Initial work to update to pydantic 2 and newer fastapi. Still need to review all fields, fix schema generation (to link output types), and update all Config classes to use model_config.

.github/CODEOWNERS

@@ -1,34 +1,34 @@
 # continuous integration
-/.github/workflows/  @lstein @blessedcoolant @hipsterusername
+/.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @blessedcoolant @hipsterusername @Millu
-/mkdocs.yml @lstein  @blessedcoolant @hipsterusername @Millu
+/docs/ @lstein @blessedcoolant @hipsterusername
+/mkdocs.yml @lstein  @blessedcoolant
 
 # nodes
-/invokeai/app/ @Kyle0654 @blessedcoolant @psychedelicious @brandonrising @hipsterusername
+/invokeai/app/ @Kyle0654 @blessedcoolant @psychedelicious @brandonrising 
 
 # installation and configuration
-/pyproject.toml  @lstein @blessedcoolant @hipsterusername
-/docker/  @lstein @blessedcoolant @hipsterusername
-/scripts/ @ebr @lstein @hipsterusername
-/installer/ @lstein @ebr @hipsterusername
-/invokeai/assets @lstein @ebr @hipsterusername
-/invokeai/configs @lstein @hipsterusername
-/invokeai/version @lstein @blessedcoolant @hipsterusername
+/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 @lstein @maryhipp @hipsterusername
-/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp @hipsterusername
+/invokeai/frontend @blessedcoolant @psychedelicious @lstein @maryhipp
+/invokeai/backend @blessedcoolant @psychedelicious @lstein @maryhipp
 
 # generation, model management, postprocessing
-/invokeai/backend  @damian0815 @lstein @blessedcoolant @gregghelt2 @StAlKeR7779 @brandonrising @ryanjdick @hipsterusername
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @gregghelt2 @StAlKeR7779 @brandonrising
 
 # front ends
-/invokeai/frontend/CLI @lstein @hipsterusername
-/invokeai/frontend/install @lstein @ebr @hipsterusername 
-/invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
-/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp @hipsterusername
+/invokeai/frontend/CLI @lstein
+/invokeai/frontend/install @lstein @ebr  
+/invokeai/frontend/merge @lstein @blessedcoolant 
+/invokeai/frontend/training @lstein @blessedcoolant 
+/invokeai/frontend/web @psychedelicious @blessedcoolant @maryhipp 
 
 

.github/ISSUE_TEMPLATE/FEATURE_REQUEST.yml

@@ -1,5 +1,5 @@
 name: Feature Request
-description: Contribute a idea or request a new feature
+description: Commit a idea or Request a new feature
 title: '[enhancement]: '
 labels: ['enhancement']
 # assignees:
@@ -9,14 +9,14 @@ body:
   - type: markdown
     attributes:
       value: |
-        Thanks for taking the time to fill out this feature request!
+        Thanks for taking the time to fill out this Feature request!
 
   - type: checkboxes
     attributes:
       label: Is there an existing issue for this?
       description: |
         Please make use of the [search function](https://github.com/invoke-ai/InvokeAI/labels/enhancement)
-        to see if a similar issue already exists for the feature you want to request
+        to see if a simmilar issue already exists for the feature you want to request
       options:
         - label: I have searched the existing issues
           required: true
@@ -34,9 +34,12 @@ body:
     id: whatisexpected
     attributes:
       label: What should this feature add?
-      description: Explain the functionality this feature should add. Feature requests should be for single features. Please create multiple requests if you want to request multiple features.
+      description: Please try to explain the functionality this feature should add
       placeholder: |
-        I'd like a button that creates an image of banana sushi every time I press it. Each image should be different. There should be a toggle next to the button that enables strawberry mode, in which the images are of strawberry sushi instead.
+        Instead of one huge textfield, it would be nice to have forms for bug-reports, feature-requests, ...
+        Great benefits with automatic labeling, assigning and other functionalitys not available in that form
+        via old-fashioned markdown-templates. I would also love to see the use of a moderator bot 🤖 like
+        https://github.com/marketplace/actions/issue-moderator-with-commands to auto close old issues and other things
     validations:
       required: true
 
@@ -48,6 +51,6 @@ body:
 
   - type: textarea
     attributes:
-      label: Additional Content
+      label: Aditional Content
       description: Add any other context or screenshots about the feature request here.
-      placeholder: This is a mockup of the design how I imagine it <screenshot>
+      placeholder: This is a Mockup of the design how I imagine it <screenshot>

.github/workflows/pypi-release.yml

@@ -28,7 +28,7 @@ jobs:
         run: twine check dist/*
 
       - name: check PyPI versions
-        if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
+        if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3'
         run: |
           pip install --upgrade requests
           python -c "\

.github/workflows/style-checks.yml

@@ -1,4 +1,6 @@
 name: style checks
+# just formatting for now
+# TODO: add isort and flake8 later
 
 on:
   pull_request:
@@ -18,8 +20,8 @@ jobs:
 
       - name: Install dependencies with pip
         run: |
-          pip install black flake8 Flake8-pyproject isort
+          pip install black
 
-      - run: isort --check-only .
+      # - run: isort --check-only .
       - run: black --check .
-      - run: flake8
+      # - run: flake8

.gitignore

@@ -1,8 +1,23 @@
+# ignore default image save location and model symbolic link
 .idea/
+embeddings/
+outputs/
+models/ldm/stable-diffusion-v1/model.ckpt
+**/restoration/codeformer/weights
+
+# ignore user models config
+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
 
+# ignore a directory which serves as a place for initial images
+inputs/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -174,17 +189,39 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
+src
 **/__pycache__/
+outputs
 
+# Logs and associated folders
+# created from generated embeddings.
+logs
+testtube
+checkpoints
 # If it's a Mac
 .DS_Store
 
+invokeai/frontend/yarn.lock
+invokeai/frontend/node_modules
+
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*
 
 # Scratch folder
 .scratch/
 .vscode/
+gfpgan/
+models/ldm/stable-diffusion-v1/*.sha256
+
+
+# GFPGAN model files
+gfpgan/
+
+# config file (will be created by installer)
+configs/models.yaml
+
+# ignore initfile
+.invokeai
 
 # ignore environment.yml and requirements.txt
 # these are links to the real files in environments-and-requirements

.pre-commit-config.yaml

@@ -8,17 +8,3 @@ repos:
     language: system
     entry: black
     types: [python]
-
-  - id: flake8
-    name: flake8
-    stages: [commit]
-    language: system
-    entry: flake8
-    types: [python]
-
-  - id: isort
-    name: isort
-    stages: [commit]
-    language: system
-    entry: isort
-    types: [python]

README.md

@@ -43,16 +43,16 @@ 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/INSTALLATION/)] [<a
+  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/issues">Bug Reports</a>]
+  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>] 
-   [<a
-  href="https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/">Contributing</a>] 
+  Ideas & Q&A</a>]
 
 <div align="center">
 
@@ -81,7 +81,7 @@ Table of Contents 📝
 ## Quick Start
 
 For full installation and upgrade instructions, please see:
-[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/INSTALLATION/)
+[InvokeAI Installation Overview](https://invoke-ai.github.io/InvokeAI/installation/)
 
 If upgrading from version 2.3, please read [Migrating a 2.3 root
 directory to 3.0](#migrating-to-3) first.
@@ -368,9 +368,9 @@ InvokeAI offers a locally hosted Web Server & React Frontend, with an industry l
 
 The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
 
-### *Workflows & Nodes*
+### *Node Architecture & Editor (Beta)*
 
-InvokeAI offers a fully featured workflow management solution, enabling users to combine the power of nodes based workflows with the easy of a UI. This allows for customizable generation pipelines to be developed and shared by users looking to create specific workflows to support their production use-cases.
+Invoke AI's backend is built on a graph-based execution architecture. This allows for customizable generation pipelines to be developed by professional users looking to create specific workflows to support their production use-cases, and will be extended in the future with additional capabilities.
 
 ### *Board & Gallery Management*
 
@@ -383,9 +383,8 @@ Invoke AI provides an organized gallery system for easily storing, accessing, an
 - *Upscaling Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
-- *Workflow creation & management*
 - *Node-Based Architecture*
-
+- *Node-Based Plug-&-Play UI (Beta)*
 
 ### Latest Changes
 
@@ -396,18 +395,20 @@ Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
 ### Troubleshooting
 
 Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
-problems and other issues. For more help, please join our [Discord][discord link]
+problems and other issues.
 
 ## Contributing
 
 Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
 cleanup, testing, or code reviews, is very much encouraged to do so.
 
-Get started with contributing by reading our [Contribution documentation](https://invoke-ai.github.io/InvokeAI/contributing/CONTRIBUTING/), joining the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) or the GitHub discussion board.
+To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.
+
+If you'd like to help with translation, please see our [translation guide](docs/other/TRANSLATION.md).
 
 If you are unfamiliar with how
-to contribute to GitHub projects, we have a new contributor checklist you can follow to get started contributing: 
-[New Contributor Checklist](https://invoke-ai.github.io/InvokeAI/contributing/contribution_guides/newContributorChecklist/).
+to contribute to GitHub projects, here is a
+[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). A full set of contribution guidelines, along with templates, are in progress. You can **make your pull request against the "main" branch**.
 
 We hope you enjoy using our software as much as we enjoy creating it,
 and we hope that some of those of you who are reading this will elect
@@ -423,7 +424,7 @@ their time, hard work and effort.
 
 ### Support
 
-For support, please use this repository's GitHub Issues tracking service, or join the [Discord][discord link].
+For support, please use this repository's GitHub Issues tracking service, or join the Discord.
 
 Original portions of the software are Copyright (c) 2023 by respective contributors.
 

docker/docker-entrypoint.sh

@@ -29,8 +29,8 @@ configure() {
         echo "To reconfigure InvokeAI, delete the above file."
         echo "======================================================================"
     else
-        mkdir -p "${INVOKEAI_ROOT}"
-        chown --recursive ${USER} "${INVOKEAI_ROOT}"
+        mkdir -p ${INVOKEAI_ROOT}
+        chown --recursive ${USER} ${INVOKEAI_ROOT}
         gosu ${USER} invokeai-configure --yes --default_only
     fi
 }
@@ -50,16 +50,16 @@ fi
 if [[ -v "PUBLIC_KEY" ]] && [[ ! -d "${HOME}/.ssh" ]]; then
     apt-get update
     apt-get install -y openssh-server
-    pushd "$HOME"
+    pushd $HOME
     mkdir -p .ssh
-    echo "${PUBLIC_KEY}" > .ssh/authorized_keys
+    echo ${PUBLIC_KEY} > .ssh/authorized_keys
     chmod -R 700 .ssh
     popd
     service ssh start
 fi
 
 
-cd "${INVOKEAI_ROOT}"
+cd ${INVOKEAI_ROOT}
 
 # Run the CMD as the Container User (not root).
 exec gosu ${USER} "$@"

docs/contributing/CONTRIBUTING.md

@@ -1,41 +1,36 @@
-# Contributing
+# How to Contribute
 
+## Welcome to Invoke AI
 Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
 
 
-# Methods of Contributing to Invoke AI
+## Contributing to Invoke AI
 Anyone who wishes to contribute to InvokeAI, whether features, bug fixes, code cleanup, testing, code reviews, documentation or translation is very much encouraged to do so.
 
-## Development
-If you’d like to help with development, please see our [development guide](contribution_guides/development.md). 
+To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.
 
-**New Contributors:** If you’re unfamiliar with contributing to open source projects, take a look at our [new contributor guide](contribution_guides/newContributorChecklist.md).
+### Areas of contribution: 
 
-## Nodes
-If you’d like to add a Node, please see our [nodes contribution guide](../nodes/contributingNodes.md).
+#### Development
+If you’d like to help with development, please see our [development guide](contribution_guides/development.md). If you’re unfamiliar with contributing to open source projects, there is a tutorial contained within the development guide.
 
-## Support and Triaging
-Helping support other users in [Discord](https://discord.gg/ZmtBAhwWhy) and on Github are valuable forms of contribution that we greatly appreciate. 
+#### Documentation
+If you’d like to help with documentation, please see our [documentation guide](contribution_guides/documenation.md).
 
-We receive many issues and requests for help from users. We're limited in bandwidth relative to our the user base, so providing answers to questions or helping identify causes of issues is very helpful. By doing this, you enable us to spend time on the highest priority work. 
+#### Translation
+If you'd like to help with translation, please see our [translation guide](docs/contributing/.contribution_guides/translation.md).
 
-## Documentation
-If you’d like to help with documentation, please see our [documentation guide](contribution_guides/documentation.md).
-
-## Translation
-If you'd like to help with translation, please see our [translation guide](contribution_guides/translation.md).
-
-## Tutorials 
+#### Tutorials 
 Please reach out to @imic or @hipsterusername on [Discord](https://discord.gg/ZmtBAhwWhy) to help create tutorials for InvokeAI.
 
 We hope you enjoy using our software as much as we enjoy creating it, and we hope that some of those of you who are reading this will elect to become part of our contributor community.
 
 
-# Contributors
+### Contributors
 
 This project is a combined effort of dedicated people from across the world. [Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for their time, hard work and effort.
 
-# Code of Conduct
+### Code of Conduct
 
 The InvokeAI community is a welcoming place, and we want your help in maintaining that. Please review our [Code of Conduct](https://github.com/invoke-ai/InvokeAI/blob/main/CODE_OF_CONDUCT.md) to learn more - it's essential to maintaining a respectful and inclusive environment.
 
@@ -49,7 +44,8 @@ By making a contribution to this project, you certify that:
 This disclaimer is not a license and does not grant any rights or permissions. You must obtain necessary permissions and licenses, including from third parties, before contributing to this project.
 
 This disclaimer is provided "as is" without warranty of any kind, whether expressed or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, or non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the contribution or the use or other dealings in the contribution.
-# Support
+
+### Support
 
 For support, please use this repository's [GitHub Issues](https://github.com/invoke-ai/InvokeAI/issues), or join the [Discord](https://discord.gg/ZmtBAhwWhy).
 

docs/contributing/INVOCATIONS.md

@@ -29,13 +29,12 @@ The first set of things we need to do when creating a new Invocation are -
 
 - Create a new class that derives from a predefined parent class called
   `BaseInvocation`.
+- The name of every Invocation must end with the word `Invocation` in order for
+  it to be recognized as an Invocation.
 - Every Invocation must have a `docstring` that describes what this Invocation
   does.
-- While not strictly required, we suggest every invocation class name ends in
-  "Invocation", eg "CropImageInvocation".
-- Every Invocation must use the `@invocation` decorator to provide its unique
-  invocation type. You may also provide its title, tags and category using the
-  decorator.
+- Every Invocation must have a unique `type` field defined which becomes its
+  indentifier.
 - Invocations are strictly typed. We make use of the native
   [typing](https://docs.python.org/3/library/typing.html) library and the
   installed [pydantic](https://pydantic-docs.helpmanual.io/) library for
@@ -44,11 +43,12 @@ The first set of things we need to do when creating a new Invocation are -
 So let us do that.
 
 ```python
-from .baseinvocation import BaseInvocation, invocation
+from typing import Literal
+from .baseinvocation import BaseInvocation
 
-@invocation('resize')
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 ```
 
 That's great.
@@ -62,10 +62,8 @@ our Invocation takes.
 
 ### **Inputs**
 
-Every Invocation input must be defined using the `InputField` function. This is
-a wrapper around the pydantic `Field` function, which handles a few extra things
-and provides type hints. Like everything else, this should be strictly typed and
-defined.
+Every Invocation input is a pydantic `Field` and like everything else should be
+strictly typed and defined.
 
 So let us create these inputs for our Invocation. First up, the `image` input we
 need. Generally, we can use standard variable types in Python but InvokeAI
@@ -78,51 +76,55 @@ create your own custom field types later in this guide. For now, let's go ahead
 and use it.
 
 ```python
-from .baseinvocation import BaseInvocation, InputField, invocation
-from .primitives import ImageField
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation
+from ..models.image import ImageField
 
-@invocation('resize')
 class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 
     # Inputs
-    image: ImageField = InputField(description="The input image")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
 ```
 
 Let us break down our input code.
 
 ```python
-image: ImageField = InputField(description="The input image")
+image: Union[ImageField, None] = Field(description="The input image", default=None)
 ```
 
-| Part      | Value                                       | Description                                                                     |
-| --------- | ------------------------------------------- | ------------------------------------------------------------------------------- |
-| Name      | `image`                                     | The variable that will hold our image                                           |
-| Type Hint | `ImageField`                                | The types for our field. Indicates that the image must be an `ImageField` type. |
-| Field     | `InputField(description="The input image")` | The image variable is an `InputField` which needs a description.                |
+| Part      | Value                                                | Description                                                                                        |
+| --------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
+| Name      | `image`                                              | The variable that will hold our image                                                              |
+| Type Hint | `Union[ImageField, None]`                            | The types for our field. Indicates that the image can either be an `ImageField` type or `None`     |
+| Field     | `Field(description="The input image", default=None)` | The image variable is a field which needs a description and a default value that we set to `None`. |
 
 Great. Now let us create our other inputs for `width` and `height`
 
 ```python
-from .baseinvocation import BaseInvocation, InputField, invocation
-from .primitives import ImageField
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation
+from ..models.image import ImageField
 
-@invocation('resize')
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 
     # Inputs
-    image: ImageField = InputField(description="The input image")
-    width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
 ```
 
-As you might have noticed, we added two new arguments to the `InputField`
-definition for `width` and `height`, called `gt` and `le`. They stand for
-_greater than or equal to_ and _less than or equal to_.
-
-These impose contraints on those fields, and will raise an exception if the
-values do not meet the constraints. Field constraints are provided by
-**pydantic**, so anything you see in the **pydantic docs** will work.
+As you might have noticed, we added two new parameters to the field type for
+`width` and `height` called `gt` and `le`. These basically stand for _greater
+than or equal to_ and _less than or equal to_. There are various other param
+types for field that you can find on the **pydantic** documentation.
 
 **Note:** _Any time it is possible to define constraints for our field, we
 should do it so the frontend has more information on how to parse this field._
@@ -139,17 +141,20 @@ that are provided by it by InvokeAI.
 Let us create this function first.
 
 ```python
-from .baseinvocation import BaseInvocation, InputField, invocation
-from .primitives import ImageField
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField
 
-@invocation('resize')
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 
     # Inputs
-    image: ImageField = InputField(description="The input image")
-    width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext):
         pass
@@ -168,18 +173,21 @@ all the necessary info related to image outputs. So let us use that.
 We will cover how to create your own output types later in this guide.
 
 ```python
-from .baseinvocation import BaseInvocation, InputField, invocation
-from .primitives import ImageField
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField
 from .image import ImageOutput
 
-@invocation('resize')
 class ResizeInvocation(BaseInvocation):
     '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 
     # Inputs
-    image: ImageField = InputField(description="The input image")
-    width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         pass
@@ -187,34 +195,39 @@ class ResizeInvocation(BaseInvocation):
 
 Perfect. Now that we have our Invocation setup, let us do what we want to do.
 
-- We will first load the image using one of the services provided by InvokeAI to
-  load the image.
+- We will first load the image. Generally we do this using the `PIL` library but
+  we can use one of the services provided by InvokeAI to load the image.
 - We will resize the image using `PIL` to our input data.
 - We will output this image in the format we set above.
 
 So let's do that.
 
 ```python
-from .baseinvocation import BaseInvocation, InputField, invocation
-from .primitives import ImageField
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext
+from ..models.image import ImageField, ResourceOrigin, ImageCategory
 from .image import ImageOutput
 
-@invocation("resize")
 class ResizeInvocation(BaseInvocation):
-    """Resizes an image"""
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
 
-    image: ImageField = InputField(description="The input image")
-    width: int = InputField(default=512, ge=64, le=2048, description="Width of the new image")
-    height: int = InputField(default=512, ge=64, le=2048, description="Height of the new image")
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # Load the image using InvokeAI's predefined Image Service. Returns the PIL image.
-        image = context.services.images.get_pil_image(self.image.image_name)
+        # Load the image using InvokeAI's predefined Image Service.
+        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
 
         # Resizing the image
+        # Because we used the above service, we already have a PIL image. So we can simply resize.
         resized_image = image.resize((self.width, self.height))
 
-        # Save the image using InvokeAI's predefined Image Service. Returns the prepared PIL image.
+        # Preparing the image for output using InvokeAI's predefined Image Service.
         output_image = context.services.images.create(
             image=resized_image,
             image_origin=ResourceOrigin.INTERNAL,
@@ -228,6 +241,7 @@ class ResizeInvocation(BaseInvocation):
         return ImageOutput(
             image=ImageField(
                 image_name=output_image.image_name,
+                image_origin=output_image.image_origin,
             ),
             width=output_image.width,
             height=output_image.height,
@@ -239,24 +253,6 @@ certain way that the images need to be dispatched in order to be stored and read
 correctly. In 99% of the cases when dealing with an image output, you can simply
 copy-paste the template above.
 
-### Customization
-
-We can use the `@invocation` decorator to provide some additional info to the
-UI, like a custom title, tags and category.
-
-We also encourage providing a version. This must be a
-[semver](https://semver.org/) version string ("$MAJOR.$MINOR.$PATCH"). The UI
-will let users know if their workflow is using a mismatched version of the node.
-
-```python
-@invocation("resize", title="My Resizer", tags=["resize", "image"], category="My Invocations", version="1.0.0")
-class ResizeInvocation(BaseInvocation):
-    """Resizes an image"""
-
-    image: ImageField = InputField(description="The input image")
-    ...
-```
-
 That's it. You made your own **Resize Invocation**.
 
 ## Result
@@ -274,57 +270,9 @@ new Invocation ready to be used.
 
 ![resize node editor](../assets/contributing/resize_node_editor.png)
 
-## Contributing Nodes
+# Advanced
 
-Once you've created a Node, the next step is to share it with the community! The
-best way to do this is to submit a Pull Request to add the Node to the
-[Community Nodes](nodes/communityNodes) list. If you're not sure how to do that,
-take a look a at our [contributing nodes overview](contributingNodes).
-
-## Advanced
-
-### Custom Output Types
-
-Like with custom inputs, sometimes you might find yourself needing custom
-outputs that InvokeAI does not provide. We can easily set one up.
-
-Now that you are familiar with Invocations and Inputs, let us use that knowledge
-to create an output that has an `image` field, a `color` field and a `string`
-field.
-
-- An invocation output is a class that derives from the parent class of
-  `BaseInvocationOutput`.
-- All invocation outputs must use the `@invocation_output` decorator to provide
-  their unique output type.
-- Output fields must use the provided `OutputField` function. This is very
-  similar to the `InputField` function described earlier - it's a wrapper around
-  `pydantic`'s `Field()`.
-- It is not mandatory but we recommend using names ending with `Output` for
-  output types.
-- It is not mandatory but we highly recommend adding a `docstring` to describe
-  what your output type is for.
-
-Now that we know the basic rules for creating a new output type, let us go ahead
-and make it.
-
-```python
-from .baseinvocation import BaseInvocationOutput, OutputField, invocation_output
-from .primitives import ImageField, ColorField
-
-@invocation_output('image_color_string_output')
-class ImageColorStringOutput(BaseInvocationOutput):
-    '''Base class for nodes that output a single image'''
-
-    image: ImageField = OutputField(description="The image")
-    color: ColorField = OutputField(description="The color")
-    text: str = OutputField(description="The string")
-```
-
-That's all there is to it.
-
-<!-- TODO: DANGER - we probably do not want people to create their own field types, because this requires a lot of work on the frontend to accomodate.
-
-### Custom Input Fields
+## Custom Input Fields
 
 Now that you know how to create your own Invocations, let us dive into slightly
 more advanced topics.
@@ -378,7 +326,173 @@ like this.
 color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
 ```
 
-### Custom Components For Frontend
+**Extra Config**
+
+All input fields also take an additional `Config` class that you can use to do
+various advanced things like setting required parameters and etc.
+
+Let us do that for our _ColorField_ and enforce all the values because we did
+not define any defaults for our fields.
+
+```python
+class ColorField(BaseModel):
+    '''A field that holds the rgba values of a color'''
+    r: int = Field(ge=0, le=255, description="The red channel")
+    g: int = Field(ge=0, le=255, description="The green channel")
+    b: int = Field(ge=0, le=255, description="The blue channel")
+    a: int = Field(ge=0, le=255, description="The alpha channel")
+
+    class Config:
+        schema_extra = {"required": ["r", "g", "b", "a"]}
+```
+
+Now it becomes mandatory for the user to supply all the values required by our
+input field.
+
+We will discuss the `Config` class in extra detail later in this guide and how
+you can use it to make your Invocations more robust.
+
+## Custom Output Types
+
+Like with custom inputs, sometimes you might find yourself needing custom
+outputs that InvokeAI does not provide. We can easily set one up.
+
+Now that you are familiar with Invocations and Inputs, let us use that knowledge
+to put together a custom output type for an Invocation that returns _width_,
+_height_ and _background_color_ that we need to create a blank image.
+
+- A custom output type is a class that derives from the parent class of
+  `BaseInvocationOutput`.
+- It is not mandatory but we recommend using names ending with `Output` for
+  output types. So we'll call our class `BlankImageOutput`
+- It is not mandatory but we highly recommend adding a `docstring` to describe
+  what your output type is for.
+- Like Invocations, each output type should have a `type` variable that is
+  **unique**
+
+Now that we know the basic rules for creating a new output type, let us go ahead
+and make it.
+
+```python
+from typing import Literal
+from pydantic import Field
+
+from .baseinvocation import BaseInvocationOutput
+
+class BlankImageOutput(BaseInvocationOutput):
+    '''Base output type for creating a blank image'''
+    type: Literal['blank_image_output'] = 'blank_image_output'
+
+    # Inputs
+    width: int = Field(description='Width of blank image')
+    height: int = Field(description='Height of blank image')
+    bg_color: ColorField = Field(description='Background color of blank image')
+
+    class Config:
+        schema_extra = {"required": ["type", "width", "height", "bg_color"]}
+```
+
+All set. We now have an output type that requires what we need to create a
+blank_image. And if you noticed it, we even used the `Config` class to ensure
+the fields are required.
+
+## Custom Configuration
+
+As you might have noticed when making inputs and outputs, we used a class called
+`Config` from _pydantic_ to further customize them. Because our inputs and
+outputs essentially inherit from _pydantic_'s `BaseModel` class, all
+[configuration options](https://docs.pydantic.dev/latest/usage/schema/#schema-customization)
+that are valid for _pydantic_ classes are also valid for our inputs and outputs.
+You can do the same for your Invocations too but InvokeAI makes our life a
+little bit easier on that end.
+
+InvokeAI provides a custom configuration class called `InvocationConfig`
+particularly for configuring Invocations. This is exactly the same as the raw
+`Config` class from _pydantic_ with some extra stuff on top to help faciliate
+parsing of the scheme in the frontend UI.
+
+At the current moment, tihs `InvocationConfig` class is further improved with
+the following features related the `ui`.
+
+| Config Option | Field Type                                                                                                    | Example                                                                                                               |
+| ------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
+| type_hints    | `Dict[str, Literal["integer", "float", "boolean", "string", "enum", "image", "latents", "model", "control"]]` | `type_hint: "model"` provides type hints related to the model like displaying a list of available models              |
+| tags          | `List[str]`                                                                                                   | `tags: ['resize', 'image']` will classify your invocation under the tags of resize and image.                         |
+| title         | `str`                                                                                                         | `title: 'Resize Image` will rename your to this custom title rather than infer from the name of the Invocation class. |
+
+So let us update your `ResizeInvocation` with some extra configuration and see
+how that works.
+
+```python
+from typing import Literal, Union
+from pydantic import Field
+
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from ..models.image import ImageField, ResourceOrigin, ImageCategory
+from .image import ImageOutput
+
+class ResizeInvocation(BaseInvocation):
+    '''Resizes an image'''
+    type: Literal['resize'] = 'resize'
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The input image", default=None)
+    width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
+    height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
+
+    class Config(InvocationConfig):
+        schema_extra: {
+            ui: {
+                tags: ['resize', 'image'],
+                title: ['My Custom Resize']
+            }
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Load the image using InvokeAI's predefined Image Service.
+        image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
+
+        # Resizing the image
+        # Because we used the above service, we already have a PIL image. So we can simply resize.
+        resized_image = image.resize((self.width, self.height))
+
+        # Preparing the image for output using InvokeAI's predefined Image Service.
+        output_image = context.services.images.create(
+            image=resized_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        # Returning the Image
+        return ImageOutput(
+            image=ImageField(
+                image_name=output_image.image_name,
+                image_origin=output_image.image_origin,
+            ),
+            width=output_image.width,
+            height=output_image.height,
+        )
+```
+
+We now customized our code to let the frontend know that our Invocation falls
+under `resize` and `image` categories. So when the user searches for these
+particular words, our Invocation will show up too.
+
+We also set a custom title for our Invocation. So instead of being called
+`Resize`, it will be called `My Custom Resize`.
+
+As simple as that.
+
+As time goes by, InvokeAI will further improve and add more customizability for
+Invocation configuration. We will have more documentation regarding this at a
+later time.
+
+# **[TODO]**
+
+## Custom Components For Frontend
 
 Every backend input type should have a corresponding frontend component so the
 UI knows what to render when you use a particular field type.
@@ -396,4 +510,281 @@ Let us create a new component for our custom color field we created above. When
 we use a color field, let us say we want the UI to display a color picker for
 the user to pick from rather than entering values. That is what we will build
 now.
--->
+
+---
+
+# OLD -- TO BE DELETED OR MOVED LATER
+
+---
+
+## Creating a new invocation
+
+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."""
+
+    # 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_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+```
+
+Each portion is important to implement correctly.
+
+### 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.
+
+### Config
+
+```py
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
+```
+
+This is an optional configuration for the invocation. It inherits from
+pydantic's model `Config` class, and it used primarily to customize the
+autogenerated OpenAPI schema.
+
+The UI relies on the OpenAPI schema in two ways:
+
+- An API client & Typescript types are generated from it. This happens at build
+  time.
+- The node editor parses the schema into a template used by the UI to create the
+  node editor UI. This parsing happens at runtime.
+
+In this example, a `ui` key has been added to the `schema_extra` dict to provide
+some tags for the UI, to facilitate filtering nodes.
+
+See the Schema Generation section below for more information.
+
+### Invoke Function
+
+```py
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(
+            self.image.image_origin, self.image.image_name
+        )
+        results = context.services.restoration.upscale_and_reconstruct(
+            image_list=[[image, 0]],
+            upscale=(self.level, self.strength),
+            strength=0.0,  # GFPGAN strength
+            save_original=False,
+            image_callback=None,
+        )
+
+        # Results are image and seed, unwrap for now
+        # TODO: can this return multiple results?
+        image_dto = context.services.images.create(
+            image=results[0][0],
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+        )
+
+        return ImageOutput(
+            image=ImageField(
+                image_name=image_dto.image_name,
+                image_origin=image_dto.image_origin,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+```
+
+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"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
+```
+
+Output classes look like an invocation class without the invoke method. Prefer
+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"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+```
+
+The OpenAPI schema that results from this `ImageOutput` will have the `type`,
+`image`, `width` and `height` properties marked as optional, even though we know
+they will always have a value.
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    # Add schema customization
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
+```
+
+With the customization in place, the schema will now show these properties as
+required, obviating the need for extensive null checks in client code.
+
+See this `pydantic` issue for discussion on this solution:
+<https://github.com/pydantic/pydantic/discussions/4577>

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -35,34 +35,46 @@ access.
 
 ## Backend
 
-The backend is contained within the `./invokeai/backend` and `./invokeai/app` directories.
-To get started please install the development dependencies.
+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 ".[dev,test]"
+pip install ".[test]"
 ```
 
-These are optional groups of packages which are defined within the `pyproject.toml`
-and will be required for testing the changes you make to the code.
+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.
 
-### Tests
+### Running Tests
 
-See the [tests documentation](./TESTS.md) for information about running and writing tests.
-### Reloading Changes
+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`.
 
-Experimenting with changes to the Python source code is a drag if you have to re-start the server —
-and re-load those multi-gigabyte models —
-after every change.
+```zsh
+pytest --cov
+```
 
-For a faster development workflow, add the `--dev_reload` flag when starting the server.
-The server will watch for changes to all the Python files in the `invokeai` directory and apply those changes to the
-running server on the fly.
+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`.
 
-This will allow you to avoid restarting the server (and reloading models) in most cases, but there are some caveats; see
-the [jurigged documentation](https://github.com/breuleux/jurigged#caveats) for details.
+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
 
@@ -142,23 +154,6 @@ and so you'll have access to the same python environment as the InvokeAI app.
 
 This is _super_ handy.
 
-#### Enabling Type-Checking with Pylance
-
-We use python's typing system in InvokeAI. PR reviews will include checking that types are present and correct. We don't enforce types with `mypy` at this time, but that is on the horizon.
-
-Using a code analysis tool to automatically type check your code (and types) is very important when writing with types. These tools provide immediate feedback in your editor when types are incorrect, and following their suggestions lead to fewer runtime bugs.
-
-Pylance, installed at the beginning of this guide, is the de-facto python LSP (language server protocol). It provides type checking in the editor (among many other features). Once installed, you do need to enable type checking manually:
-
-- Open a python file
-- Look along the status bar in VSCode for `{ } Python`
-- Click the `{ }`
-- Turn type checking on - basic is fine
-
-You'll now see red squiggly lines where type issues are detected. Hover your cursor over the indicated symbols to see what's wrong.
-
-In 99% of cases when the type checker says there is a problem, there really is a problem, and you should take some time to understand and resolve what it is pointing out.
-
 #### Debugging configs with `launch.json`
 
 Debugging configs are managed in a `launch.json` file. Like most VSCode configs,

docs/contributing/TESTS.md

@@ -1,89 +0,0 @@
-# InvokeAI Backend Tests
-
-We use `pytest` to run the backend python tests. (See [pyproject.toml](/pyproject.toml) for the default `pytest` options.)
-
-## Fast vs. Slow
-All tests are categorized as either 'fast' (no test annotation) or 'slow' (annotated with the `@pytest.mark.slow` decorator).
-
-'Fast' tests are run to validate every PR, and are fast enough that they can be run routinely during development.
-
-'Slow' tests are currently only run manually on an ad-hoc basis. In the future, they may be automated to run nightly. Most developers are only expected to run the 'slow' tests that directly relate to the feature(s) that they are working on.
-
-As a rule of thumb, tests should be marked as 'slow' if there is a chance that they take >1s (e.g. on a CPU-only machine with slow internet connection). Common examples of slow tests are tests that depend on downloading a model, or running model inference.
-
-## Running Tests
-
-Below are some common test commands:
-```bash
-# Run the fast tests. (This implicitly uses the configured default option: `-m "not slow"`.)
-pytest tests/
-
-# Equivalent command to run the fast tests.
-pytest tests/ -m "not slow"
-
-# Run the slow tests.
-pytest tests/ -m "slow"
-
-# Run the slow tests from a specific file.
-pytest tests/path/to/slow_test.py -m "slow"
-
-# Run all tests (fast and slow).
-pytest tests -m ""
-```
-
-## Test Organization
-
-All backend tests are in the [`tests/`](/tests/) directory. This directory mirrors the organization of the `invokeai/` directory. For example, tests for `invokeai/model_management/model_manager.py` would be found in `tests/model_management/test_model_manager.py`.
-
-TODO: The above statement is aspirational. A re-organization of legacy tests is required to make it true.
-
-## Tests that depend on models
-
-There are a few things to keep in mind when adding tests that depend on models.
-
-1. If a required model is not already present, it should automatically be downloaded as part of the test setup.
-2. If a model is already downloaded, it should not be re-downloaded unnecessarily.
-3. Take reasonable care to keep the total number of models required for the tests low. Whenever possible, re-use models that are already required for other tests. If you are adding a new model, consider including a comment to explain why it is required/unique.
-
-There are several utilities to help with model setup for tests. Here is a sample test that depends on a model:
-```python
-import pytest
-import torch
-
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.util.test_utils import install_and_load_model
-
-@pytest.mark.slow
-def test_model(model_installer, torch_device):
-    model_info = install_and_load_model(
-        model_installer=model_installer,
-        model_path_id_or_url="HF/dummy_model_id",
-        model_name="dummy_model",
-        base_model=BaseModelType.StableDiffusion1,
-        model_type=ModelType.Dummy,
-    )
-
-    dummy_input = build_dummy_input(torch_device)
-
-    with torch.no_grad(), model_info as model:
-        model.to(torch_device, dtype=torch.float32)
-        output = model(dummy_input)
-
-    # Validate output...
-
-```
-
-## Test Coverage
-
-To review test coverage, append `--cov` to your pytest command:
-```bash
-pytest tests/ --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 output is particularly helpful in identifying untested statements where coverage should be improved. The HTML report can be viewed by opening `./coverage/html/index.html`.
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)

docs/contributing/contribution_guides/development.md

@@ -4,21 +4,14 @@
 
 If you are looking to help to with a code contribution, InvokeAI uses several different technologies under the hood: Python (Pydantic, FastAPI, diffusers) and Typescript (React, Redux Toolkit, ChakraUI, Mantine, Konva). Familiarity with StableDiffusion and image generation concepts is helpful, but not essential. 
 
-
-## **Get Started**
-
-To get started, take a look at our [new contributors checklist](newContributorChecklist.md)
-
-Once you're setup, for more information, you can review the documentation specific to your area of interest:
+For more information, please review our area specific documentation:
 
 * #### [InvokeAI Architecure](../ARCHITECTURE.md)
-* #### [Frontend Documentation](./contributingToFrontend.md)
+* #### [Frontend Documentation](development_guides/contributingToFrontend.md)
 * #### [Node Documentation](../INVOCATIONS.md)
 * #### [Local Development](../LOCAL_DEVELOPMENT.md)
 
-
-
-If you don't feel ready to make a code contribution yet, no problem! You can also help out in other ways, such as [documentation](documentation.md), [translation](translation.md) or helping support other users and triage issues as they're reported in GitHub.
+If you don't feel ready to make a code contribution yet, no problem! You can also help out in other ways, such as [documentation](documentation.md) or [translation](translation.md).
 
 There are two paths to making a development contribution: 
 
@@ -30,18 +23,67 @@ There are two paths to making a development contribution:
 
 ## Best Practices: 
 * Keep your pull requests small. Smaller pull requests are more likely to be accepted and merged
-* Comments! Commenting your code helps reviewers easily understand your contribution
+* Comments! Commenting your code helps reviwers easily understand your contribution
 * Use Python and Typescript’s typing systems, and consider using an editor with [LSP](https://microsoft.github.io/language-server-protocol/) support to streamline development
 * Make all communications public. This ensure knowledge is shared with the whole community
 
+## **How do I make a contribution?**
+
+Never made an open source contribution before? Wondering how contributions work in our project? Here's a quick rundown!
+
+Before starting these steps, ensure you have your local environment [configured for development](../LOCAL_DEVELOPMENT.md).
+
+1.  Find a [good first issue](https://github.com/invoke-ai/InvokeAI/contribute) that you are interested in addressing or a feature that you would like to add. Then, reach out to our team in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord to ensure you are  setup for success. 
+2. Fork the [InvokeAI](https://github.com/invoke-ai/InvokeAI) repository to your GitHub profile. This means that you will have a copy of the repository under **your-GitHub-username/InvokeAI**.
+3. Clone the repository to your local machine using:
+
+```bash
+git clone https://github.com/your-GitHub-username/InvokeAI.git
+```
+
+If you're unfamiliar with using Git through the commandline, [GitHub Desktop](https://desktop.github.com) is a easy-to-use alternative with a UI. You can do all the same steps listed here, but through the interface. 
+
+4. Create a new branch for your fix using:
+
+```bash
+git checkout -b branch-name-here
+```
+
+5. Make the appropriate changes for the issue you are trying to address or the feature that you want to add.
+6. Add the file contents of the changed files to the "snapshot" git uses to manage the state of the project, also known as the index:
+
+```bash
+git add insert-paths-of-changed-files-here
+```
+
+7. Store the contents of the index with a descriptive message.
+
+```bash
+git commit -m "Insert a short message of the changes made here"
+```
+
+8. Push the changes to the remote repository using
+
+```markdown
+git push origin branch-name-here
+```
+
+9. Submit a pull request to the **main** branch of the InvokeAI repository.
+10. Title the pull request with a short description of the changes made and the issue or bug number associated with your change. For example, you can title an issue like so "Added more log outputting to resolve #1234".
+11. In the description of the pull request, explain the changes that you made, any issues you think exist with the pull request you made, and any questions you have for the maintainer. It's OK if your pull request is not perfect (no pull request is), the reviewer will be able to help you fix any problems and improve it!
+12. Wait for the pull request to be reviewed by other collaborators.
+13. Make changes to the pull request if the reviewer(s) recommend them.
+14. Celebrate your success after your pull request is merged!
+
+If you’d like to learn more about contributing to Open Source projects, here is a [Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). 
+
 ## **Where can I go for help?**
 
 If you need help, you can ask questions in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord.
 
-For frontend related work, **@psychedelicious** is the best person to reach out to. 
-
-For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@psychedelicious**.
+For frontend related work, **@pyschedelicious** is the best person to reach out to. 
 
+For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.
 
 ## **What does the Code of Conduct mean for me?**
 

docs/contributing/contribution_guides/documentation.md

@@ -10,4 +10,4 @@ When updating or creating documentation, please keep in mind InvokeAI is a tool
 
 ## Help & Questions
 
-Please ping @imic or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.
+Please ping @imic1 or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.

docs/contributing/contribution_guides/newContributorChecklist.md

@@ -1,68 +0,0 @@
-# New Contributor Guide
-
-If you're a new contributor to InvokeAI or Open Source Projects, this is the guide for you. 
-
-## New Contributor Checklist
-- [x] Set up your local development environment & fork of InvokAI by following [the steps outlined here](../../installation/020_INSTALL_MANUAL.md#developer-install)
-- [x] Set up your local tooling with [this guide](InvokeAI/contributing/LOCAL_DEVELOPMENT/#developing-invokeai-in-vscode). Feel free to skip this step if you already have tooling you're comfortable with. 
-- [x] Familiarize yourself with [Git](https://www.atlassian.com/git) & our project structure by reading through the [development documentation](development.md)
-- [x] Join the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord
-- [x] Choose an issue to work on! This can be achieved by asking in the #dev-chat channel, tackling a [good first issue](https://github.com/invoke-ai/InvokeAI/contribute) or finding an item on the [roadmap](https://github.com/orgs/invoke-ai/projects/7). If nothing in any of those places catches your eye, feel free to work on something of interest to you! 
-- [x] Make your first Pull Request with the guide below
-- [x] Happy development! Don't be afraid to ask for help - we're happy to help you contribute!
-
-
-## How do I make a contribution?
-
-Never made an open source contribution before? Wondering how contributions work in our project? Here's a quick rundown!
-
-Before starting these steps, ensure you have your local environment [configured for development](../LOCAL_DEVELOPMENT.md).
-
-1.  Find a [good first issue](https://github.com/invoke-ai/InvokeAI/contribute) that you are interested in addressing or a feature that you would like to add. Then, reach out to our team in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord to ensure you are  setup for success. 
-2. Fork the [InvokeAI](https://github.com/invoke-ai/InvokeAI) repository to your GitHub profile. This means that you will have a copy of the repository under **your-GitHub-username/InvokeAI**.
-3. Clone the repository to your local machine using:
-```bash
-git clone https://github.com/your-GitHub-username/InvokeAI.git
-```
-If you're unfamiliar with using Git through the commandline, [GitHub Desktop](https://desktop.github.com) is a easy-to-use alternative with a UI. You can do all the same steps listed here, but through the interface. 
-4. Create a new branch for your fix using:
-```bash
-git checkout -b branch-name-here
-```
-5. Make the appropriate changes for the issue you are trying to address or the feature that you want to add.
-6. Add the file contents of the changed files to the "snapshot" git uses to manage the state of the project, also known as the index:
-```bash
-git add -A
-```
-7. Store the contents of the index with a descriptive message.
-```bash
-git commit -m "Insert a short message of the changes made here"
-```
-8. Push the changes to the remote repository using
-```bash
-git push origin branch-name-here
-```
-9. Submit a pull request to the **main** branch of the InvokeAI repository. If you're not sure how to, [follow this guide](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request)
-10. Title the pull request with a short description of the changes made and the issue or bug number associated with your change. For example, you can title an issue like so "Added more log outputting to resolve #1234".
-11. In the description of the pull request, explain the changes that you made, any issues you think exist with the pull request you made, and any questions you have for the maintainer. It's OK if your pull request is not perfect (no pull request is), the reviewer will be able to help you fix any problems and improve it!
-12. Wait for the pull request to be reviewed by other collaborators.
-13. Make changes to the pull request if the reviewer(s) recommend them.
-14. Celebrate your success after your pull request is merged!
-
-If you’d like to learn more about contributing to Open Source projects, here is a [Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). 
-
-
-## Best Practices: 
-* Keep your pull requests small. Smaller pull requests are more likely to be accepted and merged
-* Comments! Commenting your code helps reviewers easily understand your contribution
-* Use Python and Typescript’s typing systems, and consider using an editor with [LSP](https://microsoft.github.io/language-server-protocol/) support to streamline development
-* Make all communications public. This ensure knowledge is shared with the whole community
-
-
-## **Where can I go for help?**
-
-If you need help, you can ask questions in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord.
-
-For frontend related work, **@pyschedelicious** is the best person to reach out to. 
-
-For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.

docs/features/CONCEPTS.md

@@ -21,8 +21,8 @@ TI files that you'll encounter are `.pt` and `.bin` files, which are produced by
 different TI training packages. InvokeAI supports both formats, but its
 [built-in TI training system](TRAINING.md) produces `.pt`.
 
-[Hugging Face](https://huggingface.co/sd-concepts-library) has
-amassed a large library of >800 community-contributed TI files covering a
+The [Hugging Face company](https://huggingface.co/sd-concepts-library) has
+amassed a large ligrary of >800 community-contributed TI files covering a
 broad range of subjects and styles. You can also install your own or others' TI files 
 by placing them in the designated directory for the compatible model type
 

docs/features/CONFIGURATION.md

@@ -159,7 +159,7 @@ groups in `invokeia.yaml`:
 | `host`     | `localhost`      | Name or IP address of the network interface that the web server will listen on  |
 | `port`     | `9090`           | Network port number that the web server will listen on  |
 | `allow_origins`  | `[]`       | A list of host names or IP addresses that are allowed to connect to the InvokeAI API in the format `['host1','host2',...]` |
-| `allow_credentials` | `true`   | Require credentials for a foreign host to access the InvokeAI API (don't change this) |
+| `allow_credentials | `true`   | Require credentials for a foreign host to access the InvokeAI API (don't change this) |
 | `allow_methods` | `*`         | List of HTTP methods ("GET", "POST") that the web server is allowed to use when accessing the API  |
 | `allow_headers` | `*`         | List of HTTP headers that the web server will accept when accessing the API  |
 
@@ -175,27 +175,22 @@ These configuration settings allow you to enable and disable various InvokeAI fe
 | `internet_available` | `true`     | When a resource is not available locally, try to fetch it via the internet |
 | `log_tokenization` | `false`      | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
 | `patchmatch` | `true`     | Activate the "patchmatch" algorithm for improved inpainting |
+| `restore`    | `true`     | Activate the facial restoration features (DEPRECATED; restoration features will be removed in 3.0.0) |
 
-### Generation
+### Memory/Performance
 
 These options tune InvokeAI's memory and performance characteristics.
 
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `sequential_guidance` | `false`       | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss                                                                                                                                          |
-| `attention_type`      | `auto`        | Select the type of attention to use. One of `auto`,`normal`,`xformers`,`sliced`, or `torch-sdp`                                                                                                                                                                  |
-| `attention_slice_size` | `auto`       | When "sliced" attention is selected, set the slice size. One of `auto`, `balanced`, `max` or the integers 1-8|
-| `force_tiled_decode`  | `false`       | Force the VAE step to decode in tiles, reducing memory consumption at the cost of performance |
-
-### Device
-
-These options configure the generation execution device.
-
-| Setting               | Default Value | Description                                                                                                                                                                                                                                                      |
-|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| `device`           | `auto`        | Preferred execution device. One of `auto`, `cpu`, `cuda`, `cuda:1`, `mps`. `auto` will choose the device depending on the hardware platform and the installed torch capabilities. |
-| `precision`           | `auto`        | Floating point precision. One of `auto`, `float16` or `float32`. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system |
-
+| Setting  | Default Value  |  Description |
+|----------|----------------|--------------|
+| `always_use_cpu`     | `false`      | Use the CPU to generate images, even if a GPU is available |
+| `free_gpu_mem`       | `false`      | Aggressively free up GPU memory after each operation; this will allow you to run in low-VRAM environments with some performance penalties |
+| `max_cache_size`       | `6`      | Amount of CPU RAM (in GB) to reserve for caching models in memory; more cache allows you to keep models in memory and switch among them quickly |
+| `max_vram_cache_size`  | `2.75`   | Amount of GPU VRAM (in GB) to reserve for caching models in VRAM; more cache speeds up generation but reduces the size of the images that can be generated. This can be set to zero to maximize the amount of memory available for generation. |
+| `precision`       | `auto`      | Floating point precision. One of `auto`, `float16` or `float32`. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system |
+| `sequential_guidance`     | `false`      | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss |
+| `xformers_enabled`        | `true`      | If the x-formers memory-efficient attention module is installed, activate it for better memory usage and generation speed|
+| `tiled_decode`            | `false`     | If true, then during the VAE decoding phase the image will be decoded a section at a time, reducing memory consumption at the cost of a performance hit |
 
 ### Paths
 

docs/features/CONTROLNET.md

@@ -1,11 +1,13 @@
 ---
-title: Control Adapters
+title: ControlNet
 ---
 
-# :material-loupe: Control Adapters
+# :material-loupe: ControlNet
 
 ## ControlNet
 
+ControlNet
+
 ControlNet is a powerful set of features developed by the open-source
 community (notably, Stanford researcher
 [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to
@@ -18,7 +20,7 @@ towards generating images that better fit your desired style or
 outcome.
 
 
-#### How it works
+### How it works
 
 ControlNet works by analyzing an input image, pre-processing that
 image to identify relevant information that can be interpreted by each
@@ -28,7 +30,7 @@ composition, or other aspects of the image to better achieve a
 specific result.
 
 
-#### Models
+### Models
 
 InvokeAI provides access to a series of ControlNet models that provide
 different effects or styles in your generated images.  Currently
@@ -94,8 +96,6 @@ A model that generates normal maps from input images, allowing for more realisti
 **Image Segmentation**: 
 A model that divides input images into segments or regions, each of which corresponds to a different object or part of the image. (More details coming soon)
 
-**QR Code Monster**:
-A model that helps generate creative QR codes that still scan. Can also be used to create images with text, logos or shapes within them. 
 
 **Openpose**: 
 The OpenPose control model allows for the identification of the general pose of a character by pre-processing an existing image with a clear human structure. With advanced options, Openpose can also detect the face or hands in the image. 
@@ -104,7 +104,7 @@ The OpenPose control model allows for the identification of the general pose of
 
 The MediaPipe Face identification processor is able to clearly identify facial features in order to capture vivid expressions of human faces.
 
-**Tile**:
+**Tile (experimental)**:
 
 The Tile model fills out details in the image to match the image, rather than the prompt. The Tile Model is a versatile tool that offers a range of functionalities. Its primary capabilities can be boiled down to two main behaviors:
 
@@ -117,10 +117,12 @@ The Tile Model can be a powerful tool in your arsenal for enhancing image qualit
 
 With Pix2Pix, you can input an image into the controlnet, and then "instruct" the model to change it using your prompt. For example, you can say "Make it winter" to add more wintry elements to a scene.
 
+**Inpaint**: Coming Soon - Currently this model is available but not functional on the Canvas. An upcoming release will provide additional capabilities for using this model when inpainting.
+
 Each of these models can be adjusted and combined with other ControlNet models to achieve different results, giving you even more control over your image generation process.
 
 
-### Using ControlNet
+## Using ControlNet
 
 To use ControlNet, you can simply select the desired model and adjust both the ControlNet and Pre-processor settings to achieve the desired result. You can also use multiple ControlNet models at the same time, allowing you to achieve even more complex effects or styles in your generated images.
 
@@ -132,31 +134,3 @@ Weight - Strength of the Controlnet model applied to the generation for the sect
 Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
 
 Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.
-
-
-## IP-Adapter
-
-[IP-Adapter](https://ip-adapter.github.io) is a tooling that allows for image prompt capabilities with text-to-image diffusion models. IP-Adapter works by analyzing the given image prompt to extract features, then passing those features to the UNet along with any other conditioning provided. 
-
-![IP-Adapter + T2I](https://github.com/tencent-ailab/IP-Adapter/raw/main/assets/demo/ip_adpter_plus_multi.jpg)
-
-![IP-Adapter + IMG2IMG](https://github.com/tencent-ailab/IP-Adapter/blob/main/assets/demo/image-to-image.jpg)
-
-#### Installation
-There are several ways to install IP-Adapter models with an existing InvokeAI installation:
-
-1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [5] to download models.
-2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.  
-3. **Advanced -- Not recommended ** Manually downloading the IP-Adapter and Image Encoder files - Image Encoder folders shouid be placed in the `models\any\clip_vision` folders. IP Adapter Model folders should be placed in the relevant `ip-adapter` folder of relevant base model folder of Invoke root directory. For example, for the SDXL IP-Adapter, files should be added to the `model/sdxl/ip_adapter/` folder. 
-
-#### Using IP-Adapter
-
-IP-Adapter can be used by navigating to the *Control Adapters* options and enabling IP-Adapter. 
-
-IP-Adapter requires an image to be used as the Image Prompt. It can also be used in conjunction with text prompts, Image-to-Image, Inpainting, Outpainting, ControlNets and LoRAs.
-
-
-Each IP-Adapter has two settings that are applied to the IP-Adapter:
-
-* Weight - Strength of the IP-Adapter model applied to the generation for the section, defined by start/end
-* Start/End  - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the IP-Adapter applied.

docs/features/MODEL_MERGING.md

@@ -2,50 +2,17 @@
 title: Model Merging
 ---
 
-InvokeAI provides the ability to merge two or three diffusers-type models into a new merged model. The
-resulting model will combine characteristics of the original, and can
-be used to teach an old model new tricks.
+# :material-image-off: Model Merging
 
 ## How to Merge Models
 
-Model Merging can be be done by navigating to the Model Manager and clicking the "Merge Models" tab. From there, you can select the models and settings you want to use to merge th models. 
-
-## Settings
-
-* Model Selection: there are three multiple choice fields that
-  display all the diffusers-style models that InvokeAI knows about.
-  If you do not see the model you are looking for, then it is probably
-  a legacy checkpoint model and needs to be converted using the
-  `invoke` command-line client and its `!optimize` command. You
-  must select at least two models to merge. The third can be left at
-  "None" if you desire.
-
-* Alpha: This is the ratio to use when combining models. It ranges
-  from 0 to 1. The higher the value, the more weight is given to the
-  2d and (optionally) 3d models. So if you have two models named "A"
-  and "B", an alpha value of 0.25 will give you a merged model that is
-  25% A and 75% B.
-
-* Interpolation Method: This is the method used to combine
-  weights. The options are "weighted_sum" (the default), "sigmoid",
-  "inv_sigmoid" and "add_difference". Each produces slightly different
-  results. When three models are in use, only "add_difference" is
-  available.
-
-* Save Location: The location you want the merged model to be saved in. Default is in the InvokeAI root folder
-
-* Name for merged model: This is the name for the new model. Please
-  use InvokeAI conventions - only alphanumeric letters and the
-  characters ".+-".
-
-* Ignore Mismatches / Force: Not all models are compatible with each other. The merge
-  script will check for compatibility and refuse to merge ones that
-  are incompatible. Set this checkbox to try merging anyway.
-
-
+As of version 2.3, InvokeAI comes with a script that allows you to
+merge two or three diffusers-type models into a new merged model. The
+resulting model will combine characteristics of the original, and can
+be used to teach an old model new tricks.
 
 You may run the merge script by starting the invoke launcher
-(`invoke.sh` or `invoke.bat`) and choosing the option (4) for _merge
+(`invoke.sh` or `invoke.bat`) and choosing the option for _merge
 models_. This will launch a text-based interactive user interface that
 prompts you to select the models to merge, how to merge them, and the
 merged model name.
@@ -73,4 +40,34 @@ this to get back.
 If the merge runs successfully, it will create a new diffusers model
 under the selected name and register it with InvokeAI.
 
+## The Settings
+
+* Model Selection -- there are three multiple choice fields that
+  display all the diffusers-style models that InvokeAI knows about.
+  If you do not see the model you are looking for, then it is probably
+  a legacy checkpoint model and needs to be converted using the
+  `invoke` command-line client and its `!optimize` command. You
+  must select at least two models to merge. The third can be left at
+  "None" if you desire.
+
+* Alpha -- This is the ratio to use when combining models. It ranges
+  from 0 to 1. The higher the value, the more weight is given to the
+  2d and (optionally) 3d models. So if you have two models named "A"
+  and "B", an alpha value of 0.25 will give you a merged model that is
+  25% A and 75% B.
+
+* Interpolation Method -- This is the method used to combine
+  weights. The options are "weighted_sum" (the default), "sigmoid",
+  "inv_sigmoid" and "add_difference". Each produces slightly different
+  results. When three models are in use, only "add_difference" is
+  available. (TODO: cite a reference that describes what these
+  interpolation methods actually do and how to decide among them).
+
+* Force -- Not all models are compatible with each other. The merge
+  script will check for compatibility and refuse to merge ones that
+  are incompatible. Set this checkbox to try merging anyway.
+
+* Name for merged model - This is the name for the new model. Please
+  use InvokeAI conventions - only alphanumeric letters and the
+  characters ".+-".
 

docs/features/NODES.md

@@ -0,0 +1,208 @@
+# Nodes Editor (Experimental)
+
+🚨
+*The node editor is experimental. We've made it accessible because we use it to develop the application, but we have not addressed the many known rough edges. It's very easy to shoot yourself in the foot, and we cannot offer support for it until it sees full release (ETA v3.1). Everything is subject to change without warning.* 
+🚨
+
+The nodes editor is a blank canvas allowing for the use of individual functions and image transformations to control the image generation workflow. The node processing flow is usually done from left (inputs) to right (outputs), though linearity can become abstracted the more complex the node graph becomes. Nodes inputs and outputs are connected by dragging connectors from node to node.
+
+To better understand how nodes are used, think of how an electric power bar works. It takes in one input (electricity from a wall outlet) and passes it to multiple devices through multiple outputs. Similarly, a node could have multiple inputs and outputs functioning at the same (or different) time, but all node outputs pass information onward like a power bar passes electricity. Not all outputs are compatible with all inputs, however - Each node has different constraints on how it is expecting to input/output information. In general, node outputs are colour-coded to match compatible inputs of other nodes.
+
+## Anatomy of a Node
+
+Individual nodes are made up of the following:
+
+- Inputs: Edge points on the left side of the node window where you connect outputs from other nodes.
+- Outputs: Edge points on the right side of the node window where you connect to inputs on other nodes.
+- Options: Various options which are either manually configured, or overridden by connecting an output from another node to the input.
+
+## Diffusion Overview
+
+Taking the time to understand the diffusion process will help you to understand how to set up your nodes in the nodes editor. 
+
+There are two main spaces Stable Diffusion works in: image space and latent space.
+
+Image space represents images in pixel form that you look at. Latent space represents compressed inputs. It’s in latent space that Stable Diffusion processes images. A VAE (Variational Auto Encoder) is responsible for compressing and encoding inputs into latent space, as well as decoding outputs back into image space.
+
+When you generate an image using text-to-image, multiple steps occur in latent space:
+1. Random noise is generated at the chosen height and width. The noise’s characteristics are dictated by the chosen (or not chosen) seed. This noise tensor is passed into latent space. We’ll call this noise A.
+1. Using a model’s U-Net, a noise predictor examines noise A, and the words tokenized by CLIP from your prompt (conditioning). It generates its own noise tensor to predict what the final image might look like in latent space. We’ll call this noise B.
+1. Noise B is subtracted from noise A in an attempt to create a final latent image indicative of the inputs. This step is repeated for the number of sampler steps chosen.
+1. The VAE decodes the final latent image from latent space into image space.
+
+image-to-image is a similar process, with only step 1 being different:
+1. The input image is decoded from image space into latent space by the VAE. Noise is then added to the input latent image. Denoising Strength dictates how much noise is added, 0 being none, and 1 being all-encompassing. We’ll call this noise A. The process is then the same as steps 2-4 in the text-to-image explanation above. 
+
+Furthermore, a model provides the CLIP prompt tokenizer, the VAE, and a U-Net (where noise prediction occurs given a prompt and initial noise tensor).
+
+A noise scheduler (eg. DPM++ 2M Karras) schedules the subtraction of noise from the latent image across the sampler steps chosen (step 3 above). Less noise is usually subtracted at higher sampler steps. 
+
+## Node Types (Base Nodes)
+
+| Node <img width=160 align="right"> | Function                                                                              |
+| ---------------------------------- | --------------------------------------------------------------------------------------|
+| Add                                | Adds two numbers |
+| CannyImageProcessor                | Canny edge detection for ControlNet |
+| ClipSkip                           | Skip layers in clip text_encoder model |
+| Collect                            | Collects values into a collection |
+| Prompt (Compel)                    | Parse prompt using compel package to conditioning |
+| ContentShuffleImageProcessor       | Applies content shuffle processing to image |
+| ControlNet                         | Collects ControlNet info to pass to other nodes |
+| CvInpaint                          | Simple inpaint using opencv |
+| Divide                             | Divides two numbers |
+| DynamicPrompt                      | Parses a prompt using adieyal/dynamic prompt's random or combinatorial generator |
+| FloatLinearRange                   | Creates a range |
+| HedImageProcessor                  | Applies HED edge detection to image |
+| ImageBlur                          | Blurs an image |
+| ImageChannel                       | Gets a channel from an image |
+| ImageCollection                    | Load a collection of images and provide it as output |
+| ImageConvert                       | Converts an image to a different mode |
+| ImageCrop                          | Crops an image to a specified box. The box can be outside of the image. |
+| ImageInverseLerp                   | Inverse linear interpolation of all pixels of an image |
+| ImageLerp                          | Linear interpolation of all pixels of an image |
+| ImageMultiply                      | Multiplies two images together using `PIL.ImageChops.Multiply()` |
+| ImageNSFWBlurInvocation            | Detects and blurs images that may contain sexually explicit content |
+| ImagePaste                         | Pastes an image into another image |
+| ImageProcessor                     | Base class for invocations that reprocess images for ControlNet |
+| ImageResize                        | Resizes an image to specific dimensions |
+| ImageScale                         | Scales an image by a factor |
+| ImageToLatents                     | Scales latents by a given factor |
+| ImageWatermarkInvocation           | Adds an invisible watermark to images |
+| InfillColor                        | Infills transparent areas of an image with a solid color |
+| InfillPatchMatch                   | Infills transparent areas of an image using the PatchMatch algorithm |
+| InfillTile                         | Infills transparent areas of an image with tiles of the image |
+| Inpaint                            | Generates an image using inpaint |
+| Iterate                            | Iterates over a list of items |
+| LatentsToImage                     | Generates an image from latents |
+| LatentsToLatents                   | Generates latents using latents as base image |
+| LeresImageProcessor                | Applies leres processing to image |
+| LineartAnimeImageProcessor         | Applies line art anime processing to image |
+| LineartImageProcessor              | Applies line art processing to image |
+| LoadImage                          | Load an image and provide it as output |
+| Lora Loader                        | Apply selected lora to unet and text_encoder |
+| Model Loader                       | Loads a main model, outputting its submodels |
+| MaskFromAlpha                      | Extracts the alpha channel of an image as a mask |
+| MediapipeFaceProcessor             | Applies mediapipe face processing to image |
+| MidasDepthImageProcessor           | Applies Midas depth processing to image |
+| MlsdImageProcessor                 | Applied MLSD processing to image |
+| Multiply                           | Multiplies two numbers |
+| Noise                              | Generates latent noise |
+| NormalbaeImageProcessor            | Applies NormalBAE processing to image |
+| OpenposeImageProcessor             | Applies Openpose processing to image |
+| ParamFloat                         | A float parameter |
+| ParamInt                           | An integer parameter |
+| PidiImageProcessor                 | Applies PIDI processing to an image |
+| Progress Image                     | Displays the progress image in the Node Editor |
+| RandomInit                         | Outputs a single random integer |
+| RandomRange                        | Creates a collection of random numbers |
+| Range                              | Creates a range of numbers from start to stop with step |
+| RangeOfSize                        | Creates a range from start to start + size with step |
+| ResizeLatents                      | Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8. |
+| RestoreFace                        | Restores faces in the image |
+| ScaleLatents                       | Scales latents by a given factor |
+| SegmentAnythingProcessor           | Applies segment anything processing to image |
+| ShowImage                          | Displays a provided image, and passes it forward in the pipeline |
+| StepParamEasing                    | Experimental per-step parameter for easing for denoising steps |
+| Subtract                           | Subtracts two numbers |
+| TextToLatents                      | Generates latents from conditionings |
+| TileResampleProcessor              | Bass class for invocations that preprocess images for ControlNet |
+| Upscale                            | Upscales an image |
+| VAE Loader                         | Loads a VAE model, outputting a VaeLoaderOutput |
+| ZoeDepthImageProcessor             | Applies Zoe depth processing to image |
+
+## Node Grouping Concepts
+
+There are several node grouping concepts that can be examined with a narrow focus. These (and other) groupings can be pieced together to make up functional graph setups, and are important to understanding how groups of nodes work together as part of a whole. Note that the screenshots below aren't examples of complete functioning node graphs (see Examples).
+
+### Noise
+
+As described, an initial noise tensor is necessary for the latent diffusion process. As a result, all non-image *ToLatents nodes require a noise node input.  
+
+![groupsnoise](../assets/nodes/groupsnoise.png)
+
+### Conditioning
+
+As described, conditioning is necessary for the latent diffusion process, whether empty or not. As a result, all non-image *ToLatents nodes require positive and negative conditioning inputs. Conditioning is reliant on a CLIP tokenizer provided by the Model Loader node.
+
+![groupsconditioning](../assets/nodes/groupsconditioning.png)
+
+### Image Space & VAE
+
+The ImageToLatents node doesn't require a noise node input, but requires a VAE input to convert the image from image space into latent space. In reverse, the LatentsToImage node requires a VAE input to convert from latent space back into image space.
+
+![groupsimgvae](../assets/nodes/groupsimgvae.png)
+
+### Defined & Random Seeds
+
+It is common to want to use both the same seed (for continuity) and random seeds (for variance). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed.
+
+![groupsrandseed](../assets/nodes/groupsrandseed.png)
+
+### Control
+
+Control means to guide the diffusion process to adhere to a defined input or structure. Control can be provided as input to non-image *ToLatents nodes from ControlNet nodes. ControlNet nodes usually require an image processor which converts an input image for use with ControlNet.
+
+![groupscontrol](../assets/nodes/groupscontrol.png)
+
+### LoRA
+
+The Lora Loader node lets you load a LoRA (say that ten times fast) and pass it as output to both the Prompt (Compel) and non-image *ToLatents nodes. A model's CLIP tokenizer is passed through the LoRA into Prompt (Compel), where it affects conditioning. A model's U-Net is also passed through the LoRA into a non-image *ToLatents node, where it affects noise prediction.
+
+![groupslora](../assets/nodes/groupslora.png)
+
+### Scaling
+
+Use the ImageScale, ScaleLatents, and Upscale nodes to upscale images and/or latent images. The chosen method differs across contexts. However, be aware that latents are already noisy and compressed at their original resolution; scaling an image could produce more detailed results.
+
+![groupsallscale](../assets/nodes/groupsallscale.png)
+
+### Iteration + Multiple Images as Input
+
+Iteration is a common concept in any processing, and means to repeat a process with given input. In nodes, you're able to use the Iterate node to iterate through collections usually gathered by the Collect node. The Iterate node has many potential uses, from processing a collection of images one after another, to varying seeds across multiple image generations and more. This screenshot demonstrates how to collect several images and pass them out one at a time.
+
+![groupsiterate](../assets/nodes/groupsiterate.png)
+
+### Multiple Image Generation + Random Seeds
+
+Multiple image generation in the node editor is done using the RandomRange node. In this case, the 'Size' field represents the number of images to generate. As RandomRange produces a collection of integers, we need to add the Iterate node to iterate through the collection. 
+
+To control seeds across generations takes some care. The first row in the screenshot will generate multiple images with different seeds, but using the same RandomRange parameters across invocations will result in the same group of random seeds being used across the images, producing repeatable results. In the second row, adding the RandomInt node as input to RandomRange's 'Seed' edge point will ensure that seeds are varied across all images across invocations, producing varied results.
+
+![groupsmultigenseeding](../assets/nodes/groupsmultigenseeding.png)
+
+## Examples
+
+With our knowledge of node grouping and the diffusion process, let’s break down some basic graphs in the nodes editor. Note that a node's options can be overridden by inputs from other nodes. These examples aren't strict rules to follow and only demonstrate some basic configurations.
+
+### Basic text-to-image Node Graph
+
+![nodest2i](../assets/nodes/nodest2i.png)
+
+- Model Loader: A necessity to generating images (as we’ve read above). We choose our model from the dropdown. It outputs a U-Net, CLIP tokenizer, and VAE.
+- Prompt (Compel): Another necessity. Two prompt nodes are created. One will output positive conditioning (what you want, ‘dog’), one will output negative (what you don’t want, ‘cat’). They both input the CLIP tokenizer that the Model Loader node outputs.
+- Noise: Consider this noise A from step one of the text-to-image explanation above. Choose a seed number, width, and height.
+- TextToLatents: This node takes many inputs for converting and processing text & noise from image space into latent space, hence the name TextTo**Latents**. In this setup, it inputs positive and negative conditioning from the prompt nodes for processing (step 2 above). It inputs noise from the noise node for processing (steps 2 & 3 above). Lastly, it inputs a U-Net from the Model Loader node for processing (step 2 above). It outputs latents for use in the next LatentsToImage node. Choose number of sampler steps, CFG scale, and scheduler.
+- LatentsToImage: This node takes in processed latents from the TextToLatents node, and the model’s VAE from the Model Loader node which is responsible for decoding latents back into the image space, hence the name LatentsTo**Image**. This node is the last stop, and once the image is decoded, it is saved to the gallery.
+
+### Basic image-to-image Node Graph
+
+![nodesi2i](../assets/nodes/nodesi2i.png)
+
+- Model Loader: Choose a model from the dropdown.
+- Prompt (Compel): Two prompt nodes. One positive (dog), one negative (dog). Same CLIP inputs from the Model Loader node as before.
+- ImageToLatents: Upload a source image directly in the node window, via drag'n'drop from the gallery, or passed in as input. The ImageToLatents node inputs the VAE from the Model Loader node to decode the chosen image from image space into latent space, hence the name ImageTo**Latents**. It outputs latents for use in the next LatentsToLatents node. It also outputs the source image's width and height for use in the next Noise node if the final image is to be the same dimensions as the source image.
+- Noise: A noise tensor is created with the width and height of the source image, and connected to the next LatentsToLatents node. Notice the width and height fields are overridden by the input from the ImageToLatents width and height outputs.
+- LatentsToLatents: The inputs and options are nearly identical to TextToLatents, except that LatentsToLatents also takes latents as an input. Considering our source image is already converted to latents in the last ImageToLatents node, and text + noise are no longer the only inputs to process, we use the LatentsToLatents node. 
+- LatentsToImage: Like previously, the LatentsToImage node will use the VAE from the Model Loader as input to decode the latents from LatentsToLatents into image space, and save it to the gallery.
+
+### Basic ControlNet Node Graph
+
+![nodescontrol](../assets/nodes/nodescontrol.png)
+
+- Model Loader
+- Prompt (Compel)
+- Noise: Width and height of the CannyImageProcessor ControlNet image is passed in to set the dimensions of the noise passed to TextToLatents.
+- CannyImageProcessor: The CannyImageProcessor node is used to process the source image being used as a ControlNet. Each ControlNet processor node applies control in different ways, and has some different options to configure. Width and height are passed to noise, as mentioned. The processed ControlNet image is output to the ControlNet node.
+- ControlNet: Select the type of control model. In this case, canny is chosen as the CannyImageProcessor was used to generate the ControlNet image. Configure the control node options, and pass the control output to TextToLatents.
+- TextToLatents: Similar to the basic text-to-image example, except ControlNet is passed to the control input edge point.
+- LatentsToImage

docs/features/POSTPROCESS.md

@@ -4,13 +4,35 @@ title: Postprocessing
 
 # :material-image-edit: Postprocessing
 
-This sections details the ability to improve faces and upscale images.
+## Intro
+
+This extension provides the ability to restore faces and upscale images.
 
 ## Face Fixing
 
-As of InvokeAI 3.0, the easiest way to improve faces created during image generation is through the Inpainting functionality of the Unified Canvas. Simply add the image containing the faces that you would like to improve to the canvas, mask the face to be improved and run the invocation. For best results, make sure to use an inpainting specific model; these are usually identified by the "-inpainting" term in the model name. 
+The default face restoration module is GFPGAN. The default upscale is
+Real-ESRGAN. For an alternative face restoration module, see
+[CodeFormer Support](#codeformer-support) below.
 
-## Upscaling
+As of version 1.14, environment.yaml will install the Real-ESRGAN package into
+the standard install location for python packages, and will put GFPGAN into a
+subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
+should "just work" without further intervention. Simply indicate the desired scale on
+the popup in the Web GUI.
+
+**GFPGAN** requires a series of downloadable model files to work. These are
+loaded when you run `invokeai-configure`. If GFPAN is failing with an
+error, please run the following from the InvokeAI directory:
+
+```bash
+invokeai-configure
+```
+
+If you do not run this script in advance, the GFPGAN module will attempt to
+download the models files the first time you try to perform facial
+reconstruction.
+
+### Upscaling
 
 Open the upscaling dialog by clicking on the "expand" icon located
 above the image display area in the Web UI:
@@ -19,23 +41,82 @@ above the image display area in the Web UI:
 ![upscale1](../assets/features/upscale-dialog.png)
 </figure>
 
-The default upscaling option is Real-ESRGAN x2 Plus, which will scale your image by a factor of two. This means upscaling a 512x512 image will result in a new 1024x1024 image.
+There are three different upscaling parameters that you can
+adjust. The first is the scale itself, either 2x or 4x.
 
-Other options are the x4 upscalers, which will scale your image by a factor of 4. 
+The second is the "Denoising Strength." Higher values will smooth out
+the image and remove digital chatter, but may lose fine detail at
+higher values.
 
+Third, "Upscale Strength" allows you to adjust how the You can set the
+scaling stength between `0` and `1.0` to control the intensity of the
+scaling. AI upscalers generally tend to smooth out texture details. If
+you wish to retain some of those for natural looking results, we
+recommend using values between `0.5 to 0.8`.
+
+[This figure](../assets/features/upscaling-montage.png) illustrates
+the effects of denoising and strength. The original image was 512x512,
+4x scaled to 2048x2048. The "original" version on the upper left was
+scaled using simple pixel averaging. The remainder use the ESRGAN
+upscaling algorithm at different levels of denoising and strength.
+
+<figure markdown>
+![upscaling](../assets/features/upscaling-montage.png){ width=720 }
+</figure>
+
+Both denoising and strength default to 0.75.
+
+### Face Restoration
+
+InvokeAI offers alternative two face restoration algorithms,
+[GFPGAN](https://github.com/TencentARC/GFPGAN) and
+[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
+algorithms improve the appearance of faces, particularly eyes and
+mouths. Issues with faces are less common with the latest set of
+Stable Diffusion models than with the original 1.4 release, but the
+restoration algorithms can still make a noticeable improvement in
+certain cases. You can also apply restoration to old photographs you
+upload.
+
+To access face restoration, click the "smiley face" icon in the
+toolbar above the InvokeAI image panel. You will be presented with a
+dialog that offers a choice between the two algorithm and sliders that
+allow you to adjust their parameters. Alternatively, you may open the
+left-hand accordion panel labeled "Face Restoration" and have the
+restoration algorithm of your choice applied to generated images
+automatically.
+
+
+Like upscaling, there are a number of parameters that adjust the face
+restoration output. GFPGAN has a single parameter, `strength`, which
+controls how much the algorithm is allowed to adjust the
+image. CodeFormer has two parameters, `strength`, and `fidelity`,
+which together control the quality of the output image as described in
+the [CodeFormer project
+page](https://shangchenzhou.com/projects/CodeFormer/). Default values
+are 0.75 for both parameters, which achieves a reasonable balance
+between changing the image too much and not enough.
+
+[This figure](../assets/features/restoration-montage.png) illustrates
+the effects of adjusting GFPGAN and CodeFormer parameters.
+
+<figure markdown>
+![upscaling](../assets/features/restoration-montage.png){ width=720 }
+</figure>
 
 !!! note
 
-    Real-ESRGAN is memory intensive. In order to avoid crashes and memory overloads
+    GFPGAN and Real-ESRGAN are both memory intensive. In order to avoid crashes and memory overloads
     during the Stable Diffusion process, these effects are applied after Stable Diffusion has completed
     its work.
 
     In single image generations, you will see the output right away but when you are using multiple
-    iterations, the images will first be generated and then upscaled after that
+    iterations, the images will first be generated and then upscaled and face restored after that
     process is complete. While the image generation is taking place, you will still be able to preview
     the base images.
 
 ## How to disable
 
-If, for some reason, you do not wish to load the ESRGAN libraries,
-you can disable them on the invoke.py command line with the `--no_esrgan` options.
+If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
+you can disable them on the invoke.py command line with the `--no_restore` and
+`--no_esrgan` options, respectively.

docs/features/PROMPTS.md

@@ -4,6 +4,80 @@ title: Prompting-Features
 
 # :octicons-command-palette-24: Prompting-Features
 
+## **Negative and Unconditioned Prompts**
+
+Any words between a pair of square brackets will instruct Stable
+Diffusion to attempt to ban the concept from the generated image. The
+same effect is achieved by placing words in the "Negative Prompts"
+textbox in the Web UI.
+
+```text
+this is a test prompt [not really] to make you understand [cool] how this works.
+```
+
+In the above statement, the words 'not really cool` will be ignored by Stable
+Diffusion.
+
+Here's a prompt that depicts what it does.
+
+original prompt:
+
+`#!bash "A fantastical translucent pony made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve"`
+
+`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
+
+<figure markdown>
+
+![step1](../assets/negative_prompt_walkthru/step1.png)
+
+</figure>
+
+That image has a woman, so if we want the horse without a rider, we can
+influence the image not to have a woman by putting [woman] in the prompt, like
+this:
+
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]"`
+(same parameters as above)
+
+<figure markdown>
+
+![step2](../assets/negative_prompt_walkthru/step2.png)
+
+</figure>
+
+That's nice - but say we also don't want the image to be quite so blue. We can
+add "blue" to the list of negative prompts, so it's now [woman blue]:
+
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]"`
+(same parameters as above)
+
+<figure markdown>
+
+![step3](../assets/negative_prompt_walkthru/step3.png)
+
+</figure>
+
+Getting close - but there's no sense in having a saddle when our horse doesn't
+have a rider, so we'll add one more negative prompt: [woman blue saddle].
+
+`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]"`
+(same parameters as above)
+
+<figure markdown>
+
+![step4](../assets/negative_prompt_walkthru/step4.png)
+
+</figure>
+
+!!! notes "Notes about this feature:"
+
+    * The only requirement for words to be ignored is that they are in between a pair of square brackets.
+    * You can provide multiple words within the same bracket.
+    * You can provide multiple brackets with multiple words in different places of your prompt. That works just fine.
+    * To improve typical anatomy problems, you can add negative prompts like `[bad anatomy, extra legs, extra arms, extra fingers, poorly drawn hands, poorly drawn feet, disfigured, out of frame, tiling, bad art, deformed, mutated]`.
+
+---
+
 ## **Prompt Syntax Features**
 
 The InvokeAI prompting language has the following features:
@@ -28,6 +102,9 @@ The following syntax is recognised:
   `a tall thin man (picking (apricots)1.3)1.1`. (`+` is equivalent to 1.1, `++`
   is pow(1.1,2), `+++` is pow(1.1,3), etc; `-` means 0.9, `--` means pow(0.9,2),
   etc.)
+- attention also applies to `[unconditioning]` so
+  `a tall thin man picking apricots [(ladder)0.01]` will _very gently_ nudge SD
+  away from trying to draw the man on a ladder
 
 You can use this to increase or decrease the amount of something. Starting from
 this prompt of `a man picking apricots from a tree`, let's see what happens if
@@ -73,7 +150,7 @@ Or, alternatively, with more man:
 | ---------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- |
 | ![](../assets/prompt_syntax/mountain-man1.png) | ![](../assets/prompt_syntax/mountain-man2.png) | ![](../assets/prompt_syntax/mountain-man3.png) | ![](../assets/prompt_syntax/mountain-man4.png) |
 
-### Prompt Blending
+### Blending between prompts
 
 - `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,1)`
 - The existing prompt blending using `:<weight>` will continue to be supported -
@@ -91,24 +168,6 @@ Or, alternatively, with more man:
 See the section below on "Prompt Blending" for more information about how this
 works.
 
-### Prompt Conjunction  
-Join multiple clauses together to create a conjoined prompt. Each clause will be passed to CLIP separately. 
-
-For example, the prompt: 
-
-```bash
-"A mystical valley surround by towering granite cliffs, watercolor, warm"
-```
-
-Can be used with .and():
-```bash
-("A mystical valley", "surround by towering granite cliffs", "watercolor", "warm").and()
-```
-
-Each will give you different results - try them out and see what you prefer!
-
-
-
 ### Cross-Attention Control ('prompt2prompt')
 
 Sometimes an image you generate is almost right, and you just want to change one
@@ -131,7 +190,7 @@ For example, consider the prompt `a cat.swap(dog) playing with a ball in the for
 
       - For multiple word swaps, use parentheses: `a (fluffy cat).swap(barking dog) playing with a ball in the forest`.
       - To swap a comma, use quotes: `a ("fluffy, grey cat").swap("big, barking dog") playing with a ball in the forest`.
-- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to (bloc97's)[(https://github.com/bloc97/CrossAttentionControl)] `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
+- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to bloc97's `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
   intuitively understand. `t_start` and `t_end` are used to control on which steps cross-attention control should run. With the default values `t_start=0` and `t_end=1`, cross-attention control is active on every step of image generation. Other values can be used to turn cross-attention control off for part of the image generation process.
     - For example, if doing a diffusion with 10 steps for the prompt is `a cat.swap(dog, t_start=0.3, t_end=1.0) playing with a ball in the forest`, the first 3 steps will be run as `a cat playing with a ball in the forest`, while the last 7 steps will run as `a dog playing with a ball in the forest`, but the pixels that represent `dog` will be locked to the pixels that would have represented `cat` if the `cat` prompt had been used instead.
     - Conversely, for `a cat.swap(dog, t_start=0, t_end=0.7) playing with a ball in the forest`, the first 7 steps will run as `a dog playing with a ball in the forest` with the pixels that represent `dog` locked to the same pixels that would have represented `cat` if the `cat` prompt was being used instead. The final 3 steps will just run `a cat playing with a ball in the forest`.
@@ -142,7 +201,7 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
 The `prompt2prompt` code is based off
 [bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
 
-### Escaping parentheses and speech marks 
+### Escaping parantheses () and speech marks ""
 
 If the model you are using has parentheses () or speech marks "" as part of its
 syntax, you will need to "escape" these using a backslash, so that`(my_keyword)`
@@ -153,16 +212,23 @@ the parentheses as part of the prompt syntax and it will get confused.
 
 ## **Prompt Blending**
 
-You may blend together prompts to explore the AI's
+You may blend together different sections of the prompt to explore the AI's
 latent semantic space and generate interesting (and often surprising!)
 variations. The syntax is:
 
 ```bash
-("prompt #1", "prompt #2").blend(0.25, 0.75)
+blue sphere:0.25 red cube:0.75 hybrid
 ```
 
-This will tell the sampler to blend 25% of the concept of prompt #1 with 75%
-of the concept of prompt #2. It is recommended to keep the sum of the weights to around 1.0, but interesting things might happen if you go outside of this range.
+This will tell the sampler to blend 25% of the concept of a blue sphere with 75%
+of the concept of a red cube. The blend weights can use any combination of
+integers and floating point numbers, and they do not need to add up to 1.
+Everything to the left of the `:XX` up to the previous `:XX` is used for
+merging, so the overall effect is:
+
+```bash
+0.25 * "blue sphere" + 0.75 * "white duck" + hybrid
+```
 
 Because you are exploring the "mind" of the AI, the AI's way of mixing two
 concepts may not match yours, leading to surprising effects. To illustrate, here
@@ -170,14 +236,13 @@ are three images generated using various combinations of blend weights. As
 usual, unless you fix the seed, the prompts will give you different results each
 time you run them.
 
-Let's examine how this affects image generation results:
+<figure markdown>
 
+### "blue sphere, red cube, hybrid"
 
-```bash
-"blue sphere, red cube, hybrid"
-```
+</figure>
 
-This example doesn't use blending at all and represents the default way of mixing
+This example doesn't use melding at all and represents the default way of mixing
 concepts.
 
 <figure markdown>
@@ -186,47 +251,55 @@ concepts.
 
 </figure>
 
-It's interesting to see how the AI expressed the concept of "cube" within the sphere. If you look closely, there is depth there, so the enclosing frame is actually a cube.
+It's interesting to see how the AI expressed the concept of "cube" as the four
+quadrants of the enclosing frame. If you look closely, there is depth there, so
+the enclosing frame is actually a cube.
 
 <figure markdown>
 
-```bash
-("blue sphere", "red cube").blend(0.25, 0.75)
-```
+### "blue sphere:0.25 red cube:0.75 hybrid"
 
 ![blue-sphere-25-red-cube-75](../assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png)
 
 </figure>
 
-Now that's interesting. We get an image with a resemblance of a red cube, with a hint of blue shadows which represents a melding of concepts within the AI's "latent space" of semantic representations. 
+Now that's interesting. We get neither a blue sphere nor a red cube, but a red
+sphere embedded in a brick wall, which represents a melding of concepts within
+the AI's "latent space" of semantic representations. Where is Ludwig
+Wittgenstein when you need him?
 
 <figure markdown>
 
-```bash
-("blue sphere", "red cube").blend(0.75, 0.25)
-```
+### "blue sphere:0.75 red cube:0.25 hybrid"
 
 ![blue-sphere-75-red-cube-25](../assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png)
 
 </figure>
 
-Definitely more blue-spherey. 
+Definitely more blue-spherey. The cube is gone entirely, but it's really cool
+abstract art.
 
 <figure markdown>
 
-```bash
-("blue sphere", "red cube").blend(0.5, 0.5)
-```
-</figure>
+### "blue sphere:0.5 red cube:0.5 hybrid"
 
-<figure markdown>
 ![blue-sphere-5-red-cube-5-hybrid](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png)
+
 </figure>
 
+Whoa...! I see blue and red, but no spheres or cubes. Is the word "hybrid"
+summoning up the concept of some sort of scifi creature? Let's find out.
 
-Whoa...! I see blue and red, and if I squint, spheres and cubes.
+<figure markdown>
 
+### "blue sphere:0.5 red cube:0.5"
 
+![blue-sphere-5-red-cube-5](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png)
+
+</figure>
+
+Indeed, removing the word "hybrid" produces an image that is more like what we'd
+expect.
 
 ## Dynamic Prompts
 
@@ -246,7 +319,7 @@ To create a Dynamic Prompt, follow these steps:
     Within the braces, separate each option using a vertical bar |.
     If you want to include multiple options from a single group, prefix with the desired number and $$.
 
-For instance: A {house|apartment|lodge|cottage} in {summer|winter|autumn|spring} designed in {style1|style2|style3}.
+For instance: A {house|apartment|lodge|cottage} in {summer|winter|autumn|spring} designed in {2$$style1|style2|style3}.
 ### How Dynamic Prompts Work
 
 Once a Dynamic Prompt is configured, the system generates an array of combinations using the options provided. Each group of options in curly braces is treated independently, with the system selecting one option from each group. For a prefixed set (e.g., 2$$), the system will select two distinct options.
@@ -273,36 +346,3 @@ Below are some useful strategies for creating Dynamic Prompts:
     Experiment with different quantities for the prefix. For example, 3$$ will select three distinct options.
     Be aware of coherence in your prompts. Although the system can generate all possible combinations, not all may semantically make sense. Therefore, carefully choose the options for each group.
     Always review and fine-tune the generated prompts as needed. While Dynamic Prompts can help you generate a multitude of combinations, the final polishing and refining remain in your hands.
-
-
-## SDXL Prompting
-
-Prompting with SDXL is slightly different than prompting with SD1.5 or SD2.1 models - SDXL expects a prompt _and_ a style. 
-
-
-### Prompting 
-<figure markdown>
-
-![SDXL prompt boxes in InvokeAI](../assets/prompt_syntax/sdxl-prompt.png)
-
-</figure>
-
-In the prompt box, enter a positive or negative prompt as you normally would. 
-
-For the style box you can enter a style that you want the image to be generated in. You can use styles from this example list, or any other style you wish: anime, photographic, digital art, comic book, fantasy art, analog film, neon punk, isometric, low poly, origami, line art, cinematic, 3d model, pixel art, etc.
-
-
-### Concatenated Prompts
-
-
-InvokeAI also has the option to concatenate the prompt and style inputs, by pressing the "link" button in the Positive Prompt box. 
-
-This concatenates the prompt & style inputs, and passes the joined prompt and style to the SDXL model. 
-![SDXL concatenated prompt boxes in InvokeAI](../assets/prompt_syntax/sdxl-prompt-concatenated.png)
-
-
-
-
-
-
-

docs/features/TRAINING.md

@@ -43,22 +43,27 @@ into the directory
 
 InvokeAI 2.3 and higher comes with a text console-based training front
 end. From within the `invoke.sh`/`invoke.bat` Invoke launcher script,
-start training tool selecting choice (3):
+start the front end by selecting choice (3):
 
 ```sh
-1 "Generate images with a browser-based interface"
-2 "Explore InvokeAI nodes using a command-line interface"
-3 "Textual inversion training"
-4 "Merge models (diffusers type only)"
-5 "Download and install models"
-6 "Change InvokeAI startup options"
-7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
-8 "Open the developer console"
-9 "Update InvokeAI"
+Do you want to generate images using the
+1: Browser-based UI
+2: Command-line interface
+3: Run textual inversion training
+4: Merge models (diffusers type only)
+5: Download and install models
+6: Change InvokeAI startup options
+7: Re-run the configure script to fix a broken install
+8: Open the developer console
+9: Update InvokeAI
+10: Command-line help
+Q: Quit
+
+Please enter 1-10, Q: [1] 
 ```
 
-Alternatively, you can select option (8) or from the command line, with the InvokeAI virtual environment active,
-you can then launch the front end with the command `invokeai-ti --gui`.
+From the command line, with the InvokeAI virtual environment active,
+you can launch the front end with the command `invokeai-ti --gui`.
 
 This will launch a text-based front end that will look like this:
 

docs/features/UTILITIES.md

@@ -1,336 +0,0 @@
----
-title: Command-line Utilities
----
-
-# :material-file-document: Utilities
-
-# Command-line Utilities
-
-InvokeAI comes with several scripts that are accessible via the
-command line. To access these commands, start the "developer's
-console" from the launcher (`invoke.bat` menu item [8]). Users who are
-familiar with Python can alternatively activate InvokeAI's virtual
-environment (typically, but not necessarily `invokeai/.venv`).
-
-In the developer's console, type the script's name to run it. To get a
-synopsis of what a utility does and the command-line arguments it
-accepts, pass it the `-h` argument, e.g.
-
-```bash
-invokeai-merge -h
-```
-## **invokeai-web**
-
-This script launches the web server and is effectively identical to
-selecting option [1] in the launcher. An advantage of launching the
-server from the command line is that you can override any setting
-configuration option in `invokeai.yaml` using like-named command-line
-arguments. For example, to temporarily change the size of the RAM
-cache to 7 GB, you can launch as follows:
-
-```bash
-invokeai-web --ram 7
-```
-
-## **invokeai-merge**
-
-This is the model merge script, the same as launcher option [4]. Call
-it with the `--gui` command-line argument to start the interactive
-console-based GUI. Alternatively, you can run it non-interactively
-using command-line arguments as illustrated in the example below which
-merges models named `stable-diffusion-1.5` and `inkdiffusion` into a new model named
-`my_new_model`:
-
-```bash
-invokeai-merge --force --base-model sd-1 --models stable-diffusion-1.5 inkdiffusion --merged_model_name my_new_model
-```
-
-## **invokeai-ti**
-
-This is the textual inversion training script that is run by launcher
-option [3]. Call it with `--gui` to run the interactive console-based
-front end. It can also be run non-interactively. It has about a
-zillion arguments, but a typical training session can be launched
-with:
-
-```bash
-invokeai-ti --model stable-diffusion-1.5 \
-            --placeholder_token 'jello' \
-            --learnable_property object \
-			--num_train_epochs 50 \
-			--train_data_dir /path/to/training/images \
-			--output_dir /path/to/trained/model
-```
-
-(Note that \\ is the Linux/Mac long-line continuation character. Use ^
-in Windows).
-
-## **invokeai-install**
-
-This is the console-based model install script that is run by launcher
-option [5]. If called without arguments, it will launch the
-interactive console-based interface. It can also be used
-non-interactively to list, add and remove models as shown by these
-examples:
-
-* This will download and install three models from CivitAI, HuggingFace,
-and local disk:
-
-```bash
-invokeai-install --add https://civitai.com/api/download/models/161302 ^
-                  gsdf/Counterfeit-V3.0  ^
-				  D:\Models\merge_model_two.safetensors
-```
-(Note that ^ is the Windows long-line continuation character. Use \\ on
-Linux/Mac).
-
-* This will list installed models of type `main`:
-
-```bash
-invokeai-model-install --list-models main
-```
-
-* This will delete the models named `voxel-ish` and `realisticVision`:
-
-```bash
-invokeai-model-install --delete voxel-ish realisticVision
-```
-
-## **invokeai-configure**
-
-This is the console-based configure script that ran when InvokeAI was
-first installed. You can run it again at any time to change the
-configuration, repair a broken install.
-
-Called without any arguments, `invokeai-configure` enters interactive
-mode with two screens. The first screen is a form that provides access
-to most of InvokeAI's configuration options. The second screen lets
-you download, add, and delete models interactively. When you exit the
-second screen, the script will add any missing "support models"
-needed for core functionality, and any selected "sd weights" which are
-the model checkpoint/diffusers files.
-
-This behavior can be changed via a series of command-line
-arguments. Here are some of the useful ones:
-
-* `invokeai-configure --skip-sd-weights --skip-support-models`
-This will run just the configuration part of the utility, skipping
-downloading of support models and stable diffusion weights.
-
-* `invokeai-configure --yes`
-This will run the configure script non-interactively. It will set the
-configuration options to their default values, install/repair support
-models, and download the "recommended" set of SD models.
-
-* `invokeai-configure --yes --default_only` 
-This will run the configure script non-interactively. In contrast to
-the previous command, it will only download the default SD model,
-Stable Diffusion v1.5
-
-* `invokeai-configure --yes --default_only --skip-sd-weights` 
-This is similar to the previous command, but will not download any
-SD models at all. It is usually used to repair a broken install.
-
-By default, `invokeai-configure` runs on the currently active InvokeAI
-root folder. To run it against a different root, pass it the `--root
-</path/to/root>` argument.
-
-Lastly, you can use `invokeai-configure` to create a working root
-directory entirely from scratch. Assuming you wish to make a root directory
-named `InvokeAI-New`, run this command:
-
-```bash
-invokeai-configure --root InvokeAI-New --yes --default_only
-```
-This will create a minimally functional root directory. You can now
-launch the web server against it with `invokeai-web --root InvokeAI-New`.
-
-## **invokeai-update**
-
-This is the interactive console-based script that is run by launcher
-menu item [9] to update to a new version of InvokeAI. It takes no
-command-line arguments.
-
-## **invokeai-metadata**
-
-This is a script which takes a list of InvokeAI-generated images and
-outputs their metadata in the same JSON format that you get from the
-`</>` button in the Web GUI. For example:
-
-```bash
-$ invokeai-metadata ffe2a115-b492-493c-afff-7679aa034b50.png
-ffe2a115-b492-493c-afff-7679aa034b50.png:
-{
-    "app_version": "3.1.0",
-    "cfg_scale": 8.0,
-    "clip_skip": 0,
-    "controlnets": [],
-    "generation_mode": "sdxl_txt2img",
-    "height": 1024,
-    "loras": [],
-    "model": {
-        "base_model": "sdxl",
-        "model_name": "stable-diffusion-xl-base-1.0",
-        "model_type": "main"
-    },
-    "negative_prompt": "",
-    "negative_style_prompt": "",
-    "positive_prompt": "military grade sushi dinner for shock troopers",
-    "positive_style_prompt": "",
-    "rand_device": "cpu",
-    "refiner_cfg_scale": 7.5,
-    "refiner_model": {
-        "base_model": "sdxl-refiner",
-        "model_name": "sd_xl_refiner_1.0",
-        "model_type": "main"
-    },
-    "refiner_negative_aesthetic_score": 2.5,
-    "refiner_positive_aesthetic_score": 6.0,
-    "refiner_scheduler": "euler",
-    "refiner_start": 0.8,
-    "refiner_steps": 20,
-    "scheduler": "euler",
-    "seed": 387129902,
-    "steps": 25,
-    "width": 1024
-}
-```
-
-You may list multiple files on the command line.
-
-## **invokeai-import-images**
-
-InvokeAI uses a database to store information about images it
-generated, and just copying the image files from one InvokeAI root
-directory to another does not automatically import those images into
-the destination's gallery. This script allows you to bulk import
-images generated by one instance of InvokeAI into a gallery maintained
-by another. It also works on images generated by older versions of
-InvokeAI, going way back to version 1.
-
-This script has an interactive mode only. The following example shows
-it in action:
-
-```bash
-$ invokeai-import-images
-===============================================================================
-This script will import images generated by earlier versions of
-InvokeAI into the currently installed root directory:
-   /home/XXXX/invokeai-main
-If this is not what you want to do, type ctrl-C now to cancel.
-===============================================================================
-= Configuration & Settings
-Found invokeai.yaml file at /home/XXXX/invokeai-main/invokeai.yaml:
-  Database : /home/XXXX/invokeai-main/databases/invokeai.db
-  Outputs  : /home/XXXX/invokeai-main/outputs/images
- 
-Use these paths for import (yes) or choose different ones (no) [Yn]:
-Inputs: Specify absolute path containing InvokeAI .png images to import: /home/XXXX/invokeai-2.3/outputs/images/
-Include files from subfolders recursively [yN]?
-
-Options for board selection for imported images:
-1) Select an existing board name. (found 4)
-2) Specify a board name to create/add to.
-3) Create/add to board named 'IMPORT'.
-4) Create/add to board named 'IMPORT' with the current datetime string appended (.e.g IMPORT_20230919T203519Z).
-5) Create/add to board named 'IMPORT' with a the original file app_version appended (.e.g IMPORT_2.2.5).
-Specify desired board option: 3
-
-===============================================================================
-= Import Settings Confirmation
-
-Database File Path               : /home/XXXX/invokeai-main/databases/invokeai.db
-Outputs/Images Directory         : /home/XXXX/invokeai-main/outputs/images
-Import Image Source Directory    : /home/XXXX/invokeai-2.3/outputs/images/
-  Recurse Source SubDirectories  : No
-Count of .png file(s) found      : 5785
-Board name option specified      : IMPORT
-Database backup will be taken at : /home/XXXX/invokeai-main/databases/backup
-
-Notes about the import process:
-- Source image files will not be modified, only copied to the outputs directory.
-- If the same file name already exists in the destination, the file will be skipped.
-- If the same file name already has a record in the database, the file will be skipped.
-- Invoke AI metadata tags will be updated/written into the imported copy only.
-- On the imported copy, only Invoke AI known tags (latest and legacy) will be retained (dream, sd-metadata, invokeai, invokeai_metadata)
-- A property 'imported_app_version' will be added to metadata that can be viewed in the UI's metadata viewer.
-- The new 3.x InvokeAI outputs folder structure is flat so recursively found source imges will all be placed into the single outputs/images folder.
- 
-Do you wish to continue with the import [Yn] ?
-
-Making DB Backup at /home/lstein/invokeai-main/databases/backup/backup-20230919T203519Z-invokeai.db...Done!
-
-===============================================================================
-Importing /home/XXXX/invokeai-2.3/outputs/images/17d09907-297d-4db3-a18a-60b337feac66.png
-... (5785 more lines) ...
-===============================================================================
-= Import Complete - Elpased Time: 0.28 second(s)
-
-Source File(s)                          : 5785
-Total Imported                          : 5783
-Skipped b/c file already exists on disk : 1
-Skipped b/c file already exists in db   : 0
-Errors during import                    : 1
-```
-## **invokeai-db-maintenance**
-
-This script helps maintain the integrity of your InvokeAI database by
-finding and fixing three problems that can arise over time:
-
-1. An image was manually deleted from the outputs directory, leaving a
-   dangling image record in the InvokeAI database. This will cause a
-   black image to appear in the gallery. This is an "orphaned database
-   image record." The script can fix this by running a "clean"
-   operation on the database, removing the orphaned entries.
-   
-2. An image is present in the outputs directory but there is no
-   corresponding entry in the database. This can happen when the image
-   is added manually to the outputs directory, or if a crash occurred
-   after the image was generated but before the database was
-   completely updated. The symptom is that the image is present in the
-   outputs folder but doesn't appear in the InvokeAI gallery. This is
-   called an "orphaned image file." The script can fix this problem by
-   running an "archive" operation in which orphaned files are moved
-   into a directory named `outputs/images-archive`. If you wish, you
-   can then run `invokeai-image-import` to reimport these images back
-   into the database.
-   
-3. The thumbnail for an image is missing, again causing a black
-   gallery thumbnail. This is fixed by running the "thumbnaiils"
-   operation, which simply regenerates and re-registers the missing
-   thumbnail.
-   
-You can find and fix all three of these problems in a single go by
-executing this command:
-
-```bash
-invokeai-db-maintenance --operation all
-```
-
-Or you can run just the clean and thumbnail operations like this:
-
-```bash
-invokeai-db-maintenance -operation clean, thumbnail
-```
-
-If called without any arguments, the script will ask you which
-operations you wish to perform.
-
-## **invokeai-migrate3**
-
-This script will migrate settings and models (but not images!) from an
-InvokeAI v2.3 root folder to an InvokeAI 3.X folder. Call it with the
-source and destination root folders like this:
-
-```bash
-invokeai-migrate3 --from ~/invokeai-2.3 --to invokeai-3.1.1
-```
-
-Both directories must previously have been properly created and
-initialized by `invokeai-configure`. If you wish to migrate the images
-contained in the older root as well, you can use the
-`invokeai-image-migrate` script described earlier.
-
----
-
-Copyright (c) 2023, Lincoln Stein and the InvokeAI Development Team

docs/features/index.md

@@ -30,6 +30,10 @@ image output.
 ### * [Image-to-Image Guide](IMG2IMG.md)
 Use a seed image to build new creations in 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)
@@ -51,9 +55,6 @@ Prevent InvokeAI from displaying unwanted racy images.
 ### * [Controlling Logging](LOGGING.md)
 Control how InvokeAI logs status messages.
 
-### * [Command-line Utilities](UTILITIES.md)
-A list of the command-line utilities available with InvokeAI.
-
 <!-- OUT OF DATE
 ### * [Miscellaneous](OTHER.md)
 Run InvokeAI on Google Colab, generate images with repeating patterns,

docs/help/diffusion.md

@@ -1,27 +0,0 @@
-Taking the time to understand the diffusion process will help you to understand how to more effectively use InvokeAI.
-
-There are two main ways Stable Diffusion works - with images, and latents.
-
-Image space represents images in pixel form that you look at. Latent space represents compressed inputs. It’s in latent space that Stable Diffusion processes images. A VAE (Variational Auto Encoder) is responsible for compressing and encoding inputs into latent space, as well as decoding outputs back into image space.
-
-To fully understand the diffusion process, we need to understand a few more terms: UNet, CLIP, and conditioning.
-
-A U-Net is a model trained on a large number of latent images with with known amounts of random noise added.  This means that the U-Net can be given a slightly noisy image and it will predict the pattern of noise needed to subtract from the image in order to recover the original. 
-
-CLIP is a model that tokenizes and encodes text into conditioning. This conditioning guides the model during the denoising steps to produce a new image. 
-
-The U-Net and CLIP work together during the image generation process at each denoising step, with the U-Net removing noise in such a way that the result is similar to images in the U-Net’s training set, while CLIP guides the U-Net towards creating images that are most similar to the prompt.
-
-
-When you generate an image using text-to-image, multiple steps occur in latent space:
-1. Random noise is generated at the chosen height and width. The noise’s characteristics are dictated by  seed. This noise tensor is passed into latent space. We’ll call this noise A.
-2. Using a model’s U-Net, a noise predictor examines noise A, and the words tokenized by CLIP from your prompt (conditioning). It generates its own noise tensor to predict what the final image might look like in latent space. We’ll call this noise B.
-3. Noise B is subtracted from noise A in an attempt to create a latent image consistent with the prompt. This step is repeated for the number of sampler steps chosen.
-4. The VAE decodes the final latent image from latent space into image space.
-
-Image-to-image is a similar process, with only step 1 being different:
-1. The input image is encoded from image space into latent space by the VAE. Noise is then added to the input latent image. Denoising Strength dictates how may noise steps are added, and the amount of noise added at each step. A Denoising Strength of 0 means there are 0 steps and no noise added, resulting in an unchanged image, while a Denoising Strength of 1 results in the image being completely replaced with noise and a full set of denoising steps are performance. The process is then the same as steps 2-4 in the text-to-image process. 
-
-Furthermore, a model provides the CLIP prompt tokenizer, the VAE, and a U-Net (where noise prediction occurs given a prompt and initial noise tensor).
-
-A noise scheduler (eg. DPM++ 2M Karras) schedules the subtraction of noise from the latent image across the sampler steps chosen (step 3 above). Less noise is usually subtracted at higher sampler steps. 

docs/index.md

@@ -15,8 +15,7 @@ title: Home
 <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@6.2.1/css/fontawesome.min.css">
 <style>
     .button {
-      width: 100%;
-      max-width: 100%;
+      width: 300px;
       height: 50px;
       background-color: #448AFF;
       color: #fff;
@@ -28,9 +27,8 @@ title: Home
 
     .button-container {
       display: grid;
-      grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
+      grid-template-columns: repeat(3, 300px);
       gap: 20px;
-      justify-content: center;
     }
 
     .button:hover {
@@ -51,9 +49,9 @@ title: Home
 [![github stars badge]][github stars link]
 [![github forks badge]][github forks link]
 
-<!-- [![CI checks on main badge]][ci checks on main link]
+[![CI checks on main badge]][ci checks on main link]
 [![CI checks on dev badge]][ci checks on dev link]
-[![latest commit to dev badge]][latest commit to dev link] -->
+<!-- [![latest commit to dev badge]][latest commit to dev link] -->
 
 [![github open issues badge]][github open issues link]
 [![github open prs badge]][github open prs link]
@@ -147,7 +145,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
 ### InvokeAI Configuration
 - [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
-- [Database Maintenance and other Command Line Utilities](features/UTILITIES.md)
 
 ## :octicons-log-16: Important Changes Since Version 2.3
 

docs/installation/020_INSTALL_MANUAL.md

@@ -8,9 +8,9 @@ title: Installing Manually
 
 </figure>
 
-!!! warning "This is for Advanced Users"
+!!! warning "This is for advanced Users"
 
-    **Python experience is mandatory**
+    **python experience is mandatory**
 
 ## Introduction
 
@@ -256,10 +256,6 @@ manager, please follow these steps:
         *highly recommended** if your virtual environment is located outside of
         your runtime directory.
 
-    !!! tip
-
-        On linux, it is recommended to run invokeai with the following env var: `MALLOC_MMAP_THRESHOLD_=1048576`. For example: `MALLOC_MMAP_THRESHOLD_=1048576 invokeai --web`. This helps to prevent memory fragmentation that can lead to memory accumulation over time. This env var is set automatically when running via `invoke.sh`.
-
 10.  Render away!
 
     Browse the [features](../features/index.md) section to learn about all the
@@ -291,7 +287,7 @@ manager, please follow these steps:
     Leave off the `--gui` option to run the script using command-line arguments. Pass the `--help` argument
     to get usage instructions.
 
-## Developer Install
+### Developer Install
 
 If you have an interest in how InvokeAI works, or you would like to
 add features or bugfixes, you are encouraged to install the source
@@ -300,29 +296,18 @@ code for InvokeAI. For this to work, you will need to install the
 on your system, please see the [Git Installation
 Guide](https://github.com/git-guides/install-git)
 
-You will also need to install the [frontend development toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md).
-
-If you have a "normal" installation, you should create a totally separate virtual environment for the git-based installation, else the two may interfere.
-
-> **Why do I need the frontend toolchain**?
->
-> The InvokeAI project uses trunk-based development. That means our `main` branch is the development branch, and releases are tags on that branch. Because development is very active, we don't keep an updated build of the UI in `main` - we only build it for production releases.
->
-> That means that between releases, to have a functioning application when running directly from the repo, you will need to run the UI in dev mode or build it regularly (any time the UI code changes).
-
-1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
-2. From the command line, run this command:
+1. From the command line, run this command:
    ```bash
-   git clone https://github.com/<your_github_username>/InvokeAI.git
+   git clone https://github.com/invoke-ai/InvokeAI.git
    ```
 
     This will create a directory named `InvokeAI` and populate it with the
-    full source code from your fork of the InvokeAI repository.
+    full source code from the InvokeAI repository.
 
-3. Activate the InvokeAI virtual environment as per step (4) of the manual
+2. Activate the InvokeAI virtual environment as per step (4) of the manual
 installation protocol (important!)
 
-4. Enter the InvokeAI repository directory and run one of these
+3. Enter the InvokeAI repository directory and run one of these
    commands, based on your GPU:
 
     === "CUDA (NVidia)"
@@ -348,15 +333,11 @@ installation protocol (important!)
     Be sure to pass `-e` (for an editable install) and don't forget the
     dot ("."). It is part of the command.
 
-5.  Install the [frontend toolchain](https://github.com/invoke-ai/InvokeAI/blob/main/docs/contributing/contribution_guides/contributingToFrontend.md) and do a production build of the UI as described.
-
-6.  You can now run `invokeai` and its related commands. The code will be
+    You can now run `invokeai` and its related commands. The code will be
     read from the repository, so that you can edit the .py source files
     and watch the code's behavior change.
 
-    When you pull in new changes to the repo, be sure to re-build the UI.
-
-7.  If you wish to contribute to the InvokeAI project, you are
+4.  If you wish to contribute to the InvokeAI project, you are
     encouraged to establish a GitHub account and "fork"
     https://github.com/invoke-ai/InvokeAI into your own copy of the
     repository. You can then use GitHub functions to create and submit

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -57,30 +57,6 @@ familiar with containerization technologies such as Docker.
 For downloads and instructions, visit the [NVIDIA CUDA Container
 Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
 
-### cuDNN Installation for 40/30 Series Optimization* (Optional)
-
-1. Find the InvokeAI folder
-2. Click on .venv folder - e.g., YourInvokeFolderHere\\.venv
-3. Click on Lib folder - e.g., YourInvokeFolderHere\\.venv\Lib
-4. Click on site-packages folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages
-5. Click on Torch directory - e.g., YourInvokeFolderHere\InvokeAI\\.venv\Lib\site-packages\torch
-6. Click on the lib folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib
-7. Copy everything inside the folder and save it elsewhere as a backup.
-8. Go to __https://developer.nvidia.com/cudnn__
-9. Login or create an Account. 
-10. Choose the newer version of cuDNN. **Note:** 
-There are two versions, 11.x or 12.x for the differents architectures(Turing,Maxwell Etc...) of GPUs.
-You can find which version you should download from [this link](https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html).
-13. Download the latest version and extract it from the download location
-14. Find the bin folder E\cudnn-windows-x86_64-__Whatever Version__\bin
-15. Copy and paste the .dll files into YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib **Make sure to copy, and not move the files**
-16. If prompted, replace any existing files 
-
-**Notes:** 
-* If no change is seen or any issues are encountered, follow the same steps as above and paste the torch/lib backup folder you made earlier and replace it. If you didn't make a backup, you can also uninstall and reinstall torch through the command line to repair this folder. 
-* This optimization is  intended for the newer version of graphics card (40/30 series) but results have been seen with older graphics card.
-
-
 ### Torch Installation
 
 When installing torch and torchvision manually with `pip`, remember to provide

docs/installation/040_INSTALL_DOCKER.md

@@ -4,9 +4,9 @@ title: Installing with Docker
 
 # :fontawesome-brands-docker: Docker
 
-!!! warning "For most users"
+!!! warning "For end users"
 
-    We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md)
+    We highly recommend to Install InvokeAI locally using [these instructions](index.md)
 
 !!! tip "For developers"
 

docs/installation/050_INSTALLING_MODELS.md

@@ -171,16 +171,3 @@ subfolders and organize them as you wish.
 
 The location of the autoimport directories are controlled by settings
 in `invokeai.yaml`. See [Configuration](../features/CONFIGURATION.md).
-
-### Installing models that live in HuggingFace subfolders
-
-On rare occasions you may need to install a diffusers-style model that
-lives in a subfolder of a HuggingFace repo id. In this event, simply
-add ":_subfolder-name_" to the end of the repo id. For example, if the
-repo id is "monster-labs/control_v1p_sd15_qrcode_monster" and the model
-you wish to fetch lives in a subfolder named "v2", then the repo id to
-pass to the various model installers should be 
-
-```
-monster-labs/control_v1p_sd15_qrcode_monster:v2
-```

docs/installation/INSTALLATION.md

@@ -17,36 +17,18 @@ This fork is supported across Linux, Windows and Macintosh. Linux users can use
 either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
 driver).
 
-
-## **[Automated Installer](010_INSTALL_AUTOMATED.md)**
+### [Installation Getting Started Guide](installation)
+#### **[Automated Installer](010_INSTALL_AUTOMATED.md)**
 ✅ This is the recommended installation method for first-time users. 
-
-  This is a script that will install all of InvokeAI's essential
-  third party libraries and InvokeAI itself. It includes access to a
-  "developer console" which will help us debug problems with you and
-  give you to access experimental features.
-
-## **[Manual Installation](020_INSTALL_MANUAL.md)**
-This method is recommended for experienced users and developers.
-
-  In this method you will manually run the commands needed to install
-  InvokeAI and its dependencies. We offer two recipes: one suited to
-  those who prefer the `conda` tool, and one suited to those who prefer
-  `pip` and Python virtual environments. In our hands the pip install
-  is faster and more reliable, but your mileage may vary.
-  Note that the conda installation method is currently deprecated and
-  will not be supported at some point in the future.
-
-## **[Docker Installation](040_INSTALL_DOCKER.md)**
-This method is recommended for those familiar with running Docker containers.
-
-We offer a method for creating Docker containers containing InvokeAI and its dependencies. This method is recommended for individuals with experience with Docker containers and understand the pluses and minuses of a container-based install.
-
-## Other Installation Guides
-  - [PyPatchMatch](060_INSTALL_PATCHMATCH.md)
-  - [XFormers](070_INSTALL_XFORMERS.md)
-  - [CUDA and ROCm Drivers](030_INSTALL_CUDA_AND_ROCM.md)
-  - [Installing New Models](050_INSTALLING_MODELS.md)
+#### [Manual Installation](020_INSTALL_MANUAL.md)
+This method is recommended for experienced users and developers
+#### [Docker 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)
 
 ## :fontawesome-solid-computer: Hardware Requirements
 
@@ -81,3 +63,43 @@ images in full-precision mode:
 - GTX 1650 series cards
 - GTX 1660 series cards
 
+## Installation options
+
+1. [Automated Installer](010_INSTALL_AUTOMATED.md)
+
+    This is a script that will install all of InvokeAI's essential
+    third party libraries and InvokeAI itself. It includes access to a
+    "developer console" which will help us debug problems with you and
+    give you to access experimental features.
+
+
+    ✅ This is the recommended option for first time users. 
+
+2. [Manual Installation](020_INSTALL_MANUAL.md)
+
+    In this method you will manually run the commands needed to install
+    InvokeAI and its dependencies. We offer two recipes: one suited to
+    those who prefer the `conda` tool, and one suited to those who prefer
+    `pip` and Python virtual environments. In our hands the pip install
+    is faster and more reliable, but your mileage may vary.
+    Note that the conda installation method is currently deprecated and
+    will not be supported at some point in the future.
+
+    This method is recommended for users who have previously used `conda`
+    or `pip` in the past, developers, and anyone who wishes to remain on
+    the cutting edge of future InvokeAI development and is willing to put
+    up with occasional glitches and breakage.
+
+3. [Docker Installation](040_INSTALL_DOCKER.md)
+
+    We also offer a method for creating Docker containers containing
+    InvokeAI and its dependencies. This method is recommended for
+    individuals with experience with Docker containers and understand
+    the pluses and minuses of a container-based install.
+
+## Quick Guides
+
+* [Installing CUDA and ROCm Drivers](./030_INSTALL_CUDA_AND_ROCM.md)
+* [Installing XFormers](./070_INSTALL_XFORMERS.md)
+* [Installing PyPatchMatch](./060_INSTALL_PATCHMATCH.md)
+* [Installing New Models](./050_INSTALLING_MODELS.md)

docs/javascripts/tablesort.js

@@ -1,7 +0,0 @@
-document$.subscribe(function() {
-    var tables = document.querySelectorAll("article table:not([class])")
-    tables.forEach(function(table) {
-      new Tablesort(table)
-    })
-  })
-  

docs/nodes/NODES.md

@@ -1,90 +0,0 @@
-# Using the Workflow Editor
-
-The workflow editor is a blank canvas allowing for the use of individual functions and image transformations to control the image generation workflow. Nodes take in inputs on the left side of the node, and return an output on the right side of the node. A node graph is composed of multiple nodes that are connected together to create a workflow. Nodes' inputs and outputs are connected by dragging connectors from node to node. Inputs and outputs are color coded for ease of use.
-
-If you're not familiar with Diffusion, take a look at our [Diffusion Overview.](../help/diffusion.md) Understanding how diffusion works will enable you to more easily use the Workflow Editor and build workflows to suit your needs.
-
-## Features
-
-### Linear View
-The Workflow Editor allows you to create a UI for your workflow, to make it easier to iterate on your generations. 
-
-To add an input to the Linear UI, right click on the input label and select "Add to Linear View".
-
-The Linear UI View will also be part of the saved workflow, allowing you share workflows and enable other to use them, regardless of complexity. 
-
-![linearview](../assets/nodes/linearview.png)
-
-### Renaming Fields and Nodes
-Any node or input field can be renamed in the workflow editor. If the input field you have renamed has been added to the Linear View, the changed name will be reflected in the Linear View and the node. 
-
-### Managing Nodes
-
-* Ctrl+C to copy a node
-* Ctrl+V to paste a node
-* Backspace/Delete to delete a node
-* Shift+Click to drag and select multiple nodes 
-
-### Node Caching 
-
-Nodes have a "Use Cache" option in their footer. This allows for performance improvements by using the previously cached values during the workflow processing. 
-
-
-## Important Concepts 
-
-There are several node grouping concepts that can be examined with a narrow focus. These (and other) groupings can be pieced together to make up functional graph setups, and are important to understanding how groups of nodes work together as part of a whole. Note that the screenshots below aren't examples of complete functioning node graphs (see Examples).
-
-### Noise
-
-An initial noise tensor is necessary for the latent diffusion process. As a result, the Denoising node requires a noise node input.  
-
-![groupsnoise](../assets/nodes/groupsnoise.png)
-
-### Text Prompt Conditioning
-
-Conditioning is necessary for the latent diffusion process, whether empty or not. As a result, the Denoising node requires positive and negative conditioning inputs. Conditioning is reliant on a CLIP text encoder provided by the Model Loader node.
-
-![groupsconditioning](../assets/nodes/groupsconditioning.png)
-
-### Image to Latents & VAE
-
-The ImageToLatents node takes in a pixel image and a VAE and outputs a latents. The LatentsToImage node does the opposite, taking in a latents and a VAE and outpus a pixel image. 
-
-![groupsimgvae](../assets/nodes/groupsimgvae.png)
-
-### Defined & Random Seeds
-
-It is common to want to use both the same seed (for continuity) and random seeds (for variety). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed.
-
-![groupsrandseed](../assets/nodes/groupsrandseed.png)
-
-### ControlNet
-
-The ControlNet node outputs a Control, which can be provided as input to a Denoise Latents node. Depending on the type of ControlNet desired, ControlNet nodes usually require an image processor node, such as a Canny Processor or Depth Processor, which prepares an input image for use with ControlNet.
-
-![groupscontrol](../assets/nodes/groupscontrol.png)
-
-### LoRA
-
-The Lora Loader node lets you load a LoRA and pass it as output.A LoRA provides fine-tunes to the UNet and text encoder weights that augment the base model’s image and text vocabularies.
-
-![groupslora](../assets/nodes/groupslora.png)
-
-### Scaling
-
-Use the ImageScale, ScaleLatents, and Upscale nodes to upscale images and/or latent images. Upscaling is the process of enlarging an image and adding more detail. The chosen method differs across contexts. However, be aware that latents are already noisy and compressed at their original resolution; scaling an image could produce more detailed results.
-
-![groupsallscale](../assets/nodes/groupsallscale.png)
-
-### Iteration + Multiple Images as Input
-
-Iteration is a common concept in any processing, and means to repeat a process with given input. In nodes, you're able to use the Iterate node to iterate through collections usually gathered by the Collect node. The Iterate node has many potential uses, from processing a collection of images one after another, to varying seeds across multiple image generations and more. This screenshot demonstrates how to collect several images and use them in an image generation workflow.
-
-![groupsiterate](../assets/nodes/groupsiterate.png)
-
-### Batch / Multiple Image Generation + Random Seeds
-
-Batch or multiple image generation in the workflow editor is done using the RandomRange node. In this case, the 'Size' field represents the number of images to generate, meaning this example will generate 4 images. As RandomRange produces a collection of integers, we need to add the Iterate node to iterate through the collection. This noise can then be fed to the Denoise Latents node for it to iterate through the denoising process with the different seeds provided.
-
-![groupsmultigenseeding](../assets/nodes/groupsmultigenseeding.png)
-

docs/nodes/comfyToInvoke.md

@@ -1,80 +0,0 @@
-# ComfyUI to InvokeAI
-
-If you're coming to InvokeAI from ComfyUI, welcome! You'll find things are similar but different - the good news is that you already know how things should work, and it's just a matter of wiring them up! 
-
-Some things to note: 
-
-- InvokeAI's nodes tend to be more granular than default nodes in Comfy. This means each node in Invoke will do a specific task and you might need to use multiple nodes to achieve the same result. The added granularity improves the control you have have over your workflows. 
-- InvokeAI's backend and ComfyUI's backend are very different which means Comfy workflows are not able to be imported into InvokeAI. However, we have created a [list of popular workflows](exampleWorkflows.md) for you to get started with Nodes in InvokeAI!
-
-## Node Equivalents:
-
-| Comfy UI Category | ComfyUI Node | Invoke Equivalent      |
-|:---------------------------------- |:---------------------------------- | :----------------------------------|
-| Sampling |KSampler |Denoise Latents|
-| Sampling |Ksampler Advanced|Denoise Latents |
-| Loaders |Load Checkpoint | Main Model Loader _or_ SDXL Main Model Loader|
-| Loaders |Load VAE | VAE Loader |
-| Loaders |Load Lora | LoRA Loader _or_ SDXL Lora Loader|
-| Loaders |Load ControlNet Model | ControlNet|
-| Loaders |Load ControlNet Model (diff) | ControlNet|
-| Loaders |Load Style Model | Reference Only ControlNet will be coming in a future version of InvokeAI|
-| Loaders |unCLIPCheckpointLoader | N/A |
-| Loaders |GLIGENLoader | N/A |
-| Loaders |Hypernetwork Loader | N/A |
-| Loaders |Load Upscale Model | Occurs within "Upscale (RealESRGAN)"|
-|Conditioning |CLIP Text Encode (Prompt) | Compel (Prompt) or SDXL Compel (Prompt) |
-|Conditioning |CLIP Set Last Layer | CLIP Skip|
-|Conditioning |Conditioning (Average) | Use the .blend() feature of prompts |
-|Conditioning |Conditioning (Combine) | N/A |
-|Conditioning |Conditioning (Concat) | See the Prompt Tools Community Node|
-|Conditioning |Conditioning (Set Area) | N/A |
-|Conditioning |Conditioning (Set Mask) | Mask Edge |
-|Conditioning |CLIP Vision Encode | N/A |
-|Conditioning |unCLIPConditioning | N/A |
-|Conditioning |Apply ControlNet | ControlNet |
-|Conditioning |Apply ControlNet (Advanced) | ControlNet |
-|Latent |VAE Decode | Latents to Image|
-|Latent |VAE Encode | Image to Latents |
-|Latent |Empty Latent Image | Noise |
-|Latent |Upscale Latent |Resize Latents |
-|Latent |Upscale Latent By |Scale Latents |
-|Latent |Latent Composite | Blend Latents |
-|Latent |LatentCompositeMasked | N/A |
-|Image |Save Image | Image |
-|Image |Preview Image |Current |
-|Image |Load Image | Image|
-|Image |Empty Image| Blank Image |
-|Image |Invert Image | Invert Lerp Image |
-|Image |Batch Images | Link "Image" nodes into an "Image Collection" node |
-|Image |Pad Image for Outpainting | Outpainting is easily accomplished in the Unified Canvas |
-|Image |ImageCompositeMasked | Paste Image |
-|Image | Upscale Image | Resize Image |
-|Image | Upscale Image By | Upscale Image |
-|Image | Upscale Image (using Model) | Upscale Image |
-|Image | ImageBlur | Blur Image |
-|Image | ImageQuantize | N/A |
-|Image | ImageSharpen | N/A |
-|Image | Canny | Canny Processor |
-|Mask |Load Image (as Mask) | Image |
-|Mask |Convert Mask to Image | Image|
-|Mask |Convert Image to Mask | Image |
-|Mask |SolidMask | N/A |
-|Mask |InvertMask |Invert Lerp Image |
-|Mask |CropMask | Crop Image |
-|Mask |MaskComposite | Combine Mask |
-|Mask |FeatherMask | Blur Image |
-|Advanced | Load CLIP | Main Model Loader _or_ SDXL Main Model Loader|
-|Advanced | UNETLoader | Main Model Loader _or_ SDXL Main Model Loader|
-|Advanced | DualCLIPLoader | Main Model Loader _or_ SDXL Main Model Loader|
-|Advanced | Load Checkpoint | Main Model Loader _or_ SDXL Main Model Loader |
-|Advanced | ConditioningZeroOut | N/A |
-|Advanced | ConditioningSetTimestepRange | N/A |
-|Advanced | CLIPTextEncodeSDXLRefiner | Compel (Prompt) or SDXL Compel (Prompt) |
-|Advanced | CLIPTextEncodeSDXL |Compel (Prompt) or SDXL Compel (Prompt) |
-|Advanced | ModelMergeSimple | Model Merging is available in the Model Manager |
-|Advanced | ModelMergeBlocks | Model Merging is available in the Model Manager|
-|Advanced | CheckpointSave | Model saving is available in the Model Manager|
-|Advanced | CLIPMergeSimple | N/A |
-
-

docs/nodes/communityNodes.md

@@ -2,29 +2,32 @@
 
 These are nodes that have been developed by the community, for the community. If you're not sure what a node is, you can learn more about nodes [here](overview.md).
 
-If you'd like to submit a node for the community, please refer to the [node creation overview](contributingNodes.md).
+If you'd like to submit a node for the community, please refer to the [node creation overview](./overview.md#contributing-nodes).
 
-To download a node, simply download the `.py` node file from the link and add it to the `invokeai/app/invocations` folder in your Invoke AI install location. If you used the automated installation, this can be found inside the `.venv` folder. Along with the node, an example node graph should be provided to help you get started with the node. 
+To download a node, simply download the `.py` node file from the link and add it to the `invokeai/app/invocations/` folder in your Invoke AI install location. Along with the node, an example node graph should be provided to help you get started with the node. 
 
-To use a community workflow, download the the `.json` node graph file and load it into Invoke AI via the **Load Workflow** button in the Workflow Editor. 
+To use a community node graph, download the the `.json` node graph file and load it into Invoke AI via the **Load Nodes** button on the Node Editor. 
 
---------------------------------
+## Disclaimer
 
---------------------------------
-### Make 3D
+The nodes linked below have been developed and contributed by members of the Invoke AI community. While we strive to ensure the quality and safety of these contributions, we do not guarantee the reliability or security of the nodes. If you have issues or concerns with any of the nodes below, please raise it on GitHub or in the Discord.
 
-**Description:** Create compelling 3D stereo images from 2D originals.
+## List of Nodes
 
-**Node Link:** [https://gitlab.com/srcrr/shift3d/-/raw/main/make3d.py](https://gitlab.com/srcrr/shift3d)
+### FaceTools
 
-**Example Node Graph:**  https://gitlab.com/srcrr/shift3d/-/raw/main/example-workflow.json?ref_type=heads&inline=false
+**Description:** FaceTools is a collection of nodes created to manipulate faces as you would in Unified Canvas. It includes FaceMask, FaceOff, and FacePlace. FaceMask autodetects a face in the image using MediaPipe and creates a mask from it. FaceOff similarly detects a face, then takes the face off of the image by adding a square bounding box around it and cropping/scaling it. FacePlace puts the bounded face image from FaceOff back onto the original image. Using these nodes with other inpainting node(s), you can put new faces on existing things, put new things around existing faces, and work closer with a face as a bounded image. Additionally, you can supply X and Y offset values to scale/change the shape of the mask for finer control on FaceMask and FaceOff. See GitHub repository below for usage examples.
 
-**Output Examples** 
+**Node Link:** https://github.com/ymgenesis/FaceTools/
 
-![Painting of a cozy delapidated house](https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png){: style="height:512px;width:512px"}
-![Photo of cute puppies](https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png){: style="height:512px;width:512px"}
+**FaceMask Output Examples** 
+
+![5cc8abce-53b0-487a-b891-3bf94dcc8960](https://github.com/invoke-ai/InvokeAI/assets/25252829/43f36d24-1429-4ab1-bd06-a4bedfe0955e)
+![b920b710-1882-49a0-8d02-82dff2cca907](https://github.com/invoke-ai/InvokeAI/assets/25252829/7660c1ed-bf7d-4d0a-947f-1fc1679557ba)
+![71a91805-fda5-481c-b380-264665703133](https://github.com/invoke-ai/InvokeAI/assets/25252829/f8f6a2ee-2b68-4482-87da-b90221d5c3e2)
+
+<hr>
 
---------------------------------
 ### Ideal Size
 
 **Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
@@ -32,282 +35,6 @@ To use a community workflow, download the the `.json` node graph file and load i
 **Node Link:** https://github.com/JPPhoto/ideal-size-node
 
 --------------------------------
-### Film Grain
-
-**Description:** This node adds a film grain effect to the input image based on the weights, seeds, and blur radii parameters. It works with RGB input images only.
-
-**Node Link:** https://github.com/JPPhoto/film-grain-node
-
---------------------------------
-### Image Picker
-
-**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
-
-**Node Link:** https://github.com/JPPhoto/image-picker-node
-
---------------------------------
-### Thresholding
-
-**Description:** This node generates masks for highlights, midtones, and shadows given an input image. You can optionally specify a blur for the lookup table used in making those masks from the source image.
-
-**Node Link:** https://github.com/JPPhoto/thresholding-node
-
-**Examples**
-
-Input:
-
-![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/c88ada13-fb3d-484c-a4fe-947b44712632){: style="height:512px;width:512px"}
-
-Highlights/Midtones/Shadows:
-
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/727021c1-36ff-4ec8-90c8-105e00de986d" style="width: 30%" />
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0b721bfc-f051-404e-b905-2f16b824ddfe" style="width: 30%" />
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/04c1297f-1c88-42b6-a7df-dd090b976286" style="width: 30%" />
-
-Highlights/Midtones/Shadows (with LUT blur enabled):
-
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/19aa718a-70c1-4668-8169-d68f4bd13771" style="width: 30%" />
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0a440e43-697f-4d17-82ee-f287467df0a5" style="width: 30%" />
-<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0701fd0f-2ca7-4fe2-8613-2b52547bafce" style="width: 30%" />
-
---------------------------------
-### Halftone
-
-**Description**: Halftone converts the source image to grayscale and then performs halftoning. CMYK Halftone converts the image to CMYK and applies a per-channel halftoning to make the source image look like a magazine or newspaper. For both nodes, you can specify angles and halftone dot spacing.
-
-**Node Link:** https://github.com/JPPhoto/halftone-node
-
-**Example**
-
-Input:
-
-![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/fd5efb9f-4355-4409-a1c2-c1ca99e0cab4){: style="height:512px;width:512px"}
-
-Halftone Output:
-
-![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/7e606f29-e68f-4d46-b3d5-97f799a4ec2f){: style="height:512px;width:512px"}
-
-CMYK Halftone Output:
-
-![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea){: style="height:512px;width:512px"}
-
---------------------------------
-### Retroize
-
-**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
-
-**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
-
-**Retroize Output Examples**
-
-![image](https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974)
-
---------------------------------
-### GPT2RandomPromptMaker
-
-**Description:** A node for InvokeAI utilizes the GPT-2 language model to generate random prompts based on a provided seed and context.
-
-**Node Link:** https://github.com/mickr777/GPT2RandomPromptMaker
-
-**Output Examples** 
-
-Generated Prompt: An enchanted weapon will be usable by any character regardless of their alignment.
-
-![9acf5aef-7254-40dd-95b3-8eac431dfab0 (1)](https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c)
-
---------------------------------
-### Load Video Frame
-
-**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
-
-**Node Link:** https://github.com/helix4u/load_video_frame
-
-**Example Node Graph:**  https://github.com/helix4u/load_video_frame/blob/main/Example_Workflow.json
-
-**Output Example:** 
-
-![Example animation](https://github.com/helix4u/load_video_frame/blob/main/testmp4_embed_converted.gif)
-[Full mp4 of Example Output test.mp4](https://github.com/helix4u/load_video_frame/blob/main/test.mp4)
-
---------------------------------
-
-### Oobabooga
-
-**Description:** asks a local LLM running in Oobabooga's Text-Generation-Webui to write a prompt based on the user input.
-
-**Link:** https://github.com/sammyf/oobabooga-node
-
-
-**Example:**
-
-"describe a new mystical  creature in its natural environment"
-
-*can return*
-
-"The mystical creature I am describing to you is called the "Glimmerwing". It is a majestic, iridescent being that inhabits the depths of the most enchanted forests and glimmering lakes. Its body is covered in shimmering scales that reflect every color of the rainbow, and it has delicate, translucent wings that sparkle like diamonds in the sunlight. The Glimmerwing's home is a crystal-clear lake, surrounded by towering trees with leaves that shimmer like jewels. In this serene environment, the Glimmerwing spends its days swimming gracefully through the water, chasing schools of glittering fish and playing with the gentle ripples of the lake's surface.
-As the sun sets, the Glimmerwing perches on a branch of one of the trees, spreading its wings to catch the last rays of light. The creature's scales glow softly, casting a rainbow of colors across the forest floor. The Glimmerwing sings a haunting melody, its voice echoing through the stillness of the night air. Its song is said to have the power to heal the sick and bring peace to troubled souls. Those who are lucky enough to hear the Glimmerwing's song are forever changed by its beauty and grace."
-
-![glimmerwing_small](https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed)
-
-**Requirement**
-
-a Text-Generation-Webui instance (might work remotely too, but I never tried it) and obviously InvokeAI 3.x
-
-**Note**
-
-This node works best with SDXL models, especially as the style can be described independantly of the LLM's output.
-
---------------------------------
-### Depth Map from Wavefront OBJ
-
-**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
-
-To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
-
-**Node Link:** https://github.com/dwringer/depth-from-obj-node
-
-**Example Usage:**
-![depth from obj usage graph](https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg)
-
---------------------------------
-### Generative Grammar-Based Prompt Nodes
-
-**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no more nonterminal terms remain in the string.
-
-This includes 3 Nodes:
-- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
-- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
-- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
-
-**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
-
-**Example Usage:**
-![lookups usage example graph](https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg)
-
---------------------------------
-### Image and Mask Composition Pack
-
-**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
-
-This includes 15 Nodes:
-
-- *Adjust Image Hue Plus* - Rotate the hue of an image in one of several different color spaces.
-- *Blend Latents/Noise (Masked)* - Use a mask to blend part of one latents tensor [including Noise outputs] into another. Can be used to "renoise" sections during a multi-stage [masked] denoising process.
-- *Enhance Image* - Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
-- *Equivalent Achromatic Lightness* - Calculates image lightness accounting for Helmholtz-Kohlrausch effect based on a method described by High, Green, and Nussbaum (2023).
-- *Text to Mask (Clipseg)* - Input a prompt and an image to generate a mask representing areas of the image matched by the prompt.
-- *Text to Mask Advanced (Clipseg)* - Output up to four prompt masks combined with logical "and", logical "or", or as separate channels of an RGBA image.
-- *Image Layer Blend* - Perform a layered blend of two images using alpha compositing. Opacity of top layer is selectable, with optional mask and several different blend modes/color spaces.
-- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
-- *Image Dilate or Erode* - Dilate or expand a mask (or any image!). This is equivalent to an expand/contract operation.
-- *Image Value Thresholds* - Clip an image to pure black/white beyond specified thresholds.
-- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
-- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
-- *Rotate/Flip Image* - Rotate an image in degrees clockwise/counterclockwise about its center, optionally resizing the image boundaries to fit, or flipping it about the vertical and/or horizontal axes.
-- *Shadows/Highlights/Midtones* - Extract three masks (with adjustable hard or soft thresholds) representing shadows, midtones, and highlights regions of an image.
-- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
-
-**Node Link:** https://github.com/dwringer/composition-nodes
-
-**Nodes and Output Examples:**
-![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg)
-
---------------------------------
-### Size Stepper Nodes
-
-**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
-
-A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
-
-**Node Link:** https://github.com/dwringer/size-stepper-nodes
-
-**Example Usage:**
-![size stepper usage graph](https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg)
-
---------------------------------
-
-### Text font to Image
-
-**Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
-
-**Node Link:** https://github.com/mickr777/textfontimage
-
-**Output Examples**
-
-![a3609d48-d9b7-41f0-b280-063d857986fb](https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36)
-
-Results after using the depth controlnet
-
-![9133eabb-bcda-4326-831e-1b641228b178](https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a)
-![4f9a3fa8-9be9-4236-8a3e-fcec66decd2a](https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc)
-![babd69c4-9d60-4a55-a834-5e8397f62610](https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89)
-
---------------------------------
-
-### Prompt Tools 
-
-**Description:** A set of InvokeAI nodes that add general prompt manipulation tools.  These where written to accompany the PromptsFromFile node and other prompt generation nodes.
-
-1. PromptJoin - Joins to prompts into one.
-2. PromptReplace - performs a search and replace on a prompt. With the option of using regex.
-3. PromptSplitNeg - splits a prompt into positive and negative using the old V2 method of [] for negative.
-4. PromptToFile - saves a prompt or collection of prompts to a file. one per line. There is an append/overwrite option.
-5. PTFieldsCollect - Converts image generation fields into a Json format string that can be passed to Prompt to file. 
-6. PTFieldsExpand - Takes Json string and converts it to individual generation parameters This can be fed from the Prompts to file node.
-7. PromptJoinThree -  Joins 3 prompt together.
-8. PromptStrength - This take a string and float and outputs another string in the format of (string)strength like the weighted format of compel. 
-9. PromptStrengthCombine - This takes a collection of prompt strength strings and outputs a string in the .and() or .blend() format that can be fed into a proper prompt node.
-
-See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/main/README.md
-
-**Node Link:** https://github.com/skunkworxdark/Prompt-tools-nodes
-
---------------------------------
-
-### XY Image to Grid and Images to Grids nodes
-
-**Description:** Image to grid nodes and supporting tools.
-
-1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then mutilple grids will be created until it runs out of images.
-2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images.  The XYImages collection has to be built using the supporoting nodes. See example node setups for more details.
-   
-
-See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/README.md
-
-**Node Link:** https://github.com/skunkworxdark/XYGrid_nodes
-
---------------------------------
-
-### Image to Character Art Image Node's
-
-**Description:** Group of nodes to convert an input image into ascii/unicode art Image
-
-**Node Link:** https://github.com/mickr777/imagetoasciiimage
-
-**Output Examples**
-
-<img src="https://github.com/invoke-ai/InvokeAI/assets/115216705/8e061fcc-9a2c-4fa9-bcc7-c0f7b01e9056" width="300" />
-<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/3c4990eb-2f42-46b9-90f9-0088b939dc6a" width="300" /></br>
-<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/fee7f800-a4a8-41e2-a66b-c66e4343307e" width="300" />
-<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/1d9c1003-a45f-45c2-aac7-46470bb89330" width="300" />
-
---------------------------------
-
-### Grid to Gif
-
-**Description:** One node that turns a grid image into an image colletion, one node that turns an image collection into a gif
-
-**Node Link:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/GridToGif.py
-
-**Example Node Graph:**  https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/Grid%20to%20Gif%20Example%20Workflow.json
-
-**Output Examples** 
-
-<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/input.png" width="300" />
-<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/output.gif" width="300" />
-
---------------------------------
-
 ### Example Node Template
 
 **Description:** This node allows you to do super cool things with InvokeAI.
@@ -320,12 +47,7 @@ See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/READ
 
 ![Example Image](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png){: style="height:115px;width:240px"}
 
-
-## Disclaimer
-
-The nodes linked have been developed and contributed by members of the Invoke AI community. While we strive to ensure the quality and safety of these contributions, we do not guarantee the reliability or security of the nodes. If you have issues or concerns with any of the nodes below, please raise it on GitHub or in the Discord.
-
-
 ## Help
 If you run into any issues with a node, please post in the [InvokeAI Discord](https://discord.gg/ZmtBAhwWhy). 
 
+

docs/nodes/contributingNodes.md

@@ -1,27 +0,0 @@
-# Contributing Nodes
-
-To learn about the specifics of creating a new node, please visit our [Node creation documentation](../contributing/INVOCATIONS.md). 
-
-Once you’ve created a node and confirmed that it behaves as expected locally, follow these steps: 
-
-- Make sure the node is contained in a new Python (.py) file. Preferrably, the node is in a repo with a README detaling the nodes usage & examples to help others more easily use your node.
-- Submit a pull request with a link to your node(s) repo in GitHub against the `main` branch to add the node to the [Community Nodes](communityNodes.md) list
-    - Make sure you are following the template below and have provided all relevant details about the node and what it does. Example output images and workflows are very helpful for other users looking to use your node.
-- A maintainer will review the pull request and node. If the node is aligned with the direction of the project, you may be asked for permission to include it in the core project.
-
-### Community Node Template
-
-```markdown
---------------------------------
-### Super Cool Node Template
-
-**Description:** This node allows you to do super cool things with InvokeAI.
-
-**Node Link:** https://github.com/invoke-ai/InvokeAI/fake_node.py
-
-**Example Node Graph:**  https://github.com/invoke-ai/InvokeAI/fake_node_graph.json
-
-**Output Examples** 
-
-![InvokeAI](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png)
-```

docs/nodes/defaultNodes.md

@@ -1,104 +0,0 @@
-# List of Default Nodes
-
-The table below contains a list of the default nodes shipped with InvokeAI and their descriptions.
-
-| Node <img width=160 align="right"> | Function                                                                              |
-|: ---------------------------------- | :--------------------------------------------------------------------------------------|
-|Add Integers 			| Adds two numbers|
-|Boolean Primitive Collection 			| A collection of boolean primitive values|
-|Boolean Primitive 			| A boolean primitive value|
-|Canny Processor 			| Canny edge detection for ControlNet|
-|CLIP Skip 			| Skip layers in clip text_encoder model.|
-|Collect 			| Collects values into a collection|
-|Color Correct 			| Shifts the colors of a target image to match the reference image, optionally using a mask to only color-correct certain regions of the target image.|
-|Color Primitive 			| A color primitive value|
-|Compel Prompt 			| Parse prompt using compel package to conditioning.|
-|Conditioning Primitive Collection 			| A collection of conditioning tensor primitive values|
-|Conditioning Primitive 			| A conditioning tensor primitive value|
-|Content Shuffle Processor 			| Applies content shuffle processing to image|
-|ControlNet 			| Collects ControlNet info to pass to other nodes|
-|Denoise Latents 			| Denoises noisy latents to decodable images|
-|Divide Integers 			| Divides two numbers|
-|Dynamic Prompt 			| Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator|
-|[FaceMask](./detailedNodes/faceTools.md#facemask) | Generates masks for faces in an image to use with Inpainting|
-|[FaceIdentifier](./detailedNodes/faceTools.md#faceidentifier)             | Identifies and labels faces in an image|
-|[FaceOff](./detailedNodes/faceTools.md#faceoff)             | Creates a new image that is a scaled bounding box with a mask on the face for Inpainting|
-|Float Math             | Perform basic math operations on two floats|
-|Float Primitive Collection 			| A collection of float primitive values|
-|Float Primitive 			| A float primitive value|
-|Float Range 			| Creates a range|
-|HED (softedge) Processor 			| Applies HED edge detection to image|
-|Blur Image 			| Blurs an image|
-|Extract Image Channel 			| Gets a channel from an image.|
-|Image Primitive Collection 			| A collection of image primitive values|
-|Integer Math           | Perform basic math operations on two integers|
-|Convert Image Mode 			| Converts an image to a different mode.|
-|Crop Image 			| Crops an image to a specified box. The box can be outside of the image.|
-|Image Hue Adjustment 			| Adjusts the Hue of an image.|
-|Inverse Lerp Image 			| Inverse linear interpolation of all pixels of an image|
-|Image Primitive 			| An image primitive value|
-|Lerp Image 			| Linear interpolation of all pixels of an image|
-|Offset Image Channel 			| Add to or subtract from an image color channel by a uniform value.|
-|Multiply Image Channel 			| Multiply or Invert an image color channel by a scalar value.|
-|Multiply Images 			| Multiplies two images together using `PIL.ImageChops.multiply()`.|
-|Blur NSFW Image 			| Add blur to NSFW-flagged images|
-|Paste Image 			| Pastes an image into another image.|
-|ImageProcessor 			| Base class for invocations that preprocess images for ControlNet|
-|Resize Image 			| Resizes an image to specific dimensions|
-|Round Float            | Rounds a float to a specified number of decimal places|
-|Float to Integer       | Converts a float to an integer. Optionally rounds to an even multiple of a input number.|
-|Scale Image 			| Scales an image by a factor|
-|Image to Latents 			| Encodes an image into latents.|
-|Add Invisible Watermark 			| Add an invisible watermark to an image|
-|Solid Color Infill 			| Infills transparent areas of an image with a solid color|
-|PatchMatch Infill 			| Infills transparent areas of an image using the PatchMatch algorithm|
-|Tile Infill 			| Infills transparent areas of an image with tiles of the image|
-|Integer Primitive Collection 			| A collection of integer primitive values|
-|Integer Primitive 			| An integer primitive value|
-|Iterate 			| Iterates over a list of items|
-|Latents Primitive Collection 			| A collection of latents tensor primitive values|
-|Latents Primitive 			| A latents tensor primitive value|
-|Latents to Image 			| Generates an image from latents.|
-|Leres (Depth) Processor 			| Applies leres processing to image|
-|Lineart Anime Processor 			| Applies line art anime processing to image|
-|Lineart Processor 			| Applies line art processing to image|
-|LoRA Loader 			| Apply selected lora to unet and text_encoder.|
-|Main Model Loader 			| Loads a main model, outputting its submodels.|
-|Combine Mask 			| Combine two masks together by multiplying them using `PIL.ImageChops.multiply()`.|
-|Mask Edge 			| Applies an edge mask to an image|
-|Mask from Alpha 			| Extracts the alpha channel of an image as a mask.|
-|Mediapipe Face Processor 			| Applies mediapipe face processing to image|
-|Midas (Depth) Processor 			| Applies Midas depth processing to image|
-|MLSD Processor 			| Applies MLSD processing to image|
-|Multiply Integers 			| Multiplies two numbers|
-|Noise 			| Generates latent noise.|
-|Normal BAE Processor 			| Applies NormalBae processing to image|
-|ONNX Latents to Image 			| Generates an image from latents.|
-|ONNX Prompt (Raw) 			| A node to process inputs and produce outputs. May use dependency injection in __init__ to receive providers.|
-|ONNX Text to Latents 			| Generates latents from conditionings.|
-|ONNX Model Loader 			| Loads a main model, outputting its submodels.|
-|OpenCV Inpaint 			| Simple inpaint using opencv.|
-|Openpose Processor 			| Applies Openpose processing to image|
-|PIDI Processor 			| Applies PIDI processing to image|
-|Prompts from File 			| Loads prompts from a text file|
-|Random Integer 			| Outputs a single random integer.|
-|Random Range 			| Creates a collection of random numbers|
-|Integer Range 			| Creates a range of numbers from start to stop with step|
-|Integer Range of Size 			| Creates a range from start to start + size with step|
-|Resize Latents 			| Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8.|
-|SDXL Compel Prompt 			| Parse prompt using compel package to conditioning.|
-|SDXL LoRA Loader 			| Apply selected lora to unet and text_encoder.|
-|SDXL Main Model Loader 			| Loads an sdxl base model, outputting its submodels.|
-|SDXL Refiner Compel Prompt 			| Parse prompt using compel package to conditioning.|
-|SDXL Refiner Model Loader 			| Loads an sdxl refiner model, outputting its submodels.|
-|Scale Latents 			| Scales latents by a given factor.|
-|Segment Anything Processor 			| Applies segment anything processing to image|
-|Show Image 			| Displays a provided image, and passes it forward in the pipeline.|
-|Step Param Easing 			| Experimental per-step parameter easing for denoising steps|
-|String Primitive Collection 			| A collection of string primitive values|
-|String Primitive 			| A string primitive value|
-|Subtract Integers 			| Subtracts two numbers|
-|Tile Resample Processor 			| Tile resampler processor|
-|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
-|VAE Loader 			| Loads a VAE model, outputting a VaeLoaderOutput|
-|Zoe (Depth) Processor 			| Applies Zoe depth processing to image|

docs/nodes/detailedNodes/faceTools.md

@@ -1,154 +0,0 @@
-# Face Nodes
-
-## FaceOff
-
-FaceOff mimics a user finding a face in an image and resizing the bounding box
-around the head in Canvas.
-
-Enter a face ID (found with FaceIdentifier) to choose which face to mask.
-
-Just as you would add more context inside the bounding box by making it larger
-in Canvas, the node gives you a padding input (in pixels) which will
-simultaneously add more context, and increase the resolution of the bounding box
-so the face remains the same size inside it.
-
-The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
-threshold a detected face must reach for it to be processed. Lowering this value
-may help if detection is failing. If the detected masks are imperfect and stray
-too far outside/inside of faces, the node gives you X & Y offsets to shrink/grow
-the masks by a multiplier.
-
-FaceOff will output the face in a bounded image, taking the face off of the
-original image for input into any node that accepts image inputs. The node also
-outputs a face mask with the dimensions of the bounded image. The X & Y outputs
-are for connecting to the X & Y inputs of the Paste Image node, which will place
-the bounded image back on the original image using these coordinates.
-
-###### Inputs/Outputs
-
-| Input              | Description                                                                                                                                                                              |
-| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Image              | Image for face detection                                                                                                                                                                 |
-| Face ID            | The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.                                                                        |
-| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
-| X Offset           | X-axis offset of the mask                                                                                                                                                                |
-| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
-| Padding            | All-axis padding around the mask in pixels                                                                                                                                               |
-| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
-
-| Output        | Description                                      |
-| ------------- | ------------------------------------------------ |
-| Bounded Image | Original image bound, cropped, and resized       |
-| Width         | The width of the bounded image in pixels         |
-| Height        | The height of the bounded image in pixels        |
-| Mask          | The output mask                                  |
-| X             | The x coordinate of the bounding box's left side |
-| Y             | The y coordinate of the bounding box's top side  |
-
-## FaceMask
-
-FaceMask mimics a user drawing masks on faces in an image in Canvas.
-
-The "Face IDs" input allows the user to select specific faces to be masked.
-Leave empty to detect and mask all faces, or a comma-separated list for a
-specific combination of faces (ex: `1,2,4`). A single integer will detect and
-mask that specific face. Find face IDs with the FaceIdentifier node.
-
-The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
-threshold a detected face must reach for it to be processed. Lowering this value
-may help if detection is failing.
-
-If the detected masks are imperfect and stray too far outside/inside of faces,
-the node gives you X & Y offsets to shrink/grow the masks by a multiplier. All
-masks shrink/grow together by the X & Y offset values.
-
-By default, masks are created to change faces. When masks are inverted, they
-change surrounding areas, protecting faces.
-
-###### Inputs/Outputs
-
-| Input              | Description                                                                                                                                                                              |
-| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Image              | Image for face detection                                                                                                                                                                 |
-| Face IDs           | Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.                                                   |
-| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
-| X Offset           | X-axis offset of the mask                                                                                                                                                                |
-| Y Offset           | Y-axis offset of the mask                                                                                                                                                                |
-| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
-| Invert Mask        | Toggle to invert the face mask                                                                                                                                                           |
-
-| Output | Description                       |
-| ------ | --------------------------------- |
-| Image  | The original image                |
-| Width  | The width of the image in pixels  |
-| Height | The height of the image in pixels |
-| Mask   | The output face mask              |
-
-## FaceIdentifier
-
-FaceIdentifier outputs an image with detected face IDs printed in white numbers
-onto each face.
-
-Face IDs can then be used in FaceMask and FaceOff to selectively mask all, a
-specific combination, or single faces.
-
-The FaceIdentifier output image is generated for user reference, and isn't meant
-to be passed on to other image-processing nodes.
-
-The "Minimum Confidence" input defaults to 0.5 (50%), and represents a pass/fail
-threshold a detected face must reach for it to be processed. Lowering this value
-may help if detection is failing. If an image is changed in the slightest, run
-it through FaceIdentifier again to get updated FaceIDs.
-
-###### Inputs/Outputs
-
-| Input              | Description                                                                                                                                                                              |
-| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Image              | Image for face detection                                                                                                                                                                 |
-| Minimum Confidence | Minimum confidence for face detection (lower if detection is failing)                                                                                                                    |
-| Chunk              | Chunk (or divide) the image into sections to greatly improve face detection success. Defaults to off, but will activate if no faces are detected normally. Activate to chunk by default. |
-
-| Output | Description                                                                                      |
-| ------ | ------------------------------------------------------------------------------------------------ |
-| Image  | The original image with small face ID numbers printed in white onto each face for user reference |
-| Width  | The width of the original image in pixels                                                        |
-| Height | The height of the original image in pixels                                                       |
-
-## Tips
-
-- If not all target faces are being detected, activate Chunk to bypass full
-  image face detection and greatly improve detection success.
-- Final results will vary between full-image detection and chunking for faces
-  that are detectable by both due to the nature of the process. Try either to
-  your taste.
-- Be sure Minimum Confidence is set the same when using FaceIdentifier with
-  FaceOff/FaceMask.
-- For FaceOff, use the color correction node before faceplace to correct edges
-  being noticeable in the final image (see example screenshot).
-- Non-inpainting models may struggle to paint/generate correctly around faces.
-- If your face won't change the way you want it to no matter what you change,
-  consider that the change you're trying to make is too much at that resolution.
-  For example, if an image is only 512x768 total, the face might only be 128x128
-  or 256x256, much smaller than the 512x512 your SD1.5 model was probably
-  trained on. Try increasing the resolution of the image by upscaling or
-  resizing, add padding to increase the bounding box's resolution, or use an
-  image where the face takes up more pixels.
-- If the resulting face seems out of place pasted back on the original image
-  (ie. too large, not proportional), add more padding on the FaceOff node to
-  give inpainting more context. Context and good prompting are important to
-  keeping things proportional.
-- If you find the mask is too big/small and going too far outside/inside the
-  area you want to affect, adjust the x & y offsets to shrink/grow the mask area
-- Use a higher denoise start value to resemble aspects of the original face or
-  surroundings. Denoise start = 0 & denoise end = 1 will make something new,
-  while denoise start = 0.50 & denoise end = 1 will be 50% old and 50% new.
-- mediapipe isn't good at detecting faces with lots of face paint, hair covering
-  the face, etc. Anything that obstructs the face will likely result in no faces
-  being detected.
-- If you find your face isn't being detected, try lowering the minimum
-  confidence value from 0.5. This could result in false positives, however
-  (random areas being detected as faces and masked).
-- After altering an image and wanting to process a different face in the newly
-  altered image, run the altered image through FaceIdentifier again to see the
-  new Face IDs. MediaPipe will most likely detect faces in a different order
-  after an image has been changed in the slightest.

docs/nodes/exampleWorkflows.md

@@ -1,14 +0,0 @@
-# Example Workflows
-
-We've curated some example workflows for you to get started with Workflows in InvokeAI
-
-To use them, right click on your desired workflow, press "Download Linked File". You can then use the "Load Workflow" functionality in InvokeAI to load the workflow and start generating images!
-
-If you're interested in finding more workflows, checkout the [#share-your-workflows](https://discord.com/channels/1020123559063990373/1130291608097661000) channel in the InvokeAI Discord.
-
-* [SD1.5 / SD2 Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/Text_to_Image.json)
-* [SDXL Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json)
-* [SDXL (with Refiner) Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json) 
-* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)
-* [FaceMask](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceMask.json)
-* [FaceOff with 2x Face Scaling](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceOff_FaceScale2x.json)

docs/nodes/overview.md

@@ -1,26 +1,42 @@
 # Nodes
 
 ## What are Nodes?
-An Node is simply a single operation that takes in inputs and returns
-out outputs. Multiple nodes can be linked together to create more
+An Node is simply a single operation that takes in some inputs and gives
+out some outputs. We can then chain multiple nodes together to create more
 complex functionality. All InvokeAI features are added through nodes.
 
-### Anatomy of a Node
+This means nodes can be used to easily extend the image generation capabilities of InvokeAI, and allow you build workflows to suit your needs. 
 
-Individual nodes are made up of the following:
-
-- Inputs: Edge points on the left side of the node window where you connect outputs from other nodes.
-- Outputs: Edge points on the right side of the node window where you connect to inputs on other nodes.
-- Options: Various options which are either manually configured, or overridden by connecting an output from another node to the input.
+You can read more about nodes and the node editor [here](../features/NODES.md). 
 
 
-With nodes, you can can easily extend the image generation capabilities of InvokeAI, and allow you build workflows that suit your needs. 
-
-You can read more about nodes and the node editor [here](../nodes/NODES.md). 
-
-To get started with nodes, take a look at some of our examples for [common workflows](../nodes/exampleWorkflows.md)
-
-## Downloading New Nodes
-To download a new node, visit our list of [Community Nodes](../nodes/communityNodes.md). These are nodes that have been created by the community, for the community. 
+## Downloading Nodes
+To download a new node, visit our list of [Community Nodes](communityNodes.md). These are nodes that have been created by the community, for the community. 
 
 
+## Contributing Nodes
+
+To learn about creating a new node, please visit our [Node creation documenation](../contributing/INVOCATIONS.md). 
+
+Once you’ve created a node and confirmed that it behaves as expected locally, follow these steps: 
+* Make sure the node is contained in a new Python (.py) file 
+* Submit a pull request with a link to your node in GitHub against the `nodes` branch to add the node to the [Community Nodes](Community Nodes) list
+    * Make sure you are following the template below and have provided all relevant details about the node and what it does.
+* A maintainer will review the pull request and node. If the node is aligned with the direction of the project, you might be asked for permission to include it in the core project.
+
+### Community Node Template
+
+```markdown
+--------------------------------
+### Super Cool Node Template
+
+**Description:** This node allows you to do super cool things with InvokeAI.
+
+**Node Link:** https://github.com/invoke-ai/InvokeAI/fake_node.py
+
+**Example Node Graph:**  https://github.com/invoke-ai/InvokeAI/fake_node_graph.json
+
+**Output Examples** 
+
+![InvokeAI](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png)
+```

docs/workflows/SDXL_Text_to_Image.json

@@ -1,735 +0,0 @@
-{
-  "name": "SDXL Text to Image",
-  "author": "InvokeAI",
-  "description": "Sample text to image workflow for SDXL",
-  "version": "1.0.1",
-  "contact": "invoke@invoke.ai",
-  "tags": "text2image, SDXL, default",
-  "notes": "",
-  "exposedFields": [
-    {
-      "nodeId": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "fieldName": "model"
-    },
-    {
-      "nodeId": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "fieldName": "prompt"
-    },
-    {
-      "nodeId": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "fieldName": "style"
-    },
-    {
-      "nodeId": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "fieldName": "prompt"
-    },
-    {
-      "nodeId": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "fieldName": "style"
-    },
-    {
-      "nodeId": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "fieldName": "steps"
-    }
-  ],
-  "meta": {
-    "version": "1.0.0"
-  },
-  "nodes": [
-    {
-      "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-        "type": "sdxl_compel_prompt",
-        "inputs": {
-          "prompt": {
-            "id": "5a6889e6-95cb-462f-8f4a-6b93ae7afaec",
-            "name": "prompt",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Negative Prompt",
-            "value": ""
-          },
-          "style": {
-            "id": "f240d0e6-3a1c-4320-af23-20ebb707c276",
-            "name": "style",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Negative Style",
-            "value": ""
-          },
-          "original_width": {
-            "id": "05af07b0-99a0-4a68-8ad2-697bbdb7fc7e",
-            "name": "original_width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "original_height": {
-            "id": "2c771996-a998-43b7-9dd3-3792664d4e5b",
-            "name": "original_height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "crop_top": {
-            "id": "66519dca-a151-4e3e-ae1f-88f1f9877bde",
-            "name": "crop_top",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "crop_left": {
-            "id": "349cf2e9-f3d0-4e16-9ae2-7097d25b6a51",
-            "name": "crop_left",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "target_width": {
-            "id": "44499347-7bd6-4a73-99d6-5a982786db05",
-            "name": "target_width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "target_height": {
-            "id": "fda359b0-ab80-4f3c-805b-c9f61319d7d2",
-            "name": "target_height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "clip": {
-            "id": "b447adaf-a649-4a76-a827-046a9fc8d89b",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "clip2": {
-            "id": "86ee4e32-08f9-4baa-9163-31d93f5c0187",
-            "name": "clip2",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "conditioning": {
-            "id": "7c10118e-7b4e-4911-b98e-d3ba6347dfd0",
-            "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "SDXL Negative Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 764,
-      "position": {
-        "x": 1275,
-        "y": -350
-      }
-    },
-    {
-      "id": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "55705012-79b9-4aac-9f26-c0b10309785b",
-        "type": "noise",
-        "inputs": {
-          "seed": {
-            "id": "6431737c-918a-425d-a3b4-5d57e2f35d4d",
-            "name": "seed",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "width": {
-            "id": "38fc5b66-fe6e-47c8-bba9-daf58e454ed7",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "height": {
-            "id": "16298330-e2bf-4872-a514-d6923df53cbb",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "use_cpu": {
-            "id": "c7c436d3-7a7a-4e76-91e4-c6deb271623c",
-            "name": "use_cpu",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": true
-          }
-        },
-        "outputs": {
-          "noise": {
-            "id": "50f650dc-0184-4e23-a927-0497a96fe954",
-            "name": "noise",
-            "type": "LatentsField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "bb8a452b-133d-42d1-ae4a-3843d7e4109a",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "35cfaa12-3b8b-4b7a-a884-327ff3abddd9",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": false,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 32,
-      "position": {
-        "x": 1650,
-        "y": -300
-      }
-    },
-    {
-      "id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-        "type": "l2i",
-        "inputs": {
-          "tiled": {
-            "id": "24f5bc7b-f6a1-425d-8ab1-f50b4db5d0df",
-            "name": "tiled",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "id": "b146d873-ffb9-4767-986a-5360504841a2",
-            "name": "fp32",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": true
-          },
-          "latents": {
-            "id": "65441abd-7713-4b00-9d8d-3771404002e8",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "vae": {
-            "id": "a478b833-6e13-4611-9a10-842c89603c74",
-            "name": "vae",
-            "type": "VaeField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "image": {
-            "id": "c87ae925-f858-417a-8940-8708ba9b4b53",
-            "name": "image",
-            "type": "ImageField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "4bcb8512-b5a1-45f1-9e52-6e92849f9d6c",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "23e41c00-a354-48e8-8f59-5875679c27ab",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": true,
-        "isIntermediate": false
-      },
-      "width": 320,
-      "height": 224,
-      "position": {
-        "x": 2025,
-        "y": -250
-      }
-    },
-    {
-      "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-        "type": "rand_int",
-        "inputs": {
-          "low": {
-            "id": "3ec65a37-60ba-4b6c-a0b2-553dd7a84b84",
-            "name": "low",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "high": {
-            "id": "085f853a-1a5f-494d-8bec-e4ba29a3f2d1",
-            "name": "high",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 2147483647
-          }
-        },
-        "outputs": {
-          "value": {
-            "id": "812ade4d-7699-4261-b9fc-a6c9d2ab55ee",
-            "name": "value",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "Random Seed",
-        "isOpen": false,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 32,
-      "position": {
-        "x": 1650,
-        "y": -350
-      }
-    },
-    {
-      "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-        "type": "sdxl_model_loader",
-        "inputs": {
-          "model": {
-            "id": "39f9e799-bc95-4318-a200-30eed9e60c42",
-            "name": "model",
-            "type": "SDXLMainModelField",
-            "fieldKind": "input",
-            "label": "",
-            "value": {
-              "model_name": "stable-diffusion-xl-base-1.0",
-              "base_model": "sdxl",
-              "model_type": "main"
-            }
-          }
-        },
-        "outputs": {
-          "unet": {
-            "id": "2626a45e-59aa-4609-b131-2d45c5eaed69",
-            "name": "unet",
-            "type": "UNetField",
-            "fieldKind": "output"
-          },
-          "clip": {
-            "id": "7c9c42fa-93d5-4639-ab8b-c4d9b0559baf",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "output"
-          },
-          "clip2": {
-            "id": "0dafddcf-a472-49c1-a47c-7b8fab4c8bc9",
-            "name": "clip2",
-            "type": "ClipField",
-            "fieldKind": "output"
-          },
-          "vae": {
-            "id": "ee6a6997-1b3c-4ff3-99ce-1e7bfba2750c",
-            "name": "vae",
-            "type": "VaeField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 234,
-      "position": {
-        "x": 475,
-        "y": 25
-      }
-    },
-    {
-      "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-        "type": "sdxl_compel_prompt",
-        "inputs": {
-          "prompt": {
-            "id": "5a6889e6-95cb-462f-8f4a-6b93ae7afaec",
-            "name": "prompt",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Positive Prompt",
-            "value": ""
-          },
-          "style": {
-            "id": "f240d0e6-3a1c-4320-af23-20ebb707c276",
-            "name": "style",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Positive Style",
-            "value": ""
-          },
-          "original_width": {
-            "id": "05af07b0-99a0-4a68-8ad2-697bbdb7fc7e",
-            "name": "original_width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "original_height": {
-            "id": "2c771996-a998-43b7-9dd3-3792664d4e5b",
-            "name": "original_height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "crop_top": {
-            "id": "66519dca-a151-4e3e-ae1f-88f1f9877bde",
-            "name": "crop_top",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "crop_left": {
-            "id": "349cf2e9-f3d0-4e16-9ae2-7097d25b6a51",
-            "name": "crop_left",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "target_width": {
-            "id": "44499347-7bd6-4a73-99d6-5a982786db05",
-            "name": "target_width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "target_height": {
-            "id": "fda359b0-ab80-4f3c-805b-c9f61319d7d2",
-            "name": "target_height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1024
-          },
-          "clip": {
-            "id": "b447adaf-a649-4a76-a827-046a9fc8d89b",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "clip2": {
-            "id": "86ee4e32-08f9-4baa-9163-31d93f5c0187",
-            "name": "clip2",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "conditioning": {
-            "id": "7c10118e-7b4e-4911-b98e-d3ba6347dfd0",
-            "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "SDXL Positive Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 764,
-      "position": {
-        "x": 900,
-        "y": -350
-      }
-    },
-    {
-      "id": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-        "type": "denoise_latents",
-        "inputs": {
-          "noise": {
-            "id": "4884a4b7-cc19-4fea-83c7-1f940e6edd24",
-            "name": "noise",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "steps": {
-            "id": "4c61675c-b6b9-41ac-b187-b5c13b587039",
-            "name": "steps",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 36
-          },
-          "cfg_scale": {
-            "id": "f8213f35-4637-4a1a-83f4-1f8cfb9ccd2c",
-            "name": "cfg_scale",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 7.5
-          },
-          "denoising_start": {
-            "id": "01e2f30d-0acd-4e21-98b9-a9b8e24c6db2",
-            "name": "denoising_start",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "denoising_end": {
-            "id": "3db95479-a73b-4c75-9b44-08daec16b224",
-            "name": "denoising_end",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1
-          },
-          "scheduler": {
-            "id": "db8430a9-64c3-4c54-ae38-9f597cf7b6d5",
-            "name": "scheduler",
-            "type": "Scheduler",
-            "fieldKind": "input",
-            "label": "",
-            "value": "euler"
-          },
-          "control": {
-            "id": "599b49e8-6435-4576-be41-a5155f3a17e3",
-            "name": "control",
-            "type": "ControlField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "latents": {
-            "id": "226f9e91-454e-4159-9fa6-019c0cf29277",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "denoise_mask": {
-            "id": "de019cb6-7fb5-45bf-a266-22e20889893f",
-            "name": "denoise_mask",
-            "type": "DenoiseMaskField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "positive_conditioning": {
-            "id": "02fc400a-110d-470e-8411-f404f966a949",
-            "name": "positive_conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "negative_conditioning": {
-            "id": "4bd3bdfa-fcf4-42be-8e47-1e314255798f",
-            "name": "negative_conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "unet": {
-            "id": "7c2d58a8-b5f1-4e63-8ffd-8ada52c35832",
-            "name": "unet",
-            "type": "UNetField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "latents": {
-            "id": "6a6fa492-de26-4e95-b1d9-a322fe37eb13",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "a9790729-7d6c-4418-903d-4da961fccf56",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "fa74efe5-7330-4a3c-b256-c82a544585b4",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 558,
-      "position": {
-        "x": 1650,
-        "y": -250
-      }
-    }
-  ],
-  "edges": [
-    {
-      "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "target": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2-55705012-79b9-4aac-9f26-c0b10309785b-collapsed",
-      "type": "collapsed"
-    },
-    {
-      "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "sourceHandle": "value",
-      "target": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "targetHandle": "seed",
-      "id": "reactflow__edge-ea94bc37-d995-4a83-aa99-4af42479f2f2value-55705012-79b9-4aac-9f26-c0b10309785bseed",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "clip",
-      "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "targetHandle": "clip",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip-faf965a4-7530-427b-b1f3-4ba6505c2a08clip",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "clip2",
-      "target": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "targetHandle": "clip2",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip2-faf965a4-7530-427b-b1f3-4ba6505c2a08clip2",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "clip",
-      "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "targetHandle": "clip",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204clip",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "clip2",
-      "target": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "targetHandle": "clip2",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22clip2-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204clip2",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "vae",
-      "target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "targetHandle": "vae",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22vae-dbcd2f98-d809-48c8-bf64-2635f88a2fe9vae",
-      "type": "default"
-    },
-    {
-      "source": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "sourceHandle": "latents",
-      "target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "targetHandle": "latents",
-      "id": "reactflow__edge-87ee6243-fb0d-4f77-ad5f-56591659339elatents-dbcd2f98-d809-48c8-bf64-2635f88a2fe9latents",
-      "type": "default"
-    },
-    {
-      "source": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
-      "sourceHandle": "conditioning",
-      "target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "targetHandle": "positive_conditioning",
-      "id": "reactflow__edge-faf965a4-7530-427b-b1f3-4ba6505c2a08conditioning-87ee6243-fb0d-4f77-ad5f-56591659339epositive_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
-      "sourceHandle": "conditioning",
-      "target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "targetHandle": "negative_conditioning",
-      "id": "reactflow__edge-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204conditioning-87ee6243-fb0d-4f77-ad5f-56591659339enegative_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
-      "sourceHandle": "unet",
-      "target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "targetHandle": "unet",
-      "id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22unet-87ee6243-fb0d-4f77-ad5f-56591659339eunet",
-      "type": "default"
-    },
-    {
-      "source": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "sourceHandle": "noise",
-      "target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
-      "targetHandle": "noise",
-      "id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-87ee6243-fb0d-4f77-ad5f-56591659339enoise",
-      "type": "default"
-    }
-  ]
-}

docs/workflows/Text_to_Image.json

@@ -1,573 +0,0 @@
-{
-  "name": "Text to Image",
-  "author": "InvokeAI",
-  "description": "Sample text to image workflow for Stable Diffusion 1.5/2",
-  "version": "1.0.1",
-  "contact": "invoke@invoke.ai",
-  "tags": "text2image, SD1.5, SD2, default",
-  "notes": "",
-  "exposedFields": [
-    {
-      "nodeId": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "fieldName": "model"
-    },
-    {
-      "nodeId": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "fieldName": "prompt"
-    },
-    {
-      "nodeId": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-      "fieldName": "prompt"
-    },
-    {
-      "nodeId": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "fieldName": "steps"
-    }
-  ],
-  "meta": {
-    "version": "1.0.0"
-  },
-  "nodes": [
-    {
-      "id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "id": "7739aff6-26cb-4016-8897-5a1fb2305e4e",
-            "name": "prompt",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Negative Prompt",
-            "value": ""
-          },
-          "clip": {
-            "id": "48d23dce-a6ae-472a-9f8c-22a714ea5ce0",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "conditioning": {
-            "id": "37cf3a9d-f6b7-4b64-8ff6-2558c5ecc447",
-            "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "Negative Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 235,
-      "position": {
-        "x": 1400,
-        "y": -75
-      }
-    },
-    {
-      "id": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "55705012-79b9-4aac-9f26-c0b10309785b",
-        "type": "noise",
-        "inputs": {
-          "seed": {
-            "id": "6431737c-918a-425d-a3b4-5d57e2f35d4d",
-            "name": "seed",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "width": {
-            "id": "38fc5b66-fe6e-47c8-bba9-daf58e454ed7",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 512
-          },
-          "height": {
-            "id": "16298330-e2bf-4872-a514-d6923df53cbb",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 512
-          },
-          "use_cpu": {
-            "id": "c7c436d3-7a7a-4e76-91e4-c6deb271623c",
-            "name": "use_cpu",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": true
-          }
-        },
-        "outputs": {
-          "noise": {
-            "id": "50f650dc-0184-4e23-a927-0497a96fe954",
-            "name": "noise",
-            "type": "LatentsField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "bb8a452b-133d-42d1-ae4a-3843d7e4109a",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "35cfaa12-3b8b-4b7a-a884-327ff3abddd9",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 364,
-      "position": {
-        "x": 1000,
-        "y": 350
-      }
-    },
-    {
-      "id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-        "type": "l2i",
-        "inputs": {
-          "tiled": {
-            "id": "24f5bc7b-f6a1-425d-8ab1-f50b4db5d0df",
-            "name": "tiled",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": false
-          },
-          "fp32": {
-            "id": "b146d873-ffb9-4767-986a-5360504841a2",
-            "name": "fp32",
-            "type": "boolean",
-            "fieldKind": "input",
-            "label": "",
-            "value": false
-          },
-          "latents": {
-            "id": "65441abd-7713-4b00-9d8d-3771404002e8",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "vae": {
-            "id": "a478b833-6e13-4611-9a10-842c89603c74",
-            "name": "vae",
-            "type": "VaeField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "image": {
-            "id": "c87ae925-f858-417a-8940-8708ba9b4b53",
-            "name": "image",
-            "type": "ImageField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "4bcb8512-b5a1-45f1-9e52-6e92849f9d6c",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "23e41c00-a354-48e8-8f59-5875679c27ab",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": true,
-        "isIntermediate": false
-      },
-      "width": 320,
-      "height": 266,
-      "position": {
-        "x": 1800,
-        "y": 200
-      }
-    },
-    {
-      "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-        "type": "main_model_loader",
-        "inputs": {
-          "model": {
-            "id": "993eabd2-40fd-44fe-bce7-5d0c7075ddab",
-            "name": "model",
-            "type": "MainModelField",
-            "fieldKind": "input",
-            "label": "",
-            "value": {
-              "model_name": "stable-diffusion-v1-5",
-              "base_model": "sd-1",
-              "model_type": "main"
-            }
-          }
-        },
-        "outputs": {
-          "unet": {
-            "id": "5c18c9db-328d-46d0-8cb9-143391c410be",
-            "name": "unet",
-            "type": "UNetField",
-            "fieldKind": "output"
-          },
-          "clip": {
-            "id": "6effcac0-ec2f-4bf5-a49e-a2c29cf921f4",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "output"
-          },
-          "vae": {
-            "id": "57683ba3-f5f5-4f58-b9a2-4b83dacad4a1",
-            "name": "vae",
-            "type": "VaeField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": false,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 32,
-      "position": {
-        "x": 1000,
-        "y": 200
-      }
-    },
-    {
-      "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-        "type": "compel",
-        "inputs": {
-          "prompt": {
-            "id": "7739aff6-26cb-4016-8897-5a1fb2305e4e",
-            "name": "prompt",
-            "type": "string",
-            "fieldKind": "input",
-            "label": "Positive Prompt",
-            "value": ""
-          },
-          "clip": {
-            "id": "48d23dce-a6ae-472a-9f8c-22a714ea5ce0",
-            "name": "clip",
-            "type": "ClipField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "conditioning": {
-            "id": "37cf3a9d-f6b7-4b64-8ff6-2558c5ecc447",
-            "name": "conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "output"
-          }
-        },
-        "label": "Positive Compel Prompt",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 235,
-      "position": {
-        "x": 1000,
-        "y": -75
-      }
-    },
-    {
-      "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-        "type": "rand_int",
-        "inputs": {
-          "low": {
-            "id": "3ec65a37-60ba-4b6c-a0b2-553dd7a84b84",
-            "name": "low",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "high": {
-            "id": "085f853a-1a5f-494d-8bec-e4ba29a3f2d1",
-            "name": "high",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 2147483647
-          }
-        },
-        "outputs": {
-          "value": {
-            "id": "812ade4d-7699-4261-b9fc-a6c9d2ab55ee",
-            "name": "value",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "Random Seed",
-        "isOpen": false,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 32,
-      "position": {
-        "x": 1000,
-        "y": 275
-      }
-    },
-    {
-      "id": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "type": "invocation",
-      "data": {
-        "version": "1.0.0",
-        "id": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-        "type": "denoise_latents",
-        "inputs": {
-          "noise": {
-            "id": "8b18f3eb-40d2-45c1-9a9d-28d6af0dce2b",
-            "name": "noise",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "steps": {
-            "id": "0be4373c-46f3-441c-80a7-a4bb6ceb498c",
-            "name": "steps",
-            "type": "integer",
-            "fieldKind": "input",
-            "label": "",
-            "value": 36
-          },
-          "cfg_scale": {
-            "id": "107267ce-4666-4cd7-94b3-7476b7973ae9",
-            "name": "cfg_scale",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 7.5
-          },
-          "denoising_start": {
-            "id": "d2ce9f0f-5fc2-48b2-b917-53442941e9a1",
-            "name": "denoising_start",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 0
-          },
-          "denoising_end": {
-            "id": "8ad51505-b8d0-422a-beb8-96fc6fc6b65f",
-            "name": "denoising_end",
-            "type": "float",
-            "fieldKind": "input",
-            "label": "",
-            "value": 1
-          },
-          "scheduler": {
-            "id": "53092874-a43b-4623-91a2-76e62fdb1f2e",
-            "name": "scheduler",
-            "type": "Scheduler",
-            "fieldKind": "input",
-            "label": "",
-            "value": "euler"
-          },
-          "control": {
-            "id": "7abe57cc-469d-437e-ad72-a18efa28215f",
-            "name": "control",
-            "type": "ControlField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "latents": {
-            "id": "add8bbe5-14d0-42d4-a867-9c65ab8dd129",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "denoise_mask": {
-            "id": "f373a190-0fc8-45b7-ae62-c4aa8e9687e1",
-            "name": "denoise_mask",
-            "type": "DenoiseMaskField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "positive_conditioning": {
-            "id": "c7160303-8a23-4f15-9197-855d48802a7f",
-            "name": "positive_conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "negative_conditioning": {
-            "id": "fd750efa-1dfc-4d0b-accb-828e905ba320",
-            "name": "negative_conditioning",
-            "type": "ConditioningField",
-            "fieldKind": "input",
-            "label": ""
-          },
-          "unet": {
-            "id": "af1f41ba-ce2a-4314-8d7f-494bb5800381",
-            "name": "unet",
-            "type": "UNetField",
-            "fieldKind": "input",
-            "label": ""
-          }
-        },
-        "outputs": {
-          "latents": {
-            "id": "8508d04d-f999-4a44-94d0-388ab1401d27",
-            "name": "latents",
-            "type": "LatentsField",
-            "fieldKind": "output"
-          },
-          "width": {
-            "id": "93dc8287-0a2a-4320-83a4-5e994b7ba23e",
-            "name": "width",
-            "type": "integer",
-            "fieldKind": "output"
-          },
-          "height": {
-            "id": "d9862f5c-0ab5-46fa-8c29-5059bb581d96",
-            "name": "height",
-            "type": "integer",
-            "fieldKind": "output"
-          }
-        },
-        "label": "",
-        "isOpen": true,
-        "notes": "",
-        "embedWorkflow": false,
-        "isIntermediate": true
-      },
-      "width": 320,
-      "height": 558,
-      "position": {
-        "x": 1400,
-        "y": 200
-      }
-    }
-  ],
-  "edges": [
-    {
-      "source": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
-      "sourceHandle": "value",
-      "target": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "targetHandle": "seed",
-      "id": "reactflow__edge-ea94bc37-d995-4a83-aa99-4af42479f2f2value-55705012-79b9-4aac-9f26-c0b10309785bseed",
-      "type": "default"
-    },
-    {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "clip",
-      "target": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "targetHandle": "clip",
-      "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-7d8bf987-284f-413a-b2fd-d825445a5d6cclip",
-      "type": "default"
-    },
-    {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "clip",
-      "target": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-      "targetHandle": "clip",
-      "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8clip-93dc02a4-d05b-48ed-b99c-c9b616af3402clip",
-      "type": "default"
-    },
-    {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "vae",
-      "target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "targetHandle": "vae",
-      "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8vae-dbcd2f98-d809-48c8-bf64-2635f88a2fe9vae",
-      "type": "default"
-    },
-    {
-      "source": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "sourceHandle": "latents",
-      "target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
-      "targetHandle": "latents",
-      "id": "reactflow__edge-75899702-fa44-46d2-b2d5-3e17f234c3e7latents-dbcd2f98-d809-48c8-bf64-2635f88a2fe9latents",
-      "type": "default"
-    },
-    {
-      "source": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
-      "sourceHandle": "conditioning",
-      "target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "targetHandle": "positive_conditioning",
-      "id": "reactflow__edge-7d8bf987-284f-413a-b2fd-d825445a5d6cconditioning-75899702-fa44-46d2-b2d5-3e17f234c3e7positive_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
-      "sourceHandle": "conditioning",
-      "target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "targetHandle": "negative_conditioning",
-      "id": "reactflow__edge-93dc02a4-d05b-48ed-b99c-c9b616af3402conditioning-75899702-fa44-46d2-b2d5-3e17f234c3e7negative_conditioning",
-      "type": "default"
-    },
-    {
-      "source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
-      "sourceHandle": "unet",
-      "target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "targetHandle": "unet",
-      "id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8unet-75899702-fa44-46d2-b2d5-3e17f234c3e7unet",
-      "type": "default"
-    },
-    {
-      "source": "55705012-79b9-4aac-9f26-c0b10309785b",
-      "sourceHandle": "noise",
-      "target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
-      "targetHandle": "noise",
-      "id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-75899702-fa44-46d2-b2d5-3e17f234c3e7noise",
-      "type": "default"
-    }
-  ]
-}

installer/create_installer.sh

@@ -14,7 +14,7 @@ fi
 VERSION=$(cd ..; python -c "from invokeai.version import __version__ as version; print(version)")
 PATCH=""
 VERSION="v${VERSION}${PATCH}"
-LATEST_TAG="v3-latest"
+LATEST_TAG="v3.0-latest"
 
 echo Building installer for version $VERSION
 echo "Be certain that you're in the 'installer' directory before continuing."
@@ -46,7 +46,6 @@ if [[ $(python -c 'from importlib.util import find_spec; print(find_spec("build"
     pip install --user build
 fi
 
-rm -r ../build
 python -m build --wheel --outdir dist/ ../.
 
 # ----------------------

installer/lib/installer.py

@@ -332,7 +332,6 @@ class InvokeAiInstance:
         Configure the InvokeAI runtime directory
         """
 
-        auto_install = False
         # set sys.argv to a consistent state
         new_argv = [sys.argv[0]]
         for i in range(1, len(sys.argv)):
@@ -341,17 +340,13 @@ class InvokeAiInstance:
                 new_argv.append(el)
                 new_argv.append(sys.argv[i + 1])
             elif el in ["-y", "--yes", "--yes-to-all"]:
-                auto_install = True
+                new_argv.append(el)
         sys.argv = new_argv
 
-        import messages
         import requests  # to catch download exceptions
+        from messages import introduction
 
-        auto_install = auto_install or messages.user_wants_auto_configuration()
-        if auto_install:
-            sys.argv.append("--yes")
-        else:
-            messages.introduction()
+        introduction()
 
         from invokeai.frontend.install.invokeai_configure import invokeai_configure
 
@@ -412,7 +407,7 @@ def get_pip_from_venv(venv_path: Path) -> str:
     :rtype: str
     """
 
-    pip = "Scripts\\pip.exe" if OS == "Windows" else "bin/pip"
+    pip = "Scripts\pip.exe" if OS == "Windows" else "bin/pip"
     return str(venv_path.expanduser().resolve() / pip)
 
 

installer/lib/main.py

@@ -5,7 +5,6 @@ InvokeAI Installer
 import argparse
 import os
 from pathlib import Path
-
 from installer import Installer
 
 if __name__ == "__main__":
@@ -50,7 +49,7 @@ if __name__ == "__main__":
 
     try:
         inst.install(**args.__dict__)
-    except KeyboardInterrupt:
+    except KeyboardInterrupt as exc:
         print("\n")
         print("Ctrl-C pressed. Aborting.")
         print("Come back soon!")

installer/lib/messages.py

@@ -7,7 +7,7 @@ import os
 import platform
 from pathlib import Path
 
-from prompt_toolkit import HTML, prompt
+from prompt_toolkit import prompt
 from prompt_toolkit.completion import PathCompleter
 from prompt_toolkit.validation import Validator
 from rich import box, print
@@ -65,50 +65,17 @@ def confirm_install(dest: Path) -> bool:
     if dest.exists():
         print(f":exclamation: Directory {dest} already exists :exclamation:")
         dest_confirmed = Confirm.ask(
-            ":stop_sign: (re)install in this location?",
+            ":stop_sign: Are you sure you want to (re)install in this location?",
             default=False,
         )
     else:
         print(f"InvokeAI will be installed in {dest}")
-        dest_confirmed = Confirm.ask("Use this location?", default=True)
+        dest_confirmed = not Confirm.ask(f"Would you like to pick a different location?", default=False)
     console.line()
 
     return dest_confirmed
 
 
-def user_wants_auto_configuration() -> bool:
-    """Prompt the user to choose between manual and auto configuration."""
-    console.rule("InvokeAI Configuration Section")
-    console.print(
-        Panel(
-            Group(
-                "\n".join(
-                    [
-                        "Libraries are installed and InvokeAI will now set up its root directory and configuration. Choose between:",
-                        "",
-                        "  * AUTOMATIC configuration:  install reasonable defaults and a minimal set of starter models.",
-                        "  * MANUAL configuration: manually inspect and adjust configuration options and pick from a larger set of starter models.",
-                        "",
-                        "Later you can fine tune your configuration by selecting option [6] 'Change InvokeAI startup options' from the invoke.bat/invoke.sh launcher script.",
-                    ]
-                ),
-            ),
-            box=box.MINIMAL,
-            padding=(1, 1),
-        )
-    )
-    choice = (
-        prompt(
-            HTML("Choose <b>&lt;a&gt;</b>utomatic or <b>&lt;m&gt;</b>anual configuration [a/m] (a): "),
-            validator=Validator.from_callable(
-                lambda n: n == "" or n.startswith(("a", "A", "m", "M")), error_message="Please select 'a' or 'm'"
-            ),
-        )
-        or "a"
-    )
-    return choice.lower().startswith("a")
-
-
 def dest_path(dest=None) -> Path:
     """
     Prompt the user for the destination path and create the path
@@ -123,7 +90,7 @@ def dest_path(dest=None) -> Path:
         dest = Path(dest).expanduser().resolve()
     else:
         dest = Path.cwd().expanduser().resolve()
-    prev_dest = init_path = dest
+    prev_dest = dest.expanduser().resolve()
 
     dest_confirmed = confirm_install(dest)
 
@@ -142,9 +109,9 @@ def dest_path(dest=None) -> Path:
         )
 
         console.line()
-        console.print(f"[orange3]Please select the destination directory for the installation:[/] \\[{browse_start}]: ")
+        print(f"[orange3]Please select the destination directory for the installation:[/] \[{browse_start}]: ")
         selected = prompt(
-            ">>> ",
+            f">>> ",
             complete_in_thread=True,
             completer=path_completer,
             default=str(browse_start) + os.sep,
@@ -167,14 +134,14 @@ def dest_path(dest=None) -> Path:
     try:
         dest.mkdir(exist_ok=True, parents=True)
         return dest
-    except PermissionError:
-        console.print(
+    except PermissionError as exc:
+        print(
             f"Failed to create directory {dest} due to insufficient permissions",
             style=Style(color="red"),
             highlight=True,
         )
-    except OSError:
-        console.print_exception()
+    except OSError as exc:
+        console.print_exception(exc)
 
     if Confirm.ask("Would you like to try again?"):
         dest_path(init_path)

installer/templates/invoke.bat.in

@@ -17,10 +17,9 @@ echo 6. Change InvokeAI startup options
 echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
 echo 8. Open the developer console
 echo 9. Update InvokeAI
-echo 10. Run the InvokeAI image database maintenance script
-echo 11. Command-line help
+echo 10. Command-line help
 echo Q - Quit
-set /P choice="Please enter 1-11, Q: [1] "
+set /P choice="Please enter 1-10, Q: [1] "
 if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
@@ -59,11 +58,8 @@ IF /I "%choice%" == "1" (
    echo Running invokeai-update...
    python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "10" (
-   echo Running the db maintenance script...
-   python .venv\Scripts\invokeai-db-maintenance.exe
-) ELSE IF /I "%choice%" == "11" (
     echo Displaying command line help...
-    python .venv\Scripts\invokeai-web.exe --help %*
+    python .venv\Scripts\invokeai.exe --help %*
     pause
     exit /b
 ) ELSE IF /I "%choice%" == "q" (

installer/templates/invoke.sh.in

@@ -46,9 +46,6 @@ if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
-# Avoid glibc memory fragmentation. See invokeai/backend/model_management/README.md for details.
-export MALLOC_MMAP_THRESHOLD_=1048576
-
 # Primary function for the case statement to determine user input
 do_choice() {
     case $1 in
@@ -100,13 +97,13 @@ do_choice() {
         ;;
     10)
         clear
-        printf "Running the db maintenance script\n"
-        invokeai-db-maintenance --root ${INVOKEAI_ROOT}
+        printf "Command-line help\n"
+        invokeai --help
         ;;
-    11)
+    "HELP 1")
         clear
         printf "Command-line help\n"
-        invokeai-web --help
+        invokeai --help
         ;;
     *)
         clear
@@ -128,10 +125,7 @@ do_dialog() {
         6 "Change InvokeAI startup options"
         7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
         8 "Open the developer console"
-        9 "Update InvokeAI"
-	10 "Run the InvokeAI image database maintenance script"
-	11 "Command-line help"
-    )
+        9 "Update InvokeAI")
 
     choice=$(dialog --clear \
         --backtitle "\Zb\Zu\Z3InvokeAI" \
@@ -163,10 +157,9 @@ do_line_input() {
     printf "7: Re-run the configure script to fix a broken install\n"
     printf "8: Open the developer console\n"
     printf "9: Update InvokeAI\n"
-    printf "10: Run the InvokeAI image database maintenance script\n"
-    printf "11: Command-line help\n"
+    printf "10: Command-line help\n"
     printf "Q: Quit\n\n"
-    read -p "Please enter 1-11, Q: [1] " yn
+    read -p "Please enter 1-10, Q: [1] " yn
     choice=${yn:='1'}
     do_choice $choice
     clear

invokeai/app/api/dependencies.py

@@ -1,35 +1,35 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import sqlite3
+from typing import Optional
 from logging import Logger
-
-from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
-from invokeai.app.services.board_images import BoardImagesService, BoardImagesServiceDependencies
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
 from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
 from invokeai.app.services.boards import BoardService, BoardServiceDependencies
 from invokeai.app.services.config import InvokeAIAppConfig
 from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
 from invokeai.app.services.images import ImageService, ImageServiceDependencies
-from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
 from invokeai.app.services.resource_name import SimpleNameService
-from invokeai.app.services.session_processor.session_processor_default import DefaultSessionProcessor
-from invokeai.app.services.session_queue.session_queue_sqlite import SqliteSessionQueue
 from invokeai.app.services.urls import LocalUrlService
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.version.invokeai_version import __version__
 
 from ..services.default_graphs import create_system_graphs
+from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
 from ..services.graph import GraphExecutionState, LibraryGraph
 from ..services.image_file_storage import DiskImageFileStorage
 from ..services.invocation_queue import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
-from ..services.invocation_stats import InvocationStatsService
 from ..services.invoker import Invoker
-from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-from ..services.model_manager_service import ModelManagerService
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
-from ..services.thread import lock
+from ..services.model_manager_service import ModelManagerService
+from ..services.invocation_stats import InvocationStatsService
 from .events import FastAPIEventService
 
 
@@ -45,11 +45,11 @@ def check_internet() -> bool:
     try:
         urllib.request.urlopen(host, timeout=1)
         return True
-    except Exception:
+    except:
         return False
 
 
-logger = InvokeAILogger.get_logger()
+logger = InvokeAILogger.getLogger()
 
 
 class ApiDependencies:
@@ -68,32 +68,22 @@ class ApiDependencies:
         output_folder = config.output_path
 
         # TODO: build a file/path manager?
-        if config.use_memory_db:
-            db_location = ":memory:"
-        else:
-            db_path = config.db_path
-            db_path.parent.mkdir(parents=True, exist_ok=True)
-            db_location = str(db_path)
-
-        logger.info(f"Using database at {db_location}")
-        db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
-
-        if config.log_sql:
-            db_conn.set_trace_callback(print)
-        db_conn.execute("PRAGMA foreign_keys = ON;")
+        db_path = config.db_path
+        db_path.parent.mkdir(parents=True, exist_ok=True)
+        db_location = str(db_path)
 
         graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            conn=db_conn, table_name="graph_executions", lock=lock
+            filename=db_location, table_name="graph_executions"
         )
 
         urls = LocalUrlService()
-        image_record_storage = SqliteImageRecordStorage(conn=db_conn, lock=lock)
+        image_record_storage = SqliteImageRecordStorage(db_location)
         image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
         names = SimpleNameService()
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
 
-        board_record_storage = SqliteBoardRecordStorage(conn=db_conn, lock=lock)
-        board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn, lock=lock)
+        board_record_storage = SqliteBoardRecordStorage(db_location)
+        board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
 
         boards = BoardService(
             services=BoardServiceDependencies(
@@ -135,29 +125,18 @@ class ApiDependencies:
             boards=boards,
             board_images=board_images,
             queue=MemoryInvocationQueue(),
-            graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, lock=lock, table_name="graphs"),
+            graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
             graph_execution_manager=graph_execution_manager,
             processor=DefaultInvocationProcessor(),
             configuration=config,
             performance_statistics=InvocationStatsService(graph_execution_manager),
             logger=logger,
-            session_queue=SqliteSessionQueue(conn=db_conn, lock=lock),
-            session_processor=DefaultSessionProcessor(),
-            invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
         )
 
         create_system_graphs(services.graph_library)
 
         ApiDependencies.invoker = Invoker(services)
 
-        try:
-            lock.acquire()
-            db_conn.execute("VACUUM;")
-            db_conn.commit()
-            logger.info("Cleaned database")
-        finally:
-            lock.release()
-
     @staticmethod
     def shutdown():
         if ApiDependencies.invoker:

invokeai/app/api/routers/app_info.py

@@ -1,20 +1,19 @@
 import typing
 from enum import Enum
-from pathlib import Path
-
 from fastapi import Body
 from fastapi.routing import APIRouter
+from pathlib import Path
 from pydantic import BaseModel, Field
 
-from invokeai.app.invocations.upscale import ESRGAN_MODELS
-from invokeai.app.services.invocation_cache.invocation_cache_common import InvocationCacheStatus
-from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.patchmatch import PatchMatch
 from invokeai.backend.image_util.safety_checker import SafetyChecker
-from invokeai.backend.util.logging import logging
+from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
+from invokeai.app.invocations.upscale import ESRGAN_MODELS
+
 from invokeai.version import __version__
 
 from ..dependencies import ApiDependencies
+from invokeai.backend.util.logging import logging
 
 
 class LogLevel(int, Enum):
@@ -56,7 +55,7 @@ async def get_version() -> AppVersion:
 
 @app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
 async def get_config() -> AppConfig:
-    infill_methods = ["tile", "lama", "cv2"]
+    infill_methods = ["tile"]
     if PatchMatch.patchmatch_available():
         infill_methods.append("patchmatch")
 
@@ -104,43 +103,3 @@ async def set_log_level(
     """Sets the log verbosity level"""
     ApiDependencies.invoker.services.logger.setLevel(level)
     return LogLevel(ApiDependencies.invoker.services.logger.level)
-
-
-@app_router.delete(
-    "/invocation_cache",
-    operation_id="clear_invocation_cache",
-    responses={200: {"description": "The operation was successful"}},
-)
-async def clear_invocation_cache() -> None:
-    """Clears the invocation cache"""
-    ApiDependencies.invoker.services.invocation_cache.clear()
-
-
-@app_router.put(
-    "/invocation_cache/enable",
-    operation_id="enable_invocation_cache",
-    responses={200: {"description": "The operation was successful"}},
-)
-async def enable_invocation_cache() -> None:
-    """Clears the invocation cache"""
-    ApiDependencies.invoker.services.invocation_cache.enable()
-
-
-@app_router.put(
-    "/invocation_cache/disable",
-    operation_id="disable_invocation_cache",
-    responses={200: {"description": "The operation was successful"}},
-)
-async def disable_invocation_cache() -> None:
-    """Clears the invocation cache"""
-    ApiDependencies.invoker.services.invocation_cache.disable()
-
-
-@app_router.get(
-    "/invocation_cache/status",
-    operation_id="get_invocation_cache_status",
-    responses={200: {"model": InvocationCacheStatus}},
-)
-async def get_invocation_cache_status() -> InvocationCacheStatus:
-    """Clears the invocation cache"""
-    return ApiDependencies.invoker.services.invocation_cache.get_status()

invokeai/app/api/routers/board_images.py

@@ -34,7 +34,7 @@ async def add_image_to_board(
             board_id=board_id, image_name=image_name
         )
         return result
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to add image to board")
 
 
@@ -53,7 +53,7 @@ async def remove_image_from_board(
     try:
         result = ApiDependencies.invoker.services.board_images.remove_image_from_board(image_name=image_name)
         return result
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to remove image from board")
 
 
@@ -79,10 +79,10 @@ async def add_images_to_board(
                     board_id=board_id, image_name=image_name
                 )
                 added_image_names.append(image_name)
-            except Exception:
+            except:
                 pass
         return AddImagesToBoardResult(board_id=board_id, added_image_names=added_image_names)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to add images to board")
 
 
@@ -105,8 +105,8 @@ async def remove_images_from_board(
             try:
                 ApiDependencies.invoker.services.board_images.remove_image_from_board(image_name=image_name)
                 removed_image_names.append(image_name)
-            except Exception:
+            except:
                 pass
         return RemoveImagesFromBoardResult(removed_image_names=removed_image_names)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to remove images from board")

invokeai/app/api/routers/boards.py

@@ -37,7 +37,7 @@ async def create_board(
     try:
         result = ApiDependencies.invoker.services.boards.create(board_name=board_name)
         return result
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to create board")
 
 
@@ -50,7 +50,7 @@ async def get_board(
     try:
         result = ApiDependencies.invoker.services.boards.get_dto(board_id=board_id)
         return result
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404, detail="Board not found")
 
 
@@ -73,7 +73,7 @@ async def update_board(
     try:
         result = ApiDependencies.invoker.services.boards.update(board_id=board_id, changes=changes)
         return result
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to update board")
 
 
@@ -105,7 +105,7 @@ async def delete_board(
                 deleted_board_images=deleted_board_images,
                 deleted_images=[],
             )
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to delete board")
 
 

invokeai/app/api/routers/images.py

@@ -1,22 +1,24 @@
 import io
 from typing import Optional
 
+from PIL import Image
 from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
-from PIL import Image
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 
 from invokeai.app.invocations.metadata import ImageMetadata
 from invokeai.app.models.image import ImageCategory, ResourceOrigin
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import ImageDTO, ImageRecordChanges, ImageUrlsDTO
-
+from invokeai.app.services.models.image_record import (
+    ImageDTO,
+    ImageRecordChanges,
+    ImageUrlsDTO,
+)
 from ..dependencies import ApiDependencies
 
 images_router = APIRouter(prefix="/v1/images", tags=["images"])
 
-
 # images are immutable; set a high max-age
 IMAGE_MAX_AGE = 31536000
 
@@ -52,7 +54,7 @@ async def upload_image(
         if crop_visible:
             bbox = pil_image.getbbox()
             pil_image = pil_image.crop(bbox)
-    except Exception:
+    except:
         # Error opening the image
         raise HTTPException(status_code=415, detail="Failed to read image")
 
@@ -70,7 +72,7 @@ async def upload_image(
         response.headers["Location"] = image_dto.image_url
 
         return image_dto
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to create image")
 
 
@@ -82,7 +84,7 @@ async def delete_image(
 
     try:
         ApiDependencies.invoker.services.images.delete(image_name)
-    except Exception:
+    except Exception as e:
         # TODO: Does this need any exception handling at all?
         pass
 
@@ -94,7 +96,7 @@ async def clear_intermediates() -> int:
     try:
         count_deleted = ApiDependencies.invoker.services.images.delete_intermediates()
         return count_deleted
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to clear intermediates")
         pass
 
@@ -112,7 +114,7 @@ async def update_image(
 
     try:
         return ApiDependencies.invoker.services.images.update(image_name, image_changes)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=400, detail="Failed to update image")
 
 
@@ -128,7 +130,7 @@ async def get_image_dto(
 
     try:
         return ApiDependencies.invoker.services.images.get_dto(image_name)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404)
 
 
@@ -144,7 +146,7 @@ async def get_image_metadata(
 
     try:
         return ApiDependencies.invoker.services.images.get_metadata(image_name)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404)
 
 
@@ -180,7 +182,7 @@ async def get_image_full(
         )
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
         return response
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404)
 
 
@@ -209,7 +211,7 @@ async def get_image_thumbnail(
         response = FileResponse(path, media_type="image/webp", content_disposition_type="inline")
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
         return response
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404)
 
 
@@ -231,7 +233,7 @@ async def get_image_urls(
             image_url=image_url,
             thumbnail_url=thumbnail_url,
         )
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=404)
 
 
@@ -279,63 +281,8 @@ async def delete_images_from_list(
             try:
                 ApiDependencies.invoker.services.images.delete(image_name)
                 deleted_images.append(image_name)
-            except Exception:
+            except:
                 pass
         return DeleteImagesFromListResult(deleted_images=deleted_images)
-    except Exception:
+    except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to delete images")
-
-
-class ImagesUpdatedFromListResult(BaseModel):
-    updated_image_names: list[str] = Field(description="The image names that were updated")
-
-
-@images_router.post("/star", operation_id="star_images_in_list", response_model=ImagesUpdatedFromListResult)
-async def star_images_in_list(
-    image_names: list[str] = Body(description="The list of names of images to star", embed=True),
-) -> ImagesUpdatedFromListResult:
-    try:
-        updated_image_names: list[str] = []
-        for image_name in image_names:
-            try:
-                ApiDependencies.invoker.services.images.update(image_name, changes=ImageRecordChanges(starred=True))
-                updated_image_names.append(image_name)
-            except Exception:
-                pass
-        return ImagesUpdatedFromListResult(updated_image_names=updated_image_names)
-    except Exception:
-        raise HTTPException(status_code=500, detail="Failed to star images")
-
-
-@images_router.post("/unstar", operation_id="unstar_images_in_list", response_model=ImagesUpdatedFromListResult)
-async def unstar_images_in_list(
-    image_names: list[str] = Body(description="The list of names of images to unstar", embed=True),
-) -> ImagesUpdatedFromListResult:
-    try:
-        updated_image_names: list[str] = []
-        for image_name in image_names:
-            try:
-                ApiDependencies.invoker.services.images.update(image_name, changes=ImageRecordChanges(starred=False))
-                updated_image_names.append(image_name)
-            except Exception:
-                pass
-        return ImagesUpdatedFromListResult(updated_image_names=updated_image_names)
-    except Exception:
-        raise HTTPException(status_code=500, detail="Failed to unstar images")
-
-
-class ImagesDownloaded(BaseModel):
-    response: Optional[str] = Field(
-        description="If defined, the message to display to the user when images begin downloading"
-    )
-
-
-@images_router.post("/download", operation_id="download_images_from_list", response_model=ImagesDownloaded)
-async def download_images_from_list(
-    image_names: list[str] = Body(description="The list of names of images to download", embed=True),
-    board_id: Optional[str] = Body(
-        default=None, description="The board from which image should be downloaded from", embed=True
-    ),
-) -> ImagesDownloaded:
-    # return ImagesDownloaded(response="Your images are downloading")
-    raise HTTPException(status_code=501, detail="Endpoint is not yet implemented")

invokeai/app/api/routers/models.py

@@ -2,7 +2,7 @@
 
 
 import pathlib
-from typing import List, Literal, Optional, Union
+from typing import Literal, List, Optional, Union
 
 from fastapi import Body, Path, Query, Response
 from fastapi.routing import APIRouter
@@ -10,13 +10,13 @@ from pydantic import BaseModel, parse_obj_as
 from starlette.exceptions import HTTPException
 
 from invokeai.backend import BaseModelType, ModelType
-from invokeai.backend.model_management import MergeInterpolationMethod
 from invokeai.backend.model_management.models import (
     OPENAPI_MODEL_CONFIGS,
-    InvalidModelException,
-    ModelNotFoundException,
     SchedulerPredictionType,
+    ModelNotFoundException,
+    InvalidModelException,
 )
+from invokeai.backend.model_management import MergeInterpolationMethod
 
 from ..dependencies import ApiDependencies
 
@@ -105,7 +105,7 @@ async def update_model(
                 info.path = new_info.get("path")
 
         # replace empty string values with None/null to avoid phenomenon of vae: ''
-        info_dict = info.dict()
+        info_dict = info.model_dump()
         info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
 
         ApiDependencies.invoker.services.model_manager.update_model(
@@ -146,8 +146,7 @@ async def update_model(
 async def import_model(
     location: str = Body(description="A model path, repo_id or URL to import"),
     prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
-        default=None,
+        description="Prediction type for SDv2 checkpoint files", default="v_prediction"
     ),
 ) -> ImportModelResponse:
     """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
@@ -204,7 +203,7 @@ async def add_model(
 
     try:
         ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name, info.base_model, info.model_type, model_attributes=info.dict()
+            info.model_name, info.base_model, info.model_type, model_attributes=info.model_dump()
         )
         logger.info(f"Successfully added {info.model_name}")
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@@ -349,7 +348,7 @@ async def sync_to_config() -> bool:
 )
 async def merge_models(
     base_model: BaseModelType = Path(description="Base model"),
-    model_names: List[str] = Body(description="model name", min_items=2, max_items=3),
+    model_names: List[str] = Body(description="model name", min_length=2, max_length=3),
     merged_model_name: Optional[str] = Body(description="Name of destination model"),
     alpha: Optional[float] = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
     interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),

invokeai/app/api/routers/session_queue.py

@@ -1,247 +0,0 @@
-from typing import Optional
-
-from fastapi import Body, Path, Query
-from fastapi.routing import APIRouter
-from pydantic import BaseModel
-
-from invokeai.app.services.session_processor.session_processor_common import SessionProcessorStatus
-from invokeai.app.services.session_queue.session_queue_common import (
-    QUEUE_ITEM_STATUS,
-    Batch,
-    BatchStatus,
-    CancelByBatchIDsResult,
-    ClearResult,
-    EnqueueBatchResult,
-    EnqueueGraphResult,
-    PruneResult,
-    SessionQueueItem,
-    SessionQueueItemDTO,
-    SessionQueueStatus,
-)
-from invokeai.app.services.shared.models import CursorPaginatedResults
-
-from ...services.graph import Graph
-from ..dependencies import ApiDependencies
-
-session_queue_router = APIRouter(prefix="/v1/queue", tags=["queue"])
-
-
-class SessionQueueAndProcessorStatus(BaseModel):
-    """The overall status of session queue and processor"""
-
-    queue: SessionQueueStatus
-    processor: SessionProcessorStatus
-
-
-@session_queue_router.post(
-    "/{queue_id}/enqueue_graph",
-    operation_id="enqueue_graph",
-    responses={
-        201: {"model": EnqueueGraphResult},
-    },
-)
-async def enqueue_graph(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    graph: Graph = Body(description="The graph to enqueue"),
-    prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
-) -> EnqueueGraphResult:
-    """Enqueues a graph for single execution."""
-
-    return ApiDependencies.invoker.services.session_queue.enqueue_graph(queue_id=queue_id, graph=graph, prepend=prepend)
-
-
-@session_queue_router.post(
-    "/{queue_id}/enqueue_batch",
-    operation_id="enqueue_batch",
-    responses={
-        201: {"model": EnqueueBatchResult},
-    },
-)
-async def enqueue_batch(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    batch: Batch = Body(description="Batch to process"),
-    prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
-) -> EnqueueBatchResult:
-    """Processes a batch and enqueues the output graphs for execution."""
-
-    return ApiDependencies.invoker.services.session_queue.enqueue_batch(queue_id=queue_id, batch=batch, prepend=prepend)
-
-
-@session_queue_router.get(
-    "/{queue_id}/list",
-    operation_id="list_queue_items",
-    responses={
-        200: {"model": CursorPaginatedResults[SessionQueueItemDTO]},
-    },
-)
-async def list_queue_items(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    limit: int = Query(default=50, description="The number of items to fetch"),
-    status: Optional[QUEUE_ITEM_STATUS] = Query(default=None, description="The status of items to fetch"),
-    cursor: Optional[int] = Query(default=None, description="The pagination cursor"),
-    priority: int = Query(default=0, description="The pagination cursor priority"),
-) -> CursorPaginatedResults[SessionQueueItemDTO]:
-    """Gets all queue items (without graphs)"""
-
-    return ApiDependencies.invoker.services.session_queue.list_queue_items(
-        queue_id=queue_id, limit=limit, status=status, cursor=cursor, priority=priority
-    )
-
-
-@session_queue_router.put(
-    "/{queue_id}/processor/resume",
-    operation_id="resume",
-    responses={200: {"model": SessionProcessorStatus}},
-)
-async def resume(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> SessionProcessorStatus:
-    """Resumes session processor"""
-    return ApiDependencies.invoker.services.session_processor.resume()
-
-
-@session_queue_router.put(
-    "/{queue_id}/processor/pause",
-    operation_id="pause",
-    responses={200: {"model": SessionProcessorStatus}},
-)
-async def Pause(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> SessionProcessorStatus:
-    """Pauses session processor"""
-    return ApiDependencies.invoker.services.session_processor.pause()
-
-
-@session_queue_router.put(
-    "/{queue_id}/cancel_by_batch_ids",
-    operation_id="cancel_by_batch_ids",
-    responses={200: {"model": CancelByBatchIDsResult}},
-)
-async def cancel_by_batch_ids(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    batch_ids: list[str] = Body(description="The list of batch_ids to cancel all queue items for", embed=True),
-) -> CancelByBatchIDsResult:
-    """Immediately cancels all queue items from the given batch ids"""
-    return ApiDependencies.invoker.services.session_queue.cancel_by_batch_ids(queue_id=queue_id, batch_ids=batch_ids)
-
-
-@session_queue_router.put(
-    "/{queue_id}/clear",
-    operation_id="clear",
-    responses={
-        200: {"model": ClearResult},
-    },
-)
-async def clear(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> ClearResult:
-    """Clears the queue entirely, immediately canceling the currently-executing session"""
-    queue_item = ApiDependencies.invoker.services.session_queue.get_current(queue_id)
-    if queue_item is not None:
-        ApiDependencies.invoker.services.session_queue.cancel_queue_item(queue_item.item_id)
-    clear_result = ApiDependencies.invoker.services.session_queue.clear(queue_id)
-    return clear_result
-
-
-@session_queue_router.put(
-    "/{queue_id}/prune",
-    operation_id="prune",
-    responses={
-        200: {"model": PruneResult},
-    },
-)
-async def prune(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> PruneResult:
-    """Prunes all completed or errored queue items"""
-    return ApiDependencies.invoker.services.session_queue.prune(queue_id)
-
-
-@session_queue_router.get(
-    "/{queue_id}/current",
-    operation_id="get_current_queue_item",
-    responses={
-        200: {"model": Optional[SessionQueueItem]},
-    },
-)
-async def get_current_queue_item(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> Optional[SessionQueueItem]:
-    """Gets the currently execution queue item"""
-    return ApiDependencies.invoker.services.session_queue.get_current(queue_id)
-
-
-@session_queue_router.get(
-    "/{queue_id}/next",
-    operation_id="get_next_queue_item",
-    responses={
-        200: {"model": Optional[SessionQueueItem]},
-    },
-)
-async def get_next_queue_item(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> Optional[SessionQueueItem]:
-    """Gets the next queue item, without executing it"""
-    return ApiDependencies.invoker.services.session_queue.get_next(queue_id)
-
-
-@session_queue_router.get(
-    "/{queue_id}/status",
-    operation_id="get_queue_status",
-    responses={
-        200: {"model": SessionQueueAndProcessorStatus},
-    },
-)
-async def get_queue_status(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-) -> SessionQueueAndProcessorStatus:
-    """Gets the status of the session queue"""
-    queue = ApiDependencies.invoker.services.session_queue.get_queue_status(queue_id)
-    processor = ApiDependencies.invoker.services.session_processor.get_status()
-    return SessionQueueAndProcessorStatus(queue=queue, processor=processor)
-
-
-@session_queue_router.get(
-    "/{queue_id}/b/{batch_id}/status",
-    operation_id="get_batch_status",
-    responses={
-        200: {"model": BatchStatus},
-    },
-)
-async def get_batch_status(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    batch_id: str = Path(description="The batch to get the status of"),
-) -> BatchStatus:
-    """Gets the status of the session queue"""
-    return ApiDependencies.invoker.services.session_queue.get_batch_status(queue_id=queue_id, batch_id=batch_id)
-
-
-@session_queue_router.get(
-    "/{queue_id}/i/{item_id}",
-    operation_id="get_queue_item",
-    responses={
-        200: {"model": SessionQueueItem},
-    },
-)
-async def get_queue_item(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    item_id: int = Path(description="The queue item to get"),
-) -> SessionQueueItem:
-    """Gets a queue item"""
-    return ApiDependencies.invoker.services.session_queue.get_queue_item(item_id)
-
-
-@session_queue_router.put(
-    "/{queue_id}/i/{item_id}/cancel",
-    operation_id="cancel_queue_item",
-    responses={
-        200: {"model": SessionQueueItem},
-    },
-)
-async def cancel_queue_item(
-    queue_id: str = Path(description="The queue id to perform this operation on"),
-    item_id: int = Path(description="The queue item to cancel"),
-) -> SessionQueueItem:
-    """Deletes a queue item"""
-
-    return ApiDependencies.invoker.services.session_queue.cancel_queue_item(item_id)

invokeai/app/api/routers/sessions.py

@@ -1,15 +1,20 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Annotated, Optional, Union
+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
 
-# Importing * is bad karma but needed here for node detection
-from ...invocations import *  # noqa: F401 F403
+from ...invocations import *
 from ...invocations.baseinvocation import BaseInvocation
-from ...services.graph import Edge, EdgeConnection, Graph, GraphExecutionState, NodeAlreadyExecutedError
+from ...services.graph import (
+    Edge,
+    EdgeConnection,
+    Graph,
+    GraphExecutionState,
+    NodeAlreadyExecutedError,
+)
 from ...services.item_storage import PaginatedResults
 from ..dependencies import ApiDependencies
 
@@ -23,14 +28,12 @@ session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
         200: {"model": GraphExecutionState},
         400: {"description": "Invalid json"},
     },
-    deprecated=True,
 )
 async def create_session(
-    queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
-    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
+    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with")
 ) -> GraphExecutionState:
     """Creates a new session, optionally initializing it with an invocation graph"""
-    session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
+    session = ApiDependencies.invoker.create_execution_state(graph)
     return session
 
 
@@ -38,7 +41,6 @@ async def create_session(
     "/",
     operation_id="list_sessions",
     responses={200: {"model": PaginatedResults[GraphExecutionState]}},
-    deprecated=True,
 )
 async def list_sessions(
     page: int = Query(default=0, description="The page of results to get"),
@@ -60,7 +62,6 @@ async def list_sessions(
         200: {"model": GraphExecutionState},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def get_session(
     session_id: str = Path(description="The id of the session to get"),
@@ -81,7 +82,6 @@ async def get_session(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def add_node(
     session_id: str = Path(description="The id of the session"),
@@ -114,7 +114,6 @@ async def add_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def update_node(
     session_id: str = Path(description="The id of the session"),
@@ -148,7 +147,6 @@ async def update_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def delete_node(
     session_id: str = Path(description="The id of the session"),
@@ -179,7 +177,6 @@ async def delete_node(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def add_edge(
     session_id: str = Path(description="The id of the session"),
@@ -211,7 +208,6 @@ async def add_edge(
         400: {"description": "Invalid node or link"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def delete_edge(
     session_id: str = Path(description="The id of the session"),
@@ -250,10 +246,8 @@ async def delete_edge(
         400: {"description": "The session has no invocations ready to invoke"},
         404: {"description": "Session not found"},
     },
-    deprecated=True,
 )
 async def invoke_session(
-    queue_id: str = Query(description="The id of the queue to associate the session with"),
     session_id: str = Path(description="The id of the session to invoke"),
     all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
 ) -> Response:
@@ -265,7 +259,7 @@ async def invoke_session(
     if session.is_complete():
         raise HTTPException(status_code=400)
 
-    ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
+    ApiDependencies.invoker.invoke(session, invoke_all=all)
     return Response(status_code=202)
 
 
@@ -273,7 +267,6 @@ async def invoke_session(
     "/{session_id}/invoke",
     operation_id="cancel_session_invoke",
     responses={202: {"description": "The invocation is canceled"}},
-    deprecated=True,
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),

invokeai/app/api/routers/utilities.py

@@ -1,41 +0,0 @@
-from typing import Optional
-
-from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
-from fastapi import Body
-from fastapi.routing import APIRouter
-from pydantic import BaseModel
-from pyparsing import ParseException
-
-utilities_router = APIRouter(prefix="/v1/utilities", tags=["utilities"])
-
-
-class DynamicPromptsResponse(BaseModel):
-    prompts: list[str]
-    error: Optional[str] = None
-
-
-@utilities_router.post(
-    "/dynamicprompts",
-    operation_id="parse_dynamicprompts",
-    responses={
-        200: {"model": DynamicPromptsResponse},
-    },
-)
-async def parse_dynamicprompts(
-    prompt: str = Body(description="The prompt to parse with dynamicprompts"),
-    max_prompts: int = Body(default=1000, description="The max number of prompts to generate"),
-    combinatorial: bool = Body(default=True, description="Whether to use the combinatorial generator"),
-) -> DynamicPromptsResponse:
-    """Creates a batch process"""
-    try:
-        error: Optional[str] = None
-        if combinatorial:
-            generator = CombinatorialPromptGenerator()
-            prompts = generator.generate(prompt, max_prompts=max_prompts)
-        else:
-            generator = RandomPromptGenerator()
-            prompts = generator.generate(prompt, num_images=max_prompts)
-    except ParseException as e:
-        prompts = [prompt]
-        error = str(e)
-    return DynamicPromptsResponse(prompts=prompts if prompts else [""], error=error)

invokeai/app/api/sockets.py

@@ -3,35 +3,34 @@
 from fastapi import FastAPI
 from fastapi_events.handlers.local import local_handler
 from fastapi_events.typing import Event
-from socketio import ASGIApp, AsyncServer
+from fastapi_socketio import SocketManager
 
 from ..services.events import EventServiceBase
 
 
 class SocketIO:
-    __sio: AsyncServer
-    __app: ASGIApp
+    __sio: SocketManager
 
     def __init__(self, app: FastAPI):
-        self.__sio = AsyncServer(async_mode="asgi", cors_allowed_origins="*")
-        self.__app = ASGIApp(socketio_server=self.__sio, socketio_path="socket.io")
-        app.mount("/ws", self.__app)
+        self.__sio = SocketManager(app=app)
+        self.__sio.on("subscribe", handler=self._handle_sub)
+        self.__sio.on("unsubscribe", handler=self._handle_unsub)
 
-        self.__sio.on("subscribe_queue", handler=self._handle_sub_queue)
-        self.__sio.on("unsubscribe_queue", handler=self._handle_unsub_queue)
-        local_handler.register(event_name=EventServiceBase.queue_event, _func=self._handle_queue_event)
+        local_handler.register(event_name=EventServiceBase.session_event, _func=self._handle_session_event)
 
-    async def _handle_queue_event(self, event: 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"]["queue_id"],
+            room=event[1]["data"]["graph_execution_state_id"],
         )
 
-    async def _handle_sub_queue(self, sid, data, *args, **kwargs):
-        if "queue_id" in data:
-            self.__sio.enter_room(sid, data["queue_id"])
+    async def _handle_sub(self, sid, data, *args, **kwargs):
+        if "session" in data:
+            self.__sio.enter_room(sid, data["session"])
 
-    async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
-        if "queue_id" in data:
-            self.__sio.enter_room(sid, data["queue_id"])
+        # @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

@@ -1,48 +1,51 @@
+# Copyright (c) 2022-2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+import asyncio
+import sys
+from inspect import signature
+
+import logging
+import uvicorn
+import socket
+
+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 pathlib import Path
+#from pydantic.schema import schema
+
+# This should come early so that modules can log their initialization properly
 from .services.config import InvokeAIAppConfig
-
-# parse_args() must be called before any other imports. if it is not called first, consumers of the config
-# which are imported/used before parse_args() is called will get the default config values instead of the
-# values from the command line or config file.
-app_config = InvokeAIAppConfig.get_config()
-app_config.parse_args()
-
-if True:  # hack to make flake8 happy with imports coming after setting up the config
-    import asyncio
-    import mimetypes
-    import socket
-    from inspect import signature
-    from pathlib import Path
-
-    import torch
-    import uvicorn
-    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
-
-    # noinspection PyUnresolvedReferences
-    import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
-    import invokeai.frontend.web as web_dir
-    from invokeai.version.invokeai_version import __version__
-
-    from ..backend.util.logging import InvokeAILogger
-    from .api.dependencies import ApiDependencies
-    from .api.routers import app_info, board_images, boards, images, models, session_queue, sessions, utilities
-    from .api.sockets import SocketIO
-    from .invocations.baseinvocation import BaseInvocation, UIConfigBase, _InputField, _OutputField
-
-    if torch.backends.mps.is_available():
-        # noinspection PyUnresolvedReferences
-        import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
-
+from ..backend.util.logging import InvokeAILogger
 
 app_config = InvokeAIAppConfig.get_config()
 app_config.parse_args()
-logger = InvokeAILogger.get_logger(config=app_config)
+logger = InvokeAILogger.getLogger(config=app_config)
+from invokeai.version.invokeai_version import __version__
+
+# we call this early so that the message appears before
+# other invokeai initialization messages
+if app_config.version:
+    print(f"InvokeAI version {__version__}")
+    sys.exit(0)
+
+import invokeai.frontend.web as web_dir
+import mimetypes
+
+from .api.dependencies import ApiDependencies
+from .api.routers import sessions, models, images, boards, board_images, app_info
+from .api.sockets import SocketIO
+from .invocations.baseinvocation import BaseInvocation
+
+
+import torch
+import invokeai.backend.util.hotfixes
+
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
 
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
@@ -92,8 +95,6 @@ async def shutdown_event():
 
 app.include_router(sessions.session_router, prefix="/api")
 
-app.include_router(utilities.utilities_router, prefix="/api")
-
 app.include_router(models.models_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
@@ -104,8 +105,6 @@ app.include_router(board_images.board_images_router, prefix="/api")
 
 app.include_router(app_info.app_router, prefix="/api")
 
-app.include_router(session_queue.session_queue_router, prefix="/api")
-
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -127,19 +126,13 @@ def custom_openapi():
         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():
-        output_schema["class"] = "output"
-        openapi_schema["components"]["schemas"][schema_key] = output_schema
+    # 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 Node Editor UI helper schemas
-    ui_config_schemas = schema([UIConfigBase, _InputField, _OutputField], ref_prefix="#/components/schemas/")
-    for schema_key, ui_config_schema in ui_config_schemas["definitions"].items():
-        openapi_schema["components"]["schemas"][schema_key] = ui_config_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:
@@ -148,8 +141,8 @@ def custom_openapi():
         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
-        invoker_schema["class"] = "invocation"
 
     from invokeai.backend.model_management.models import get_model_config_enums
 
@@ -215,17 +208,6 @@ def invoke_api():
 
     check_invokeai_root(app_config)  # note, may exit with an exception if root not set up
 
-    if app_config.dev_reload:
-        try:
-            import jurigged
-        except ImportError as e:
-            logger.error(
-                'Can\'t start `--dev_reload` because jurigged is not found; `pip install -e ".[dev]"` to include development dependencies.',
-                exc_info=e,
-            )
-        else:
-            jurigged.watch(logger=InvokeAILogger.get_logger(name="jurigged").info)
-
     port = find_port(app_config.port)
     if port != app_config.port:
         logger.warn(f"Port {app_config.port} in use, using port {port}")
@@ -243,16 +225,13 @@ def invoke_api():
 
     # replace uvicorn's loggers with InvokeAI's for consistent appearance
     for logname in ["uvicorn.access", "uvicorn"]:
-        log = InvokeAILogger.get_logger(logname)
-        log.handlers.clear()
+        l = logging.getLogger(logname)
+        l.handlers.clear()
         for ch in logger.handlers:
-            log.addHandler(ch)
+            l.addHandler(ch)
 
     loop.run_until_complete(server.serve())
 
 
 if __name__ == "__main__":
-    if app_config.version:
-        print(f"InvokeAI version {__version__}")
-    else:
-        invoke_api()
+    invoke_api()

invokeai/app/cli/commands.py

@@ -1,18 +1,16 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-import argparse
 from abc import ABC, abstractmethod
+import argparse
 from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
-
-import matplotlib.pyplot as plt
-import networkx as nx
 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 Edge, GraphExecutionState, LibraryGraph
+from ..services.graph import GraphExecutionState, LibraryGraph, Edge
 from ..services.invoker import Invoker
 
 
@@ -69,7 +67,7 @@ def add_parsers(
             add_arguments(command_parser)
 
         # Convert all fields to arguments
-        fields = command.__fields__  # type: ignore
+        fields = command.model_fields  # type: ignore
         for name, field in fields.items():
             if name in exclude_fields:
                 continue
@@ -89,7 +87,7 @@ def add_graph_parsers(
         # 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]
+            field = node.model_fields[exposed_input.field]
             default_override = getattr(node, exposed_input.field)
             add_field_argument(command_parser, exposed_input.alias, field, default_override)
 
@@ -196,7 +194,7 @@ def get_graph_execution_history(
 
 
 def get_invocation_command(invocation) -> str:
-    fields = invocation.__fields__.items()
+    fields = invocation.model_fields.items()
     type_hints = get_type_hints(type(invocation))
     command = [invocation.type]
     for name, field in fields:

invokeai/app/cli/completer.py

@@ -6,15 +6,15 @@ completer object.
 import atexit
 import readline
 import shlex
+
 from pathlib import Path
-from typing import Dict, List, Literal, get_args, get_origin, get_type_hints
+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 ..services.invocation_services import InvocationServices
 from .commands import BaseCommand
+from ..services.invocation_services import InvocationServices
 
 # singleton object, class variable
 completer = None
@@ -145,10 +145,10 @@ def set_autocompleter(services: InvocationServices) -> 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 AttributeError:
-        # pyreadline3 does not have a set_auto_history() method
+    except:
         pass
     readline.set_pre_input_hook(completer._pre_input_hook)
     readline.set_completer_delims(" ")

invokeai/app/cli_app.py

@@ -1,67 +1,71 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
+import argparse
+import re
+import shlex
+import sys
+import time
+from typing import Union, get_type_hints, Optional
 
+from pydantic import BaseModel, ValidationError
+from pydantic.fields import Field
+
+# This should come early so that the logger can pick up its configuration options
 from .services.config import InvokeAIAppConfig
-
-# parse_args() must be called before any other imports. if it is not called first, consumers of the config
-# which are imported/used before parse_args() is called will get the default config values instead of the
-# values from the command line or config file.
-
-if True:  # hack to make flake8 happy with imports coming after setting up the config
-    import argparse
-    import re
-    import shlex
-    import sqlite3
-    import sys
-    import time
-    from typing import Optional, Union, get_type_hints
-
-    import torch
-    from pydantic import BaseModel, ValidationError
-    from pydantic.fields import Field
-
-    import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
-    from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
-    from invokeai.app.services.board_images import BoardImagesService, BoardImagesServiceDependencies
-    from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
-    from invokeai.app.services.boards import BoardService, BoardServiceDependencies
-    from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
-    from invokeai.app.services.images import ImageService, ImageServiceDependencies
-    from invokeai.app.services.invocation_stats import InvocationStatsService
-    from invokeai.app.services.resource_name import SimpleNameService
-    from invokeai.app.services.urls import LocalUrlService
-    from invokeai.backend.util.logging import InvokeAILogger
-    from invokeai.version.invokeai_version import __version__
-
-    from .cli.commands import BaseCommand, CliContext, ExitCli, SortedHelpFormatter, add_graph_parsers, add_parsers
-    from .cli.completer import set_autocompleter
-    from .invocations.baseinvocation import BaseInvocation
-    from .services.default_graphs import create_system_graphs, default_text_to_image_graph_id
-    from .services.events import EventServiceBase
-    from .services.graph import (
-        Edge,
-        EdgeConnection,
-        GraphExecutionState,
-        GraphInvocation,
-        LibraryGraph,
-        are_connection_types_compatible,
-    )
-    from .services.image_file_storage import DiskImageFileStorage
-    from .services.invocation_queue import MemoryInvocationQueue
-    from .services.invocation_services import InvocationServices
-    from .services.invoker import Invoker
-    from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-    from .services.model_manager_service import ModelManagerService
-    from .services.processor import DefaultInvocationProcessor
-    from .services.sqlite import SqliteItemStorage
-
-    if torch.backends.mps.is_available():
-        import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
+from invokeai.backend.util.logging import InvokeAILogger
 
 config = InvokeAIAppConfig.get_config()
 config.parse_args()
-logger = InvokeAILogger().get_logger(config=config)
+logger = InvokeAILogger().getLogger(config=config)
+from invokeai.version.invokeai_version import __version__
+
+# we call this early so that the message appears before other invokeai initialization messages
+if config.version:
+    print(f"InvokeAI version {__version__}")
+    sys.exit(0)
+
+from invokeai.app.services.board_image_record_storage import (
+    SqliteBoardImageRecordStorage,
+)
+from invokeai.app.services.board_images import (
+    BoardImagesService,
+    BoardImagesServiceDependencies,
+)
+from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
+from invokeai.app.services.boards import BoardService, BoardServiceDependencies
+from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
+from invokeai.app.services.images import ImageService, ImageServiceDependencies
+from invokeai.app.services.resource_name import SimpleNameService
+from invokeai.app.services.urls import LocalUrlService
+from invokeai.app.services.invocation_stats import InvocationStatsService
+from .services.default_graphs import default_text_to_image_graph_id, create_system_graphs
+from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from .cli.commands import BaseCommand, CliContext, ExitCli, SortedHelpFormatter, add_graph_parsers, add_parsers
+from .cli.completer import set_autocompleter
+from .invocations.baseinvocation import BaseInvocation
+from .services.events import EventServiceBase
+from .services.graph import (
+    Edge,
+    EdgeConnection,
+    GraphExecutionState,
+    GraphInvocation,
+    LibraryGraph,
+    are_connection_types_compatible,
+)
+from .services.image_file_storage import DiskImageFileStorage
+from .services.invocation_queue import MemoryInvocationQueue
+from .services.invocation_services import InvocationServices
+from .services.invoker import Invoker
+from .services.model_manager_service import ModelManagerService
+from .services.processor import DefaultInvocationProcessor
+from .services.sqlite import SqliteItemStorage
+
+import torch
+import invokeai.backend.util.hotfixes
+
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes
 
 
 class CliCommand(BaseModel):
@@ -251,18 +255,19 @@ def invoke_cli():
         db_location = config.db_path
         db_location.parent.mkdir(parents=True, exist_ok=True)
 
-    db_conn = sqlite3.connect(db_location, check_same_thread=False)  # TODO: figure out a better threading solution
     logger.info(f'InvokeAI database location is "{db_location}"')
 
-    graph_execution_manager = SqliteItemStorage[GraphExecutionState](conn=db_conn, table_name="graph_executions")
+    graph_execution_manager = SqliteItemStorage[GraphExecutionState](
+        filename=db_location, table_name="graph_executions"
+    )
 
     urls = LocalUrlService()
-    image_record_storage = SqliteImageRecordStorage(conn=db_conn)
+    image_record_storage = SqliteImageRecordStorage(db_location)
     image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
     names = SimpleNameService()
 
-    board_record_storage = SqliteBoardRecordStorage(conn=db_conn)
-    board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn)
+    board_record_storage = SqliteBoardRecordStorage(db_location)
+    board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
 
     boards = BoardService(
         services=BoardServiceDependencies(
@@ -304,13 +309,12 @@ def invoke_cli():
         boards=boards,
         board_images=board_images,
         queue=MemoryInvocationQueue(),
-        graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, table_name="graphs"),
+        graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
         graph_execution_manager=graph_execution_manager,
         processor=DefaultInvocationProcessor(),
         performance_statistics=InvocationStatsService(graph_execution_manager),
         logger=logger,
         configuration=config,
-        invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
     )
 
     system_graphs = create_system_graphs(services.graph_library)
@@ -478,7 +482,4 @@ def invoke_cli():
 
 
 if __name__ == "__main__":
-    if config.version:
-        print(f"InvokeAI version {__version__}")
-    else:
-        invoke_cli()
+    invoke_cli()

invokeai/app/invocations/baseinvocation.py

@@ -2,460 +2,30 @@
 
 from __future__ import annotations
 
-import json
-import re
 from abc import ABC, abstractmethod
-from enum import Enum
 from inspect import signature
-from typing import (
-    TYPE_CHECKING,
-    AbstractSet,
-    Any,
-    Callable,
-    ClassVar,
-    Literal,
-    Mapping,
-    Optional,
-    Type,
-    TypeVar,
-    Union,
-    get_args,
-    get_type_hints,
-)
+from typing import TYPE_CHECKING, Dict, List, Literal, TypedDict, get_args, get_type_hints
 
-import semver
-from pydantic import BaseModel, Field, validator
-from pydantic.fields import ModelField, Undefined
-from pydantic.typing import NoArgAnyCallable
-
-from invokeai.app.services.config.invokeai_config import InvokeAIAppConfig
+from pydantic import BaseConfig, BaseModel, Field
 
 if TYPE_CHECKING:
     from ..services.invocation_services import InvocationServices
 
 
-class InvalidVersionError(ValueError):
-    pass
-
-
-class FieldDescriptions:
-    denoising_start = "When to start denoising, expressed a percentage of total steps"
-    denoising_end = "When to stop denoising, expressed a percentage of total steps"
-    cfg_scale = "Classifier-Free Guidance scale"
-    scheduler = "Scheduler to use during inference"
-    positive_cond = "Positive conditioning tensor"
-    negative_cond = "Negative conditioning tensor"
-    noise = "Noise tensor"
-    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
-    unet = "UNet (scheduler, LoRAs)"
-    vae = "VAE"
-    cond = "Conditioning tensor"
-    controlnet_model = "ControlNet model to load"
-    vae_model = "VAE model to load"
-    lora_model = "LoRA model to load"
-    main_model = "Main model (UNet, VAE, CLIP) to load"
-    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
-    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
-    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
-    lora_weight = "The weight at which the LoRA is applied to each model"
-    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
-    raw_prompt = "Raw prompt text (no parsing)"
-    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
-    skipped_layers = "Number of layers to skip in text encoder"
-    seed = "Seed for random number generation"
-    steps = "Number of steps to run"
-    width = "Width of output (px)"
-    height = "Height of output (px)"
-    control = "ControlNet(s) to apply"
-    ip_adapter = "IP-Adapter to apply"
-    t2i_adapter = "T2I-Adapter(s) to apply"
-    denoised_latents = "Denoised latents tensor"
-    latents = "Latents tensor"
-    strength = "Strength of denoising (proportional to steps)"
-    core_metadata = "Optional core metadata to be written to image"
-    interp_mode = "Interpolation mode"
-    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
-    fp32 = "Whether or not to use full float32 precision"
-    precision = "Precision to use"
-    tiled = "Processing using overlapping tiles (reduce memory consumption)"
-    detect_res = "Pixel resolution for detection"
-    image_res = "Pixel resolution for output image"
-    safe_mode = "Whether or not to use safe mode"
-    scribble_mode = "Whether or not to use scribble mode"
-    scale_factor = "The factor by which to scale"
-    blend_alpha = (
-        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
-    )
-    num_1 = "The first number"
-    num_2 = "The second number"
-    mask = "The mask to use for the operation"
-    board = "The board to save the image to"
-    image = "The image to process"
-    tile_size = "Tile size"
-    inclusive_low = "The inclusive low value"
-    exclusive_high = "The exclusive high value"
-    decimal_places = "The number of decimal places to round to"
-
-
-class Input(str, Enum):
-    """
-    The type of input a field accepts.
-    - `Input.Direct`: The field must have its value provided directly, when the invocation and field \
-      are instantiated.
-    - `Input.Connection`: The field must have its value provided by a connection.
-    - `Input.Any`: The field may have its value provided either directly or by a connection.
-    """
-
-    Connection = "connection"
-    Direct = "direct"
-    Any = "any"
-
-
-class UIType(str, Enum):
-    """
-    Type hints for the UI.
-    If a field should be provided a data type that does not exactly match the python type of the field, \
-    use this to provide the type that should be used instead. See the node development docs for detail \
-    on adding a new field type, which involves client-side changes.
-    """
-
-    # region Primitives
-    Boolean = "boolean"
-    Color = "ColorField"
-    Conditioning = "ConditioningField"
-    Control = "ControlField"
-    Float = "float"
-    Image = "ImageField"
-    Integer = "integer"
-    Latents = "LatentsField"
-    String = "string"
-    # endregion
-
-    # region Collection Primitives
-    BooleanCollection = "BooleanCollection"
-    ColorCollection = "ColorCollection"
-    ConditioningCollection = "ConditioningCollection"
-    ControlCollection = "ControlCollection"
-    FloatCollection = "FloatCollection"
-    ImageCollection = "ImageCollection"
-    IntegerCollection = "IntegerCollection"
-    LatentsCollection = "LatentsCollection"
-    StringCollection = "StringCollection"
-    # endregion
-
-    # region Polymorphic Primitives
-    BooleanPolymorphic = "BooleanPolymorphic"
-    ColorPolymorphic = "ColorPolymorphic"
-    ConditioningPolymorphic = "ConditioningPolymorphic"
-    ControlPolymorphic = "ControlPolymorphic"
-    FloatPolymorphic = "FloatPolymorphic"
-    ImagePolymorphic = "ImagePolymorphic"
-    IntegerPolymorphic = "IntegerPolymorphic"
-    LatentsPolymorphic = "LatentsPolymorphic"
-    StringPolymorphic = "StringPolymorphic"
-    # endregion
-
-    # region Models
-    MainModel = "MainModelField"
-    SDXLMainModel = "SDXLMainModelField"
-    SDXLRefinerModel = "SDXLRefinerModelField"
-    ONNXModel = "ONNXModelField"
-    VaeModel = "VaeModelField"
-    LoRAModel = "LoRAModelField"
-    ControlNetModel = "ControlNetModelField"
-    IPAdapterModel = "IPAdapterModelField"
-    UNet = "UNetField"
-    Vae = "VaeField"
-    CLIP = "ClipField"
-    # endregion
-
-    # region Iterate/Collect
-    Collection = "Collection"
-    CollectionItem = "CollectionItem"
-    # endregion
-
-    # region Misc
-    Enum = "enum"
-    Scheduler = "Scheduler"
-    WorkflowField = "WorkflowField"
-    IsIntermediate = "IsIntermediate"
-    MetadataField = "MetadataField"
-    BoardField = "BoardField"
-    # endregion
-
-
-class UIComponent(str, Enum):
-    """
-    The type of UI component to use for a field, used to override the default components, which are \
-    inferred from the field type.
-    """
-
-    None_ = "none"
-    Textarea = "textarea"
-    Slider = "slider"
-
-
-class _InputField(BaseModel):
-    """
-    *DO NOT USE*
-    This helper class is used to tell the client about our custom field attributes via OpenAPI
-    schema generation, and Typescript type generation from that schema. It serves no functional
-    purpose in the backend.
-    """
-
-    input: Input
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_component: Optional[UIComponent]
-    ui_order: Optional[int]
-    ui_choice_labels: Optional[dict[str, str]]
-    item_default: Optional[Any]
-
-
-class _OutputField(BaseModel):
-    """
-    *DO NOT USE*
-    This helper class is used to tell the client about our custom field attributes via OpenAPI
-    schema generation, and Typescript type generation from that schema. It serves no functional
-    purpose in the backend.
-    """
-
-    ui_hidden: bool
-    ui_type: Optional[UIType]
-    ui_order: Optional[int]
-
-
-def InputField(
-    *args: Any,
-    default: Any = Undefined,
-    default_factory: Optional[NoArgAnyCallable] = None,
-    alias: Optional[str] = None,
-    title: Optional[str] = None,
-    description: Optional[str] = None,
-    exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    const: Optional[bool] = None,
-    gt: Optional[float] = None,
-    ge: Optional[float] = None,
-    lt: Optional[float] = None,
-    le: Optional[float] = None,
-    multiple_of: Optional[float] = None,
-    allow_inf_nan: Optional[bool] = None,
-    max_digits: Optional[int] = None,
-    decimal_places: Optional[int] = None,
-    min_items: Optional[int] = None,
-    max_items: Optional[int] = None,
-    unique_items: Optional[bool] = None,
-    min_length: Optional[int] = None,
-    max_length: Optional[int] = None,
-    allow_mutation: bool = True,
-    regex: Optional[str] = None,
-    discriminator: Optional[str] = None,
-    repr: bool = True,
-    input: Input = Input.Any,
-    ui_type: Optional[UIType] = None,
-    ui_component: Optional[UIComponent] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    ui_choice_labels: Optional[dict[str, str]] = None,
-    item_default: Optional[Any] = None,
-    **kwargs: Any,
-) -> Any:
-    """
-    Creates an input field for an invocation.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param Input input: [Input.Any] The kind of input this field requires. \
-      `Input.Direct` means a value must be provided on instantiation. \
-      `Input.Connection` means the value must be provided by a connection. \
-      `Input.Any` means either will do.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    :param UIComponent ui_component: [None] Optionally specifies a specific component to use in the UI. \
-      The UI will always render a suitable component, but sometimes you want something different than the default. \
-      For example, a `string` field will default to a single-line input, but you may want a multi-line textarea instead. \
-      For this case, you could provide `UIComponent.Textarea`.
-
-    : param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI.
-
-    : param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-
-    : param bool item_default: [None] Specifies the default item value, if this is a collection input. \
-      Ignored for non-collection fields..
-    """
-    return Field(
-        *args,
-        default=default,
-        default_factory=default_factory,
-        alias=alias,
-        title=title,
-        description=description,
-        exclude=exclude,
-        include=include,
-        const=const,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_items=min_items,
-        max_items=max_items,
-        unique_items=unique_items,
-        min_length=min_length,
-        max_length=max_length,
-        allow_mutation=allow_mutation,
-        regex=regex,
-        discriminator=discriminator,
-        repr=repr,
-        input=input,
-        ui_type=ui_type,
-        ui_component=ui_component,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        item_default=item_default,
-        ui_choice_labels=ui_choice_labels,
-        **kwargs,
-    )
-
-
-def OutputField(
-    *args: Any,
-    default: Any = Undefined,
-    default_factory: Optional[NoArgAnyCallable] = None,
-    alias: Optional[str] = None,
-    title: Optional[str] = None,
-    description: Optional[str] = None,
-    exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
-    const: Optional[bool] = None,
-    gt: Optional[float] = None,
-    ge: Optional[float] = None,
-    lt: Optional[float] = None,
-    le: Optional[float] = None,
-    multiple_of: Optional[float] = None,
-    allow_inf_nan: Optional[bool] = None,
-    max_digits: Optional[int] = None,
-    decimal_places: Optional[int] = None,
-    min_items: Optional[int] = None,
-    max_items: Optional[int] = None,
-    unique_items: Optional[bool] = None,
-    min_length: Optional[int] = None,
-    max_length: Optional[int] = None,
-    allow_mutation: bool = True,
-    regex: Optional[str] = None,
-    discriminator: Optional[str] = None,
-    repr: bool = True,
-    ui_type: Optional[UIType] = None,
-    ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
-    **kwargs: Any,
-) -> Any:
-    """
-    Creates an output field for an invocation output.
-
-    This is a wrapper for Pydantic's [Field](https://docs.pydantic.dev/1.10/usage/schema/#field-customization) \
-    that adds a few extra parameters to support graph execution and the node editor UI.
-
-    :param UIType ui_type: [None] Optionally provides an extra type hint for the UI. \
-      In some situations, the field's type is not enough to infer the correct UI type. \
-      For example, model selection fields should render a dropdown UI component to select a model. \
-      Internally, there is no difference between SD-1, SD-2 and SDXL model fields, they all use \
-      `MainModelField`. So to ensure the base-model-specific UI is rendered, you can use \
-      `UIType.SDXLMainModelField` to indicate that the field is an SDXL main model field.
-
-    : param bool ui_hidden: [False] Specifies whether or not this field should be hidden in the UI. \
-
-    : param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
-    """
-    return Field(
-        *args,
-        default=default,
-        default_factory=default_factory,
-        alias=alias,
-        title=title,
-        description=description,
-        exclude=exclude,
-        include=include,
-        const=const,
-        gt=gt,
-        ge=ge,
-        lt=lt,
-        le=le,
-        multiple_of=multiple_of,
-        allow_inf_nan=allow_inf_nan,
-        max_digits=max_digits,
-        decimal_places=decimal_places,
-        min_items=min_items,
-        max_items=max_items,
-        unique_items=unique_items,
-        min_length=min_length,
-        max_length=max_length,
-        allow_mutation=allow_mutation,
-        regex=regex,
-        discriminator=discriminator,
-        repr=repr,
-        ui_type=ui_type,
-        ui_hidden=ui_hidden,
-        ui_order=ui_order,
-        **kwargs,
-    )
-
-
-class UIConfigBase(BaseModel):
-    """
-    Provides additional node configuration to the UI.
-    This is used internally by the @invocation decorator logic. Do not use this directly.
-    """
-
-    tags: Optional[list[str]] = Field(default_factory=None, description="The node's tags")
-    title: Optional[str] = Field(default=None, description="The node's display name")
-    category: Optional[str] = Field(default=None, description="The node's category")
-    version: Optional[str] = Field(
-        default=None, description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".'
-    )
-
-
 class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
     services: InvocationServices
     graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: int
-    queue_batch_id: str
 
-    def __init__(
-        self,
-        services: InvocationServices,
-        queue_id: str,
-        queue_item_id: int,
-        queue_batch_id: str,
-        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
-        self.queue_id = queue_id
-        self.queue_item_id = queue_item_id
-        self.queue_batch_id = queue_batch_id
 
 
 class BaseInvocationOutput(BaseModel):
-    """
-    Base class for all invocation outputs.
+    """Base class for all invocation outputs"""
 
-    All invocation outputs must use the `@invocation_output` decorator to provide their unique type.
-    """
+    # All outputs must include a type name like this:
+    # type: Literal['your_output_name']
 
     @classmethod
     def get_all_subclasses_tuple(cls):
@@ -468,39 +38,17 @@ class BaseInvocationOutput(BaseModel):
             toprocess.extend(next_subclasses)
         return tuple(subclasses)
 
-    class Config:
-        @staticmethod
-        def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
-            if "required" not in schema or not isinstance(schema["required"], list):
-                schema["required"] = list()
-            schema["required"].extend(["type"])
-
-
-class RequiredConnectionException(Exception):
-    """Raised when an field which requires a connection did not receive a value."""
-
-    def __init__(self, node_id: str, field_name: str):
-        super().__init__(f"Node {node_id} missing connections for field {field_name}")
-
-
-class MissingInputException(Exception):
-    """Raised when an field which requires some input, but did not receive a value."""
-
-    def __init__(self, node_id: str, field_name: str):
-        super().__init__(f"Node {node_id} missing value or connection for field {field_name}")
-
 
 class BaseInvocation(ABC, BaseModel):
-    """
-    A node to process inputs and produce outputs.
+    """A node to process inputs and produce outputs.
     May use dependency injection in __init__ to receive providers.
-
-    All invocations must use the `@invocation` decorator to provide their unique type.
     """
 
+    # All invocations must include a type name like this:
+    # type: Literal['your_output_name']
+
     @classmethod
     def get_all_subclasses(cls):
-        app_config = InvokeAIAppConfig.get_config()
         subclasses = []
         toprocess = [cls]
         while len(toprocess) > 0:
@@ -508,23 +56,7 @@ class BaseInvocation(ABC, BaseModel):
             next_subclasses = next.__subclasses__()
             subclasses.extend(next_subclasses)
             toprocess.extend(next_subclasses)
-        allowed_invocations = []
-        for sc in subclasses:
-            is_in_allowlist = (
-                sc.__fields__.get("type").default in app_config.allow_nodes
-                if isinstance(app_config.allow_nodes, list)
-                else True
-            )
-
-            is_in_denylist = (
-                sc.__fields__.get("type").default in app_config.deny_nodes
-                if isinstance(app_config.deny_nodes, list)
-                else False
-            )
-
-            if is_in_allowlist and not is_in_denylist:
-                allowed_invocations.append(sc)
-        return allowed_invocations
+        return subclasses
 
     @classmethod
     def get_invocations(cls):
@@ -544,206 +76,70 @@ class BaseInvocation(ABC, BaseModel):
     def get_output_type(cls):
         return signature(cls.invoke).return_annotation
 
-    class Config:
-        validate_assignment = True
-        validate_all = True
-
-        @staticmethod
-        def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
-            uiconfig = getattr(model_class, "UIConfig", None)
-            if uiconfig and hasattr(uiconfig, "title"):
-                schema["title"] = uiconfig.title
-            if uiconfig and hasattr(uiconfig, "tags"):
-                schema["tags"] = uiconfig.tags
-            if uiconfig and hasattr(uiconfig, "category"):
-                schema["category"] = uiconfig.category
-            if uiconfig and hasattr(uiconfig, "version"):
-                schema["version"] = uiconfig.version
-            if "required" not in schema or not isinstance(schema["required"], list):
-                schema["required"] = list()
-            schema["required"].extend(["type", "id"])
-
     @abstractmethod
     def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
         """Invoke with provided context and return outputs."""
         pass
 
-    def __init__(self, **data):
-        # nodes may have required fields, that can accept input from connections
-        # on instantiation of the model, we need to exclude these from validation
-        restore = dict()
-        try:
-            field_names = list(self.__fields__.keys())
-            for field_name in field_names:
-                # if the field is required and may get its value from a connection, exclude it from validation
-                field = self.__fields__[field_name]
-                _input = field.field_info.extra.get("input", None)
-                if _input in [Input.Connection, Input.Any] and field.required:
-                    if field_name not in data:
-                        restore[field_name] = self.__fields__.pop(field_name)
-            # instantiate the node, which will validate the data
-            super().__init__(**data)
-        finally:
-            # restore the removed fields
-            for field_name, field in restore.items():
-                self.__fields__[field_name] = field
-
-    def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
-        for field_name, field in self.__fields__.items():
-            _input = field.field_info.extra.get("input", None)
-            if field.required and not hasattr(self, field_name):
-                if _input == Input.Connection:
-                    raise RequiredConnectionException(self.__fields__["type"].default, field_name)
-                elif _input == Input.Any:
-                    raise MissingInputException(self.__fields__["type"].default, field_name)
-
-        # skip node cache codepath if it's disabled
-        if context.services.configuration.node_cache_size == 0:
-            return self.invoke(context)
-
-        output: BaseInvocationOutput
-        if self.use_cache:
-            key = context.services.invocation_cache.create_key(self)
-            cached_value = context.services.invocation_cache.get(key)
-            if cached_value is None:
-                context.services.logger.debug(f'Invocation cache miss for type "{self.get_type()}": {self.id}')
-                output = self.invoke(context)
-                context.services.invocation_cache.save(key, output)
-                return output
-            else:
-                context.services.logger.debug(f'Invocation cache hit for type "{self.get_type()}": {self.id}')
-                return cached_value
-        else:
-            context.services.logger.debug(f'Skipping invocation cache for "{self.get_type()}": {self.id}')
-            return self.invoke(context)
-
-    def get_type(self) -> str:
-        return self.__fields__["type"].default
-
-    id: str = Field(
-        description="The id of this instance of an invocation. Must be unique among all instances of invocations."
-    )
-    is_intermediate: bool = InputField(
-        default=False, description="Whether or not this is an intermediate invocation.", ui_type=UIType.IsIntermediate
-    )
-    workflow: Optional[str] = InputField(
-        default=None,
-        description="The workflow to save with the image",
-        ui_type=UIType.WorkflowField,
-    )
-    use_cache: bool = InputField(default=True, description="Whether or not to use the cache")
-
-    @validator("workflow", pre=True)
-    def validate_workflow_is_json(cls, v):
-        if v is None:
-            return None
-        try:
-            json.loads(v)
-        except json.decoder.JSONDecodeError:
-            raise ValueError("Workflow must be valid JSON")
-        return v
-
-    UIConfig: ClassVar[Type[UIConfigBase]]
+    # fmt: off
+    id: str = Field(description="The id of this node. Must be unique among all nodes.")
+    is_intermediate: bool = Field(default=False, description="Whether or not this node is an intermediate node.")
+    # fmt: on
 
 
-GenericBaseInvocation = TypeVar("GenericBaseInvocation", bound=BaseInvocation)
+# 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",
+            "control",
+            "image_collection",
+            "vae_model",
+            "lora_model",
+        ],
+    ]
+    tags: List[str]
+    title: str
 
 
-def invocation(
-    invocation_type: str,
-    title: Optional[str] = None,
-    tags: Optional[list[str]] = None,
-    category: Optional[str] = None,
-    version: Optional[str] = None,
-    use_cache: Optional[bool] = True,
-) -> Callable[[Type[GenericBaseInvocation]], Type[GenericBaseInvocation]]:
-    """
-    Adds metadata to an invocation.
+class CustomisedSchemaExtra(TypedDict):
+    ui: UIConfig
 
-    :param str invocation_type: The type of the invocation. Must be unique among all invocations.
-    :param Optional[str] title: Adds a title to the invocation. Use if the auto-generated title isn't quite right. Defaults to None.
-    :param Optional[list[str]] tags: Adds tags to the invocation. Invocations may be searched for by their tags. Defaults to None.
-    :param Optional[str] category: Adds a category to the invocation. Used to group the invocations in the UI. Defaults to None.
-    :param Optional[str] version: Adds a version to the invocation. Must be a valid semver string. Defaults to None.
-    :param Optional[bool] use_cache: Whether or not to use the invocation cache. Defaults to True. The user may override this in the workflow editor.
+
+class InvocationConfig(BaseConfig):
+    """Customizes pydantic's BaseModel.Config class for use by Invocations.
+
+    Provide `json_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):
+      json_schema_extra = {
+          "ui": {
+              "tags": ["stable-diffusion", "image"],
+              "type_hints": {
+                  "initial_image": "image",
+              },
+          },
+      }
+    ```
     """
 
-    def wrapper(cls: Type[GenericBaseInvocation]) -> Type[GenericBaseInvocation]:
-        # Validate invocation types on creation of invocation classes
-        # TODO: ensure unique?
-        if re.compile(r"^\S+$").match(invocation_type) is None:
-            raise ValueError(f'"invocation_type" must consist of non-whitespace characters, got "{invocation_type}"')
-
-        # Add OpenAPI schema extras
-        uiconf_name = cls.__qualname__ + ".UIConfig"
-        if not hasattr(cls, "UIConfig") or cls.UIConfig.__qualname__ != uiconf_name:
-            cls.UIConfig = type(uiconf_name, (UIConfigBase,), dict())
-        if title is not None:
-            cls.UIConfig.title = title
-        if tags is not None:
-            cls.UIConfig.tags = tags
-        if category is not None:
-            cls.UIConfig.category = category
-        if version is not None:
-            try:
-                semver.Version.parse(version)
-            except ValueError as e:
-                raise InvalidVersionError(f'Invalid version string for node "{invocation_type}": "{version}"') from e
-            cls.UIConfig.version = version
-        if use_cache is not None:
-            cls.__fields__["use_cache"].default = use_cache
-
-        # Add the invocation type to the pydantic model of the invocation
-        invocation_type_annotation = Literal[invocation_type]  # type: ignore
-        invocation_type_field = ModelField.infer(
-            name="type",
-            value=invocation_type,
-            annotation=invocation_type_annotation,
-            class_validators=None,
-            config=cls.__config__,
-        )
-        cls.__fields__.update({"type": invocation_type_field})
-        # to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
-        if annotations := cls.__dict__.get("__annotations__", None):
-            annotations.update({"type": invocation_type_annotation})
-        return cls
-
-    return wrapper
-
-
-GenericBaseInvocationOutput = TypeVar("GenericBaseInvocationOutput", bound=BaseInvocationOutput)
-
-
-def invocation_output(
-    output_type: str,
-) -> Callable[[Type[GenericBaseInvocationOutput]], Type[GenericBaseInvocationOutput]]:
-    """
-    Adds metadata to an invocation output.
-
-    :param str output_type: The type of the invocation output. Must be unique among all invocation outputs.
-    """
-
-    def wrapper(cls: Type[GenericBaseInvocationOutput]) -> Type[GenericBaseInvocationOutput]:
-        # Validate output types on creation of invocation output classes
-        # TODO: ensure unique?
-        if re.compile(r"^\S+$").match(output_type) is None:
-            raise ValueError(f'"output_type" must consist of non-whitespace characters, got "{output_type}"')
-
-        # Add the output type to the pydantic model of the invocation output
-        output_type_annotation = Literal[output_type]  # type: ignore
-        output_type_field = ModelField.infer(
-            name="type",
-            value=output_type,
-            annotation=output_type_annotation,
-            class_validators=None,
-            config=cls.__config__,
-        )
-        cls.__fields__.update({"type": output_type_field})
-
-        # to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
-        if annotations := cls.__dict__.get("__annotations__", None):
-            annotations.update({"type": output_type_annotation})
-
-        return cls
-
-    return wrapper
+    json_schema_extra: CustomisedSchemaExtra

invokeai/app/invocations/collections.py

@@ -1,76 +1,137 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 
+from typing import Literal
 
 import numpy as np
-from pydantic import validator
+from pydantic import Field, field_field_validator
 
-from invokeai.app.invocations.primitives import IntegerCollectionOutput
+from invokeai.app.models.image import ImageField
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext, UIConfig
+
+
+class IntCollectionOutput(BaseInvocationOutput):
+    """A collection of integers"""
+
+    type: Literal["int_collection"] = "int_collection"
+
+    # Outputs
+    collection: list[int] = Field(default=[], description="The int collection")
+
+
+class FloatCollectionOutput(BaseInvocationOutput):
+    """A collection of floats"""
+
+    type: Literal["float_collection"] = "float_collection"
+
+    # Outputs
+    collection: list[float] = Field(default=[], description="The float collection")
+
+
+class ImageCollectionOutput(BaseInvocationOutput):
+    """A collection of images"""
+
+    type: Literal["image_collection"] = "image_collection"
+
+    # Outputs
+    collection: list[ImageField] = Field(default=[], description="The output images")
+
+    class Config:
+        json_schema_extra = {"required": ["type", "collection"]}
 
 
-@invocation(
-    "range", title="Integer Range", tags=["collection", "integer", "range"], category="collections", version="1.0.0"
-)
 class RangeInvocation(BaseInvocation):
     """Creates a range of numbers from start to stop with step"""
 
-    start: int = InputField(default=0, description="The start of the range")
-    stop: int = InputField(default=10, description="The stop of the range")
-    step: int = InputField(default=1, description="The step of the range")
+    type: Literal["range"] = "range"
 
-    @validator("stop")
+    # 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")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Range", "tags": ["range", "integer", "collection"]},
+        }
+
+    @field_validator("stop")
     def stop_gt_start(cls, v, values):
         if "start" in values and v <= values["start"]:
             raise ValueError("stop must be greater than start")
         return v
 
-    def invoke(self, context: InvocationContext) -> IntegerCollectionOutput:
-        return IntegerCollectionOutput(collection=list(range(self.start, self.stop, self.step)))
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(collection=list(range(self.start, self.stop, self.step)))
 
 
-@invocation(
-    "range_of_size",
-    title="Integer Range of Size",
-    tags=["collection", "integer", "size", "range"],
-    category="collections",
-    version="1.0.0",
-)
 class RangeOfSizeInvocation(BaseInvocation):
-    """Creates a range from start to start + (size * step) incremented by step"""
+    """Creates a range from start to start + size with step"""
 
-    start: int = InputField(default=0, description="The start of the range")
-    size: int = InputField(default=1, gt=0, description="The number of values")
-    step: int = InputField(default=1, description="The step of the range")
+    type: Literal["range_of_size"] = "range_of_size"
 
-    def invoke(self, context: InvocationContext) -> IntegerCollectionOutput:
-        return IntegerCollectionOutput(
-            collection=list(range(self.start, self.start + (self.step * self.size), self.step))
-        )
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    size: int = Field(default=1, description="The number of values")
+    step: int = Field(default=1, description="The step of the range")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Sized Range", "tags": ["range", "integer", "size", "collection"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(collection=list(range(self.start, self.start + self.size, self.step)))
 
 
-@invocation(
-    "random_range",
-    title="Random Range",
-    tags=["range", "integer", "random", "collection"],
-    category="collections",
-    version="1.0.0",
-    use_cache=False,
-)
 class RandomRangeInvocation(BaseInvocation):
     """Creates a collection of random numbers"""
 
-    low: int = InputField(default=0, description="The inclusive low value")
-    high: int = InputField(default=np.iinfo(np.int32).max, description="The exclusive high value")
-    size: int = InputField(default=1, description="The number of values to generate")
-    seed: int = InputField(
+    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) -> IntegerCollectionOutput:
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Random Range", "tags": ["range", "integer", "random", "collection"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
         rng = np.random.default_rng(self.seed)
-        return IntegerCollectionOutput(collection=list(rng.integers(low=self.low, high=self.high, size=self.size)))
+        return IntCollectionOutput(collection=list(rng.integers(low=self.low, high=self.high, size=self.size)))
+
+
+class ImageCollectionInvocation(BaseInvocation):
+    """Load a collection of images and provide it as output."""
+
+    # fmt: off
+    type: Literal["image_collection"] = "image_collection"
+
+    # Inputs
+    images: list[ImageField] = Field(
+        default=[], description="The image collection to load"
+    )
+    # fmt: on
+
+    def invoke(self, context: InvocationContext) -> ImageCollectionOutput:
+        return ImageCollectionOutput(collection=self.images)
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "type_hints": {
+                    "title": "Image Collection",
+                    "images": "image_collection",
+                }
+            },
+        }

invokeai/app/invocations/compel.py

@@ -1,39 +1,56 @@
+from typing import Literal, Optional, Union, List, Annotated
+from pydantic import BaseModel, Field
 import re
-from dataclasses import dataclass
-from typing import List, Union
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+from .model import ClipField
+
+from ...backend.util.devices import torch_dtype
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from ...backend.model_management import BaseModelType, ModelType, SubModelType, ModelPatcher
 
 import torch
 from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
-
-from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
-    BasicConditioningInfo,
-    ExtraConditioningInfo,
-    SDXLConditioningInfo,
-)
-
-from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
 from ...backend.util.devices import torch_dtype
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    invocation,
-    invocation_output,
-)
+from ...backend.model_management import ModelType
+from ...backend.model_management.models import ModelNotFoundException
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 from .model import ClipField
+from dataclasses import dataclass
+
+
+class ConditioningField(BaseModel):
+    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
+
+    class Config:
+        json_schema_extra = {"required": ["conditioning_name"]}
+
+
+@dataclass
+class BasicConditioningInfo:
+    # type: Literal["basic_conditioning"] = "basic_conditioning"
+    embeds: torch.Tensor
+    extra_conditioning: Optional[InvokeAIDiffuserComponent.ExtraConditioningInfo]
+    # weight: float
+    # mode: ConditioningAlgo
+
+
+@dataclass
+class SDXLConditioningInfo(BasicConditioningInfo):
+    # type: Literal["sdxl_conditioning"] = "sdxl_conditioning"
+    pooled_embeds: torch.Tensor
+    add_time_ids: torch.Tensor
+
+
+ConditioningInfoType = Annotated[Union[BasicConditioningInfo, SDXLConditioningInfo], Field(discriminator="type")]
 
 
 @dataclass
 class ConditioningFieldData:
-    conditionings: List[BasicConditioningInfo]
+    conditionings: List[Union[BasicConditioningInfo, SDXLConditioningInfo]]
     # unconditioned: Optional[torch.Tensor]
 
 
@@ -43,29 +60,38 @@ class ConditioningFieldData:
 #    PerpNeg = "perp_neg"
 
 
-@invocation("compel", title="Prompt", tags=["prompt", "compel"], category="conditioning", version="1.0.0")
+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."""
 
-    prompt: str = InputField(
-        default="",
-        description=FieldDescriptions.compel_prompt,
-        ui_component=UIComponent.Textarea,
-    )
-    clip: ClipField = InputField(
-        title="CLIP",
-        description=FieldDescriptions.clip,
-        input=Input.Connection,
-    )
+    type: Literal["compel"] = "compel"
+
+    prompt: str = Field(default="", description="Prompt")
+    clip: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Prompt (Compel)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
+        }
 
     @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
+    def invoke(self, context: InvocationContext) -> CompelOutput:
         tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.dict(),
+            **self.clip.tokenizer.model_dump(),
             context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.dict(),
+            **self.clip.text_encoder.model_dump(),
             context=context,
         )
 
@@ -99,31 +125,31 @@ class CompelInvocation(BaseInvocation):
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
-        with (
-            ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
-                tokenizer,
-                ti_manager,
-            ),
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
-            text_encoder_info as text_encoder,
-        ):
+        with ModelPatcher.apply_lora_text_encoder(
+            text_encoder_info.context.model, _lora_loader()
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, self.clip.skipped_layers
+        ), text_encoder_info as text_encoder:
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
                 dtype_for_device_getter=torch_dtype,
-                truncate_long_prompts=False,
+                truncate_long_prompts=True,
             )
 
             conjunction = Compel.parse_prompt_string(self.prompt)
+            prompt: Union[FlattenedPrompt, Blend] = conjunction.prompts[0]
 
             if context.services.configuration.log_tokenization:
-                log_tokenization_for_conjunction(conjunction, tokenizer)
+                log_tokenization_for_prompt_object(prompt, tokenizer)
 
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            c, options = compel.build_conditioning_tensor_for_prompt_object(prompt)
 
-            ec = ExtraConditioningInfo(
+            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
                 tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
                 cross_attention_control_args=options.get("cross_attention_control", None),
             )
@@ -142,7 +168,7 @@ class CompelInvocation(BaseInvocation):
         conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
         context.services.latents.save(conditioning_name, conditioning_data)
 
-        return ConditioningOutput(
+        return CompelOutput(
             conditioning=ConditioningField(
                 conditioning_name=conditioning_name,
             ),
@@ -150,40 +176,16 @@ class CompelInvocation(BaseInvocation):
 
 
 class SDXLPromptInvocationBase:
-    def run_clip_compel(
-        self,
-        context: InvocationContext,
-        clip_field: ClipField,
-        prompt: str,
-        get_pooled: bool,
-        lora_prefix: str,
-        zero_on_empty: bool,
-    ):
+    def run_clip_raw(self, context, clip_field, prompt, get_pooled, lora_prefix):
         tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.dict(),
+            **clip_field.tokenizer.model_dump(),
             context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.dict(),
+            **clip_field.text_encoder.model_dump(),
             context=context,
         )
 
-        # return zero on empty
-        if prompt == "" and zero_on_empty:
-            cpu_text_encoder = text_encoder_info.context.model
-            c = torch.zeros(
-                (1, cpu_text_encoder.config.max_position_embeddings, cpu_text_encoder.config.hidden_size),
-                dtype=text_encoder_info.context.cache.precision,
-            )
-            if get_pooled:
-                c_pooled = torch.zeros(
-                    (1, cpu_text_encoder.config.hidden_size),
-                    dtype=c.dtype,
-                )
-            else:
-                c_pooled = None
-            return c, c_pooled, None
-
         def _lora_loader():
             for lora in clip_field.loras:
                 lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
@@ -214,30 +216,107 @@ class SDXLPromptInvocationBase:
                 # print(traceback.format_exc())
                 print(f'Warn: trigger: "{trigger}" not found')
 
-        with (
-            ModelPatcher.apply_lora(text_encoder_info.context.model, _lora_loader(), lora_prefix),
-            ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
-                tokenizer,
-                ti_manager,
-            ),
-            ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
-            text_encoder_info as text_encoder,
-        ):
+        with ModelPatcher.apply_lora(
+            text_encoder_info.context.model, _lora_loader(), lora_prefix
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, clip_field.skipped_layers
+        ), text_encoder_info as text_encoder:
+            text_inputs = tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=tokenizer.model_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+            text_input_ids = text_inputs.input_ids
+            prompt_embeds = text_encoder(
+                text_input_ids.to(text_encoder.device),
+                output_hidden_states=True,
+            )
+            if get_pooled:
+                c_pooled = prompt_embeds[0]
+            else:
+                c_pooled = None
+            c = prompt_embeds.hidden_states[-2]
+
+        del tokenizer
+        del text_encoder
+        del tokenizer_info
+        del text_encoder_info
+
+        c = c.detach().to("cpu")
+        if c_pooled is not None:
+            c_pooled = c_pooled.detach().to("cpu")
+
+        return c, c_pooled, None
+
+    def run_clip_compel(self, context, clip_field, prompt, get_pooled, lora_prefix):
+        tokenizer_info = context.services.model_manager.get_model(
+            **clip_field.tokenizer.model_dump(),
+            context=context,
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **clip_field.text_encoder.model_dump(),
+            context=context,
+        )
+
+        def _lora_loader():
+            for lora in clip_field.loras:
+                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
+
+        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+
+        ti_list = []
+        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    (
+                        name,
+                        context.services.model_manager.get_model(
+                            model_name=name,
+                            base_model=clip_field.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                            context=context,
+                        ).context.model,
+                    )
+                )
+            except ModelNotFoundException:
+                # print(e)
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
+
+        with ModelPatcher.apply_lora(
+            text_encoder_info.context.model, _lora_loader(), lora_prefix
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, clip_field.skipped_layers
+        ), text_encoder_info as text_encoder:
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
                 dtype_for_device_getter=torch_dtype,
-                truncate_long_prompts=False,  # TODO:
+                truncate_long_prompts=True,  # TODO:
                 returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,  # TODO: clip skip
-                requires_pooled=get_pooled,
+                requires_pooled=True,
             )
 
             conjunction = Compel.parse_prompt_string(prompt)
 
             if context.services.configuration.log_tokenization:
                 # TODO: better logging for and syntax
-                log_tokenization_for_conjunction(conjunction, tokenizer)
+                for prompt_obj in conjunction.prompts:
+                    log_tokenization_for_prompt_object(prompt_obj, tokenizer)
 
             # TODO: ask for optimizations? to not run text_encoder twice
             c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
@@ -246,7 +325,7 @@ class SDXLPromptInvocationBase:
             else:
                 c_pooled = None
 
-            ec = ExtraConditioningInfo(
+            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
                 tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
                 cross_attention_control_args=options.get("cross_attention_control", None),
             )
@@ -263,40 +342,35 @@ class SDXLPromptInvocationBase:
         return c, c_pooled, ec
 
 
-@invocation(
-    "sdxl_compel_prompt",
-    title="SDXL Prompt",
-    tags=["sdxl", "compel", "prompt"],
-    category="conditioning",
-    version="1.0.0",
-)
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
-    prompt: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
-    style: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
-    original_width: int = InputField(default=1024, description="")
-    original_height: int = InputField(default=1024, description="")
-    crop_top: int = InputField(default=0, description="")
-    crop_left: int = InputField(default=0, description="")
-    target_width: int = InputField(default=1024, description="")
-    target_height: int = InputField(default=1024, description="")
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    type: Literal["sdxl_compel_prompt"] = "sdxl_compel_prompt"
+
+    prompt: str = Field(default="", description="Prompt")
+    style: str = Field(default="", description="Style prompt")
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    target_width: int = Field(1024, description="")
+    target_height: int = Field(1024, description="")
+    clip: ClipField = Field(None, description="Clip to use")
+    clip2: ClipField = Field(None, description="Clip2 to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "SDXL Prompt (Compel)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
+        }
 
     @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        c1, c1_pooled, ec1 = self.run_clip_compel(
-            context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True
-        )
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c1, c1_pooled, ec1 = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_")
         if self.style.strip() == "":
-            c2, c2_pooled, ec2 = self.run_clip_compel(
-                context, self.clip2, self.prompt, True, "lora_te2_", zero_on_empty=True
-            )
+            c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.prompt, True, "lora_te2_")
         else:
-            c2, c2_pooled, ec2 = self.run_clip_compel(
-                context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True
-            )
+            c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "lora_te2_")
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -304,29 +378,6 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
 
         add_time_ids = torch.tensor([original_size + crop_coords + target_size])
 
-        # [1, 77, 768], [1, 154, 1280]
-        if c1.shape[1] < c2.shape[1]:
-            c1 = torch.cat(
-                [
-                    c1,
-                    torch.zeros(
-                        (c1.shape[0], c2.shape[1] - c1.shape[1], c1.shape[2]), device=c1.device, dtype=c1.dtype
-                    ),
-                ],
-                dim=1,
-            )
-
-        elif c1.shape[1] > c2.shape[1]:
-            c2 = torch.cat(
-                [
-                    c2,
-                    torch.zeros(
-                        (c2.shape[0], c1.shape[1] - c2.shape[1], c2.shape[2]), device=c2.device, dtype=c2.dtype
-                    ),
-                ],
-                dim=1,
-            )
-
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
@@ -341,37 +392,40 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
         context.services.latents.save(conditioning_name, conditioning_data)
 
-        return ConditioningOutput(
+        return CompelOutput(
             conditioning=ConditioningField(
                 conditioning_name=conditioning_name,
             ),
         )
 
 
-@invocation(
-    "sdxl_refiner_compel_prompt",
-    title="SDXL Refiner Prompt",
-    tags=["sdxl", "compel", "prompt"],
-    category="conditioning",
-    version="1.0.0",
-)
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
-    style: str = InputField(
-        default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea
-    )  # TODO: ?
-    original_width: int = InputField(default=1024, description="")
-    original_height: int = InputField(default=1024, description="")
-    crop_top: int = InputField(default=0, description="")
-    crop_left: int = InputField(default=0, description="")
-    aesthetic_score: float = InputField(default=6.0, description=FieldDescriptions.sdxl_aesthetic)
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
+    type: Literal["sdxl_refiner_compel_prompt"] = "sdxl_refiner_compel_prompt"
+
+    style: str = Field(default="", description="Style prompt")  # TODO: ?
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    aesthetic_score: float = Field(6.0, description="")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "SDXL Refiner Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {"model": "model"},
+            },
+        }
 
     @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> ConditioningOutput:
+    def invoke(self, context: InvocationContext) -> CompelOutput:
         # TODO: if there will appear lora for refiner - write proper prefix
-        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
+        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>")
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -392,26 +446,143 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
         conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
         context.services.latents.save(conditioning_name, conditioning_data)
 
-        return ConditioningOutput(
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Pass unmodified prompt to conditioning without compel processing."""
+
+    type: Literal["sdxl_raw_prompt"] = "sdxl_raw_prompt"
+
+    prompt: str = Field(default="", description="Prompt")
+    style: str = Field(default="", description="Style prompt")
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    target_width: int = Field(1024, description="")
+    target_height: int = Field(1024, description="")
+    clip: ClipField = Field(None, description="Clip to use")
+    clip2: ClipField = Field(None, description="Clip2 to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "SDXL Prompt (Raw)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c1, c1_pooled, ec1 = self.run_clip_raw(context, self.clip, self.prompt, False, "lora_te1_")
+        if self.style.strip() == "":
+            c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.prompt, True, "lora_te2_")
+        else:
+            c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.style, True, "lora_te2_")
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+        target_size = (self.target_height, self.target_width)
+
+        add_time_ids = torch.tensor([original_size + crop_coords + target_size])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=torch.cat([c1, c2], dim=-1),
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec1,
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["sdxl_refiner_raw_prompt"] = "sdxl_refiner_raw_prompt"
+
+    style: str = Field(default="", description="Style prompt")  # TODO: ?
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    aesthetic_score: float = Field(6.0, description="")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "SDXL Refiner Prompt (Raw)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        # TODO: if there will appear lora for refiner - write proper prefix
+        c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.style, True, "<NONE>")
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+
+        add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=c2,
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec2,  # or None
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
             conditioning=ConditioningField(
                 conditioning_name=conditioning_name,
             ),
         )
 
 
-@invocation_output("clip_skip_output")
 class ClipSkipInvocationOutput(BaseInvocationOutput):
     """Clip skip node output"""
 
-    clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    type: Literal["clip_skip_output"] = "clip_skip_output"
+    clip: ClipField = Field(None, description="Clip with skipped layers")
 
 
-@invocation("clip_skip", title="CLIP Skip", tags=["clipskip", "clip", "skip"], category="conditioning", version="1.0.0")
 class ClipSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
-    skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
+    type: Literal["clip_skip"] = "clip_skip"
+
+    clip: ClipField = Field(None, description="Clip to use")
+    skipped_layers: int = Field(0, description="Number of layers to skip in text_encoder")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "CLIP Skip", "tags": ["clip", "skip"]},
+        }
 
     def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
         self.clip.skipped_layers += self.skipped_layers
@@ -438,11 +609,9 @@ def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, trun
         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))
-        )
+        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)

invokeai/app/invocations/controlnet_image_processors.py

@@ -24,30 +24,81 @@ from controlnet_aux import (
 )
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
-from pydantic import BaseModel, Field, validator
+from pydantic import BaseModel, Field, field_validator
 
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
+from ...backend.model_management import BaseModelType, ModelType
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
+from ..models.image import ImageOutput, PILInvocationConfig
 
-from ...backend.model_management import BaseModelType
-from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    invocation,
-    invocation_output,
-)
+CONTROLNET_DEFAULT_MODELS = [
+    ###########################################
+    # lllyasviel sd v1.5, ControlNet v1.0 models
+    ##############################################
+    "lllyasviel/sd-controlnet-canny",
+    "lllyasviel/sd-controlnet-depth",
+    "lllyasviel/sd-controlnet-hed",
+    "lllyasviel/sd-controlnet-seg",
+    "lllyasviel/sd-controlnet-openpose",
+    "lllyasviel/sd-controlnet-scribble",
+    "lllyasviel/sd-controlnet-normal",
+    "lllyasviel/sd-controlnet-mlsd",
+    #############################################
+    # lllyasviel sd v1.5, ControlNet v1.1 models
+    #############################################
+    "lllyasviel/control_v11p_sd15_canny",
+    "lllyasviel/control_v11p_sd15_openpose",
+    "lllyasviel/control_v11p_sd15_seg",
+    # "lllyasviel/control_v11p_sd15_depth",  # broken
+    "lllyasviel/control_v11f1p_sd15_depth",
+    "lllyasviel/control_v11p_sd15_normalbae",
+    "lllyasviel/control_v11p_sd15_scribble",
+    "lllyasviel/control_v11p_sd15_mlsd",
+    "lllyasviel/control_v11p_sd15_softedge",
+    "lllyasviel/control_v11p_sd15s2_lineart_anime",
+    "lllyasviel/control_v11p_sd15_lineart",
+    "lllyasviel/control_v11p_sd15_inpaint",
+    # "lllyasviel/control_v11u_sd15_tile",
+    # problem (temporary?) with huffingface "lllyasviel/control_v11u_sd15_tile",
+    # so for now replace  "lllyasviel/control_v11f1e_sd15_tile",
+    "lllyasviel/control_v11e_sd15_shuffle",
+    "lllyasviel/control_v11e_sd15_ip2p",
+    "lllyasviel/control_v11f1e_sd15_tile",
+    #################################################
+    #  thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
+    ##################################################
+    "thibaud/controlnet-sd21-openpose-diffusers",
+    "thibaud/controlnet-sd21-canny-diffusers",
+    "thibaud/controlnet-sd21-depth-diffusers",
+    "thibaud/controlnet-sd21-scribble-diffusers",
+    "thibaud/controlnet-sd21-hed-diffusers",
+    "thibaud/controlnet-sd21-zoedepth-diffusers",
+    "thibaud/controlnet-sd21-color-diffusers",
+    "thibaud/controlnet-sd21-openposev2-diffusers",
+    "thibaud/controlnet-sd21-lineart-diffusers",
+    "thibaud/controlnet-sd21-normalbae-diffusers",
+    "thibaud/controlnet-sd21-ade20k-diffusers",
+    ##############################################
+    #  ControlNetMediaPipeface, ControlNet v1.1
+    ##############################################
+    # ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"],  # SD 1.5
+    #    diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg
+    #    hacked t2l to split to model & subfolder if format is "model,subfolder"
+    "CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15",  # SD 1.5
+    "CrucibleAI/ControlNetMediaPipeFace",  # SD 2.1?
+]
 
-CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
+CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
+CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
 CONTROLNET_RESIZE_VALUES = Literal[
-    "just_resize",
-    "crop_resize",
-    "fill_resize",
-    "just_resize_simple",
+    tuple(
+        [
+            "just_resize",
+            "crop_resize",
+            "fill_resize",
+            "just_resize_simple",
+        ]
+    )
 ]
 
 
@@ -59,8 +110,9 @@ class ControlNetModelField(BaseModel):
 
 
 class ControlField(BaseModel):
-    image: ImageField = Field(description="The control image")
-    control_model: ControlNetModelField = Field(description="The ControlNet model to use")
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: Optional[ControlNetModelField] = Field(default=None, description="The ControlNet model to use")
+    # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
     control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
@@ -71,7 +123,7 @@ class ControlField(BaseModel):
     control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
     resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
 
-    @validator("control_weight")
+    @field_validator("control_weight")
     def validate_control_weight(cls, v):
         """Validate that all control weights in the valid range"""
         if isinstance(v, list):
@@ -83,32 +135,60 @@ class ControlField(BaseModel):
                 raise ValueError("Control weights must be within -1 to 2 range")
         return v
 
+    class Config:
+        json_schema_extra = {
+            "required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"],
+            "ui": {
+                "type_hints": {
+                    "control_weight": "float",
+                    "control_model": "controlnet_model",
+                    # "control_weight": "number",
+                }
+            },
+        }
+
 
-@invocation_output("control_output")
 class ControlOutput(BaseInvocationOutput):
     """node output for ControlNet info"""
 
-    # Outputs
-    control: ControlField = OutputField(description=FieldDescriptions.control)
+    # fmt: off
+    type: Literal["control_output"] = "control_output"
+    control: ControlField = Field(default=None, description="The control info")
+    # fmt: on
 
 
-@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.0.0")
 class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
-    image: ImageField = InputField(description="The control image")
-    control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
-    control_weight: Union[float, List[float]] = InputField(
-        default=1.0, description="The weight given to the ControlNet"
-    )
-    begin_step_percent: float = InputField(
-        default=0, ge=-1, le=2, description="When the ControlNet is first applied (% of total steps)"
-    )
-    end_step_percent: float = InputField(
-        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
-    )
-    control_mode: CONTROLNET_MODE_VALUES = InputField(default="balanced", description="The control mode used")
-    resize_mode: CONTROLNET_RESIZE_VALUES = InputField(default="just_resize", description="The resize mode used")
+    # fmt: off
+    type: Literal["controlnet"] = "controlnet"
+    # Inputs
+    image: ImageField = Field(default=None, description="The control image")
+    control_model: ControlNetModelField = Field(default="lllyasviel/sd-controlnet-canny",
+                                                  description="control model used")
+    control_weight: Union[float, List[float]] = Field(default=1.0, description="The weight given to the ControlNet")
+    begin_step_percent: float = Field(default=0, ge=-1, le=2,
+                                      description="When the ControlNet is first applied (% of total steps)")
+    end_step_percent: float = Field(default=1, ge=0, le=1,
+                                    description="When the ControlNet is last applied (% of total steps)")
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode used")
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode used")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "ControlNet",
+                "tags": ["controlnet", "latents"],
+                "type_hints": {
+                    "model": "model",
+                    "control": "control",
+                    # "cfg_scale": "float",
+                    "cfg_scale": "number",
+                    "control_weight": "float",
+                },
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> ControlOutput:
         return ControlOutput(
@@ -124,13 +204,19 @@ class ControlNetInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "image_processor", title="Base Image Processor", tags=["controlnet"], category="controlnet", version="1.0.0"
-)
-class ImageProcessorInvocation(BaseInvocation):
+class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
     """Base class for invocations that preprocess images for ControlNet"""
 
-    image: ImageField = InputField(description="The image to process")
+    # fmt: off
+    type: Literal["image_processor"] = "image_processor"
+    # Inputs
+    image: ImageField = Field(default=None, description="The image to process")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Image Processor", "tags": ["image", "processor"]},
+        }
 
     def run_processor(self, image):
         # superclass just passes through image without processing
@@ -141,6 +227,11 @@ class ImageProcessorInvocation(BaseInvocation):
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
 
+        # FIXME: what happened to image metadata?
+        # metadata = context.services.metadata.build_metadata(
+        #     session_id=context.graph_execution_state_id, node=self
+        # )
+
         # currently can't see processed image in node UI without a showImage node,
         #    so for now setting image_type to RESULT instead of INTERMEDIATE so will get saved in gallery
         image_dto = context.services.images.create(
@@ -150,7 +241,6 @@ class ImageProcessorInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             node_id=self.id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         """Builds an ImageOutput and its ImageField"""
@@ -165,22 +255,20 @@ class ImageProcessorInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "canny_image_processor",
-    title="Canny Processor",
-    tags=["controlnet", "canny"],
-    category="controlnet",
-    version="1.0.0",
-)
-class CannyImageProcessorInvocation(ImageProcessorInvocation):
+class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Canny edge detection for ControlNet"""
 
-    low_threshold: int = InputField(
-        default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)"
-    )
-    high_threshold: int = InputField(
-        default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)"
-    )
+    # fmt: off
+    type: Literal["canny_image_processor"] = "canny_image_processor"
+    # Input
+    low_threshold: int = Field(default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)")
+    high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Canny Processor", "tags": ["controlnet", "canny", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         canny_processor = CannyDetector()
@@ -188,21 +276,23 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "hed_image_processor",
-    title="HED (softedge) Processor",
-    tags=["controlnet", "hed", "softedge"],
-    category="controlnet",
-    version="1.0.0",
-)
-class HedImageProcessorInvocation(ImageProcessorInvocation):
+class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies HED edge detection to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    # fmt: off
+    type: Literal["hed_image_processor"] = "hed_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
     # safe not supported in controlnet_aux v0.0.3
-    # safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
-    scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
+    # safe: bool = Field(default=False, description="whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Softedge(HED) Processor", "tags": ["controlnet", "softedge", "hed", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
@@ -217,19 +307,21 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "lineart_image_processor",
-    title="Lineart Processor",
-    tags=["controlnet", "lineart"],
-    category="controlnet",
-    version="1.0.0",
-)
-class LineartImageProcessorInvocation(ImageProcessorInvocation):
+class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies line art processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-    coarse: bool = InputField(default=False, description="Whether to use coarse mode")
+    # fmt: off
+    type: Literal["lineart_image_processor"] = "lineart_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    coarse: bool = Field(default=False, description="Whether to use coarse mode")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Lineart Processor", "tags": ["controlnet", "lineart", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
@@ -239,18 +331,23 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "lineart_anime_image_processor",
-    title="Lineart Anime Processor",
-    tags=["controlnet", "lineart", "anime"],
-    category="controlnet",
-    version="1.0.0",
-)
-class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
+class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies line art anime processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    # fmt: off
+    type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Lineart Anime Processor",
+                "tags": ["controlnet", "lineart", "anime", "image", "processor"],
+            },
+        }
 
     def run_processor(self, image):
         processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
@@ -262,19 +359,21 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.0.0",
-)
-class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
+class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Openpose processing to image"""
 
-    hand_and_face: bool = InputField(default=False, description="Whether to use hands and face mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    # fmt: off
+    type: Literal["openpose_image_processor"] = "openpose_image_processor"
+    # Inputs
+    hand_and_face: bool = Field(default=False, description="Whether to use hands and face mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Openpose Processor", "tags": ["controlnet", "openpose", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
@@ -287,20 +386,22 @@ class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "midas_depth_image_processor",
-    title="Midas Depth Processor",
-    tags=["controlnet", "midas"],
-    category="controlnet",
-    version="1.0.0",
-)
-class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
+class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Midas depth processing to image"""
 
-    a_mult: float = InputField(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
-    bg_th: float = InputField(default=0.1, ge=0, description="Midas parameter `bg_th`")
+    # fmt: off
+    type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
+    # Inputs
+    a_mult: float = Field(default=2.0, ge=0, description="Midas parameter `a_mult` (a = a_mult * PI)")
+    bg_th: float = Field(default=0.1, ge=0, description="Midas parameter `bg_th`")
     # depth_and_normal not supported in controlnet_aux v0.0.3
-    # depth_and_normal: bool = InputField(default=False, description="whether to use depth and normal mode")
+    # depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Midas (Depth) Processor", "tags": ["controlnet", "midas", "depth", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
@@ -314,18 +415,20 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "normalbae_image_processor",
-    title="Normal BAE Processor",
-    tags=["controlnet"],
-    category="controlnet",
-    version="1.0.0",
-)
-class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
+class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies NormalBae processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    # fmt: off
+    type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Normal BAE Processor", "tags": ["controlnet", "normal", "bae", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
@@ -335,16 +438,22 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.0.0"
-)
-class MlsdImageProcessorInvocation(ImageProcessorInvocation):
+class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies MLSD processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-    thr_v: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_v`")
-    thr_d: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_d`")
+    # fmt: off
+    type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    thr_v: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_v`")
+    thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "MLSD Processor", "tags": ["controlnet", "mlsd", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
@@ -358,16 +467,22 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.0.0"
-)
-class PidiImageProcessorInvocation(ImageProcessorInvocation):
+class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies PIDI processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-    safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
-    scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
+    # fmt: off
+    type: Literal["pidi_image_processor"] = "pidi_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    safe: bool = Field(default=False, description="Whether to use safe mode")
+    scribble: bool = Field(default=False, description="Whether to use scribble mode")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "PIDI Processor", "tags": ["controlnet", "pidi", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
@@ -381,21 +496,26 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "content_shuffle_image_processor",
-    title="Content Shuffle Processor",
-    tags=["controlnet", "contentshuffle"],
-    category="controlnet",
-    version="1.0.0",
-)
-class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
+class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies content shuffle processing to image"""
 
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
-    h: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `h` parameter")
-    w: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
-    f: Optional[int] = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
+    # fmt: off
+    type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
+    # Inputs
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    h: Optional[int] = Field(default=512, ge=0, description="Content shuffle `h` parameter")
+    w: Optional[int] = Field(default=512, ge=0, description="Content shuffle `w` parameter")
+    f: Optional[int] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Content Shuffle Processor",
+                "tags": ["controlnet", "contentshuffle", "image", "processor"],
+            },
+        }
 
     def run_processor(self, image):
         content_shuffle_processor = ContentShuffleDetector()
@@ -411,34 +531,38 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
 
 
 # should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
-@invocation(
-    "zoe_depth_image_processor",
-    title="Zoe (Depth) Processor",
-    tags=["controlnet", "zoe", "depth"],
-    category="controlnet",
-    version="1.0.0",
-)
-class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
+class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Zoe depth processing to image"""
 
+    # fmt: off
+    type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Zoe (Depth) Processor", "tags": ["controlnet", "zoe", "depth", "image", "processor"]},
+        }
+
     def run_processor(self, image):
         zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = zoe_depth_processor(image)
         return processed_image
 
 
-@invocation(
-    "mediapipe_face_processor",
-    title="Mediapipe Face Processor",
-    tags=["controlnet", "mediapipe", "face"],
-    category="controlnet",
-    version="1.0.0",
-)
-class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
+class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies mediapipe face processing to image"""
 
-    max_faces: int = InputField(default=1, ge=1, description="Maximum number of faces to detect")
-    min_confidence: float = InputField(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    # fmt: off
+    type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
+    # Inputs
+    max_faces: int = Field(default=1, ge=1, description="Maximum number of faces to detect")
+    min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Mediapipe Processor", "tags": ["controlnet", "mediapipe", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         # MediaPipeFaceDetector throws an error if image has alpha channel
@@ -450,21 +574,23 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "leres_image_processor",
-    title="Leres (Depth) Processor",
-    tags=["controlnet", "leres", "depth"],
-    category="controlnet",
-    version="1.0.0",
-)
-class LeresImageProcessorInvocation(ImageProcessorInvocation):
+class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies leres processing to image"""
 
-    thr_a: float = InputField(default=0, description="Leres parameter `thr_a`")
-    thr_b: float = InputField(default=0, description="Leres parameter `thr_b`")
-    boost: bool = InputField(default=False, description="Whether to use boost mode")
-    detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
-    image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
+    # fmt: off
+    type: Literal["leres_image_processor"] = "leres_image_processor"
+    # Inputs
+    thr_a: float = Field(default=0, description="Leres parameter `thr_a`")
+    thr_b: float = Field(default=0, description="Leres parameter `thr_b`")
+    boost: bool = Field(default=False, description="Whether to use boost mode")
+    detect_resolution: int = Field(default=512, ge=0, description="The pixel resolution for detection")
+    image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Leres (Depth) Processor", "tags": ["controlnet", "leres", "depth", "image", "processor"]},
+        }
 
     def run_processor(self, image):
         leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
@@ -479,18 +605,21 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "tile_image_processor",
-    title="Tile Resample Processor",
-    tags=["controlnet", "tile"],
-    category="controlnet",
-    version="1.0.0",
-)
-class TileResamplerProcessorInvocation(ImageProcessorInvocation):
-    """Tile resampler processor"""
+class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
+    # fmt: off
+    type: Literal["tile_image_processor"] = "tile_image_processor"
+    # Inputs
+    #res: int = Field(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
+    down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
+    # fmt: on
 
-    # res: int = InputField(default=512, ge=0, le=1024, description="The pixel resolution for each tile")
-    down_sampling_rate: float = InputField(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Tile Resample Processor",
+                "tags": ["controlnet", "tile", "resample", "image", "processor"],
+            },
+        }
 
     # tile_resample copied from sd-webui-controlnet/scripts/processor.py
     def tile_resample(
@@ -519,16 +648,21 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "segment_anything_processor",
-    title="Segment Anything Processor",
-    tags=["controlnet", "segmentanything"],
-    category="controlnet",
-    version="1.0.0",
-)
-class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
+class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies segment anything processing to image"""
 
+    # fmt: off
+    type: Literal["segment_anything_processor"] = "segment_anything_processor"
+    # fmt: on
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Segment Anything Processor",
+                "tags": ["controlnet", "segment", "anything", "sam", "image", "processor"],
+            },
+        }
+
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
@@ -559,33 +693,3 @@ class SamDetectorReproducibleColors(SamDetector):
             img[:, :] = ann_color
             final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
         return np.array(final_img, dtype=np.uint8)
-
-
-@invocation(
-    "color_map_image_processor",
-    title="Color Map Processor",
-    tags=["controlnet"],
-    category="controlnet",
-    version="1.0.0",
-)
-class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
-    """Generates a color map from the provided image"""
-
-    color_map_tile_size: int = InputField(default=64, ge=0, description=FieldDescriptions.tile_size)
-
-    def run_processor(self, image: Image.Image):
-        image = image.convert("RGB")
-        image = np.array(image, dtype=np.uint8)
-        height, width = image.shape[:2]
-
-        width_tile_size = min(self.color_map_tile_size, width)
-        height_tile_size = min(self.color_map_tile_size, height)
-
-        color_map = cv2.resize(
-            image,
-            (width // width_tile_size, height // height_tile_size),
-            interpolation=cv2.INTER_CUBIC,
-        )
-        color_map = cv2.resize(color_map, (width, height), interpolation=cv2.INTER_NEAREST)
-        color_map = Image.fromarray(color_map)
-        return color_map

invokeai/app/invocations/cv.py

@@ -1,22 +1,44 @@
 # 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.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
-
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.0.0")
-class CvInpaintInvocation(BaseInvocation):
+class CvInvocationConfig(BaseModel):
+    """Helper class to provide all OpenCV invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "tags": ["cv", "image"],
+            },
+        }
+
+
+class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
     """Simple inpaint using opencv."""
 
-    image: ImageField = InputField(description="The image to inpaint")
-    mask: ImageField = InputField(description="The mask to use when inpainting")
+    # 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
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "OpenCV Inpaint", "tags": ["opencv", "inpaint"]},
+        }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -41,7 +63,6 @@ class CvInpaintInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(

invokeai/app/invocations/facetools.py

@@ -1,692 +0,0 @@
-import math
-import re
-from pathlib import Path
-from typing import Optional, TypedDict
-
-import cv2
-import numpy as np
-from mediapipe.python.solutions.face_mesh import FaceMesh  # type: ignore[import]
-from PIL import Image, ImageDraw, ImageFilter, ImageFont, ImageOps
-from PIL.Image import Image as ImageType
-from pydantic import validator
-
-import invokeai.assets.fonts as font_assets
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    InputField,
-    InvocationContext,
-    OutputField,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.primitives import ImageField, ImageOutput
-from invokeai.app.models.image import ImageCategory, ResourceOrigin
-
-
-@invocation_output("face_mask_output")
-class FaceMaskOutput(ImageOutput):
-    """Base class for FaceMask output"""
-
-    mask: ImageField = OutputField(description="The output mask")
-
-
-@invocation_output("face_off_output")
-class FaceOffOutput(ImageOutput):
-    """Base class for FaceOff Output"""
-
-    mask: ImageField = OutputField(description="The output mask")
-    x: int = OutputField(description="The x coordinate of the bounding box's left side")
-    y: int = OutputField(description="The y coordinate of the bounding box's top side")
-
-
-class FaceResultData(TypedDict):
-    image: ImageType
-    mask: ImageType
-    x_center: float
-    y_center: float
-    mesh_width: int
-    mesh_height: int
-
-
-class FaceResultDataWithId(FaceResultData):
-    face_id: int
-
-
-class ExtractFaceData(TypedDict):
-    bounded_image: ImageType
-    bounded_mask: ImageType
-    x_min: int
-    y_min: int
-    x_max: int
-    y_max: int
-
-
-class FaceMaskResult(TypedDict):
-    image: ImageType
-    mask: ImageType
-
-
-def create_white_image(w: int, h: int) -> ImageType:
-    return Image.new("L", (w, h), color=255)
-
-
-def create_black_image(w: int, h: int) -> ImageType:
-    return Image.new("L", (w, h), color=0)
-
-
-FONT_SIZE = 32
-FONT_STROKE_WIDTH = 4
-
-
-def prepare_faces_list(
-    face_result_list: list[FaceResultData],
-) -> list[FaceResultDataWithId]:
-    """Deduplicates a list of faces, adding IDs to them."""
-    deduped_faces: list[FaceResultData] = []
-
-    if len(face_result_list) == 0:
-        return list()
-
-    for candidate in face_result_list:
-        should_add = True
-        candidate_x_center = candidate["x_center"]
-        candidate_y_center = candidate["y_center"]
-        for face in deduped_faces:
-            face_center_x = face["x_center"]
-            face_center_y = face["y_center"]
-            face_radius_w = face["mesh_width"] / 2
-            face_radius_h = face["mesh_height"] / 2
-            # Determine if the center of the candidate_face is inside the ellipse of the added face
-            # p < 1 -> Inside
-            # p = 1 -> Exactly on the ellipse
-            # p > 1 -> Outside
-            p = (math.pow((candidate_x_center - face_center_x), 2) / math.pow(face_radius_w, 2)) + (
-                math.pow((candidate_y_center - face_center_y), 2) / math.pow(face_radius_h, 2)
-            )
-
-            if p < 1:  # Inside of the already-added face's radius
-                should_add = False
-                break
-
-        if should_add is True:
-            deduped_faces.append(candidate)
-
-    sorted_faces = sorted(deduped_faces, key=lambda x: x["y_center"])
-    sorted_faces = sorted(sorted_faces, key=lambda x: x["x_center"])
-
-    # add face_id for reference
-    sorted_faces_with_ids: list[FaceResultDataWithId] = []
-    face_id_counter = 0
-    for face in sorted_faces:
-        sorted_faces_with_ids.append(
-            FaceResultDataWithId(
-                **face,
-                face_id=face_id_counter,
-            )
-        )
-        face_id_counter += 1
-
-    return sorted_faces_with_ids
-
-
-def generate_face_box_mask(
-    context: InvocationContext,
-    minimum_confidence: float,
-    x_offset: float,
-    y_offset: float,
-    pil_image: ImageType,
-    chunk_x_offset: int = 0,
-    chunk_y_offset: int = 0,
-    draw_mesh: bool = True,
-    check_bounds: bool = True,
-) -> list[FaceResultData]:
-    result = []
-    mask_pil = None
-
-    # Convert the PIL image to a NumPy array.
-    np_image = np.array(pil_image, dtype=np.uint8)
-
-    # Check if the input image has four channels (RGBA).
-    if np_image.shape[2] == 4:
-        # Convert RGBA to RGB by removing the alpha channel.
-        np_image = np_image[:, :, :3]
-
-    # Create a FaceMesh object for face landmark detection and mesh generation.
-    face_mesh = FaceMesh(
-        max_num_faces=999,
-        min_detection_confidence=minimum_confidence,
-        min_tracking_confidence=minimum_confidence,
-    )
-
-    # Detect the face landmarks and mesh in the input image.
-    results = face_mesh.process(np_image)
-
-    # Check if any face is detected.
-    if results.multi_face_landmarks:  # type: ignore # this are via protobuf and not typed
-        # Search for the face_id in the detected faces.
-        for face_id, face_landmarks in enumerate(results.multi_face_landmarks):  # type: ignore #this are via protobuf and not typed
-            # Get the bounding box of the face mesh.
-            x_coordinates = [landmark.x for landmark in face_landmarks.landmark]
-            y_coordinates = [landmark.y for landmark in face_landmarks.landmark]
-            x_min, x_max = min(x_coordinates), max(x_coordinates)
-            y_min, y_max = min(y_coordinates), max(y_coordinates)
-
-            # Calculate the width and height of the face mesh.
-            mesh_width = int((x_max - x_min) * np_image.shape[1])
-            mesh_height = int((y_max - y_min) * np_image.shape[0])
-
-            # Get the center of the face.
-            x_center = np.mean([landmark.x * np_image.shape[1] for landmark in face_landmarks.landmark])
-            y_center = np.mean([landmark.y * np_image.shape[0] for landmark in face_landmarks.landmark])
-
-            face_landmark_points = np.array(
-                [
-                    [landmark.x * np_image.shape[1], landmark.y * np_image.shape[0]]
-                    for landmark in face_landmarks.landmark
-                ]
-            )
-
-            # Apply the scaling offsets to the face landmark points with a multiplier.
-            scale_multiplier = 0.2
-            x_center = np.mean(face_landmark_points[:, 0])
-            y_center = np.mean(face_landmark_points[:, 1])
-
-            if draw_mesh:
-                x_scaled = face_landmark_points[:, 0] + scale_multiplier * x_offset * (
-                    face_landmark_points[:, 0] - x_center
-                )
-                y_scaled = face_landmark_points[:, 1] + scale_multiplier * y_offset * (
-                    face_landmark_points[:, 1] - y_center
-                )
-
-                convex_hull = cv2.convexHull(np.column_stack((x_scaled, y_scaled)).astype(np.int32))
-
-                # Generate a binary face mask using the face mesh.
-                mask_image = np.ones(np_image.shape[:2], dtype=np.uint8) * 255
-                cv2.fillConvexPoly(mask_image, convex_hull, 0)
-
-                # Convert the binary mask image to a PIL Image.
-                init_mask_pil = Image.fromarray(mask_image, mode="L")
-                w, h = init_mask_pil.size
-                mask_pil = create_white_image(w + chunk_x_offset, h + chunk_y_offset)
-                mask_pil.paste(init_mask_pil, (chunk_x_offset, chunk_y_offset))
-
-            left_side = x_center - mesh_width
-            right_side = x_center + mesh_width
-            top_side = y_center - mesh_height
-            bottom_side = y_center + mesh_height
-            im_width, im_height = pil_image.size
-            over_w = im_width * 0.1
-            over_h = im_height * 0.1
-            if not check_bounds or (
-                (left_side >= -over_w)
-                and (right_side < im_width + over_w)
-                and (top_side >= -over_h)
-                and (bottom_side < im_height + over_h)
-            ):
-                x_center = float(x_center)
-                y_center = float(y_center)
-                face = FaceResultData(
-                    image=pil_image,
-                    mask=mask_pil or create_white_image(*pil_image.size),
-                    x_center=x_center + chunk_x_offset,
-                    y_center=y_center + chunk_y_offset,
-                    mesh_width=mesh_width,
-                    mesh_height=mesh_height,
-                )
-
-                result.append(face)
-            else:
-                context.services.logger.info("FaceTools --> Face out of bounds, ignoring.")
-
-    return result
-
-
-def extract_face(
-    context: InvocationContext,
-    image: ImageType,
-    face: FaceResultData,
-    padding: int,
-) -> ExtractFaceData:
-    mask = face["mask"]
-    center_x = face["x_center"]
-    center_y = face["y_center"]
-    mesh_width = face["mesh_width"]
-    mesh_height = face["mesh_height"]
-
-    # Determine the minimum size of the square crop
-    min_size = min(mask.width, mask.height)
-
-    # Calculate the crop boundaries for the output image and mask.
-    mesh_width += 128 + padding  # add pixels to account for mask variance
-    mesh_height += 128 + padding  # add pixels to account for mask variance
-    crop_size = min(
-        max(mesh_width, mesh_height, 128), min_size
-    )  # Choose the smaller of the two (given value or face mask size)
-    if crop_size > 128:
-        crop_size = (crop_size + 7) // 8 * 8  # Ensure crop side is multiple of 8
-
-    # Calculate the actual crop boundaries within the bounds of the original image.
-    x_min = int(center_x - crop_size / 2)
-    y_min = int(center_y - crop_size / 2)
-    x_max = int(center_x + crop_size / 2)
-    y_max = int(center_y + crop_size / 2)
-
-    # Adjust the crop boundaries to stay within the original image's dimensions
-    if x_min < 0:
-        context.services.logger.warning("FaceTools --> -X-axis padding reached image edge.")
-        x_max -= x_min
-        x_min = 0
-    elif x_max > mask.width:
-        context.services.logger.warning("FaceTools --> +X-axis padding reached image edge.")
-        x_min -= x_max - mask.width
-        x_max = mask.width
-
-    if y_min < 0:
-        context.services.logger.warning("FaceTools --> +Y-axis padding reached image edge.")
-        y_max -= y_min
-        y_min = 0
-    elif y_max > mask.height:
-        context.services.logger.warning("FaceTools --> -Y-axis padding reached image edge.")
-        y_min -= y_max - mask.height
-        y_max = mask.height
-
-    # Ensure the crop is square and adjust the boundaries if needed
-    if x_max - x_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting x-axis padding to constrain bounding box to a square.")
-        diff = crop_size - (x_max - x_min)
-        x_min -= diff // 2
-        x_max += diff - diff // 2
-
-    if y_max - y_min != crop_size:
-        context.services.logger.warning("FaceTools --> Limiting y-axis padding to constrain bounding box to a square.")
-        diff = crop_size - (y_max - y_min)
-        y_min -= diff // 2
-        y_max += diff - diff // 2
-
-    context.services.logger.info(f"FaceTools --> Calculated bounding box (8 multiple): {crop_size}")
-
-    # Crop the output image to the specified size with the center of the face mesh as the center.
-    mask = mask.crop((x_min, y_min, x_max, y_max))
-    bounded_image = image.crop((x_min, y_min, x_max, y_max))
-
-    # blur mask edge by small radius
-    mask = mask.filter(ImageFilter.GaussianBlur(radius=2))
-
-    return ExtractFaceData(
-        bounded_image=bounded_image,
-        bounded_mask=mask,
-        x_min=x_min,
-        y_min=y_min,
-        x_max=x_max,
-        y_max=y_max,
-    )
-
-
-def get_faces_list(
-    context: InvocationContext,
-    image: ImageType,
-    should_chunk: bool,
-    minimum_confidence: float,
-    x_offset: float,
-    y_offset: float,
-    draw_mesh: bool = True,
-) -> list[FaceResultDataWithId]:
-    result = []
-
-    # Generate the face box mask and get the center of the face.
-    if not should_chunk:
-        context.services.logger.info("FaceTools --> Attempting full image face detection.")
-        result = generate_face_box_mask(
-            context=context,
-            minimum_confidence=minimum_confidence,
-            x_offset=x_offset,
-            y_offset=y_offset,
-            pil_image=image,
-            chunk_x_offset=0,
-            chunk_y_offset=0,
-            draw_mesh=draw_mesh,
-            check_bounds=False,
-        )
-    if should_chunk or len(result) == 0:
-        context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
-        width, height = image.size
-        image_chunks = []
-        x_offsets = []
-        y_offsets = []
-        result = []
-
-        # If width == height, there's nothing more we can do... otherwise...
-        if width > height:
-            # Landscape - slice the image horizontally
-            fx = 0.0
-            steps = int(width * 2 / height)
-            while fx <= (width - height):
-                x = int(fx)
-                image_chunks.append(image.crop((x, 0, x + height - 1, height - 1)))
-                x_offsets.append(x)
-                y_offsets.append(0)
-                fx += (width - height) / steps
-                context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
-        elif height > width:
-            # Portrait - slice the image vertically
-            fy = 0.0
-            steps = int(height * 2 / width)
-            while fy <= (height - width):
-                y = int(fy)
-                image_chunks.append(image.crop((0, y, width - 1, y + width - 1)))
-                x_offsets.append(0)
-                y_offsets.append(y)
-                fy += (height - width) / steps
-                context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
-
-        for idx in range(len(image_chunks)):
-            context.services.logger.info(f"FaceTools --> Evaluating faces in chunk {idx}")
-            result = result + generate_face_box_mask(
-                context=context,
-                minimum_confidence=minimum_confidence,
-                x_offset=x_offset,
-                y_offset=y_offset,
-                pil_image=image_chunks[idx],
-                chunk_x_offset=x_offsets[idx],
-                chunk_y_offset=y_offsets[idx],
-                draw_mesh=draw_mesh,
-            )
-
-        if len(result) == 0:
-            # Give up
-            context.services.logger.warning(
-                "FaceTools --> No face detected in chunked input image. Passing through original image."
-            )
-
-    all_faces = prepare_faces_list(result)
-
-    return all_faces
-
-
-@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.1")
-class FaceOffInvocation(BaseInvocation):
-    """Bound, extract, and mask a face from an image using MediaPipe detection"""
-
-    image: ImageField = InputField(description="Image for face detection")
-    face_id: int = InputField(
-        default=0,
-        ge=0,
-        description="The face ID to process, numbered from 0. Multiple faces not supported. Find a face's ID with FaceIdentifier node.",
-    )
-    minimum_confidence: float = InputField(
-        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
-    )
-    x_offset: float = InputField(default=0.0, description="X-axis offset of the mask")
-    y_offset: float = InputField(default=0.0, description="Y-axis offset of the mask")
-    padding: int = InputField(default=0, description="All-axis padding around the mask in pixels")
-    chunk: bool = InputField(
-        default=False,
-        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
-    )
-
-    def faceoff(self, context: InvocationContext, image: ImageType) -> Optional[ExtractFaceData]:
-        all_faces = get_faces_list(
-            context=context,
-            image=image,
-            should_chunk=self.chunk,
-            minimum_confidence=self.minimum_confidence,
-            x_offset=self.x_offset,
-            y_offset=self.y_offset,
-            draw_mesh=True,
-        )
-
-        if len(all_faces) == 0:
-            context.services.logger.warning("FaceOff --> No faces detected. Passing through original image.")
-            return None
-
-        if self.face_id > len(all_faces) - 1:
-            context.services.logger.warning(
-                f"FaceOff --> Face ID {self.face_id} is outside of the number of faces detected ({len(all_faces)}). Passing through original image."
-            )
-            return None
-
-        face_data = extract_face(context=context, image=image, face=all_faces[self.face_id], padding=self.padding)
-        # Convert the input image to RGBA mode to ensure it has an alpha channel.
-        face_data["bounded_image"] = face_data["bounded_image"].convert("RGBA")
-
-        return face_data
-
-    def invoke(self, context: InvocationContext) -> FaceOffOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        result = self.faceoff(context=context, image=image)
-
-        if result is None:
-            result_image = image
-            result_mask = create_white_image(*image.size)
-            x = 0
-            y = 0
-        else:
-            result_image = result["bounded_image"]
-            result_mask = result["bounded_mask"]
-            x = result["x_min"]
-            y = result["y_min"]
-
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
-        )
-
-        mask_dto = context.services.images.create(
-            image=result_mask,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        output = FaceOffOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-            mask=ImageField(image_name=mask_dto.image_name),
-            x=x,
-            y=y,
-        )
-
-        return output
-
-
-@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.1")
-class FaceMaskInvocation(BaseInvocation):
-    """Face mask creation using mediapipe face detection"""
-
-    image: ImageField = InputField(description="Image to face detect")
-    face_ids: str = InputField(
-        default="",
-        description="Comma-separated list of face ids to mask eg '0,2,7'. Numbered from 0. Leave empty to mask all. Find face IDs with FaceIdentifier node.",
-    )
-    minimum_confidence: float = InputField(
-        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
-    )
-    x_offset: float = InputField(default=0.0, description="Offset for the X-axis of the face mask")
-    y_offset: float = InputField(default=0.0, description="Offset for the Y-axis of the face mask")
-    chunk: bool = InputField(
-        default=False,
-        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
-    )
-    invert_mask: bool = InputField(default=False, description="Toggle to invert the mask")
-
-    @validator("face_ids")
-    def validate_comma_separated_ints(cls, v) -> str:
-        comma_separated_ints_regex = re.compile(r"^\d*(,\d+)*$")
-        if comma_separated_ints_regex.match(v) is None:
-            raise ValueError('Face IDs must be a comma-separated list of integers (e.g. "1,2,3")')
-        return v
-
-    def facemask(self, context: InvocationContext, image: ImageType) -> FaceMaskResult:
-        all_faces = get_faces_list(
-            context=context,
-            image=image,
-            should_chunk=self.chunk,
-            minimum_confidence=self.minimum_confidence,
-            x_offset=self.x_offset,
-            y_offset=self.y_offset,
-            draw_mesh=True,
-        )
-
-        mask_pil = create_white_image(*image.size)
-
-        id_range = list(range(0, len(all_faces)))
-        ids_to_extract = id_range
-        if self.face_ids != "":
-            parsed_face_ids = [int(id) for id in self.face_ids.split(",")]
-            # get requested face_ids that are in range
-            intersected_face_ids = set(parsed_face_ids) & set(id_range)
-
-            if len(intersected_face_ids) == 0:
-                id_range_str = ",".join([str(id) for id in id_range])
-                context.services.logger.warning(
-                    f"Face IDs must be in range of detected faces - requested {self.face_ids}, detected {id_range_str}. Passing through original image."
-                )
-                return FaceMaskResult(
-                    image=image,  # original image
-                    mask=mask_pil,  # white mask
-                )
-
-            ids_to_extract = list(intersected_face_ids)
-
-        for face_id in ids_to_extract:
-            face_data = extract_face(context=context, image=image, face=all_faces[face_id], padding=0)
-            face_mask_pil = face_data["bounded_mask"]
-            x_min = face_data["x_min"]
-            y_min = face_data["y_min"]
-            x_max = face_data["x_max"]
-            y_max = face_data["y_max"]
-
-            mask_pil.paste(
-                create_black_image(x_max - x_min, y_max - y_min),
-                box=(x_min, y_min),
-                mask=ImageOps.invert(face_mask_pil),
-            )
-
-        if self.invert_mask:
-            mask_pil = ImageOps.invert(mask_pil)
-
-        # Create an RGBA image with transparency
-        image = image.convert("RGBA")
-
-        return FaceMaskResult(
-            image=image,
-            mask=mask_pil,
-        )
-
-    def invoke(self, context: InvocationContext) -> FaceMaskOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        result = self.facemask(context=context, image=image)
-
-        image_dto = context.services.images.create(
-            image=result["image"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
-        )
-
-        mask_dto = context.services.images.create(
-            image=result["mask"],
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.MASK,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        output = FaceMaskOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-            mask=ImageField(image_name=mask_dto.image_name),
-        )
-
-        return output
-
-
-@invocation(
-    "face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.1"
-)
-class FaceIdentifierInvocation(BaseInvocation):
-    """Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
-
-    image: ImageField = InputField(description="Image to face detect")
-    minimum_confidence: float = InputField(
-        default=0.5, description="Minimum confidence for face detection (lower if detection is failing)"
-    )
-    chunk: bool = InputField(
-        default=False,
-        description="Whether to bypass full image face detection and default to image chunking. Chunking will occur if no faces are found in the full image.",
-    )
-
-    def faceidentifier(self, context: InvocationContext, image: ImageType) -> ImageType:
-        image = image.copy()
-
-        all_faces = get_faces_list(
-            context=context,
-            image=image,
-            should_chunk=self.chunk,
-            minimum_confidence=self.minimum_confidence,
-            x_offset=0,
-            y_offset=0,
-            draw_mesh=False,
-        )
-
-        # Note - font may be found either in the repo if running an editable install, or in the venv if running a package install
-        font_path = [x for x in [Path(y, "inter/Inter-Regular.ttf") for y in font_assets.__path__] if x.exists()]
-        font = ImageFont.truetype(font_path[0].as_posix(), FONT_SIZE)
-
-        # Paste face IDs on the output image
-        draw = ImageDraw.Draw(image)
-        for face in all_faces:
-            x_coord = face["x_center"]
-            y_coord = face["y_center"]
-            text = str(face["face_id"])
-            # get bbox of the text so we can center the id on the face
-            _, _, bbox_w, bbox_h = draw.textbbox(xy=(0, 0), text=text, font=font, stroke_width=FONT_STROKE_WIDTH)
-            x = x_coord - bbox_w / 2
-            y = y_coord - bbox_h / 2
-            draw.text(
-                xy=(x, y),
-                text=str(text),
-                fill=(255, 255, 255, 255),
-                font=font,
-                stroke_width=FONT_STROKE_WIDTH,
-                stroke_fill=(0, 0, 0, 255),
-            )
-
-        # Create an RGBA image with transparency
-        image = image.convert("RGBA")
-
-        return image
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        result_image = self.faceidentifier(context=context, image=image)
-
-        image_dto = context.services.images.create(
-            image=result_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )

invokeai/app/invocations/generate.py

@@ -0,0 +1,248 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from contextlib import contextmanager, ContextDecorator
+from functools import partial
+from typing import Literal, Optional, get_args
+
+from pydantic import Field
+
+from invokeai.app.models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.generator.inpaint import infill_methods
+from .baseinvocation import BaseInvocation, InvocationConfig, InvocationContext
+from .compel import ConditioningField
+from .image import ImageOutput
+from .model import UNetField, VaeField
+from ..util.step_callback import stable_diffusion_step_callback
+from ...backend.generator import Inpaint, InvokeAIGenerator
+from ...backend.model_management.lora import ModelPatcher
+from ...backend.stable_diffusion import PipelineIntermediateState
+from ...backend.stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
+
+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"
+
+
+from .latent import get_scheduler
+
+
+class OldModelContext(ContextDecorator):
+    model: StableDiffusionGeneratorPipeline
+
+    def __init__(self, model):
+        self.model = model
+
+    def __enter__(self):
+        return self.model
+
+    def __exit__(self, *exc):
+        return False
+
+
+class OldModelInfo:
+    name: str
+    hash: str
+    context: OldModelContext
+
+    def __init__(self, name: str, hash: str, model: StableDiffusionGeneratorPipeline):
+        self.name = name
+        self.hash = hash
+        self.context = OldModelContext(
+            model=model,
+        )
+
+
+class InpaintInvocation(BaseInvocation):
+    """Generates an image using inpaint."""
+
+    type: Literal["inpaint"] = "inpaint"
+
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    seed: int = Field(
+        ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed
+    )
+    steps: int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
+    width: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The width of the resulting image",
+    )
+    height: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The height of the resulting image",
+    )
+    cfg_scale: float = Field(
+        default=7.5,
+        ge=1,
+        description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt",
+    )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use")
+    unet: UNetField = Field(default=None, description="UNet model")
+    vae: VaeField = Field(default=None, description="Vae model")
+
+    # Inputs
+    image: Optional[ImageField] = Field(description="The input image")
+    strength: float = Field(default=0.75, gt=0, le=1, description="The strength of the original image")
+    fit: bool = Field(
+        default=True,
+        description="Whether or not the result should be fit to the aspect ratio of the input image",
+    )
+
+    # Inputs
+    mask: Optional[ImageField] = Field(description="The mask")
+    seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
+    seam_blur: int = Field(default=16, ge=0, description="The seam inpaint blur radius (px)")
+    seam_strength: float = Field(default=0.75, gt=0, le=1, description="The seam inpaint strength")
+    seam_steps: int = Field(default=30, ge=1, description="The number of steps to use for seam inpaint")
+    tile_size: int = Field(default=32, ge=1, description="The tile infill method size (px)")
+    infill_method: INFILL_METHODS = Field(
+        default=DEFAULT_INFILL_METHOD,
+        description="The method used to infill empty regions (px)",
+    )
+    inpaint_width: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The width of the inpaint region (px)",
+    )
+    inpaint_height: Optional[int] = Field(
+        default=None,
+        multiple_of=8,
+        gt=0,
+        description="The height of the inpaint region (px)",
+    )
+    inpaint_fill: Optional[ColorField] = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The solid infill method color",
+    )
+    inpaint_replace: float = Field(
+        default=0.0,
+        ge=0.0,
+        le=1.0,
+        description="The amount by which to replace masked areas with latent noise",
+    )
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"tags": ["stable-diffusion", "image"], "title": "Inpaint"},
+        }
+
+    def dispatch_progress(
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.model_dump(),
+            source_node_id=source_node_id,
+        )
+
+    def get_conditioning(self, context, unet):
+        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        c = positive_cond_data.conditionings[0].embeds.to(device=unet.device, dtype=unet.dtype)
+        extra_conditioning_info = positive_cond_data.conditionings[0].extra_conditioning
+
+        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        uc = negative_cond_data.conditionings[0].embeds.to(device=unet.device, dtype=unet.dtype)
+
+        return (uc, c, extra_conditioning_info)
+
+    @contextmanager
+    def load_model_old_way(self, context, scheduler):
+        def _lora_loader():
+            for lora in self.unet.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}),
+                    context=context,
+                )
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
+
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.model_dump(),
+            context=context,
+        )
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.model_dump(),
+            context=context,
+        )
+
+        with vae_info as vae, ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()), unet_info as unet:
+            device = context.services.model_manager.mgr.cache.execution_device
+            dtype = context.services.model_manager.mgr.cache.precision
+
+            vae.to(dtype=unet.dtype)
+
+            pipeline = StableDiffusionGeneratorPipeline(
+                vae=vae,
+                text_encoder=None,
+                tokenizer=None,
+                unet=unet,
+                scheduler=scheduler,
+                safety_checker=None,
+                feature_extractor=None,
+                requires_safety_checker=False,
+            )
+
+            yield OldModelInfo(
+                name=self.unet.unet.model_name,
+                hash="<NO-HASH>",
+                model=pipeline,
+            )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = None if self.image is None else context.services.images.get_pil_image(self.image.image_name)
+        mask = None if self.mask is None else context.services.images.get_pil_image(self.mask.image_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]
+
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
+        )
+
+        with self.load_model_old_way(context, scheduler) as model:
+            conditioning = self.get_conditioning(context, model.context.model.unet)
+
+            outputs = Inpaint(model).generate(
+                conditioning=conditioning,
+                scheduler=scheduler,
+                init_image=image,
+                mask_image=mask,
+                step_callback=partial(self.dispatch_progress, context, source_node_id),
+                **self.dict(
+                    exclude={"positive_conditioning", "negative_conditioning", "scheduler", "image", "mask"}
+                ),  # Shorthand for passing all of the parameters above manually
+            )
+
+            # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
+            # each time it is called. We only need the first one.
+            generator_output = next(outputs)
+
+            image_dto = context.services.images.create(
+                image=generator_output.image,
+                image_origin=ResourceOrigin.INTERNAL,
+                image_category=ImageCategory.GENERAL,
+                session_id=context.graph_execution_state_id,
+                node_id=self.id,
+                is_intermediate=self.is_intermediate,
+            )
+
+            return ImageOutput(
+                image=ImageField(image_name=image_dto.image_name),
+                width=image_dto.width,
+                height=image_dto.height,
+            )

invokeai/app/invocations/infill.py

@@ -1,24 +1,29 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 
-import math
 from typing import Literal, Optional, get_args
 
 import numpy as np
+import math
 from PIL import Image, ImageOps
+from pydantic import Field
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
+from invokeai.app.invocations.image import ImageOutput
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
-from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
-from invokeai.backend.image_util.lama import LaMA
 from invokeai.backend.image_util.patchmatch import PatchMatch
 
-from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
-from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
+from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationConfig,
+    InvocationContext,
+)
 
 
 def infill_methods() -> list[str]:
-    methods = ["tile", "solid", "lama", "cv2"]
+    methods = [
+        "tile",
+        "solid",
+    ]
     if PatchMatch.patchmatch_available():
         methods.insert(0, "patchmatch")
     return methods
@@ -28,11 +33,6 @@ INFILL_METHODS = Literal[tuple(infill_methods())]
 DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
-def infill_lama(im: Image.Image) -> Image.Image:
-    lama = LaMA()
-    return lama(im)
-
-
 def infill_patchmatch(im: Image.Image) -> Image.Image:
     if im.mode != "RGBA":
         return im
@@ -47,10 +47,6 @@ def infill_patchmatch(im: Image.Image) -> Image.Image:
     return im_patched
 
 
-def infill_cv2(im: Image.Image) -> Image.Image:
-    return cv2_inpaint(im)
-
-
 def get_tile_images(image: np.ndarray, width=8, height=8):
     _nrows, _ncols, depth = image.shape
     _strides = image.strides
@@ -99,7 +95,7 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
         return im
 
     # Find all invalid tiles and replace with a random valid tile
-    replace_count = (tiles_mask == False).sum()  # noqa: E712
+    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), :, :, :]
 
@@ -118,16 +114,21 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
     return si
 
 
-@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
 class InfillColorInvocation(BaseInvocation):
     """Infills transparent areas of an image with a solid color"""
 
-    image: ImageField = InputField(description="The image to infill")
-    color: ColorField = InputField(
+    type: Literal["infill_rgba"] = "infill_rgba"
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
+    color: ColorField = Field(
         default=ColorField(r=127, g=127, b=127, a=255),
         description="The color to use to infill",
     )
 
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Color Infill", "tags": ["image", "inpaint", "color", "infill"]},
+        }
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
@@ -143,7 +144,6 @@ class InfillColorInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -153,19 +153,25 @@ class InfillColorInvocation(BaseInvocation):
         )
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
 class InfillTileInvocation(BaseInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
-    image: ImageField = InputField(description="The image to infill")
-    tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
-    seed: int = InputField(
+    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,
     )
 
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Tile Infill", "tags": ["image", "inpaint", "tile", "infill"]},
+        }
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
@@ -179,7 +185,6 @@ class InfillTileInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -189,97 +194,26 @@ class InfillTileInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0"
-)
 class InfillPatchMatchInvocation(BaseInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
-    image: ImageField = InputField(description="The image to infill")
-    downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
-    resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
+    type: Literal["infill_patchmatch"] = "infill_patchmatch"
+
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Patch Match Infill", "tags": ["image", "inpaint", "patchmatch", "infill"]},
+        }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name).convert("RGBA")
-
-        resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
-
-        infill_image = image.copy()
-        width = int(image.width / self.downscale)
-        height = int(image.height / self.downscale)
-        infill_image = infill_image.resize(
-            (width, height),
-            resample=resample_mode,
-        )
+        image = context.services.images.get_pil_image(self.image.image_name)
 
         if PatchMatch.patchmatch_available():
-            infilled = infill_patchmatch(infill_image)
+            infilled = infill_patchmatch(image.copy())
         else:
             raise ValueError("PatchMatch is not available on this system")
 
-        infilled = infilled.resize(
-            (image.width, image.height),
-            resample=resample_mode,
-        )
-
-        infilled.paste(image, (0, 0), mask=image.split()[-1])
-        # image.paste(infilled, (0, 0), mask=image.split()[-1])
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class LaMaInfillInvocation(BaseInvocation):
-    """Infills transparent areas of an image using the LaMa model"""
-
-    image: ImageField = InputField(description="The image to infill")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = infill_lama(image.copy())
-
-        image_dto = context.services.images.create(
-            image=infilled,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
-class CV2InfillInvocation(BaseInvocation):
-    """Infills transparent areas of an image using OpenCV Inpainting"""
-
-    image: ImageField = InputField(description="The image to infill")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        infilled = infill_cv2(image.copy())
-
         image_dto = context.services.images.create(
             image=infilled,
             image_origin=ResourceOrigin.INTERNAL,

invokeai/app/invocations/ip_adapter.py

@@ -1,103 +0,0 @@
-import os
-from builtins import float
-from typing import List, Union
-
-from pydantic import BaseModel, Field
-
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.primitives import ImageField
-from invokeai.backend.model_management.models.base import BaseModelType, ModelType
-from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
-
-
-class IPAdapterModelField(BaseModel):
-    model_name: str = Field(description="Name of the IP-Adapter model")
-    base_model: BaseModelType = Field(description="Base model")
-
-
-class CLIPVisionModelField(BaseModel):
-    model_name: str = Field(description="Name of the CLIP Vision image encoder model")
-    base_model: BaseModelType = Field(description="Base model (usually 'Any')")
-
-
-class IPAdapterField(BaseModel):
-    image: ImageField = Field(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
-    image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
-    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
-    # weight: float = Field(default=1.0, ge=0, description="The weight of the IP-Adapter.")
-    begin_step_percent: float = Field(
-        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
-    )
-    end_step_percent: float = Field(
-        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
-    )
-
-
-@invocation_output("ip_adapter_output")
-class IPAdapterOutput(BaseInvocationOutput):
-    # Outputs
-    ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
-
-
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.0.0")
-class IPAdapterInvocation(BaseInvocation):
-    """Collects IP-Adapter info to pass to other nodes."""
-
-    # Inputs
-    image: ImageField = InputField(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = InputField(
-        description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
-    )
-
-    # weight: float = InputField(default=1.0, description="The weight of the IP-Adapter.", ui_type=UIType.Float)
-    weight: Union[float, List[float]] = InputField(
-        default=1, ge=0, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
-    )
-
-    begin_step_percent: float = InputField(
-        default=0, ge=-1, le=2, description="When the IP-Adapter is first applied (% of total steps)"
-    )
-    end_step_percent: float = InputField(
-        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
-    )
-
-    def invoke(self, context: InvocationContext) -> IPAdapterOutput:
-        # Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
-        ip_adapter_info = context.services.model_manager.model_info(
-            self.ip_adapter_model.model_name, self.ip_adapter_model.base_model, ModelType.IPAdapter
-        )
-        # HACK(ryand): This is bad for a couple of reasons: 1) we are bypassing the model manager to read the model
-        # directly, and 2) we are reading from disk every time this invocation is called without caching the result.
-        # A better solution would be to store the image encoder model reference in the IP-Adapter model info, but this
-        # is currently messy due to differences between how the model info is generated when installing a model from
-        # disk vs. downloading the model.
-        image_encoder_model_id = get_ip_adapter_image_encoder_model_id(
-            os.path.join(context.services.configuration.get_config().models_path, ip_adapter_info["path"])
-        )
-        image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
-        image_encoder_model = CLIPVisionModelField(
-            model_name=image_encoder_model_name,
-            base_model=BaseModelType.Any,
-        )
-        return IPAdapterOutput(
-            ip_adapter=IPAdapterField(
-                image=self.image,
-                ip_adapter_model=self.ip_adapter_model,
-                image_encoder_model=image_encoder_model,
-                weight=self.weight,
-                begin_step_percent=self.begin_step_percent,
-                end_step_percent=self.end_step_percent,
-            ),
-        )

invokeai/app/invocations/math.py

@@ -2,283 +2,134 @@
 
 from typing import Literal
 
+from pydantic import BaseModel, Field
 import numpy as np
-from pydantic import validator
 
-from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
-
-from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, invocation
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
 
 
-@invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")
-class AddInvocation(BaseInvocation):
+class MathInvocationConfig(BaseModel):
+    """Helper class to provide all math invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_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 FloatOutput(BaseInvocationOutput):
+    """A float output"""
+
+    # fmt: off
+    type: Literal["float_output"] = "float_output"
+    param: float = Field(default=None, description="The output float")
+    # fmt: on
+
+
+class AddInvocation(BaseInvocation, MathInvocationConfig):
     """Adds two numbers"""
 
-    a: int = InputField(default=0, description=FieldDescriptions.num_1)
-    b: int = InputField(default=0, description=FieldDescriptions.num_2)
+    # 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) -> IntegerOutput:
-        return IntegerOutput(value=self.a + self.b)
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Add", "tags": ["math", "add"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a + self.b)
 
 
-@invocation("sub", title="Subtract Integers", tags=["math", "subtract"], category="math", version="1.0.0")
-class SubtractInvocation(BaseInvocation):
+class SubtractInvocation(BaseInvocation, MathInvocationConfig):
     """Subtracts two numbers"""
 
-    a: int = InputField(default=0, description=FieldDescriptions.num_1)
-    b: int = InputField(default=0, description=FieldDescriptions.num_2)
+    # 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) -> IntegerOutput:
-        return IntegerOutput(value=self.a - self.b)
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Subtract", "tags": ["math", "subtract"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a - self.b)
 
 
-@invocation("mul", title="Multiply Integers", tags=["math", "multiply"], category="math", version="1.0.0")
-class MultiplyInvocation(BaseInvocation):
+class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
     """Multiplies two numbers"""
 
-    a: int = InputField(default=0, description=FieldDescriptions.num_1)
-    b: int = InputField(default=0, description=FieldDescriptions.num_2)
+    # 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) -> IntegerOutput:
-        return IntegerOutput(value=self.a * self.b)
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Multiply", "tags": ["math", "multiply"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a * self.b)
 
 
-@invocation("div", title="Divide Integers", tags=["math", "divide"], category="math", version="1.0.0")
-class DivideInvocation(BaseInvocation):
+class DivideInvocation(BaseInvocation, MathInvocationConfig):
     """Divides two numbers"""
 
-    a: int = InputField(default=0, description=FieldDescriptions.num_1)
-    b: int = InputField(default=0, description=FieldDescriptions.num_2)
+    # 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) -> IntegerOutput:
-        return IntegerOutput(value=int(self.a / self.b))
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Divide", "tags": ["math", "divide"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=int(self.a / self.b))
 
 
-@invocation(
-    "rand_int",
-    title="Random Integer",
-    tags=["math", "random"],
-    category="math",
-    version="1.0.0",
-    use_cache=False,
-)
 class RandomIntInvocation(BaseInvocation):
     """Outputs a single random integer."""
 
-    low: int = InputField(default=0, description=FieldDescriptions.inclusive_low)
-    high: int = InputField(default=np.iinfo(np.int32).max, description=FieldDescriptions.exclusive_high)
-
-    def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=np.random.randint(self.low, self.high))
-
-
-@invocation("rand_float", title="Random Float", tags=["math", "float", "random"], category="math", version="1.0.0")
-class RandomFloatInvocation(BaseInvocation):
-    """Outputs a single random float"""
-
-    low: float = InputField(default=0.0, description=FieldDescriptions.inclusive_low)
-    high: float = InputField(default=1.0, description=FieldDescriptions.exclusive_high)
-    decimals: int = InputField(default=2, description=FieldDescriptions.decimal_places)
-
-    def invoke(self, context: InvocationContext) -> FloatOutput:
-        random_float = np.random.uniform(self.low, self.high)
-        rounded_float = round(random_float, self.decimals)
-        return FloatOutput(value=rounded_float)
-
-
-@invocation(
-    "float_to_int",
-    title="Float To Integer",
-    tags=["math", "round", "integer", "float", "convert"],
-    category="math",
-    version="1.0.0",
-)
-class FloatToIntegerInvocation(BaseInvocation):
-    """Rounds a float number to (a multiple of) an integer."""
-
-    value: float = InputField(default=0, description="The value to round")
-    multiple: int = InputField(default=1, ge=1, title="Multiple of", description="The multiple to round to")
-    method: Literal["Nearest", "Floor", "Ceiling", "Truncate"] = InputField(
-        default="Nearest", description="The method to use for rounding"
+    # 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) -> IntegerOutput:
-        if self.method == "Nearest":
-            return IntegerOutput(value=round(self.value / self.multiple) * self.multiple)
-        elif self.method == "Floor":
-            return IntegerOutput(value=np.floor(self.value / self.multiple) * self.multiple)
-        elif self.method == "Ceiling":
-            return IntegerOutput(value=np.ceil(self.value / self.multiple) * self.multiple)
-        else:  # self.method == "Truncate"
-            return IntegerOutput(value=int(self.value / self.multiple) * self.multiple)
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {"title": "Random Integer", "tags": ["math", "random", "integer"]},
+        }
 
-
-@invocation("round_float", title="Round Float", tags=["math", "round"], category="math", version="1.0.0")
-class RoundInvocation(BaseInvocation):
-    """Rounds a float to a specified number of decimal places."""
-
-    value: float = InputField(default=0, description="The float value")
-    decimals: int = InputField(default=0, description="The number of decimal places")
-
-    def invoke(self, context: InvocationContext) -> FloatOutput:
-        return FloatOutput(value=round(self.value, self.decimals))
-
-
-INTEGER_OPERATIONS = Literal[
-    "ADD",
-    "SUB",
-    "MUL",
-    "DIV",
-    "EXP",
-    "MOD",
-    "ABS",
-    "MIN",
-    "MAX",
-]
-
-
-INTEGER_OPERATIONS_LABELS = dict(
-    ADD="Add A+B",
-    SUB="Subtract A-B",
-    MUL="Multiply A*B",
-    DIV="Divide A/B",
-    EXP="Exponentiate A^B",
-    MOD="Modulus A%B",
-    ABS="Absolute Value of A",
-    MIN="Minimum(A,B)",
-    MAX="Maximum(A,B)",
-)
-
-
-@invocation(
-    "integer_math",
-    title="Integer Math",
-    tags=[
-        "math",
-        "integer",
-        "add",
-        "subtract",
-        "multiply",
-        "divide",
-        "modulus",
-        "power",
-        "absolute value",
-        "min",
-        "max",
-    ],
-    category="math",
-    version="1.0.0",
-)
-class IntegerMathInvocation(BaseInvocation):
-    """Performs integer math."""
-
-    operation: INTEGER_OPERATIONS = InputField(
-        default="ADD", description="The operation to perform", ui_choice_labels=INTEGER_OPERATIONS_LABELS
-    )
-    a: int = InputField(default=0, description=FieldDescriptions.num_1)
-    b: int = InputField(default=0, description=FieldDescriptions.num_2)
-
-    @validator("b")
-    def no_unrepresentable_results(cls, v, values):
-        if values["operation"] == "DIV" and v == 0:
-            raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "MOD" and v == 0:
-            raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "EXP" and v < 0:
-            raise ValueError("Result of exponentiation is not an integer")
-        return v
-
-    def invoke(self, context: InvocationContext) -> IntegerOutput:
-        # Python doesn't support switch statements until 3.10, but InvokeAI supports back to 3.9
-        if self.operation == "ADD":
-            return IntegerOutput(value=self.a + self.b)
-        elif self.operation == "SUB":
-            return IntegerOutput(value=self.a - self.b)
-        elif self.operation == "MUL":
-            return IntegerOutput(value=self.a * self.b)
-        elif self.operation == "DIV":
-            return IntegerOutput(value=int(self.a / self.b))
-        elif self.operation == "EXP":
-            return IntegerOutput(value=self.a**self.b)
-        elif self.operation == "MOD":
-            return IntegerOutput(value=self.a % self.b)
-        elif self.operation == "ABS":
-            return IntegerOutput(value=abs(self.a))
-        elif self.operation == "MIN":
-            return IntegerOutput(value=min(self.a, self.b))
-        else:  # self.operation == "MAX":
-            return IntegerOutput(value=max(self.a, self.b))
-
-
-FLOAT_OPERATIONS = Literal[
-    "ADD",
-    "SUB",
-    "MUL",
-    "DIV",
-    "EXP",
-    "ABS",
-    "SQRT",
-    "MIN",
-    "MAX",
-]
-
-
-FLOAT_OPERATIONS_LABELS = dict(
-    ADD="Add A+B",
-    SUB="Subtract A-B",
-    MUL="Multiply A*B",
-    DIV="Divide A/B",
-    EXP="Exponentiate A^B",
-    ABS="Absolute Value of A",
-    SQRT="Square Root of A",
-    MIN="Minimum(A,B)",
-    MAX="Maximum(A,B)",
-)
-
-
-@invocation(
-    "float_math",
-    title="Float Math",
-    tags=["math", "float", "add", "subtract", "multiply", "divide", "power", "root", "absolute value", "min", "max"],
-    category="math",
-    version="1.0.0",
-)
-class FloatMathInvocation(BaseInvocation):
-    """Performs floating point math."""
-
-    operation: FLOAT_OPERATIONS = InputField(
-        default="ADD", description="The operation to perform", ui_choice_labels=FLOAT_OPERATIONS_LABELS
-    )
-    a: float = InputField(default=0, description=FieldDescriptions.num_1)
-    b: float = InputField(default=0, description=FieldDescriptions.num_2)
-
-    @validator("b")
-    def no_unrepresentable_results(cls, v, values):
-        if values["operation"] == "DIV" and v == 0:
-            raise ValueError("Cannot divide by zero")
-        elif values["operation"] == "EXP" and values["a"] == 0 and v < 0:
-            raise ValueError("Cannot raise zero to a negative power")
-        elif values["operation"] == "EXP" and type(values["a"] ** v) is complex:
-            raise ValueError("Root operation resulted in a complex number")
-        return v
-
-    def invoke(self, context: InvocationContext) -> FloatOutput:
-        # Python doesn't support switch statements until 3.10, but InvokeAI supports back to 3.9
-        if self.operation == "ADD":
-            return FloatOutput(value=self.a + self.b)
-        elif self.operation == "SUB":
-            return FloatOutput(value=self.a - self.b)
-        elif self.operation == "MUL":
-            return FloatOutput(value=self.a * self.b)
-        elif self.operation == "DIV":
-            return FloatOutput(value=self.a / self.b)
-        elif self.operation == "EXP":
-            return FloatOutput(value=self.a**self.b)
-        elif self.operation == "SQRT":
-            return FloatOutput(value=np.sqrt(self.a))
-        elif self.operation == "ABS":
-            return FloatOutput(value=abs(self.a))
-        elif self.operation == "MIN":
-            return FloatOutput(value=min(self.a, self.b))
-        else:  # self.operation == "MAX":
-            return FloatOutput(value=max(self.a, self.b))
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/metadata.py

@@ -1,25 +1,18 @@
-from typing import Optional
+from typing import Literal, Optional, Union
 
 from pydantic import Field
 
+from ...version import __version__
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    InputField,
+    InvocationConfig,
     InvocationContext,
-    OutputField,
-    invocation,
-    invocation_output,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
-from invokeai.app.invocations.ip_adapter import IPAdapterModelField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
-from invokeai.app.invocations.primitives import ImageField
-from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
 
-from ...version import __version__
-
 
 class LoRAMetadataField(BaseModelExcludeNull):
     """LoRA metadata for an image generated in InvokeAI."""
@@ -28,18 +21,6 @@ class LoRAMetadataField(BaseModelExcludeNull):
     weight: float = Field(description="The weight of the LoRA model")
 
 
-class IPAdapterMetadataField(BaseModelExcludeNull):
-    image: ImageField = Field(description="The IP-Adapter image prompt.")
-    ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
-    weight: float = Field(description="The weight of the IP-Adapter model")
-    begin_step_percent: float = Field(
-        default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
-    )
-    end_step_percent: float = Field(
-        default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
-    )
-
-
 class CoreMetadata(BaseModelExcludeNull):
     """Core generation metadata for an image generated in InvokeAI."""
 
@@ -47,7 +28,6 @@ class CoreMetadata(BaseModelExcludeNull):
     generation_mode: str = Field(
         description="The generation mode that output this image",
     )
-    created_by: Optional[str] = Field(description="The name of the creator of the image")
     positive_prompt: str = Field(description="The positive prompt parameter")
     negative_prompt: str = Field(description="The negative prompt parameter")
     width: int = Field(description="The width parameter")
@@ -57,46 +37,40 @@ class CoreMetadata(BaseModelExcludeNull):
     cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
     steps: int = Field(description="The number of steps used for inference")
     scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: Optional[int] = Field(
-        default=None,
+    clip_skip: int = Field(
         description="The number of skipped CLIP layers",
     )
     model: MainModelField = Field(description="The main model used for inference")
     controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
-    ipAdapters: list[IPAdapterMetadataField] = Field(description="The IP Adapters used for inference")
-    t2iAdapters: list[T2IAdapterField] = Field(description="The IP Adapters used for inference")
     loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
-    vae: Optional[VAEModelField] = Field(
+    vae: Union[VAEModelField, None] = Field(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
     # Latents-to-Latents
-    strength: Optional[float] = Field(
+    strength: Union[float, None] = Field(
         default=None,
         description="The strength used for latents-to-latents",
     )
-    init_image: Optional[str] = Field(default=None, description="The name of the initial image")
+    init_image: Union[str, None] = Field(default=None, description="The name of the initial image")
 
     # SDXL
-    positive_style_prompt: Optional[str] = Field(default=None, description="The positive style prompt parameter")
-    negative_style_prompt: Optional[str] = Field(default=None, description="The negative style prompt parameter")
+    positive_style_prompt: Union[str, None] = Field(default=None, description="The positive style prompt parameter")
+    negative_style_prompt: Union[str, None] = Field(default=None, description="The negative style prompt parameter")
 
     # SDXL Refiner
-    refiner_model: Optional[MainModelField] = Field(default=None, description="The SDXL Refiner model used")
-    refiner_cfg_scale: Optional[float] = Field(
+    refiner_model: Union[MainModelField, None] = Field(default=None, description="The SDXL Refiner model used")
+    refiner_cfg_scale: Union[float, None] = Field(
         default=None,
         description="The classifier-free guidance scale parameter used for the refiner",
     )
-    refiner_steps: Optional[int] = Field(default=None, description="The number of steps used for the refiner")
-    refiner_scheduler: Optional[str] = Field(default=None, description="The scheduler used for the refiner")
-    refiner_positive_aesthetic_score: Optional[float] = Field(
+    refiner_steps: Union[int, None] = Field(default=None, description="The number of steps used for the refiner")
+    refiner_scheduler: Union[str, None] = Field(default=None, description="The scheduler used for the refiner")
+    refiner_aesthetic_store: Union[float, None] = Field(
         default=None, description="The aesthetic score used for the refiner"
     )
-    refiner_negative_aesthetic_score: Optional[float] = Field(
-        default=None, description="The aesthetic score used for the refiner"
-    )
-    refiner_start: Optional[float] = Field(default=None, description="The start value used for refiner denoising")
+    refiner_start: Union[float, None] = Field(default=None, description="The start value used for refiner denoising")
 
 
 class ImageMetadata(BaseModelExcludeNull):
@@ -109,106 +83,73 @@ class ImageMetadata(BaseModelExcludeNull):
     graph: Optional[dict] = Field(default=None, description="The graph that created the image")
 
 
-@invocation_output("metadata_accumulator_output")
 class MetadataAccumulatorOutput(BaseInvocationOutput):
     """The output of the MetadataAccumulator node"""
 
-    metadata: CoreMetadata = OutputField(description="The core metadata for the image")
+    type: Literal["metadata_accumulator_output"] = "metadata_accumulator_output"
+
+    metadata: CoreMetadata = Field(description="The core metadata for the image")
 
 
-@invocation(
-    "metadata_accumulator", title="Metadata Accumulator", tags=["metadata"], category="metadata", version="1.0.0"
-)
 class MetadataAccumulatorInvocation(BaseInvocation):
     """Outputs a Core Metadata Object"""
 
-    generation_mode: str = InputField(
+    type: Literal["metadata_accumulator"] = "metadata_accumulator"
+
+    generation_mode: str = Field(
         description="The generation mode that output this image",
     )
-    positive_prompt: str = InputField(description="The positive prompt parameter")
-    negative_prompt: str = InputField(description="The negative prompt parameter")
-    width: int = InputField(description="The width parameter")
-    height: int = InputField(description="The height parameter")
-    seed: int = InputField(description="The seed used for noise generation")
-    rand_device: str = InputField(description="The device used for random number generation")
-    cfg_scale: float = InputField(description="The classifier-free guidance scale parameter")
-    steps: int = InputField(description="The number of steps used for inference")
-    scheduler: str = InputField(description="The scheduler used for inference")
-    clip_skip: Optional[int] = Field(
-        default=None,
+    positive_prompt: str = Field(description="The positive prompt parameter")
+    negative_prompt: str = Field(description="The negative prompt parameter")
+    width: int = Field(description="The width parameter")
+    height: int = Field(description="The height parameter")
+    seed: int = Field(description="The seed used for noise generation")
+    rand_device: str = Field(description="The device used for random number generation")
+    cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
+    steps: int = Field(description="The number of steps used for inference")
+    scheduler: str = Field(description="The scheduler used for inference")
+    clip_skip: int = Field(
         description="The number of skipped CLIP layers",
     )
-    model: MainModelField = InputField(description="The main model used for inference")
-    controlnets: list[ControlField] = InputField(description="The ControlNets used for inference")
-    ipAdapters: list[IPAdapterMetadataField] = InputField(description="The IP Adapters used for inference")
-    t2iAdapters: list[T2IAdapterField] = Field(description="The IP Adapters used for inference")
-    loras: list[LoRAMetadataField] = InputField(description="The LoRAs used for inference")
-    strength: Optional[float] = InputField(
+    model: MainModelField = Field(description="The main model used for inference")
+    controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
+    loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
+    strength: Union[float, None] = Field(
         default=None,
         description="The strength used for latents-to-latents",
     )
-    init_image: Optional[str] = InputField(
-        default=None,
-        description="The name of the initial image",
-    )
-    vae: Optional[VAEModelField] = InputField(
+    init_image: Union[str, None] = Field(default=None, description="The name of the initial image")
+    vae: Union[VAEModelField, None] = Field(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
-    # High resolution fix metadata.
-    hrf_width: Optional[int] = InputField(
-        description="The high resolution fix height and width multipler.",
-    )
-    hrf_height: Optional[int] = InputField(
-        description="The high resolution fix height and width multipler.",
-    )
-    hrf_strength: Optional[float] = InputField(
-        default=None,
-        description="The high resolution fix img2img strength used in the upscale pass.",
-    )
-
     # SDXL
-    positive_style_prompt: Optional[str] = InputField(
-        default=None,
-        description="The positive style prompt parameter",
-    )
-    negative_style_prompt: Optional[str] = InputField(
-        default=None,
-        description="The negative style prompt parameter",
-    )
+    positive_style_prompt: Union[str, None] = Field(default=None, description="The positive style prompt parameter")
+    negative_style_prompt: Union[str, None] = Field(default=None, description="The negative style prompt parameter")
 
     # SDXL Refiner
-    refiner_model: Optional[MainModelField] = InputField(
-        default=None,
-        description="The SDXL Refiner model used",
-    )
-    refiner_cfg_scale: Optional[float] = InputField(
+    refiner_model: Union[MainModelField, None] = Field(default=None, description="The SDXL Refiner model used")
+    refiner_cfg_scale: Union[float, None] = Field(
         default=None,
         description="The classifier-free guidance scale parameter used for the refiner",
     )
-    refiner_steps: Optional[int] = InputField(
-        default=None,
-        description="The number of steps used for the refiner",
-    )
-    refiner_scheduler: Optional[str] = InputField(
-        default=None,
-        description="The scheduler used for the refiner",
-    )
-    refiner_positive_aesthetic_score: Optional[float] = InputField(
-        default=None,
-        description="The aesthetic score used for the refiner",
-    )
-    refiner_negative_aesthetic_score: Optional[float] = InputField(
-        default=None,
-        description="The aesthetic score used for the refiner",
-    )
-    refiner_start: Optional[float] = InputField(
-        default=None,
-        description="The start value used for refiner denoising",
+    refiner_steps: Union[int, None] = Field(default=None, description="The number of steps used for the refiner")
+    refiner_scheduler: Union[str, None] = Field(default=None, description="The scheduler used for the refiner")
+    refiner_aesthetic_store: Union[float, None] = Field(
+        default=None, description="The aesthetic score used for the refiner"
     )
+    refiner_start: Union[float, None] = Field(default=None, description="The start value used for refiner denoising")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Metadata Accumulator",
+                "tags": ["image", "metadata", "generation"],
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.dict()))
+        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.model_dump()))

invokeai/app/invocations/model.py

@@ -1,21 +1,10 @@
 import copy
-from typing import List, Optional
+from typing import List, Literal, Optional, Union
 
 from pydantic import BaseModel, Field
 
 from ...backend.model_management import BaseModelType, ModelType, SubModelType
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIType,
-    invocation,
-    invocation_output,
-)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 
 
 class ModelInfo(BaseModel):
@@ -33,7 +22,6 @@ class UNetField(BaseModel):
     unet: ModelInfo = Field(description="Info to load unet submodel")
     scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
     loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
-    seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
 
 
 class ClipField(BaseModel):
@@ -46,16 +34,18 @@ class ClipField(BaseModel):
 class VaeField(BaseModel):
     # TODO: better naming?
     vae: ModelInfo = Field(description="Info to load vae submodel")
-    seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
 
 
-@invocation_output("model_loader_output")
 class ModelLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
-    unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
-    clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP")
-    vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    # fmt: off
+    type: Literal["model_loader_output"] = "model_loader_output"
+
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
 
 
 class MainModelField(BaseModel):
@@ -73,13 +63,24 @@ class LoRAModelField(BaseModel):
     base_model: BaseModelType = Field(description="Base model")
 
 
-@invocation("main_model_loader", title="Main Model", tags=["model"], category="model", version="1.0.0")
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
-    model: MainModelField = InputField(description=FieldDescriptions.main_model, input=Input.Direct)
+    type: Literal["main_model_loader"] = "main_model_loader"
+
+    model: MainModelField = Field(description="The model to load")
     # TODO: precision?
 
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Model Loader",
+                "tags": ["model", "loader"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
     def invoke(self, context: InvocationContext) -> ModelLoaderOutput:
         base_model = self.model.base_model
         model_name = self.model.model_name
@@ -154,6 +155,22 @@ class MainModelLoaderInvocation(BaseInvocation):
                 loras=[],
                 skipped_layers=0,
             ),
+            clip2=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
             vae=VaeField(
                 vae=ModelInfo(
                     model_name=model_name,
@@ -165,26 +182,36 @@ class MainModelLoaderInvocation(BaseInvocation):
         )
 
 
-@invocation_output("lora_loader_output")
 class LoraLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
-    unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    # fmt: off
+    type: Literal["lora_loader_output"] = "lora_loader_output"
+
+    unet: Optional[UNetField] = Field(default=None, description="UNet submodel")
+    clip: Optional[ClipField] = Field(default=None, description="Tokenizer and text_encoder submodels")
+    # fmt: on
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.0")
 class LoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
-    lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
-    weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
-    unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
-    )
-    clip: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP"
-    )
+    type: Literal["lora_loader"] = "lora_loader"
+
+    lora: Union[LoRAModelField, None] = Field(default=None, description="Lora model name")
+    weight: float = Field(default=0.75, description="With what weight to apply lora")
+
+    unet: Optional[UNetField] = Field(description="UNet model for applying lora")
+    clip: Optional[ClipField] = Field(description="Clip model for applying lora")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Lora Loader",
+                "tags": ["lora", "loader"],
+                "type_hints": {"lora": "lora_model"},
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
         if self.lora is None:
@@ -235,30 +262,38 @@ class LoraLoaderInvocation(BaseInvocation):
         return output
 
 
-@invocation_output("sdxl_lora_loader_output")
 class SDXLLoraLoaderOutput(BaseInvocationOutput):
-    """SDXL LoRA Loader Output"""
+    """Model loader output"""
 
-    unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
-    clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
-    clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
+    # fmt: off
+    type: Literal["sdxl_lora_loader_output"] = "sdxl_lora_loader_output"
+
+    unet: Optional[UNetField] = Field(default=None, description="UNet submodel")
+    clip: Optional[ClipField] = Field(default=None, description="Tokenizer and text_encoder submodels")
+    clip2: Optional[ClipField] = Field(default=None, description="Tokenizer2 and text_encoder2 submodels")
+    # fmt: on
 
 
-@invocation("sdxl_lora_loader", title="SDXL LoRA", tags=["lora", "model"], category="model", version="1.0.0")
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
-    lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
-    weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
-    unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
-    )
-    clip: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1"
-    )
-    clip2: Optional[ClipField] = InputField(
-        default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2"
-    )
+    type: Literal["sdxl_lora_loader"] = "sdxl_lora_loader"
+
+    lora: Union[LoRAModelField, None] = Field(default=None, description="Lora model name")
+    weight: float = Field(default=0.75, description="With what weight to apply lora")
+
+    unet: Optional[UNetField] = Field(description="UNet model for applying lora")
+    clip: Optional[ClipField] = Field(description="Clip model for applying lora")
+    clip2: Optional[ClipField] = Field(description="Clip2 model for applying lora")
+
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "SDXL Lora Loader",
+                "tags": ["lora", "loader"],
+                "type_hints": {"lora": "lora_model"},
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> SDXLLoraLoaderOutput:
         if self.lora is None:
@@ -331,20 +366,32 @@ class VAEModelField(BaseModel):
     base_model: BaseModelType = Field(description="Base model")
 
 
-@invocation_output("vae_loader_output")
 class VaeLoaderOutput(BaseInvocationOutput):
-    """VAE output"""
+    """Model loader output"""
 
-    vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    # fmt: off
+    type: Literal["vae_loader_output"] = "vae_loader_output"
+
+    vae: VaeField = Field(default=None, description="Vae model")
+    # fmt: on
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
 class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
-    vae_model: VAEModelField = InputField(
-        description=FieldDescriptions.vae_model, input=Input.Direct, ui_type=UIType.VaeModel, title="VAE"
-    )
+    type: Literal["vae_loader"] = "vae_loader"
+
+    vae_model: VAEModelField = Field(description="The VAE to load")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "VAE Loader",
+                "tags": ["vae", "loader"],
+                "type_hints": {"vae_model": "vae_model"},
+            },
+        }
 
     def invoke(self, context: InvocationContext) -> VaeLoaderOutput:
         base_model = self.vae_model.base_model
@@ -366,44 +413,3 @@ class VaeLoaderInvocation(BaseInvocation):
                 )
             )
         )
-
-
-@invocation_output("seamless_output")
-class SeamlessModeOutput(BaseInvocationOutput):
-    """Modified Seamless Model output"""
-
-    unet: Optional[UNetField] = OutputField(description=FieldDescriptions.unet, title="UNet")
-    vae: Optional[VaeField] = OutputField(description=FieldDescriptions.vae, title="VAE")
-
-
-@invocation("seamless", title="Seamless", tags=["seamless", "model"], category="model", version="1.0.0")
-class SeamlessModeInvocation(BaseInvocation):
-    """Applies the seamless transformation to the Model UNet and VAE."""
-
-    unet: Optional[UNetField] = InputField(
-        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
-    )
-    vae: Optional[VaeField] = InputField(
-        default=None, description=FieldDescriptions.vae_model, input=Input.Connection, title="VAE"
-    )
-    seamless_y: bool = InputField(default=True, input=Input.Any, description="Specify whether Y axis is seamless")
-    seamless_x: bool = InputField(default=True, input=Input.Any, description="Specify whether X axis is seamless")
-
-    def invoke(self, context: InvocationContext) -> SeamlessModeOutput:
-        # Conditionally append 'x' and 'y' based on seamless_x and seamless_y
-        unet = copy.deepcopy(self.unet)
-        vae = copy.deepcopy(self.vae)
-
-        seamless_axes_list = []
-
-        if self.seamless_x:
-            seamless_axes_list.append("x")
-        if self.seamless_y:
-            seamless_axes_list.append("y")
-
-        if unet is not None:
-            unet.seamless_axes = seamless_axes_list
-        if vae is not None:
-            vae.seamless_axes = seamless_axes_list
-
-        return SeamlessModeOutput(unet=unet, vae=vae)

invokeai/app/invocations/noise.py

@@ -1,22 +1,19 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
 
+import math
+from typing import Literal
 
+from pydantic import Field, field_validator
 import torch
-from pydantic import validator
-
 from invokeai.app.invocations.latent import LatentsField
-from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
 from ...backend.util.devices import choose_torch_device, torch_dtype
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
-    InputField,
+    InvocationConfig,
     InvocationContext,
-    OutputField,
-    invocation,
-    invocation_output,
 )
 
 """
@@ -61,51 +58,66 @@ Nodes
 """
 
 
-@invocation_output("noise_output")
 class NoiseOutput(BaseInvocationOutput):
     """Invocation noise output"""
 
-    noise: LatentsField = OutputField(default=None, description=FieldDescriptions.noise)
-    width: int = OutputField(description=FieldDescriptions.width)
-    height: int = OutputField(description=FieldDescriptions.height)
+    # 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, seed: int):
+def build_noise_output(latents_name: str, latents: torch.Tensor):
     return NoiseOutput(
-        noise=LatentsField(latents_name=latents_name, seed=seed),
+        noise=LatentsField(latents_name=latents_name),
         width=latents.size()[3] * 8,
         height=latents.size()[2] * 8,
     )
 
 
-@invocation("noise", title="Noise", tags=["latents", "noise"], category="latents", version="1.0.0")
 class NoiseInvocation(BaseInvocation):
     """Generates latent noise."""
 
-    seed: int = InputField(
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed: int = Field(
         ge=0,
         le=SEED_MAX,
-        description=FieldDescriptions.seed,
+        description="The seed to use",
         default_factory=get_random_seed,
     )
-    width: int = InputField(
+    width: int = Field(
         default=512,
         multiple_of=8,
         gt=0,
-        description=FieldDescriptions.width,
+        description="The width of the resulting noise",
     )
-    height: int = InputField(
+    height: int = Field(
         default=512,
         multiple_of=8,
         gt=0,
-        description=FieldDescriptions.height,
+        description="The height of the resulting noise",
     )
-    use_cpu: bool = InputField(
+    use_cpu: bool = Field(
         default=True,
         description="Use CPU for noise generation (for reproducible results across platforms)",
     )
 
-    @validator("seed", pre=True)
+    # Schema customisation
+    class Config(InvocationConfig):
+        json_schema_extra = {
+            "ui": {
+                "title": "Noise",
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    @field_validator("seed", pre=True)
     def modulo_seed(cls, v):
         """Returns the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
         return v % (SEED_MAX + 1)
@@ -120,4 +132,4 @@ class NoiseInvocation(BaseInvocation):
         )
         name = f"{context.graph_execution_state_id}__{self.id}"
         context.services.latents.save(name, noise)
-        return build_noise_output(latents_name=name, latents=noise, seed=self.seed)
+        return build_noise_output(latents_name=name, latents=noise)