Merge branch 'main' into Convert-Model-Endpoint

# Application-wide configuration service

This PR creates a new `InvokeAIAppConfig` object that reads
application-wide settings from an init file, the environment, and the
command line.

Arguments and fields are taken from the pydantic definition of the
model. Defaults can be set by creating a yaml configuration file that
has a top-level key of "InvokeAI" and subheadings for each of the
categories returned by `invokeai --help`.

The file looks like this:

[file: invokeai.yaml]
```
InvokeAI:
  Paths:
    root: /home/lstein/invokeai-main
    conf_path: configs/models.yaml
    legacy_conf_dir: configs/stable-diffusion
    outdir: outputs
    embedding_dir: embeddings
    lora_dir: loras
    autoconvert_dir: null
    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
  Models:
    model: stable-diffusion-1.5
    embeddings: true
  Memory/Performance:
    xformers_enabled: false
    sequential_guidance: false
    precision: float16
    max_loaded_models: 4
    always_use_cpu: false
    free_gpu_mem: false
  Features:
    nsfw_checker: true
    restore: true
    esrgan: true
    patchmatch: true
    internet_available: true
    log_tokenization: false
  Cross-Origin Resource Sharing:
    allow_origins: []
    allow_credentials: true
    allow_methods:
    - '*'
    allow_headers:
    - '*'
  Web Server:
    host: 127.0.0.1
    port: 8081

```

The default name of the configuration file is `invokeai.yaml`, located
in INVOKEAI_ROOT. You can use any OmegaConf dictionary by passing it to
the config object at initialization time:

```
 omegaconf = OmegaConf.load('/tmp/init.yaml')
 conf = InvokeAIAppConfig(conf=omegaconf)
```
The default name of the configuration file is `invokeai.yaml`, located
in INVOKEAI_ROOT. You can replace supersede this by providing
anyOmegaConf dictionary object initialization time:

```
omegaconf = OmegaConf.load('/tmp/init.yaml')
conf = InvokeAIAppConfig(conf=omegaconf)
```

By default, InvokeAIAppConfig will parse the contents of `sys.argv` at
initialization time. You may pass a list of strings in the optional
`argv` argument to use instead of the system argv:

```
conf = InvokeAIAppConfig(arg=['--xformers_enabled'])
```

It is also possible to set a value at initialization time. This value
has highest priority.
```
conf = InvokeAIAppConfig(xformers_enabled=True)
```
Any setting can be overwritten by setting an environment variable of
form: "INVOKEAI_<setting>", as in:

```
export INVOKEAI_port=8080
```

Order of precedence (from highest):
   1) initialization options
   2) command line options
   3) environment variable options
   4) config file options
   5) pydantic defaults

Typical usage:

```
from invokeai.app.services.config import InvokeAIAppConfig

# get global configuration and print its nsfw_checker value
conf = InvokeAIAppConfig()
print(conf.nsfw_checker)
```
Finally, the configuration object is able to recreate its (modified)
yaml file, by calling its `to_yaml()` method:

```
conf = InvokeAIAppConfig(outdir='/tmp', port=8080)
print(conf.to_yaml())
```

# Legacy code removal and porting

This PR replaces Globals with the InvokeAIAppConfig system throughout,
and therefore removes the `globals.py` and `args.py` modules. It also
removes `generate` and the legacy CLI. ***The old CLI and web servers
are now gone.***

I have ported the functionality of the configuration script, the model
installer, and the merge and textual inversion scripts. The `invokeai`
command will now launch `invokeai-node-cli`, and `invokeai-web` will
launch the web server.

I have changed the continuous invocation tests to accommodate the new
command syntax in `invokeai-node-cli`. As a convenience function, you
can also pass invocations to `invokeai-node-cli` (or its alias
`invokeai`) on the command line as as standard input:

```
invokeai-node-cli "t2i --positive_prompt 'banana sushi' --seed 42"
invokeai < invocation_commands.txt
```

.dockerignore

@@ -4,22 +4,22 @@
 !ldm
 !pyproject.toml
 
-# Guard against pulling in any models that might exist in the directory tree
-**/*.pt*
-**/*.ckpt
-
-# ignore frontend but whitelist dist
-invokeai/frontend/
-!invokeai/frontend/dist/
+# ignore 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
+**/*.egg-info/
+**/*.egg

.editorconfig

@@ -1,8 +1,5 @@
-root = true
-
 # All files
 [*]
-max_line_length = 80
 charset = utf-8
 end_of_line = lf
 indent_size = 2
@@ -13,18 +10,3 @@ trim_trailing_whitespace = true
 # Python
 [*.py]
 indent_size = 4
-max_line_length = 120
-
-# css
-[*.css]
-indent_size = 4
-
-# flake8
-[.flake8]
-indent_size = 4
-
-# Markdown MkDocs
-[docs/**/*.md]
-max_line_length = 80
-indent_size = 4
-indent_style = unset

.flake8

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

.git-blame-ignore-revs

@@ -0,0 +1 @@
+b3dccfaeb636599c02effc377cdd8a87d658256c

.github/CODEOWNERS

@@ -1,61 +1,34 @@
 # continuous integration
-/.github/workflows/ @mauwii @lstein @blessedcoolant
+/.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @mauwii @blessedcoolant
-mkdocs.yml @mauwii @lstein
+/docs/ @lstein  @tildebyte @blessedcoolant
+/mkdocs.yml @lstein  @blessedcoolant
+
+# nodes
+/invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
-/pyproject.toml @mauwii @lstein @ebr
-/docker/ @mauwii
-/scripts/ @ebr @lstein @blessedcoolant
-/installer/ @ebr @lstein 
-ldm/invoke/config @lstein @ebr
-invokeai/assets @lstein @blessedcoolant
-invokeai/configs @lstein @ebr  @blessedcoolant
-/ldm/invoke/_version.py @lstein @blessedcoolant
+/pyproject.toml  @lstein @blessedcoolant
+/docker/  @lstein @blessedcoolant
+/scripts/ @ebr @lstein
+/installer/ @lstein @ebr
+/invokeai/assets @lstein @ebr
+/invokeai/configs @lstein
+/invokeai/version @lstein @blessedcoolant
 
 # web ui
-/invokeai/frontend @blessedcoolant @psychedelicious
-/invokeai/backend @blessedcoolant @psychedelicious
+/invokeai/frontend @blessedcoolant @psychedelicious @lstein
+/invokeai/backend @blessedcoolant @psychedelicious @lstein
 
-# generation and model management
-/ldm/*.py @lstein @blessedcoolant
-/ldm/generate.py @lstein @keturn
-/ldm/invoke/args.py @lstein @blessedcoolant
-/ldm/invoke/ckpt* @lstein @blessedcoolant
-/ldm/invoke/ckpt_generator @lstein @blessedcoolant
-/ldm/invoke/CLI.py @lstein @blessedcoolant
-/ldm/invoke/config @lstein @ebr @mauwii @blessedcoolant
-/ldm/invoke/generator @keturn @damian0815
-/ldm/invoke/globals.py @lstein @blessedcoolant 
-/ldm/invoke/merge_diffusers.py @lstein @blessedcoolant
-/ldm/invoke/model_manager.py @lstein @blessedcoolant
-/ldm/invoke/txt2mask.py @lstein @blessedcoolant
-/ldm/invoke/patchmatch.py @Kyle0654 @lstein
-/ldm/invoke/restoration @lstein @blessedcoolant
+# generation, model management, postprocessing
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2
 
-# attention, textual inversion, model configuration
-/ldm/models @damian0815 @keturn @blessedcoolant
-/ldm/modules/textual_inversion_manager.py @lstein @blessedcoolant
-/ldm/modules/attention.py @damian0815 @keturn
-/ldm/modules/diffusionmodules @damian0815 @keturn
-/ldm/modules/distributions @damian0815 @keturn
-/ldm/modules/ema.py  @damian0815 @keturn
-/ldm/modules/embedding_manager.py @lstein
-/ldm/modules/encoders @damian0815 @keturn
-/ldm/modules/image_degradation @damian0815 @keturn
-/ldm/modules/losses  @damian0815 @keturn
-/ldm/modules/x_transformer.py @damian0815 @keturn
-
-# Nodes
-apps/ @Kyle0654 @jpphoto
-
-# legacy REST API
-# these are dead code
-#/ldm/invoke/pngwriter.py @CapableWeb
-#/ldm/invoke/server_legacy.py @CapableWeb
-#/scripts/legacy_api.py @CapableWeb
-#/tests/legacy_tests.sh @CapableWeb
+# 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
 
 

.github/ISSUE_TEMPLATE/BUG_REPORT.yml

@@ -65,6 +65,16 @@ body:
       placeholder: 8GB
     validations:
       required: false
+      
+  - type: input
+    id: version-number
+    attributes:
+      label: What version did you experience this issue on?
+      description: |
+        Please share the version of Invoke AI that you experienced the issue on. If this is not the latest version, please update first to confirm the issue still exists. If you are testing main, please include the commit hash instead.
+      placeholder: X.X.X
+    validations:
+      required: true
 
   - type: textarea
     id: what-happened

.github/stale.yaml

@@ -0,0 +1,19 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 28
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 14
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: stale
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Please
+  update the ticket if this is still a problem on the latest release.
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: >
+  Due to inactivity, this issue has been automatically closed. If this is
+  still a problem on the latest release, please recreate the issue.

.github/workflows/build-container.yml

@@ -5,17 +5,20 @@ on:
       - 'main'
       - 'update/ci/docker/*'
       - 'update/docker/*'
+      - 'dev/ci/docker/*'
+      - 'dev/docker/*'
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - '.dockerignore'
+      - 'invokeai/**'
       - 'docker/Dockerfile'
     tags:
       - 'v*.*.*'
   workflow_dispatch:
 
+permissions:
+  contents: write
+  packages: write
 
 jobs:
   docker:
@@ -24,11 +27,11 @@ jobs:
       fail-fast: false
       matrix:
         flavor:
-          - amd
+          - rocm
           - cuda
           - cpu
         include:
-          - flavor: amd
+          - flavor: rocm
             pip-extra-index-url: 'https://download.pytorch.org/whl/rocm5.2'
           - flavor: cuda
             pip-extra-index-url: ''
@@ -54,9 +57,9 @@ jobs:
           tags: |
             type=ref,event=branch
             type=ref,event=tag
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=semver,pattern={{major}}
+            type=pep440,pattern={{version}}
+            type=pep440,pattern={{major}}.{{minor}}
+            type=pep440,pattern={{major}}
             type=sha,enable=true,prefix=sha-,format=short
           flavor: |
             latest=${{ matrix.flavor == 'cuda' && github.ref == 'refs/heads/main' }}
@@ -92,7 +95,7 @@ jobs:
           context: .
           file: ${{ env.DOCKERFILE }}
           platforms: ${{ env.PLATFORMS }}
-          push: ${{ github.ref == 'refs/heads/main' || github.ref == 'refs/tags/*' }}
+          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 }}

.github/workflows/close-inactive-issues.yml

@@ -0,0 +1,27 @@
+name: Close inactive issues
+on:
+  schedule:
+    - cron: "00 6 * * *"
+
+env:
+  DAYS_BEFORE_ISSUE_STALE: 14
+  DAYS_BEFORE_ISSUE_CLOSE: 28
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v5
+        with:
+          days-before-issue-stale: ${{ env.DAYS_BEFORE_ISSUE_STALE }}
+          days-before-issue-close: ${{ env.DAYS_BEFORE_ISSUE_CLOSE }}
+          stale-issue-label: "Inactive Issue"
+          stale-issue-message: "There has been no activity in this issue for ${{ env.DAYS_BEFORE_ISSUE_STALE }} days. If this issue is still being experienced, please reply with an updated confirmation that the issue is still being experienced with the latest release."
+          close-issue-message: "Due to inactivity, this issue was automatically closed. If you are still experiencing the issue, please recreate the issue."
+          days-before-pr-stale: -1
+          days-before-pr-close: -1
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          operations-per-run: 500

.github/workflows/lint-frontend.yml

@@ -3,14 +3,22 @@ name: Lint frontend
 on:
   pull_request:
     paths:
-      - 'invokeai/frontend/**'
+      - 'invokeai/frontend/web/**'
+    types:
+      - 'ready_for_review'
+      - 'opened'
+      - 'synchronize'
   push:
+    branches:
+      - 'main'
     paths:
-      - 'invokeai/frontend/**'
+      - 'invokeai/frontend/web/**'
+  merge_group:
+  workflow_dispatch:
 
 defaults:
   run:
-    working-directory: invokeai/frontend
+    working-directory: invokeai/frontend/web
 
 jobs:
   lint-frontend:
@@ -23,7 +31,7 @@ jobs:
           node-version: '18'
       - uses: actions/checkout@v3
       - run: 'yarn install --frozen-lockfile'
-      - run: 'yarn tsc'
-      - run: 'yarn run madge'
-      - run: 'yarn run lint --max-warnings=0'
-      - run: 'yarn run prettier --check'
+      - run: 'yarn run lint:tsc'
+      - run: 'yarn run lint:madge'
+      - run: 'yarn run lint:eslint'
+      - run: 'yarn run lint:prettier'

.github/workflows/mkdocs-material.yml

@@ -2,8 +2,10 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'main'
-      - 'development'
+      - 'refs/heads/v2.3'
+
+permissions:
+    contents: write
 
 jobs:
   mkdocs-material:
@@ -41,7 +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/pypi-release.yml

@@ -3,7 +3,7 @@ name: PyPI Release
 on:
   push:
     paths:
-      - 'ldm/invoke/_version.py'
+      - 'invokeai/version/invokeai_version.py'
   workflow_dispatch:
 
 jobs:

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

@@ -1,12 +1,11 @@
 name: Test invoke.py pip
 on:
   pull_request:
-    paths-ignore:
-      - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+    paths:
+      - '**'
+      - '!pyproject.toml'
+      - '!invokeai/**'
+      - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
 

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

@@ -5,17 +5,13 @@ on:
       - 'main'
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - 'invokeai/**'
+      - '!invokeai/frontend/web/**'
   pull_request:
     paths:
       - 'pyproject.toml'
-      - 'ldm/**'
-      - 'invokeai/backend/**'
-      - 'invokeai/configs/**'
-      - 'invokeai/frontend/dist/**'
+      - 'invokeai/**'
+      - '!invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
       - 'opened'
@@ -84,12 +80,7 @@ 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 }}
+        run:echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
         uses: actions/setup-python@v4
@@ -109,12 +100,6 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: set INVOKEAI_OUTDIR
-        run: >
-          python -c
-          "import os;from ldm.invoke.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
-          >> ${{ matrix.github-env }}
-
       - name: run invokeai-configure
         id: run-preload-models
         env:
@@ -133,15 +118,20 @@ jobs:
           HF_HUB_OFFLINE: 1
           HF_DATASETS_OFFLINE: 1
           TRANSFORMERS_OFFLINE: 1
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         run: >
           invokeai
           --no-patchmatch
           --no-nsfw_checker
-          --from_file ${{ env.TEST_PROMPTS }}
+          --precision=float32
+          --always_use_cpu
           --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+          --from_file ${{ env.TEST_PROMPTS }}
 
       - name: Archive results
         id: archive-results
+        env:
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         uses: actions/upload-artifact@v3
         with:
           name: results

.gitignore

@@ -9,6 +9,8 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
+.version
+.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -63,15 +65,18 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
+.coveragerc
 .coverage
 .coverage.*
 .cache
 nosetests.xml
 coverage.xml
+cov.xml
 *.cover
 *.py,cover
 .hypothesis/
 .pytest_cache/
+.pytest.ini
 cover/
 junit/
 
@@ -196,8 +201,10 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
+invokeai/frontend/web/dist/*
+
 # Let the frontend manage its own gitignore
-!invokeai/frontend/*
+!invokeai/frontend/web/*
 
 # Scratch folder
 .scratch/
@@ -212,11 +219,6 @@ gfpgan/
 # config file (will be created by installer)
 configs/models.yaml
 
-# weights (will be created by installer)
-models/ldm/stable-diffusion-v1/*.ckpt
-models/clipseg
-models/gfpgan
-
 # ignore initfile
 .invokeai
 
@@ -231,6 +233,3 @@ installer/install.bat
 installer/install.sh
 installer/update.bat
 installer/update.sh
-
-# no longer stored in source directory
-models

.pre-commit-config.yaml

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

.prettierignore

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

.prettierrc.yaml

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

README.md

@@ -33,6 +33,8 @@
 
 </div>
 
+_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+
 InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
 **Quick links**: [[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>]
@@ -84,7 +86,7 @@ installing lots of models.
 
 6. Wait while the installer does its thing. After installing the software,
 the installer will launch a script that lets you configure InvokeAI and
-select a set of starting image generaiton models.
+select a set of starting image generation models.
 
 7. Find the folder that InvokeAI was installed into (it is not the
 same as the unpacked zip file directory!) The default location of this
@@ -139,7 +141,7 @@ not supported.
     _For Windows/Linux with an NVIDIA GPU:_
 
     ```terminal
-    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
     ```
 
     _For Linux with an AMD GPU:_
@@ -148,6 +150,11 @@ not supported.
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
+    _For non-GPU systems:_
+    ```terminal
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+    ``` 
+
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh

binary_installer/install.bat.in

@@ -0,0 +1,164 @@
+@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

@@ -0,0 +1,235 @@
+#!/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

@@ -0,0 +1,36 @@
+@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

@@ -0,0 +1,46 @@
+#!/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

@@ -0,0 +1,17 @@
+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

@@ -0,0 +1,33 @@
+--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

coverage/.gitignore

@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore

docker/Dockerfile

@@ -4,15 +4,15 @@ ARG PYTHON_VERSION=3.9
 ##################
 ##  base image  ##
 ##################
-FROM python:${PYTHON_VERSION}-slim AS python-base
+FROM --platform=${TARGETPLATFORM} python:${PYTHON_VERSION}-slim AS python-base
 
 LABEL org.opencontainers.image.authors="mauwii@outlook.de"
 
-# prepare for buildkit cache
+# 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
 
-# Install necessary packages
+# Install dependencies
 RUN \
   --mount=type=cache,target=/var/cache/apt,sharing=locked \
   --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -23,7 +23,7 @@ RUN \
     libglib2.0-0=2.66.* \
     libopencv-dev=4.5.*
 
-# set working directory and env
+# Set working directory and env
 ARG APPDIR=/usr/src
 ARG APPNAME=InvokeAI
 WORKDIR ${APPDIR}
@@ -32,7 +32,7 @@ ENV PATH ${APPDIR}/${APPNAME}/bin:$PATH
 ENV PYTHONDONTWRITEBYTECODE 1
 # Turns off buffering for easier container logging
 ENV PYTHONUNBUFFERED 1
-# don't fall back to legacy build system
+# Don't fall back to legacy build system
 ENV PIP_USE_PEP517=1
 
 #######################
@@ -40,7 +40,7 @@ ENV PIP_USE_PEP517=1
 #######################
 FROM python-base AS pyproject-builder
 
-# Install dependencies
+# Install build dependencies
 RUN \
   --mount=type=cache,target=/var/cache/apt,sharing=locked \
   --mount=type=cache,target=/var/lib/apt,sharing=locked \
@@ -51,26 +51,30 @@ RUN \
     gcc=4:10.2.* \
     python3-dev=3.9.*
 
-# prepare pip for buildkit cache
+# Prepare pip for buildkit cache
 ARG PIP_CACHE_DIR=/var/cache/buildkit/pip
 ENV PIP_CACHE_DIR ${PIP_CACHE_DIR}
 RUN mkdir -p ${PIP_CACHE_DIR}
 
-# create virtual environment
-RUN --mount=type=cache,target=${PIP_CACHE_DIR},sharing=locked \
+# Create virtual environment
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
   python3 -m venv "${APPNAME}" \
   --upgrade-deps
 
-# copy sources
-COPY --link . .
-
-# install pyproject.toml
+# 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},sharing=locked \
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
+  "${APPNAME}"/bin/pip install .
+
+# Install pyproject.toml
+COPY --link . .
+RUN --mount=type=cache,target=${PIP_CACHE_DIR} \
   "${APPNAME}/bin/pip" install .
 
-# build patchmatch
+# Build patchmatch
 RUN python3 -c "from patchmatch import patch_match"
 
 #####################
@@ -86,14 +90,14 @@ RUN useradd \
   -U \
   "${UNAME}"
 
-# create volume directory
+# Create volume directory
 ARG VOLUME_DIR=/data
 RUN mkdir -p "${VOLUME_DIR}" \
-  && chown -R "${UNAME}" "${VOLUME_DIR}"
+  && chown -hR "${UNAME}:${UNAME}" "${VOLUME_DIR}"
 
-# setup runtime environment
-USER ${UNAME}
-COPY --chown=${UNAME} --from=pyproject-builder ${APPDIR}/${APPNAME} ${APPNAME}
+# 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"

docker/build.sh

@@ -41,7 +41,7 @@ else
 fi
 
 # Build Container
-DOCKER_BUILDKIT=1 docker build \
+docker build \
     --platform="${PLATFORM:-linux/amd64}" \
     --tag="${CONTAINER_IMAGE:-invokeai}" \
     ${CONTAINER_FLAVOR:+--build-arg="CONTAINER_FLAVOR=${CONTAINER_FLAVOR}"} \

docker/env.sh

@@ -49,3 +49,6 @@ 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

@@ -21,10 +21,10 @@ docker run \
   --tty \
   --rm \
   --platform="${PLATFORM}" \
-  --name="${REPOSITORY_NAME,,}" \
-  --hostname="${REPOSITORY_NAME,,}" \
-  --mount=source="${VOLUMENAME}",target=/data \
-  --mount type=bind,source="$(pwd)"/outputs,target=/data/outputs \
+  --name="${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 \
@@ -32,7 +32,7 @@ docker run \
   ${GPU_FLAGS:+--gpus="${GPU_FLAGS}"} \
   "${CONTAINER_IMAGE}" ${@:+$@}
 
-# Remove Trash folder
+echo -e "\nCleaning trash folder ..."
 for f in outputs/.Trash*; do
   if [ -e "$f" ]; then
     rm -Rf "$f"

docs/.markdownlint.jsonc

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

docs/contributing/ARCHITECTURE.md

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

docs/contributing/INVOCATIONS.md

@@ -0,0 +1,202 @@
+# Invocations
+
+Invocations represent a single operation, its inputs, and its outputs. These
+operations and their outputs can be chained together to generate and modify
+images.
+
+## Creating a new invocation
+
+To create a new invocation, either find the appropriate module file in
+`/ldm/invoke/app/invocations` to add your invocation to, or create a new one in
+that folder. All invocations in that folder will be discovered and made
+available to the CLI and API automatically. Invocations make use of
+[typing](https://docs.python.org/3/library/typing.html) and
+[pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration
+into the CLI and API.
+
+An invocation looks like this:
+
+```py
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+    type: Literal['upscale'] = 'upscale'
+
+    # Inputs
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description = "The upscale level")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image = ImageField(image_type = image_type, image_name = image_name)
+        )
+```
+
+Each portion is important to implement correctly.
+
+### Class definition and type
+
+```py
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+    type: Literal['upscale'] = 'upscale'
+```
+
+All invocations must derive from `BaseInvocation`. They should have a docstring
+that declares what they do in a single, short line. They should also have a
+`type` with a type hint that's `Literal["command_name"]`, where `command_name`
+is what the user will type on the CLI or use in the API to create this
+invocation. The `command_name` must be unique. The `type` must be assigned to
+the value of the literal in the type hint.
+
+### Inputs
+
+```py
+    # Inputs
+    image: Union[ImageField,None] = Field(description="The input image")
+    strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
+    level: Literal[2,4]           = Field(default=2, description="The upscale level")
+```
+
+Inputs consist of three parts: a name, a type hint, and a `Field` with default,
+description, and validation information. For example:
+
+| Part      | Value                                                         | Description                                                                                                               |
+| --------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
+| Name      | `strength`                                                    | This field is referred to as `strength`                                                                                   |
+| Type Hint | `float`                                                       | This field must be of type `float`                                                                                        |
+| Field     | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
+
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this
+field to be parsed with `None` as a value, which enables linking to previous
+invocations. All fields should either provide a default value or allow `None` as
+a value, so that they can be overwritten with a linked output from another
+invocation.
+
+The special type `ImageField` is also used here. All images are passed as
+`ImageField`, which protects them from pydantic validation errors (since images
+only ever come from links).
+
+Finally, note that for all linking, the `type` of the linked fields must match.
+If the `name` also matches, then the field can be **automatically linked** to a
+previous invocation by name and matching.
+
+### Invoke Function
+
+```py
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(self.image.image_type, self.image.image_name)
+        results = context.services.generate.upscale_and_reconstruct(
+            image_list     = [[image, 0]],
+            upscale        = (self.level, self.strength),
+            strength       = 0.0, # GFPGAN strength
+            save_original  = False,
+            image_callback = None,
+        )
+
+        # Results are image and seed, unwrap for now
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(context.graph_execution_state_id, self.id)
+        context.services.images.save(image_type, image_name, results[0][0])
+        return ImageOutput(
+            image = ImageField(image_type = image_type, image_name = image_name)
+        )
+```
+
+The `invoke` function is the last portion of an invocation. It is provided an
+`InvocationContext` which contains services to perform work as well as a
+`session_id` for use as needed. It should return a class with output values that
+derives from `BaseInvocationOutput`.
+
+Before being called, the invocation will have all of its fields set from
+defaults, inputs, and finally links (overriding in that order).
+
+Assume that this invocation may be running simultaneously with other
+invocations, may be running on another machine, or in other interesting
+scenarios. If you need functionality, please provide it as a service in the
+`InvocationServices` class, and make sure it can be overridden.
+
+### Outputs
+
+```py
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+    type: Literal['image'] = 'image'
+
+    image: ImageField = Field(default=None, description="The output image")
+```
+
+Output classes look like an invocation class without the invoke method. Prefer
+to use an existing output class if available, and prefer to name inputs the same
+as outputs when possible, to promote automatic invocation linking.
+
+## Schema Generation
+
+Invocation, output and related classes are used to generate an OpenAPI schema.
+
+### Required Properties
+
+The schema generation treat all properties with default values as optional. This
+makes sense internally, but when when using these classes via the generated
+schema, we end up with e.g. the `ImageOutput` class having its `image` property
+marked as optional.
+
+We know that this property will always be present, so the additional logic
+needed to always check if the property exists adds a lot of extraneous cruft.
+
+To fix this, we can leverage `pydantic`'s
+[schema customisation](https://docs.pydantic.dev/usage/schema/#schema-customization)
+to mark properties that we know will always be present as required.
+
+Here's that `ImageOutput` class, without the needed schema customisation:
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    type: Literal["image"] = "image"
+    image:      ImageField = Field(default=None, description="The output image")
+```
+
+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:
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    type: Literal["image"] = "image"
+    image:      ImageField = Field(default=None, description="The output image")
+
+    class Config:
+        schema_extra = {
+            'required': [
+                'type',
+                'image',
+            ]
+        }
+```
+
+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.
+
+See this `pydantic` issue for discussion on this solution:
+<https://github.com/pydantic/pydantic/discussions/4577>

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -0,0 +1,83 @@
+# Local Development
+
+If you are looking to contribute you will need to have a local development
+environment. See the
+[Developer Install](../installation/020_INSTALL_MANUAL.md#developer-install) for
+full details.
+
+Broadly this involves cloning the repository, installing the pre-reqs, and
+InvokeAI (in editable form). Assuming this is working, choose your area of
+focus.
+
+## Documentation
+
+We use [mkdocs](https://www.mkdocs.org) for our documentation with the
+[material theme](https://squidfunk.github.io/mkdocs-material/). Documentation is
+written in markdown files under the `./docs` folder and then built into a static
+website for hosting with GitHub Pages at
+[invoke-ai.github.io/InvokeAI](https://invoke-ai.github.io/InvokeAI).
+
+To contribute to the documentation you'll need to install the dependencies. Note
+the use of `"`.
+
+```zsh
+pip install ".[docs]"
+```
+
+Now, to run the documentation locally with hot-reloading for changes made.
+
+```zsh
+mkdocs serve
+```
+
+You'll then be prompted to connect to `http://127.0.0.1:8080` in order to
+access.
+
+## Backend
+
+The backend is contained within the `./invokeai/backend` folder structure. To
+get started however please install the development dependencies.
+
+From the root of the repository run the following command. Note the use of `"`.
+
+```zsh
+pip install ".[test]"
+```
+
+This in an optional group of packages which is defined within the
+`pyproject.toml` and will be required for testing the changes you make the the
+code.
+
+### Running Tests
+
+We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
+be found under the `./tests` folder and can be run with a single `pytest`
+command. Optionally, to review test coverage you can append `--cov`.
+
+```zsh
+pytest --cov
+```
+
+Test outcomes and coverage will be reported in the terminal. In addition a more
+detailed report is created in both XML and HTML format in the `./coverage`
+folder. The HTML one in particular can help identify missing statements
+requiring tests to ensure coverage. This can be run by opening
+`./coverage/html/index.html`.
+
+For example.
+
+```zsh
+pytest --cov; open ./coverage/html/index.html
+```
+
+??? info "HTML coverage report output"
+
+    ![html-overview](../assets/contributing/html-overview.png)
+
+    ![html-detail](../assets/contributing/html-detail.png)
+
+## Front End
+
+<!--#TODO: get input from blessedcoolant here, for the moment inserted the frontend README via snippets extension.-->
+
+--8<-- "invokeai/frontend/web/README.md"

docs/features/INPAINTING.md

@@ -168,11 +168,15 @@ used by Stable Diffusion 1.4 and 1.5.
 After installation, your `models.yaml` should contain an entry that looks like
 this one:
 
-inpainting-1.5: weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-description: SD inpainting v1.5 config:
-configs/stable-diffusion/v1-inpainting-inference.yaml vae:
-models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt width: 512
-height: 512
+```yml
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  description: SD inpainting v1.5
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+```
 
 As shown in the example, you may include a VAE fine-tuning weights file as well.
 This is strongly recommended.

docs/features/NSFW.md

@@ -32,7 +32,7 @@ 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` in your home directory). You can change the default at any
+`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`.
 

docs/features/PROMPTS.md

@@ -268,7 +268,7 @@ model is so good at inpainting, a good substitute is to use the `clipseg` text
 masking option:
 
 ```bash
-invoke> a fluffy cat eating a hotdot
+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

docs/features/TEXTUAL_INVERSION.md

@@ -17,7 +17,7 @@ notebooks.
 
 You will need a GPU to perform training in a reasonable length of
 time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS) to accelerate the
+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.
 
@@ -154,11 +154,8 @@ training sets will converge with 2000-3000 steps.
 
 This adjusts how many training images are processed simultaneously in
 each step. Higher values will cause the training process to run more
-quickly, but use more memory. The default size is selected based on
-whether you have the `xformers` memory-efficient attention library
-installed. If `xformers` is available, the batch size will be 8,
-otherwise 3.  These values were chosen to allow training to run with
-GPUs with as little as 12 GB VRAM.
+quickly, but use more memory. The default size will run with GPUs with
+as little as 12 GB.
 
 ### Learning rate
 
@@ -175,10 +172,8 @@ learning rate to improve performance.
 
 ### Use xformers acceleration
 
-This will activate XFormers memory-efficient attention, which will
-reduce memory requirements by half or more and allow you to select a
-higher batch size. You need to have XFormers installed for this to
-have an effect.
+This will activate XFormers memory-efficient attention. You need to
+have XFormers installed for this to have an effect.
 
 ### Learning rate scheduler
 
@@ -255,49 +250,6 @@ invokeai-ti \
        --only_save_embeds
 ```
 
-## Using Distributed Training
-
-If you have multiple GPUs on one machine, or a cluster of GPU-enabled
-machines, you can activate distributed training. See the [HuggingFace
-Accelerate pages](https://huggingface.co/docs/accelerate/index) for
-full information, but the basic recipe is:
-
-1. Enter the InvokeAI developer's console command line by selecting
-option [8] from the `invoke.sh`/`invoke.bat` script.
-
-2. Configurate Accelerate using `accelerate config`:
-```sh
-accelerate config
-```
-This will guide you through the configuration process, including
-specifying how many machines you will run training on and the number
-of GPUs pe rmachine.
-
-You only need to do this once.
-
-3. Launch training from the command line using `accelerate launch`. Be sure
-that your current working directory is the InvokeAI root directory (usually
-named `invokeai` in your home directory):
-
-```sh
-accelerate launch .venv/bin/invokeai-ti \
-       --model=stable-diffusion-1.5 \
-       --resolution=512 \
-       --learnable_property=object \
-       --initializer_token='*' \
-       --placeholder_token='<shraddha>' \
-       --train_data_dir=/home/lstein/invokeai/text-inversion-training-data/shraddha \
-       --output_dir=/home/lstein/invokeai/text-inversion-training/shraddha \
-       --scale_lr \
-       --train_batch_size=10 \
-       --gradient_accumulation_steps=4 \
-       --max_train_steps=2000 \
-       --learning_rate=0.0005 \
-       --lr_scheduler=constant \
-       --mixed_precision=fp16 \
-       --only_save_embeds
-```
-
 ## Using Embeddings
 
 After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.

docs/features/index.md

@@ -2,82 +2,62 @@
 title: Overview
 ---
 
--   The Basics
+Here you can find the documentation for InvokeAI's various features.
 
-    -   The [Web User Interface](WEB.md)
+## The Basics
+### * The [Web User Interface](WEB.md)
+Guide to the Web interface. Also see the [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
 
-        Guide to the Web interface. Also see the
-        [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
+### * The [Unified Canvas](UNIFIED_CANVAS.md)
+Build complex scenes by combine and modifying multiple images in a stepwise
+fashion. This feature combines img2img, inpainting and outpainting in
+a single convenient digital artist-optimized user interface.
 
-    -   The [Unified Canvas](UNIFIED_CANVAS.md)
+### * The [Command Line Interface (CLI)](CLI.md)
+Scriptable access to InvokeAI's features.
 
-        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.
+## Image Generation
+### * [Prompt Engineering](PROMPTS.md)
+Get the images you want with the InvokeAI  prompt engineering language.
 
-    -   The [Command Line Interface (CLI)](CLI.md)
+## * [Post-Processing](POSTPROCESS.md)
+Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
 
-        Scriptable access to InvokeAI's features.
+## * The [Concepts Library](CONCEPTS.md)
+Add custom subjects and styles using HuggingFace's repository of embeddings.
 
--   Image Generation
+### * [Image-to-Image Guide for the CLI](IMG2IMG.md)
+Use a seed image to build new creations in the CLI.
 
-    -   [Prompt Engineering](PROMPTS.md)
+### * [Inpainting Guide for the CLI](INPAINTING.md)
+Selectively erase and replace portions of an existing image in the CLI.
 
-        Get the images you want with the InvokeAI prompt engineering language.
+### * [Outpainting Guide for the CLI](OUTPAINTING.md)
+Extend the borders of the image with an "outcrop" function within the CLI.
 
-    -   [Post-Processing](POSTPROCESS.md)
+### * [Generating Variations](VARIATIONS.md)
+Have an image you like and want to generate many more like it? Variations
+are the ticket.
 
-        Restore mangled faces and make images larger with upscaling. Also see
-        the [Embiggen Upscaling Guide](EMBIGGEN.md).
+## Model Management
 
-    -   The [Concepts Library](CONCEPTS.md)
+## * [Model Installation](../installation/050_INSTALLING_MODELS.md)
+Learn how to import third-party models and switch among them. This
+guide also covers optimizing models to load quickly.
 
-        Add custom subjects and styles using HuggingFace's repository of
-        embeddings.
+## * [Merging Models](MODEL_MERGING.md)
+Teach an old model new tricks. Merge 2-3 models together to create a
+new model that combines characteristics of the originals.
 
-    -   [Image-to-Image Guide for the CLI](IMG2IMG.md)
+## * [Textual Inversion](TEXTUAL_INVERSION.md)
+Personalize models by adding your own style or subjects.
 
-        Use a seed image to build new creations in the CLI.
+# Other Features
 
-    -   [Inpainting Guide for the CLI](INPAINTING.md)
+## * [The NSFW Checker](NSFW.md)
+Prevent InvokeAI from displaying unwanted racy images.
 
-        Selectively erase and replace portions of an existing image in the CLI.
-
-    -   [Outpainting Guide for the CLI](OUTPAINTING.md)
-
-        Extend the borders of the image with an "outcrop" function within the
-        CLI.
-
-    -   [Generating Variations](VARIATIONS.md)
-
-        Have an image you like and want to generate many more like it?
-        Variations are the ticket.
-
--   Model Management
-
-    -   [Model Installation](../installation/050_INSTALLING_MODELS.md)
-
-        Learn how to import third-party models and switch among them. This guide
-        also covers optimizing models to load quickly.
-
-    -   [Merging Models](MODEL_MERGING.md)
-
-        Teach an old model new tricks. Merge 2-3 models together to create a new
-        model that combines characteristics of the originals.
-
-    -   [Textual Inversion](TEXTUAL_INVERSION.md)
-
-        Personalize models by adding your own style or subjects.
-
--   Other Features
-
-    -   [The NSFW Checker](NSFW.md)
-
-        Prevent InvokeAI from displaying unwanted racy images.
-
-    -   [Miscellaneous](OTHER.md)
-
-        Run InvokeAI on Google Colab, generate images with repeating patterns,
-        batch process a file of prompts, increase the "creativity" of image
-        generation by adding initial noise, and more!
+## * [Miscellaneous](OTHER.md)
+Run InvokeAI on Google Colab, generate images with repeating patterns,
+batch process a file of prompts, increase the "creativity" of image
+generation by adding initial noise, and more!

docs/help/IDE-Settings/index.md

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

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

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

docs/help/contributing/010_PULL_REQUEST.md

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

docs/help/contributing/020_ISSUES.md

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

docs/help/contributing/030_DOCS.md

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

docs/help/contributing/090_NODE_TRANSFORMATION.md

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

docs/help/contributing/index.md

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

docs/help/index.md

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

docs/index.md

@@ -2,8 +2,6 @@
 title: Home
 ---
 
-# :octicons-home-16: Home
-
 <!--
   The Docs you find here (/docs/*) are built and deployed via mkdocs. If you want to run a local version to verify your changes, it's as simple as::
 
@@ -31,36 +29,36 @@ title: Home
 [![github open prs badge]][github open prs link]
 
 [ci checks on dev badge]:
-    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
+  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
 [ci checks on dev link]:
-    https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
+  https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
 [ci checks on main badge]:
-    https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
+  https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
 [ci checks on main link]:
-    https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
+  https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
 [discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
 [discord link]: https://discord.gg/ZmtBAhwWhy
 [github forks badge]:
-    https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
 [github forks link]:
-    https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
+  https://useful-forks.github.io/?repo=lstein%2Fstable-diffusion
 [github open issues badge]:
-    https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/open-issues/invoke-ai/InvokeAI?icon=github
 [github open issues link]:
-    https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
+  https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen
 [github open prs badge]:
-    https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/open-prs/invoke-ai/InvokeAI?icon=github
 [github open prs link]:
-    https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
+  https://github.com/invoke-ai/InvokeAI/pulls?q=is%3Apr+is%3Aopen
 [github stars badge]:
-    https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
+  https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
 [latest commit to dev badge]:
-    https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
+  https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to dev link]:
-    https://github.com/invoke-ai/InvokeAI/commits/development
+  https://github.com/invoke-ai/InvokeAI/commits/development
 [latest release badge]:
-    https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
+  https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
 
 </div>
@@ -89,24 +87,24 @@ Q&A</a>]
 
 You wil need one of the following:
 
--   :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
--   :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
-    only)
--   :fontawesome-brands-apple: An Apple computer with an M1 chip.
+- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
+  only)
+- :fontawesome-brands-apple: An Apple computer with an M1 chip.
 
 We do **not recommend** the following video cards due to issues with their
 running in half-precision mode and having insufficient VRAM to render 512x512
 images in full-precision mode:
 
--   NVIDIA 10xx series cards such as the 1080ti
--   GTX 1650 series cards
--   GTX 1660 series cards
+- NVIDIA 10xx series cards such as the 1080ti
+- GTX 1650 series cards
+- GTX 1660 series cards
 
 ### :fontawesome-solid-memory: Memory and Disk
 
--   At least 12 GB Main Memory RAM.
--   At least 18 GB of free disk space for the machine learning model, Python,
-    and all its dependencies.
+- At least 12 GB Main Memory RAM.
+- At least 18 GB of free disk space for the machine learning model, Python, and
+  all its dependencies.
 
 ## :octicons-package-dependencies-24: Installation
 
@@ -115,65 +113,48 @@ either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
 ### [Installation Getting Started Guide](installation)
-
 #### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
-
 This method is recommended for 1st time users
-
 #### [Manual Installation](installation/020_INSTALL_MANUAL.md)
-
 This method is recommended for experienced users and developers
-
 #### [Docker Installation](installation/040_INSTALL_DOCKER.md)
-
 This method is recommended for those familiar with running Docker containers
-
 ### Other Installation Guides
-
--   [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
--   [XFormers](installation/070_INSTALL_XFORMERS.md)
--   [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
--   [Installing New Models](installation/050_INSTALLING_MODELS.md)
+  - [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
+  - [XFormers](installation/070_INSTALL_XFORMERS.md)
+  - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
+  - [Installing New Models](installation/050_INSTALLING_MODELS.md)
 
 ## :octicons-gift-24: InvokeAI Features
 
 ### The InvokeAI Web Interface
-
--   [WebUI overview](features/WEB.md)
--   [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
--   [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
+- [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)
+- [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)
+- [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 -->
-
 ### Model Management
-
--   [Installing](installation/050_INSTALLING_MODELS.md)
--   [Model Merging](features/MODEL_MERGING.md)
--   [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
--   [Textual Inversion](features/TEXTUAL_INVERSION.md)
--   [Not Safe for Work (NSFW) Checker](features/NSFW.md)
+- [Installing](installation/050_INSTALLING_MODELS.md)
+- [Model Merging](features/MODEL_MERGING.md)
+- [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
+- [Textual Inversion](features/TEXTUAL_INVERSION.md)
+- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
 <!-- seperator -->
-
 ### Prompt Engineering
-
--   [Prompt Syntax](features/PROMPTS.md)
--   [Generating Variations](features/VARIATIONS.md)
+- [Prompt Syntax](features/PROMPTS.md)
+- [Generating Variations](features/VARIATIONS.md)
 
 ## :octicons-log-16: Latest Changes
 
@@ -181,188 +162,84 @@ This method is recommended for those familiar with running Docker containers
 
 #### Migration to Stable Diffusion `diffusers` models
 
-Previous versions of InvokeAI supported the original model file format
-introduced with Stable Diffusion 1.4. In the original format, known variously as
-"checkpoint", or "legacy" format, there is a single large weights file ending
-with `.ckpt` or `.safetensors`. Though this format has served the community
-well, it has a number of disadvantages, including file size, slow loading times,
-and a variety of non-standard variants that require special-case code to handle.
-In addition, because checkpoint files are actually a bundle of multiple machine
-learning sub-models, it is hard to swap different sub-models in and out, or to
-share common sub-models. A new format, introduced by the StabilityAI company in
-collaboration with HuggingFace, is called `diffusers` and consists of a
-directory of individual models. The most immediate benefit of `diffusers` is
-that they load from disk very quickly. A longer term benefit is that in the near
-future `diffusers` models will be able to share common sub-models, dramatically
-reducing disk space when you have multiple fine-tune models derived from the
-same base.
+Previous versions of InvokeAI supported the original model file format introduced with Stable Diffusion 1.4. In the original format, known variously as "checkpoint", or "legacy" format, there is a single large weights file ending with `.ckpt` or `.safetensors`. Though this format has served the community well, it has a number of disadvantages, including file size, slow loading times, and a variety of non-standard variants that require special-case code to handle. In addition, because checkpoint files are actually a bundle of multiple machine learning sub-models, it is hard to swap different sub-models in and out, or to share common sub-models. A new format, introduced by the StabilityAI company in collaboration with HuggingFace, is called `diffusers` and consists of a directory of individual models. The most immediate benefit of `diffusers` is that they load from disk very quickly. A longer term benefit is that in the near future `diffusers` models will be able to share common sub-models, dramatically reducing disk space when you have multiple fine-tune models derived from the same base.
 
-When you perform a new install of version 2.3.0, you will be offered the option
-to install the `diffusers` versions of a number of popular SD models, including
-Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of
-2.1). These will act and work just like the checkpoint versions. Do not be
-concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk!
-InvokeAI 2.3.0 can still load these and generate images from them without any
-extra intervention on your part.
+When you perform a new install of version 2.3.0, you will be offered the option to install the `diffusers` versions of a number of popular SD models, including Stable Diffusion versions 1.5 and 2.1 (including the 768x768 pixel version of 2.1). These will act and work just like the checkpoint versions. Do not be concerned if you already have a lot of ".ckpt" or ".safetensors" models on disk! InvokeAI 2.3.0 can still load these and generate images from them without any extra intervention on your part.
 
-To take advantage of the optimized loading times of `diffusers` models, InvokeAI
-offers options to convert legacy checkpoint models into optimized `diffusers`
-models. If you use the `invokeai` command line interface, the relevant commands
-are:
+To take advantage of the optimized loading times of `diffusers` models, InvokeAI offers options to convert legacy checkpoint models into optimized `diffusers` models. If you use the `invokeai` command line interface, the relevant commands are:
 
--   `!convert_model` -- Take the path to a local checkpoint file or a URL that
-    is pointing to one, convert it into a `diffusers` model, and import it into
-    InvokeAI's models registry file.
--   `!optimize_model` -- If you already have a checkpoint model in your InvokeAI
-    models file, this command will accept its short name and convert it into a
-    like-named `diffusers` model, optionally deleting the original checkpoint
-    file.
--   `!import_model` -- Take the local path of either a checkpoint file or a
-    `diffusers` model directory and import it into InvokeAI's registry file. You
-    may also provide the ID of any diffusers model that has been published on
-    the
-    [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads)
-    and it will be downloaded and installed automatically.
+* `!convert_model` -- Take the path to a local checkpoint file or a URL that is pointing to one, convert it into a `diffusers` model, and import it into InvokeAI's models registry file.
+* `!optimize_model` -- If you already have a checkpoint model in your InvokeAI models file, this command will accept its short name and convert it into a like-named `diffusers` model, optionally deleting the original checkpoint file.
+* `!import_model` -- Take the local path of either a checkpoint file or a `diffusers` model directory and import it into InvokeAI's registry file. You may also provide the ID of any diffusers model that has been published on the [HuggingFace models repository](https://huggingface.co/models?pipeline_tag=text-to-image&sort=downloads) and it will be downloaded and installed automatically.
 
 The WebGUI offers similar functionality for model management.
 
-For advanced users, new command-line options provide additional functionality.
-Launching `invokeai` with the argument `--autoconvert <path to directory>` takes
-the path to a directory of checkpoint files, automatically converts them into
-`diffusers` models and imports them. Each time the script is launched, the
-directory will be scanned for new checkpoint files to be loaded. Alternatively,
-the `--ckpt_convert` argument will cause any checkpoint or safetensors model
-that is already registered with InvokeAI to be converted into a `diffusers`
-model on the fly, allowing you to take advantage of future diffusers-only
-features without explicitly converting the model and saving it to disk.
+For advanced users, new command-line options provide additional functionality. Launching `invokeai` with the argument `--autoconvert <path to directory>` takes the path to a directory of checkpoint files, automatically converts them into `diffusers` models and imports them. Each time the script is launched, the directory will be scanned for new checkpoint files to be loaded. Alternatively, the `--ckpt_convert` argument will cause any checkpoint or safetensors model that is already registered with InvokeAI to be converted into a `diffusers` model on the fly, allowing you to take advantage of future diffusers-only features without explicitly converting the model and saving it to disk.
 
-Please see
-[INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/)
-for more information on model management in both the command-line and Web
-interfaces.
+Please see [INSTALLING MODELS](https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/) for more information on model management in both the command-line and Web interfaces.
 
 #### Support for the `XFormers` Memory-Efficient Crossattention Package
 
-On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once
-installed, the`xformers` package dramatically reduces the memory footprint of
-loaded Stable Diffusion models files and modestly increases image generation
-speed. `xformers` will be installed and activated automatically if you specify a
-CUDA system at install time.
+On CUDA (Nvidia) systems, version 2.3.0 supports the `XFormers` library. Once installed,  the`xformers` package dramatically reduces the memory footprint of loaded Stable Diffusion models files and modestly increases image generation speed. `xformers` will be installed and activated automatically if you specify a CUDA system at install time.
 
-The caveat with using `xformers` is that it introduces slightly
-non-deterministic behavior, and images generated using the same seed and other
-settings will be subtly different between invocations. Generally the changes are
-unnoticeable unless you rapidly shift back and forth between images, but to
-disable `xformers` and restore fully deterministic behavior, you may launch
-InvokeAI using the `--no-xformers` option. This is most conveniently done by
-opening the file `invokeai/invokeai.init` with a text editor, and adding the
-line `--no-xformers` at the bottom.
+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.
+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.
+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.
+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.
+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.
+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`.
+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.
+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.
+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.
+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:
+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.
+* `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.
+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:
+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`
 
--   `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`.
 
-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
+Please see [2.3.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v2.3.0) for further details.
+For older changelogs, please visit the
 **[CHANGELOG](CHANGELOG/#v223-2-december-2022)**.
 
 ## :material-target: Troubleshooting
 
-Please check out our
-**[:material-frequently-asked-questions: Troubleshooting Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)**
-to get solutions for common installation problems and other issues.
+Please check out our **[:material-frequently-asked-questions:
+Troubleshooting
+Guide](installation/010_INSTALL_AUTOMATED.md#troubleshooting)** to
+get solutions for common installation problems and other issues.
 
 ## :octicons-repo-push-24: Contributing
 
@@ -388,8 +265,8 @@ thank them for their time, hard work and effort.
 For support, please use this repository's GitHub Issues tracking service. Feel
 free to send me an email if you use and like the script.
 
-Original portions of the software are Copyright (c) 2022-23 by
-[The InvokeAI Team](https://github.com/invoke-ai).
+Original portions of the software are Copyright (c) 2022-23
+by [The InvokeAI Team](https://github.com/invoke-ai).
 
 ## :octicons-book-24: Further Reading
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -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

@@ -148,13 +148,13 @@ manager, please follow these steps:
     === "CUDA (NVidia)"
 
         ```bash
-        pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+        pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
         ```
 
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -315,7 +315,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"

docs/installation/050_INSTALLING_MODELS.md

@@ -50,7 +50,7 @@ subset that are currently installed are found in
 |stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
 |sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
 |stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
-|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-inpainting|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-inpainting |
 |analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
 |deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
 |d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |
@@ -211,26 +211,6 @@ description for the model, whether to make this the default model that
 is loaded at InvokeAI startup time, and whether to replace its
 VAE. Generally the answer to the latter question is "no".
 
-### Specifying a configuration file for legacy checkpoints
-
-Some checkpoint files come with instructions to use a specific .yaml
-configuration file. For InvokeAI load this file correctly, please put
-the config file in the same directory as the corresponding `.ckpt` or
-`.safetensors` file and make sure the file has the same basename as
-the weights file. Here is an example:
-
-```bash
-wonderful-model-v2.ckpt
-wonderful-model-v2.yaml
-```
-
-Similarly, to use a custom VAE, name the VAE like this:
-
-```bash
-wonderful-model-v2.vae.pt
-```
-
-
 ### Converting legacy models into `diffusers`
 
 The CLI `!convert_model` will convert a `.safetensors` or `.ckpt`

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -24,7 +24,7 @@ You need to have opencv installed so that pypatchmatch can be built:
 brew install opencv
 ```
 
-The next time you start `invoke`, after sucesfully installing opencv, pypatchmatch will be built.
+The next time you start `invoke`, after successfully installing opencv, pypatchmatch will be built.
 
 ## Linux
 
@@ -56,7 +56,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 5. Confirm that pypatchmatch is installed. At the command-line prompt enter
    `python`, and then at the `>>>` line type
-   `from patchmatch import patch_match`: It should look like the follwing:
+   `from patchmatch import patch_match`: It should look like the following:
 
     ```py
     Python 3.9.5 (default, Nov 23 2021, 15:27:38)
@@ -108,4 +108,4 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 [**Next, Follow Steps 4-6 from the Debian Section above**](#linux)
 
-If you see no errors, then you're ready to go!
+If you see no errors you're ready to go!

docs/requirements-mkdocs.txt

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

installer/create_installer.sh

@@ -11,10 +11,10 @@ if [[ -v "VIRTUAL_ENV" ]]; then
     exit -1
 fi
 
-VERSION=$(cd ..; python -c "from ldm.invoke import __version__ as version; print(version)")
+VERSION=$(cd ..; python -c "from invokeai.version import __version__ as version; print(version)")
 PATCH=""
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v2.3-latest"
+LATEST_TAG="v3.0-latest"
 
 echo Building installer for version $VERSION
 echo "Be certain that you're in the 'installer' directory before continuing."

installer/lib/installer.py

@@ -241,17 +241,13 @@ class InvokeAiInstance:
 
         from plumbum import FG, local
 
-        # Note that we're installing pinned versions of torch and
-        # torchvision here, which may not correspond to what is
-        # in pyproject.toml. This is a hack to prevent torch 2.0 from
-        # being installed and immediately uninstalled and replaced with 1.13
         pip = local[self.pip]
 
         (
             pip[
                 "install",
                 "--require-virtualenv",
-                "torch~=1.13.1",
+                "torch~=2.0.0",
                 "torchvision>=0.14.1",
                 "--force-reinstall",
                 "--find-links" if find_links is not None else None,
@@ -295,7 +291,7 @@ class InvokeAiInstance:
                     src = Path(__file__).parents[1].expanduser().resolve()
                     # if the above directory contains one of these files, we'll do a source install
                     next(src.glob("pyproject.toml"))
-                    next(src.glob("ldm"))
+                    next(src.glob("invokeai"))
                 except StopIteration:
                     print("Unable to find a wheel or perform a source install. Giving up.")
 
@@ -346,14 +342,14 @@ class InvokeAiInstance:
 
         introduction()
 
-        from ldm.invoke.config import invokeai_configure
+        from invokeai.frontend.install import invokeai_configure
 
         # NOTE: currently the config script does its own arg parsing! this means the command-line switches
         # from the installer will also automatically propagate down to the config script.
         # this may change in the future with config refactoring!
         succeeded = False
         try:
-            invokeai_configure.main()
+            invokeai_configure()
             succeeded = True
         except requests.exceptions.ConnectionError as e:
             print(f'\nA network error was encountered during configuration and download: {str(e)}')
@@ -383,9 +379,6 @@ class InvokeAiInstance:
             shutil.copy(src, dest)
             os.chmod(dest, 0o0755)
 
-        if OS == "Linux":
-            shutil.copy(Path(__file__).parent / '..' / "templates" / "dialogrc", self.runtime / '.dialogrc')
-
     def update(self):
         pass
 
@@ -463,7 +456,7 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.2"
+            url = "https://download.pytorch.org/whl/rocm5.4.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 

installer/templates/dialogrc

@@ -1,27 +0,0 @@
-# Screen 
-use_shadow = OFF
-use_colors = ON
-screen_color = (BLACK, BLACK, ON)
-
-# Box 
-dialog_color = (YELLOW, BLACK , ON) 
-title_color = (YELLOW, BLACK, ON) 
-border_color = (YELLOW, BLACK, OFF) 
-border2_color = (YELLOW, BLACK, OFF) 
-
-# Button 
-button_active_color = (RED, BLACK, OFF) 
-button_inactive_color = (YELLOW, BLACK, OFF) 
-button_label_active_color = (YELLOW,BLACK,ON) 
-button_label_inactive_color = (YELLOW,BLACK,ON)
- 
-# Menu box 
-menubox_color = (BLACK, BLACK, ON) 
-menubox_border_color = (YELLOW, BLACK, OFF) 
-menubox_border2_color = (YELLOW, BLACK, OFF) 
-
-# Menu window 
-item_color = (YELLOW, BLACK, OFF) 
-item_selected_color = (BLACK, YELLOW, OFF) 
-tag_key_color = (YELLOW, BLACK, OFF) 
-tag_key_selected_color = (BLACK, YELLOW, OFF)

installer/templates/invoke.sh.in

@@ -1,10 +1,5 @@
 #!/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,
@@ -16,168 +11,85 @@
 
 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="$scriptdir"
-PARAMS=$@
 
-# 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 "$PARAMS" | sed 's/--no-tui//')
-            break
-        fi
-    done
-else
-    tui=false
-fi
-
-# Set required env var for torch on mac MPS
+# set required env var for torch on mac MPS
 if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-# 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 "Generate images 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\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"
-        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
-    clear
-}
-
-# Dialog-based TUI for launcing Invoke functions
-do_dialog() {
-    options=(
-        1 "Generate images with a browser-based interface"
-        2 "Generate images 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"
-        8 "Open the developer console"
-        9 "Update InvokeAI")
-
-    choice=$(dialog --clear \
-        --backtitle "\Zb\Zu\Z3InvokeAI" \
-        --colors \
-        --title "What would you like to run?" \
-        --ok-label "Run" \
-        --cancel-label "Exit" \
-        --help-button \
-        --help-label "CLI Help" \
-        --menu "Select an option:" \
-        0 0 0 \
-        "${options[@]}" \
-        2>&1 >/dev/tty) || clear
-    do_choice "$choice"
-    clear
-}
-
-# Command-line interface for launching Invoke functions
-do_line_input() {
-    clear
-    printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
-    printf "Do you want to generate images using the\n"
-    printf "1: Browser-based UI\n"
-    printf "2: Command-line interface\n"
-    printf "3: Run textual inversion training\n"
-    printf "4: Merge models (diffusers type only)\n"
-    printf "5: Download and install models\n"
-    printf "6: Change InvokeAI startup options\n"
-    printf "7: Re-run the configure script to fix a broken install\n"
-    printf "8: Open the developer console\n"
-    printf "9: Update InvokeAI\n"
-    printf "10: Command-line help\n"
-    printf "Q: Quit\n\n"
-    read -p "Please enter 1-10, Q: [1] " yn
-    choice=${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 $tui; then
-            # .dialogrc must be located in the same directory as the invoke.sh script
-            export DIALOGRC="./.dialogrc"
-            do_dialog
-        else
-            do_line_input
-        fi
-    done
+  while true
+  do
+    echo "Do you want to generate images using the"
+    echo "1. command-line interface"
+    echo "2. browser-based UI"
+    echo "3. run textual inversion training"
+    echo "4. merge models (diffusers type only)"
+    echo "5. download and install models"
+    echo "6. change InvokeAI startup options"
+    echo "7. re-run the configure script to fix a broken install"
+    echo "8. open the developer console"
+    echo "9. update InvokeAI"
+    echo "10. command-line help"
+    echo "Q - Quit"
+    echo ""
+    read -p "Please enter 1-10, Q: [2] " yn
+    choice=${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;;
+    esac
+ done
 else # in developer console
     python --version
-    printf "Press ^D to exit\n"
+    echo "Press ^D to exit"
     export PS1="(InvokeAI) \u@\h \w> "
 fi

invokeai/README

@@ -1,3 +1,11 @@
-After version 2.3 is released, the ldm/invoke modules will be migrated to this location
-so that we have a proper invokeai distribution. Currently it is only being used for
-data files.
+Organization of the source tree:
+
+app -- Home of nodes invocations and services
+assets -- Images and other data files used by InvokeAI
+backend -- Non-user facing libraries, including the rendering
+	core.
+configs -- Configuration files used at install and run times
+frontend -- User-facing scripts, including the CLI and the WebUI
+version -- Current InvokeAI version string, stored
+	in version/invokeai_version.py
+	

invokeai/app/api/dependencies.py

@@ -0,0 +1,88 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import os
+
+import invokeai.backend.util.logging as logger
+from typing import types
+
+from ..services.default_graphs import create_system_graphs
+from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+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.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.metadata import PngMetadataService
+from .events import FastAPIEventService
+
+
+# TODO: is there a better way to achieve this?
+def check_internet() -> bool:
+    """
+    Return true if the internet is reachable.
+    It does this by pinging huggingface.co.
+    """
+    import urllib.request
+
+    host = "http://huggingface.co"
+    try:
+        urllib.request.urlopen(host, timeout=1)
+        return True
+    except:
+        return False
+
+
+class ApiDependencies:
+    """Contains and initializes all dependencies for the API"""
+
+    invoker: Invoker = None
+
+    def initialize(config, event_handler_id: int, logger: types.ModuleType=logger):
+        logger.info(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)
+
+        # TODO: build a file/path manager?
+        db_location = os.path.join(output_folder, "invokeai.db")
+
+        services = InvocationServices(
+            model_manager=get_model_manager(config,logger),
+            events=events,
+            latents=latents,
+            images=images,
+            metadata=metadata,
+            queue=MemoryInvocationQueue(),
+            graph_library=SqliteItemStorage[LibraryGraph](
+                filename=db_location, table_name="graphs"
+            ),
+            graph_execution_manager=SqliteItemStorage[GraphExecutionState](
+                filename=db_location, table_name="graph_executions"
+            ),
+            processor=DefaultInvocationProcessor(),
+            restoration=RestorationServices(config,logger),
+            configuration=config,
+            logger=logger,
+        )
+
+        create_system_graphs(services.graph_library)
+
+        ApiDependencies.invoker = Invoker(services)
+
+    @staticmethod
+    def shutdown():
+        if ApiDependencies.invoker:
+            ApiDependencies.invoker.stop()

invokeai/app/api/events.py

@@ -0,0 +1,52 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import asyncio
+import threading
+from queue import Empty, Queue
+from typing import Any
+
+from fastapi_events.dispatcher import dispatch
+
+from ..services.events import EventServiceBase
+
+
+class FastAPIEventService(EventServiceBase):
+    event_handler_id: int
+    __queue: Queue
+    __stop_event: threading.Event
+
+    def __init__(self, event_handler_id: int) -> None:
+        self.event_handler_id = event_handler_id
+        self.__queue = Queue()
+        self.__stop_event = threading.Event()
+        asyncio.create_task(self.__dispatch_from_queue(stop_event=self.__stop_event))
+
+        super().__init__()
+
+    def stop(self, *args, **kwargs):
+        self.__stop_event.set()
+        self.__queue.put(None)
+
+    def dispatch(self, event_name: str, payload: Any) -> None:
+        self.__queue.put(dict(event_name=event_name, payload=payload))
+
+    async def __dispatch_from_queue(self, stop_event: threading.Event):
+        """Get events on from the queue and dispatch them, from the correct thread"""
+        while not stop_event.is_set():
+            try:
+                event = self.__queue.get(block=False)
+                if not event:  # Probably stopping
+                    continue
+
+                dispatch(
+                    event.get("event_name"),
+                    payload=event.get("payload"),
+                    middleware_id=self.event_handler_id,
+                )
+
+            except Empty:
+                await asyncio.sleep(0.1)
+                pass
+
+            except asyncio.CancelledError as e:
+                raise e  # Raise a proper error

invokeai/app/api/models/images.py

@@ -0,0 +1,40 @@
+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")
+
+
+class SavedImage(BaseModel):
+    image_name: str = Field(description="The name of the saved image")
+    thumbnail_name: str = Field(description="The name of the saved thumbnail")
+    created: int = Field(description="The created timestamp of the saved image")

invokeai/app/api/routers/images.py

@@ -0,0 +1,148 @@
+# 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 fastapi import Body, HTTPException, Path, Query, Request, UploadFile
+from fastapi.responses import FileResponse, Response
+from fastapi.routing import APIRouter
+from PIL import Image
+from invokeai.app.api.models.images import (
+    ImageResponse,
+    ImageResponseMetadata,
+)
+from invokeai.app.services.item_storage import PaginatedResults
+
+from ...services.image_storage import ImageType
+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:
+    """Gets an image"""
+
+    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.delete("/{image_type}/{image_name}", operation_id="delete_image")
+async def delete_image(
+    image_type: ImageType = Path(description="The type of image to delete"),
+    image_name: str = Path(description="The name of the image to delete"),
+) -> None:
+    """Deletes an image and its thumbnail"""
+
+    ApiDependencies.invoker.services.images.delete(
+        image_type=image_type, image_name=image_name
+    )
+
+
+@images_router.get(
+    "/{thumbnail_type}/thumbnails/{thumbnail_name}", operation_id="get_thumbnail"
+)
+async def get_thumbnail(
+    thumbnail_type: ImageType = Path(description="The type of thumbnail to get"),
+    thumbnail_name: str = Path(description="The name of the thumbnail to get"),
+) -> FileResponse | Response:
+    """Gets a thumbnail"""
+
+    path = ApiDependencies.invoker.services.images.get_path(
+        image_type=thumbnail_type, image_name=thumbnail_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/",
+    operation_id="upload_image",
+    responses={
+        201: {
+            "description": "The image was uploaded successfully",
+            "model": ImageResponse,
+        },
+        415: {"description": "Image upload failed"},
+    },
+    status_code=201,
+)
+async def upload_image(
+    file: UploadFile, image_type: ImageType, request: Request, response: Response
+) -> ImageResponse:
+    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))
+    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"
+
+    saved_image = ApiDependencies.invoker.services.images.save(
+        image_type, filename, img
+    )
+
+    invokeai_metadata = ApiDependencies.invoker.services.metadata.get_metadata(img)
+
+    image_url = ApiDependencies.invoker.services.images.get_uri(
+        image_type, saved_image.image_name
+    )
+
+    thumbnail_url = ApiDependencies.invoker.services.images.get_uri(
+        image_type, saved_image.image_name, True
+    )
+
+    res = ImageResponse(
+        image_type=image_type,
+        image_name=saved_image.image_name,
+        image_url=image_url,
+        thumbnail_url=thumbnail_url,
+        metadata=ImageResponseMetadata(
+            created=saved_image.created,
+            width=img.width,
+            height=img.height,
+            invokeai=invokeai_metadata,
+        ),
+    )
+
+    response.status_code = 201
+    response.headers["Location"] = image_url
+
+    return res
+
+
+@images_router.get(
+    "/",
+    operation_id="list_images",
+    responses={200: {"model": PaginatedResults[ImageResponse]}},
+)
+async def list_images(
+    image_type: ImageType = Query(
+        default=ImageType.RESULT, description="The type of images to get"
+    ),
+    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]:
+    """Gets a list of images"""
+    result = ApiDependencies.invoker.services.images.list(image_type, page, per_page)
+    return result

invokeai/app/api/routers/models.py

@@ -0,0 +1,335 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and Kent Keirsey (https://github.com/hipsterusername)
+
+import shutil
+import os
+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 ..dependencies import ApiDependencies
+
+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")
+    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")
+
+class ModelsList(BaseModel):
+    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
+
+
+@models_router.get(
+    "/",
+    operation_id="list_models",
+    responses={200: {"model": ModelsList }},
+)
+async def list_models() -> ModelsList:
+    """Gets a list of models"""
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
+    models = parse_obj_as(ModelsList, { "models": models_raw })
+    return models
+
+
+@models_router.post(
+    "/",
+    operation_id="update_model",
+    responses={200: {"status": "success"}},
+)
+async def update_model(
+    model_request: CreateModelRequest
+) -> CreateModelResponse:
+    """ 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,
+    )
+
+    return model_response
+
+
+@models_router.delete(
+    "/{model_name}",
+    operation_id="del_model",
+    responses={
+        204: {
+        "description": "Model deleted successfully"
+        }, 
+        404: {
+        "description": "Model not found"
+        }
+    },
+)
+async def delete_model(model_name: str) -> None:
+    """Delete Model"""
+    model_names = ApiDependencies.invoker.services.model_manager.model_names()
+    logger = ApiDependencies.invoker.services.logger
+    model_exists = model_name in model_names
+
+    # check if model exists
+    logger.info(f"Checking for model {model_name}...")
+           
+    if model_exists:
+        logger.info(f"Deleting Model: {model_name}")
+        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
+        logger.info(f"Model Deleted: {model_name}")
+        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
+    
+    else:
+        logger.error(f"Model not found")
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+
+# TODO: Refactor these support functions below to live somewhere more appropriate
+
+def get_model_info(model_name: str):
+    model_info = ApiDependencies.invoker.services.model_manager.model_info(
+        model_name=model_name
+    )
+    if not model_info:
+        raise HTTPException(status_code=404, detail=f"Unable to retrieve model info for '{model_name}'")
+    return model_info
+
+
+def ckpt_validate(model_info: dict, model_name: str):
+    if "weights" not in model_info:
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' is not a valid checkpoint model")
+    
+
+def get_paths(model: ConversionRequest, root: Path) -> tuple:
+    model_info = get_model_info(model.name)
+    ckpt_path = Path(model_info.weights)
+    config_path = Path(model_info.config)
+
+    if not ckpt_path.is_absolute():
+        ckpt_path = Path(root, ckpt_path)
+
+    if config_path and not config_path.is_absolute():
+        config_path = Path(root, config_path)
+
+    return ckpt_path, config_path
+
+
+def get_diffusers_path(convert_request: ConversionRequest, model_name: str) -> Path:
+    if convert_request.save_location == "root":
+        diffusers_path = Path(global_converted_ckpts_dir(), f"{model_name}_diffusers")
+    elif convert_request.save_location == "custom" and convert_request.save_location is not None:
+        diffusers_path = Path(convert_request.save_location, f"{model_name}_diffusers")
+    else:
+        raise ValueError("Invalid save_location value")
+
+    if diffusers_path.exists():
+        shutil.rmtree(diffusers_path)
+
+    return diffusers_path
+
+
+@models_router.post(
+    "/{model_to_convert}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "model_response": "Model converted successfully.",
+        }
+    },
+)
+async def convert_model(convert_request: ConversionRequest) -> ConvertedModelResponse:
+    """Convert Model"""
+
+    opt=Args()
+    args = opt.parse_args()
+
+    # Set the root directory for static files and relative paths
+    args.root_dir = os.path.expanduser(args.root_dir or "..")
+    if not os.path.isabs(args.outdir):
+        args.outdir = os.path.join(args.root_dir, args.outdir)
+
+    # normalize the config directory relative to root
+    if not os.path.isabs(opt.conf):
+        opt.conf = os.path.normpath(os.path.join(Globals.root, opt.conf))
+    model_info = get_model_info(convert_request.name)
+    ckpt_validate(model_info, convert_request.name)
+    ckpt_path, original_config_file = get_paths(convert_request, Globals.root)
+    diffusers_path = get_diffusers_path(convert_request, convert_request.name)
+
+    ApiDependencies.invoker.services.model_manager.convert_and_import(
+        ckpt_path,
+        diffusers_path,
+        model_name=convert_request.name,
+        model_description=model_info.description,
+        vae=None,
+        original_config_file=original_config_file,
+        commit_to_conf=opt.conf,
+    )
+
+    model_info = get_model_info(convert_request.name)
+    convert_response = ConvertedModelResponse(name=f"{convert_request.name}_diffusers", info=model_info)
+    
+    print(f">> Model Converted: {convert_request.name}")
+
+    return convert_response
+
+    
+            # @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:

invokeai/app/api/routers/sessions.py

@@ -0,0 +1,286 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Annotated, List, Optional, Union
+
+from fastapi import Body, HTTPException, Path, Query, Response
+from fastapi.routing import APIRouter
+from pydantic.fields import Field
+
+from ...invocations import *
+from ...invocations.baseinvocation import BaseInvocation
+from ...services.graph import (
+    Edge,
+    EdgeConnection,
+    Graph,
+    GraphExecutionState,
+    NodeAlreadyExecutedError,
+)
+from ...services.item_storage import PaginatedResults
+from ..dependencies import ApiDependencies
+
+session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
+
+
+@session_router.post(
+    "/",
+    operation_id="create_session",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid json"},
+    },
+)
+async def create_session(
+    graph: Optional[Graph] = Body(
+        default=None, description="The graph to initialize the session with"
+    )
+) -> GraphExecutionState:
+    """Creates a new session, optionally initializing it with an invocation graph"""
+    session = ApiDependencies.invoker.create_execution_state(graph)
+    return session
+
+
+@session_router.get(
+    "/",
+    operation_id="list_sessions",
+    responses={200: {"model": PaginatedResults[GraphExecutionState]}},
+)
+async def list_sessions(
+    page: int = Query(default=0, description="The page of results to get"),
+    per_page: int = Query(default=10, description="The number of results per page"),
+    query: str = Query(default="", description="The query string to search for"),
+) -> PaginatedResults[GraphExecutionState]:
+    """Gets a list of sessions, optionally searching"""
+    if query == "":
+        result = ApiDependencies.invoker.services.graph_execution_manager.list(
+            page, per_page
+        )
+    else:
+        result = ApiDependencies.invoker.services.graph_execution_manager.search(
+            query, page, per_page
+        )
+    return result
+
+
+@session_router.get(
+    "/{session_id}",
+    operation_id="get_session",
+    responses={
+        200: {"model": GraphExecutionState},
+        404: {"description": "Session not found"},
+    },
+)
+async def get_session(
+    session_id: str = Path(description="The id of the session to get"),
+) -> GraphExecutionState:
+    """Gets a session"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+    else:
+        return session
+
+
+@session_router.post(
+    "/{session_id}/nodes",
+    operation_id="add_node",
+    responses={
+        200: {"model": str},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def add_node(
+    session_id: str = Path(description="The id of the session"),
+    node: Annotated[
+        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
+    ] = Body(description="The node to add"),
+) -> str:
+    """Adds a node to the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.add_node(node)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session.id
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.put(
+    "/{session_id}/nodes/{node_path}",
+    operation_id="update_node",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def update_node(
+    session_id: str = Path(description="The id of the session"),
+    node_path: str = Path(description="The path to the node in the graph"),
+    node: Annotated[
+        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
+    ] = Body(description="The new node"),
+) -> GraphExecutionState:
+    """Updates a node in the graph and removes all linked edges"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.update_node(node_path, node)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.delete(
+    "/{session_id}/nodes/{node_path}",
+    operation_id="delete_node",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def delete_node(
+    session_id: str = Path(description="The id of the session"),
+    node_path: str = Path(description="The path to the node to delete"),
+) -> GraphExecutionState:
+    """Deletes a node in the graph and removes all linked edges"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.delete_node(node_path)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.post(
+    "/{session_id}/edges",
+    operation_id="add_edge",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def add_edge(
+    session_id: str = Path(description="The id of the session"),
+    edge: Edge = Body(description="The edge to add"),
+) -> GraphExecutionState:
+    """Adds an edge to the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        session.add_edge(edge)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+# TODO: the edge being in the path here is really ugly, find a better solution
+@session_router.delete(
+    "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
+    operation_id="delete_edge",
+    responses={
+        200: {"model": GraphExecutionState},
+        400: {"description": "Invalid node or link"},
+        404: {"description": "Session not found"},
+    },
+)
+async def delete_edge(
+    session_id: str = Path(description="The id of the session"),
+    from_node_id: str = Path(description="The id of the node the edge is coming from"),
+    from_field: str = Path(description="The field of the node the edge is coming from"),
+    to_node_id: str = Path(description="The id of the node the edge is going to"),
+    to_field: str = Path(description="The field of the node the edge is going to"),
+) -> GraphExecutionState:
+    """Deletes an edge from the graph"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    try:
+        edge = Edge(
+            source=EdgeConnection(node_id=from_node_id, field=from_field),
+            destination=EdgeConnection(node_id=to_node_id, field=to_field)
+        )
+        session.delete_edge(edge)
+        ApiDependencies.invoker.services.graph_execution_manager.set(
+            session
+        )  # TODO: can this be done automatically, or add node through an API?
+        return session
+    except NodeAlreadyExecutedError:
+        raise HTTPException(status_code=400)
+    except IndexError:
+        raise HTTPException(status_code=400)
+
+
+@session_router.put(
+    "/{session_id}/invoke",
+    operation_id="invoke_session",
+    responses={
+        200: {"model": None},
+        202: {"description": "The invocation is queued"},
+        400: {"description": "The session has no invocations ready to invoke"},
+        404: {"description": "Session not found"},
+    },
+)
+async def invoke_session(
+    session_id: str = Path(description="The id of the session to invoke"),
+    all: bool = Query(
+        default=False, description="Whether or not to invoke all remaining invocations"
+    ),
+) -> Response:
+    """Invokes a session"""
+    session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
+    if session is None:
+        raise HTTPException(status_code=404)
+
+    if session.is_complete():
+        raise HTTPException(status_code=400)
+
+    ApiDependencies.invoker.invoke(session, invoke_all=all)
+    return Response(status_code=202)
+
+
+@session_router.delete(
+    "/{session_id}/invoke",
+    operation_id="cancel_session_invoke",
+    responses={
+        202: {"description": "The invocation is canceled"}
+    },
+)
+async def cancel_session_invoke(
+    session_id: str = Path(description="The id of the session to cancel"),
+) -> Response:
+    """Invokes a session"""
+    ApiDependencies.invoker.cancel(session_id)
+    return Response(status_code=202)

invokeai/app/api/sockets.py

@@ -0,0 +1,38 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from fastapi import FastAPI
+from fastapi_events.handlers.local import local_handler
+from fastapi_events.typing import Event
+from fastapi_socketio import SocketManager
+
+from ..services.events import EventServiceBase
+
+
+class SocketIO:
+    __sio: SocketManager
+
+    def __init__(self, app: FastAPI):
+        self.__sio = SocketManager(app=app)
+        self.__sio.on("subscribe", handler=self._handle_sub)
+        self.__sio.on("unsubscribe", handler=self._handle_unsub)
+
+        local_handler.register(
+            event_name=EventServiceBase.session_event, _func=self._handle_session_event
+        )
+
+    async def _handle_session_event(self, event: Event):
+        await self.__sio.emit(
+            event=event[1]["event"],
+            data=event[1]["data"],
+            room=event[1]["data"]["graph_execution_state_id"],
+        )
+
+    async def _handle_sub(self, sid, data, *args, **kwargs):
+        if "session" in data:
+            self.__sio.enter_room(sid, data["session"])
+
+        # @app.sio.on('unsubscribe')
+
+    async def _handle_unsub(self, sid, data, *args, **kwargs):
+        if "session" in data:
+            self.__sio.leave_room(sid, data["session"])

invokeai/app/api_app.py

@@ -0,0 +1,153 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+import asyncio
+from inspect import signature
+
+import uvicorn
+import invokeai.backend.util.logging as logger
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
+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 pydantic.schema import schema
+
+from .api.dependencies import ApiDependencies
+from .api.routers import images, sessions, models
+from .api.sockets import SocketIO
+from .invocations.baseinvocation import BaseInvocation
+from .services.config import InvokeAIAppConfig
+
+# Create the app
+# TODO: create this all in a method so configuration/etc. can be passed in?
+app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)
+
+# Add event handler
+event_handler_id: int = id(app)
+app.add_middleware(
+    EventHandlerASGIMiddleware,
+    handlers=[
+        local_handler
+    ],  # TODO: consider doing this in services to support different configurations
+    middleware_id=event_handler_id,
+)
+
+socket_io = SocketIO(app)
+
+# initialize config
+# this is a module global
+app_config = InvokeAIAppConfig()
+
+# Add startup event to load dependencies
+@app.on_event("startup")
+async def startup_event():
+    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=app_config, event_handler_id=event_handler_id, logger=logger
+    )
+
+
+# Shut down threads
+@app.on_event("shutdown")
+async def shutdown_event():
+    ApiDependencies.shutdown()
+
+
+# Include all routers
+# TODO: REMOVE
+# app.include_router(
+#     invocation.invocation_router,
+#     prefix = '/api')
+
+app.include_router(sessions.session_router, prefix="/api")
+
+app.include_router(images.images_router, prefix="/api")
+
+app.include_router(models.models_router, prefix="/api")
+
+
+# Build a custom OpenAPI to include all outputs
+# TODO: can outputs be included on metadata of invocation schemas somehow?
+def custom_openapi():
+    if app.openapi_schema:
+        return app.openapi_schema
+    openapi_schema = get_openapi(
+        title=app.title,
+        description="An API for invoking AI image operations",
+        version="1.0.0",
+        routes=app.routes,
+    )
+
+    # Add all outputs
+    all_invocations = BaseInvocation.get_invocations()
+    output_types = set()
+    output_type_titles = dict()
+    for invoker in all_invocations:
+        output_type = signature(invoker.invoke).return_annotation
+        output_types.add(output_type)
+
+    output_schemas = schema(output_types, ref_prefix="#/components/schemas/")
+    for schema_key, output_schema in output_schemas["definitions"].items():
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
+
+        # TODO: note that we assume the schema_key here is the TYPE.__name__
+        # This could break in some cases, figure out a better way to do it
+        output_type_titles[schema_key] = output_schema["title"]
+
+    # Add a reference to the output type to additionalProperties of the invoker schema
+    for invoker in all_invocations:
+        invoker_name = invoker.__name__
+        output_type = signature(invoker.invoke).return_annotation
+        output_type_title = output_type_titles[output_type.__name__]
+        invoker_schema = openapi_schema["components"]["schemas"][invoker_name]
+        outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
+
+        invoker_schema["output"] = outputs_ref
+
+    app.openapi_schema = openapi_schema
+    return app.openapi_schema
+
+
+app.openapi = custom_openapi
+
+# Override API doc favicons
+app.mount("/static", StaticFiles(directory="static/dream_web"), name="static")
+
+@app.get("/docs", include_in_schema=False)
+def overridden_swagger():
+    return get_swagger_ui_html(
+        openapi_url=app.openapi_url,
+        title=app.title,
+        swagger_favicon_url="/static/favicon.ico",
+    )
+
+
+@app.get("/redoc", include_in_schema=False)
+def overridden_redoc():
+    return get_redoc_html(
+        openapi_url=app.openapi_url,
+        title=app.title,
+        redoc_favicon_url="/static/favicon.ico",
+    )
+
+# Must mount *after* the other routes else it borks em
+app.mount("/", StaticFiles(directory="invokeai/frontend/web/dist", html=True), name="ui")
+
+def invoke_api():
+    # Start our own event loop for eventing usage
+    loop = asyncio.new_event_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

@@ -0,0 +1,303 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from abc import ABC, abstractmethod
+import argparse
+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, Edge
+from ..services.invoker import Invoker
+
+
+def add_field_argument(command_parser, name: str, field, default_override = None):
+    default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+    if get_origin(field.type_) == Literal:
+        allowed_values = get_args(field.type_)
+        allowed_types = set()
+        for val in allowed_values:
+            allowed_types.add(type(val))
+        allowed_types_list = list(allowed_types)
+        field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+        command_parser.add_argument(
+            f"--{name}",
+            dest=name,
+            type=field_type,
+            default=default,
+            choices=allowed_values,
+            help=field.field_info.description,
+        )
+    else:
+        command_parser.add_argument(
+            f"--{name}",
+            dest=name,
+            type=field.type_,
+            default=default,
+            help=field.field_info.description,
+        )
+
+
+def add_parsers(
+    subparsers,
+    commands: list[type],
+    command_field: str = "type",
+    exclude_fields: list[str] = ["id", "type"],
+    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    ):
+    """Adds parsers for each command to the subparsers"""
+
+    # Create subparsers for each command
+    for command in commands:
+        hints = get_type_hints(command)
+        cmd_name = get_args(hints[command_field])[0]
+        command_parser = subparsers.add_parser(cmd_name, help=command.__doc__)
+
+        if add_arguments is not None:
+            add_arguments(command_parser)
+
+        # Convert all fields to arguments
+        fields = command.__fields__ # type: ignore
+        for name, field in fields.items():
+            if name in exclude_fields:
+                continue
+
+            add_field_argument(command_parser, name, field)
+
+
+def add_graph_parsers(
+    subparsers,
+    graphs: list[LibraryGraph],
+    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+):
+    for graph in graphs:
+        command_parser = subparsers.add_parser(graph.name, help=graph.description)
+        
+        if add_arguments is not None:
+            add_arguments(command_parser)
+
+        # Add arguments for inputs
+        for exposed_input in graph.exposed_inputs:
+            node = graph.graph.get_node(exposed_input.node_path)
+            field = node.__fields__[exposed_input.field]
+            default_override = getattr(node, exposed_input.field)
+            add_field_argument(command_parser, exposed_input.alias, field, default_override)
+
+
+class CliContext:
+    invoker: Invoker
+    session: GraphExecutionState
+    parser: argparse.ArgumentParser
+    defaults: dict[str, Any]
+    graph_nodes: dict[str, str]
+    nodes_added: list[str]
+
+    def __init__(self, invoker: Invoker, session: GraphExecutionState, parser: argparse.ArgumentParser):
+        self.invoker = invoker
+        self.session = session
+        self.parser = parser
+        self.defaults = dict()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
+
+    def get_session(self):
+        self.session = self.invoker.services.graph_execution_manager.get(self.session.id)
+        return self.session
+
+    def reset(self):
+        self.session = self.invoker.create_execution_state()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
+        # Leave defaults unchanged
+
+    def add_node(self, node: BaseInvocation):
+        self.get_session()
+        self.session.graph.add_node(node)
+        self.nodes_added.append(node.id)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
+    def add_edge(self, edge: Edge):
+        self.get_session()
+        self.session.add_edge(edge)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
+
+class ExitCli(Exception):
+    """Exception to exit the CLI"""
+    pass
+
+
+class BaseCommand(ABC, BaseModel):
+    """A CLI command"""
+
+    # All commands must include a type name like this:
+    # type: Literal['your_command_name'] = 'your_command_name'
+
+    @classmethod
+    def get_all_subclasses(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return subclasses
+
+    @classmethod
+    def get_commands(cls):
+        return tuple(BaseCommand.get_all_subclasses())
+
+    @classmethod
+    def get_commands_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),BaseCommand.get_all_subclasses()))
+
+    @abstractmethod
+    def run(self, context: CliContext) -> None:
+        """Run the command. Raise ExitCli to exit."""
+        pass
+
+
+class ExitCommand(BaseCommand):
+    """Exits the CLI"""
+    type: Literal['exit'] = 'exit'
+
+    def run(self, context: CliContext) -> None:
+        raise ExitCli()
+
+
+class HelpCommand(BaseCommand):
+    """Shows help"""
+    type: Literal['help'] = 'help'
+
+    def run(self, context: CliContext) -> None:
+        context.parser.print_help()
+
+
+def get_graph_execution_history(
+    graph_execution_state: GraphExecutionState,
+) -> Iterable[str]:
+    """Gets the history of fully-executed invocations for a graph execution"""
+    return (
+        n
+        for n in reversed(graph_execution_state.executed_history)
+        if n in graph_execution_state.graph.nodes
+    )
+
+
+def get_invocation_command(invocation) -> str:
+    fields = invocation.__fields__.items()
+    type_hints = get_type_hints(type(invocation))
+    command = [invocation.type]
+    for name, field in fields:
+        if name in ["id", "type"]:
+            continue
+
+        # TODO: add links
+
+        # Skip image fields when serializing command
+        type_hint = type_hints.get(name) or None
+        if type_hint is ImageField or ImageField in get_args(type_hint):
+            continue
+
+        field_value = getattr(invocation, name)
+        field_default = field.default
+        if field_value != field_default:
+            if type_hint is str or str in get_args(type_hint):
+                command.append(f'--{name} "{field_value}"')
+            else:
+                command.append(f"--{name} {field_value}")
+
+    return " ".join(command)
+
+
+class HistoryCommand(BaseCommand):
+    """Shows the invocation history"""
+    type: Literal['history'] = 'history'
+
+    # Inputs
+    # fmt: off
+    count: int = Field(default=5, gt=0, description="The number of history entries to show")
+    # fmt: on
+
+    def run(self, context: CliContext) -> None:
+        history = list(get_graph_execution_history(context.get_session()))
+        for i in range(min(self.count, len(history))):
+            entry_id = history[-1 - i]
+            entry = context.get_session().graph.get_node(entry_id)
+            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
+
+
+class SetDefaultCommand(BaseCommand):
+    """Sets a default value for a field"""
+    type: Literal['default'] = 'default'
+
+    # Inputs
+    # fmt: off
+    field: str = Field(description="The field to set the default for")
+    value: str = Field(description="The value to set the default to, or None to clear the default")
+    # fmt: on
+
+    def run(self, context: CliContext) -> None:
+        if self.value is None:
+            if self.field in context.defaults:
+                del context.defaults[self.field]
+        else:
+            context.defaults[self.field] = self.value
+
+
+class DrawGraphCommand(BaseCommand):
+    """Debugs a graph"""
+    type: Literal['draw_graph'] = 'draw_graph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
+        plt.axis("off")
+        plt.show()
+
+
+class DrawExecutionGraphCommand(BaseCommand):
+    """Debugs an execution graph"""
+    type: Literal['draw_xgraph'] = 'draw_xgraph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.execution_graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        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

@@ -0,0 +1,169 @@
+"""
+Readline helper functions for cli_app.py
+You may import the global singleton `completer` to get access to the
+completer object.
+"""
+import atexit
+import readline
+import shlex
+
+from pathlib import Path
+from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
+
+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
+
+class Completer(object):
+    
+    def __init__(self, model_manager: ModelManager):
+        self.commands = self.get_commands()
+        self.matches = None
+        self.linebuffer = None
+        self.manager = model_manager
+        return
+
+    def complete(self, text, state):
+        """
+        Complete commands and switches fromm the node CLI command line.
+        Switches are determined in a context-specific manner.
+        """
+
+        buffer = readline.get_line_buffer()
+        if state == 0:
+            options = None
+            try:
+                current_command, current_switch = self.get_current_command(buffer)
+                options = self.get_command_options(current_command, current_switch)
+            except IndexError:
+                pass
+            options = options or list(self.parse_commands().keys())
+            
+            if not text:  # first time
+                self.matches = options
+            else:
+                self.matches = [s for s in options if s and s.startswith(text)]
+
+        try:
+            match = self.matches[state]
+        except IndexError:
+            match = None
+        return match
+
+    @classmethod
+    def get_commands(self)->List[object]:
+        """
+        Return a list of all the client commands and invocations.
+        """
+        return BaseCommand.get_commands() + BaseInvocation.get_invocations()
+
+    def get_current_command(self, buffer: str)->tuple[str, str]:
+        """
+        Parse the readline buffer to find the most recent command and its switch.
+        """
+        if len(buffer)==0:
+            return None, None
+        tokens = shlex.split(buffer)
+        command = None
+        switch = None
+        for t in tokens:
+            if t[0].isalpha():
+                if switch is None:
+                    command = t
+            else:
+                switch = t
+        # don't try to autocomplete switches that are already complete
+        if switch and buffer.endswith(' '):
+            switch=None
+        return command or '', switch or ''
+
+    def parse_commands(self)->Dict[str, List[str]]:
+        """
+        Return a dict in which the keys are the command name
+        and the values are the parameters the command takes.
+        """
+        result = dict()
+        for command in self.commands:
+            hints = get_type_hints(command)
+            name = get_args(hints['type'])[0]
+            result.update({name:hints})
+        return result
+
+    def get_command_options(self, command: str, switch: str)->List[str]:
+        """
+        Return all the parameters that can be passed to the command as
+        command-line switches. Returns None if the command is unrecognized.
+        """
+        parsed_commands = self.parse_commands()
+        if command not in parsed_commands:
+            return None
+        
+        # handle switches in the format "-foo=bar"
+        argument = None
+        if switch and '=' in switch:
+            switch, argument = switch.split('=')
+            
+        parameter = switch.strip('-')
+        if parameter in parsed_commands[command]:
+            if argument is None:
+                return self.get_parameter_options(parameter, parsed_commands[command][parameter])
+            else:
+                return [f"--{parameter}={x}" for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])]
+        else:
+            return [f"--{x}" for x in parsed_commands[command].keys()]
+
+    def get_parameter_options(self, parameter: str, typehint)->List[str]:
+        """
+        Given a parameter type (such as Literal), offers autocompletions.
+        """
+        if get_origin(typehint) == Literal:
+            return get_args(typehint)
+        if parameter == 'model':
+            return self.manager.model_names()
+        
+    def _pre_input_hook(self):
+        if self.linebuffer:
+            readline.insert_text(self.linebuffer)
+            readline.redisplay()
+            self.linebuffer = None
+    
+def set_autocompleter(services: InvocationServices) -> Completer:
+    global completer
+    
+    if completer:
+        return completer
+    
+    completer = Completer(services.model_manager)
+
+    readline.set_completer(completer.complete)
+    # pyreadline3 does not have a set_auto_history() method
+    try:
+        readline.set_auto_history(True)
+    except:
+        pass
+    readline.set_pre_input_hook(completer._pre_input_hook)
+    readline.set_completer_delims(" ")
+    readline.parse_and_bind("tab: complete")
+    readline.parse_and_bind("set print-completions-horizontally off")
+    readline.parse_and_bind("set page-completions on")
+    readline.parse_and_bind("set skip-completed-text on")
+    readline.parse_and_bind("set show-all-if-ambiguous on")
+
+    histfile = Path(services.configuration.root_dir / ".invoke_history")
+    try:
+        readline.read_history_file(histfile)
+        readline.set_history_length(1000)
+    except FileNotFoundError:
+        pass
+    except OSError:  # file likely corrupted
+        newname = f"{histfile}.old"
+        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

@@ -0,0 +1,399 @@
+# 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 pydantic import BaseModel, ValidationError
+from pydantic.fields import Field
+
+
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.metadata import PngMetadataService
+from .services.default_graphs import create_system_graphs
+from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, SortedHelpFormatter
+from .cli.completer import set_autocompleter
+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, 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.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.config import get_invokeai_config
+
+class CliCommand(BaseModel):
+    command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
+
+
+class InvalidArgs(Exception):
+    pass
+
+
+def add_invocation_args(command_parser):
+    # Add linking capability
+    command_parser.add_argument(
+        "--link",
+        "-l",
+        action="append",
+        nargs=3,
+        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
+    )
+
+    command_parser.add_argument(
+        "--link_node",
+        "-ln",
+        action="append",
+        help="A link from all fields in the specified node. Node can be relative to history (e.g. -1)",
+    )
+
+
+def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
+    # Create invocation parser
+    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
+
+    def exit(*args, **kwargs):
+        raise InvalidArgs
+
+    parser.exit = exit
+    subparsers = parser.add_subparsers(dest="type")
+
+    # Create subparsers for each invocation
+    invocations = BaseInvocation.get_all_subclasses()
+    add_parsers(subparsers, invocations, add_arguments=add_invocation_args)
+
+    # Create subparsers for each command
+    commands = BaseCommand.get_all_subclasses()
+    add_parsers(subparsers, commands, exclude_fields=["type"])
+
+    # Create subparsers for exposed CLI graphs
+    # TODO: add a way to identify these graphs
+    text_to_image = services.graph_library.get(default_text_to_image_graph_id)
+    add_graph_parsers(subparsers, [text_to_image], add_arguments=add_invocation_args)
+
+    return parser
+
+
+class NodeField():
+    alias: str
+    node_path: str
+    field: str
+    field_type: type
+
+    def __init__(self, alias: str, node_path: str, field: str, field_type: type):
+        self.alias = alias
+        self.node_path = node_path
+        self.field = field
+        self.field_type = field_type
+
+
+def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str,NodeField]:
+    return {k:NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
+
+
+def get_node_input_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_input = next(e for e in graph.exposed_inputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_input.node_path))
+    return NodeField(alias=exposed_input.alias, node_path=f'{node_id}.{exposed_input.node_path}', field=exposed_input.field, field_type=get_type_hints(node_type)[exposed_input.field])
+
+
+def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_output = next(e for e in graph.exposed_outputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_output.node_path))
+    node_output_type = node_type.get_output_type()
+    return NodeField(alias=exposed_output.alias, node_path=f'{node_id}.{exposed_output.node_path}', field=exposed_output.field, field_type=get_type_hints(node_output_type)[exposed_output.field])
+
+
+def get_node_inputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the inputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_input_field(graph, e.alias, invocation.id) for e in graph.exposed_inputs}
+
+
+def get_node_outputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the outputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type.get_output_type()), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_output_field(graph, e.alias, invocation.id) for e in graph.exposed_outputs}
+
+
+def generate_matching_edges(
+    a: BaseInvocation, b: BaseInvocation, context: CliContext
+) -> list[Edge]:
+    """Generates all possible edges between two invocations"""
+    afields = get_node_outputs(a, context)
+    bfields = get_node_inputs(b, context)
+
+    matching_fields = set(afields.keys()).intersection(bfields.keys())
+
+    # Remove invalid fields
+    invalid_fields = set(["type", "id"])
+    matching_fields = matching_fields.difference(invalid_fields)
+
+    # Validate types
+    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)]
+
+    edges = [
+        Edge(
+            source=EdgeConnection(node_id=afields[alias].node_path, field=afields[alias].field),
+            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field)
+        )
+        for alias in matching_fields
+    ]
+    return edges
+
+
+class SessionError(Exception):
+    """Raised when a session error has occurred"""
+    pass
+
+
+def invoke_all(context: CliContext):
+    """Runs all invocations in the specified session"""
+    context.invoker.invoke(context.session, invoke_all=True)
+    while not context.get_session().is_complete():
+        # Wait some time
+        time.sleep(0.1)
+
+    # Print any errors
+    if context.session.has_error():
+        for n in context.session.errors:
+            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():
+    # this gets the basic configuration
+    config = get_invokeai_config()
+
+    # 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
+
+    # 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 = get_model_manager(config,logger=logger)
+    
+    events = EventServiceBase()
+    output_folder = config.output_path
+    metadata = PngMetadataService()
+
+    # TODO: build a file/path manager?
+    db_location = os.path.join(output_folder, "invokeai.db")
+
+    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,
+        queue=MemoryInvocationQueue(),
+        graph_library=SqliteItemStorage[LibraryGraph](
+            filename=db_location, table_name="graphs"
+        ),
+        graph_execution_manager=SqliteItemStorage[GraphExecutionState](
+            filename=db_location, table_name="graph_executions"
+        ),
+        processor=DefaultInvocationProcessor(),
+        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])
+
+    invoker = Invoker(services)
+    session: GraphExecutionState = invoker.create_execution_state()
+    parser = get_command_parser(services)
+
+    re_negid = re.compile('^-[0-9]+$')
+
+    # Uncomment to print out previous sessions at startup
+    # print(services.session_manager.list())
+
+    context = CliContext(invoker, session, parser)
+    set_autocompleter(services)
+
+    command_line_args_exist = len(invocation_commands) > 0
+    done = False
+    
+    while not done:
+        try:
+            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
+
+        try:
+            # Refresh the state of the session
+            #history = list(get_graph_execution_history(context.session))
+            history = list(reversed(context.nodes_added))
+
+            # Split the command for piping
+            cmds = cmd_input.split("|")
+            start_id = len(context.nodes_added)
+            current_id = start_id
+            new_invocations = list()
+            for cmd in cmds:
+                if cmd is None or cmd.strip() == "":
+                    raise InvalidArgs("Empty command")
+
+                # Parse args to create invocation
+                args = vars(context.parser.parse_args(shlex.split(cmd.strip())))
+
+                # Override defaults
+                for field_name, field_default in context.defaults.items():
+                    if field_name in args:
+                        args[field_name] = field_default
+
+                # Parse invocation
+                command: CliCommand = None # type:ignore
+                system_graph: LibraryGraph|None = 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))
+                    for exposed_input in system_graph.exposed_inputs:
+                        if exposed_input.alias in args:
+                            node = invocation.graph.get_node(exposed_input.node_path)
+                            field = exposed_input.field
+                            setattr(node, field, args[exposed_input.alias])
+                    command = CliCommand(command = invocation)
+                    context.graph_nodes[invocation.id] = system_graph.id
+                else:
+                    args["id"] = current_id
+                    command = CliCommand(command=args)
+
+                if command is None:
+                    continue
+
+                # Run any CLI commands immediately
+                if isinstance(command.command, BaseCommand):
+                    # Invoke all current nodes to preserve operation order
+                    invoke_all(context)
+
+                    # Run the command
+                    command.command.run(context)
+                    continue
+
+                # TODO: handle linking with library graphs
+                # Pipe previous command output (if there was a previous command)
+                edges: list[Edge] = list()
+                if len(history) > 0 or current_id != start_id:
+                    from_id = (
+                        history[0] if current_id == start_id else str(current_id - 1)
+                    )
+                    from_node = (
+                        next(filter(lambda n: n[0].id == from_id, new_invocations))[0]
+                        if current_id != start_id
+                        else context.session.graph.get_node(from_id)
+                    )
+                    matching_edges = generate_matching_edges(
+                        from_node, command.command, context
+                    )
+                    edges.extend(matching_edges)
+
+                # Parse provided links
+                if "link_node" in args and args["link_node"]:
+                    for link in args["link_node"]:
+                        node_id = link
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        link_node = context.session.graph.get_node(node_id)
+                        matching_edges = generate_matching_edges(
+                            link_node, command.command, context
+                        )
+                        matching_destinations = [e.destination for e in matching_edges]
+                        edges = [e for e in edges if e.destination not in matching_destinations]
+                        edges.extend(matching_edges)
+
+                if "link" in args and args["link"]:
+                    for link in args["link"]:
+                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
+
+                        node_id = link[0]
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        # TODO: handle missing input/output
+                        node_output = get_node_outputs(context.session.graph.get_node(node_id), context)[link[1]]
+                        node_input = get_node_inputs(command.command, context)[link[2]]
+
+                        edges.append(
+                            Edge(
+                                source=EdgeConnection(node_id=node_output.node_path, field=node_output.field),
+                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field)
+                            )
+                        )
+
+                new_invocations.append((command.command, edges))
+
+                current_id = current_id + 1
+
+                # Add the node to the session
+                context.add_node(command.command)
+                for edge in edges:
+                    print(edge)
+                    context.add_edge(edge)
+
+            # Execute all remaining nodes
+            invoke_all(context)
+
+        except InvalidArgs:
+            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
+            invoker.services.logger.warning("Session error: creating a new session")
+            context.reset()
+
+        except ExitCli:
+            break
+
+        except SystemExit:
+            continue
+
+    invoker.stop()
+
+
+if __name__ == "__main__":
+    invoke_cli()

invokeai/app/invocations/__init__.py

@@ -0,0 +1,12 @@
+import os
+
+__all__ = []
+
+dirname = os.path.dirname(os.path.abspath(__file__))
+for f in os.listdir(dirname):
+    if (
+        f != "__init__.py"
+        and os.path.isfile("%s/%s" % (dirname, f))
+        and f[-3:] == ".py"
+    ):
+        __all__.append(f[:-3])

invokeai/app/invocations/baseinvocation.py

@@ -0,0 +1,131 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from abc import ABC, abstractmethod
+from inspect import signature
+from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict
+
+from pydantic import BaseModel, Field
+
+from ..services.invocation_services import InvocationServices
+
+
+class InvocationContext:
+    services: InvocationServices
+    graph_execution_state_id: str
+
+    def __init__(self, services: InvocationServices, graph_execution_state_id: str):
+        self.services = services
+        self.graph_execution_state_id = graph_execution_state_id
+
+
+class BaseInvocationOutput(BaseModel):
+    """Base class for all invocation outputs"""
+
+    # All outputs must include a type name like this:
+    # type: Literal['your_output_name']
+
+    @classmethod
+    def get_all_subclasses_tuple(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return tuple(subclasses)
+
+
+class BaseInvocation(ABC, BaseModel):
+    """A node to process inputs and produce outputs.
+    May use dependency injection in __init__ to receive providers.
+    """
+
+    # All invocations must include a type name like this:
+    # type: Literal['your_output_name']
+
+    @classmethod
+    def get_all_subclasses(cls):
+        subclasses = []
+        toprocess = [cls]
+        while len(toprocess) > 0:
+            next = toprocess.pop(0)
+            next_subclasses = next.__subclasses__()
+            subclasses.extend(next_subclasses)
+            toprocess.extend(next_subclasses)
+        return subclasses
+
+    @classmethod
+    def get_invocations(cls):
+        return tuple(BaseInvocation.get_all_subclasses())
+
+    @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()))
+    
+    @classmethod
+    def get_output_type(cls):
+        return signature(cls.invoke).return_annotation
+
+    @abstractmethod
+    def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
+        """Invoke with provided context and return outputs."""
+        pass
+    
+    #fmt: off
+    id: str = Field(description="The id of this node. Must be unique among all nodes.")
+    #fmt: on
+
+
+# TODO: figure out a better way to provide these hints
+# TODO: when we can upgrade to python 3.11, we can use the`NotRequired` type instead of `total=False`
+class UIConfig(TypedDict, total=False):
+    type_hints: Dict[
+        str,
+        Literal[
+            "integer",
+            "float",
+            "boolean",
+            "string",
+            "enum",
+            "image",
+            "latents",
+            "model",
+        ],
+    ]
+    tags: List[str]
+    title: str
+
+class CustomisedSchemaExtra(TypedDict):
+    ui: UIConfig
+
+
+class InvocationConfig(BaseModel.Config):
+    """Customizes pydantic's BaseModel.Config class for use by Invocations.
+
+    Provide `schema_extra` a `ui` dict to add hints for generated UIs.
+
+    `tags`
+    - A list of strings, used to categorise invocations.
+
+    `type_hints`
+    - A dict of field types which override the types in the invocation definition.
+    - Each key should be the name of one of the invocation's fields.
+    - Each value should be one of the valid types:
+      - `integer`, `float`, `boolean`, `string`, `enum`, `image`, `latents`, `model`
+
+    ```python
+    class Config(InvocationConfig):
+      schema_extra = {
+          "ui": {
+              "tags": ["stable-diffusion", "image"],
+              "type_hints": {
+                  "initial_image": "image",
+              },
+          },
+      }
+    ```
+    """
+
+    schema_extra: CustomisedSchemaExtra

invokeai/app/invocations/collections.py

@@ -0,0 +1,64 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Optional
+
+import numpy as np
+from pydantic import Field
+
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationContext,
+    BaseInvocationOutput,
+)
+
+
+class IntCollectionOutput(BaseInvocationOutput):
+    """A collection of integers"""
+
+    type: Literal["int_collection"] = "int_collection"
+
+    # Outputs
+    collection: list[int] = Field(default=[], description="The int collection")
+
+
+class RangeInvocation(BaseInvocation):
+    """Creates a range"""
+
+    type: Literal["range"] = "range"
+
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    stop: int = Field(default=10, description="The stop of the range")
+    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.stop, self.step))
+        )
+
+
+class RandomRangeInvocation(BaseInvocation):
+    """Creates a collection of random numbers"""
+
+    type: Literal["random_range"] = "random_range"
+
+    # Inputs
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    size: int = Field(default=1, description="The number of values to generate")
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed for the RNG (omit for random)",
+        default_factory=get_random_seed,
+    )
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        rng = np.random.default_rng(self.seed)
+        return IntCollectionOutput(
+            collection=list(rng.integers(low=self.low, high=self.high, size=self.size))
+        )

invokeai/app/invocations/compel.py

@@ -0,0 +1,244 @@
+from typing import Literal, Optional, Union
+from pydantic import BaseModel, Field
+
+from invokeai.app.invocations.util.choose_model import choose_model
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from ...backend.stable_diffusion.textual_inversion_manager import TextualInversionManager
+
+from compel import Compel
+from compel.prompt_parser import (
+    Blend,
+    CrossAttentionControlSubstitute,
+    FlattenedPrompt,
+    Fragment,
+)
+
+
+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")
+    model: str = Field(default="", description="Model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+
+        # TODO: load without model
+        model = choose_model(context.services.model_manager, self.model)
+        pipeline = model["model"]
+        tokenizer = pipeline.tokenizer
+        text_encoder = pipeline.text_encoder
+
+        # TODO: global? input?
+        #use_full_precision = precision == "float32" or precision == "autocast"
+        #use_full_precision = False
+
+        # TODO: redo TI when separate model loding implemented
+        #textual_inversion_manager = TextualInversionManager(
+        #    tokenizer=tokenizer,
+        #    text_encoder=text_encoder,
+        #    full_precision=use_full_precision,
+        #)
+
+        def load_huggingface_concepts(concepts: list[str]):
+            pipeline.textual_inversion_manager.load_huggingface_concepts(concepts)
+
+        # apply the concepts library to the prompt
+        prompt_str = pipeline.textual_inversion_manager.hf_concepts_library.replace_concepts_with_triggers(
+            self.prompt,
+            lambda concepts: load_huggingface_concepts(concepts),
+            pipeline.textual_inversion_manager.get_all_trigger_strings(),
+        )
+
+        # lazy-load any deferred textual inversions.
+        # this might take a couple of seconds the first time a textual inversion is used.
+        pipeline.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(
+            prompt_str
+        )
+
+        compel = Compel(
+            tokenizer=tokenizer,
+            text_encoder=text_encoder,
+            textual_inversion_manager=pipeline.textual_inversion_manager,
+            dtype_for_device_getter=torch_dtype,
+            truncate_long_prompts=True, # TODO:
+        )
+
+        # TODO: support legacy blend?
+
+        conjunction = Compel.parse_prompt_string(prompt_str)
+        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, prompt),
+            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.set(conditioning_name, (c, ec))
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+def get_max_token_count(
+    tokenizer, prompt: Union[FlattenedPrompt, Blend], truncate_if_too_long=False
+) -> int:
+    if type(prompt) is Blend:
+        blend: Blend = prompt
+        return max(
+            [
+                get_max_token_count(tokenizer, c, truncate_if_too_long)
+                for c in blend.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
+) -> [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_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/cv.py

@@ -0,0 +1,69 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+
+import cv2 as cv
+import numpy
+from PIL import Image, ImageOps
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ImageField, ImageType
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
+
+
+class CvInvocationConfig(BaseModel):
+    """Helper class to provide all OpenCV invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["cv", "image"],
+            },
+        }
+
+
+class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
+    """Simple inpaint using opencv."""
+    #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
+
+    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)
+
+        # 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))
+
+        # Inpaint
+        cv_inpainted = cv.inpaint(cv_image, cv_mask, 3, cv.INPAINT_TELEA)
+
+        # Convert back to Pillow
+        # 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
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+        
+        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

@@ -0,0 +1,293 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from functools import partial
+from typing import Literal, Optional, Union, get_args
+
+import numpy as np
+from torch import Tensor
+
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ColorField, ImageField, ImageType
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.generator.inpaint import infill_methods
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
+from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+from ...backend.stable_diffusion import PipelineIntermediateState
+from ..util.step_callback import stable_diffusion_step_callback
+
+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"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+                "type_hints": {
+                    "model": "model",
+                },
+            },
+        }
+
+
+# Text to image
+class TextToImageInvocation(BaseInvocation, SDImageInvocation):
+    """Generates an image using text2img."""
+
+    type: Literal["txt2img"] = "txt2img"
+
+    # 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(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="lms", description="The scheduler to use" )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    # 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:
+        # 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 = Txt2Img(model).generate(
+            prompt=self.prompt,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt"}
+            ),  # 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")
+    strength: float = Field(
+        default=0.75, gt=0, le=1, description="The strength of the original image"
+    )
+    fit: bool = Field(
+        default=True,
+        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
+            )
+        )
+
+        if self.fit:
+            image = image.resize((self.width, self.height))
+
+        # 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,
+            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")
+    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,
+        le=1.0,
+        description="The amount by which to replace masked areas with latent noise",
+    )
+
+    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
+            if self.mask is None
+            else context.services.images.get(self.mask.image_type, 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_image=image,
+            mask_image=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,
+        )

invokeai/app/invocations/image.py

@@ -0,0 +1,367 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+import io
+from typing import Literal, Optional
+
+import numpy
+from PIL import Image, ImageFilter, ImageOps
+from pydantic import BaseModel, Field
+
+from ..models.image import ImageField, ImageType
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+
+class PILInvocationConfig(BaseModel):
+    """Helper class to provide all PIL invocations with additional config"""
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["PIL", "image"],
+            },
+        }
+
+
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image"] = "image"
+    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"]}
+
+
+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,
+    )
+
+
+class MaskOutput(BaseInvocationOutput):
+    """Base class for invocations that output a mask"""
+
+    # fmt: off
+    type: Literal["mask"] = "mask"
+    mask:      ImageField = Field(default=None, description="The output mask")
+    # fmt: on
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "type",
+                "mask",
+            ]
+        }
+
+
+class LoadImageInvocation(BaseInvocation):
+    """Load an image and provide it as output."""
+
+    # fmt: off
+    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")
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(self.image_type, self.image_name)
+
+        return build_image_output(
+            image_type=self.image_type,
+            image_name=self.image_name,
+            image=image,
+        )
+
+
+class ShowImageInvocation(BaseInvocation):
+    """Displays a provided image, and passes it forward in the pipeline."""
+
+    type: Literal["show_image"] = "show_image"
+
+    # Inputs
+    image: 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
+        )
+        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,
+        )
+
+
+class CropImageInvocation(BaseInvocation, PILInvocationConfig):
+    """Crops an image to a specified box. The box can be outside of the image."""
+
+    # fmt: off
+    type: Literal["crop"] = "crop"
+
+    # Inputs
+    image: 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")
+    height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(
+            self.image.image_type, 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=image_crop,
+        )
+
+
+class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
+    """Pastes an image into another image."""
+
+    # fmt: off
+    type: Literal["paste"] = "paste"
+
+    # Inputs
+    base_image:     ImageField = Field(default=None, description="The base image")
+    image:          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
+        )
+        mask = (
+            None
+            if self.mask is None
+            else ImageOps.invert(
+                context.services.images.get(self.mask.image_type, self.mask.image_name)
+            )
+        )
+        # TODO: probably shouldn't invert mask here... should user be required to do it?
+
+        min_x = min(0, self.x)
+        min_y = min(0, self.y)
+        max_x = max(base_image.width, image.width + self.x)
+        max_y = max(base_image.height, image.height + self.y)
+
+        new_image = Image.new(
+            mode="RGBA", size=(max_x - min_x, max_y - min_y), color=(0, 0, 0, 0)
+        )
+        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
+        )
+
+        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,
+        )
+
+
+class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
+    """Extracts the alpha channel of an image as a mask."""
+
+    # fmt: off
+    type: Literal["tomask"] = "tomask"
+
+    # Inputs
+    image: 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_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
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, image_mask, metadata)
+        return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
+
+
+class BlurInvocation(BaseInvocation, PILInvocationConfig):
+    """Blurs an image"""
+
+    # fmt: off
+    type: Literal["blur"] = "blur"
+
+    # Inputs
+    image: 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
+        )
+
+        blur = (
+            ImageFilter.GaussianBlur(self.radius)
+            if self.blur_type == "gaussian"
+            else ImageFilter.BoxBlur(self.radius)
+        )
+        blur_image = image.filter(blur)
+
+        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, blur_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=blur_image
+        )
+
+
+class LerpInvocation(BaseInvocation, PILInvocationConfig):
+    """Linear interpolation of all pixels of an image"""
+
+    # fmt: off
+    type: Literal["lerp"] = "lerp"
+
+    # Inputs
+    image: 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_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
+        )
+
+        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
+        )
+
+
+class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
+    """Inverse linear interpolation of all pixels of an image"""
+
+    # fmt: off
+    type: Literal["ilerp"] = "ilerp"
+
+    # Inputs
+    image: 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_arr = numpy.asarray(image, dtype=numpy.float32)
+        image_arr = (
+            numpy.minimum(
+                numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1
+            )
+            * 255
+        )
+
+        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
+        )
+
+        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
+        )

invokeai/app/invocations/infill.py

@@ -0,0 +1,233 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Optional, Union, get_args
+
+import numpy as np
+import math
+from PIL import Image, ImageOps
+from pydantic import Field
+
+from invokeai.app.invocations.image import ImageOutput, build_image_output
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.image_util.patchmatch import PatchMatch
+
+from ..models.image import ColorField, ImageField, ImageType
+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: Union[int, None] = 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: Optional[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(
+            self.image.image_type, self.image.image_name
+        )
+
+        solid_bg = Image.new("RGBA", image.size, self.color.tuple())
+        infilled = Image.alpha_composite(solid_bg, image)
+
+        infilled.paste(image, (0, 0), image.split()[-1])
+
+        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, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )
+
+
+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(
+            self.image.image_type, 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_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, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )
+
+
+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(
+            self.image.image_type, self.image.image_name
+        )
+
+        if PatchMatch.patchmatch_available():
+            infilled = infill_patchmatch(image.copy())
+        else:
+            raise ValueError("PatchMatch is not available on this system")
+
+        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, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )

invokeai/app/invocations/latent.py

@@ -0,0 +1,482 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+import random
+from typing import Literal, Optional, Union
+import einops
+from pydantic import BaseModel, Field
+import torch
+
+from invokeai.app.invocations.util.choose_model import choose_model
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+
+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, image_resized_to_grid_as_tensor
+from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
+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 .compel import ConditioningField
+from ...backend.stable_diffusion import PipelineIntermediateState
+from diffusers.schedulers import SchedulerMixin as Scheduler
+import diffusers
+from diffusers import DiffusionPipeline
+
+
+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")
+
+    class Config:
+        schema_extra = {"required": ["latents_name"]}
+
+class LatentsOutput(BaseInvocationOutput):
+    """Base class for invocations that output latents"""
+    #fmt: off
+    type: Literal["latents_output"] = "latents_output"
+
+    # 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
+
+
+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,
+      )
+
+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,
+      )
+
+
+SAMPLER_NAME_VALUES = Literal[
+    tuple(list(SCHEDULER_MAP.keys()))
+]
+
+
+def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
+    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
+    
+    scheduler_config = model.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
+
+
+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", )
+
+
+    # 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 build_noise_output(latents_name=name, latents=noise)
+
+
+# Text to image
+class TextToLatentsInvocation(BaseInvocation):
+    """Generates latents from conditionings."""
+
+    type: Literal["t2l"] = "t2l"
+
+    # Inputs
+    # fmt: off
+    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")
+    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="lms", description="The scheduler to use" )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    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
+                                        )
+        else:
+            configure_model_padding(model,
+                                    self.seamless,
+                                    self.seamless_axes
+                                    )
+
+        return model
+
+
+    def get_conditioning_data(self, context: InvocationContext, model: StableDiffusionGeneratorPipeline) -> 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(
+            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=0.0)#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(context, 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 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=0.5, description="The strength of the latents to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    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)
+
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(context, model)
+
+        # TODO: Verify the noise is the right size
+
+        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+            latent, device=model.device, dtype=latent.dtype
+        )
+
+        timesteps, _ = model.get_img2img_timesteps(self.steps, self.strength)
+
+        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
+        )
+
+        # 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 build_latents_output(latents_name=name, latents=result_latents)
+
+
+# Latent to image
+class LatentsToImageInvocation(BaseInvocation):
+    """Generates an image from latents."""
+
+    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")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    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']
+
+        with torch.inference_mode():
+            np_image = model.decode_latents(latents)
+            image = model.numpy_to_pil(np_image)[0]
+
+            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
+            )
+
+            torch.cuda.empty_cache()
+
+            context.services.images.save(image_type, image_name, image, metadata)
+            return build_image_output(
+                image_type=image_type, image_name=image_name, image=image
+            )
+
+
+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)
+        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)
+        return build_latents_output(latents_name=name, latents=resized_latents)
+
+
+class ImageToLatentsInvocation(BaseInvocation):
+    """Encodes an image into latents."""
+
+    type: Literal["i2l"] = "i2l"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The image to encode")
+    model: str = Field(default="", description="The model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info["model"]
+
+        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")
+
+        latents = model.non_noised_latents_from_image(
+            image_tensor,
+            device=model._model_group.device_for(model.unet),
+            dtype=model.unet.dtype,
+        )
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.set(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)

invokeai/app/invocations/math.py

@@ -0,0 +1,100 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+import numpy as np
+
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
+
+
+class MathInvocationConfig(BaseModel):
+    """Helper class to provide all math invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["math"],
+            }
+        }
+
+
+class IntOutput(BaseInvocationOutput):
+    """An integer output"""
+
+    # fmt: off
+    type: Literal["int_output"] = "int_output"
+    a: int = Field(default=None, description="The output integer")
+    # fmt: on
+
+
+class AddInvocation(BaseInvocation, MathInvocationConfig):
+    """Adds two numbers"""
+
+    # 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
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a + self.b)
+
+
+class SubtractInvocation(BaseInvocation, MathInvocationConfig):
+    """Subtracts two numbers"""
+
+    # 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
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a - self.b)
+
+
+class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
+    """Multiplies two numbers"""
+
+    # 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
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a * self.b)
+
+
+class DivideInvocation(BaseInvocation, MathInvocationConfig):
+    """Divides two numbers"""
+
+    # 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
+
+    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/params.py

@@ -0,0 +1,18 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+from pydantic import Field
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from .math import IntOutput
+
+# Pass-through parameter nodes - used by subgraphs
+
+class ParamIntInvocation(BaseInvocation):
+    """An integer parameter"""
+    #fmt: off
+    type: Literal["param_int"] = "param_int"
+    a: int = Field(default=0, description="The integer value")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a)

invokeai/app/invocations/prompt.py

@@ -0,0 +1,22 @@
+from typing import Literal
+
+from pydantic.fields import Field
+
+from .baseinvocation import BaseInvocationOutput
+
+
+class PromptOutput(BaseInvocationOutput):
+    """Base class for invocations that output a prompt"""
+    #fmt: off
+    type: Literal["prompt"] = "prompt"
+
+    prompt: str = Field(default=None, description="The output prompt")
+    #fmt: on
+
+    class Config:
+        schema_extra = {
+            'required': [
+                'type',
+                'prompt',
+            ]
+        }

invokeai/app/invocations/reconstruct.py

@@ -0,0 +1,56 @@
+from typing import Literal, Union
+
+from pydantic import Field
+
+from invokeai.app.models.image import ImageField, ImageType
+
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
+
+class RestoreFaceInvocation(BaseInvocation):
+    """Restores faces in an image."""
+    #fmt: off
+    type:  Literal["restore_face"] = "restore_face"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image")
+    strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
+    #fmt: on
+    
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["restoration", "image"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=None,
+            strength=self.strength,  # 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
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        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

@@ -0,0 +1,60 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Union
+
+from pydantic import Field
+
+from invokeai.app.models.image import ImageField, ImageType
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
+
+
+class UpscaleInvocation(BaseInvocation):
+    """Upscales an image."""
+    #fmt: off
+    type: Literal["upscale"] = "upscale"
+
+    # Inputs
+    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.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
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        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

@@ -0,0 +1,14 @@
+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."""
+    logger = model_manager.logger
+    if model_name and not model_manager.valid_model(model_name):
+        default_model_name = model_manager.default_model()
+        logger.warning(f"\'{model_name}\' is not a valid model name. Using default model \'{default_model_name}\' instead.")
+        model = model_manager.get_model()
+    else:
+        model = model_manager.get_model(model_name)
+
+    return model

invokeai/app/models/exceptions.py

@@ -0,0 +1,3 @@
+class CanceledException(Exception):
+    """Execution canceled by user."""
+    pass

invokeai/app/models/image.py

@@ -0,0 +1,39 @@
+from enum import Enum
+from typing import Optional, Tuple
+from pydantic import BaseModel, Field
+
+
+class ImageType(str, Enum):
+    RESULT = "results"
+    INTERMEDIATE = "intermediates"
+    UPLOAD = "uploads"
+
+
+def is_image_type(obj):
+    try:
+        ImageType(obj)
+    except ValueError:
+        return False
+    return True
+
+
+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"]}
+
+
+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)

invokeai/app/services/config.py

@@ -0,0 +1,521 @@
+# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
+
+'''Invokeai configuration system.
+
+Arguments and fields are taken from the pydantic definition of the
+model.  Defaults can be set by creating a yaml configuration file that
+has a top-level key of "InvokeAI" and subheadings for each of the
+categories returned by `invokeai --help`. The file looks like this:
+
+[file: invokeai.yaml]
+
+InvokeAI:
+  Paths:
+    root: /home/lstein/invokeai-main
+    conf_path: configs/models.yaml
+    legacy_conf_dir: configs/stable-diffusion
+    outdir: outputs
+    embedding_dir: embeddings
+    lora_dir: loras
+    autoconvert_dir: null
+    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
+  Models:
+    model: stable-diffusion-1.5
+    embeddings: true
+  Memory/Performance:
+    xformers_enabled: false
+    sequential_guidance: false
+    precision: float16
+    max_loaded_models: 4
+    always_use_cpu: false
+    free_gpu_mem: false
+  Features:
+    nsfw_checker: true
+    restore: true
+    esrgan: true
+    patchmatch: true
+    internet_available: true
+    log_tokenization: false
+  Web Server:
+    host: 127.0.0.1
+    port: 8081
+    allow_origins: []
+    allow_credentials: true
+    allow_methods:
+    - '*'
+    allow_headers:
+    - '*'
+
+The default name of the configuration file is `invokeai.yaml`, located
+in INVOKEAI_ROOT. You can replace supersede this by providing any
+OmegaConf dictionary object initialization time:
+
+ omegaconf = OmegaConf.load('/tmp/init.yaml')
+ conf = InvokeAIAppConfig(conf=omegaconf)
+
+By default, InvokeAIAppConfig will parse the contents of `sys.argv` at
+initialization time. You may pass a list of strings in the optional
+`argv` argument to use instead of the system argv:
+
+ conf = InvokeAIAppConfig(arg=['--xformers_enabled'])
+
+It is also possible to set a value at initialization time. This value
+has highest priority.
+
+ conf = InvokeAIAppConfig(xformers_enabled=True)
+
+Any setting can be overwritten by setting an environment variable of
+form: "INVOKEAI_<setting>", as in:
+
+  export INVOKEAI_port=8080
+
+Order of precedence (from highest):
+   1) initialization options
+   2) command line options
+   3) environment variable options
+   4) config file options
+   5) pydantic defaults
+
+Typical usage:
+
+ from invokeai.app.services.config import InvokeAIAppConfig
+ from invokeai.invocations.generate import TextToImageInvocation
+
+ # get global configuration and print its nsfw_checker value
+ conf = InvokeAIAppConfig()
+ print(conf.nsfw_checker)
+
+ # get the text2image invocation and print its step value
+ text2image = TextToImageInvocation()
+ print(text2image.steps)
+
+Computed properties:
+
+The InvokeAIAppConfig object has a series of properties that
+resolve paths relative to the runtime root directory. They each return
+a Path object:
+
+ root_path          - path to InvokeAI root
+ output_path        - path to default outputs directory
+ model_conf_path    - path to models.yaml
+ conf               - alias for the above
+ embedding_path     - path to the embeddings directory
+ lora_path          - path to the LoRA directory
+
+In most cases, you will want to create a single InvokeAIAppConfig
+object for the entire application. The get_invokeai_config() function
+does this:
+
+  config = get_invokeai_config()
+  print(config.root)
+
+# Subclassing
+
+If you wish to create a similar class, please subclass the
+`InvokeAISettings` class and define a Literal field named "type",
+which is set to the desired top-level name.  For example, to create a
+"InvokeBatch" configuration, define like this:
+
+  class InvokeBatch(InvokeAISettings):
+     type: Literal["InvokeBatch"] = "InvokeBatch"
+     node_count : int = Field(default=1, description="Number of nodes to run on", category='Resources')
+     cpu_count  : int = Field(default=8, description="Number of GPUs to run on per node", category='Resources')
+
+This will now read and write from the "InvokeBatch" section of the
+config file, look for environment variables named INVOKEBATCH_*, and
+accept the command-line arguments `--node_count` and `--cpu_count`. The
+two configs are kept in separate sections of the config file:
+
+  # invokeai.yaml
+
+  InvokeBatch:
+     Resources:
+        node_count: 1
+        cpu_count: 8
+
+  InvokeAI:
+     Paths:
+        root: /home/lstein/invokeai-main
+        conf_path: configs/models.yaml
+        legacy_conf_dir: configs/stable-diffusion
+        outdir: outputs
+     ...
+'''
+import argparse
+import pydoc
+import typing
+import os
+import sys
+from argparse import ArgumentParser
+from omegaconf import OmegaConf, DictConfig
+from pathlib import Path
+from pydantic import BaseSettings, Field, parse_obj_as
+from typing import Any, ClassVar, Dict, List, Literal, Type, Union, get_origin, get_type_hints, get_args
+
+INIT_FILE = Path('invokeai.yaml')
+LEGACY_INIT_FILE = Path('invokeai.init')
+
+# This global stores a singleton InvokeAIAppConfig configuration object
+global_config = None
+
+class InvokeAISettings(BaseSettings):
+    '''
+    Runtime configuration settings in which default values are
+    read from an omegaconf .yaml file.
+    '''
+    initconf             : ClassVar[DictConfig] = None
+    argparse_groups      : ClassVar[Dict] = {}
+
+    def parse_args(self, argv: list=sys.argv[1:]):
+        parser = self.get_parser()
+        opt, _ = parser.parse_known_args(argv)
+        for name in self.__fields__:
+            if name not in self._excluded():
+                setattr(self, name, getattr(opt,name))
+
+    def to_yaml(self)->str:
+        """
+        Return a YAML string representing our settings. This can be used
+        as the contents of `invokeai.yaml` to restore settings later.
+        """
+        cls = self.__class__
+        type = get_args(get_type_hints(cls)['type'])[0]
+        field_dict = dict({type:dict()})
+        for name,field in self.__fields__.items():
+            if name in cls._excluded():
+                continue
+            category = field.field_info.extra.get("category") or "Uncategorized"
+            value = getattr(self,name)
+            if category not in field_dict[type]:
+                field_dict[type][category] = dict()
+            # keep paths as strings to make it easier to read
+            field_dict[type][category][name] = str(value) if isinstance(value,Path) else value
+        conf = OmegaConf.create(field_dict)
+        return OmegaConf.to_yaml(conf)
+
+    @classmethod
+    def add_parser_arguments(cls, parser):
+        if 'type' in get_type_hints(cls):
+            settings_stanza = get_args(get_type_hints(cls)['type'])[0]
+        else:
+            settings_stanza = "Uncategorized"
+
+        env_prefix = cls.Config.env_prefix if hasattr(cls.Config,'env_prefix') else settings_stanza.upper()
+
+        initconf = cls.initconf.get(settings_stanza) \
+            if cls.initconf and settings_stanza in cls.initconf \
+               else OmegaConf.create()
+
+        # create an upcase version of the environment in
+        # order to achieve case-insensitive environment
+        # variables (the way Windows does)
+        upcase_environ = dict()
+        for key,value in os.environ.items():
+            upcase_environ[key.upper()] = value
+        
+        fields = cls.__fields__
+        cls.argparse_groups = {}
+        
+        for name, field in fields.items():
+            if name not in cls._excluded():
+                current_default = field.default
+
+                category = field.field_info.extra.get("category","Uncategorized")
+                env_name = env_prefix + '_' + name
+                if category in initconf and name in initconf.get(category):
+                    field.default = initconf.get(category).get(name)
+                if env_name.upper() in upcase_environ:
+                    field.default = upcase_environ[env_name.upper()]
+                cls.add_field_argument(parser, name, field)
+
+                field.default = current_default
+
+    @classmethod
+    def cmd_name(self, command_field: str='type')->str:
+        hints = get_type_hints(self)
+        if command_field in hints:
+            return get_args(hints[command_field])[0]
+        else:
+            return 'Uncategorized'
+
+    @classmethod
+    def get_parser(cls)->ArgumentParser:
+        parser = PagingArgumentParser(
+            prog=cls.cmd_name(),
+            description=cls.__doc__,
+        )
+        cls.add_parser_arguments(parser)
+        return parser
+
+    @classmethod
+    def add_subparser(cls, parser: argparse.ArgumentParser):
+        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
+
+    @classmethod
+    def _excluded(self)->List[str]:
+        return ['type','initconf']
+
+    class Config:
+        env_file_encoding = 'utf-8'
+        arbitrary_types_allowed = True
+        case_sensitive = True
+
+    @classmethod
+    def add_field_argument(cls, command_parser, name: str, field, default_override = None):
+        field_type = get_type_hints(cls).get(name)
+        default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+        if category := field.field_info.extra.get("category"):
+            if category not in cls.argparse_groups:
+                cls.argparse_groups[category] = command_parser.add_argument_group(category)
+            argparse_group = cls.argparse_groups[category]
+        else:
+            argparse_group = command_parser
+
+        if get_origin(field_type) == Literal:
+            allowed_values = get_args(field.type_)
+            allowed_types = set()
+            for val in allowed_values:
+                allowed_types.add(type(val))
+            allowed_types_list = list(allowed_types)
+            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field_type,
+                default=default,
+                choices=allowed_values,
+                help=field.field_info.description,
+            )
+
+        elif get_origin(field_type) == list:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                nargs='*',
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+        else:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+def _find_root()->Path:
+    if os.environ.get("INVOKEAI_ROOT"):
+        root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
+    elif (
+            os.environ.get("VIRTUAL_ENV")
+            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
+                 or
+                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
+                 )
+    ):
+        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
+    else:
+        root = Path("~/invokeai").expanduser().resolve()
+    return root
+
+class InvokeAIAppConfig(InvokeAISettings):
+    '''
+Generate images using Stable Diffusion. Use "invokeai" to launch
+the command-line client (recommended for experts only), or
+"invokeai-web" to launch the web server. Global options
+can be changed by editing the file "INVOKEAI_ROOT/invokeai.yaml" or by
+setting environment variables INVOKEAI_<setting>.
+     '''
+    #fmt: off
+    type: Literal["InvokeAI"] = "InvokeAI"
+    host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
+    port                : int = Field(default=9090, description="Port to bind to", category='Web Server')
+    allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
+    allow_credentials   : bool = Field(default=True, description="Allow CORS credentials", category='Web Server')
+    allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
+    allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
+
+    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
+    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
+    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
+    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
+    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
+    restore             : bool = Field(default=True, description="Enable/disable face restoration code", category='Features')
+
+    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
+    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
+    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
+
+    root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
+    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
+    embedding_dir       : Path = Field(default='embeddings', description='Path to InvokeAI textual inversion aembeddings directory', category='Paths')
+    gfpgan_model_dir    : Path = Field(default="./models/gfpgan/GFPGANv1.4.pth", description='Path to GFPGAN models directory.', category='Paths')
+    legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
+    lora_dir            : Path = Field(default='loras', description='Path to InvokeAI LoRA model directory', category='Paths')
+    outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
+    from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
+
+    model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
+    embeddings          : bool = Field(default=True, description='Load contents of embeddings directory', category='Models')
+    #fmt: on
+
+    def __init__(self, conf: DictConfig = None, argv: List[str]=None, **kwargs):
+        '''
+        Initialize InvokeAIAppconfig.
+        :param conf: alternate Omegaconf dictionary object
+        :param argv: aternate sys.argv list
+        :param **kwargs: attributes to initialize with
+        '''
+        super().__init__(**kwargs)
+
+        # Set the runtime root directory. We parse command-line switches here
+        # in order to pick up the --root_dir option.
+        self.parse_args(argv)
+        if conf is None:
+            try:
+                conf = OmegaConf.load(self.root_dir / INIT_FILE)
+            except:
+                pass
+        InvokeAISettings.initconf = conf
+
+        # parse args again in order to pick up settings in configuration file
+        self.parse_args(argv)
+
+        # restore initialization values
+        hints = get_type_hints(self)
+        for k in kwargs:
+            setattr(self,k,parse_obj_as(hints[k],kwargs[k]))
+
+    @property
+    def root_path(self)->Path:
+        '''
+        Path to the runtime root directory
+        '''
+        if self.root:
+            return Path(self.root).expanduser()
+        else:
+            return self.find_root()
+
+    @property
+    def root_dir(self)->Path:
+        '''
+        Alias for above.
+        '''
+        return self.root_path
+
+    def _resolve(self,partial_path:Path)->Path:
+        return (self.root_path / partial_path).resolve()
+
+    @property
+    def output_path(self)->Path:
+        '''
+        Path to defaults outputs directory.
+        '''
+        return self._resolve(self.outdir)
+
+    @property
+    def model_conf_path(self)->Path:
+        '''
+        Path to models configuration file.
+        '''
+        return self._resolve(self.conf_path)
+
+    @property
+    def legacy_conf_path(self)->Path:
+        '''
+        Path to directory of legacy configuration files (e.g. v1-inference.yaml)
+        '''
+        return self._resolve(self.legacy_conf_dir)
+
+    @property
+    def cache_dir(self)->Path:
+        '''
+        Path to the global cache directory for HuggingFace hub-managed models
+        '''
+        return self.models_dir / "hub"
+
+    @property
+    def models_dir(self)->Path:
+        '''
+        Path to the models directory
+        '''
+        return self._resolve("models")
+
+    @property
+    def embedding_path(self)->Path:
+        '''
+        Path to the textual inversion embeddings directory.
+        '''
+        return self._resolve(self.embedding_dir) if self.embedding_dir else None
+
+    @property
+    def lora_path(self)->Path:
+        '''
+        Path to the LoRA models directory.
+        '''
+        return self._resolve(self.lora_dir) if self.lora_dir else None
+
+    @property
+    def autoconvert_path(self)->Path:
+        '''
+        Path to the directory containing models to be imported automatically at startup.
+        '''
+        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
+
+    @property
+    def gfpgan_model_path(self)->Path:
+        '''
+        Path to the GFPGAN model.
+        '''
+        return self._resolve(self.gfpgan_model_dir) if self.gfpgan_model_dir else None
+
+    # the following methods support legacy calls leftover from the Globals era
+    @property
+    def full_precision(self)->bool:
+        """Return true if precision set to float32"""
+        return self.precision=='float32'
+
+    @property
+    def disable_xformers(self)->bool:
+        """Return true if xformers_enabled is false"""
+        return not self.xformers_enabled
+
+    @property
+    def try_patchmatch(self)->bool:
+        """Return true if patchmatch true"""
+        return self.patchmatch
+
+    @staticmethod
+    def find_root()->Path:
+        '''
+        Choose the runtime root directory when not specified on command line or
+        init file.
+        '''
+        return _find_root()
+
+
+class PagingArgumentParser(argparse.ArgumentParser):
+    '''
+    A custom ArgumentParser that uses pydoc to page its output.
+    It also supports reading defaults from an init file.
+    '''
+    def print_help(self, file=None):
+        text = self.format_help()
+        pydoc.pager(text)
+
+def get_invokeai_config(cls:Type[InvokeAISettings]=InvokeAIAppConfig,**kwargs)->InvokeAISettings:
+    '''
+    This returns a singleton InvokeAIAppConfig configuration object.
+    '''
+    global global_config
+    if global_config is None or type(global_config)!=cls:
+        global_config = cls(**kwargs)
+    return global_config

invokeai/app/services/default_graphs.py

@@ -0,0 +1,64 @@
+from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.compel import CompelInvocation
+from ..invocations.params import ParamIntInvocation
+from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
+from .item_storage import ItemStorageABC
+
+
+default_text_to_image_graph_id = '539b2af5-2b4d-4d8c-8071-e54a3255fc74'
+
+
+def create_text_to_image() -> LibraryGraph:
+    return LibraryGraph(
+        id=default_text_to_image_graph_id,
+        name='t2i',
+        description='Converts text to an image',
+        graph=Graph(
+            nodes={
+                'width': ParamIntInvocation(id='width', a=512),
+                'height': ParamIntInvocation(id='height', a=512),
+                'seed': ParamIntInvocation(id='seed', a=-1),
+                '3': NoiseInvocation(id='3'),
+                '4': CompelInvocation(id='4'),
+                '5': CompelInvocation(id='5'),
+                '6': TextToLatentsInvocation(id='6'),
+                '7': LatentsToImageInvocation(id='7'),
+            },
+            edges=[
+                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
+                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='3', field='height')),
+                Edge(source=EdgeConnection(node_id='seed', field='a'), destination=EdgeConnection(node_id='3', field='seed')),
+                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='6', field='noise')),
+                Edge(source=EdgeConnection(node_id='6', field='latents'), destination=EdgeConnection(node_id='7', field='latents')),
+                Edge(source=EdgeConnection(node_id='4', field='conditioning'), destination=EdgeConnection(node_id='6', field='positive_conditioning')),
+                Edge(source=EdgeConnection(node_id='5', field='conditioning'), destination=EdgeConnection(node_id='6', field='negative_conditioning')),
+            ]
+        ),
+        exposed_inputs=[
+            ExposedNodeInput(node_path='4', field='prompt', alias='positive_prompt'),
+            ExposedNodeInput(node_path='5', field='prompt', alias='negative_prompt'),
+            ExposedNodeInput(node_path='width', field='a', alias='width'),
+            ExposedNodeInput(node_path='height', field='a', alias='height'),
+            ExposedNodeInput(node_path='seed', field='a', alias='seed'),
+        ],
+        exposed_outputs=[
+            ExposedNodeOutput(node_path='7', field='image', alias='image')
+        ])
+
+
+def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
+    """Creates the default system graphs, or adds new versions if the old ones don't match"""
+    
+    # TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
+    graphs: list[LibraryGraph] = list()
+
+    # text_to_image = graph_library.get(default_text_to_image_graph_id)
+    
+    # # TODO: Check if the graph is the same as the default one, and if not, update it
+    # #if text_to_image is None:
+    text_to_image = create_text_to_image()
+    graph_library.set(text_to_image)
+
+    graphs.append(text_to_image)
+
+    return graphs

invokeai/app/services/events.py

@@ -0,0 +1,103 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Any
+from invokeai.app.api.models.images import ProgressImage
+from invokeai.app.util.misc import get_timestamp
+
+
+class EventServiceBase:
+    session_event: str = "session_event"
+
+    """Basic event bus, to have an empty stand-in when not needed"""
+
+    def dispatch(self, event_name: str, payload: Any) -> None:
+        pass
+
+    def __emit_session_event(self, event_name: str, payload: dict) -> None:
+        payload["timestamp"] = get_timestamp()
+        self.dispatch(
+            event_name=EventServiceBase.session_event,
+            payload=dict(event=event_name, data=payload),
+        )
+
+    # Define events here for every event in the system.
+    # This will make them easier to integrate until we find a schema generator.
+    def emit_generator_progress(
+        self,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+        progress_image: ProgressImage | None,
+        step: int,
+        total_steps: int,
+    ) -> None:
+        """Emitted when there is generation progress"""
+        self.__emit_session_event(
+            event_name="generator_progress",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                progress_image=progress_image.dict() if progress_image is not None else None,
+                step=step,
+                total_steps=total_steps,
+            ),
+        )
+
+    def emit_invocation_complete(
+        self,
+        graph_execution_state_id: str,
+        result: dict,
+        node: dict,
+        source_node_id: str,
+    ) -> None:
+        """Emitted when an invocation has completed"""
+        self.__emit_session_event(
+            event_name="invocation_complete",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                result=result,
+            ),
+        )
+
+    def emit_invocation_error(
+        self,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+        error: str,
+    ) -> None:
+        """Emitted when an invocation has completed"""
+        self.__emit_session_event(
+            event_name="invocation_error",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+                error=error,
+            ),
+        )
+
+    def emit_invocation_started(
+        self, graph_execution_state_id: str, node: dict, source_node_id: str
+    ) -> None:
+        """Emitted when an invocation has started"""
+        self.__emit_session_event(
+            event_name="invocation_started",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+                node=node,
+                source_node_id=source_node_id,
+            ),
+        )
+
+    def emit_graph_execution_complete(self, graph_execution_state_id: str) -> None:
+        """Emitted when a session has completed all invocations"""
+        self.__emit_session_event(
+            event_name="graph_execution_state_complete",
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+            ),
+        )