orig`                              | `False`                                  | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced.                                                                                                                                             |
-| `--variation <float>`                     | `-v<float>`                               | `0.0`                                    | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
-| `--with_variations <pattern>`             |                                           | `None`                                   | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this.                                                                                                                                                           |
-| `--save_intermediates <n>`                |                                           | `None`                                   | Save the image from every nth step into an "intermediates" folder inside the output directory                                                                                                                                                    |
-| `--h_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
-| `--v_symmetry_time_pct <float>`           |                                           | `None`                                   | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.)                                   |
-
-!!! note
-
-    the width and height of the image must be multiples of 64. You can
-    provide different values, but they will be rounded down to the nearest multiple
-    of 64.
-
-!!! example "This is a example of img2img"
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
-    ```
-
-This will modify the indicated vacation photograph by making it more like the
-prompt. Results will vary greatly depending on what is in the image. We also ask
-to --fit the image into a box no bigger than 640x480. Otherwise the image size
-will be identical to the provided photo and you may run out of memory if it is
-large.
-
-In addition to the command-line options recognized by txt2img, img2img accepts
-additional options:
-
-| Argument <img width="160" align="right"/> | Shortcut    | Default | Description                                                                                                                                |
-| ----------------------------------------- | ----------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
-| `--init_img <path>`                       | `-I<path>`  | `None`  | Path to the initialization image                                                                                                           |
-| `--fit`                                   | `-F`        | `False` | Scale the image to fit into the specified -H and -W dimensions                                                                             |
-| `--strength <float>`                      | `-s<float>` | `0.75`  | How hard to try to match the prompt to the initial image. Ranges from 0.0-0.99, with higher values replacing the initial image completely. |
-
-### inpainting
-
-!!! example ""
-
-    ```bash
-    invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
-    ```
-
-    This will do the same thing as img2img, but image alterations will
-    only occur within transparent areas defined by the mask file specified
-    by `-M`. You may also supply just a single initial image with the areas
-    to overpaint made transparent, but you must be careful not to destroy
-    the pixels underneath when you create the transparent areas. See
-    [Inpainting](./INPAINTING.md) for details.
-
-inpainting accepts all the arguments used for txt2img and img2img, as well as
-the --mask (-M) and --text_mask (-tm) arguments:
-
-| Argument <img width="100" align="right"/> | Shortcut                 | Default | Description                                                                                      |
-| ----------------------------------------- | ------------------------ | ------- | ------------------------------------------------------------------------------------------------ |
-| `--init_mask <path>`                      | `-M<path>`               | `None`  | Path to an image the same size as the initial_image, with areas for inpainting made transparent. |
-| `--invert_mask `                          |                          | False   | If true, invert the mask so that transparent areas are opaque and vice versa.                    |
-| `--text_mask <prompt> [<float>]`          | `-tm <prompt> [<float>]` | <none>  | Create a mask from a text prompt describing part of the image                                    |
-
-The mask may either be an image with transparent areas, in which case the
-inpainting will occur in the transparent areas only, or a black and white image,
-in which case all black areas will be painted into.
-
-`--text_mask` (short form `-tm`) is a way to generate a mask using a text
-description of the part of the image to replace. For example, if you have an
-image of a breakfast plate with a bagel, toast and scrambled eggs, you can
-selectively mask the bagel and replace it with a piece of cake this way:
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
-```
-
-The algorithm uses <a
-href="https://github.com/timojl/clipseg">clipseg</a> to classify different
-regions of the image. The classifier puts out a confidence score for each region
-it identifies. Generally regions that score above 0.5 are reliable, but if you
-are getting too much or too little masking you can adjust the threshold down (to
-get more mask), or up (to get less). In this example, by passing `-tm` a higher
-value, we are insisting on a more stringent classification.
-
-```bash
-invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
-```
-
-### Custom Styles and Subjects
-
-You can load and use hundreds of community-contributed Textual
-Inversion models just by typing the appropriate trigger phrase. Please
-see [Concepts Library](CONCEPTS.md) for more details.
-
-## Other Commands
-
-The CLI offers a number of commands that begin with "!".
-
-### Postprocessing images
-
-To postprocess a file using face restoration or upscaling, use the `!fix`
-command.
-
-#### `!fix`
-
-This command runs a post-processor on a previously-generated image. It takes a
-PNG filename or path and applies your choice of the `-U`, `-G`, or `--embiggen`
-switches in order to fix faces or upscale. If you provide a filename, the script
-will look for it in the current output directory. Otherwise you can provide a
-full or partial path to the desired file.
-
-Some examples:
-
-!!! example "Upscale to 4X its original size and fix faces using codeformer"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
-    ```
-
-!!! example "Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen"
-
-    ```bash
-    invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
-    >> fixing outputs/img-samples/0000045.4829112.png
-    >> retrieved seed 4829112 and prompt "boy enjoying a banana split"
-    >> GFPGAN - Restoring Faces for image seed:4829112
-    Outputs:
-    [1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S  -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
-    ```
-
-#### `!mask`
-
-This command takes an image, a text prompt, and uses the `clipseg` algorithm to
-automatically generate a mask of the area that matches the text prompt. It is
-useful for debugging the text masking process prior to inpainting with the
-`--text_mask` argument. See [INPAINTING.md] for details.
-
-### Model selection and importation
-
-The CLI allows you to add new models on the fly, as well as to switch
-among them rapidly without leaving the script. There are several
-different model formats, each described in the [Model Installation
-Guide](../installation/050_INSTALLING_MODELS.md).
-
-#### `!models`
-
-This prints out a list of the models defined in `config/models.yaml'. The active
-model is bold-faced
-
-Example:
-
-<pre>
-inpainting-1.5            not loaded  Stable Diffusion inpainting model
-<b>stable-diffusion-1.5          active  Stable Diffusion v1.5</b>
-waifu-diffusion           not loaded  Waifu Diffusion v1.4
-</pre>
-
-#### `!switch <model>`
-
-This quickly switches from one model to another without leaving the CLI script.
-`invoke.py` uses a memory caching system; once a model has been loaded,
-switching back and forth is quick. The following example shows this in action.
-Note how the second column of the `!models` table changes to `cached` after a
-model is first loaded, and that the long initialization step is not needed when
-loading a cached model.
-
-#### `!import_model <hugging_face_repo_ID>`
-
-This imports and installs a `diffusers`-style model that is stored on
-the [HuggingFace Web Site](https://huggingface.co). You can look up
-any [Stable Diffusion diffusers
-model](https://huggingface.co/models?library=diffusers) and install it
-with a command like the following:
-
-```bash
-!import_model prompthero/openjourney
-```
-
-#### `!import_model <path/to/diffusers/directory>`
-
-If you have a copy of a `diffusers`-style model saved to disk, you can
-import it by passing the path to model's top-level directory.
-
-#### `!import_model <url>`
-
-For a `.ckpt` or `.safetensors` file, if you have a direct download
-URL for the file, you can provide it to `!import_model` and the file
-will be downloaded and installed for you.
-
-#### `!import_model <path/to/model/weights.ckpt>`
-
-This command imports a new model weights file into InvokeAI, makes it available
-for image generation within the script, and writes out the configuration for the
-model into `config/models.yaml` for use in subsequent sessions.
-
-Provide `!import_model` with the path to a weights file ending in `.ckpt`. If
-you type a partial path and press tab, the CLI will autocomplete. Although it
-will also autocomplete to `.vae` files, these are not currenty supported (but
-will be soon).
-
-When you hit return, the CLI will prompt you to fill in additional information
-about the model, including the short name you wish to use for it with the
-`!switch` command, a brief description of the model, the default image width and
-height to use with this model, and the model's configuration file. The latter
-three fields are automatically filled with reasonable defaults. In the example
-below, the bold-faced text shows what the user typed in with the exception of
-the width, height and configuration file paths, which were filled in
-automatically.
-
-#### `!import_model <path/to/directory_of_models>`
-
-If you provide the path of a directory that contains one or more
-`.ckpt` or `.safetensors` files, the CLI will scan the directory and
-interactively offer to import the models it finds there. Also see the
-`--autoconvert` command-line option.
-
-#### `!edit_model <name_of_model>`
-
-The `!edit_model` command can be used to modify a model that is already defined
-in `config/models.yaml`. Call it with the short name of the model you wish to
-modify, and it will allow you to modify the model's `description`, `weights` and
-other fields.
-
-Example:
-
-<pre>
-invoke> <b>!edit_model waifu-diffusion</b>
->> Editing model waifu-diffusion from configuration file ./configs/models.yaml
-description: <b>Waifu diffusion v1.4beta</b>
-weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
-config: configs/stable-diffusion/v1-inference.yaml
-width: 512
-height: 512
-
->> New configuration:
-waifu-diffusion:
-  config: configs/stable-diffusion/v1-inference.yaml
-  description: Waifu diffusion v1.4beta
-  weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-  height: 512
-  width: 512
-
-OK to import [n]? y
->> Caching model stable-diffusion-1.4 in system RAM
->> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
-...
-</pre>
-
-### History processing
-
-The CLI provides a series of convenient commands for reviewing previous actions,
-retrieving them, modifying them, and re-running them.
-
-#### `!history`
-
-The invoke script keeps track of all the commands you issue during a session,
-allowing you to re-run them. On Mac and Linux systems, it also writes the
-command-line history out to disk, giving you access to the most recent 1000
-commands issued.
-
-The `!history` command will return a numbered list of all the commands issued
-during the session (Windows), or the most recent 1000 commands (Mac|Linux). You
-can then repeat a command by using the command `!NNN`, where "NNN" is the
-history line number. For example:
-
-!!! example ""
-
-    ```bash
-    invoke> !history
-    ...
-    [14] happy woman sitting under tree wearing broad hat and flowing garment
-    [15] beautiful woman sitting under tree wearing broad hat and flowing garment
-    [18] beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6
-    [20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    [21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ...
-    invoke> !20
-    invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-    ```
-
-####`!fetch`
-
-This command retrieves the generation parameters from a previously generated
-image and either loads them into the command line (Linux|Mac), or prints them
-out in a comment for copy-and-paste (Windows). You may provide either the name
-of a file in the current output directory, or a full file path. Specify path to
-a folder with image png files, and wildcard \*.png to retrieve the dream command
-used to generate the images, and save them to a file commands.txt for further
-processing.
-
-!!! example "load the generation command for a single png file"
-
-    ```bash
-    invoke> !fetch 0000015.8929913.png
-    # the script returns the next line, ready for editing and running:
-    invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
-    ```
-
-!!! example "fetch the generation commands from a batch of files and store them into `selected.txt`"
-
-    ```bash
-    invoke> !fetch outputs\selected-imgs\*.png selected.txt
-    ```
-
-#### `!replay`
-
-This command replays a text file generated by !fetch or created manually
-
-!!! example
-
-    ```bash
-    invoke> !replay outputs\selected-imgs\selected.txt
-    ```
-
-!!! note
-
-    These commands may behave unexpectedly if given a PNG file that was
-    not generated by InvokeAI.
-
-#### `!search <search string>`
-
-This is similar to !history but it only returns lines that contain
-`search string`. For example:
-
-```bash
-invoke> !search surreal
-[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
-```
-
-#### `!clear`
-
-This clears the search history from memory and disk. Be advised that this
-operation is irreversible and does not issue any warnings!
-
-## Command-line editing and completion
-
-The command-line offers convenient history tracking, editing, and command
-completion.
-
-- To scroll through previous commands and potentially edit/reuse them, use the
-  ++up++ and ++down++ keys.
-- To edit the current command, use the ++left++ and ++right++ keys to position
-  the cursor, and then ++backspace++, ++delete++ or insert characters.
-- To move to the very beginning of the command, type ++ctrl+a++ (or
-  ++command+a++ on the Mac)
-- To move to the end of the command, type ++ctrl+e++.
-- To cut a section of the command, position the cursor where you want to start
-  cutting and type ++ctrl+k++
-- To paste a cut section back in, position the cursor where you want to paste,
-  and type ++ctrl+y++
-
-Windows users can get similar, but more limited, functionality if they launch
-`invoke.py` with the `winpty` program and have the `pyreadline3` library
-installed:
-
-```batch
-> winpty python scripts\invoke.py
-```
-
-On the Mac and Linux platforms, when you exit invoke.py, the last 1000 lines of
-your command-line history will be saved. When you restart `invoke.py`, you can
-access the saved history using the ++up++ key.
-
-In addition, limited command-line completion is installed. In various contexts,
-you can start typing your command and press ++tab++. A list of potential
-completions will be presented to you. You can then type a little more, hit
-++tab++ again, and eventually autocomplete what you want.
-
-When specifying file paths using the one-letter shortcuts, the CLI will attempt
-to complete pathnames for you. This is most handy for the `-I` (init image) and
-`-M` (init mask) paths. To initiate completion, start the path with a slash
-(`/`) or `./`. For example:
-
-```bash
-invoke> zebra with a mustache -I./test-pictures<TAB>
--I./test-pictures/Lincoln-and-Parrot.png  -I./test-pictures/zebra.jpg        -I./test-pictures/madonna.png
--I./test-pictures/bad-sketch.png          -I./test-pictures/man_with_eagle/
-```
-
-You can then type ++z++, hit ++tab++ again, and it will autofill to `zebra.jpg`.
-
-More text completion features (such as autocompleting seeds) are on their way.

docs/features/CONCEPTS.md

@@ -1,9 +1,12 @@
 ---
-title: Concepts Library
+title: Concepts 
 ---
 
 # :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
 
+With the advances in research, many new capabilities are available to customize the knowledge and understanding of novel concepts not originally contained in the base model. 
+
+
 ## Using Textual Inversion Files
 
 Textual inversion (TI) files are small models that customize the output of
@@ -12,18 +15,16 @@ and artistic styles. They are also known as "embeds" in the machine learning
 world.
 
 Each TI file introduces one or more vocabulary terms to the SD model. These are
-known in InvokeAI as "triggers." Triggers are often, but not always, denoted
-using angle brackets as in "<trigger-phrase>". The two most common type of
+known in InvokeAI as "triggers." Triggers are denoted using angle brackets 
+as in "<trigger-phrase>". The two most common type of
 TI files that you'll encounter are `.pt` and `.bin` files, which are produced by
 different TI training packages. InvokeAI supports both formats, but its
-[built-in TI training system](TEXTUAL_INVERSION.md) produces `.pt`.
+[built-in TI training system](TRAINING.md) produces `.pt`.
 
 The [Hugging Face company](https://huggingface.co/sd-concepts-library) has
 amassed a large ligrary of >800 community-contributed TI files covering a
-broad range of subjects and styles. InvokeAI has built-in support for this
-library which downloads and merges TI files automatically upon request. You can
-also install your own or others' TI files by placing them in a designated
-directory.
+broad range of subjects and styles. You can also install your own or others' TI files 
+by placing them in the designated directory for the compatible model type
 
 ### An Example
 
@@ -41,91 +42,43 @@ You can also combine styles and concepts:
   | :--------------------------------------------------------: |
   | ![](../assets/concepts/image5.png)                         |
 </figure>
-## Using a Hugging Face Concept
 
-!!! warning "Authenticating to HuggingFace"
-
-    Some concepts require valid authentication to HuggingFace. Without it, they will not be downloaded
-    and will be silently ignored.
-
-    If you used an installer to install InvokeAI, you may have already set a HuggingFace token.
-    If you skipped this step, you can:
-
-    - run the InvokeAI configuration script again (if you used a manual installer): `invokeai-configure`
-    - set one of the `HUGGINGFACE_TOKEN` or `HUGGING_FACE_HUB_TOKEN` environment variables to contain your token
-
-    Finally, if you already used any HuggingFace library on your computer, you might already have a token
-    in your local cache. Check for a hidden `.huggingface` directory in your home folder. If it
-    contains a `token` file, then you are all set.
-
-
-Hugging Face TI concepts are downloaded and installed automatically as you
-require them. This requires your machine to be connected to the Internet. To
-find out what each concept is for, you can browse the
-[Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
-look at examples of what each concept produces.
-
-When you have an idea of a concept you wish to try, go to the command-line
-client (CLI) and type a `<` character and the beginning of the Hugging Face
-concept name you wish to load. Press ++tab++, and the CLI will show you all
-matching concepts. You can also type `<` and hit ++tab++ to get a listing of all
-~800 concepts, but be prepared to scroll up to see them all! If there is more
-than one match you can continue to type and ++tab++ until the concept is
-completed.
-
-!!! example
-
-    if you type in `<x` and hit ++tab++, you'll be prompted with the completions:
-
-    ```py
-    <xatu2>        <xatu>         <xbh>          <xi>           <xidiversity>  <xioboma>      <xuna>         <xyz>
-    ```
-
-    Now type `id` and press ++tab++. It will be autocompleted to `<xidiversity>`
-    because this is a unique match.
-
-    Finish your prompt and generate as usual. You may include multiple concept terms
-    in the prompt.
-
-If you have never used this concept before, you will see a message that the TI
-model is being downloaded and installed. After this, the concept will be saved
-locally (in the `models/sd-concepts-library` directory) for future use.
-
-Several steps happen during downloading and installation, including a scan of
-the file for malicious code. Should any errors occur, you will be warned and the
-concept will fail to load. Generation will then continue treating the trigger
-term as a normal string of characters (e.g. as literal `<ghibli-face>`).
-
-You can also use `<concept-names>` in the WebGUI's prompt textbox. There is no
-autocompletion at this time.
 
 ## Installing your Own TI Files
 
 You may install any number of `.pt` and `.bin` files simply by copying them into
-the `embeddings` directory of the InvokeAI runtime directory (usually `invokeai`
-in your home directory). You may create subdirectories in order to organize the
-files in any way you wish. Be careful not to overwrite one file with another.
+the `embedding` directory of the corresponding InvokeAI models directory (usually `invokeai`
+in your home directory). For example, you can simply move a Stable Diffusion 1.5 embedding file to
+the `sd-1/embedding` folder. Be careful not to overwrite one file with another.
 For example, TI files generated by the Hugging Face toolkit share the named
-`learned_embedding.bin`. You can use subdirectories to keep them distinct.
+`learned_embedding.bin`. You can rename these, or use subdirectories to keep them distinct.
 
-At startup time, InvokeAI will scan the `embeddings` directory and load any TI
-files it finds there. At startup you will see a message similar to this one:
+At startup time, InvokeAI will scan the various `embedding` directories and load any TI
+files it finds there for compatible models. At startup you will see a message similar to this one:
 
 ```bash
->> Current embedding manager terms: *, <HOI4-Leader>, <princess-knight>
+>> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
 ```
+To use these when generating, simply type the `<` key in your prompt to open the Textual Inversion WebUI and 
+select the embedding you'd like to use. This UI has type-ahead support, so you can easily find supported embeddings.
 
-Note the `*` trigger term. This is a placeholder term that many early TI
-tutorials taught people to use rather than a more descriptive term.
-Unfortunately, if you have multiple TI files that all use this term, only the
-first one loaded will be triggered by use of the term.
+## Using LoRAs
 
-To avoid this problem, you can use the `merge_embeddings.py` script to merge two
-or more TI files together. If it encounters a collision of terms, the script
-will prompt you to select new terms that do not collide. See
-[Textual Inversion](TEXTUAL_INVERSION.md) for details.
+LoRA files are models that customize the output of Stable Diffusion image generation.
+Larger than embeddings, but much smaller than full models, they augment SD with improved
+understanding of subjects and artistic styles.
 
-## Further Reading
+Unlike TI files, LoRAs do not introduce novel vocabulary into the model's known tokens. Instead,
+LoRAs augment the model's weights that are applied to generate imagery. LoRAs may be supplied
+with a "trigger" word that they have been explicitly trained on, or may simply apply their 
+effect without being triggered.
+
+LoRAs are typically stored in .safetensors files, which are the most secure way to store and transmit
+these types of weights. You may install any number of `.safetensors` LoRA files simply by copying them into
+the `lora` directory of the corresponding InvokeAI models directory (usually `invokeai`
+in your home directory). For example, you can simply move a Stable Diffusion 1.5 LoRA file to
+the `sd-1/lora` folder.
+
+To use these when generating, open the LoRA menu item in the options panel, select the LoRAs you want to apply
+and ensure that they have the appropriate weight recommended by the model provider. Typically, most LoRAs perform best at a weight of .75-1. 
 
-Please see [the repository](https://github.com/rinongal/textual_inversion) and
-associated paper for details and limitations.

docs/features/CONTROLNET.md

@@ -0,0 +1,92 @@
+---
+title: ControlNet
+---
+
+# :material-loupe: ControlNet
+
+## ControlNet
+
+ControlNet
+
+ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
+
+With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
+
+
+### How it works
+
+ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
+
+
+### Models
+
+As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
+
+
+**Canny**:
+
+When the Canny model is used in ControlNet, Invoke will attempt to generate images that match the edges detected. 
+
+Canny edge detection works by detecting the edges in an image by looking for abrupt changes in intensity. It is known for its ability to detect edges accurately while reducing noise and false edges, and the preprocessor can identify more information by decreasing the thresholds.
+
+**M-LSD**: 
+
+M-LSD is another edge detection algorithm used in ControlNet. It stands for Multi-Scale Line Segment Detector. 
+
+It detects straight line segments in an image by analyzing the local structure of the image at multiple scales.  It can be useful for architectural imagery, or anything where straight-line structural information is needed for the resulting output. 
+
+**Lineart**: 
+
+The Lineart model in ControlNet generates line drawings from an input image. The resulting pre-processed image is a simplified version of the original, with only the outlines of objects visible.The Lineart model in ControlNet is known for its ability to accurately capture the contours of the objects in an input sketch. 
+
+**Lineart Anime**: 
+
+A variant of the Lineart model that generates line drawings with a distinct style inspired by anime and manga art styles.
+
+**Depth**: 
+A model that generates depth maps of images, allowing you to create more realistic 3D models or to simulate depth effects in post-processing.
+
+**Normal Map (BAE):** 
+A model that generates normal maps from input images, allowing for more realistic lighting effects in 3D rendering.
+		
+**Image Segmentation**: 
+A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
+
+
+**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. 
+
+**Mediapipe Face**:
+
+The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
+
+**Tile (experimental)**:
+
+The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
+
+- It can reinterpret specific details within an image and create fresh, new elements.
+- It has the ability to disregard global instructions if there's a discrepancy between them and the local context or specific parts of the image. In such cases, it uses the local context to guide the process.
+
+The Tile Model can be a powerful tool in your arsenal for enhancing image quality and details. If there are undesirable elements in your images, such as blurriness caused by resizing, this model can effectively eliminate these issues, resulting in cleaner, crisper images. Moreover, it can generate and add refined details to your images, improving their overall quality and appeal. 
+
+**Pix2Pix (experimental)**
+
+With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
+
+**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
+
+Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
+
+
+## Using ControlNet
+
+To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
+
+
+Each ControlNet has two settings that are applied to the ControlNet.
+
+Weight - Strength of the Controlnet model applied to the generation for the section, defined by start/end.
+
+Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
+
+Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.

docs/features/IMG2IMG.md

@@ -4,86 +4,13 @@ title: Image-to-Image
 
 # :material-image-multiple: Image-to-Image
 
-Both the Web and command-line interfaces provide an "img2img" feature
-that lets you seed your creations with an initial drawing or
-photo. This is a really cool feature that tells stable diffusion to
-build the prompt on top of the image you provide, preserving the
-original's basic shape and layout.
+InvokeAI provides an "img2img" feature that lets you seed your
+creations with an initial drawing or photo. This is a really cool
+feature that tells stable diffusion to build the prompt on top of the
+image you provide, preserving the original's basic shape and layout.
 
-See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
-in the InvokeAI web server. This document describes how to use img2img
-in the command-line tool.
-
-## Basic Usage
-
-Launch the command-line client by launching `invoke.sh`/`invoke.bat`
-and choosing option (1). Alternative, activate the InvokeAI
-environment and issue the command `invokeai`.
-
-Once the `invoke> ` prompt appears, you can start an img2img render by
-pointing to a seed file with the `-I` option as shown here:
-
-!!! example ""
-
-    ```commandline
-    tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
-    ```
-
-    <figure markdown>
-
-    | original image | generated image |
-    | :------------: | :-------------: |
-    | ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
-
-    </figure>
-
-The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
-(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
-the original intact), to `1.0` (ignore the original completely). The default is
-`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
-options include `-C` (classification free guidance scale), and `-s` (steps).
-Unlike `txt2img`, adding steps will continuously change the resulting image and
-it will not converge.
-
-You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
-count variants on the original image. This is done by passing the first
-generated image back into img2img the requested number of times. It generates
-interesting variants.
-
-Note that the prompt makes a big difference. For example, this slight variation
-on the prompt produces a very different image:
-
-<figure markdown>
-![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
-<caption markdown>photograph of a tree on a hill with a river</caption>
-</figure>
-
-!!! tip
-
-    When designing prompts, think about how the images scraped from the internet were
-    captioned. Very few photographs will be labeled "photograph" or "photorealistic."
-    They will, however, be captioned with the publication, photographer, camera model,
-    or film settings.
-
-If the initial image contains transparent regions, then Stable Diffusion will
-only draw within the transparent regions, a process called
-[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
-However, for this to work correctly, the color information underneath the
-transparent needs to be preserved, not erased.
-
-!!! warning "**IMPORTANT ISSUE** "
-
-    `img2img` does not work properly on initial images smaller
-    than 512x512. Please scale your image to at least 512x512 before using it.
-    Larger images are not a problem, but may run out of VRAM on your GPU card. To
-    fix this, use the --fit option, which downscales the initial image to fit within
-    the box specified by width x height:
-
-    ```
-    tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
-    ```
-
-## How does it actually work, though?
+For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
+Web Server](./WEB.md#image-to-image).
 
 The main difference between `img2img` and `prompt2img` is the starting point.
 While `prompt2img` always starts with pure gaussian noise and progressively
@@ -99,10 +26,6 @@ seed `1592514025` develops something like this:
 
 !!! example ""
 
-    ```bash
-    invoke> "fire" -s10 -W384 -H384 -S1592514025
-    ```
-
     <figure markdown>
     ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
     </figure>
@@ -157,17 +80,8 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
 the problems of my bad drawing.
 
 If you want to try this out yourself, all of these are using a seed of
-`1592514025` with a width/height of `384`, step count `10`, the default sampler
-(`k_lms`), and the single-word prompt `"fire"`:
-
-```bash
-invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
-```
-
-The code for rendering intermediates is on my (damian0815's) branch
-[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
-run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
-generating an image.
+`1592514025` with a width/height of `384`, step count `10`, the
+`k_lms` sampler, and the single-word prompt `"fire"`.
 
 ### Compensating for the reduced step count
 
@@ -180,10 +94,6 @@ give each generation 20 steps.
 Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
 does `20` steps from my image):
 
-```bash
-invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
-```
-
 <figure markdown>
 ![000035.1592514025](../assets/img2img/000035.1592514025.png)
 </figure>
@@ -191,10 +101,6 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
 and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
 make sure SD does `20` steps from my image):
 
-```commandline
-invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
-```
-
 <figure markdown>
 ![000046.1592514025](../assets/img2img/000046.1592514025.png)
 </figure>

docs/features/LOGGING.md

@@ -0,0 +1,171 @@
+---
+title: Controlling Logging
+---
+
+# :material-image-off: Controlling Logging
+
+## Controlling How InvokeAI Logs Status Messages
+
+InvokeAI logs status messages using a configurable logging system. You
+can log to the terminal window, to a designated file on the local
+machine, to the syslog facility on a Linux or Mac, or to a properly
+configured web server. You can configure several logs at the same
+time, and control the level of message logged and the logging format
+(to a limited extent).
+
+Three command-line options control logging:
+
+### `--log_handlers <handler1> <handler2> ...`
+
+This option activates one or more log handlers. Options are "console",
+"file", "syslog" and "http". To specify more than one, separate them
+by spaces:
+
+```bash
+invokeai-web --log_handlers console syslog=/dev/log file=C:\Users\fred\invokeai.log
+```
+
+The format of these options is described below.
+
+### `--log_format {plain|color|legacy|syslog}`
+
+This controls the format of log messages written to the console. Only
+the "console" log handler is currently affected by this setting.
+
+* "plain" provides formatted messages like this:
+
+```bash
+
+[2023-05-24 23:18:2[2023-05-24 23:18:50,352]::[InvokeAI]::DEBUG --> this is a debug message
+[2023-05-24 23:18:50,352]::[InvokeAI]::INFO --> this is an informational messages
+[2023-05-24 23:18:50,352]::[InvokeAI]::WARNING --> this is a warning
+[2023-05-24 23:18:50,352]::[InvokeAI]::ERROR --> this is an error
+[2023-05-24 23:18:50,352]::[InvokeAI]::CRITICAL --> this is a critical error
+```
+
+* "color" produces similar output, but the text will be color coded to
+indicate the severity of the message.
+
+* "legacy" produces output similar to InvokeAI versions 2.3 and earlier:
+
+```bash
+### this is a critical error
+*** this is an error
+** this is a warning
+>> this is an informational messages
+   | this is a debug message
+```
+
+* "syslog" produces messages suitable for syslog entries:
+
+```bash
+InvokeAI [2691178] <CRITICAL> this is a critical error
+InvokeAI [2691178] <ERROR> this is an error
+InvokeAI [2691178] <WARNING> this is a warning
+InvokeAI [2691178] <INFO> this is an informational messages
+InvokeAI [2691178] <DEBUG> this is a debug message
+```
+
+(note that the date, time and hostname will be added by the syslog
+system)
+
+### `--log_level {debug|info|warning|error|critical}`
+
+Providing this command-line option will cause only messages at the
+specified level or above to be emitted.
+
+## Console logging
+
+When "console" is provided to `--log_handlers`, messages will be
+written to the command line window in which InvokeAI was launched. By
+default, the color formatter will be used unless overridden by
+`--log_format`.
+
+## File logging
+
+When "file" is provided to `--log_handlers`, entries will be written
+to the file indicated in the path argument. By default, the "plain"
+format will be used:
+
+```bash
+invokeai-web --log_handlers file=/var/log/invokeai.log
+```
+
+## Syslog logging
+
+When "syslog" is requested, entries will be sent to the syslog
+system. There are a variety of ways to control where the log message
+is sent:
+
+* Send to the local machine using the `/dev/log` socket:
+
+```
+invokeai-web --log_handlers syslog=/dev/log
+```
+
+* Send to the local machine using a UDP message:
+
+```
+invokeai-web --log_handlers syslog=localhost
+```
+
+* Send to the local machine using a UDP message on a nonstandard
+  port:
+
+```
+invokeai-web --log_handlers syslog=localhost:512
+```
+
+* Send to a remote machine named "loghost" on the local LAN using
+  facility LOG_USER and UDP packets:
+
+```
+invokeai-web --log_handlers syslog=loghost,facility=LOG_USER,socktype=SOCK_DGRAM
+```
+
+This can be abbreviated `syslog=loghost`, as LOG_USER and SOCK_DGRAM
+are defaults.
+
+* Send to a remote machine named "loghost" using the facility LOCAL0
+  and using a TCP socket:
+
+```
+invokeai-web --log_handlers syslog=loghost,facility=LOG_LOCAL0,socktype=SOCK_STREAM
+```
+
+If no arguments are specified (just a bare "syslog"), then the logging
+system will look for a UNIX socket named `/dev/log`, and if not found
+try to send a UDP message to `localhost`. The Macintosh OS used to
+support logging to a socket named `/var/run/syslog`, but this feature
+has since been disabled.
+
+## Web logging
+
+If you have access to a web server that is configured to log messages
+when a particular URL is requested, you can log using the "http"
+method:
+
+```
+invokeai-web --log_handlers http=http://my.server/path/to/logger,method=POST
+```
+
+The optional [,method=] part can be used to specify whether the URL
+accepts GET (default) or POST messages.
+
+Currently password authentication and SSL are not supported.
+
+## Using the configuration file
+
+You can set and forget logging options by adding a "Logging" section
+to `invokeai.yaml`:
+
+```
+InvokeAI:
+  [... other settings...]
+  Logging:
+    log_handlers:
+       - console
+       - syslog=/dev/log
+    log_level: info
+    log_format: color
+```

docs/features/MODEL_MERGING.md

@@ -71,6 +71,3 @@ under the selected name and register it with InvokeAI.
   use InvokeAI conventions - only alphanumeric letters and the
   characters ".+-".
 
-## Caveats
-
-This is a new script and may contain bugs.

docs/features/NSFW.md

@@ -31,10 +31,22 @@ turned on and off on the command line using `--nsfw_checker` and
 
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file (usually
-`invokeai.init` in your home directory). You can change the default at any
-time by opening this file in a text editor and commenting or
-uncommenting the line `--nsfw_checker`.
+response is stored in the InvokeAI initialization file
+(`invokeai.yaml` in the InvokeAI root directory).  You can change the
+default at any time by opening this file in a text editor and
+changing the line `nsfw_checker:` from true to false or vice-versa:
+
+
+```
+...
+  Features:
+    esrgan: true
+    internet_available: true
+    log_tokenization: false
+    nsfw_checker: true
+    patchmatch: true
+    restore: true
+```
 
 ## Caveats
 
@@ -79,11 +91,3 @@ generates. However, it does write metadata into the PNG data area,
 including the prompt used to generate the image and relevant parameter
 settings. These fields can be examined using the `sd-metadata.py`
 script that comes with the InvokeAI package.
-
-Note that several other Stable Diffusion distributions offer
-wavelet-based "invisible" watermarking. We have experimented with the
-library used to generate these watermarks and have reached the
-conclusion that while the watermarking library may be adding
-watermarks to PNG images, the currently available version is unable to
-retrieve them successfully. If and when a functioning version of the
-library becomes available, we will offer this feature as well.

docs/features/OTHER.md

@@ -18,43 +18,16 @@ Output Example:
 
 ## **Seamless Tiling**
 
-The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
-`--seamless` option when starting the script which will result in all generated images to tile, or
-for each `invoke>` prompt as shown here:
+The seamless tiling mode causes generated images to seamlessly tile
+with itself creating repetitive wallpaper-like patterns. To use it,
+activate the Seamless Tiling option in the Web GUI and then select
+whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
+will then be active for the next set of generations.
+
+A nice prompt to test seamless tiling with is:
 
-```python
-invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
 ```
-
-By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
-Possible values are `x`, `y`, and `x,y`:
-```python
-invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
-```
-
----
-
-## **Shortcuts: Reusing Seeds**
-
-Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
-1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
-generated. If you produced multiple images with the `-n` switch, then you can go back further
-using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
-back further than one command.
-
-Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
-switch to turn on upscaling and face enhancement (see previous section):
-
-```bash
-invoke> a cute child playing hopscotch -G0.5
-[...]
-outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
-
-# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
-invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
-reusing previous seed 3498014304
-[...]
-outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304
+pond garden with lotus by claude monet"
 ```
 
 ---
@@ -73,66 +46,27 @@ This will tell the sampler to invest 25% of its effort on the tabby cat aspect o
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
----
-
-## **Filename Format**
-
-The argument `--fnformat` allows to specify the filename of the
- image. Supported wildcards are all arguments what can be set such as
- `perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
- `sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
- `prefix`.
-
-The following prompt
-```bash
-dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
-```
-
-generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
-
----
-
 ## **Thresholding and Perlin Noise Initialization Options**
 
-Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.
+Under the Noise section of the Web UI, you will find two options named
+Perlin Noise and Noise Threshold. [Perlin
+noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
+structured noise used to simulate terrain and other natural
+textures. The slider controls the percentage of perlin noise that will
+be mixed into the image at the beginning of generation. Adding a little
+perlin noise to a generation will alter the image substantially.
+
+The noise threshold limits the range of the latent values during
+sampling and helps combat the oversharpening seem with higher CFG
+scale values.
 
 For better intuition into what these options do in practice:
 
 ![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
 
-In generating this graphic, perlin noise at initialization was programmatically varied going across on the diagram by values 0.0, 0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied going down from
-0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are fixed, so the initial prompt is as follows (no thresholding or perlin noise):
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 0 --perlin 0
-```
-
-Here's an example of another prompt used when setting the threshold to 5 and perlin noise to 0.2:
-
-```bash
-invoke> "a portrait of a beautiful young lady" -S 1950357039 -s 100 -C 20 -A k_euler_a --threshold 5 --perlin 0.2
-```
-
-!!! note
-
-    currently the thresholding feature is only implemented for the k-diffusion style samplers, and empirically appears to work best with `k_euler_a` and `k_dpm_2_a`. Using 0 disables thresholding. Using 0 for perlin noise disables using perlin noise for initialization. Finally, using 1 for perlin noise uses only perlin noise for initialization.
-
----
-
-## **Simplified API**
-
-For programmers who wish to incorporate stable-diffusion into other products, this repository
-includes a simplified API for text to image generation, which lets you create images from a prompt
-in just three lines of code:
-
-```bash
-from ldm.generate import Generate
-g       = Generate()
-outputs = g.txt2img("a unicorn in manhattan")
-```
-
-Outputs is a list of lists in the format [filename1,seed1],[filename2,seed2]...].
-
-Please see the documentation in ldm/generate.py for more information.
-
----
+In generating this graphic, perlin noise at initialization was
+programmatically varied going across on the diagram by values 0.0,
+0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
+going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
+fixed using the prompt "a portrait of a beautiful young lady" a CFG of
+20, 100 steps, and a seed of 1950357039.

docs/features/POSTPROCESS.md

@@ -8,12 +8,6 @@ title: Postprocessing
 
 This extension provides the ability to restore faces and upscale images.
 
-Face restoration and upscaling can be applied at the time you generate the
-images, or at any later time against a previously-generated PNG file, using the
-[!fix](#fixing-previously-generated-images) command.
-[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
-fact.
-
 ## Face Fixing
 
 The default face restoration module is GFPGAN. The default upscale is
@@ -23,8 +17,7 @@ Real-ESRGAN. For an alternative face restoration module, see
 As of version 1.14, environment.yaml will install the Real-ESRGAN package into
 the standard install location for python packages, and will put GFPGAN into a
 subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
-should "just work" without further intervention. Simply pass the `--upscale`
-(`-U`) option on the `invoke>` command line, or indicate the desired scale on
+should "just work" without further intervention. Simply indicate the desired scale on
 the popup in the Web GUI.
 
 **GFPGAN** requires a series of downloadable model files to work. These are
@@ -41,48 +34,75 @@ reconstruction.
 
 ### Upscaling
 
-`-U : <upscaling_factor> <upscaling_strength>`
+Open the upscaling dialog by clicking on the "expand" icon located
+above the image display area in the Web UI:
 
-The upscaling prompt argument takes two values. The first value is a scaling
-factor and should be set to either `2` or `4` only. This will either scale the
-image 2x or 4x respectively using different models.
+<figure markdown>
+![upscale1](../assets/features/upscale-dialog.png)
+</figure>
 
-You can set the scaling stength between `0` and `1.0` to control intensity of
-the of the scaling. This is handy because AI upscalers generally tend to smooth
-out texture details. If you wish to retain some of those for natural looking
-results, we recommend using values between `0.5 to 0.8`.
+There are three different upscaling parameters that you can
+adjust. The first is the scale itself, either 2x or 4x.
 
-If you do not explicitly specify an upscaling_strength, it will default to 0.75.
+The second is the "Denoising Strength." Higher values will smooth out
+the image and remove digital chatter, but may lose fine detail at
+higher values.
+
+Third, "Upscale Strength" allows you to adjust how the You can set the
+scaling stength between `0` and `1.0` to control the intensity of the
+scaling. AI upscalers generally tend to smooth out texture details. If
+you wish to retain some of those for natural looking results, we
+recommend using values between `0.5 to 0.8`.
+
+[This figure](../assets/features/upscaling-montage.png) illustrates
+the effects of denoising and strength. The original image was 512x512,
+4x scaled to 2048x2048. The "original" version on the upper left was
+scaled using simple pixel averaging. The remainder use the ESRGAN
+upscaling algorithm at different levels of denoising and strength.
+
+<figure markdown>
+![upscaling](../assets/features/upscaling-montage.png){ width=720 }
+</figure>
+
+Both denoising and strength default to 0.75.
 
 ### Face Restoration
 
-`-G : <facetool_strength>`
+InvokeAI offers alternative two face restoration algorithms,
+[GFPGAN](https://github.com/TencentARC/GFPGAN) and
+[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
+algorithms improve the appearance of faces, particularly eyes and
+mouths. Issues with faces are less common with the latest set of
+Stable Diffusion models than with the original 1.4 release, but the
+restoration algorithms can still make a noticeable improvement in
+certain cases. You can also apply restoration to old photographs you
+upload.
 
-This prompt argument controls the strength of the face restoration that is being
-applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.
+To access face restoration, click the "smiley face" icon in the
+toolbar above the InvokeAI image panel. You will be presented with a
+dialog that offers a choice between the two algorithm and sliders that
+allow you to adjust their parameters. Alternatively, you may open the
+left-hand accordion panel labeled "Face Restoration" and have the
+restoration algorithm of your choice applied to generated images
+automatically.
 
-You can use either one or both without any conflicts. In cases where you use
-both, the image will be first upscaled and then the face restoration process
-will be executed to ensure you get the highest quality facial features.
 
-`--save_orig`
+Like upscaling, there are a number of parameters that adjust the face
+restoration output. GFPGAN has a single parameter, `strength`, which
+controls how much the algorithm is allowed to adjust the
+image. CodeFormer has two parameters, `strength`, and `fidelity`,
+which together control the quality of the output image as described in
+the [CodeFormer project
+page](https://shangchenzhou.com/projects/CodeFormer/). Default values
+are 0.75 for both parameters, which achieves a reasonable balance
+between changing the image too much and not enough.
 
-When you use either `-U` or `-G`, the final result you get is upscaled or face
-modified. If you want to save the original Stable Diffusion generation, you can
-use the `-save_orig` prompt argument to save the original unaffected version
-too.
+[This figure](../assets/features/restoration-montage.png) illustrates
+the effects of adjusting GFPGAN and CodeFormer parameters.
 
-### Example Usage
-
-```bash
-invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
-```
-
-This also works with img2img:
-
-```bash
-invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
-```
+<figure markdown>
+![upscaling](../assets/features/restoration-montage.png){ width=720 }
+</figure>
 
 !!! note
 
@@ -95,69 +115,8 @@ invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
-If you wish to stop during the image generation but want to upscale or face
-restore a particular generated image, pass it again with the same prompt and
-generated seed along with the `-U` and `-G` prompt arguments to perform those
-actions.
-
-## CodeFormer Support
-
-This repo also allows you to perform face restoration using
-[CodeFormer](https://github.com/sczhou/CodeFormer).
-
-In order to setup CodeFormer to work, you need to download the models like with
-GFPGAN. You can do this either by running `invokeai-configure` or by manually
-downloading the
-[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
-and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
-
-You can use `-ft` prompt argument to swap between CodeFormer and the default
-GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
-strength of the restoration effect.
-
-### CodeFormer Usage
-
-The following command will perform face restoration with CodeFormer instead of
-the default gfpgan.
-
-`<prompt> -G 0.8 -ft codeformer`
-
-### Other Options
-
-- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
-  high quality results but low accuracy and 1 produces lower quality results but
-  higher accuacy to your original face.
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is closely matching to the input face.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.9`
-
-The following command will perform face restoration with CodeFormer. CodeFormer
-will output a result that is the best restoration possible. This may deviate
-slightly from the original face. This is an excellent option to use in
-situations when there is very little facial data to work with.
-
-`<prompt> -G 1.0 -ft codeformer -cf 0.1`
-
-## Fixing Previously-Generated Images
-
-It is easy to apply face restoration and/or upscaling to any
-previously-generated file. Just use the syntax
-`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
-and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
-just run:
-
-```bash
-invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
-```
-
-A new file named `000044.2945021133.fixed.png` will be created in the output
-directory. Note that the `!fix` command does not replace the original file,
-unlike the behavior at generate time.
-
 ## How to disable
 
 If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
 you can disable them on the invoke.py command line with the `--no_restore` and
-`--no_upscale` options, respectively.
+`--no_esrgan` options, respectively.

docs/features/PROMPTS.md

@@ -4,77 +4,12 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
-## **Reading Prompts from a File**
-
-You can automate `invoke.py` by providing a text file with the prompts you want
-to run, one line per prompt. The text file must be composed with a text editor
-(e.g. Notepad) and not a word processor. Each line should look like what you
-would type at the invoke> prompt:
-
-```bash
-"a beautiful sunny day in the park, children playing" -n4 -C10
-"stormy weather on a mountain top, goats grazing" -s100
-"innovative packaging for a squid's dinner" -S137038382
-```
-
-Then pass this file's name to `invoke.py` when you invoke it:
-
-```bash
-python scripts/invoke.py --from_file "/path/to/prompts.txt"
-```
-
-You may also read a series of prompts from standard input by providing
-a filename of `-`. For example, here is a python script that creates a
-matrix of prompts, each one varying slightly:
-
-```bash
-#!/usr/bin/env python
-
-adjectives = ['sunny','rainy','overcast']
-samplers = ['k_lms','k_euler_a','k_heun']
-cfg = [7.5, 9, 11]
-
-for adj in adjectives:
-    for samp in samplers:
-        for cg in cfg:
-            print(f'a {adj} day -A{samp} -C{cg}')
-```
-
-Its output looks like this (abbreviated):
-
-```bash
-a sunny day -Aklms -C7.5
-a sunny day -Aklms -C9
-a sunny day -Aklms -C11
-a sunny day -Ak_euler_a -C7.5
-a sunny day -Ak_euler_a -C9
-...
-a overcast day -Ak_heun -C9
-a overcast day -Ak_heun -C11
-```
-
-To feed it to invoke.py, pass the filename of "-"
-
-```bash
-python matrix.py | python scripts/invoke.py --from_file -
-```
-
-When the script is finished, each of the 27 combinations
-of adjective, sampler and CFG will be executed.
-
-The command-line interface provides `!fetch` and `!replay` commands
-which allow you to read the prompts from a single previously-generated
-image or a whole directory of them, write the prompts to a file, and
-then replay them. Or you can create your own file of prompts and feed
-them to the command-line client from within an interactive session.
-See [Command-Line Interface](CLI.md) for details.
-
----
-
 ## **Negative and Unconditioned Prompts**
 
-Any words between a pair of square brackets will instruct Stable Diffusion to
-attempt to ban the concept from the generated image.
+Any words between a pair of square brackets will instruct Stable
+Diffusion to attempt to ban the concept from the generated image. The
+same effect is achieved by placing words in the "Negative Prompts"
+textbox in the Web UI.
 
 ```text
 this is a test prompt [not really] to make you understand [cool] how this works.
@@ -87,7 +22,9 @@ Here's a prompt that depicts what it does.
 
 original prompt:
 
-`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
+
+`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
 
 <figure markdown>
 
@@ -99,7 +36,8 @@ That image has a woman, so if we want the horse without a rider, we can
 influence the image not to have a woman by putting [woman] in the prompt, like
 this:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -110,7 +48,8 @@ this:
 That's nice - but say we also don't want the image to be quite so blue. We can
 add "blue" to the list of negative prompts, so it's now [woman blue]:
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -121,7 +60,8 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
 Getting close - but there's no sense in having a saddle when our horse doesn't
 have a rider, so we'll add one more negative prompt: [woman blue saddle].
 
-`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
+(same parameters as above)
 
 <figure markdown>
 
@@ -261,19 +201,6 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
-Note that `prompt2prompt` is not currently working with the runwayML inpainting
-model, and may never work due to the way this model is set up. If you attempt to
-use `prompt2prompt` you will get the original image back. However, since this
-model is so good at inpainting, a good substitute is to use the `clipseg` text
-masking option:
-
-```bash
-invoke> a fluffy cat eating a hotdog
-Outputs:
-[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
-invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
-```
-
 ### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
@@ -374,6 +301,48 @@ summoning up the concept of some sort of scifi creature? Let's find out.
 Indeed, removing the word "hybrid" produces an image that is more like what we'd
 expect.
 
-In conclusion, prompt blending is great for exploring creative space, but can be
-difficult to direct. A forthcoming release of InvokeAI will feature more
-deterministic prompt weighting.
+## Dynamic Prompts
+
+Dynamic Prompts are a powerful feature designed to produce a variety of prompts based on user-defined options. Using a special syntax, you can construct a prompt with multiple possibilities, and the system will automatically generate a series of permutations based on your settings. This is extremely beneficial for ideation, exploring various scenarios, or testing different concepts swiftly and efficiently.
+
+### Structure of a Dynamic Prompt
+
+A Dynamic Prompt comprises of regular text, supplemented with alternatives enclosed within curly braces {} and separated by a vertical bar |. For example: {option1|option2|option3}. The system will then select one of the options to include in the final prompt. This flexible system allows for options to be placed throughout the text as needed.
+
+Furthermore, Dynamic Prompts can designate multiple selections from a single group of options. This feature is triggered by prefixing the options with a numerical value followed by $$. For example, in {2$$option1|option2|option3}, the system will select two distinct options from the set.
+### Creating Dynamic Prompts
+
+To create a Dynamic Prompt, follow these steps:
+
+    Draft your sentence or phrase, identifying words or phrases with multiple possible options.
+    Encapsulate the different options within curly braces {}.
+    Within the braces, separate each option using a vertical bar |.
+    If you want to include multiple options from a single group, prefix with the desired number and $$.
+
+For instance: A {house|apartment|lodge|cottage} in {summer|winter|autumn|spring} designed in {2$$style1|style2|style3}.
+### How Dynamic Prompts Work
+
+Once a Dynamic Prompt is configured, the system generates an array of combinations using the options provided. Each group of options in curly braces is treated independently, with the system selecting one option from each group. For a prefixed set (e.g., 2$$), the system will select two distinct options.
+
+For example, the following prompts could be generated from the above Dynamic Prompt:
+
+    A house in summer designed in style1, style2
+    A lodge in autumn designed in style3, style1
+    A cottage in winter designed in style2, style3
+    And many more!
+
+When the `Combinatorial` setting is on, Invoke will disable the "Images" selection, and generate every combination up until the setting for Max Prompts is reached.
+When the `Combinatorial` setting is off, Invoke will randomly generate combinations up until the setting for Images has been reached.
+
+
+
+### Tips and Tricks for Using Dynamic Prompts
+
+Below are some useful strategies for creating Dynamic Prompts:
+
+    Utilize Dynamic Prompts to generate a wide spectrum of prompts, perfect for brainstorming and exploring diverse ideas.
+    Ensure that the options within a group are contextually relevant to the part of the sentence where they are used. For instance, group building types together, and seasons together.
+    Apply the 2$$ prefix when you want to incorporate more than one option from a single group. This becomes quite handy when mixing and matching different elements.
+    Experiment with different quantities for the prefix. For example, 3$$ will select three distinct options.
+    Be aware of coherence in your prompts. Although the system can generate all possible combinations, not all may semantically make sense. Therefore, carefully choose the options for each group.
+    Always review and fine-tune the generated prompts as needed. While Dynamic Prompts can help you generate a multitude of combinations, the final polishing and refining remain in your hands.

docs/features/TEXTUAL_INVERSION.md

@@ -1,287 +0,0 @@
----
-title: Textual-Inversion
----
-
-# :material-file-document: Textual Inversion
-
-## **Personalizing Text-to-Image Generation**
-
-You may personalize the generated images to provide your own styles or objects
-by training a new LDM checkpoint and introducing a new vocabulary to the fixed
-model as a (.pt) embeddings file. Alternatively, you may use or train
-HuggingFace Concepts embeddings files (.bin) from
-<https://huggingface.co/sd-concepts-library> and its associated
-notebooks.
-
-## **Hardware and Software Requirements**
-
-You will need a GPU to perform training in a reasonable length of
-time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
-training process further. During training, about ~8 GB is temporarily
-needed in order to store intermediate models, checkpoints and logs.
-
-## **Preparing for Training**
-
-To train, prepare a folder that contains 3-5 images that illustrate
-the object or concept. It is good to provide a variety of examples or
-poses to avoid overtraining the system. Format these images as PNG
-(preferred) or JPG. You do not need to resize or crop the images in
-advance, but for more control you may wish to do so.
-
-Place the training images in a directory on the machine InvokeAI runs
-on. We recommend placing them in a subdirectory of the
-`text-inversion-training-data` folder located in the InvokeAI root
-directory, ordinarily `~/invokeai` (Linux/Mac), or
-`C:\Users\your_name\invokeai` (Windows). For example, to create an
-embedding for the "psychedelic" style, you'd place the training images
-into the directory
-`~invokeai/text-inversion-training-data/psychedelic`.
-
-## **Launching Training Using the Console Front End**
-
-InvokeAI 2.3 and higher comes with a text console-based training front
-end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
-start the front end by selecting choice (3):
-
-```sh
-Do you want to generate images using the
-1. command-line
-2. browser-based UI
-3. textual inversion training
-4. open the developer console
-Please enter 1, 2, 3, or 4: [1] 3
-```
-
-From the command line, with the InvokeAI virtual environment active,
-you can launch the front end with the command `invokeai-ti --gui`.
-
-This will launch a text-based front end that will look like this:
-
-<figure markdown>
-![ti-frontend](../assets/textual-inversion/ti-frontend.png)
-</figure>
-
-The interface is keyboard-based. Move from field to field using
-control-N (^N) to move to the next field and control-P (^P) to the
-previous one. <Tab> and <shift-TAB> work as well. Once a field is
-active, use the cursor keys. In a checkbox group, use the up and down
-cursor keys to move from choice to choice, and <space> to select a
-choice. In a scrollbar, use the left and right cursor keys to increase
-and decrease the value of the scroll. In textfields, type the desired
-values.
-
-The number of parameters may look intimidating, but in most cases the
-predefined defaults work fine. The red circled fields in the above
-illustration are the ones you will adjust most frequently.
-
-### Model Name
-
-This will list all the diffusers models that are currently
-installed. Select the one you wish to use as the basis for your
-embedding. Be aware that if you use a SD-1.X-based model for your
-training, you will only be able to use this embedding with other
-SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
-be able to use the embeddings with models based on SD-2.X.
-
-### Trigger Term
-
-This is the prompt term you will use to trigger the embedding. Type a
-single word or phrase you wish to use as the trigger, example
-"psychedelic" (without angle brackets). Within InvokeAI, you will then
-be able to activate the trigger using the syntax `<psychedelic>`.
-
-### Initializer
-
-This is a single character that is used internally during the training
-process as a placeholder for the trigger term. It defaults to "*" and
-can usually be left alone.
-
-### Resume from last saved checkpoint
-
-As training proceeds, textual inversion will write a series of
-intermediate files that can be used to resume training from where it
-was left off in the case of an interruption. This checkbox will be
-automatically selected if you provide a previously used trigger term
-and at least one checkpoint file is found on disk.
-
-Note that as of 20 January 2023, resume does not seem to be working
-properly due to an issue with the upstream code.
-
-### Data Training Directory
-
-This is the location of the images to be used for training. When you
-select a trigger term like "my-trigger", the frontend will prepopulate
-this field with `~/invokeai/text-inversion-training-data/my-trigger`,
-but you can change the path to wherever you want.
-
-### Output Destination Directory
-
-This is the location of the logs, checkpoint files, and embedding
-files created during training. When you select a trigger term like
-"my-trigger", the frontend will prepopulate this field with
-`~/invokeai/text-inversion-output/my-trigger`, but you can change the
-path to wherever you want.
-
-### Image resolution
-
-The images in the training directory will be automatically scaled to
-the value you use here. For best results, you will want to use the
-same default resolution of the underlying model (512 pixels for
-SD-1.5, 768 for the larger version of SD-2.1).
-
-### Center crop images
-
-If this is selected, your images will be center cropped to make them
-square before resizing them to the desired resolution. Center cropping
-can indiscriminately cut off the top of subjects' heads for portrait
-aspect images, so if you have images like this, you may wish to use a
-photoeditor to manually crop them to a square aspect ratio.
-
-### Mixed precision
-
-Select the floating point precision for the embedding. "no" will
-result in a full 32-bit precision, "fp16" will provide 16-bit
-precision, and "bf16" will provide mixed precision (only available
-when XFormers is used).
-
-### Max training steps
-
-How many steps the training will take before the model converges. Most
-training sets will converge with 2000-3000 steps.
-
-### Batch size
-
-This adjusts how many training images are processed simultaneously in
-each step. Higher values will cause the training process to run more
-quickly, but use more memory. The default size will run with GPUs with
-as little as 12 GB.
-
-### Learning rate
-
-The rate at which the system adjusts its internal weights during
-training. Higher values risk overtraining (getting the same image each
-time), and lower values will take more steps to train a good
-model. The default of 0.0005 is conservative; you may wish to increase
-it to 0.005 to speed up training.
-
-### Scale learning rate by number of GPUs, steps and batch size
-
-If this is selected (the default) the system will adjust the provided
-learning rate to improve performance.
-
-### Use xformers acceleration
-
-This will activate XFormers memory-efficient attention. You need to
-have XFormers installed for this to have an effect.
-
-### Learning rate scheduler
-
-This adjusts how the learning rate changes over the course of
-training. The default "constant" means to use a constant learning rate
-for the entire training session. The other values scale the learning
-rate according to various formulas.
-
-Only "constant" is supported by the XFormers library.
-
-### Gradient accumulation steps
-
-This is a parameter that allows you to use bigger batch sizes than
-your GPU's VRAM would ordinarily accommodate, at the cost of some
-performance.
-
-### Warmup steps
-
-If "constant_with_warmup" is selected in the learning rate scheduler,
-then this provides the number of warmup steps. Warmup steps have a
-very low learning rate, and are one way of preventing early
-overtraining.
-
-## The training run
-
-Start the training run by advancing to the OK button (bottom right)
-and pressing <enter>. A series of progress messages will be displayed
-as the training process proceeds. This may take an hour or two,
-depending on settings and the speed of your system. Various log and
-checkpoint files will be written into the output directory (ordinarily
-`~/invokeai/text-inversion-output/my-model/`)
-
-At the end of successful training, the system will copy the file
-`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
-directory, using a subdirectory named after the trigger token. For
-example, if the trigger token was `psychedelic`, then look for the
-embeddings file in
-`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
-
-You may now launch InvokeAI and try out a prompt that uses the trigger
-term. For example `a plate of banana sushi in <psychedelic> style`.
-
-## **Training with the Command-Line Script**
-
-Training can also be done using a traditional command-line script. It
-can be launched from within the "developer's console", or from the
-command line after activating InvokeAI's virtual environment.
-
-It accepts a large number of arguments, which can be summarized by
-passing the `--help` argument:
-
-```sh
-invokeai-ti --help
-```
-
-Typical usage is shown here:
-```sh
-invokeai-ti \
-       --model=stable-diffusion-1.5 \
-       --resolution=512 \
-       --learnable_property=style \
-       --initializer_token='*' \
-       --placeholder_token='<psychedelic>' \
-       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
-       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
-       --scale_lr \
-       --train_batch_size=8 \
-       --gradient_accumulation_steps=4 \
-       --max_train_steps=3000 \
-       --learning_rate=0.0005 \
-       --resume_from_checkpoint=latest \
-       --lr_scheduler=constant \
-       --mixed_precision=fp16 \
-       --only_save_embeds
-```
-
-## Using Embeddings
-
-After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.
-
-These will be automatically loaded when you start InvokeAI.
-
-Add the trigger word, surrounded by angle brackets, to use that embedding. For example, if your trigger word was `terence`, use `<terence>` in prompts. This is the same syntax used by the HuggingFace concepts library.
-
-**Note:** `.pt` embeddings do not require the angle brackets.
-
-## Troubleshooting
-
-### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
-
-Messages like this indicate you trained the embedding on a different base model than the currently selected one.
-
-For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
-
-## Reading
-
-For more information on textual inversion, please see the following
-resources:
-
-* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
-  associated paper for details and limitations.
-* [HuggingFace's textual inversion training
-  page](https://huggingface.co/docs/diffusers/training/text_inversion)
-* [HuggingFace example script
-  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
-  (Note that this script is similar to, but not identical, to
-  `textual_inversion`, but produces embed files that are completely compatible.
-
----
-
-copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/TRAINING.md

@@ -0,0 +1,286 @@
+---
+title: Training
+---
+
+# :material-file-document: Training
+
+# Textual Inversion Training
+## **Personalizing Text-to-Image Generation**
+
+You may personalize the generated images to provide your own styles or objects
+by training a new LDM checkpoint and introducing a new vocabulary to the fixed
+model as a (.pt) embeddings file. Alternatively, you may use or train
+HuggingFace Concepts embeddings files (.bin) from
+<https://huggingface.co/sd-concepts-library> and its associated
+notebooks.
+
+## **Hardware and Software Requirements**
+
+You will need a GPU to perform training in a reasonable length of
+time, and at least 12 GB of VRAM. We recommend using the [`xformers`
+library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
+training process further. During training, about ~8 GB is temporarily
+needed in order to store intermediate models, checkpoints and logs.
+
+## **Preparing for Training**
+
+To train, prepare a folder that contains 3-5 images that illustrate
+the object or concept. It is good to provide a variety of examples or
+poses to avoid overtraining the system. Format these images as PNG
+(preferred) or JPG. You do not need to resize or crop the images in
+advance, but for more control you may wish to do so.
+
+Place the training images in a directory on the machine InvokeAI runs
+on. We recommend placing them in a subdirectory of the
+`text-inversion-training-data` folder located in the InvokeAI root
+directory, ordinarily `~/invokeai` (Linux/Mac), or
+`C:\Users\your_name\invokeai` (Windows). For example, to create an
+embedding for the "psychedelic" style, you'd place the training images
+into the directory
+`~invokeai/text-inversion-training-data/psychedelic`.
+
+## **Launching Training Using the Console Front End**
+
+InvokeAI 2.3 and higher comes with a text console-based training front
+end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
+start the front end by selecting choice (3):
+
+```sh
+Do you want to generate images using the
+1: Browser-based UI
+2: Command-line interface
+3: Run textual inversion training
+4: Merge models (diffusers type only)
+5: Download and install models
+6: Change InvokeAI startup options
+7: Re-run the configure script to fix a broken install
+8: Open the developer console
+9: Update InvokeAI
+10: Command-line help
+Q: Quit
+
+Please enter 1-10, Q: [1] 
+```
+
+From the command line, with the InvokeAI virtual environment active,
+you can launch the front end with the command `invokeai-ti --gui`.
+
+This will launch a text-based front end that will look like this:
+
+<figure markdown>
+![ti-frontend](../assets/textual-inversion/ti-frontend.png)
+</figure>
+
+The interface is keyboard-based. Move from field to field using
+control-N (^N) to move to the next field and control-P (^P) to the
+previous one. <Tab> and <shift-TAB> work as well. Once a field is
+active, use the cursor keys. In a checkbox group, use the up and down
+cursor keys to move from choice to choice, and <space> to select a
+choice. In a scrollbar, use the left and right cursor keys to increase
+and decrease the value of the scroll. In textfields, type the desired
+values.
+
+The number of parameters may look intimidating, but in most cases the
+predefined defaults work fine. The red circled fields in the above
+illustration are the ones you will adjust most frequently.
+
+### Model Name
+
+This will list all the diffusers models that are currently
+installed. Select the one you wish to use as the basis for your
+embedding. Be aware that if you use a SD-1.X-based model for your
+training, you will only be able to use this embedding with other
+SD-1.X-based models. Similarly, if you train on SD-2.X, you will only
+be able to use the embeddings with models based on SD-2.X.
+
+### Trigger Term
+
+This is the prompt term you will use to trigger the embedding. Type a
+single word or phrase you wish to use as the trigger, example
+"psychedelic" (without angle brackets). Within InvokeAI, you will then
+be able to activate the trigger using the syntax `<psychedelic>`.
+
+### Initializer
+
+This is a single character that is used internally during the training
+process as a placeholder for the trigger term. It defaults to "*" and
+can usually be left alone.
+
+### Resume from last saved checkpoint
+
+As training proceeds, textual inversion will write a series of
+intermediate files that can be used to resume training from where it
+was left off in the case of an interruption. This checkbox will be
+automatically selected if you provide a previously used trigger term
+and at least one checkpoint file is found on disk.
+
+Note that as of 20 January 2023, resume does not seem to be working
+properly due to an issue with the upstream code.
+
+### Data Training Directory
+
+This is the location of the images to be used for training. When you
+select a trigger term like "my-trigger", the frontend will prepopulate
+this field with `~/invokeai/text-inversion-training-data/my-trigger`,
+but you can change the path to wherever you want.
+
+### Output Destination Directory
+
+This is the location of the logs, checkpoint files, and embedding
+files created during training. When you select a trigger term like
+"my-trigger", the frontend will prepopulate this field with
+`~/invokeai/text-inversion-output/my-trigger`, but you can change the
+path to wherever you want.
+
+### Image resolution
+
+The images in the training directory will be automatically scaled to
+the value you use here. For best results, you will want to use the
+same default resolution of the underlying model (512 pixels for
+SD-1.5, 768 for the larger version of SD-2.1).
+
+### Center crop images
+
+If this is selected, your images will be center cropped to make them
+square before resizing them to the desired resolution. Center cropping
+can indiscriminately cut off the top of subjects' heads for portrait
+aspect images, so if you have images like this, you may wish to use a
+photoeditor to manually crop them to a square aspect ratio.
+
+### Mixed precision
+
+Select the floating point precision for the embedding. "no" will
+result in a full 32-bit precision, "fp16" will provide 16-bit
+precision, and "bf16" will provide mixed precision (only available
+when XFormers is used).
+
+### Max training steps
+
+How many steps the training will take before the model converges. Most
+training sets will converge with 2000-3000 steps.
+
+### Batch size
+
+This adjusts how many training images are processed simultaneously in
+each step. Higher values will cause the training process to run more
+quickly, but use more memory. The default size will run with GPUs with
+as little as 12 GB.
+
+### Learning rate
+
+The rate at which the system adjusts its internal weights during
+training. Higher values risk overtraining (getting the same image each
+time), and lower values will take more steps to train a good
+model. The default of 0.0005 is conservative; you may wish to increase
+it to 0.005 to speed up training.
+
+### Scale learning rate by number of GPUs, steps and batch size
+
+If this is selected (the default) the system will adjust the provided
+learning rate to improve performance.
+
+### Use xformers acceleration
+
+This will activate XFormers memory-efficient attention. You need to
+have XFormers installed for this to have an effect.
+
+### Learning rate scheduler
+
+This adjusts how the learning rate changes over the course of
+training. The default "constant" means to use a constant learning rate
+for the entire training session. The other values scale the learning
+rate according to various formulas.
+
+Only "constant" is supported by the XFormers library.
+
+### Gradient accumulation steps
+
+This is a parameter that allows you to use bigger batch sizes than
+your GPU's VRAM would ordinarily accommodate, at the cost of some
+performance.
+
+### Warmup steps
+
+If "constant_with_warmup" is selected in the learning rate scheduler,
+then this provides the number of warmup steps. Warmup steps have a
+very low learning rate, and are one way of preventing early
+overtraining.
+
+## The training run
+
+Start the training run by advancing to the OK button (bottom right)
+and pressing <enter>. A series of progress messages will be displayed
+as the training process proceeds. This may take an hour or two,
+depending on settings and the speed of your system. Various log and
+checkpoint files will be written into the output directory (ordinarily
+`~/invokeai/text-inversion-output/my-model/`)
+
+At the end of successful training, the system will copy the file
+`learned_embeds.bin` into the InvokeAI root directory's `embeddings`
+directory, using a subdirectory named after the trigger token. For
+example, if the trigger token was `psychedelic`, then look for the
+embeddings file in
+`~/invokeai/embeddings/psychedelic/learned_embeds.bin`
+
+You may now launch InvokeAI and try out a prompt that uses the trigger
+term. For example `a plate of banana sushi in <psychedelic> style`.
+
+## **Training with the Command-Line Script**
+
+Training can also be done using a traditional command-line script. It
+can be launched from within the "developer's console", or from the
+command line after activating InvokeAI's virtual environment.
+
+It accepts a large number of arguments, which can be summarized by
+passing the `--help` argument:
+
+```sh
+invokeai-ti --help
+```
+
+Typical usage is shown here:
+```sh
+invokeai-ti \
+       --model=stable-diffusion-1.5 \
+       --resolution=512 \
+       --learnable_property=style \
+       --initializer_token='*' \
+       --placeholder_token='<psychedelic>' \
+       --train_data_dir=/home/lstein/invokeai/training-data/psychedelic \
+       --output_dir=/home/lstein/invokeai/text-inversion-training/psychedelic \
+       --scale_lr \
+       --train_batch_size=8 \
+       --gradient_accumulation_steps=4 \
+       --max_train_steps=3000 \
+       --learning_rate=0.0005 \
+       --resume_from_checkpoint=latest \
+       --lr_scheduler=constant \
+       --mixed_precision=fp16 \
+       --only_save_embeds
+```
+
+## Troubleshooting
+
+### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`
+
+Messages like this indicate you trained the embedding on a different base model than the currently selected one.
+
+For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512).
+
+## Reading
+
+For more information on textual inversion, please see the following
+resources:
+
+* The [textual inversion repository](https://github.com/rinongal/textual_inversion) and
+  associated paper for details and limitations.
+* [HuggingFace's textual inversion training
+  page](https://huggingface.co/docs/diffusers/training/text_inversion)
+* [HuggingFace example script
+  documentation](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion)
+  (Note that this script is similar to, but not identical, to
+  `textual_inversion`, but produces embed files that are completely compatible.
+
+---
+
+copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/VARIATIONS.md

@@ -6,9 +6,7 @@ title: Variations
 
 ## Intro
 
-Release 1.13 of SD-Dream adds support for image variations.
-
-You are able to do the following:
+InvokeAI's support for variations enables you to do the following:
 
 1. Generate a series of systematic variations of an image, given a prompt. The
    amount of variation from one image to the next can be controlled.
@@ -30,19 +28,7 @@ The prompt we will use throughout is:
 This will be indicated as `#!bash "prompt"` in the examples below.
 
 First we let SD create a series of images in the usual way, in this case
-requesting six iterations:
-
-```bash
-invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
-...
-Outputs:
-./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
-./outputs/Xena/000001.1880768722.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1880768722
-./outputs/Xena/000001.332057179.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S332057179
-./outputs/Xena/000001.2224800325.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S2224800325
-./outputs/Xena/000001.465250761.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S465250761
-./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
-```
+requesting six iterations.
 
 <figure markdown>
 ![var1](../assets/variation_walkthru/000001.3357757885.png)
@@ -53,22 +39,16 @@ Outputs:
 
 ## Step 2 - Generating Variations
 
-Let's try to generate some variations. Using the same seed, we pass the argument
-`-v0.1` (or --variant_amount), which generates a series of variations each
-differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
-with higher numbers being larger amounts of variation.
+Let's try to generate some variations on this image. We select the "*"
+symbol in the line of icons above the image in order to fix the prompt
+and seed. Then we open up the "Variations" section of the generation
+panel and use the slider to set the variation amount to 0.2. The
+higher this value, the more each generated image will differ from the
+previous one.
 
-```bash
-invoke> "prompt" -n6 -S3357757885 -v0.2
-...
-Outputs:
-./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
-./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
-./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
-./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
-./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
-./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
-```
+Now we run the prompt a second time, requesting six iterations. You
+will see six images that are thematically related to each other. Try
+increasing and decreasing the variation amount and see what happens.
 
 ### **Variation Sub Seeding**
 

docs/features/WEB.md

@@ -299,14 +299,6 @@ initial image" icons are located.
 
 See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
 
-## Parting remarks
-
-This concludes the walkthrough, but there are several more features that you can
-explore. Please check out the [Command Line Interface](CLI.md) documentation for
-further explanation of the advanced features that were not covered here.
-
-The WebUI is only rapid development. Check back regularly for updates!
-
 ## Reference
 
 ### Additional Options
@@ -349,11 +341,9 @@ the settings configured in the toolbar.
 
 See below for additional documentation related to each feature:
 
-- [Core Prompt Settings](./CLI.md)
 - [Variations](./VARIATIONS.md)
 - [Upscaling](./POSTPROCESS.md#upscaling)
 - [Image to Image](./IMG2IMG.md)
-- [Inpainting](./INPAINTING.md)
 - [Other](./OTHER.md)
 
 #### Invocation Gallery

docs/features/index.md

@@ -13,28 +13,16 @@ Build complex scenes by combine and modifying multiple images in a stepwise
 fashion. This feature combines img2img, inpainting and outpainting in
 a single convenient digital artist-optimized user interface.
 
-### * The [Command Line Interface (CLI)](CLI.md)
-Scriptable access to InvokeAI's features.
-
 ## Image Generation
 ### * [Prompt Engineering](PROMPTS.md)
 Get the images you want with the InvokeAI  prompt engineering language.
 
-## * [Post-Processing](POSTPROCESS.md)
-Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
-
 ## * The [Concepts Library](CONCEPTS.md)
 Add custom subjects and styles using HuggingFace's repository of embeddings.
 
-### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
+### * [Image-to-Image Guide](IMG2IMG.md)
 Use a seed image to build new creations in the CLI.
 
-### * [Inpainting Guide for the CLI](INPAINTING.md)
-Selectively erase and replace portions of an existing image in the CLI.
-
-### * [Outpainting Guide for the CLI](OUTPAINTING.md)
-Extend the borders of the image with an "outcrop" function within the CLI.
-
 ### * [Generating Variations](VARIATIONS.md)
 Have an image you like and want to generate many more like it? Variations
 are the ticket.
@@ -57,6 +45,9 @@ Personalize models by adding your own style or subjects.
 ## * [The NSFW Checker](NSFW.md)
 Prevent InvokeAI from displaying unwanted racy images.
 
+## * [Controlling Logging](LOGGING.md)
+Control how InvokeAI logs status messages.
+
 ## * [Miscellaneous](OTHER.md)
 Run InvokeAI on Google Colab, generate images with repeating patterns,
 batch process a file of prompts, increase the "creativity" of image

docs/index.md

@@ -13,6 +13,7 @@ title: Home
 
 <div align="center" markdown>
 
+
 [![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI)
 
 [![discord badge]][discord link]
@@ -67,7 +68,7 @@ title: Home
 implementation of Stable Diffusion, the open source text-to-image and
 image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
-Mac and Linux machines, and runs on GPU cards with as little as 4 GB or RAM.
+Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 **Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>]
 [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a
@@ -131,17 +132,13 @@ This method is recommended for those familiar with running Docker containers
 - [WebUI overview](features/WEB.md)
 - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
 - [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+
 <!-- separator -->
-### The InvokeAI Command Line Interface
-- [Command Line Interace Reference Guide](features/CLI.md)
-<!-- separator -->
+
 ### Image Management
 - [Image2Image](features/IMG2IMG.md)
-- [Inpainting](features/INPAINTING.md)
-- [Outpainting](features/OUTPAINTING.md)
 - [Adding custom styles and subjects](features/CONCEPTS.md)
 - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
-- [Embiggen upscaling](features/EMBIGGEN.md)
 - [Other Features](features/OTHER.md)
 
 <!-- separator -->
@@ -156,83 +153,60 @@ This method is recommended for those familiar with running Docker containers
 - [Prompt Syntax](features/PROMPTS.md)
 - [Generating Variations](features/VARIATIONS.md)
 
-## :octicons-log-16: Latest Changes
+## :octicons-log-16: Important Changes Since Version 2.3
 
-### v2.3.0 <small>(9 February 2023)</small>
+### Nodes
 
-#### Migration to Stable Diffusion `diffusers` models
+Behind the scenes, InvokeAI has been completely rewritten to support
+"nodes," small unitary operations that can be combined into graphs to
+form arbitrary workflows. For example, there is a prompt node that
+processes the prompt string and feeds it to a text2latent node that
+generates a latent image. The latents are then fed to a latent2image
+node that translates the latent image into a PNG.
 
-Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
+The WebGUI has a node editor that allows you to graphically design and
+execute custom node graphs. The ability to save and load graphs is
+still a work in progress, but coming soon.
 
-When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
+### Command-Line Interface Retired
 
-To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
+The original "invokeai" command-line interface has been retired. The
+`invokeai` command will now launch a new command-line client that can
+be used by developers to create and test nodes. It is not intended to
+be used for routine image generation or manipulation.
 
-* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
-* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
-* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
+To launch the Web GUI from the command-line, use the command
+`invokeai-web` rather than the traditional `invokeai --web`.
 
-The WebGUI offers similar functionality for model management.
+### ControlNet
 
-For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
+This version of InvokeAI features ControlNet, a system that allows you
+to achieve exact poses for human and animal figures by providing a
+model to follow. Full details are found in [ControlNet](features/CONTROLNET.md)
 
-Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
+### New Schedulers
 
-#### Support for the `XFormers` Memory-Efficient Crossattention Package
+The list of schedulers has been completely revamped and brought up to date:
 
-On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
+| **Short Name** | **Scheduler**                   | **Notes**                   |
+|----------------|---------------------------------|-----------------------------|
+| **ddim**       | DDIMScheduler                   |                             |
+| **ddpm**       | DDPMScheduler                   |                             |
+| **deis**       | DEISMultistepScheduler          |                             |
+| **lms**        | LMSDiscreteScheduler            |                             |
+| **pndm**       | PNDMScheduler                   |                             |
+| **heun**       | HeunDiscreteScheduler           | original noise schedule     |
+| **heun_k**     | HeunDiscreteScheduler           | using karras noise schedule |
+| **euler**      | EulerDiscreteScheduler          | original noise schedule     |
+| **euler_k**    | EulerDiscreteScheduler          | using karras noise schedule |
+| **kdpm_2**     | KDPM2DiscreteScheduler          |                             |
+| **kdpm_2_a**   | KDPM2AncestralDiscreteScheduler |                             |
+| **dpmpp_2s**   | DPMSolverSinglestepScheduler    |                             |
+| **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
+| **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
+| **unipc**      | UniPCMultistepScheduler         | CPU only                    |
 
-The caveat with using `xformers` is that it introduces slightly non-deterministic behavior, and images generated using the same seed and other settings will be subtly different between invocations. Generally the changes are unnoticeable unless you rapidly shift back and forth between images, but to disable `xformers` and restore fully deterministic behavior, you may launch InvokeAI using the `--no-xformers` option. This is most conveniently done by opening the file `invokeai/invokeai.init` with a text editor, and adding the line `--no-xformers` at the bottom.
-
-#### A Negative Prompt Box in the WebUI
-
-There is now a separate text input box for negative prompts in the WebUI. This is convenient for stashing frequently-used negative prompts ("mangled limbs, bad anatomy"). The `[negative prompt]` syntax continues to work in the main prompt box as well.
-
-To see exactly how your prompts are being parsed, launch `invokeai` with the `--log_tokenization` option. The console window will then display the tokenization process for both positive and negative prompts.
-
-#### Model Merging
-
-Version 2.3.0 offers an intuitive user interface for merging up to three Stable Diffusion models using an intuitive user interface. Model merging allows you to mix the behavior of models to achieve very interesting effects. To use this, each of the models must already be imported into InvokeAI and saved in `diffusers` format, then launch the merger using a new menu item in the InvokeAI launcher script (`invoke.sh`, `invoke.bat`) or directly from the command line with `invokeai-merge --gui`. You will be prompted to select the models to merge, the proportions in which to mix them, and the mixing algorithm. The script will create a new merged `diffusers` model and import it into InvokeAI for your use.
-
-See [MODEL MERGING](https://invoke-ai.github.io/InvokeAI/features/MODEL_MERGING/) for more details.
-
-#### Textual Inversion Training
-
-Textual Inversion (TI) is a technique for training a Stable Diffusion model to emit a particular subject or style when triggered by a keyword phrase. You can perform TI training by placing a small number of images of the subject or style in a directory, and choosing a distinctive trigger phrase, such as "pointillist-style". After successful training, The subject or style will be activated by including `<pointillist-style>` in your prompt.
-
-Previous versions of InvokeAI were able to perform TI, but it required using a command-line script with dozens of obscure command-line arguments. Version 2.3.0 features an intuitive TI frontend that will build a TI model on top of any `diffusers` model. To access training you can launch from a new item in the launcher script or from the command line using `invokeai-ti --gui`.
-
-See [TEXTUAL INVERSION](https://invoke-ai.github.io/InvokeAI/features/TEXTUAL_INVERSION/) for further details.
-
-#### A New Installer Experience
-
-The InvokeAI installer has been upgraded in order to provide a smoother and hopefully more glitch-free experience. In addition, InvokeAI is now packaged as a PyPi project, allowing developers and power-users to install InvokeAI with the command `pip install InvokeAI  --use-pep517`. Please see [Installation](#installation) for details.
-
-Developers should be aware that the `pip` installation procedure has been simplified and that the `conda` method is no longer supported at all. Accordingly, the `environments_and_requirements` directory has been deleted from the repository.
-
-#### Command-line name changes
-
-All of InvokeAI's functionality, including the WebUI, command-line interface, textual inversion training and model merging, can all be accessed from the `invoke.sh` and `invoke.bat` launcher scripts. The menu of options has been expanded to add the new functionality. For the convenience of developers and power users, we have normalized the names of the InvokeAI command-line scripts:
-
-* `invokeai` -- Command-line client
-* `invokeai --web` -- Web GUI
-* `invokeai-merge --gui` -- Model merging script with graphical front end
-* `invokeai-ti --gui` -- Textual inversion script with graphical front end
-* `invokeai-configure` -- Configuration tool for initializing the `invokeai` directory and selecting popular starter models.
-
-For backward compatibility, the old command names are also recognized, including `invoke.py` and `configure-invokeai.py`. However, these are deprecated and will eventually be removed.
-
-Developers should be aware that the locations of the script's source code has been moved. The new locations are:
-* `invokeai` =>  `ldm/invoke/CLI.py`
-* `invokeai-configure` => `ldm/invoke/config/configure_invokeai.py`
-* `invokeai-ti`=> `ldm/invoke/training/textual_inversion.py`
-* `invokeai-merge` => `ldm/invoke/merge_diffusers`
-
-Developers are strongly encouraged to perform an "editable" install of InvokeAI using `pip install -e .  --use-pep517` in the Git repository, and then to call the scripts using their 2.3.0 names, rather than executing the scripts directly. Developers should also be aware that the several important data files have been relocated into a new directory named `invokeai`. This includes the WebGUI's `frontend` and `backend` directories, and the `INITIAL_MODELS.yaml` files used by the installer to select starter models. Eventually all InvokeAI modules will be in subdirectories of `invokeai`.
-
-Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
-For older changelogs, please visit the
-**[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
+Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
 
 ## :material-target: Troubleshooting
 
@@ -268,8 +242,3 @@ free to send me an email if you use and like the script.
 Original portions of the software are Copyright (c) 2022-23
 by [The InvokeAI Team](https://github.com/invoke-ai).
 
-## :octicons-book-24: Further Reading
-
-Please see the original README for more information on this software and
-underlying algorithm, located in the file
-[README-CompViz.md](other/README-CompViz.md).

docs/installation/010_INSTALL_AUTOMATED.md

@@ -89,7 +89,7 @@ experimental versions later.
          sudo apt update
          sudo apt install -y software-properties-common
          sudo add-apt-repository -y ppa:deadsnakes/ppa
-         sudo apt install python3.10 python3-pip python3.10-venv
+         sudo apt install -y python3.10 python3-pip python3.10-venv
          sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
          ```
 

docs/installation/020_INSTALL_MANUAL.md

@@ -216,7 +216,7 @@ manager, please follow these steps:
 9.  Run the command-line- or the web- interface:
 
     From within INVOKEAI_ROOT, activate the environment
-    (with `source .venv/bin/activate` or `.venv\scripts\activate), and then run
+    (with `source .venv/bin/activate` or `.venv\scripts\activate`), and then run
     the script `invokeai`. If the virtual environment you selected is NOT inside
     INVOKEAI_ROOT, then you must specify the path to the root directory by adding
     `--root_dir \path\to\invokeai` to the commands below:

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -87,18 +87,18 @@ Prior to installing PyPatchMatch, you need to take the following steps:
     sudo pacman -S --needed base-devel
     ```
 
-2. Install `opencv`:
+2. Install `opencv` and `blas`:
 
     ```sh
-    sudo pacman -S opencv
+    sudo pacman -S opencv blas
     ```
 
     or for CUDA support
 
     ```sh
-    sudo pacman -S opencv-cuda
+    sudo pacman -S opencv-cuda blas
     ```
-
+    
 3. Fix the naming of the `opencv` package configuration file:
 
     ```sh

installer/install.bat.in

@@ -38,6 +38,7 @@ echo    https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist
 echo.
 echo See %INSTRUCTIONS% for more details.
 echo.
+echo "For the best user experience we suggest enlarging or maximizing this window now."
 pause
 
 @rem ---------------------------- check Python version ---------------

installer/install.sh.in

@@ -25,7 +25,8 @@ done
 
 if [ -z "$PYTHON" ]; then
     echo "A suitable Python interpreter could not be found"
-    echo "Please install Python 3.9 or higher before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "Please install Python $MINIMUM_PYTHON_VERSION or higher (maximum $MAXIMUM_PYTHON_VERSION) before running this script. See instructions at $INSTRUCTIONS for help."
+    echo "For the best user experience we suggest enlarging or maximizing this window now."
     read -p "Press any key to exit"
     exit -1
 fi

installer/lib/installer.py

@@ -149,7 +149,7 @@ class Installer:
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
         """
         Install the InvokeAI application into the given runtime path
 
@@ -247,8 +247,9 @@ class InvokeAiInstance:
             pip[
                 "install",
                 "--require-virtualenv",
-                "torch",
-                "torchvision",
+                "torch~=2.0.0",
+                "torchmetrics==0.11.4",
+                "torchvision>=0.14.1",
                 "--force-reinstall",
                 "--find-links" if find_links is not None else None,
                 find_links,

installer/lib/messages.py

@@ -293,6 +293,8 @@ def introduction() -> None:
                 "3. Create initial configuration files.",
                 "",
                 "[i]At any point you may interrupt this program and resume later.",
+                "",
+                "[b]For the best user experience, please enlarge or maximize this window",
             ),
         )
     )

installer/templates/invoke.bat.in

@@ -7,42 +7,42 @@ call .venv\Scripts\activate.bat
 set INVOKEAI_ROOT=.
 
 :start
-echo Do you want to generate images using the
-echo 1. command-line interface
-echo 2. browser-based UI
-echo 3. run textual inversion training
-echo 4. merge models (diffusers type only)
-echo 5. download and install models
-echo 6. change InvokeAI startup options
-echo 7. re-run the configure script to fix a broken install
-echo 8. open the developer console
-echo 9. update InvokeAI
-echo 10. command-line help
-echo Q - quit
-set /P restore="Please enter 1-10, Q: [2] "
-if not defined restore set restore=2
-IF /I "%restore%" == "1" (
+echo Desired action:
+echo 1. Generate images with the browser-based interface
+echo 2. Explore InvokeAI nodes using a command-line interface
+echo 3. Run textual inversion training
+echo 4. Merge models (diffusers type only)
+echo 5. Download and install models
+echo 6. Change InvokeAI startup options
+echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
+echo 8. Open the developer console
+echo 9. Update InvokeAI
+echo 10. Command-line help
+echo Q - Quit
+set /P choice="Please enter 1-10, Q: [2] "
+if not defined choice set choice=1
+IF /I "%choice%" == "1" (
+    echo Starting the InvokeAI browser-based UI..
+    python .venv\Scripts\invokeai-web.exe %*
+) ELSE IF /I "%choice%" == "2" (
     echo Starting the InvokeAI command-line..
     python .venv\Scripts\invokeai.exe %*
-) ELSE IF /I "%restore%" == "2" (
-    echo Starting the InvokeAI browser-based UI..
-    python .venv\Scripts\invokeai.exe --web %*
-) ELSE IF /I "%restore%" == "3" (
+) ELSE IF /I "%choice%" == "3" (
     echo Starting textual inversion training..
     python .venv\Scripts\invokeai-ti.exe --gui
-) ELSE IF /I "%restore%" == "4" (
+) ELSE IF /I "%choice%" == "4" (
     echo Starting model merging script..
     python .venv\Scripts\invokeai-merge.exe --gui
-) ELSE IF /I "%restore%" == "5" (
+) ELSE IF /I "%choice%" == "5" (
     echo Running invokeai-model-install...
     python .venv\Scripts\invokeai-model-install.exe
-) ELSE IF /I "%restore%" == "6" (
+) ELSE IF /I "%choice%" == "6" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
-) ELSE IF /I "%restore%" == "7" (
+) ELSE IF /I "%choice%" == "7" (
     echo Running invokeai-configure...
     python .venv\Scripts\invokeai-configure.exe --yes --default_only
-) ELSE IF /I "%restore%" == "8" (
+) ELSE IF /I "%choice%" == "8" (
     echo Developer Console
     echo Python command is:
     where python
@@ -54,15 +54,15 @@ IF /I "%restore%" == "1" (
     echo *************************
     echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
     call cmd /k
-) ELSE IF /I "%restore%" == "9" (
+) ELSE IF /I "%choice%" == "9" (
    echo Running invokeai-update...
-   python .venv\Scripts\invokeai-update.exe %*
-) ELSE IF /I "%restore%" == "10" (
+   python -m invokeai.frontend.install.invokeai_update
+) ELSE IF /I "%choice%" == "10" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai.exe --help %*
     pause
     exit /b
-) ELSE IF /I "%restore%" == "q" (
+) ELSE IF /I "%choice%" == "q" (
     echo Goodbye!
     goto ending
 ) ELSE (

installer/templates/invoke.sh.in

@@ -1,5 +1,10 @@
 #!/bin/bash
 
+# MIT License
+
+# Coauthored by Lincoln Stein, Eugene Brodsky and Joshua Kimsey
+# Copyright 2023, The InvokeAI Development Team
+
 ####
 # This launch script assumes that:
 # 1. it is located in the runtime directory,
@@ -11,85 +16,168 @@
 
 set -eu
 
-# ensure we're in the correct folder in case user's CWD is somewhere else
+# Ensure we're in the correct folder in case user's CWD is somewhere else
 scriptdir=$(dirname "$0")
 cd "$scriptdir"
 
 . .venv/bin/activate
 
 export INVOKEAI_ROOT="$scriptdir"
+PARAMS=$@
 
-# set required env var for torch on mac MPS
+# Check to see if dialog is installed (it seems to be fairly standard, but good to check regardless) and if the user has passed the --no-tui argument to disable the dialog TUI
+tui=true
+if command -v dialog &>/dev/null; then
+    # This must use $@ to properly loop through the arguments passed by the user
+    for arg in "$@"; do
+        if [ "$arg" == "--no-tui" ]; then
+            tui=false
+            # Remove the --no-tui argument to avoid errors later on when passing arguments to InvokeAI
+            PARAMS=$(echo "$PARAMS" | sed 's/--no-tui//')
+            break
+        fi
+    done
+else
+    tui=false
+fi
+
+# Set required env var for torch on mac MPS
 if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-if [ "$0" != "bash" ]; then
-  while true
-  do
-    echo "Do you want to generate images using the"
-    echo "1. command-line interface"
-    echo "2. browser-based UI"
-    echo "3. run textual inversion training"
-    echo "4. merge models (diffusers type only)"
-    echo "5. download and install models"
-    echo "6. change InvokeAI startup options"
-    echo "7. re-run the configure script to fix a broken install"
-    echo "8. open the developer console"
-    echo "9. update InvokeAI"
-    echo "10. command-line help"
-    echo "Q - Quit"
-    echo ""
-    read -p "Please enter 1-10, Q: [2] " yn
-    choice=${yn:='2'}
-    case $choice in
-        1)
-            echo "Starting the InvokeAI command-line..."
-            invokeai $@
-            ;;
-        2)
-            echo "Starting the InvokeAI browser-based UI..."
-            invokeai --web $@
-            ;;
-        3)
-            echo "Starting Textual Inversion:"
-            invokeai-ti --gui $@
-            ;;
-        4)
-            echo "Merging Models:"
-            invokeai-merge --gui $@
-            ;;
-        5)
-            invokeai-model-install --root ${INVOKEAI_ROOT}
-            ;;
-        6)
-            invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
-            ;;
-        7)
-            invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
-            ;;
-        8)
-            echo "Developer Console:"
-            file_name=$(basename "${BASH_SOURCE[0]}")
-            bash --init-file "$file_name"
-            ;;
-        9)
-            echo "Update:"
-            invokeai-update
-            ;;
-        10)
-            invokeai --help
-            ;;
-        [qQ])
-            exit 0
-            ;;
-        *)
-            echo "Invalid selection"
-            exit;;
+# Primary function for the case statement to determine user input
+do_choice() {
+    case $1 in
+    1)
+        clear
+        printf "Generate images with a browser-based interface\n"
+        invokeai-web $PARAMS
+        ;;
+    2)
+        clear
+        printf "Explore InvokeAI nodes using a command-line interface\n"
+        invokeai $PARAMS
+        ;;
+    3)
+        clear
+        printf "Textual inversion training\n"
+        invokeai-ti --gui $PARAMS
+        ;;
+    4)
+        clear
+        printf "Merge models (diffusers type only)\n"
+        invokeai-merge --gui $PARAMS
+        ;;
+    5)
+        clear
+        printf "Download and install models\n"
+        invokeai-model-install --root ${INVOKEAI_ROOT}
+        ;;
+    6)
+        clear
+        printf "Change InvokeAI startup options\n"
+        invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
+        ;;
+    7)
+        clear
+        printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
+        invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
+        ;;
+    8)
+        clear
+        printf "Open the developer console\n"
+        file_name=$(basename "${BASH_SOURCE[0]}")
+        bash --init-file "$file_name"
+        ;;
+    9)
+        clear
+        printf "Update InvokeAI\n"
+        python -m invokeai.frontend.install.invokeai_update
+        ;;
+    10)
+        clear
+        printf "Command-line help\n"
+        invokeai --help
+        ;;
+    "HELP 1")
+        clear
+        printf "Command-line help\n"
+        invokeai --help
+        ;;
+    *)
+        clear
+        printf "Exiting...\n"
+        exit
+        ;;
     esac
- done
+    clear
+}
+
+# Dialog-based TUI for launcing Invoke functions
+do_dialog() {
+    options=(
+        1 "Generate images with a browser-based interface"
+        2 "Explore InvokeAI nodes using a command-line interface"
+        3 "Textual inversion training"
+        4 "Merge models (diffusers type only)"
+        5 "Download and install models"
+        6 "Change InvokeAI startup options"
+        7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
+        8 "Open the developer console"
+        9 "Update InvokeAI")
+
+    choice=$(dialog --clear \
+        --backtitle "\Zb\Zu\Z3InvokeAI" \
+        --colors \
+        --title "What would you like to do?" \
+        --ok-label "Run" \
+        --cancel-label "Exit" \
+        --help-button \
+        --help-label "CLI Help" \
+        --menu "Select an option:" \
+        0 0 0 \
+        "${options[@]}" \
+        2>&1 >/dev/tty) || clear
+    do_choice "$choice"
+    clear
+}
+
+# Command-line interface for launching Invoke functions
+do_line_input() {
+    clear
+    printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
+    printf "What would you like to do?\n"
+    printf "1: Generate images using the browser-based interface\n"
+    printf "2: Explore InvokeAI nodes using the command-line interface\n"
+    printf "3: Run textual inversion training\n"
+    printf "4: Merge models (diffusers type only)\n"
+    printf "5: Download and install models\n"
+    printf "6: Change InvokeAI startup options\n"
+    printf "7: Re-run the configure script to fix a broken install\n"
+    printf "8: Open the developer console\n"
+    printf "9: Update InvokeAI\n"
+    printf "10: Command-line help\n"
+    printf "Q: Quit\n\n"
+    read -p "Please enter 1-10, Q: [1] " yn
+    choice=${yn:='1'}
+    do_choice $choice
+    clear
+}
+
+# Main IF statement for launching Invoke with either the TUI or CLI, and for checking if the user is in the developer console
+if [ "$0" != "bash" ]; then
+    while true; do
+        if $tui; then
+            # .dialogrc must be located in the same directory as the invoke.sh script
+            export DIALOGRC="./.dialogrc"
+            do_dialog
+        else
+            do_line_input
+        fi
+    done
 else # in developer console
     python --version
-    echo "Press ^D to exit"
+    printf "Press ^D to exit\n"
     export PS1="(InvokeAI) \u@\h \w> "
 fi

invokeai/app/api/dependencies.py

@@ -1,24 +1,35 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from logging import Logger
 import os
-from argparse import Namespace
-
-from invokeai.app.services.metadata import PngMetadataService, MetadataServiceBase
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
+from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
+from invokeai.app.services.metadata import CoreMetadataService
+from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.urls import LocalUrlService
+from invokeai.backend.util.logging import InvokeAILogger
+from invokeai.version.invokeai_version import __version__
 
 from ..services.default_graphs import create_system_graphs
-
 from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-
-from ...backend import Globals
-from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
 from ..services.graph import GraphExecutionState, LibraryGraph
-from ..services.image_storage import DiskImageStorage
+from ..services.image_file_storage import DiskImageFileStorage
 from ..services.invocation_queue import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
 from ..services.invoker import Invoker
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
+from ..services.model_manager_service import ModelManagerService
 from .events import FastAPIEventService
 
 
@@ -38,52 +49,92 @@ def check_internet() -> bool:
         return False
 
 
+logger = InvokeAILogger.getLogger()
+
+
 class ApiDependencies:
     """Contains and initializes all dependencies for the API"""
 
     invoker: Invoker = None
 
     @staticmethod
-    def initialize(config, event_handler_id: int):
-        Globals.try_patchmatch = config.patchmatch
-        Globals.always_use_cpu = config.always_use_cpu
-        Globals.internet_available = config.internet_available and check_internet()
-        Globals.disable_xformers = not config.xformers
-        Globals.ckpt_convert = config.ckpt_convert
-
-        # TODO: Use a logger
-        print(f">> Internet connectivity is {Globals.internet_available}")
+    def initialize(config, event_handler_id: int, logger: Logger = logger):
+        logger.debug(f'InvokeAI version {__version__}')
+        logger.debug(f"Internet connectivity is {config.internet_available}")
 
         events = FastAPIEventService(event_handler_id)
 
-        output_folder = os.path.abspath(
-            os.path.join(os.path.dirname(__file__), "../../../../outputs")
-        )
-
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
-
-        metadata = PngMetadataService()
-
-        images = DiskImageStorage(f'{output_folder}/images', metadata_service=metadata)
+        output_folder = config.output_path
 
         # TODO: build a file/path manager?
-        db_location = os.path.join(output_folder, "invokeai.db")
+        db_location = config.db_path
+        db_location.parent.mkdir(parents=True, exist_ok=True)
+
+        graph_execution_manager = SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        )
+
+        urls = LocalUrlService()
+        metadata = CoreMetadataService()
+        image_record_storage = SqliteImageRecordStorage(db_location)
+        image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
+        names = SimpleNameService()
+        latents = ForwardCacheLatentsStorage(
+            DiskLatentsStorage(f"{output_folder}/latents")
+        )
+
+        board_record_storage = SqliteBoardRecordStorage(db_location)
+        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+
+        boards = BoardService(
+            services=BoardServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                board_record_storage=board_record_storage,
+                image_record_storage=image_record_storage,
+                url=urls,
+                logger=logger,
+            )
+        )
+
+        board_images = BoardImagesService(
+            services=BoardImagesServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                board_record_storage=board_record_storage,
+                image_record_storage=image_record_storage,
+                url=urls,
+                logger=logger,
+            )
+        )
+
+        images = ImageService(
+            services=ImageServiceDependencies(
+                board_image_record_storage=board_image_record_storage,
+                image_record_storage=image_record_storage,
+                image_file_storage=image_file_storage,
+                metadata=metadata,
+                url=urls,
+                logger=logger,
+                names=names,
+                graph_execution_manager=graph_execution_manager,
+            )
+        )
 
         services = InvocationServices(
-            model_manager=get_model_manager(config),
+            model_manager=ModelManagerService(config,logger),
             events=events,
             latents=latents,
             images=images,
-            metadata=metadata,
+            boards=boards,
+            board_images=board_images,
             queue=MemoryInvocationQueue(),
             graph_library=SqliteItemStorage[LibraryGraph](
                 filename=db_location, table_name="graphs"
             ),
-            graph_execution_manager=SqliteItemStorage[GraphExecutionState](
-                filename=db_location, table_name="graph_executions"
-            ),
+            graph_execution_manager=graph_execution_manager,
             processor=DefaultInvocationProcessor(),
-            restoration=RestorationServices(config),
+            restoration=RestorationServices(config, logger),
+            configuration=config,
+            logger=logger,
         )
 
         create_system_graphs(services.graph_library)

invokeai/app/api/models/images.py

@@ -1,34 +0,0 @@
-from typing import Optional
-from pydantic import BaseModel, Field
-
-from invokeai.app.models.image import ImageType
-from invokeai.app.services.metadata import InvokeAIMetadata
-
-
-class ImageResponseMetadata(BaseModel):
-    """An image's metadata. Used only in HTTP responses."""
-
-    created: int = Field(description="The creation timestamp of the image")
-    width: int = Field(description="The width of the image in pixels")
-    height: int = Field(description="The height of the image in pixels")
-    invokeai: Optional[InvokeAIMetadata] = Field(
-        description="The image's InvokeAI-specific metadata"
-    )
-
-
-class ImageResponse(BaseModel):
-    """The response type for images"""
-
-    image_type: ImageType = Field(description="The type of the image")
-    image_name: str = Field(description="The name of the image")
-    image_url: str = Field(description="The url of the image")
-    thumbnail_url: str = Field(description="The url of the image's thumbnail")
-    metadata: ImageResponseMetadata = Field(description="The image's metadata")
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")

invokeai/app/api/routers/app_info.py

@@ -0,0 +1,18 @@
+from fastapi.routing import APIRouter
+from pydantic import BaseModel
+
+from invokeai.version import __version__
+
+app_router = APIRouter(prefix="/v1/app", tags=['app'])
+
+
+class AppVersion(BaseModel):
+    """App Version Response"""
+    version: str
+
+
+@app_router.get('/version', operation_id="app_version",
+                status_code=200,
+                response_model=AppVersion)
+async def get_version() -> AppVersion:
+    return AppVersion(version=__version__)

invokeai/app/api/routers/board_images.py

@@ -0,0 +1,118 @@
+from fastapi import Body, HTTPException, Path
+from fastapi.routing import APIRouter
+
+from invokeai.app.models.image import (AddManyImagesToBoardResult,
+                                       GetAllBoardImagesForBoardResult,
+                                       RemoveManyImagesFromBoardResult)
+
+from ..dependencies import ApiDependencies
+
+board_images_router = APIRouter(prefix="/v1/board_images", tags=["boards"])
+
+
+@board_images_router.post(
+    "/{board_id}",
+    operation_id="create_board_image",
+    responses={
+        201: {"description": "The image was added to a board successfully"},
+    },
+    status_code=201,
+)
+async def create_board_image(
+    board_id: str = Path(description="The id of the board to add to"),
+    image_name: str = Body(description="The name of the image to add"),
+):
+    """Creates a board_image"""
+    try:
+        result = ApiDependencies.invoker.services.board_images.add_image_to_board(
+            board_id=board_id, image_name=image_name
+        )
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to add to board")
+
+
+@board_images_router.delete(
+    "/",
+    operation_id="remove_board_image",
+    responses={
+        201: {"description": "The image was removed from the board successfully"},
+    },
+    status_code=201,
+)
+async def remove_board_image(
+    image_name: str = Body(
+        description="The name of the image to remove from its board"
+    ),
+):
+    """Deletes a board_image"""
+    try:
+        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(
+            image_name=image_name
+        )
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to update board")
+
+
+@board_images_router.get(
+    "/{board_id}",
+    operation_id="get_all_board_images_for_board",
+    response_model=GetAllBoardImagesForBoardResult,
+)
+async def get_all_board_images_for_board(
+    board_id: str = Path(description="The id of the board"),
+) -> GetAllBoardImagesForBoardResult:
+    """Gets all image names for a board"""
+
+    result = (
+        ApiDependencies.invoker.services.board_images.get_all_board_images_for_board(
+            board_id,
+        )
+    )
+    return result
+
+
+@board_images_router.patch(
+    "/{board_id}/images",
+    operation_id="create_multiple_board_images",
+    responses={
+        201: {"description": "The images were added to the board successfully"},
+    },
+    status_code=201,
+)
+async def create_multiple_board_images(
+    board_id: str = Path(description="The id of the board"),
+    image_names: list[str] = Body(
+        description="The names of the images to add to the board"
+    ),
+) -> AddManyImagesToBoardResult:
+    """Add many images to a board"""
+
+    results = ApiDependencies.invoker.services.board_images.add_many_images_to_board(
+        board_id, image_names
+    )
+    return results
+
+
+@board_images_router.post(
+    "/images",
+    operation_id="delete_multiple_board_images",
+    responses={
+        201: {"description": "The images were removed from their boards successfully"},
+    },
+    status_code=201,
+)
+async def delete_multiple_board_images(
+    image_names: list[str] = Body(
+        description="The names of the images to remove from their boards, if they have one"
+    ),
+) -> RemoveManyImagesFromBoardResult:
+    """Remove many images from their boards, if they have one"""
+
+    results = (
+        ApiDependencies.invoker.services.board_images.remove_many_images_from_board(
+            image_names
+        )
+    )
+    return results

invokeai/app/api/routers/boards.py

@@ -0,0 +1,120 @@
+from typing import Optional, Union
+
+from fastapi import Body, HTTPException, Path, Query
+from fastapi.routing import APIRouter
+
+from invokeai.app.models.image import DeleteManyImagesResult
+from invokeai.app.services.board_record_storage import BoardChanges
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.board_record import BoardDTO
+
+from ..dependencies import ApiDependencies
+
+boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
+
+
+@boards_router.post(
+    "/",
+    operation_id="create_board",
+    responses={
+        201: {"description": "The board was created successfully"},
+    },
+    status_code=201,
+    response_model=BoardDTO,
+)
+async def create_board(
+    board_name: str = Query(description="The name of the board to create"),
+) -> BoardDTO:
+    """Creates a board"""
+    try:
+        result = ApiDependencies.invoker.services.boards.create(board_name=board_name)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to create board")
+
+
+@boards_router.get("/{board_id}", operation_id="get_board", response_model=BoardDTO)
+async def get_board(
+    board_id: str = Path(description="The id of board to get"),
+) -> BoardDTO:
+    """Gets a board"""
+
+    try:
+        result = ApiDependencies.invoker.services.boards.get_dto(board_id=board_id)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=404, detail="Board not found")
+
+
+@boards_router.patch(
+    "/{board_id}",
+    operation_id="update_board",
+    responses={
+        201: {
+            "description": "The board was updated successfully",
+        },
+    },
+    status_code=201,
+    response_model=BoardDTO,
+)
+async def update_board(
+    board_id: str = Path(description="The id of board to update"),
+    changes: BoardChanges = Body(description="The changes to apply to the board"),
+) -> BoardDTO:
+    """Updates a board"""
+    try:
+        result = ApiDependencies.invoker.services.boards.update(
+            board_id=board_id, changes=changes
+        )
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to update board")
+
+
+@boards_router.delete("/{board_id}", operation_id="delete_board", response_model=DeleteManyImagesResult)
+async def delete_board(
+    board_id: str = Path(description="The id of board to delete"),
+    include_images: Optional[bool] = Query(
+        description="Permanently delete all images on the board", default=False
+    ),
+) -> DeleteManyImagesResult:
+    """Deletes a board"""
+    try:
+        if include_images is True:
+            result = ApiDependencies.invoker.services.images.delete_images_on_board(
+                board_id=board_id
+            )
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+        else:
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+            result = DeleteManyImagesResult(deleted_images=[])
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to delete images on board")
+
+
+@boards_router.get(
+    "/",
+    operation_id="list_boards",
+    response_model=Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]],
+)
+async def list_boards(
+    all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
+    offset: Optional[int] = Query(default=None, description="The page offset"),
+    limit: Optional[int] = Query(
+        default=None, description="The number of boards per page"
+    ),
+) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
+    """Gets a list of boards"""
+    if all:
+        return ApiDependencies.invoker.services.boards.get_all()
+    elif offset is not None and limit is not None:
+        return ApiDependencies.invoker.services.boards.get_many(
+            offset,
+            limit,
+        )
+    else:
+        raise HTTPException(
+            status_code=400,
+            detail="Invalid request: Must provide either 'all' or both 'offset' and 'limit'",
+        )

invokeai/app/api/routers/images.py

@@ -1,128 +1,274 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 import io
-from datetime import datetime, timezone
-import json
-import os
-from typing import Any
-import uuid
+from typing import Optional
 
-from fastapi import HTTPException, Path, Query, Request, UploadFile
-from fastapi.responses import FileResponse, Response
+from fastapi import (Body, HTTPException, Path, Query, Request, Response,
+                     UploadFile)
+from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
-from invokeai.app.api.models.images import ImageResponse, ImageResponseMetadata
-from invokeai.app.services.metadata import InvokeAIMetadata
-from invokeai.app.services.item_storage import PaginatedResults
 
-from ...services.image_storage import ImageType
+from invokeai.app.models.image import (DeleteManyImagesResult, ImageCategory,
+                                       ResourceOrigin)
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.image_record import (GetImagesByNamesResult,
+                                                       ImageDTO,
+                                                       ImageRecordChanges,
+                                                       ImageUrlsDTO)
+
 from ..dependencies import ApiDependencies
 
 images_router = APIRouter(prefix="/v1/images", tags=["images"])
 
 
-@images_router.get("/{image_type}/{image_name}", operation_id="get_image")
-async def get_image(
-    image_type: ImageType = Path(description="The type of image to get"),
-    image_name: str = Path(description="The name of the image to get"),
-) -> FileResponse | Response:
-    """Gets a result"""
-
-    path = ApiDependencies.invoker.services.images.get_path(
-        image_type=image_type, image_name=image_name
-    )
-
-    if ApiDependencies.invoker.services.images.validate_path(path):
-        return FileResponse(path)
-    else:
-        raise HTTPException(status_code=404)
-
-
-@images_router.get(
-    "/{image_type}/thumbnails/{image_name}", operation_id="get_thumbnail"
-)
-async def get_thumbnail(
-    image_type: ImageType = Path(description="The type of image to get"),
-    image_name: str = Path(description="The name of the image to get"),
-) -> FileResponse | Response:
-    """Gets a thumbnail"""
-
-    path = ApiDependencies.invoker.services.images.get_path(
-        image_type=image_type, image_name=image_name, is_thumbnail=True
-    )
-
-    if ApiDependencies.invoker.services.images.validate_path(path):
-        return FileResponse(path)
-    else:
-        raise HTTPException(status_code=404)
-
-
 @images_router.post(
-    "/uploads/",
+    "/upload",
     operation_id="upload_image",
     responses={
-        201: {
-            "description": "The image was uploaded successfully",
-            "model": ImageResponse,
-        },
+        201: {"description": "The image was uploaded successfully"},
         415: {"description": "Image upload failed"},
     },
     status_code=201,
+    response_model=ImageDTO,
 )
 async def upload_image(
-    file: UploadFile, request: Request, response: Response
-) -> ImageResponse:
+    file: UploadFile,
+    request: Request,
+    response: Response,
+    image_category: ImageCategory = Query(description="The category of the image"),
+    is_intermediate: bool = Query(description="Whether this is an intermediate image"),
+    session_id: Optional[str] = Query(
+        default=None, description="The session ID associated with this upload, if any"
+    ),
+) -> ImageDTO:
+    """Uploads an image"""
     if not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
     contents = await file.read()
 
     try:
-        img = Image.open(io.BytesIO(contents))
+        pil_image = Image.open(io.BytesIO(contents))
     except:
         # Error opening the image
         raise HTTPException(status_code=415, detail="Failed to read image")
 
-    filename = f"{uuid.uuid4()}_{str(int(datetime.now(timezone.utc).timestamp()))}.png"
+    try:
+        image_dto = ApiDependencies.invoker.services.images.create(
+            image=pil_image,
+            image_origin=ResourceOrigin.EXTERNAL,
+            image_category=image_category,
+            session_id=session_id,
+            is_intermediate=is_intermediate,
+        )
 
-    (image_path, thumbnail_path, ctime) = ApiDependencies.invoker.services.images.save(
-        ImageType.UPLOAD, filename, img
-    )
+        response.status_code = 201
+        response.headers["Location"] = image_dto.image_url
 
-    invokeai_metadata = ApiDependencies.invoker.services.metadata.get_metadata(img)
+        return image_dto
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to create image")
 
-    res = ImageResponse(
-        image_type=ImageType.UPLOAD,
-        image_name=filename,
-        image_url=f"api/v1/images/{ImageType.UPLOAD.value}/{filename}",
-        thumbnail_url=f"api/v1/images/{ImageType.UPLOAD.value}/thumbnails/{os.path.splitext(filename)[0]}.webp",
-        metadata=ImageResponseMetadata(
-            created=ctime,
-            width=img.width,
-            height=img.height,
-            invokeai=invokeai_metadata,
-        ),
-    )
 
-    response.status_code = 201
-    response.headers["Location"] = request.url_for(
-        "get_image", image_type=ImageType.UPLOAD.value, image_name=filename
-    )
+@images_router.delete("/{image_name}", operation_id="delete_image")
+async def delete_image(
+    image_name: str = Path(description="The name of the image to delete"),
+) -> None:
+    """Deletes an image"""
 
-    return res
+    try:
+        ApiDependencies.invoker.services.images.delete(image_name)
+    except Exception as e:
+        # TODO: Does this need any exception handling at all?
+        pass
+
+
+@images_router.patch(
+    "/{image_name}",
+    operation_id="update_image",
+    response_model=ImageDTO,
+)
+async def update_image(
+    image_name: str = Path(description="The name of the image to update"),
+    image_changes: ImageRecordChanges = Body(
+        description="The changes to apply to the image"
+    ),
+) -> ImageDTO:
+    """Updates an image"""
+
+    try:
+        return ApiDependencies.invoker.services.images.update(image_name, image_changes)
+    except Exception as e:
+        raise HTTPException(status_code=400, detail="Failed to update image")
+
+
+@images_router.get(
+    "/{image_name}",
+    operation_id="get_image",
+    response_model=ImageDTO,
+)
+async def get_image_dto(
+    image_name: str = Path(description="The name of image to get"),
+) -> ImageDTO:
+    """Gets an image's DTO"""
+
+    try:
+        return ApiDependencies.invoker.services.images.get_dto(image_name)
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_name}/full_size",
+    operation_id="get_image_full_size",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the full-resolution image",
+            "content": {"image/png": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_image_full_size(
+    image_name: str = Path(description="The name of full-resolution image file to get"),
+) -> FileResponse:
+    """Gets a full-resolution image file"""
+
+    try:
+        path = ApiDependencies.invoker.services.images.get_path(image_name)
+
+        if not ApiDependencies.invoker.services.images.validate_path(path):
+            raise HTTPException(status_code=404)
+
+        return FileResponse(
+            path,
+            media_type="image/png",
+            filename=image_name,
+            content_disposition_type="inline",
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_name}/thumbnail",
+    operation_id="get_image_thumbnail",
+    response_class=Response,
+    responses={
+        200: {
+            "description": "Return the image thumbnail",
+            "content": {"image/webp": {}},
+        },
+        404: {"description": "Image not found"},
+    },
+)
+async def get_image_thumbnail(
+    image_name: str = Path(description="The name of thumbnail image file to get"),
+) -> FileResponse:
+    """Gets a thumbnail image file"""
+
+    try:
+        path = ApiDependencies.invoker.services.images.get_path(
+            image_name, thumbnail=True
+        )
+        if not ApiDependencies.invoker.services.images.validate_path(path):
+            raise HTTPException(status_code=404)
+
+        return FileResponse(
+            path, media_type="image/webp", content_disposition_type="inline"
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
+
+
+@images_router.get(
+    "/{image_name}/urls",
+    operation_id="get_image_urls",
+    response_model=ImageUrlsDTO,
+)
+async def get_image_urls(
+    image_name: str = Path(description="The name of the image whose URL to get"),
+) -> ImageUrlsDTO:
+    """Gets an image and thumbnail URL"""
+
+    try:
+        image_url = ApiDependencies.invoker.services.images.get_url(image_name)
+        thumbnail_url = ApiDependencies.invoker.services.images.get_url(
+            image_name, thumbnail=True
+        )
+        return ImageUrlsDTO(
+            image_name=image_name,
+            image_url=image_url,
+            thumbnail_url=thumbnail_url,
+        )
+    except Exception as e:
+        raise HTTPException(status_code=404)
 
 
 @images_router.get(
     "/",
-    operation_id="list_images",
-    responses={200: {"model": PaginatedResults[ImageResponse]}},
+    operation_id="get_many_images",
+    response_model=OffsetPaginatedResults[ImageDTO],
 )
-async def list_images(
-    image_type: ImageType = Query(
-        default=ImageType.RESULT, description="The type of images to get"
+async def get_many_images(
+    image_origin: Optional[ResourceOrigin] = Query(
+        default=None, description="The origin of images to list"
     ),
-    page: int = Query(default=0, description="The page of images to get"),
-    per_page: int = Query(default=10, description="The number of images per page"),
-) -> PaginatedResults[ImageResponse]:
+    categories: Optional[list[ImageCategory]] = Query(
+        default=None, description="The categories of image to include"
+    ),
+    is_intermediate: Optional[bool] = Query(
+        default=None, description="Whether to list intermediate images"
+    ),
+    board_id: Optional[str] = Query(
+        default=None,
+        description="The board id to filter by, provide 'none' for images without a board",
+    ),
+    offset: int = Query(default=0, description="The page offset"),
+    limit: int = Query(default=10, description="The number of images per page"),
+) -> OffsetPaginatedResults[ImageDTO]:
     """Gets a list of images"""
-    result = ApiDependencies.invoker.services.images.list(image_type, page, per_page)
+
+    image_dtos = ApiDependencies.invoker.services.images.get_many(
+        offset,
+        limit,
+        image_origin,
+        categories,
+        is_intermediate,
+        board_id,
+    )
+
+    return image_dtos
+
+
+@images_router.post(
+    "/",
+    operation_id="get_images_by_names",
+    response_model=GetImagesByNamesResult,
+)
+async def get_images_by_names(
+    image_names: list[str] = Body(description="The names of the images to get"),
+) -> GetImagesByNamesResult:
+    """Gets a list of images"""
+
+    result = ApiDependencies.invoker.services.images.get_images_by_names(
+        image_names
+    )
+
     return result
+
+
+@images_router.post(
+    "/delete",
+    operation_id="delete_many_images",
+    response_model=DeleteManyImagesResult,
+)
+async def delete_many_images(
+    image_names: list[str] = Body(description="The names of the images to delete"),
+) -> DeleteManyImagesResult:
+    """Deletes many images"""
+
+    try:
+        return ApiDependencies.invoker.services.images.delete_many(image_names)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to delete images")

invokeai/app/api/routers/models.py

@@ -1,104 +1,134 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654), 2023 Kent Keirsey (https://github.com/hipsterusername), 2024 Lincoln Stein
 
-import shutil
-import asyncio
-from typing import Annotated, Any, List, Literal, Optional, Union
 
-from fastapi.routing import APIRouter, HTTPException
-from pydantic import BaseModel, Field, parse_obj_as
-from pathlib import Path
+from typing import Literal, List, Optional, Union
+
+from fastapi import Body, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic import BaseModel, parse_obj_as
+from starlette.exceptions import HTTPException
+
+from invokeai.backend import BaseModelType, ModelType
+from invokeai.backend.model_management.models import (
+    OPENAPI_MODEL_CONFIGS,
+    SchedulerPredictionType,
+)
+from invokeai.backend.model_management import MergeInterpolationMethod
 from ..dependencies import ApiDependencies
-from invokeai.backend.globals import Globals, global_converted_ckpts_dir
-from invokeai.backend.args import Args
-
-
 
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
-
-class VaeRepo(BaseModel):
-    repo_id: str = Field(description="The repo ID to use for this VAE")
-    path: Optional[str] = Field(description="The path to the VAE")
-    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
-
-class ModelInfo(BaseModel):
-    description: Optional[str] = Field(description="A description of the model")
-    
-class CkptModelInfo(ModelInfo):
-    format: Literal['ckpt'] = 'ckpt'
-
-    config: str = Field(description="The path to the model config")
-    weights: str = Field(description="The path to the model weights")
-    vae: str = Field(description="The path to the model VAE")
-    width: Optional[int] = Field(description="The width of the model")
-    height: Optional[int] = Field(description="The height of the model")
-
-class DiffusersModelInfo(ModelInfo):
-    format: Literal['diffusers'] = 'diffusers'
-
-    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
-    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
-    path: Optional[str] = Field(description="The path to the model")
-
-class CreateModelRequest(BaseModel):
-    name: str = Field(description="The name of the model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-
-class CreateModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
-    status: str = Field(description="The status of the API response")
-
-class ConversionRequest(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: CkptModelInfo = Field(description="The converted model info")
-    save_location: str = Field(description="The path to save the converted model weights")
-    
-
-class ConvertedModelResponse(BaseModel):
-    name: str = Field(description="The name of the new model")
-    info: DiffusersModelInfo = Field(description="The converted model info")
+UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
+MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 
 class ModelsList(BaseModel):
-    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
-
+    models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
 
 @models_router.get(
     "/",
     operation_id="list_models",
     responses={200: {"model": ModelsList }},
 )
-async def list_models() -> ModelsList:
+async def list_models(
+    base_model: Optional[BaseModelType] = Query(default=None, description="Base model"),
+    model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
+) -> ModelsList:
     """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type)
     models = parse_obj_as(ModelsList, { "models": models_raw })
     return models
 
-
-@models_router.post(
-    "/",
+@models_router.patch(
+    "/{base_model}/{model_type}/{model_name}",
     operation_id="update_model",
-    responses={200: {"status": "success"}},
+    responses={200: {"description" : "The model was updated successfully"},
+               404: {"description" : "The model could not be found"},
+               400: {"description" : "Bad request"}
+               },
+    status_code = 200,
+    response_model = UpdateModelResponse,
 )
 async def update_model(
-    model_request: CreateModelRequest
-) -> CreateModelResponse:
+        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:
     """ Add Model """
-    model_request_info = model_request.info
-    info_dict = model_request_info.dict()
-    model_response = CreateModelResponse(name=model_request.name, info=model_request.info, status="success")
-
-    ApiDependencies.invoker.services.model_manager.add_model(
-        model_name=model_request.name,
-        model_attributes=info_dict,
-        clobber=True,
-    )
+    try:
+        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 = parse_obj_as(UpdateModelResponse, model_raw)
+    except KeyError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
 
     return model_response
 
+@models_router.post(
+    "/",
+    operation_id="import_model",
+    responses= {
+        201: {"description" : "The model imported successfully"},
+        404: {"description" : "The model could not be found"},
+        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 checkpoint files', default="v_prediction"),
+) -> ImportModelResponse:
+    """ Add a model using its local path, repo_id, or remote URL """
+    
+    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=424)
+        
+        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 parse_obj_as(ImportModelResponse, model_raw)
+    
+    except KeyError 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(
-    "/{model_name}",
+    "/{base_model}/{model_type}/{model_name}",
     operation_id="del_model",
     responses={
         204: {
@@ -109,143 +139,95 @@ async def update_model(
         }
     },
 )
-async def delete_model(model_name: str) -> 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"""
-    model_names = ApiDependencies.invoker.services.model_manager.model_names()
-    model_exists = model_name in model_names
-
-    # check if model exists
-    print(f">> Checking for model {model_name}...")
-           
-    if model_exists:
-        print(f">> Deleting Model: {model_name}")
-        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
-        print(f">> Model Deleted: {model_name}")
-        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
+    logger = ApiDependencies.invoker.services.logger
     
-    else:
-        print(f">> Model not found")
+    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 KeyError:
+        logger.error(f"Model not found: {model_name}")
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
-    
 
-            # @socketio.on("convertToDiffusers")
-        # def convert_to_diffusers(model_to_convert: dict):
-        #     try:
-        #         if model_info := self.generate.model_manager.model_info(
-        #             model_name=model_to_convert["model_name"]
-        #         ):
-        #             if "weights" in model_info:
-        #                 ckpt_path = Path(model_info["weights"])
-        #                 original_config_file = Path(model_info["config"])
-        #                 model_name = model_to_convert["model_name"]
-        #                 model_description = model_info["description"]
-        #             else:
-        #                 self.socketio.emit(
-        #                     "error", {"message": "Model is not a valid checkpoint file"}
-        #                 )
-        #         else:
-        #             self.socketio.emit(
-        #                 "error", {"message": "Could not retrieve model info."}
-        #             )
-
-        #         if not ckpt_path.is_absolute():
-        #             ckpt_path = Path(Globals.root, ckpt_path)
-
-        #         if original_config_file and not original_config_file.is_absolute():
-        #             original_config_file = Path(Globals.root, original_config_file)
-
-        #         diffusers_path = Path(
-        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
-        #         )
-
-        #         if model_to_convert["save_location"] == "root":
-        #             diffusers_path = Path(
-        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
-        #             )
-
-        #         if (
-        #             model_to_convert["save_location"] == "custom"
-        #             and model_to_convert["custom_location"] is not None
-        #         ):
-        #             diffusers_path = Path(
-        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
-        #             )
-
-        #         if diffusers_path.exists():
-        #             shutil.rmtree(diffusers_path)
-
-        #         self.generate.model_manager.convert_and_import(
-        #             ckpt_path,
-        #             diffusers_path,
-        #             model_name=model_name,
-        #             model_description=model_description,
-        #             vae=None,
-        #             original_config_file=original_config_file,
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         new_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "modelConverted",
-        #             {
-        #                 "new_model_name": model_name,
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Model Converted: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("mergeDiffusersModels")
-        # def merge_diffusers_models(model_merge_info: dict):
-        #     try:
-        #         models_to_merge = model_merge_info["models_to_merge"]
-        #         model_ids_or_paths = [
-        #             self.generate.model_manager.model_name_or_path(x)
-        #             for x in models_to_merge
-        #         ]
-        #         merged_pipe = merge_diffusion_models(
-        #             model_ids_or_paths,
-        #             model_merge_info["alpha"],
-        #             model_merge_info["interp"],
-        #             model_merge_info["force"],
-        #         )
-
-        #         dump_path = global_models_dir() / "merged_models"
-        #         if model_merge_info["model_merge_save_path"] is not None:
-        #             dump_path = Path(model_merge_info["model_merge_save_path"])
-
-        #         os.makedirs(dump_path, exist_ok=True)
-        #         dump_path = dump_path / model_merge_info["merged_model_name"]
-        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
-
-        #         merged_model_config = dict(
-        #             model_name=model_merge_info["merged_model_name"],
-        #             description=f'Merge of models {", ".join(models_to_merge)}',
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
-        #             "vae", None
-        #         ):
-        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
-        #             merged_model_config.update(vae=vae)
-
-        #         self.generate.model_manager.import_diffuser_model(
-        #             dump_path, **merged_model_config
-        #         )
-        #         new_model_list = self.generate.model_manager.list_models()
-
-        #         socketio.emit(
-        #             "modelsMerged",
-        #             {
-        #                 "merged_models": models_to_merge,
-        #                 "merged_model_name": model_merge_info["merged_model_name"],
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Models Merged: {models_to_merge}")
-        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as 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"),
+) -> ConvertModelResponse:
+    """Convert a checkpoint model into a diffusers model"""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Converting model: {model_name}")
+        ApiDependencies.invoker.services.model_manager.convert_model(model_name,
+                                                                     base_model = base_model,
+                                                                     model_type = model_type
+                                                                     )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(model_name,
+                                                                              base_model = base_model,
+                                                                              model_type = model_type)
+        response = parse_obj_as(ConvertModelResponse, model_raw)
+    except KeyError:
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response
+        
+@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(
+        base_model: BaseModelType                  = Path(description="Base model"),
+        model_names: List[str]                     = Body(description="model name", min_items=2, max_items=3),
+        merged_model_name: Optional[str]           = Body(description="Name of destination model"),
+        alpha: Optional[float]                     = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+        interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
+        force: Optional[bool]                      = Body(description="Force merging of models created with different versions of diffusers", default=False),
+) -> MergeModelResponse:
+    """Convert a checkpoint model into a diffusers model"""
+    logger = ApiDependencies.invoker.services.logger
+    try:
+        logger.info(f"Merging models: {model_names}")
+        result = ApiDependencies.invoker.services.model_manager.merge_models(model_names,
+                                                                             base_model,
+                                                                             merged_model_name or "+".join(model_names),
+                                                                             alpha,
+                                                                             interp,
+                                                                             force)
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(result.name,
+                                                                              base_model = base_model,
+                                                                              model_type = ModelType.Main,
+                                                                              )
+        response = parse_obj_as(ConvertModelResponse, model_raw)
+    except KeyError:
+        raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    return response

invokeai/app/api/routers/sessions.py

@@ -2,8 +2,7 @@
 
 from typing import Annotated, List, Optional, Union
 
-from fastapi import Body, Path, Query
-from fastapi.responses import Response
+from fastapi import Body, HTTPException, Path, Query, Response
 from fastapi.routing import APIRouter
 from pydantic.fields import Field
 
@@ -76,7 +75,7 @@ async def get_session(
     """Gets a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
     else:
         return session
 
@@ -99,7 +98,7 @@ async def add_node(
     """Adds a node to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_node(node)
@@ -108,9 +107,9 @@ async def add_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session.id
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -132,7 +131,7 @@ async def update_node(
     """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:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.update_node(node_path, node)
@@ -141,9 +140,9 @@ async def update_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.delete(
@@ -162,7 +161,7 @@ async def delete_node(
     """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:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.delete_node(node_path)
@@ -171,9 +170,9 @@ async def delete_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.post(
@@ -192,7 +191,7 @@ async def add_edge(
     """Adds an edge to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_edge(edge)
@@ -201,9 +200,9 @@ async def add_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 # TODO: the edge being in the path here is really ugly, find a better solution
@@ -226,7 +225,7 @@ async def delete_edge(
     """Deletes an edge from the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         edge = Edge(
@@ -239,9 +238,9 @@ async def delete_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -259,14 +258,14 @@ async def invoke_session(
     all: bool = Query(
         default=False, description="Whether or not to invoke all remaining invocations"
     ),
-) -> None:
+) -> Response:
     """Invokes a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     if session.is_complete():
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
     ApiDependencies.invoker.invoke(session, invoke_all=all)
     return Response(status_code=202)
@@ -281,7 +280,7 @@ async def invoke_session(
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),
-) -> None:
+) -> Response:
     """Invokes a session"""
     ApiDependencies.invoker.cancel(session_id)
     return Response(status_code=202)

invokeai/app/api_app.py

@@ -1,8 +1,10 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2022-2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 import asyncio
+import sys
 from inspect import signature
 
 import uvicorn
+
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
@@ -10,14 +12,40 @@ from fastapi.openapi.utils import get_openapi
 from fastapi.staticfiles import StaticFiles
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.middleware import EventHandlerASGIMiddleware
+from pathlib import Path
 from pydantic.schema import schema
 
-from ..backend import Args
+#This should come early so that modules can log their initialization properly
+from .services.config import InvokeAIAppConfig
+from ..backend.util.logging import InvokeAILogger
+app_config = InvokeAIAppConfig.get_config()
+app_config.parse_args()
+logger = InvokeAILogger.getLogger(config=app_config)
+from invokeai.version.invokeai_version import __version__
+
+# we call this early so that the message appears before
+# other invokeai initialization messages
+if app_config.version:
+    print(f'InvokeAI version {__version__}')
+    sys.exit(0)
+
+import invokeai.frontend.web as web_dir
+import mimetypes
+
 from .api.dependencies import ApiDependencies
-from .api.routers import images, sessions, models
+from .api.routers import sessions, models, images, boards, board_images, app_info
 from .api.sockets import SocketIO
-from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
+    
+
+import torch
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
+
+# fix for windows mimetypes registry entries being borked
+# see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
+mimetypes.add_type('application/javascript', '.js')
+mimetypes.add_type('text/css', '.css')
 
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
@@ -33,30 +61,21 @@ app.add_middleware(
     middleware_id=event_handler_id,
 )
 
-# Add CORS
-# TODO: use configuration for this
-origins = []
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
 socket_io = SocketIO(app)
 
-config = {}
-
-
 # Add startup event to load dependencies
 @app.on_event("startup")
 async def startup_event():
-    config = Args()
-    config.parse_args()
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=app_config.allow_origins,
+        allow_credentials=app_config.allow_credentials,
+        allow_methods=app_config.allow_methods,
+        allow_headers=app_config.allow_headers,
+    )
 
     ApiDependencies.initialize(
-        config=config, event_handler_id=event_handler_id
+        config=app_config, event_handler_id=event_handler_id, logger=logger
     )
 
 
@@ -74,10 +93,15 @@ async def shutdown_event():
 
 app.include_router(sessions.session_router, prefix="/api")
 
-app.include_router(images.images_router, prefix="/api")
-
 app.include_router(models.models_router, prefix="/api")
 
+app.include_router(images.images_router, prefix="/api")
+
+app.include_router(boards.boards_router, prefix="/api")
+
+app.include_router(board_images.board_images_router, prefix="/api")
+
+app.include_router(app_info.app_router, prefix='/api')
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -117,6 +141,22 @@ def custom_openapi():
 
         invoker_schema["output"] = outputs_ref
 
+    from invokeai.backend.model_management.models import get_model_config_enums
+    for model_config_format_enum in set(get_model_config_enums()):
+        name = model_config_format_enum.__qualname__
+
+        if name in openapi_schema["components"]["schemas"]:
+            # print(f"Config with name {name} already defined")
+            continue
+
+        # "BaseModelType":{"title":"BaseModelType","description":"An enumeration.","enum":["sd-1","sd-2"],"type":"string"}
+        openapi_schema["components"]["schemas"][name] = dict(
+            title=name,
+            description="An enumeration.",
+            type="string",
+            enum=list(v.value for v in model_config_format_enum),
+        )
+
     app.openapi_schema = openapi_schema
     return app.openapi_schema
 
@@ -124,8 +164,7 @@ def custom_openapi():
 app.openapi = custom_openapi
 
 # Override API doc favicons
-app.mount("/static", StaticFiles(directory="static/dream_web"), name="static")
-
+app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], 'static/dream_web')), name="static")
 
 @app.get("/docs", include_in_schema=False)
 def overridden_swagger():
@@ -145,16 +184,20 @@ def overridden_redoc():
     )
 
 
+# Must mount *after* the other routes else it borks em
+app.mount("/", 
+          StaticFiles(directory=Path(web_dir.__path__[0],"dist"), 
+                      html=True
+                     ), name="ui"
+         )
+
 def invoke_api():
     # Start our own event loop for eventing usage
-    # TODO: determine if there's a better way to do this
     loop = asyncio.new_event_loop()
-    config = uvicorn.Config(app=app, host="0.0.0.0", port=9090, loop=loop)
+    config = uvicorn.Config(app=app, host=app_config.host, port=app_config.port, loop=loop)
     # Use access_log to turn off logging
-
     server = uvicorn.Server(config)
     loop.run_until_complete(server.serve())
 
-
 if __name__ == "__main__":
     invoke_api()

invokeai/app/cli/commands.py

@@ -2,14 +2,15 @@
 
 from abc import ABC, abstractmethod
 import argparse
-from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
+from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
 from pydantic import BaseModel, Field
 import networkx as nx
 import matplotlib.pyplot as plt
 
+import invokeai.backend.util.logging as logger
 from ..invocations.baseinvocation import BaseInvocation
 from ..invocations.image import ImageField
-from ..services.graph import GraphExecutionState, LibraryGraph, GraphInvocation, Edge
+from ..services.graph import GraphExecutionState, LibraryGraph, Edge
 from ..services.invoker import Invoker
 
 
@@ -46,7 +47,7 @@ def add_parsers(
     commands: list[type],
     command_field: str = "type",
     exclude_fields: list[str] = ["id", "type"],
-    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None],None] = None
     ):
     """Adds parsers for each command to the subparsers"""
 
@@ -71,7 +72,7 @@ def add_parsers(
 def add_graph_parsers(
     subparsers,
     graphs: list[LibraryGraph],
-    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
 ):
     for graph in graphs:
         command_parser = subparsers.add_parser(graph.name, help=graph.description)
@@ -229,7 +230,7 @@ class HistoryCommand(BaseCommand):
         for i in range(min(self.count, len(history))):
             entry_id = history[-1 - i]
             entry = context.get_session().graph.get_node(entry_id)
-            print(f"{entry_id}: {get_invocation_command(entry)}")
+            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
 
 
 class SetDefaultCommand(BaseCommand):
@@ -284,3 +285,19 @@ class DrawExecutionGraphCommand(BaseCommand):
         nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
         plt.axis("off")
         plt.show()
+
+class SortedHelpFormatter(argparse.HelpFormatter):
+    def _iter_indented_subactions(self, action):
+        try:
+            get_subactions = action._get_subactions
+        except AttributeError:
+            pass
+        else:
+            self._indent()
+            if isinstance(action, argparse._SubParsersAction):
+                for subaction in sorted(get_subactions(), key=lambda x: x.dest):
+                    yield subaction
+            else:
+                for subaction in get_subactions():
+                    yield subaction
+                self._dedent()

invokeai/app/cli/completer.py

@@ -10,9 +10,11 @@ import shlex
 from pathlib import Path
 from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
 
-from ...backend import ModelManager, Globals
+import invokeai.backend.util.logging as logger
+from ...backend import ModelManager
 from ..invocations.baseinvocation import BaseInvocation
 from .commands import BaseCommand
+from ..services.invocation_services import InvocationServices
 
 # singleton object, class variable
 completer = None
@@ -130,13 +132,13 @@ class Completer(object):
             readline.redisplay()
             self.linebuffer = None
     
-def set_autocompleter(model_manager: ModelManager) -> Completer:
+def set_autocompleter(services: InvocationServices) -> Completer:
     global completer
     
     if completer:
         return completer
     
-    completer = Completer(model_manager)
+    completer = Completer(services.model_manager)
 
     readline.set_completer(completer.complete)
     # pyreadline3 does not have a set_auto_history() method
@@ -152,7 +154,7 @@ def set_autocompleter(model_manager: ModelManager) -> Completer:
     readline.parse_and_bind("set skip-completed-text on")
     readline.parse_and_bind("set show-all-if-ambiguous on")
 
-    histfile = Path(Globals.root, ".invoke_history")
+    histfile = Path(services.configuration.root_dir / ".invoke_history")
     try:
         readline.read_history_file(histfile)
         readline.set_history_length(1000)
@@ -160,8 +162,8 @@ def set_autocompleter(model_manager: ModelManager) -> Completer:
         pass
     except OSError:  # file likely corrupted
         newname = f"{histfile}.old"
-        print(
-            f"## Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
+        logger.error(
+            f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
         )
         histfile.replace(Path(newname))
     atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -1,41 +1,67 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 import argparse
-import os
 import re
 import shlex
+import sys
 import time
-from typing import (
-    Union,
-    get_type_hints,
-)
+from typing import Union, get_type_hints, Optional
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ValidationError
 from pydantic.fields import Field
 
-from invokeai.app.services.metadata import PngMetadataService
+# This should come early so that the logger can pick up its configuration options
+from .services.config import InvokeAIAppConfig
+from invokeai.backend.util.logging import InvokeAILogger
+config = InvokeAIAppConfig.get_config()
+config.parse_args()
+logger = InvokeAILogger().getLogger(config=config)
+from invokeai.version.invokeai_version import __version__
 
-from .services.default_graphs import create_system_graphs
+# we call this early so that the message appears before other invokeai initialization messages
+if config.version:
+    print(f'InvokeAI version {__version__}')
+    sys.exit(0)
 
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
+from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
+from invokeai.app.services.metadata import CoreMetadataService
+from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.urls import LocalUrlService
+from .services.default_graphs import (default_text_to_image_graph_id,
+                                      create_system_graphs)
 from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
 
-from ..backend import Args
-from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, get_graph_execution_history
+from .cli.commands import (BaseCommand, CliContext, ExitCli,
+                           SortedHelpFormatter, add_graph_parsers, add_parsers)
 from .cli.completer import set_autocompleter
-from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
-from .services.model_manager_initializer import get_model_manager
-from .services.restoration_services import RestorationServices
-from .services.graph import Edge, EdgeConnection, ExposedNodeInput, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
-from .services.default_graphs import default_text_to_image_graph_id
-from .services.image_storage import DiskImageStorage
+from .services.graph import (Edge, EdgeConnection, GraphExecutionState,
+                             GraphInvocation, LibraryGraph,
+                             are_connection_types_compatible)
+from .services.image_file_storage import DiskImageFileStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
 from .services.invoker import Invoker
+from .services.model_manager_service import ModelManagerService
 from .services.processor import DefaultInvocationProcessor
+from .services.restoration_services import RestorationServices
 from .services.sqlite import SqliteItemStorage
 
+import torch
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
+
 
 class CliCommand(BaseModel):
     command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
@@ -44,7 +70,6 @@ class CliCommand(BaseModel):
 class InvalidArgs(Exception):
     pass
 
-
 def add_invocation_args(command_parser):
     # Add linking capability
     command_parser.add_argument(
@@ -65,7 +90,7 @@ def add_invocation_args(command_parser):
 
 def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
     # Create invocation parser
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
 
     def exit(*args, **kwargs):
         raise InvalidArgs
@@ -182,54 +207,106 @@ def invoke_all(context: CliContext):
     # Print any errors
     if context.session.has_error():
         for n in context.session.errors:
-            print(
+            context.invoker.services.logger.error(
                 f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
             )
         
         raise SessionError()
 
-
 def invoke_cli():
-    config = Args()
-    config.parse_args()
-    model_manager = get_model_manager(config)
+    logger.info(f'InvokeAI version {__version__}')
+    # get the optional list of invocations to execute on the command line
+    parser = config.get_parser()
+    parser.add_argument('commands',nargs='*')
+    invocation_commands = parser.parse_args().commands
 
-    # This initializes the autocompleter and returns it.
-    # Currently nothing is done with the returned Completer
-    # object, but the object can be used to change autocompletion
-    # behavior on the fly, if desired.
-    completer = set_autocompleter(model_manager)
+    # get the optional file to read commands from.
+    # Simplest is to use it for STDIN
+    if infile := config.from_file:
+        sys.stdin = open(infile,"r")
+    
+    model_manager = ModelManagerService(config,logger)
 
     events = EventServiceBase()
-
-    metadata = PngMetadataService()
-
-    output_folder = os.path.abspath(
-        os.path.join(os.path.dirname(__file__), "../../../outputs")
-    )
+    output_folder = config.output_path
 
     # TODO: build a file/path manager?
-    db_location = os.path.join(output_folder, "invokeai.db")
+    if config.use_memory_db:
+        db_location = ":memory:"
+    else:
+        db_location = config.db_path
+        db_location.parent.mkdir(parents=True,exist_ok=True)
 
+    logger.info(f'InvokeAI database location is "{db_location}"')
+
+    graph_execution_manager = SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        )
+
+    urls = LocalUrlService()
+    metadata = CoreMetadataService()
+    image_record_storage = SqliteImageRecordStorage(db_location)
+    image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
+    names = SimpleNameService()
+
+    board_record_storage = SqliteBoardRecordStorage(db_location)
+    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
+
+    boards = BoardService(
+        services=BoardServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
+    )
+
+    board_images = BoardImagesService(
+        services=BoardImagesServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            board_record_storage=board_record_storage,
+            image_record_storage=image_record_storage,
+            url=urls,
+            logger=logger,
+        )
+    )
+
+    images = ImageService(
+        services=ImageServiceDependencies(
+            board_image_record_storage=board_image_record_storage,
+            image_record_storage=image_record_storage,
+            image_file_storage=image_file_storage,
+            metadata=metadata,
+            url=urls,
+            logger=logger,
+            names=names,
+            graph_execution_manager=graph_execution_manager,
+        )
+    )
+        
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
-        images=DiskImageStorage(f'{output_folder}/images', metadata_service=metadata),
-        metadata=metadata,
+        images=images,
+        boards=boards,
+        board_images=board_images,
         queue=MemoryInvocationQueue(),
         graph_library=SqliteItemStorage[LibraryGraph](
             filename=db_location, table_name="graphs"
         ),
-        graph_execution_manager=SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
-        ),
+        graph_execution_manager=graph_execution_manager,
         processor=DefaultInvocationProcessor(),
-        restoration=RestorationServices(config),
+        restoration=RestorationServices(config,logger=logger),
+        logger=logger,
+        configuration=config,
     )
+    
 
     system_graphs = create_system_graphs(services.graph_library)
     system_graph_names = set([g.name for g in system_graphs])
+    set_autocompleter(services)
 
     invoker = Invoker(services)
     session: GraphExecutionState = invoker.create_execution_state()
@@ -241,10 +318,18 @@ def invoke_cli():
     # print(services.session_manager.list())
 
     context = CliContext(invoker, session, parser)
+    set_autocompleter(services)
 
-    while True:
+    command_line_args_exist = len(invocation_commands) > 0
+    done = False
+    
+    while not done:
         try:
-            cmd_input = input("invoke> ")
+            if command_line_args_exist:
+                cmd_input = invocation_commands.pop(0)
+                done = len(invocation_commands) == 0
+            else:
+                cmd_input = input("invoke> ")
         except (KeyboardInterrupt, EOFError):
             # Ctrl-c exits
             break
@@ -273,7 +358,7 @@ def invoke_cli():
 
                 # Parse invocation
                 command: CliCommand = None # type:ignore
-                system_graph: LibraryGraph|None = None
+                system_graph: Optional[LibraryGraph] = None
                 if args['type'] in system_graph_names:
                     system_graph = next(filter(lambda g: g.name == args['type'], system_graphs))
                     invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))
@@ -365,12 +450,15 @@ def invoke_cli():
             invoke_all(context)
 
         except InvalidArgs:
-            print('Invalid command, use "help" to list commands')
+            invoker.services.logger.warning('Invalid command, use "help" to list commands')
             continue
 
+        except ValidationError:
+            invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
+
         except SessionError:
             # Start a new session
-            print("Session error: creating a new session")
+            invoker.services.logger.warning("Session error: creating a new session")
             context.reset()
 
         except ExitCli:

invokeai/app/invocations/baseinvocation.py

@@ -1,12 +1,16 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict
+from typing import (TYPE_CHECKING, Dict, List, Literal, TypedDict, get_args,
+                    get_type_hints)
 
-from pydantic import BaseModel, Field
+from pydantic import BaseConfig, BaseModel, Field
 
-from ..services.invocation_services import InvocationServices
+if TYPE_CHECKING:
+    from ..services.invocation_services import InvocationServices
 
 
 class InvocationContext:
@@ -62,8 +66,13 @@ class BaseInvocation(ABC, BaseModel):
     @classmethod
     def get_invocations_map(cls):
         # Get the type strings out of the literals and into a dictionary
-        return dict(map(lambda t: (get_args(get_type_hints(t)['type'])[0], t),BaseInvocation.get_all_subclasses()))
-    
+        return dict(
+            map(
+                lambda t: (get_args(get_type_hints(t)["type"])[0], t),
+                BaseInvocation.get_all_subclasses(),
+            )
+        )
+
     @classmethod
     def get_output_type(cls):
         return signature(cls.invoke).return_annotation
@@ -72,10 +81,11 @@ class BaseInvocation(ABC, BaseModel):
     def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
         """Invoke with provided context and return outputs."""
         pass
-    
-    #fmt: off
+
+    # fmt: off
     id: str = Field(description="The id of this node. Must be unique among all nodes.")
-    #fmt: on
+    is_intermediate: bool = Field(default=False, description="Whether or not this node is an intermediate node.")
+    # fmt: on
 
 
 # TODO: figure out a better way to provide these hints
@@ -92,16 +102,21 @@ class UIConfig(TypedDict, total=False):
             "image",
             "latents",
             "model",
+            "control",
+            "image_collection",
+            "vae_model",
+            "lora_model",
         ],
     ]
     tags: List[str]
     title: str
 
+
 class CustomisedSchemaExtra(TypedDict):
     ui: UIConfig
 
 
-class InvocationConfig(BaseModel.Config):
+class InvocationConfig(BaseConfig):
     """Customizes pydantic's BaseModel.Config class for use by Invocations.
 
     Provide `schema_extra` a `ui` dict to add hints for generated UIs.

invokeai/app/invocations/collections.py

@@ -1,16 +1,19 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 
-from typing import Literal, Optional
+from typing import Literal
 
 import numpy as np
-import numpy.random
-from pydantic import Field
+from pydantic import Field, validator
+from invokeai.app.models.image import ImageField
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
 from .baseinvocation import (
     BaseInvocation,
     InvocationConfig,
     InvocationContext,
     BaseInvocationOutput,
+    UIConfig,
 )
 
 
@@ -23,8 +26,29 @@ class IntCollectionOutput(BaseInvocationOutput):
     collection: list[int] = Field(default=[], description="The int collection")
 
 
+class FloatCollectionOutput(BaseInvocationOutput):
+    """A collection of floats"""
+
+    type: Literal["float_collection"] = "float_collection"
+
+    # Outputs
+    collection: list[float] = Field(default=[], description="The float collection")
+
+
+class ImageCollectionOutput(BaseInvocationOutput):
+    """A collection of images"""
+
+    type: Literal["image_collection"] = "image_collection"
+
+    # Outputs
+    collection: list[ImageField] = Field(default=[], description="The output images")
+
+    class Config:
+        schema_extra = {"required": ["type", "collection"]}
+
+
 class RangeInvocation(BaseInvocation):
-    """Creates a range"""
+    """Creates a range of numbers from start to stop with step"""
 
     type: Literal["range"] = "range"
 
@@ -33,12 +57,34 @@ class RangeInvocation(BaseInvocation):
     stop: int = Field(default=10, description="The stop of the range")
     step: int = Field(default=1, description="The step of the range")
 
+    @validator("stop")
+    def stop_gt_start(cls, v, values):
+        if "start" in values and v <= values["start"]:
+            raise ValueError("stop must be greater than start")
+        return v
+
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
         return IntCollectionOutput(
             collection=list(range(self.start, self.stop, self.step))
         )
 
 
+class RangeOfSizeInvocation(BaseInvocation):
+    """Creates a range from start to start + size with step"""
+
+    type: Literal["range_of_size"] = "range_of_size"
+
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    size: int = Field(default=1, description="The number of values")
+    step: int = Field(default=1, description="The step of the range")
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(
+            collection=list(range(self.start, self.start + self.size, self.step))
+        )
+
+
 class RandomRangeInvocation(BaseInvocation):
     """Creates a collection of random numbers"""
 
@@ -50,11 +96,11 @@ class RandomRangeInvocation(BaseInvocation):
         default=np.iinfo(np.int32).max, description="The exclusive high value"
     )
     size: int = Field(default=1, description="The number of values to generate")
-    seed: Optional[int] = Field(
+    seed: int = Field(
         ge=0,
-        le=np.iinfo(np.int32).max,
-        description="The seed for the RNG",
-        default_factory=lambda: numpy.random.randint(0, np.iinfo(np.int32).max),
+        le=SEED_MAX,
+        description="The seed for the RNG (omit for random)",
+        default_factory=get_random_seed,
     )
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
@@ -62,3 +108,27 @@ class RandomRangeInvocation(BaseInvocation):
         return IntCollectionOutput(
             collection=list(rng.integers(low=self.low, high=self.high, size=self.size))
         )
+
+
+class ImageCollectionInvocation(BaseInvocation):
+    """Load a collection of images and provide it as output."""
+
+    # fmt: off
+    type: Literal["image_collection"] = "image_collection"
+
+    # Inputs
+    images: list[ImageField] = Field(
+        default=[], description="The image collection to load"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> ImageCollectionOutput:
+        return ImageCollectionOutput(collection=self.images)
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "type_hints": {
+                    "images": "image_collection",
+                }
+            },
+        }

invokeai/app/invocations/compel.py

@@ -0,0 +1,293 @@
+from typing import Literal, Optional, Union, List
+from pydantic import BaseModel, Field
+import re
+import torch
+from compel import Compel
+from compel.prompt_parser import (Blend, Conjunction,
+                                  CrossAttentionControlSubstitute,
+                                  FlattenedPrompt, Fragment)
+from ...backend.util.devices import torch_dtype
+from ...backend.model_management import ModelType
+from ...backend.model_management.models import ModelNotFoundException
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+from .model import ClipField
+
+
+class ConditioningField(BaseModel):
+    conditioning_name: Optional[str] = Field(
+        default=None, description="The name of conditioning data")
+
+    class Config:
+        schema_extra = {"required": ["conditioning_name"]}
+
+
+class CompelOutput(BaseInvocationOutput):
+    """Compel parser output"""
+
+    #fmt: off
+    type: Literal["compel_output"] = "compel_output"
+
+    conditioning: ConditioningField = Field(default=None, description="Conditioning")
+    #fmt: on
+
+
+class CompelInvocation(BaseInvocation):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["compel"] = "compel"
+
+    prompt: str = Field(default="", description="Prompt")
+    clip: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        tokenizer_info = context.services.model_manager.get_model(
+            **self.clip.tokenizer.dict(),
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **self.clip.text_encoder.dict(),
+        )
+
+        def _lora_loader():
+            for lora in self.clip.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.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]
+
+        ti_list = []
+        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    context.services.model_manager.get_model(
+                        model_name=name,
+                        base_model=self.clip.text_encoder.base_model,
+                        model_type=ModelType.TextualInversion,
+                    ).context.model
+                )
+            except ModelNotFoundException:
+                # print(e)
+                #import traceback
+                #print(traceback.format_exc())
+                print(f"Warn: trigger: \"{trigger}\" not found")
+
+        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
+                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
+                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),\
+                text_encoder_info as text_encoder:
+
+            compel = Compel(
+                tokenizer=tokenizer,
+                text_encoder=text_encoder,
+                textual_inversion_manager=ti_manager,
+                dtype_for_device_getter=torch_dtype,
+                truncate_long_prompts=True,  # TODO:
+            )
+
+            conjunction = Compel.parse_prompt_string(self.prompt)
+            prompt: Union[FlattenedPrompt, Blend] = conjunction.prompts[0]
+
+            if context.services.configuration.log_tokenization:
+                log_tokenization_for_prompt_object(prompt, tokenizer)
+
+            c, options = compel.build_conditioning_tensor_for_prompt_object(
+                prompt)
+
+            # TODO: long prompt support
+            # if not self.truncate_long_prompts:
+            #    [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
+            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+                tokens_count_including_eos_bos=get_max_token_count(
+                    tokenizer, conjunction),
+                cross_attention_control_args=options.get(
+                    "cross_attention_control", None),)
+
+        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, (c, ec))
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+class ClipSkipInvocationOutput(BaseInvocationOutput):
+    """Clip skip node output"""
+    type: Literal["clip_skip_output"] = "clip_skip_output"
+    clip: ClipField = Field(None, description="Clip with skipped layers")
+
+class ClipSkipInvocation(BaseInvocation):
+    """Skip layers in clip text_encoder model."""
+    type: Literal["clip_skip"] = "clip_skip"
+
+    clip: ClipField = Field(None, description="Clip to use")
+    skipped_layers: int = Field(0, description="Number of layers to skip in text_encoder")
+
+    def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
+        self.clip.skipped_layers += self.skipped_layers
+        return ClipSkipInvocationOutput(
+            clip=self.clip,
+        )
+
+
+def get_max_token_count(
+        tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction],
+        truncate_if_too_long=False) -> int:
+    if type(prompt) is Blend:
+        blend: Blend = prompt
+        return max(
+            [
+                get_max_token_count(tokenizer, p, truncate_if_too_long)
+                for p in blend.prompts
+            ]
+        )
+    elif type(prompt) is Conjunction:
+        conjunction: Conjunction = prompt
+        return sum(
+            [
+                get_max_token_count(tokenizer, p, truncate_if_too_long)
+                for p in conjunction.prompts
+            ]
+        )
+    else:
+        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]:
+    if type(parsed_prompt) is Blend:
+        raise ValueError(
+            "Blend is not supported here - you need to get tokens for each of its .children"
+        )
+
+    text_fragments = [
+        x.text
+        if type(x) is Fragment
+        else (
+            " ".join([f.text for f in x.original])
+            if type(x) is CrossAttentionControlSubstitute
+            else str(x)
+        )
+        for x in parsed_prompt.children
+    ]
+    text = " ".join(text_fragments)
+    tokens = 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
+):
+    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:
+            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
+):
+    display_label_prefix = display_label_prefix or ""
+    if type(p) is Blend:
+        blend: Blend = p
+        for i, c in enumerate(blend.prompts):
+            log_tokenization_for_prompt_object(
+                c,
+                tokenizer,
+                display_label_prefix=f"{display_label_prefix}(blend part {i + 1}, weight={blend.weights[i]})",
+            )
+    elif type(p) is FlattenedPrompt:
+        flattened_prompt: FlattenedPrompt = p
+        if flattened_prompt.wants_cross_attention_control:
+            original_fragments = []
+            edited_fragments = []
+            for f in flattened_prompt.children:
+                if type(f) is CrossAttentionControlSubstitute:
+                    original_fragments += f.original
+                    edited_fragments += f.edited
+                else:
+                    original_fragments.append(f)
+                    edited_fragments.append(f)
+
+            original_text = " ".join([x.text for x in original_fragments])
+            log_tokenization_for_text(
+                original_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap originals)",
+            )
+            edited_text = " ".join([x.text for x in edited_fragments])
+            log_tokenization_for_text(
+                edited_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap replacements)",
+            )
+        else:
+            text = " ".join([x.text for x in flattened_prompt.children])
+            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):
+    """shows how the prompt is tokenized
+    # usually tokens have '</w>' to indicate end-of-word,
+    # but for readability it has been replaced with ' '
+    """
+    tokens = tokenizer.tokenize(text)
+    tokenized = ""
+    discarded = ""
+    usedTokens = 0
+    totalTokens = len(tokens)
+
+    for i in range(0, totalTokens):
+        token = tokens[i].replace("</w>", " ")
+        # alternate color
+        s = (usedTokens % 6) + 1
+        if truncate_if_too_long and i >= tokenizer.model_max_length:
+            discarded = discarded + f"\x1b[0;3{s};40m{token}"
+        else:
+            tokenized = tokenized + f"\x1b[0;3{s};40m{token}"
+            usedTokens += 1
+
+    if usedTokens > 0:
+        print(f'\n>> [TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
+        print(f"{tokenized}\x1b[0m")
+
+    if discarded != "":
+        print(f"\n>> [TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
+        print(f"{discarded}\x1b[0m")

invokeai/app/invocations/controlnet_image_processors.py

@@ -0,0 +1,565 @@
+# Invocations for ControlNet image preprocessors
+# initial implementation by Gregg Helt, 2023
+# heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
+from builtins import float, bool
+
+import cv2
+import numpy as np
+from typing import Literal, Optional, Union, List, Dict
+from PIL import Image
+from pydantic import BaseModel, Field, validator
+
+from ..models.image import ImageField, ImageCategory, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+from controlnet_aux import (
+    CannyDetector,
+    HEDdetector,
+    LineartDetector,
+    LineartAnimeDetector,
+    MidasDetector,
+    MLSDdetector,
+    NormalBaeDetector,
+    OpenposeDetector,
+    PidiNetDetector,
+    ContentShuffleDetector,
+    ZoeDetector,
+    MediapipeFaceDetector,
+    SamDetector,
+    LeresDetector,
+)
+
+from controlnet_aux.util import HWC3, ade_palette
+
+
+from .image import ImageOutput, PILInvocationConfig
+
+CONTROLNET_DEFAULT_MODELS = [
+    ###########################################
+    # lllyasviel sd v1.5, ControlNet v1.0 models
+    ##############################################
+    "lllyasviel/sd-controlnet-canny",
+    "lllyasviel/sd-controlnet-depth",
+    "lllyasviel/sd-controlnet-hed",
+    "lllyasviel/sd-controlnet-seg",
+    "lllyasviel/sd-controlnet-openpose",
+    "lllyasviel/sd-controlnet-scribble",
+    "lllyasviel/sd-controlnet-normal",
+    "lllyasviel/sd-controlnet-mlsd",
+
+    #############################################
+    # lllyasviel sd v1.5, ControlNet v1.1 models
+    #############################################
+    "lllyasviel/control_v11p_sd15_canny",
+    "lllyasviel/control_v11p_sd15_openpose",
+    "lllyasviel/control_v11p_sd15_seg",
+    # "lllyasviel/control_v11p_sd15_depth",  # broken
+    "lllyasviel/control_v11f1p_sd15_depth",
+    "lllyasviel/control_v11p_sd15_normalbae",
+    "lllyasviel/control_v11p_sd15_scribble",
+    "lllyasviel/control_v11p_sd15_mlsd",
+    "lllyasviel/control_v11p_sd15_softedge",
+    "lllyasviel/control_v11p_sd15s2_lineart_anime",
+    "lllyasviel/control_v11p_sd15_lineart",
+    "lllyasviel/control_v11p_sd15_inpaint",
+    # "lllyasviel/control_v11u_sd15_tile",
+    # problem (temporary?) with huffingface "lllyasviel/control_v11u_sd15_tile",
+    # so for now replace  "lllyasviel/control_v11f1e_sd15_tile",
+    "lllyasviel/control_v11e_sd15_shuffle",
+    "lllyasviel/control_v11e_sd15_ip2p",
+    "lllyasviel/control_v11f1e_sd15_tile",
+
+     #################################################
+     #  thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
+     ##################################################
+     "thibaud/controlnet-sd21-openpose-diffusers",
+     "thibaud/controlnet-sd21-canny-diffusers",
+     "thibaud/controlnet-sd21-depth-diffusers",
+     "thibaud/controlnet-sd21-scribble-diffusers",
+     "thibaud/controlnet-sd21-hed-diffusers",
+     "thibaud/controlnet-sd21-zoedepth-diffusers",
+     "thibaud/controlnet-sd21-color-diffusers",
+     "thibaud/controlnet-sd21-openposev2-diffusers",
+     "thibaud/controlnet-sd21-lineart-diffusers",
+     "thibaud/controlnet-sd21-normalbae-diffusers",
+     "thibaud/controlnet-sd21-ade20k-diffusers",
+
+     ##############################################
+     #  ControlNetMediaPipeface, ControlNet v1.1
+     ##############################################
+     # ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"],  # SD 1.5
+     #    diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg
+     #    hacked t2l to split to model & subfolder if format is "model,subfolder"
+     "CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15",  # SD 1.5
+     "CrucibleAI/ControlNetMediaPipeFace",  # SD 2.1?
+]
+
+CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
+CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
+# crop and fill options not ready yet
+# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
+
+
+class ControlField(BaseModel):
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: Optional[str] = Field(default=None, description="The ControlNet model to use")
+    # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
+    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")
+
+    @validator("control_weight")
+    def abs_le_one(cls, v):
+        """validate that all abs(values) are <=1"""
+        if isinstance(v, list):
+            for i in v:
+                if abs(i) > 1:
+                    raise ValueError('all abs(control_weight) must be <= 1')
+        else:
+            if abs(v) > 1:
+                raise ValueError('abs(control_weight) must be <= 1')
+        return v
+    class Config:
+        schema_extra = {
+            "required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"],
+            "ui": {
+                "type_hints": {
+                    "control_weight": "float",
+                    # "control_weight": "number",
+                }
+            }
+        }
+
+
+class ControlOutput(BaseInvocationOutput):
+    """node output for ControlNet info"""
+    # fmt: off
+    type: Literal["control_output"] = "control_output"
+    control: ControlField = Field(default=None, description="The control info")
+    # fmt: on
+
+
+class ControlNetInvocation(BaseInvocation):
+    """Collects ControlNet info to pass to other nodes"""
+    # fmt: off
+    type: Literal["controlnet"] = "controlnet"
+    # Inputs
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: CONTROLNET_NAME_VALUES = Field(default="lllyasviel/sd-controlnet-canny",
+                                                  description="control model used")
+    control_weight: Union[float, List[float]] = Field(default=1.0, 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 used")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                  "model": "model",
+                  "control": "control",
+                  # "cfg_scale": "float",
+                  "cfg_scale": "number",
+                  "control_weight": "float",
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ControlOutput:
+        return ControlOutput(
+            control=ControlField(
+                image=self.image,
+                control_model=self.control_model,
+                control_weight=self.control_weight,
+                begin_step_percent=self.begin_step_percent,
+                end_step_percent=self.end_step_percent,
+                control_mode=self.control_mode,
+            ),
+        )
+
+
+class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
+    """Base class for invocations that preprocess images for ControlNet"""
+
+    # fmt: off
+    type: Literal["image_processor"] = "image_processor"
+    # Inputs
+    image: ImageField = Field(default=None, description="The image to process")
+    # fmt: on
+
+
+    def run_processor(self, image):
+        # superclass just passes through image without processing
+        return image
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        raw_image = context.services.images.get_pil_image(self.image.image_name)
+        # image type should be PIL.PngImagePlugin.PngImageFile ?
+        processed_image = self.run_processor(raw_image)
+
+        # FIXME: what happened to image metadata?
+        # metadata = context.services.metadata.build_metadata(
+        #     session_id=context.graph_execution_state_id, node=self
+        # )
+
+        # 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
+        )
+
+        """Builds an ImageOutput and its ImageField"""
+        processed_image_field = ImageField(image_name=image_dto.image_name)
+        return ImageOutput(
+            image=processed_image_field,
+            # width=processed_image.width,
+            width = image_dto.width,
+            # height=processed_image.height,
+            height = image_dto.height,
+            # mode=processed_image.mode,
+        )
+
+
+class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Canny edge detection for ControlNet"""
+    # fmt: off
+    type: Literal["canny_image_processor"] = "canny_image_processor"
+    # Input
+    low_threshold: int = Field(default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)")
+    high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)")
+    # fmt: on
+
+    def run_processor(self, image):
+        canny_processor = CannyDetector()
+        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
+        return processed_image
+
+
+class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies HED edge detection to image"""
+    # fmt: off
+    type: Literal["hed_image_processor"] = "hed_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # safe not supported in controlnet_aux v0.0.3
+    # safe: bool = Field(default=False, description="whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = hed_processor(image,
+                                        detect_resolution=self.detect_resolution,
+                                        image_resolution=self.image_resolution,
+                                        # safe not supported in controlnet_aux v0.0.3
+                                        # safe=self.safe,
+                                        scribble=self.scribble,
+                                        )
+        return processed_image
+
+
+class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies line art processing to image"""
+    # fmt: off
+    type: Literal["lineart_image_processor"] = "lineart_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    coarse: bool = Field(default=False, description="Whether to use coarse mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = lineart_processor(image,
+                                            detect_resolution=self.detect_resolution,
+                                            image_resolution=self.image_resolution,
+                                            coarse=self.coarse)
+        return processed_image
+
+
+class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies line art anime processing to image"""
+    # fmt: off
+    type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = processor(image,
+                                    detect_resolution=self.detect_resolution,
+                                    image_resolution=self.image_resolution,
+                                    )
+        return processed_image
+
+
+class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Openpose processing to image"""
+    # fmt: off
+    type: Literal["openpose_image_processor"] = "openpose_image_processor"
+    # Inputs
+    hand_and_face: bool = Field(default=False, description="Whether to use hands and face mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    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
+
+
+class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Midas depth processing to image"""
+    # fmt: off
+    type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
+    # Inputs
+    a_mult: float = Field(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
+    bg_th: float = Field(default=0.1, ge=0, description="Midas parameter `bg_th`")
+    # depth_and_normal not supported in controlnet_aux v0.0.3
+    # depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = midas_processor(image,
+                                          a=np.pi * self.a_mult,
+                                          bg_th=self.bg_th,
+                                          # dept_and_normal not supported in controlnet_aux v0.0.3
+                                          # depth_and_normal=self.depth_and_normal,
+                                          )
+        return processed_image
+
+
+class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies NormalBae processing to image"""
+    # fmt: off
+    type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = normalbae_processor(image,
+                                              detect_resolution=self.detect_resolution,
+                                              image_resolution=self.image_resolution)
+        return processed_image
+
+
+class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies MLSD processing to image"""
+    # fmt: off
+    type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    thr_v: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_v`")
+    thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`")
+    # fmt: on
+
+    def run_processor(self, image):
+        mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = mlsd_processor(image,
+                                         detect_resolution=self.detect_resolution,
+                                         image_resolution=self.image_resolution,
+                                         thr_v=self.thr_v,
+                                         thr_d=self.thr_d)
+        return processed_image
+
+
+class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies PIDI processing to image"""
+    # fmt: off
+    type: Literal["pidi_image_processor"] = "pidi_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    safe: bool = Field(default=False, description="Whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    def run_processor(self, image):
+        pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = pidi_processor(image,
+                                         detect_resolution=self.detect_resolution,
+                                         image_resolution=self.image_resolution,
+                                         safe=self.safe,
+                                         scribble=self.scribble)
+        return processed_image
+
+
+class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies content shuffle processing to image"""
+    # fmt: off
+    type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    h: Optional[int] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
+    w: Optional[int] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
+    f: Optional[int] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
+    # fmt: on
+
+    def run_processor(self, image):
+        content_shuffle_processor = ContentShuffleDetector()
+        processed_image = content_shuffle_processor(image,
+                                                    detect_resolution=self.detect_resolution,
+                                                    image_resolution=self.image_resolution,
+                                                    h=self.h,
+                                                    w=self.w,
+                                                    f=self.f
+                                                    )
+        return processed_image
+
+
+# should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
+class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies Zoe depth processing to image"""
+    # fmt: off
+    type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
+    # fmt: on
+
+    def run_processor(self, image):
+        zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = zoe_depth_processor(image)
+        return processed_image
+
+
+class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies mediapipe face processing to image"""
+    # fmt: off
+    type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
+    # Inputs
+    max_faces: int = Field(default=1, ge=1, description="Maximum number of faces to detect")
+    min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    # fmt: on
+
+    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
+
+class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies leres processing to image"""
+    # fmt: off
+    type: Literal["leres_image_processor"] = "leres_image_processor"
+    # Inputs
+    thr_a: float = Field(default=0, description="Leres parameter `thr_a`")
+    thr_b: float = Field(default=0, description="Leres parameter `thr_b`")
+    boost: bool = Field(default=False, description="Whether to use boost mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    def run_processor(self, image):
+        leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = leres_processor(image,
+                                          thr_a=self.thr_a,
+                                          thr_b=self.thr_b,
+                                          boost=self.boost,
+                                          detect_resolution=self.detect_resolution,
+                                          image_resolution=self.image_resolution)
+        return processed_image
+
+
+class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+
+    # fmt: off
+    type: Literal["tile_image_processor"] = "tile_image_processor"
+    # Inputs
+    #res: int = Field(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
+    down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
+    # fmt: on
+
+    # tile_resample copied from sd-webui-controlnet/scripts/processor.py
+    def tile_resample(self,
+                      np_img: np.ndarray,
+                      res=512,   # never used?
+                      down_sampling_rate=1.0,
+                      ):
+        np_img = HWC3(np_img)
+        if down_sampling_rate < 1.1:
+            return np_img
+        H, W, C = np_img.shape
+        H = int(float(H) / float(down_sampling_rate))
+        W = int(float(W) / float(down_sampling_rate))
+        np_img = cv2.resize(np_img, (W, H), interpolation=cv2.INTER_AREA)
+        return np_img
+
+    def run_processor(self, img):
+        np_img = np.array(img, dtype=np.uint8)
+        processed_np_image = self.tile_resample(np_img,
+                                                #res=self.tile_size,
+                                                down_sampling_rate=self.down_sampling_rate
+                                                )
+        processed_image = Image.fromarray(processed_np_image)
+        return processed_image
+
+
+
+
+class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    """Applies segment anything processing to image"""
+    # fmt: off
+    type: Literal["segment_anything_processor"] = "segment_anything_processor"
+    # fmt: on
+
+    def run_processor(self, image):
+        # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        segment_anything_processor = SamDetectorReproducibleColors.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
+        np_img = np.array(image, dtype=np.uint8)
+        processed_image = segment_anything_processor(np_img)
+        return processed_image
+
+class SamDetectorReproducibleColors(SamDetector):
+
+    # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
+    #     base class show_anns() method randomizes colors,
+    #     which seems to also lead to non-reproducible image generation
+    # so using ADE20k color palette instead
+    def show_anns(self, anns: List[Dict]):
+        if len(anns) == 0:
+            return
+        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
+        h, w = anns[0]['segmentation'].shape
+        final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
+        palette = ade_palette()
+        for i, ann in enumerate(sorted_anns):
+            m = ann['segmentation']
+            img = np.empty((m.shape[0], m.shape[1], 3), dtype=np.uint8)
+            # doing modulo just in case number of annotated regions exceeds number of colors in palette
+            ann_color = palette[i % len(palette)]
+            img[:, :] = ann_color
+            final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
+        return np.array(final_img, dtype=np.uint8)

invokeai/app/invocations/cv.py

@@ -7,9 +7,9 @@ import numpy
 from PIL import Image, ImageOps
 from pydantic import BaseModel, Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from .image import ImageOutput
 
 
 class CvInvocationConfig(BaseModel):
@@ -26,24 +26,23 @@ class CvInvocationConfig(BaseModel):
 
 class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
     """Simple inpaint using opencv."""
-    #fmt: off
+
+    # fmt: off
     type: Literal["cv_inpaint"] = "cv_inpaint"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to inpaint")
     mask: ImageField = Field(default=None, description="The mask to use when inpainting")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
-        mask = context.services.images.get(self.mask.image_type, self.mask.image_name)
+        image = context.services.images.get_pil_image(self.image.image_name)
+        mask = context.services.images.get_pil_image(self.mask.image_name)
 
         # Convert to cv image/mask
         # TODO: consider making these utility functions
         cv_image = cv.cvtColor(numpy.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
-        cv_mask = numpy.array(ImageOps.invert(mask))
+        cv_mask = numpy.array(ImageOps.invert(mask.convert("L")))
 
         # Inpaint
         cv_inpainted = cv.inpaint(cv_image, cv_mask, 3, cv.INPAINT_TELEA)
@@ -52,18 +51,17 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
         # TODO: consider making a utility function
         image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        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,
         )
 
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
-        
-        context.services.images.save(image_type, image_name, image_inpainted, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=image_inpainted,
-        )

invokeai/app/invocations/generate.py

@@ -1,145 +1,80 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from functools import partial
-from typing import Literal, Optional, Union
+from typing import Literal, Optional, get_args
 
-import numpy as np
-from diffusers import ControlNetModel
-from torch import Tensor
 import torch
+from pydantic import Field
 
-from pydantic import BaseModel, Field
+from invokeai.app.models.image import (ColorField, ImageCategory, ImageField,
+                                       ResourceOrigin)
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.generator.inpaint import infill_methods
 
-from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.invocations.util.choose_model import choose_model
-from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
-from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+from ...backend.generator import Inpaint, InvokeAIGenerator
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ..util.step_callback import stable_diffusion_step_callback
+from .baseinvocation import BaseInvocation, InvocationConfig, InvocationContext
+from .image import ImageOutput
+
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
+from .model import UNetField, VaeField
+from .compel import ConditioningField
+from contextlib import contextmanager, ExitStack, ContextDecorator
 
 SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = (
+    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+)
 
 
-class SDImageInvocation(BaseModel):
-    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
+from .latent import get_scheduler
 
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["stable-diffusion", "image"],
-                "type_hints": {
-                    "model": "model",
-                },
-            },
-        }
+class OldModelContext(ContextDecorator):
+    model: StableDiffusionGeneratorPipeline
+
+    def __init__(self, model):
+        self.model = model
+
+    def __enter__(self):
+        return self.model
+
+    def __exit__(self, *exc):
+        return False
+
+class OldModelInfo:
+    name: str
+    hash: str
+    context: OldModelContext
+
+    def __init__(self, name: str, hash: str, model: StableDiffusionGeneratorPipeline):
+        self.name = name
+        self.hash = hash
+        self.context = OldModelContext(
+            model=model,
+        )
 
 
-# Text to image
-class TextToImageInvocation(BaseInvocation, SDImageInvocation):
-    """Generates an image using text2img."""
+class InpaintInvocation(BaseInvocation):
+    """Generates an image using inpaint."""
 
-    type: Literal["txt2img"] = "txt2img"
+    type: Literal["inpaint"] = "inpaint"
+
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
+    steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
+    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
+    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
+    cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    unet: UNetField = Field(default=None, description="UNet model")
+    vae: VaeField = Field(default=None, description="Vae model")
 
     # Inputs
-    # TODO: consider making prompt optional to enable providing prompt through a link
-    # fmt: off
-    prompt: Optional[str] = Field(description="The prompt to generate an image from")
-    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
-    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
-    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
-    control_model: Optional[str] = Field(default=None, description="The control model to use")
-    control_image: Optional[ImageField] = Field(default=None, description="The processed control image")
-    # control_strength: Optional[float] = Field(default=1.0, ge=0, le=1, description="The strength of the controlnet")
-    # fmt: on
-
-    # 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,
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.dict(),
-            source_node_id=source_node_id,
-        )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        model = choose_model(context.services.model_manager, self.model)
-
-        # loading controlnet image (currently requires pre-processed image)
-        control_image = (
-            None if self.control_image is None
-            else context.services.images.get(
-                self.control_image.image_type, self.control_image.image_name
-            )
-        )
-        # loading controlnet model
-        if (self.control_model is None or self.control_model==''):
-            control_model = None
-        else:
-            # FIXME: change this to dropdown menu?
-            control_model = ControlNetModel.from_pretrained(self.control_model,
-                                                            torch_dtype=torch.float16).to("cuda")
-
-        # 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]
-
-        txt2img = Txt2Img(model, control_model=control_model)
-        outputs = txt2img.generate(
-            prompt=self.prompt,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            control_image=control_image,
-            **self.dict(
-                exclude={"prompt", "control_image" }
-            ),  # Shorthand for passing all of the parameters above manually
-        )
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generate_output = next(outputs)
-
-        # Results are image and seed, unwrap for now and ignore the seed
-        # TODO: pre-seed?
-        # TODO: can this return multiple results? Should it?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
-        )
-
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(
-            image_type, image_name, generate_output.image, metadata
-        )
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=generate_output.image,
-        )
-
-
-class ImageToImageInvocation(TextToImageInvocation):
-    """Generates an image using img2img."""
-
-    type: Literal["img2img"] = "img2img"
-
-    # Inputs
-    image: Union[ImageField, None] = Field(description="The input image")
+    image: Optional[ImageField] = Field(description="The input image")
     strength: float = Field(
         default=0.75, gt=0, le=1, description="The strength of the original image"
     )
@@ -148,81 +83,41 @@ class ImageToImageInvocation(TextToImageInvocation):
         description="Whether or not the result should be fit to the aspect ratio of the input image",
     )
 
-    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.dict(),
-            source_node_id=source_node_id,
-        )
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = (
-            None
-            if self.image is None
-            else context.services.images.get(
-                self.image.image_type, self.image.image_name
-            )
-        )
-        mask = None
-
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-
-        # 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]
-
-        outputs = Img2Img(model).generate(
-            prompt=self.prompt,
-            init_image=image,
-            init_mask=mask,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            **self.dict(
-                exclude={"prompt", "image", "mask"}
-            ),  # Shorthand for passing all of the parameters above manually
-        )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
-
-        result_image = generator_output.image
-
-        # Results are image and seed, unwrap for now and ignore the seed
-        # TODO: pre-seed?
-        # TODO: can this return multiple results? Should it?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
-        )
-
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(image_type, image_name, result_image, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=result_image,
-        )
-
-
-class InpaintInvocation(ImageToImageInvocation):
-    """Generates an image using inpaint."""
-
-    type: Literal["inpaint"] = "inpaint"
-
     # Inputs
-    mask: Union[ImageField, None] = Field(description="The mask")
+    mask: Optional[ImageField] = Field(description="The mask")
+    seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
+    seam_blur: int = Field(
+        default=16, ge=0, description="The seam inpaint blur radius (px)"
+    )
+    seam_strength: float = Field(
+        default=0.75, gt=0, le=1, description="The seam inpaint strength"
+    )
+    seam_steps: int = Field(
+        default=30, ge=1, description="The number of steps to use for seam inpaint"
+    )
+    tile_size: int = Field(
+        default=32, ge=1, description="The tile infill method size (px)"
+    )
+    infill_method: INFILL_METHODS = Field(
+        default=DEFAULT_INFILL_METHOD,
+        description="The method used to infill empty regions (px)",
+    )
+    inpaint_width: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The width of the inpaint region (px)",
+    )
+    inpaint_height: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The height of the inpaint region (px)",
+    )
+    inpaint_fill: Optional[ColorField] = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The solid infill method color",
+    )
     inpaint_replace: float = Field(
         default=0.0,
         ge=0.0,
@@ -230,6 +125,14 @@ class InpaintInvocation(ImageToImageInvocation):
         description="The amount by which to replace masked areas with latent noise",
     )
 
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+            },
+        }
+
     def dispatch_progress(
         self,
         context: InvocationContext,
@@ -243,60 +146,101 @@ class InpaintInvocation(ImageToImageInvocation):
             source_node_id=source_node_id,
         )
 
+    def get_conditioning(self, context):
+        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+
+        return (uc, c, extra_conditioning_info)
+
+    @contextmanager
+    def load_model_old_way(self, context, scheduler):
+        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
+        vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
+
+        #unet = unet_info.context.model
+        #vae = vae_info.context.model
+
+        with 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]
+
+            with vae_info as vae,\
+                 unet_info as unet,\
+                 ModelPatcher.apply_lora_unet(unet, loras):
+
+                device = context.services.model_manager.mgr.cache.execution_device
+                dtype = context.services.model_manager.mgr.cache.precision
+
+                pipeline = StableDiffusionGeneratorPipeline(
+                    vae=vae,
+                    text_encoder=None,
+                    tokenizer=None,
+                    unet=unet,
+                    scheduler=scheduler,
+                    safety_checker=None,
+                    feature_extractor=None,
+                    requires_safety_checker=False,
+                    precision="float16" if dtype == torch.float16 else "float32",
+                    execution_device=device,
+                )
+
+                yield OldModelInfo(
+                    name=self.unet.unet.model_name,
+                    hash="<NO-HASH>",
+                    model=pipeline,
+                )
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
             if self.image is None
-            else context.services.images.get(
-                self.image.image_type, self.image.image_name
-            )
+            else context.services.images.get_pil_image(self.image.image_name)
         )
         mask = (
             None
             if self.mask is None
-            else context.services.images.get(self.mask.image_type, self.mask.image_name)
+            else context.services.images.get_pil_image(self.mask.image_name)
         )
 
-        # Handle invalid model parameter
-        model = choose_model(context.services.model_manager, self.model)
-
         # 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]
 
-        outputs = Inpaint(model).generate(
-            prompt=self.prompt,
-            init_img=image,
-            init_mask=mask,
-            step_callback=partial(self.dispatch_progress, context, source_node_id),
-            **self.dict(
-                exclude={"prompt", "image", "mask"}
-            ),  # Shorthand for passing all of the parameters above manually
+        conditioning = self.get_conditioning(context)
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
         )
 
+        with self.load_model_old_way(context, scheduler) as model:
+            outputs = Inpaint(model).generate(
+                conditioning=conditioning,
+                scheduler=scheduler,
+                init_image=image,
+                mask_image=mask,
+                step_callback=partial(self.dispatch_progress, context, source_node_id),
+                **self.dict(
+                    exclude={"positive_conditioning", "negative_conditioning", "scheduler", "image", "mask"}
+                ),  # Shorthand for passing all of the parameters above manually
+            )
+
         # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
         # each time it is called. We only need the first one.
         generator_output = next(outputs)
 
-        result_image = generator_output.image
-
-        # Results are image and seed, unwrap for now and ignore the seed
-        # TODO: pre-seed?
-        # TODO: can this return multiple results? Should it?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=generator_output.image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            session_id=context.graph_execution_state_id,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate,
         )
 
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(image_type, image_name, result_image, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=result_image,
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )

invokeai/app/invocations/image.py

@@ -3,10 +3,10 @@
 from typing import Literal, Optional
 
 import numpy
-from PIL import Image, ImageFilter, ImageOps
+from PIL import Image, ImageFilter, ImageOps, ImageChops
 from pydantic import BaseModel, Field
 
-from ..models.image import ImageField, ImageType
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
@@ -30,32 +30,14 @@ class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
 
     # fmt: off
-    type: Literal["image"] = "image"
+    type: Literal["image_output"] = "image_output"
     image:      ImageField = Field(default=None, description="The output image")
-    width:   Optional[int] = Field(default=None, description="The width of the image in pixels")
-    height:  Optional[int] = Field(default=None, description="The height of the image in pixels")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
     # fmt: on
 
     class Config:
-        schema_extra = {
-            "required": ["type", "image", "width", "height", "mode"]
-        }
-
-
-def build_image_output(
-    image_type: ImageType, image_name: str, image: Image.Image
-) -> ImageOutput:
-    """Builds an ImageOutput and its ImageField"""
-    image_field = ImageField(
-        image_name=image_name,
-        image_type=image_type,
-    )
-    return ImageOutput(
-        image=image_field,
-        width=image.width,
-        height=image.height,
-        mode=image.mode,
-    )
+        schema_extra = {"required": ["type", "image", "width", "height"]}
 
 
 class MaskOutput(BaseInvocationOutput):
@@ -64,6 +46,8 @@ class MaskOutput(BaseInvocationOutput):
     # fmt: off
     type: Literal["mask"] = "mask"
     mask:      ImageField = Field(default=None, description="The output mask")
+    width:            int = Field(description="The width of the mask in pixels")
+    height:           int = Field(description="The height of the mask in pixels")
     # fmt: on
 
     class Config:
@@ -82,16 +66,17 @@ class LoadImageInvocation(BaseInvocation):
     type: Literal["load_image"] = "load_image"
 
     # Inputs
-    image_type: ImageType = Field(description="The type of the image")
-    image_name:       str = Field(description="The name of the image")
+    image: Optional[ImageField] = Field(
+        default=None, description="The image to load"
+    )
     # fmt: on
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(self.image_type, self.image_name)
+        image = context.services.images.get_pil_image(self.image.image_name)
 
-        return build_image_output(
-            image_type=self.image_type,
-            image_name=self.image_name,
-            image=image,
+        return ImageOutput(
+            image=ImageField(image_name=self.image.image_name),
+            width=image.width,
+            height=image.height,
         )
 
 
@@ -101,32 +86,32 @@ class ShowImageInvocation(BaseInvocation):
     type: Literal["show_image"] = "show_image"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to show")
+    image: Optional[ImageField] = Field(
+        default=None, description="The image to show"
+    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         if image:
             image.show()
 
         # TODO: how to handle failure?
 
-        return build_image_output(
-            image_type=self.image.image_type,
-            image_name=self.image.image_name,
-            image=image,
+        return ImageOutput(
+            image=ImageField(image_name=self.image.image_name),
+            width=image.width,
+            height=image.height,
         )
 
 
-class CropImageInvocation(BaseInvocation, PILInvocationConfig):
+class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
     """Crops an image to a specified box. The box can be outside of the image."""
 
     # fmt: off
-    type: Literal["crop"] = "crop"
+    type: Literal["img_crop"] = "img_crop"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to crop")
+    image: Optional[ImageField]  = Field(default=None, description="The image to crop")
     x:      int = Field(default=0, description="The left x coordinate of the crop rectangle")
     y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
     width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
@@ -134,58 +119,51 @@ class CropImageInvocation(BaseInvocation, PILInvocationConfig):
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_crop = Image.new(
             mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
         )
         image_crop.paste(image, (-self.x, -self.y))
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
-        )
-
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-        
-        context.services.images.save(image_type, image_name, image_crop, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
+        image_dto = context.services.images.create(
             image=image_crop,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 
 
-class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
+class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
     """Pastes an image into another image."""
 
     # fmt: off
-    type: Literal["paste"] = "paste"
+    type: Literal["img_paste"] = "img_paste"
 
     # Inputs
-    base_image:     ImageField = Field(default=None, description="The base image")
-    image:          ImageField = Field(default=None, description="The image to paste")
+    base_image:     Optional[ImageField]  = Field(default=None, description="The base image")
+    image:          Optional[ImageField]  = Field(default=None, description="The image to paste")
     mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
     x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
     y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        base_image = context.services.images.get(
-            self.base_image.image_type, self.base_image.image_name
-        )
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        base_image = context.services.images.get_pil_image(self.base_image.image_name)
+        image = context.services.images.get_pil_image(self.image.image_name)
         mask = (
             None
             if self.mask is None
             else ImageOps.invert(
-                context.services.images.get(self.mask.image_type, self.mask.image_name)
+                context.services.images.get_pil_image(self.mask.image_name)
             )
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
@@ -201,20 +179,19 @@ class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
         new_image.paste(base_image, (abs(min_x), abs(min_y)))
         new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
 
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=new_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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-        
-        context.services.images.save(image_type, image_name, new_image, metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=new_image,
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 
 
@@ -225,48 +202,150 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
     type: Literal["tomask"] = "tomask"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to create the mask from")
+    image: Optional[ImageField]  = Field(default=None, description="The image to create the mask from")
     invert:      bool = Field(default=False, description="Whether or not to invert the mask")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_mask = image.split()[-1]
         if self.invert:
             image_mask = ImageOps.invert(image_mask)
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=image_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,
         )
 
-        metadata = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
+        return MaskOutput(
+            mask=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 
-        context.services.images.save(image_type, image_name, image_mask, metadata)
-        return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
+
+class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
+    """Multiplies two images together using `PIL.ImageChops.multiply()`."""
+
+    # fmt: off
+    type: Literal["img_mul"] = "img_mul"
+
+    # Inputs
+    image1: Optional[ImageField]  = Field(default=None, description="The first image to multiply")
+    image2: Optional[ImageField]  = Field(default=None, description="The second image to multiply")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image1 = context.services.images.get_pil_image(self.image1.image_name)
+        image2 = context.services.images.get_pil_image(self.image2.image_name)
+
+        multiply_image = ImageChops.multiply(image1, image2)
+
+        image_dto = context.services.images.create(
+            image=multiply_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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
 
 
-class BlurInvocation(BaseInvocation, PILInvocationConfig):
+IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
+
+
+class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
+    """Gets a channel from an image."""
+
+    # fmt: off
+    type: Literal["img_chan"] = "img_chan"
+
+    # Inputs
+    image: Optional[ImageField]  = Field(default=None, description="The image to get the channel from")
+    channel: IMAGE_CHANNELS  = Field(default="A", description="The channel to get")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        channel_image = image.getchannel(self.channel)
+
+        image_dto = context.services.images.create(
+            image=channel_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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
+
+
+class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
+    """Converts an image to a different mode."""
+
+    # fmt: off
+    type: Literal["img_conv"] = "img_conv"
+
+    # Inputs
+    image: Optional[ImageField]  = Field(default=None, description="The image to convert")
+    mode: IMAGE_MODES  = Field(default="L", description="The mode to convert to")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        converted_image = image.convert(self.mode)
+
+        image_dto = context.services.images.create(
+            image=converted_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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
     """Blurs an image"""
 
     # fmt: off
-    type: Literal["blur"] = "blur"
+    type: Literal["img_blur"] = "img_blur"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to blur")
+    image: Optional[ImageField]  = Field(default=None, description="The image to blur")
     radius:     float = Field(default=8.0, ge=0, description="The blur radius")
     blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         blur = (
             ImageFilter.GaussianBlur(self.radius)
@@ -275,74 +354,171 @@ class BlurInvocation(BaseInvocation, PILInvocationConfig):
         )
         blur_image = image.filter(blur)
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=blur_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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(image_type, image_name, blur_image, metadata)
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=blur_image
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 
 
-class LerpInvocation(BaseInvocation, PILInvocationConfig):
+PIL_RESAMPLING_MODES = Literal[
+    "nearest",
+    "box",
+    "bilinear",
+    "hamming",
+    "bicubic",
+    "lanczos",
+]
+
+
+PIL_RESAMPLING_MAP = {
+    "nearest": Image.Resampling.NEAREST,
+    "box": Image.Resampling.BOX,
+    "bilinear": Image.Resampling.BILINEAR,
+    "hamming": Image.Resampling.HAMMING,
+    "bicubic": Image.Resampling.BICUBIC,
+    "lanczos": Image.Resampling.LANCZOS,
+}
+
+
+class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
+    """Resizes an image to specific dimensions"""
+
+    # fmt: off
+    type: Literal["img_resize"] = "img_resize"
+
+    # Inputs
+    image: Optional[ImageField]  = Field(default=None, description="The image to resize")
+    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
+    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
+
+        resize_image = image.resize(
+            (self.width, self.height),
+            resample=resample_mode,
+        )
+
+        image_dto = context.services.images.create(
+            image=resize_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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
+    """Scales an image by a factor"""
+
+    # fmt: off
+    type: Literal["img_scale"] = "img_scale"
+
+    # Inputs
+    image:       Optional[ImageField] = Field(default=None, description="The image to scale")
+    scale_factor:                  float = Field(gt=0, description="The factor by which to scale the image")
+    resample_mode:  PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
+        width = int(image.width * self.scale_factor)
+        height = int(image.height * self.scale_factor)
+
+        resize_image = image.resize(
+            (width, height),
+            resample=resample_mode,
+        )
+
+        image_dto = context.services.images.create(
+            image=resize_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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
     """Linear interpolation of all pixels of an image"""
 
     # fmt: off
-    type: Literal["lerp"] = "lerp"
+    type: Literal["img_lerp"] = "img_lerp"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to lerp")
+    image: Optional[ImageField]  = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32) / 255
         image_arr = image_arr * (self.max - self.min) + self.max
 
         lerp_image = Image.fromarray(numpy.uint8(image_arr))
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=lerp_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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(image_type, image_name, lerp_image, metadata)
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=lerp_image
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
 
 
-class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
+class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
     """Inverse linear interpolation of all pixels of an image"""
 
     # fmt: off
-    type: Literal["ilerp"] = "ilerp"
+    type: Literal["img_ilerp"] = "img_ilerp"
 
     # Inputs
-    image: ImageField = Field(default=None, description="The image to lerp")
+    image: Optional[ImageField]  = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
     # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32)
         image_arr = (
@@ -354,16 +530,17 @@ class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
 
         ilerp_image = Image.fromarray(numpy.uint8(image_arr))
 
-        image_type = ImageType.INTERMEDIATE
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=ilerp_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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
-        )
-
-        context.services.images.save(image_type, image_name, ilerp_image, metadata)
-        return build_image_output(
-            image_type=image_type, image_name=image_name, image=ilerp_image
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )

invokeai/app/invocations/infill.py

@@ -0,0 +1,230 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+
+from typing import Literal, Optional, get_args
+
+import numpy as np
+import math
+from PIL import Image, ImageOps
+from pydantic import Field
+
+from invokeai.app.invocations.image import ImageOutput
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.image_util.patchmatch import PatchMatch
+
+from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationContext,
+)
+
+
+def infill_methods() -> list[str]:
+    methods = [
+        "tile",
+        "solid",
+    ]
+    if PatchMatch.patchmatch_available():
+        methods.insert(0, "patchmatch")
+    return methods
+
+
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = (
+    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+)
+
+
+def infill_patchmatch(im: Image.Image) -> Image.Image:
+    if im.mode != "RGBA":
+        return im
+
+    # Skip patchmatch if patchmatch isn't available
+    if not PatchMatch.patchmatch_available():
+        return im
+
+    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
+    im_patched_np = PatchMatch.inpaint(
+        im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3
+    )
+    im_patched = Image.fromarray(im_patched_np, mode="RGB")
+    return im_patched
+
+
+def get_tile_images(image: np.ndarray, width=8, height=8):
+    _nrows, _ncols, depth = image.shape
+    _strides = image.strides
+
+    nrows, _m = divmod(_nrows, height)
+    ncols, _n = divmod(_ncols, width)
+    if _m != 0 or _n != 0:
+        return None
+
+    return np.lib.stride_tricks.as_strided(
+        np.ravel(image),
+        shape=(nrows, ncols, height, width, depth),
+        strides=(height * _strides[0], width * _strides[1], *_strides),
+        writeable=False,
+    )
+
+
+def tile_fill_missing(
+    im: Image.Image, tile_size: int = 16, seed: Optional[int] = None
+) -> Image.Image:
+    # Only fill if there's an alpha layer
+    if im.mode != "RGBA":
+        return im
+
+    a = np.asarray(im, dtype=np.uint8)
+
+    tile_size_tuple = (tile_size, tile_size)
+
+    # Get the image as tiles of a specified size
+    tiles = get_tile_images(a, *tile_size_tuple).copy()
+
+    # Get the mask as tiles
+    tiles_mask = tiles[:, :, :, :, 3]
+
+    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
+    tmask_shape = tiles_mask.shape
+    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
+    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
+    tiles_mask = tiles_mask > 0
+    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
+
+    # Get RGB tiles in single array and filter by the mask
+    tshape = tiles.shape
+    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
+    filtered_tiles = tiles_all[tiles_mask]
+
+    if len(filtered_tiles) == 0:
+        return im
+
+    # Find all invalid tiles and replace with a random valid tile
+    replace_count = (tiles_mask == False).sum()
+    rng = np.random.default_rng(seed=seed)
+    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[
+        rng.choice(filtered_tiles.shape[0], replace_count), :, :, :
+    ]
+
+    # Convert back to an image
+    tiles_all = tiles_all.reshape(tshape)
+    tiles_all = tiles_all.swapaxes(1, 2)
+    st = tiles_all.reshape(
+        (
+            math.prod(tiles_all.shape[0:2]),
+            math.prod(tiles_all.shape[2:4]),
+            tiles_all.shape[4],
+        )
+    )
+    si = Image.fromarray(st, mode="RGBA")
+
+    return si
+
+
+class InfillColorInvocation(BaseInvocation):
+    """Infills transparent areas of an image with a solid color"""
+
+    type: Literal["infill_rgba"] = "infill_rgba"
+    image: Optional[ImageField] = Field(
+        default=None, description="The image to infill"
+    )
+    color: ColorField = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The color to use to infill",
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class InfillTileInvocation(BaseInvocation):
+    """Infills transparent areas of an image with tiles of the image"""
+
+    type: Literal["infill_tile"] = "infill_tile"
+
+    image: Optional[ImageField] = Field(
+        default=None, description="The image to infill"
+    )
+    tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use for tile generation (omit for random)",
+        default_factory=get_random_seed,
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class InfillPatchMatchInvocation(BaseInvocation):
+    """Infills transparent areas of an image using the PatchMatch algorithm"""
+
+    type: Literal["infill_patchmatch"] = "infill_patchmatch"
+
+    image: Optional[ImageField] = Field(
+        default=None, description="The image to infill"
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        if PatchMatch.patchmatch_available():
+            infilled = infill_patchmatch(image.copy())
+        else:
+            raise ValueError("PatchMatch is not available on this system")
+
+        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,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/latent.py

@@ -1,265 +1,124 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-import random
-from typing import Literal, Optional
-from pydantic import BaseModel, Field
-import torch
+from typing import List, Literal, Optional, Union
 
-from invokeai.app.invocations.util.choose_model import choose_model
+import einops
+import torch
+from diffusers import ControlNetModel
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.schedulers import SchedulerMixin as Scheduler
+from pydantic import BaseModel, Field, validator
 
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 
-from ...backend.model_management.model_manager import ModelManager
-from ...backend.util.devices import choose_torch_device, torch_dtype
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
-from ...backend.image_util.seamless import configure_model_padding
-from ...backend.prompting.conditioning import get_uc_and_c_and_ec
-from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
-import numpy as np
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput, build_image_output
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from ...backend.model_management.lora import ModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
-from diffusers.schedulers import SchedulerMixin as Scheduler
-import diffusers
-from diffusers import DiffusionPipeline
+from ...backend.stable_diffusion.diffusers_pipeline import (
+    ConditioningData, ControlNetData, StableDiffusionGeneratorPipeline,
+    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 torch_dtype
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+from .compel import ConditioningField
+from .controlnet_image_processors import ControlField
+from .image import ImageOutput
+from .model import ModelInfo, UNetField, VaeField
 
 
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
 
-    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
+    latents_name: Optional[str] = Field(
+        default=None, description="The name of the latents")
 
     class Config:
         schema_extra = {"required": ["latents_name"]}
 
+
 class LatentsOutput(BaseInvocationOutput):
     """Base class for invocations that output latents"""
     #fmt: off
-    type: Literal["latent_output"] = "latent_output"
-    latents: LatentsField            = Field(default=None, description="The output latents")
-    #fmt: on
+    type: Literal["latents_output"] = "latents_output"
 
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-    #fmt: off
-    type: Literal["noise_output"] = "noise_output"
-    noise: LatentsField            = Field(default=None, description="The output noise")
+    # Inputs
+    latents: LatentsField          = Field(default=None, description="The output latents")
+    width:                     int = Field(description="The width of the latents in pixels")
+    height:                    int = Field(description="The height of the latents in pixels")
     #fmt: on
 
 
-# TODO: this seems like a hack
-scheduler_map = dict(
-    ddim=diffusers.DDIMScheduler,
-    dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_dpm_2=diffusers.KDPM2DiscreteScheduler,
-    k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
-    k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_euler=diffusers.EulerDiscreteScheduler,
-    k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
-    k_heun=diffusers.HeunDiscreteScheduler,
-    k_lms=diffusers.LMSDiscreteScheduler,
-    plms=diffusers.PNDMScheduler,
-)
+def build_latents_output(latents_name: str, latents: torch.Tensor):
+    return LatentsOutput(
+        latents=LatentsField(latents_name=latents_name),
+        width=latents.size()[3] * 8,
+        height=latents.size()[2] * 8,
+    )
 
 
 SAMPLER_NAME_VALUES = Literal[
-    tuple(list(scheduler_map.keys()))
+    tuple(list(SCHEDULER_MAP.keys()))
 ]
 
 
-def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-    scheduler_class = scheduler_map.get(scheduler_name,'ddim')
-    scheduler = scheduler_class.from_config(model.scheduler.config)
+def get_scheduler(
+    context: InvocationContext,
+    scheduler_info: ModelInfo,
+    scheduler_name: str,
+) -> 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.dict())
+    with orig_scheduler_info as orig_scheduler:
+        scheduler_config = orig_scheduler.config
+
+    if "_backup" in scheduler_config:
+        scheduler_config = scheduler_config["_backup"]
+    scheduler_config = {**scheduler_config, **
+                        scheduler_extra_config, "_backup": scheduler_config}
+    scheduler = scheduler_class.from_config(scheduler_config)
+
     # hack copied over from generate.py
     if not hasattr(scheduler, 'uses_inpainting_model'):
         scheduler.uses_inpainting_model = lambda: False
     return scheduler
 
 
-def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
-    generator = torch.Generator(device=use_device).manual_seed(seed)
-    x = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width //  downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=use_device,
-        generator=generator,
-    ).to(device)
-    # if self.perlin > 0.0:
-    #     perlin_noise = self.get_perlin_noise(
-    #         width // self.downsampling_factor, height // self.downsampling_factor
-    #     )
-    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
-    return x
-
-
-def random_seed():
-    return random.randint(0, np.iinfo(np.uint32).max)
-
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed:        int = Field(ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", default_factory=random_seed)
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting noise", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting noise", )
-
-
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "noise"],
-            },
-        }
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        device = torch.device(choose_torch_device())
-        noise = get_noise(self.width, self.height, device, self.seed)
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, noise)
-        return NoiseOutput(
-            noise=LatentsField(latents_name=name)
-        )
-
-
 # Text to image
 class TextToLatentsInvocation(BaseInvocation):
-    """Generates latents from a prompt."""
+    """Generates latents from conditionings."""
 
     type: Literal["t2l"] = "t2l"
 
     # Inputs
-    # TODO: consider making prompt optional to enable providing prompt through a link
     # fmt: off
-    prompt: Optional[str] = Field(description="The prompt to generate an image from")
-    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
     noise: Optional[LatentsField] = Field(description="The noise to use")
     steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
-    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
+    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
+    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
     # fmt: on
 
-    # Schema customisation
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["latents", "image"],
-                "type_hints": {
-                  "model": "model"
-                }
-            },
-        }
-
-    # 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
-    ) -> None:
-        stable_diffusion_step_callback(
-            context=context,
-            intermediate_state=intermediate_state,
-            node=self.dict(),
-            source_node_id=source_node_id,
-        )
-
-    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
-        model_info = choose_model(model_manager, self.model)
-        model_name = model_info['model_name']
-        model_hash = model_info['hash']
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-        model.scheduler = get_scheduler(
-            model=model,
-            scheduler_name=self.scheduler
-        )
-
-        if isinstance(model, DiffusionPipeline):
-            for component in [model.unet, model.vae]:
-                configure_model_padding(component,
-                                        self.seamless,
-                                        self.seamless_axes
-                                        )
+    @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:
-            configure_model_padding(model,
-                                    self.seamless,
-                                    self.seamless_axes
-                                    )
-
-        return model
-
-
-    def get_conditioning_data(self, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
-        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(self.prompt, model=model)
-        conditioning_data = ConditioningData(
-            uc,
-            c,
-            self.cfg_scale,
-            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,
-            ),
-        ).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
-        return conditioning_data
-
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-
-        # 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]
-
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, source_node_id, state)
-
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
-
-        # TODO: Verify the noise is the right size
-
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
-
-
-class LatentsToLatentsInvocation(TextToLatentsInvocation):
-    """Generates latents using latents as base image."""
-
-    type: Literal["l2l"] = "l2l"
+            if v < 1:
+                raise ValueError('cfg_scale must be greater than 1')
+        return v
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -267,58 +126,314 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             "ui": {
                 "tags": ["latents"],
                 "type_hints": {
-                    "model": "model"
+                    "model": "model",
+                    "control": "control",
+                    # "cfg_scale": "float",
+                    "cfg_scale": "number"
                 }
             },
         }
 
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
-    strength: float = Field(default=0.5, description="The strength of the latents to use")
+    # 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) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
 
+    def get_conditioning_data(
+            self, context: InvocationContext, scheduler) -> ConditioningData:
+        c, extra_conditioning_info = context.services.latents.get(
+            self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(
+            self.negative_conditioning.conditioning_name)
+
+        conditioning_data = ConditioningData(
+            unconditioned_embeddings=uc,
+            text_embeddings=c,
+            guidance_scale=self.cfg_scale,
+            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(
+            scheduler,
+
+            # for ddim scheduler
+            eta=0.0,  # ddim_eta
+
+            # for ancestral and sde schedulers
+            generator=torch.Generator(device=uc.device).manual_seed(0),
+        )
+        return conditioning_data
+
+    def create_pipeline(
+            self, unet, scheduler) -> StableDiffusionGeneratorPipeline:
+        # TODO:
+        # configure_model_padding(
+        #    unet,
+        #    self.seamless,
+        #    self.seamless_axes,
+        # )
+
+        class FakeVae:
+            class FakeVaeConfig:
+                def __init__(self):
+                    self.block_out_channels = [0]
+
+            def __init__(self):
+                self.config = FakeVae.FakeVaeConfig()
+
+        return StableDiffusionGeneratorPipeline(
+            vae=FakeVae(),  # TODO: oh...
+            text_encoder=None,
+            tokenizer=None,
+            unet=unet,
+            scheduler=scheduler,
+            safety_checker=None,
+            feature_extractor=None,
+            requires_safety_checker=False,
+            precision="float16" if unet.dtype == torch.float16 else "float32",
+        )
+
+    def prep_control_data(
+        self,
+        context: InvocationContext,
+        # really only need model for dtype and device
+        model: StableDiffusionGeneratorPipeline,
+        control_input: List[ControlField],
+        latents_shape: List[int],
+        do_classifier_free_guidance: bool = True,
+    ) -> List[ControlNetData]:
+
+        # assuming fixed dimensional scaling of 8:1 for image:latents
+        control_height_resize = latents_shape[2] * 8
+        control_width_resize = latents_shape[3] * 8
+        if control_input is None:
+            control_list = None
+        elif isinstance(control_input, list) and len(control_input) == 0:
+            control_list = None
+        elif isinstance(control_input, ControlField):
+            control_list = [control_input]
+        elif isinstance(control_input, list) and len(control_input) > 0 and isinstance(control_input[0], ControlField):
+            control_list = control_input
+        else:
+            control_list = None
+        if (control_list is None):
+            control_data = None
+            # from above handling, any control that is not None should now be of type list[ControlField]
+        else:
+            # FIXME: add checks to skip entry if model or image is None
+            #        and if weight is None, populate with default 1.0?
+            control_data = []
+            control_models = []
+            for control_info in control_list:
+                # handle control models
+                if ("," in control_info.control_model):
+                    control_model_split = control_info.control_model.split(",")
+                    control_name = control_model_split[0]
+                    control_subfolder = control_model_split[1]
+                    print("Using HF model subfolders")
+                    print("    control_name: ", control_name)
+                    print("    control_subfolder: ", control_subfolder)
+                    control_model = ControlNetModel.from_pretrained(
+                        control_name, subfolder=control_subfolder,
+                        torch_dtype=model.unet.dtype).to(
+                        model.device)
+                else:
+                    control_model = ControlNetModel.from_pretrained(
+                        control_info.control_model, torch_dtype=model.unet.dtype).to(model.device)
+                control_models.append(control_model)
+                control_image_field = control_info.image
+                input_image = context.services.images.get_pil_image(
+                    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?
+                #        and do real check for classifier_free_guidance?
+                # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
+                control_image = model.prepare_control_image(
+                    image=input_image,
+                    do_classifier_free_guidance=do_classifier_free_guidance,
+                    width=control_width_resize,
+                    height=control_height_resize,
+                    # batch_size=batch_size * num_images_per_prompt,
+                    # num_images_per_prompt=num_images_per_prompt,
+                    device=control_model.device,
+                    dtype=control_model.dtype,
+                    control_mode=control_info.control_mode,
+                )
+                control_item = ControlNetData(
+                    model=control_model, image_tensor=control_image,
+                    weight=control_info.control_weight,
+                    begin_step_percent=control_info.begin_step_percent,
+                    end_step_percent=control_info.end_step_percent,
+                    control_mode=control_info.control_mode,)
+                control_data.append(control_item)
+                # MultiControlNetModel has been refactored out, just need list[ControlNetData]
+        return control_data
+
+    @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
-        latent = context.services.latents.get(self.latents.latents_name)
 
         # 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)
+        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]
 
         def step_callback(state: PipelineIntermediateState):
             self.dispatch_progress(context, source_node_id, state)
 
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
+        def _lora_loader():
+            for lora in self.unet.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
 
-        # TODO: Verify the noise is the right size
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict())
+        with ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
+                unet_info as unet:
 
-        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-            latent, device=model.device, dtype=latent.dtype
-        )
+            scheduler = get_scheduler(
+                context=context,
+                scheduler_info=self.unet.scheduler,
+                scheduler_name=self.scheduler,
+            )
 
-        timesteps, _ = model.get_img2img_timesteps(
-            self.steps,
-            self.strength,
-            device=model.device,
-        )
+            pipeline = self.create_pipeline(unet, scheduler)
+            conditioning_data = self.get_conditioning_data(context, scheduler)
 
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=initial_latents,
-            timesteps=timesteps,
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
+            control_data = self.prep_control_data(
+                model=pipeline, context=context, control_input=self.control,
+                latents_shape=noise.shape,
+                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                do_classifier_free_guidance=True,
+            )
+
+            # TODO: Verify the noise is the right size
+            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
+                noise=noise,
+                num_inference_steps=self.steps,
+                conditioning_data=conditioning_data,
+                control_data=control_data,  # list[ControlNetData]
+                callback=step_callback,
+            )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         torch.cuda.empty_cache()
 
         name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
+        context.services.latents.save(name, result_latents)
+        return build_latents_output(latents_name=name, latents=result_latents)
+
+
+class LatentsToLatentsInvocation(TextToLatentsInvocation):
+    """Generates latents using latents as base image."""
+
+    type: Literal["l2l"] = "l2l"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(
+        description="The latents to use as a base image")
+    strength: float = Field(
+        default=0.7, ge=0, le=1,
+        description="The strength of the latents to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                    "model": "model",
+                    "control": "control",
+                    "cfg_scale": "number",
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        noise = context.services.latents.get(self.noise.latents_name)
+        latent = context.services.latents.get(self.latents.latents_name)
+
+        # 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]
+
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, source_node_id, state)
+
+        def _lora_loader():
+            for lora in self.unet.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
+
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict())
+        with ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
+                unet_info as unet:
+
+            scheduler = get_scheduler(
+                context=context,
+                scheduler_info=self.unet.scheduler,
+                scheduler_name=self.scheduler,
+            )
+
+            pipeline = self.create_pipeline(unet, scheduler)
+            conditioning_data = self.get_conditioning_data(context, scheduler)
+
+            control_data = self.prep_control_data(
+                model=pipeline, context=context, control_input=self.control,
+                latents_shape=noise.shape,
+                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                do_classifier_free_guidance=True,
+            )
+
+            # TODO: Verify the noise is the right size
+            initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+                latent, device=unet.device, dtype=latent.dtype)
+
+            timesteps, _ = pipeline.get_img2img_timesteps(
+                self.steps,
+                self.strength,
+                device=unet.device,
+            )
+
+            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                latents=initial_latents,
+                timesteps=timesteps,
+                noise=noise,
+                num_inference_steps=self.steps,
+                conditioning_data=conditioning_data,
+                control_data=control_data,  # list[ControlNetData]
+                callback=step_callback
+            )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.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)
 
 
 # Latent to image
@@ -328,17 +443,18 @@ class LatentsToImageInvocation(BaseInvocation):
     type: Literal["l2i"] = "l2i"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
-    model: str = Field(default="", description="The model to use")
+    latents: Optional[LatentsField] = Field(
+        description="The latents to generate an image from")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    tiled: bool = Field(
+        default=False,
+        description="Decode latents by overlaping tiles(less memory consumption)")
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "tags": ["latents", "image"],
-                "type_hints": {
-                  "model": "model"
-                }
             },
         }
 
@@ -346,26 +462,173 @@ class LatentsToImageInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
-        # TODO: this only really needs the vae
-        model_info = choose_model(context.services.model_manager, self.model)
-        model: StableDiffusionGeneratorPipeline = model_info['model']
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+        )
 
-        with torch.inference_mode():
-            np_image = model.decode_latents(latents)
-            image = model.numpy_to_pil(np_image)[0]
+        with vae_info as vae:
+            if self.tiled or context.services.configuration.tiled_decode:
+                vae.enable_tiling()
+            else:
+                vae.disable_tiling()
 
-            image_type = ImageType.RESULT
-            image_name = context.services.images.create_name(
-                context.graph_execution_state_id, self.id
-            )
+            # clear memory as vae decode can request a lot
+            torch.cuda.empty_cache()
 
-            metadata = context.services.metadata.build_metadata(
-                session_id=context.graph_execution_state_id, node=self
-            )
+            with torch.inference_mode():
+                # copied from diffusers pipeline
+                latents = latents / vae.config.scaling_factor
+                image = vae.decode(latents, return_dict=False)[0]
+                image = (image / 2 + 0.5).clamp(0, 1)  # denormalize
+                # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
+                np_image = image.cpu().permute(0, 2, 3, 1).float().numpy()
 
-            context.services.images.save(image_type, image_name, image, metadata)
-            return build_image_output(
-                image_type=image_type,
-                image_name=image_name,
-                image=image
-            )
+                image = VaeImageProcessor.numpy_to_pil(np_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
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear",
+                                     "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
+
+
+class ResizeLatentsInvocation(BaseInvocation):
+    """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
+
+    type: Literal["lresize"] = "lresize"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(
+        description="The latents to resize")
+    width:                         int = Field(
+        ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(
+        ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode:   LATENTS_INTERPOLATION_MODE = Field(
+        default="bilinear", description="The interpolation mode")
+    antialias: bool = Field(
+        default=False,
+        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        resized_latents = torch.nn.functional.interpolate(
+            latents, size=(self.height // 8, self.width // 8),
+            mode=self.mode, antialias=self.antialias
+            if self.mode in ["bilinear", "bicubic"] else False,)
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.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)
+
+
+class ScaleLatentsInvocation(BaseInvocation):
+    """Scales latents by a given factor."""
+
+    type: Literal["lscale"] = "lscale"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(
+        description="The latents to scale")
+    scale_factor:               float = Field(
+        gt=0, description="The factor by which to scale the latents")
+    mode:  LATENTS_INTERPOLATION_MODE = Field(
+        default="bilinear", description="The interpolation mode")
+    antialias: bool = Field(
+        default=False,
+        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # resizing
+        resized_latents = torch.nn.functional.interpolate(
+            latents, scale_factor=self.scale_factor, mode=self.mode,
+            antialias=self.antialias
+            if self.mode in ["bilinear", "bicubic"] else False,)
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.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)
+
+
+class ImageToLatentsInvocation(BaseInvocation):
+    """Encodes an image into latents."""
+
+    type: Literal["i2l"] = "i2l"
+
+    # Inputs
+    image: Optional[ImageField] = Field(description="The image to encode")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    tiled: bool = Field(
+        default=False,
+        description="Encode latents by overlaping tiles(less memory consumption)")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        # image = context.services.images.get(
+        #     self.image.image_type, self.image.image_name
+        # )
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        #vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+        )
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
+        with vae_info as vae:
+            if self.tiled:
+                vae.enable_tiling()
+            else:
+                vae.disable_tiling()
+
+            # non_noised_latents_from_image
+            image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
+            with torch.inference_mode():
+                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 = 0.18215 * latents
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        # context.services.latents.set(name, latents)
+        context.services.latents.save(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)

invokeai/app/invocations/math.py

@@ -3,8 +3,14 @@
 from typing import Literal
 
 from pydantic import BaseModel, Field
+import numpy as np
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
 
 
 class MathInvocationConfig(BaseModel):
@@ -21,19 +27,30 @@ class MathInvocationConfig(BaseModel):
 
 class IntOutput(BaseInvocationOutput):
     """An integer output"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["int_output"] = "int_output"
     a: int = Field(default=None, description="The output integer")
-    #fmt: on
+    # fmt: on
+
+
+class FloatOutput(BaseInvocationOutput):
+    """A float output"""
+
+    # fmt: off
+    type: Literal["float_output"] = "float_output"
+    param: float = Field(default=None, description="The output float")
+    # fmt: on
 
 
 class AddInvocation(BaseInvocation, MathInvocationConfig):
     """Adds two numbers"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["add"] = "add"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a + self.b)
@@ -41,11 +58,12 @@ class AddInvocation(BaseInvocation, MathInvocationConfig):
 
 class SubtractInvocation(BaseInvocation, MathInvocationConfig):
     """Subtracts two numbers"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["sub"] = "sub"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a - self.b)
@@ -53,11 +71,12 @@ class SubtractInvocation(BaseInvocation, MathInvocationConfig):
 
 class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
     """Multiplies two numbers"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["mul"] = "mul"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a * self.b)
@@ -65,11 +84,26 @@ class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
 
 class DivideInvocation(BaseInvocation, MathInvocationConfig):
     """Divides two numbers"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["div"] = "div"
     a: int = Field(default=0, description="The first number")
     b: int = Field(default=0, description="The second number")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=int(self.a / self.b))
+
+
+class RandomIntInvocation(BaseInvocation):
+    """Outputs a single random integer."""
+
+    # fmt: off
+    type: Literal["rand_int"] = "rand_int"
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/model.py

@@ -0,0 +1,310 @@
+import copy
+from typing import List, Literal, Optional, Union
+
+from pydantic import BaseModel, Field
+
+from ...backend.model_management import BaseModelType, ModelType, SubModelType
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+
+
+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 LoraInfo(ModelInfo):
+    weight: float = Field(description="Lora's weight which to use when apply to 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")
+
+
+class ClipField(BaseModel):
+    tokenizer: ModelInfo = Field(description="Info to load tokenizer submodel")
+    text_encoder: ModelInfo = 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")
+
+
+class VaeField(BaseModel):
+    # TODO: better naming?
+    vae: ModelInfo = Field(description="Info to load vae submodel")
+
+
+class ModelLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["model_loader_output"] = "model_loader_output"
+
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
+
+
+class MainModelField(BaseModel):
+    """Main model field"""
+
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class LoRAModelField(BaseModel):
+    """LoRA model field"""
+
+    model_name: str = Field(description="Name of the LoRA model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class MainModelLoaderInvocation(BaseInvocation):
+    """Loads a main model, outputting its submodels."""
+
+    type: Literal["main_model_loader"] = "main_model_loader"
+
+    model: MainModelField = Field(description="The model to load")
+    # TODO: precision?
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Model Loader",
+                "tags": ["model", "loader"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    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.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 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,
+                ),
+            ),
+        )
+
+
+class LoraLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["lora_loader_output"] = "lora_loader_output"
+
+    unet: Optional[UNetField] = Field(default=None, description="UNet submodel")
+    clip: Optional[ClipField] = Field(default=None, description="Tokenizer and text_encoder submodels")
+    # fmt: on
+
+
+class LoraLoaderInvocation(BaseInvocation):
+    """Apply selected lora to unet and text_encoder."""
+
+    type: Literal["lora_loader"] = "lora_loader"
+
+    lora: Union[LoRAModelField, None] = Field(
+        default=None, description="Lora model name"
+    )
+    weight: float = Field(default=0.75, description="With what weight to apply lora")
+
+    unet: Optional[UNetField] = Field(description="UNet model for applying lora")
+    clip: Optional[ClipField] = Field(description="Clip model for applying lora")
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Lora Loader",
+                "tags": ["lora", "loader"],
+                "type_hints": {"lora": "lora_model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
+        if self.lora is None:
+            raise Exception("No LoRA provided")
+
+        base_model = self.lora.base_model
+        lora_name = self.lora.model_name
+
+        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.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.model_name == lora_name for lora in self.clip.loras
+        ):
+            raise Exception(f'Lora "{lora_name}" already applied to clip')
+
+        output = LoraLoaderOutput()
+
+        if self.unet is not None:
+            output.unet = copy.deepcopy(self.unet)
+            output.unet.loras.append(
+                LoraInfo(
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
+                    weight=self.weight,
+                )
+            )
+
+        if self.clip is not None:
+            output.clip = copy.deepcopy(self.clip)
+            output.clip.loras.append(
+                LoraInfo(
+                    base_model=base_model,
+                    model_name=lora_name,
+                    model_type=ModelType.Lora,
+                    submodel=None,
+                    weight=self.weight,
+                )
+            )
+
+        return output
+
+
+class VAEModelField(BaseModel):
+    """Vae model field"""
+
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+
+
+class VaeLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["vae_loader_output"] = "vae_loader_output"
+
+    vae: VaeField = Field(default=None, description="Vae model")
+    # fmt: on
+
+
+class VaeLoaderInvocation(BaseInvocation):
+    """Loads a VAE model, outputting a VaeLoaderOutput"""
+
+    type: Literal["vae_loader"] = "vae_loader"
+
+    vae_model: VAEModelField = Field(description="The VAE to load")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "VAE Loader",
+                "tags": ["vae", "loader"],
+                "type_hints": {"vae_model": "vae_model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> VaeLoaderOutput:
+        base_model = self.vae_model.base_model
+        model_name = self.vae_model.model_name
+        model_type = ModelType.Vae
+
+        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 VaeLoaderOutput(
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                )
+            )
+        )

invokeai/app/invocations/noise.py

@@ -0,0 +1,134 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
+
+import math
+from typing import Literal
+
+from pydantic import Field, validator
+import torch
+from invokeai.app.invocations.latent import LatentsField
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationConfig,
+    InvocationContext,
+)
+
+"""
+Utilities
+"""
+
+
+def get_noise(
+    width: int,
+    height: int,
+    device: torch.device,
+    seed: int = 0,
+    latent_channels: int = 4,
+    downsampling_factor: int = 8,
+    use_cpu: bool = True,
+    perlin: float = 0.0,
+):
+    """Generate noise for a given image size."""
+    noise_device_type = "cpu" if use_cpu else device.type
+
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    generator = torch.Generator(device=noise_device_type).manual_seed(seed)
+
+    noise_tensor = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width // downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=noise_device_type,
+        generator=generator,
+    ).to(device)
+
+    return noise_tensor
+
+
+"""
+Nodes
+"""
+
+
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+
+    # fmt: off
+    type:  Literal["noise_output"] = "noise_output"
+
+    # Inputs
+    noise: LatentsField            = Field(default=None, description="The output noise")
+    width:                     int = Field(description="The width of the noise in pixels")
+    height:                    int = Field(description="The height of the noise in pixels")
+    # fmt: on
+
+
+def build_noise_output(latents_name: str, latents: torch.Tensor):
+    return NoiseOutput(
+        noise=LatentsField(latents_name=latents_name),
+        width=latents.size()[3] * 8,
+        height=latents.size()[2] * 8,
+    )
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use",
+        default_factory=get_random_seed,
+    )
+    width: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The width of the resulting noise",
+    )
+    height: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The height of the resulting noise",
+    )
+    use_cpu: bool = Field(
+        default=True,
+        description="Use CPU for noise generation (for reproducible results across platforms)",
+    )
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    @validator("seed", pre=True)
+    def modulo_seed(cls, v):
+        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
+        return v % SEED_MAX
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        noise = get_noise(
+            width=self.width,
+            height=self.height,
+            device=choose_torch_device(),
+            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)

invokeai/app/invocations/param_easing.py

@@ -0,0 +1,236 @@
+import io
+from typing import Literal, Optional, Any
+
+# from PIL.Image import Image
+import PIL.Image
+from matplotlib.ticker import MaxNLocator
+from matplotlib.figure import Figure
+
+from pydantic import BaseModel, Field
+import numpy as np
+import matplotlib.pyplot as plt
+
+from easing_functions import (
+    LinearInOut,
+    QuadEaseInOut, QuadEaseIn, QuadEaseOut,
+    CubicEaseInOut, CubicEaseIn, CubicEaseOut,
+    QuarticEaseInOut, QuarticEaseIn, QuarticEaseOut,
+    QuinticEaseInOut, QuinticEaseIn, QuinticEaseOut,
+    SineEaseInOut, SineEaseIn, SineEaseOut,
+    CircularEaseIn, CircularEaseInOut, CircularEaseOut,
+    ExponentialEaseInOut, ExponentialEaseIn, ExponentialEaseOut,
+    ElasticEaseIn, ElasticEaseInOut, ElasticEaseOut,
+    BackEaseIn, BackEaseInOut, BackEaseOut,
+    BounceEaseIn, BounceEaseInOut, BounceEaseOut)
+
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+from ...backend.util.logging import InvokeAILogger
+from .collections import FloatCollectionOutput
+
+
+class FloatLinearRangeInvocation(BaseInvocation):
+    """Creates a range"""
+
+    type: Literal["float_range"] = "float_range"
+
+    # Inputs
+    start: float = Field(default=5, description="The first value of the range")
+    stop: float = Field(default=10, description="The last value of the range")
+    steps: int = Field(default=30, description="number of values to interpolate over (including start and stop)")
+
+    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
+        param_list = list(np.linspace(self.start, self.stop, self.steps))
+        return FloatCollectionOutput(
+            collection=param_list
+        )
+
+
+EASING_FUNCTIONS_MAP = {
+    "Linear": LinearInOut,
+    "QuadIn": QuadEaseIn,
+    "QuadOut": QuadEaseOut,
+    "QuadInOut": QuadEaseInOut,
+    "CubicIn": CubicEaseIn,
+    "CubicOut": CubicEaseOut,
+    "CubicInOut": CubicEaseInOut,
+    "QuarticIn": QuarticEaseIn,
+    "QuarticOut": QuarticEaseOut,
+    "QuarticInOut": QuarticEaseInOut,
+    "QuinticIn": QuinticEaseIn,
+    "QuinticOut": QuinticEaseOut,
+    "QuinticInOut": QuinticEaseInOut,
+    "SineIn": SineEaseIn,
+    "SineOut": SineEaseOut,
+    "SineInOut": SineEaseInOut,
+    "CircularIn": CircularEaseIn,
+    "CircularOut": CircularEaseOut,
+    "CircularInOut": CircularEaseInOut,
+    "ExponentialIn": ExponentialEaseIn,
+    "ExponentialOut": ExponentialEaseOut,
+    "ExponentialInOut": ExponentialEaseInOut,
+    "ElasticIn": ElasticEaseIn,
+    "ElasticOut": ElasticEaseOut,
+    "ElasticInOut": ElasticEaseInOut,
+    "BackIn": BackEaseIn,
+    "BackOut": BackEaseOut,
+    "BackInOut": BackEaseInOut,
+    "BounceIn": BounceEaseIn,
+    "BounceOut": BounceEaseOut,
+    "BounceInOut": BounceEaseInOut,
+}
+
+EASING_FUNCTION_KEYS: Any = Literal[
+    tuple(list(EASING_FUNCTIONS_MAP.keys()))
+]
+
+
+# actually I think for now could just use CollectionOutput (which is list[Any]
+class StepParamEasingInvocation(BaseInvocation):
+    """Experimental per-step parameter easing for denoising steps"""
+
+    type: Literal["step_param_easing"] = "step_param_easing"
+
+    # Inputs
+    # fmt: off
+    easing: EASING_FUNCTION_KEYS = Field(default="Linear", description="The easing function to use")
+    num_steps: int = Field(default=20, description="number of denoising steps")
+    start_value: float = Field(default=0.0, description="easing starting value")
+    end_value: float = Field(default=1.0, description="easing ending value")
+    start_step_percent: float = Field(default=0.0, description="fraction of steps at which to start easing")
+    end_step_percent: float = Field(default=1.0, description="fraction of steps after which to end easing")
+    # if None, then start_value is used prior to easing start
+    pre_start_value: Optional[float] = Field(default=None, description="value before easing start")
+    # if None, then end value is used prior to easing end
+    post_end_value: Optional[float] = Field(default=None, description="value after easing end")
+    mirror: bool = Field(default=False, description="include mirror of easing function")
+    # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+    # alt_mirror: bool = Field(default=False, description="alternative mirroring by dual easing")
+    show_easing_plot: bool = Field(default=False, description="show easing plot")
+    # fmt: on
+
+
+    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
+        log_diagnostics = False
+        # convert from start_step_percent to nearest step <= (steps * start_step_percent)
+        # start_step = int(np.floor(self.num_steps * self.start_step_percent))
+        start_step = int(np.round(self.num_steps * self.start_step_percent))
+        # convert from end_step_percent to nearest step >= (steps * end_step_percent)
+        # end_step = int(np.ceil((self.num_steps - 1) * self.end_step_percent))
+        end_step = int(np.round((self.num_steps - 1) * self.end_step_percent))
+
+        # end_step = int(np.ceil(self.num_steps * self.end_step_percent))
+        num_easing_steps = end_step - start_step + 1
+
+        # num_presteps = max(start_step - 1, 0)
+        num_presteps = start_step
+        num_poststeps = self.num_steps - (num_presteps + num_easing_steps)
+        prelist = list(num_presteps * [self.pre_start_value])
+        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))
+
+        easing_class = EASING_FUNCTIONS_MAP[self.easing]
+        if log_diagnostics:
+            context.services.logger.debug("easing class: " + str(easing_class))
+        easing_list = list()
+        if self.mirror:  # "expected" mirroring
+            # if number of steps is even, squeeze duration down to (number_of_steps)/2
+            # and create reverse copy of list to append
+            # if number of steps is odd, squeeze duration down to ceil(number_of_steps/2)
+            # and create reverse copy of list[1:end-1]
+            # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
+
+            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))
+            even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
+            easing_function = easing_class(start=self.start_value,
+                                           end=self.end_value,
+                                           duration=base_easing_duration - 1)
+            base_easing_vals = list()
+            for step_index in range(base_easing_duration):
+                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))
+            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))
+            easing_list = base_easing_vals + mirror_easing_vals
+
+        # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+        # elif self.alt_mirror:  # function mirroring (unintuitive behavior (at least to me))
+        #     # half_ease_duration = round(num_easing_steps - 1 / 2)
+        #     half_ease_duration = round((num_easing_steps - 1) / 2)
+        #     easing_function = easing_class(start=self.start_value,
+        #                                    end=self.end_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #
+        #     mirror_function = easing_class(start=self.end_value,
+        #                                    end=self.start_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #     for step_index in range(num_easing_steps):
+        #         if step_index <= half_ease_duration:
+        #             step_val = easing_function.ease(step_index)
+        #         else:
+        #             step_val = mirror_function.ease(step_index - half_ease_duration)
+        #         easing_list.append(step_val)
+        #         if log_diagnostics: logger.debug(step_index, step_val)
+        #
+
+        else:  # no mirroring (default)
+            easing_function = easing_class(start=self.start_value,
+                                           end=self.end_value,
+                                           duration=num_easing_steps - 1)
+            for step_index in range(num_easing_steps):
+                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))
+
+        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)))
+
+        param_list = prelist + easing_list + postlist
+
+        if self.show_easing_plot:
+            plt.figure()
+            plt.xlabel("Step")
+            plt.ylabel("Param Value")
+            plt.title("Per-Step Values Based On Easing: " + self.easing)
+            plt.bar(range(len(param_list)), param_list)
+            # plt.plot(param_list)
+            ax = plt.gca()
+            ax.xaxis.set_major_locator(MaxNLocator(integer=True))
+            buf = io.BytesIO()
+            plt.savefig(buf, format='png')
+            buf.seek(0)
+            im = PIL.Image.open(buf)
+            im.show()
+            buf.close()
+
+        # output array of size steps, each entry list[i] is param value for step i
+        return FloatCollectionOutput(
+            collection=param_list
+        )

invokeai/app/invocations/params.py

@@ -3,7 +3,7 @@
 from typing import Literal
 from pydantic import Field
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
-from .math import IntOutput
+from .math import IntOutput, FloatOutput
 
 # Pass-through parameter nodes - used by subgraphs
 
@@ -16,3 +16,13 @@ class ParamIntInvocation(BaseInvocation):
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a)
+
+class ParamFloatInvocation(BaseInvocation):
+    """A float parameter"""
+    #fmt: off
+    type: Literal["param_float"] = "param_float"
+    param: float = Field(default=0.0, description="The float value")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> FloatOutput:
+        return FloatOutput(param=self.param)

invokeai/app/invocations/prompt.py

@@ -2,8 +2,8 @@ from typing import Literal
 
 from pydantic.fields import Field
 
-from .baseinvocation import BaseInvocationOutput
-
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator
 
 class PromptOutput(BaseInvocationOutput):
     """Base class for invocations that output a prompt"""
@@ -20,3 +20,38 @@ class PromptOutput(BaseInvocationOutput):
                 'prompt',
             ]
         }
+
+
+class PromptCollectionOutput(BaseInvocationOutput):
+    """Base class for invocations that output a collection of prompts"""
+
+    # fmt: off
+    type: Literal["prompt_collection_output"] = "prompt_collection_output"
+
+    prompt_collection: list[str] = Field(description="The output prompt collection")
+    count: int = Field(description="The size of the prompt collection")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "prompt_collection", "count"]}
+
+
+class DynamicPromptInvocation(BaseInvocation):
+    """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
+
+    type: Literal["dynamic_prompt"] = "dynamic_prompt"
+    prompt: str = Field(description="The prompt to parse with dynamicprompts")
+    max_prompts: int = Field(default=1, description="The number of prompts to generate")
+    combinatorial: bool = Field(
+        default=False, description="Whether to use the combinatorial generator"
+    )
+
+    def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
+        if self.combinatorial:
+            generator = CombinatorialPromptGenerator()
+            prompts = generator.generate(self.prompt, max_prompts=self.max_prompts)
+        else:
+            generator = RandomPromptGenerator()
+            prompts = generator.generate(self.prompt, num_images=self.max_prompts)
+
+        return PromptCollectionOutput(prompt_collection=prompts, count=len(prompts))

invokeai/app/invocations/reconstruct.py

@@ -1,22 +1,24 @@
-from typing import Literal, Union
+from typing import Literal, Optional
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
 
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from .image import ImageOutput
+
 
 class RestoreFaceInvocation(BaseInvocation):
     """Restores faces in an image."""
-    #fmt: off
+
+    # fmt: off
     type:  Literal["restore_face"] = "restore_face"
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image")
+    image: Optional[ImageField] = Field(description="The input image")
     strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
-    #fmt: on
-    
+    # fmt: on
+
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
@@ -26,9 +28,7 @@ class RestoreFaceInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=None,
@@ -39,18 +39,17 @@ class RestoreFaceInvocation(BaseInvocation):
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
-
-        context.services.images.save(image_type, image_name, results[0][0], metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=results[0][0]
-        )

invokeai/app/invocations/upscale.py

@@ -1,25 +1,25 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Literal, Union
+from typing import Literal, Optional
 
 from pydantic import Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
-from .image import ImageOutput, build_image_output
+from .image import ImageOutput
 
 
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
-    #fmt: off
+
+    # fmt: off
     type: Literal["upscale"] = "upscale"
 
     # Inputs
-    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    image: Optional[ImageField] = Field(description="The input image", default=None)
     strength: float = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2, 4] = Field(default=2, description="The upscale level")
-    #fmt: on
-
+    # fmt: on
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -30,9 +30,7 @@ class UpscaleInvocation(BaseInvocation):
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get(
-            self.image.image_type, self.image.image_name
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
         results = context.services.restoration.upscale_and_reconstruct(
             image_list=[[image, 0]],
             upscale=(self.level, self.strength),
@@ -43,18 +41,17 @@ class UpscaleInvocation(BaseInvocation):
 
         # Results are image and seed, unwrap for now
         # TODO: can this return multiple results?
-        image_type = ImageType.RESULT
-        image_name = context.services.images.create_name(
-            context.graph_execution_state_id, self.id
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            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 = context.services.metadata.build_metadata(
-            session_id=context.graph_execution_state_id, node=self
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
         )
-
-        context.services.images.save(image_type, image_name, results[0][0], metadata)
-        return build_image_output(
-            image_type=image_type,
-            image_name=image_name,
-            image=results[0][0]
-        )

invokeai/app/invocations/util/choose_model.py

@@ -1,14 +0,0 @@
-from invokeai.backend.model_management.model_manager import ModelManager
-
-
-def choose_model(model_manager: ModelManager, model_name: str):
-    """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
-    if model_manager.valid_model(model_name):
-        model = model_manager.get_model(model_name)
-    else:
-        model = model_manager.get_model()
-        print(
-            f"* Warning: '{model_name}' is not a valid model name. Using default model \'{model['model_name']}\' instead."
-        )
-
-    return model

invokeai/app/models/image.py

@@ -1,29 +1,129 @@
 from enum import Enum
-from typing import Optional
+from typing import Optional, Tuple
+
 from pydantic import BaseModel, Field
 
-
-class ImageType(str, Enum):
-    RESULT = "results"
-    INTERMEDIATE = "intermediates"
-    UPLOAD = "uploads"
+from invokeai.app.util.metaenum import MetaEnum
 
 
-def is_image_type(obj):
-    try:
-        ImageType(obj)
-    except ValueError:
-        return False
-    return True
+class ResourceOrigin(str, Enum, metaclass=MetaEnum):
+    """The origin of a resource (eg image).
+
+    - INTERNAL: The resource was created by the application.
+    - EXTERNAL: The resource was not created by the application.
+    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
+    """
+
+    INTERNAL = "internal"
+    """The resource was created by the application."""
+    EXTERNAL = "external"
+    """The resource was not created by the application.
+    This may be a user-initiated upload, or an internal application upload (eg Canvas init image).
+    """
+
+
+class InvalidOriginException(ValueError):
+    """Raised when a provided value is not a valid ResourceOrigin.
+
+    Subclasses `ValueError`.
+    """
+
+    def __init__(self, message="Invalid resource origin."):
+        super().__init__(message)
+
+
+class ImageCategory(str, Enum, metaclass=MetaEnum):
+    """The category of an image.
+
+    - GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose.
+    - MASK: The image is a mask image.
+    - CONTROL: The image is a ControlNet control image.
+    - USER: The image is a user-provide image.
+    - OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes.
+    """
+
+    GENERAL = "general"
+    """GENERAL: The image is an output, init image, or otherwise an image without a specialized purpose."""
+    MASK = "mask"
+    """MASK: The image is a mask image."""
+    CONTROL = "control"
+    """CONTROL: The image is a ControlNet control image."""
+    USER = "user"
+    """USER: The image is a user-provide image."""
+    OTHER = "other"
+    """OTHER: The image is some other type of image with a specialized purpose. To be used by external nodes."""
+
+
+class InvalidImageCategoryException(ValueError):
+    """Raised when a provided value is not a valid ImageCategory.
+
+    Subclasses `ValueError`.
+    """
+
+    def __init__(self, message="Invalid image category."):
+        super().__init__(message)
 
 
 class ImageField(BaseModel):
     """An image field used for passing image objects between invocations"""
 
-    image_type: ImageType = Field(
-        default=ImageType.RESULT, description="The type of the image"
-    )
     image_name: Optional[str] = Field(default=None, description="The name of the image")
 
     class Config:
-        schema_extra = {"required": ["image_type", "image_name"]}
+        schema_extra = {"required": ["image_name"]}
+
+
+class ColorField(BaseModel):
+    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 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 DeleteManyImagesResult(BaseModel):
+    """The result of a delete many image operation."""
+
+    deleted_images: list[str] = Field(
+        description="The names of the images that were successfully deleted"
+    )
+
+
+class AddManyImagesToBoardResult(BaseModel):
+    """The result of an add many images to board operation."""
+
+    board_id: str = Field(description="The id of the board the images were added to")
+    added_images: list[str] = Field(
+        description="The names of the images that were successfully added"
+    )
+    total: int = Field(description="The total number of images on the board")
+
+
+class RemoveManyImagesFromBoardResult(BaseModel):
+    """The result of a remove many images from their boards operation."""
+
+    removed_images: list[str] = Field(
+        description="The names of the images that were successfully removed from their boards"
+    )
+
+
+class GetAllBoardImagesForBoardResult(BaseModel):
+    """The result of a get all image names for board operation."""
+
+    board_id: str = Field(
+        description="The id of the board with which the images are associated"
+    )
+    image_names: list[str] = Field(
+        description="The names of the images that are associated with the board"
+    )
+

invokeai/app/models/metadata.py

@@ -0,0 +1,93 @@
+from typing import Optional, Union, List
+from pydantic import BaseModel, Extra, Field, StrictFloat, StrictInt, StrictStr
+
+
+class ImageMetadata(BaseModel):
+    """
+    Core generation metadata for an image/tensor generated in InvokeAI.
+
+    Also includes any metadata from the image's PNG tEXt chunks.
+
+    Generated by traversing the execution graph, collecting the parameters of the nearest ancestors
+    of a given node.
+
+    Full metadata may be accessed by querying for the session in the `graph_executions` table.
+    """
+
+    class Config:
+        extra = Extra.allow
+        """
+        This lets the ImageMetadata class accept arbitrary additional fields. The CoreMetadataService
+        won't add any fields that are not already defined, but other a different metadata service
+        implementation might.
+        """
+
+    type: Optional[StrictStr] = Field(
+        default=None,
+        description="The type of the ancestor node of the image output node.",
+    )
+    """The type of the ancestor node of the image output node."""
+    positive_conditioning: Optional[StrictStr] = Field(
+        default=None, description="The positive conditioning."
+    )
+    """The positive conditioning"""
+    negative_conditioning: Optional[StrictStr] = Field(
+        default=None, description="The negative conditioning."
+    )
+    """The negative conditioning"""
+    width: Optional[StrictInt] = Field(
+        default=None, description="Width of the image/latents in pixels."
+    )
+    """Width of the image/latents in pixels"""
+    height: Optional[StrictInt] = Field(
+        default=None, description="Height of the image/latents in pixels."
+    )
+    """Height of the image/latents in pixels"""
+    seed: Optional[StrictInt] = Field(
+        default=None, description="The seed used for noise generation."
+    )
+    """The seed used for noise generation"""
+    # cfg_scale: Optional[StrictFloat] = Field(
+    # cfg_scale: Union[float, list[float]] = Field(
+    cfg_scale: Union[StrictFloat, List[StrictFloat]] = Field(
+        default=None, description="The classifier-free guidance scale."
+    )
+    """The classifier-free guidance scale"""
+    steps: Optional[StrictInt] = Field(
+        default=None, description="The number of steps used for inference."
+    )
+    """The number of steps used for inference"""
+    scheduler: Optional[StrictStr] = Field(
+        default=None, description="The scheduler used for inference."
+    )
+    """The scheduler used for inference"""
+    model: Optional[StrictStr] = Field(
+        default=None, description="The model used for inference."
+    )
+    """The model used for inference"""
+    strength: Optional[StrictFloat] = Field(
+        default=None,
+        description="The strength used for image-to-image/latents-to-latents.",
+    )
+    """The strength used for image-to-image/latents-to-latents."""
+    latents: Optional[StrictStr] = Field(
+        default=None, description="The ID of the initial latents."
+    )
+    """The ID of the initial latents"""
+    vae: Optional[StrictStr] = Field(
+        default=None, description="The VAE used for decoding."
+    )
+    """The VAE used for decoding"""
+    unet: Optional[StrictStr] = Field(
+        default=None, description="The UNet used dor inference."
+    )
+    """The UNet used dor inference"""
+    clip: Optional[StrictStr] = Field(
+        default=None, description="The CLIP Encoder used for conditioning."
+    )
+    """The CLIP Encoder used for conditioning"""
+    extra: Optional[StrictStr] = Field(
+        default=None,
+        description="Uploaded image metadata, extracted from the PNG tEXt chunk.",
+    )
+    """Uploaded image metadata, extracted from the PNG tEXt chunk."""

invokeai/app/services/board_image_record_storage.py

@@ -0,0 +1,240 @@
+import sqlite3
+import threading
+from abc import ABC, abstractmethod
+from typing import Optional, cast
+
+from invokeai.app.models.image import GetAllBoardImagesForBoardResult
+from invokeai.app.services.image_record_storage import OffsetPaginatedResults
+from invokeai.app.services.models.image_record import (
+    ImageRecord, deserialize_image_record)
+
+
+class BoardImageRecordStorageBase(ABC):
+    """Abstract base class for the one-to-many board-image relationship record storage."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        """Removes an image from a board."""
+        pass
+
+    @abstractmethod
+    def get_all_board_images_for_board(
+        self,
+        board_id: str,
+    ) -> GetAllBoardImagesForBoardResult:
+        """Gets all image names for a board."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass
+
+    @abstractmethod
+    def get_image_count_for_board(
+        self,
+        board_id: str,
+    ) -> int:
+        """Gets the number of images for a board."""
+        pass
+
+
+class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
+    _filename: str
+    _conn: sqlite3.Connection
+    _cursor: sqlite3.Cursor
+    _lock: threading.Lock
+
+    def __init__(self, filename: str) -> None:
+        super().__init__()
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
+        # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
+        self._conn.row_factory = sqlite3.Row
+        self._cursor = self._conn.cursor()
+        self._lock = threading.Lock()
+
+        try:
+            self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
+            self._create_tables()
+            self._conn.commit()
+        finally:
+            self._lock.release()
+
+    def _create_tables(self) -> None:
+        """Creates the `board_images` junction table."""
+
+        # Create the `board_images` junction table.
+        self._cursor.execute(
+            """--sql
+            CREATE TABLE IF NOT EXISTS board_images (
+                board_id TEXT NOT NULL,
+                image_name TEXT NOT NULL,
+                created_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- updated via trigger
+                updated_at DATETIME NOT NULL DEFAULT(STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')),
+                -- Soft delete, currently unused
+                deleted_at DATETIME,
+                -- enforce one-to-many relationship between boards and images using PK
+                -- (we can extend this to many-to-many later)
+                PRIMARY KEY (image_name),
+                FOREIGN KEY (board_id) REFERENCES boards (board_id) ON DELETE CASCADE,
+                FOREIGN KEY (image_name) REFERENCES images (image_name) ON DELETE CASCADE
+            );
+            """
+        )
+
+        # Add index for board id
+        self._cursor.execute(
+            """--sql
+            CREATE INDEX IF NOT EXISTS idx_board_images_board_id ON board_images (board_id);
+            """
+        )
+
+        # Add index for board id, sorted by created_at
+        self._cursor.execute(
+            """--sql
+            CREATE INDEX IF NOT EXISTS idx_board_images_board_id_created_at ON board_images (board_id, created_at);
+            """
+        )
+
+        # Add trigger for `updated_at`.
+        self._cursor.execute(
+            """--sql
+            CREATE TRIGGER IF NOT EXISTS tg_board_images_updated_at
+            AFTER UPDATE
+            ON board_images FOR EACH ROW
+            BEGIN
+                UPDATE board_images SET updated_at = STRFTIME('%Y-%m-%d %H:%M:%f', 'NOW')
+                    WHERE board_id = old.board_id AND image_name = old.image_name;
+            END;
+            """
+        )
+
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                INSERT INTO board_images (board_id, image_name)
+                VALUES (?, ?)
+                ON CONFLICT (image_name) DO UPDATE SET board_id = ?;
+                """,
+                (board_id, image_name, board_id),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                DELETE FROM board_images
+                WHERE image_name = ?;
+                """,
+                (image_name,),
+            )
+            self._conn.commit()
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def get_all_board_images_for_board(
+        self,
+        board_id: str,
+    ) -> GetAllBoardImagesForBoardResult:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT image_name
+                FROM board_images
+                WHERE board_id = ?
+                ORDER BY updated_at DESC;
+                """,
+                (board_id,),
+            )
+
+            result = cast(list[sqlite3.Row], self._cursor.fetchall())
+            image_names = list(map(lambda r: r[0], result))
+
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+        return GetAllBoardImagesForBoardResult(
+            board_id=board_id, image_names=image_names
+        )
+
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT board_id
+                FROM board_images
+                WHERE image_name = ?;
+                """,
+                (image_name,),
+            )
+            result = self._cursor.fetchone()
+            if result is None:
+                return None
+            return cast(str, result[0])
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()
+
+    def get_image_count_for_board(self, board_id: str) -> int:
+        try:
+            self._lock.acquire()
+            self._cursor.execute(
+                """--sql
+                SELECT COUNT(*) FROM board_images WHERE board_id = ?;
+                """,
+                (board_id,),
+            )
+            count = cast(int, self._cursor.fetchone()[0])
+            return count
+        except sqlite3.Error as e:
+            self._conn.rollback()
+            raise e
+        finally:
+            self._lock.release()

invokeai/app/services/board_images.py

@@ -0,0 +1,181 @@
+from abc import ABC, abstractmethod
+from logging import Logger
+from typing import List, Optional, Union
+
+from invokeai.app.models.image import (AddManyImagesToBoardResult,
+                                       GetAllBoardImagesForBoardResult,
+                                       RemoveManyImagesFromBoardResult)
+from invokeai.app.services.board_image_record_storage import \
+    BoardImageRecordStorageBase
+from invokeai.app.services.board_record_storage import (BoardRecord,
+                                                        BoardRecordStorageBase)
+from invokeai.app.services.image_record_storage import (ImageRecordStorageBase,
+                                                        OffsetPaginatedResults)
+from invokeai.app.services.models.board_record import BoardDTO
+from invokeai.app.services.models.image_record import (ImageDTO,
+                                                       image_record_to_dto)
+from invokeai.app.services.urls import UrlServiceBase
+
+
+class BoardImagesServiceABC(ABC):
+    """High-level service for board-image relationship management."""
+
+    @abstractmethod
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        """Adds an image to a board. If the image is on a different board, it is removed from that board."""
+        pass
+
+    @abstractmethod
+    def add_many_images_to_board(
+        self,
+        board_id: str,
+        image_names: list[str],
+    ) -> AddManyImagesToBoardResult:
+        """Adds many images to a board. If an image is on a different board, it is removed from that board."""
+        pass
+
+    @abstractmethod
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        """Removes an image from its board."""
+        pass
+
+    @abstractmethod
+    def remove_many_images_from_board(
+        self,
+        image_names: list[str],
+    ) -> RemoveManyImagesFromBoardResult:
+        """Removes many images from their board, if they had one."""
+        pass
+
+    @abstractmethod
+    def get_all_board_images_for_board(
+        self,
+        board_id: str,
+    ) -> GetAllBoardImagesForBoardResult:
+        """Gets all image names for a board."""
+        pass
+
+    @abstractmethod
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        """Gets an image's board id, if it has one."""
+        pass
+
+
+class BoardImagesServiceDependencies:
+    """Service dependencies for the BoardImagesService."""
+
+    board_image_records: BoardImageRecordStorageBase
+    board_records: BoardRecordStorageBase
+    image_records: ImageRecordStorageBase
+    urls: UrlServiceBase
+    logger: Logger
+
+    def __init__(
+        self,
+        board_image_record_storage: BoardImageRecordStorageBase,
+        image_record_storage: ImageRecordStorageBase,
+        board_record_storage: BoardRecordStorageBase,
+        url: UrlServiceBase,
+        logger: Logger,
+    ):
+        self.board_image_records = board_image_record_storage
+        self.image_records = image_record_storage
+        self.board_records = board_record_storage
+        self.urls = url
+        self.logger = logger
+
+
+class BoardImagesService(BoardImagesServiceABC):
+    _services: BoardImagesServiceDependencies
+
+    def __init__(self, services: BoardImagesServiceDependencies):
+        self._services = services
+
+    def add_image_to_board(
+        self,
+        board_id: str,
+        image_name: str,
+    ) -> None:
+        self._services.board_image_records.add_image_to_board(board_id, image_name)
+
+    def add_many_images_to_board(
+        self,
+        board_id: str,
+        image_names: list[str],
+    ) -> AddManyImagesToBoardResult:
+        added_images: list[str] = []
+
+        for image_name in image_names:
+            try:
+                self._services.board_image_records.add_image_to_board(
+                    board_id, image_name
+                )
+                added_images.append(image_name)
+            except Exception as e:
+                self._services.logger.exception(e)
+
+        total = self._services.board_image_records.get_image_count_for_board(board_id)
+
+        return AddManyImagesToBoardResult(
+            board_id=board_id, added_images=added_images, total=total
+        )
+
+    def remove_image_from_board(
+        self,
+        image_name: str,
+    ) -> None:
+        self._services.board_image_records.remove_image_from_board(image_name)
+
+    def remove_many_images_from_board(
+        self,
+        image_names: list[str],
+    ) -> RemoveManyImagesFromBoardResult:
+        removed_images: list[str] = []
+
+        for image_name in image_names:
+            try:
+                self._services.board_image_records.remove_image_from_board(image_name)
+                removed_images.append(image_name)
+            except Exception as e:
+                self._services.logger.exception(e)
+
+        return RemoveManyImagesFromBoardResult(
+            removed_images=removed_images,
+        )
+
+    def get_all_board_images_for_board(
+        self,
+        board_id: str,
+    ) -> GetAllBoardImagesForBoardResult:
+        result = self._services.board_image_records.get_all_board_images_for_board(
+            board_id
+        )
+        return result
+
+    def get_board_for_image(
+        self,
+        image_name: str,
+    ) -> Optional[str]:
+        board_id = self._services.board_image_records.get_board_for_image(image_name)
+        return board_id
+
+
+def board_record_to_dto(
+    board_record: BoardRecord, cover_image_name: Optional[str], image_count: int
+) -> BoardDTO:
+    """Converts a board record to a board DTO."""
+    return BoardDTO(
+        **board_record.dict(exclude={"cover_image_name"}),
+        cover_image_name=cover_image_name,
+        image_count=image_count,
+    )