feat(ui): experimental dynamic prompts in js

.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/style-checks.yml

@@ -1,4 +1,6 @@
 name: style checks
+# just formatting and flake8 for now
+# TODO: add isort 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 flake8 Flake8-pyproject
 
-      - run: isort --check-only .
+      # - run: isort --check-only .
       - run: black --check .
       - 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

@@ -15,10 +15,3 @@ repos:
     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.
 

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

@@ -35,17 +35,18 @@ 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.
 
 ### Running Tests
 
@@ -75,20 +76,6 @@ pytest --cov; open ./coverage/html/index.html
 
     ![html-detail](../assets/contributing/html-detail.png)
 
-### Reloading Changes
-
-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.
-
-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.
-
-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.
-
-
 ## Front End
 
 <!--#TODO: get input from blessedcoolant here, for the moment inserted the frontend README via snippets extension.-->

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](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: 
 
@@ -30,10 +23,60 @@ 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.
@@ -42,7 +85,6 @@ For frontend related work, **@pyschedelicious** is the best person to reach out
 
 For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.
 
-
 ## **What does the Code of Conduct mean for me?**
 
 Our [Code of Conduct](CODE_OF_CONDUCT.md)  means that you are responsible for treating everyone on the project with respect and courtesy regardless of their identity. If you are the victim of any inappropriate behavior or comments as described in our Code of Conduct, we are here for you and will do the best to ensure that the abuser is reprimanded appropriately, per our code.

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

@@ -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

@@ -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:
 
@@ -117,6 +117,8 @@ 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.
 
 

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/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/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)

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]

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
 
@@ -287,7 +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
@@ -296,14 +296,13 @@ 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)
 
-1. Create a fork of the InvokeAI repository through the GitHub UI or [this link](https://github.com/invoke-ai/InvokeAI/fork) 
 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.
 
 2. Activate the InvokeAI virtual environment as per step (4) of the manual
 installation protocol (important!)

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/INSTALLATION.md

@@ -17,32 +17,14 @@ 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
+#### [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](060_INSTALL_PATCHMATCH.md)
   - [XFormers](070_INSTALL_XFORMERS.md)
   - [CUDA and ROCm Drivers](030_INSTALL_CUDA_AND_ROCM.md)
@@ -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

@@ -1,86 +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.
-
-## UI 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 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 
-
-
-## 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

@@ -2,13 +2,17 @@
 
 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. 
 
-## Community Nodes
+## Disclaimer
+
+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.
+
+## List of Nodes
 
 ### FaceTools
 
@@ -22,7 +26,8 @@ To use a community workflow, download the the `.json` node graph file and load i
 ![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.
@@ -30,172 +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
-
---------------------------------
-### 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)
-
---------------------------------
-### Enhance Image (simple adjustments)
-
-**Description:** 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.
-
-Color inversion is toggled with a simple switch, while each of the four enhancer modes are activated by entering a value other than 1 in each corresponding input field. Values less than 1 will reduce the corresponding property, while values greater than 1 will enhance it.
-
-**Node Link:** https://github.com/dwringer/image-enhance-node
-
-**Example Usage:**
-![enhance image usage graph](https://raw.githubusercontent.com/dwringer/image-enhance-node/main/image_enhance_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 4 Nodes:
-- *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.
-- *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.
-- *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.
-
-**Node Link:** https://github.com/dwringer/composition-nodes
-
-**Example Usage:**
-![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_nodes_usage.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)
-
---------------------------------
-
 ### Example Node Template
 
 **Description:** This node allows you to do super cool things with InvokeAI.
@@ -208,12 +47,7 @@ Results after using the depth controlnet
 
 ![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

@@ -1,101 +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|
-|OpenCV Inpaint 			| Simple inpaint using opencv.|
-|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|
-|Upscale (RealESRGAN) 			| Upscales an image using RealESRGAN.|
-|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.|
-|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|
-|VAE Loader 			| Loads a VAE model, outputting a VaeLoaderOutput|
-|Zoe (Depth) Processor 			| Applies Zoe depth processing to image|

docs/nodes/exampleWorkflows.md

@@ -1,13 +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)ß
-

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/main.py

@@ -5,7 +5,6 @@ InvokeAI Installer
 import argparse
 import os
 from pathlib import Path
-
 from installer import Installer
 
 if __name__ == "__main__":

invokeai/app/api/dependencies.py

@@ -1,35 +1,34 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import sqlite3
 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
 
 
@@ -68,32 +67,22 @@ 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 +124,18 @@ 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

@@ -1,19 +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.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):
@@ -55,7 +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")
 

invokeai/app/api/routers/images.py

@@ -1,17 +1,20 @@
 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 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"])

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
 

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, order_id=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: str = 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: str = 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

@@ -9,7 +9,13 @@ from pydantic.fields import Field
 # Importing * is bad karma but needed here for node detection
 from ...invocations import *  # noqa: F401 F403
 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 +29,12 @@ 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 +42,6 @@ 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 +63,6 @@ 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 +83,6 @@ 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 +115,6 @@ 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 +148,6 @@ 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 +178,6 @@ 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 +209,6 @@ 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 +247,8 @@ 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 +260,7 @@ 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 +268,6 @@ 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

@@ -13,22 +13,24 @@ class SocketIO:
 
     def __init__(self, app: FastAPI):
         self.__sio = SocketManager(app=app)
+        self.__sio.on("subscribe", handler=self._handle_sub)
+        self.__sio.on("unsubscribe", handler=self._handle_unsub)
 
-        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 +1,46 @@
-from .services.config import InvokeAIAppConfig
+# Copyright (c) 2022-2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+import asyncio
+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
+
+from .services.config import InvokeAIAppConfig
+from ..backend.util.logging import InvokeAILogger
+
+from invokeai.version.invokeai_version import __version__
+
+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, _InputField, _OutputField, UIConfigBase
+
+import torch
+import invokeai.backend.util.hotfixes  # noqa: F401 (monkeypatching on import)
+
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
+
 
-# 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 logging
-    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)
-
-
 logger = InvokeAILogger.getLogger(config=app_config)
 
+
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
 mimetypes.add_type("application/javascript", ".js")
@@ -91,8 +89,6 @@ 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")
@@ -103,8 +99,6 @@ 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?
@@ -128,7 +122,6 @@ def custom_openapi():
 
     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
 
         # TODO: note that we assume the schema_key here is the TYPE.__name__
@@ -137,8 +130,8 @@ def custom_openapi():
 
     # 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
+    for schema_key, output_schema in ui_config_schemas["definitions"].items():
+        openapi_schema["components"]["schemas"][schema_key] = output_schema
 
     # Add a reference to the output type to additionalProperties of the invoker schema
     for invoker in all_invocations:
@@ -147,8 +140,8 @@ 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
 
@@ -214,17 +207,6 @@ 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.getLogger(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}")

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
 
 

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

invokeai/app/cli_app.py

@@ -1,67 +1,67 @@
-# 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
+from invokeai.backend.util.logging import InvokeAILogger
+from invokeai.version.invokeai_version import __version__
+
+
+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  # noqa: F401 (monkeypatching on import)
+
+if torch.backends.mps.is_available():
+    import invokeai.backend.util.mps_fixes  # noqa: F401 (monkeypatching on import)
+
 
-# 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.
 config = InvokeAIAppConfig.get_config()
 config.parse_args()
-
-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)
-
-
 logger = InvokeAILogger().getLogger(config=config)
 
 
@@ -252,18 +252,19 @@ 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(
@@ -305,13 +306,12 @@ 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)

invokeai/app/invocations/baseinvocation.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-import json
-import re
 from abc import ABC, abstractmethod
 from enum import Enum
 from inspect import signature
@@ -13,7 +11,6 @@ from typing import (
     Any,
     Callable,
     ClassVar,
-    Literal,
     Mapping,
     Optional,
     Type,
@@ -23,21 +20,14 @@ from typing import (
     get_type_hints,
 )
 
-import semver
-from pydantic import BaseModel, Field, validator
-from pydantic.fields import ModelField, Undefined
+from pydantic import BaseModel, Field
+from pydantic.fields import Undefined
 from pydantic.typing import NoArgAnyCallable
 
-from invokeai.app.services.config.invokeai_config import InvokeAIAppConfig
-
 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"
@@ -81,9 +71,6 @@ class FieldDescriptions:
     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"
@@ -112,39 +99,24 @@ class UIType(str, Enum):
     """
 
     # region Primitives
+    Integer = "integer"
+    Float = "float"
     Boolean = "boolean"
-    Color = "ColorField"
+    String = "string"
+    Array = "array"
+    Image = "ImageField"
+    Latents = "LatentsField"
     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"
+    Color = "ColorField"
     ImageCollection = "ImageCollection"
-    IntegerCollection = "IntegerCollection"
+    ConditioningCollection = "ConditioningCollection"
+    ColorCollection = "ColorCollection"
     LatentsCollection = "LatentsCollection"
+    IntegerCollection = "IntegerCollection"
+    FloatCollection = "FloatCollection"
     StringCollection = "StringCollection"
-    # endregion
-
-    # region Polymorphic Primitives
-    BooleanPolymorphic = "BooleanPolymorphic"
-    ColorPolymorphic = "ColorPolymorphic"
-    ConditioningPolymorphic = "ConditioningPolymorphic"
-    ControlPolymorphic = "ControlPolymorphic"
-    FloatPolymorphic = "FloatPolymorphic"
-    ImagePolymorphic = "ImagePolymorphic"
-    IntegerPolymorphic = "IntegerPolymorphic"
-    LatentsPolymorphic = "LatentsPolymorphic"
-    StringPolymorphic = "StringPolymorphic"
+    BooleanCollection = "BooleanCollection"
     # endregion
 
     # region Models
@@ -166,11 +138,8 @@ class UIType(str, Enum):
     # endregion
 
     # region Misc
+    FilePath = "FilePath"
     Enum = "enum"
-    Scheduler = "Scheduler"
-    WorkflowField = "WorkflowField"
-    IsIntermediate = "IsIntermediate"
-    MetadataField = "MetadataField"
     # endregion
 
 
@@ -197,9 +166,6 @@ class _InputField(BaseModel):
     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):
@@ -212,7 +178,6 @@ class _OutputField(BaseModel):
 
     ui_hidden: bool
     ui_type: Optional[UIType]
-    ui_order: Optional[int]
 
 
 def InputField(
@@ -246,9 +211,6 @@ def InputField(
     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:
     """
@@ -275,11 +237,6 @@ def InputField(
       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,
@@ -312,9 +269,6 @@ def InputField(
         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,
     )
 
@@ -348,7 +302,6 @@ def OutputField(
     repr: bool = True,
     ui_type: Optional[UIType] = None,
     ui_hidden: bool = False,
-    ui_order: Optional[int] = None,
     **kwargs: Any,
 ) -> Any:
     """
@@ -365,8 +318,6 @@ def OutputField(
       `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,
@@ -397,7 +348,6 @@ def OutputField(
         repr=repr,
         ui_type=ui_type,
         ui_hidden=ui_hidden,
-        ui_order=ui_order,
         **kwargs,
     )
 
@@ -405,38 +355,28 @@ def OutputField(
 class UIConfigBase(BaseModel):
     """
     Provides additional node configuration to the UI.
-    This is used internally by the @invocation decorator logic. Do not use this directly.
+    This is used internally by the @tags and @title decorator logic. You probably want to use those
+    decorators, though you may add this class to a node definition to specify the title and tags.
     """
 
-    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".'
-    )
+    tags: Optional[list[str]] = Field(default_factory=None, description="The tags to display in the UI")
+    title: Optional[str] = Field(default=None, description="The display name of the node")
 
 
 class InvocationContext:
-    """Initialized and provided to on execution of invocations."""
-
     services: InvocationServices
     graph_execution_state_id: str
-    queue_id: str
-    queue_item_id: str
 
-    def __init__(self, services: InvocationServices, queue_id: str, queue_item_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
 
 
 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):
@@ -449,13 +389,6 @@ 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."""
@@ -472,16 +405,15 @@ class MissingInputException(Exception):
 
 
 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:
@@ -489,23 +421,7 @@ 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):
@@ -526,9 +442,6 @@ class BaseInvocation(ABC, BaseModel):
         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)
@@ -536,13 +449,6 @@ class BaseInvocation(ABC, BaseModel):
                 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:
@@ -577,152 +483,39 @@ class BaseInvocation(ABC, BaseModel):
                     raise RequiredConnectionException(self.__fields__["type"].default, field_name)
                 elif _input == Input.Any:
                     raise MissingInputException(self.__fields__["type"].default, field_name)
+        return self.invoke(context)
 
-        # 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(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."
-    )
+    id: str = InputField(description="The id of this node. Must be unique among all nodes.")
     is_intermediate: bool = InputField(
-        default=False, description="Whether or not this is an intermediate invocation.", ui_type=UIType.IsIntermediate
+        default=False, description="Whether or not this node is an intermediate node.", input=Input.Direct
     )
-    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]]
 
 
-GenericBaseInvocation = TypeVar("GenericBaseInvocation", bound=BaseInvocation)
+T = TypeVar("T", bound=BaseInvocation)
 
 
-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.
+def title(title: str) -> Callable[[Type[T]], Type[T]]:
+    """Adds a title to the invocation. Use this to override the default title generation, which is based on the class name."""
 
-    :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.
-    """
-
-    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
+    def wrapper(cls: Type[T]) -> Type[T]:
         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})
+        cls.UIConfig.title = title
         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})
+def tags(*tags: str) -> Callable[[Type[T]], Type[T]]:
+    """Adds tags to the invocation. Use this to improve the streamline finding the invocation in the UI."""
 
+    def wrapper(cls: Type[T]) -> Type[T]:
+        uiconf_name = cls.__qualname__ + ".UIConfig"
+        if not hasattr(cls, "UIConfig") or cls.UIConfig.__qualname__ != uiconf_name:
+            cls.UIConfig = type(uiconf_name, (UIConfigBase,), dict())
+        cls.UIConfig.tags = list(tags)
         return cls
 
     return wrapper

invokeai/app/invocations/collections.py

@@ -1,5 +1,6 @@
 # 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
@@ -7,15 +8,17 @@ from pydantic import validator
 from invokeai.app.invocations.primitives import IntegerCollectionOutput
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, tags, title
 
 
-@invocation(
-    "range", title="Integer Range", tags=["collection", "integer", "range"], category="collections", version="1.0.0"
-)
+@title("Integer Range")
+@tags("collection", "integer", "range")
 class RangeInvocation(BaseInvocation):
     """Creates a range of numbers from start to stop with step"""
 
+    type: Literal["range"] = "range"
+
+    # Inputs
     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")
@@ -30,37 +33,30 @@ class RangeInvocation(BaseInvocation):
         return IntegerCollectionOutput(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",
-)
+@title("Integer Range of Size")
+@tags("range", "integer", "size", "collection")
 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"""
 
+    type: Literal["range_of_size"] = "range_of_size"
+
+    # Inputs
     start: int = InputField(default=0, description="The start of the range")
-    size: int = InputField(default=1, gt=0, description="The number of values")
+    size: int = InputField(default=1, description="The number of values")
     step: int = InputField(default=1, description="The step of the range")
 
     def invoke(self, context: InvocationContext) -> IntegerCollectionOutput:
-        return IntegerCollectionOutput(
-            collection=list(range(self.start, self.start + (self.step * self.size), self.step))
-        )
+        return IntegerCollectionOutput(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,
-)
+@title("Random Range")
+@tags("range", "integer", "random", "collection")
 class RandomRangeInvocation(BaseInvocation):
     """Creates a collection of random numbers"""
 
+    type: Literal["random_range"] = "random_range"
+
+    # Inputs
     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")

invokeai/app/invocations/compel.py

@@ -1,19 +1,20 @@
 import re
 from dataclasses import dataclass
-from typing import List, Union
+from typing import List, Literal, Union
 
 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.shared_invokeai_diffusion import (
     BasicConditioningInfo,
     SDXLConditioningInfo,
 )
 
+from ...backend.model_management.models import ModelType
 from ...backend.model_management.lora import ModelPatcher
-from ...backend.model_management.models import ModelNotFoundException, ModelType
+from ...backend.model_management.models import ModelNotFoundException
 from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
 from ...backend.util.devices import torch_dtype
 from .baseinvocation import (
@@ -25,8 +26,8 @@ from .baseinvocation import (
     InvocationContext,
     OutputField,
     UIComponent,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 from .model import ClipField
 
@@ -43,10 +44,13 @@ class ConditioningFieldData:
 #    PerpNeg = "perp_neg"
 
 
-@invocation("compel", title="Prompt", tags=["prompt", "compel"], category="conditioning", version="1.0.0")
+@title("Compel Prompt")
+@tags("prompt", "compel")
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
 
+    type: Literal["compel"] = "compel"
+
     prompt: str = InputField(
         default="",
         description=FieldDescriptions.compel_prompt,
@@ -112,15 +116,16 @@ class CompelInvocation(BaseInvocation):
                 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 = InvokeAIDiffuserComponent.ExtraConditioningInfo(
                 tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
@@ -226,16 +231,17 @@ class SDXLPromptInvocationBase:
                 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)
@@ -261,16 +267,13 @@ class SDXLPromptInvocationBase:
         return c, c_pooled, ec
 
 
-@invocation(
-    "sdxl_compel_prompt",
-    title="SDXL Prompt",
-    tags=["sdxl", "compel", "prompt"],
-    category="conditioning",
-    version="1.0.0",
-)
+@title("SDXL Compel Prompt")
+@tags("sdxl", "compel", "prompt")
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
+    type: Literal["sdxl_compel_prompt"] = "sdxl_compel_prompt"
+
     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="")
@@ -279,8 +282,8 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     crop_left: int = InputField(default=0, description="")
     target_width: int = InputField(default=1024, description="")
     target_height: int = InputField(default=1024, description="")
-    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
-    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
+    clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -302,29 +305,6 @@ 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(
@@ -346,16 +326,13 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         )
 
 
-@invocation(
-    "sdxl_refiner_compel_prompt",
-    title="SDXL Refiner Prompt",
-    tags=["sdxl", "compel", "prompt"],
-    category="conditioning",
-    version="1.0.0",
-)
+@title("SDXL Refiner Compel Prompt")
+@tags("sdxl", "compel", "prompt")
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
+    type: Literal["sdxl_refiner_compel_prompt"] = "sdxl_refiner_compel_prompt"
+
     style: str = InputField(
         default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea
     )  # TODO: ?
@@ -397,17 +374,20 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
         )
 
 
-@invocation_output("clip_skip_output")
 class ClipSkipInvocationOutput(BaseInvocationOutput):
     """Clip skip node output"""
 
+    type: Literal["clip_skip_output"] = "clip_skip_output"
     clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
 
 
-@invocation("clip_skip", title="CLIP Skip", tags=["clipskip", "clip", "skip"], category="conditioning", version="1.0.0")
+@title("CLIP Skip")
+@tags("clipskip", "clip", "skip")
 class ClipSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
 
+    type: Literal["clip_skip"] = "clip_skip"
+
     clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
     skipped_layers: int = InputField(default=0, description=FieldDescriptions.skipped_layers)
 

invokeai/app/invocations/controlnet_image_processors.py

@@ -28,21 +28,23 @@ from pydantic import BaseModel, Field, validator
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 
+
 from ...backend.model_management import BaseModelType
 from ..models.image import ImageCategory, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     FieldDescriptions,
-    Input,
     InputField,
+    Input,
     InvocationContext,
     OutputField,
     UIType,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 
+
 CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
 CONTROLNET_RESIZE_VALUES = Literal[
     "just_resize",
@@ -85,20 +87,27 @@ class ControlField(BaseModel):
         return v
 
 
-@invocation_output("control_output")
 class ControlOutput(BaseInvocationOutput):
     """node output for ControlNet info"""
 
+    type: Literal["control_output"] = "control_output"
+
     # Outputs
     control: ControlField = OutputField(description=FieldDescriptions.control)
 
 
-@invocation("controlnet", title="ControlNet", tags=["controlnet"], category="controlnet", version="1.0.0")
+@title("ControlNet")
+@tags("controlnet")
 class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
 
+    type: Literal["controlnet"] = "controlnet"
+
+    # Inputs
     image: ImageField = InputField(description="The control image")
-    control_model: ControlNetModelField = InputField(description=FieldDescriptions.controlnet_model, input=Input.Direct)
+    control_model: ControlNetModelField = InputField(
+        default="lllyasviel/sd-controlnet-canny", description=FieldDescriptions.controlnet_model, input=Input.Direct
+    )
     control_weight: Union[float, List[float]] = InputField(
         default=1.0, description="The weight given to the ControlNet", ui_type=UIType.Float
     )
@@ -125,12 +134,12 @@ class ControlNetInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "image_processor", title="Base Image Processor", tags=["controlnet"], category="controlnet", version="1.0.0"
-)
 class ImageProcessorInvocation(BaseInvocation):
     """Base class for invocations that preprocess images for ControlNet"""
 
+    type: Literal["image_processor"] = "image_processor"
+
+    # Inputs
     image: ImageField = InputField(description="The image to process")
 
     def run_processor(self, image):
@@ -142,6 +151,11 @@ 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(
@@ -151,7 +165,6 @@ 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"""
@@ -166,16 +179,14 @@ class ImageProcessorInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "canny_image_processor",
-    title="Canny Processor",
-    tags=["controlnet", "canny"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Canny Processor")
+@tags("controlnet", "canny")
 class CannyImageProcessorInvocation(ImageProcessorInvocation):
     """Canny edge detection for ControlNet"""
 
+    type: Literal["canny_image_processor"] = "canny_image_processor"
+
+    # Input
     low_threshold: int = InputField(
         default=100, ge=0, le=255, description="The low threshold of the Canny pixel gradient (0-255)"
     )
@@ -189,16 +200,14 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "hed_image_processor",
-    title="HED (softedge) Processor",
-    tags=["controlnet", "hed", "softedge"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("HED (softedge) Processor")
+@tags("controlnet", "hed", "softedge")
 class HedImageProcessorInvocation(ImageProcessorInvocation):
     """Applies HED edge detection to image"""
 
+    type: Literal["hed_image_processor"] = "hed_image_processor"
+
+    # Inputs
     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 not supported in controlnet_aux v0.0.3
@@ -218,16 +227,14 @@ class HedImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "lineart_image_processor",
-    title="Lineart Processor",
-    tags=["controlnet", "lineart"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Lineart Processor")
+@tags("controlnet", "lineart")
 class LineartImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art processing to image"""
 
+    type: Literal["lineart_image_processor"] = "lineart_image_processor"
+
+    # Inputs
     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")
@@ -240,16 +247,14 @@ 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",
-)
+@title("Lineart Anime Processor")
+@tags("controlnet", "lineart", "anime")
 class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies line art anime processing to image"""
 
+    type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
+
+    # Inputs
     detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
@@ -263,16 +268,14 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "openpose_image_processor",
-    title="Openpose Processor",
-    tags=["controlnet", "openpose", "pose"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Openpose Processor")
+@tags("controlnet", "openpose", "pose")
 class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Openpose processing to image"""
 
+    type: Literal["openpose_image_processor"] = "openpose_image_processor"
+
+    # Inputs
     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)
@@ -288,16 +291,14 @@ class OpenposeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "midas_depth_image_processor",
-    title="Midas Depth Processor",
-    tags=["controlnet", "midas"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Midas (Depth) Processor")
+@tags("controlnet", "midas", "depth")
 class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Midas depth processing to image"""
 
+    type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
+
+    # Inputs
     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`")
     # depth_and_normal not supported in controlnet_aux v0.0.3
@@ -315,16 +316,14 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "normalbae_image_processor",
-    title="Normal BAE Processor",
-    tags=["controlnet"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Normal BAE Processor")
+@tags("controlnet", "normal", "bae")
 class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     """Applies NormalBae processing to image"""
 
+    type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
+
+    # Inputs
     detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
 
@@ -336,12 +335,14 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "mlsd_image_processor", title="MLSD Processor", tags=["controlnet", "mlsd"], category="controlnet", version="1.0.0"
-)
+@title("MLSD Processor")
+@tags("controlnet", "mlsd")
 class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     """Applies MLSD processing to image"""
 
+    type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
+
+    # Inputs
     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`")
@@ -359,12 +360,14 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "pidi_image_processor", title="PIDI Processor", tags=["controlnet", "pidi"], category="controlnet", version="1.0.0"
-)
+@title("PIDI Processor")
+@tags("controlnet", "pidi")
 class PidiImageProcessorInvocation(ImageProcessorInvocation):
     """Applies PIDI processing to image"""
 
+    type: Literal["pidi_image_processor"] = "pidi_image_processor"
+
+    # Inputs
     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)
@@ -382,16 +385,14 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "content_shuffle_image_processor",
-    title="Content Shuffle Processor",
-    tags=["controlnet", "contentshuffle"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Content Shuffle Processor")
+@tags("controlnet", "contentshuffle")
 class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     """Applies content shuffle processing to image"""
 
+    type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
+
+    # Inputs
     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")
@@ -412,32 +413,27 @@ 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",
-)
+@title("Zoe (Depth) Processor")
+@tags("controlnet", "zoe", "depth")
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
 
+    type: Literal["zoe_depth_image_processor"] = "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",
-)
+@title("Mediapipe Face Processor")
+@tags("controlnet", "mediapipe", "face")
 class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     """Applies mediapipe face processing to image"""
 
+    type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
+
+    # Inputs
     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")
 
@@ -451,16 +447,14 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "leres_image_processor",
-    title="Leres (Depth) Processor",
-    tags=["controlnet", "leres", "depth"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Leres (Depth) Processor")
+@tags("controlnet", "leres", "depth")
 class LeresImageProcessorInvocation(ImageProcessorInvocation):
     """Applies leres processing to image"""
 
+    type: Literal["leres_image_processor"] = "leres_image_processor"
+
+    # Inputs
     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")
@@ -480,16 +474,14 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "tile_image_processor",
-    title="Tile Resample Processor",
-    tags=["controlnet", "tile"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Tile Resample Processor")
+@tags("controlnet", "tile")
 class TileResamplerProcessorInvocation(ImageProcessorInvocation):
     """Tile resampler processor"""
 
+    type: Literal["tile_image_processor"] = "tile_image_processor"
+
+    # Inputs
     # 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")
 
@@ -520,16 +512,13 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
         return processed_image
 
 
-@invocation(
-    "segment_anything_processor",
-    title="Segment Anything Processor",
-    tags=["controlnet", "segmentanything"],
-    category="controlnet",
-    version="1.0.0",
-)
+@title("Segment Anything Processor")
+@tags("controlnet", "segmentanything")
 class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     """Applies segment anything processing to image"""
 
+    type: Literal["segment_anything_processor"] = "segment_anything_processor"
+
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(

invokeai/app/invocations/cv.py

@@ -1,20 +1,24 @@
 # 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 invokeai.app.invocations.primitives import ImageField, ImageOutput
+
 from invokeai.app.models.image import ImageCategory, ResourceOrigin
-
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, tags, title
 
 
-@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.0.0")
+@title("OpenCV Inpaint")
+@tags("opencv", "inpaint")
 class CvInpaintInvocation(BaseInvocation):
     """Simple inpaint using opencv."""
 
+    type: Literal["cv_inpaint"] = "cv_inpaint"
+
+    # Inputs
     image: ImageField = InputField(description="The image to inpaint")
     mask: ImageField = InputField(description="The mask to use when inpainting")
 
@@ -41,7 +45,6 @@ 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/image.py

@@ -8,18 +8,23 @@ import numpy
 from PIL import Image, ImageChops, ImageFilter, ImageOps
 
 from invokeai.app.invocations.metadata import CoreMetadata
-from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
+from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
 from ..models.image import ImageCategory, ResourceOrigin
-from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, tags, title
 
 
-@invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")
+@title("Show Image")
+@tags("image")
 class ShowImageInvocation(BaseInvocation):
-    """Displays a provided image using the OS image viewer, and passes it forward in the pipeline."""
+    """Displays a provided image, and passes it forward in the pipeline."""
 
+    # Metadata
+    type: Literal["show_image"] = "show_image"
+
+    # Inputs
     image: ImageField = InputField(description="The image to show")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -36,39 +41,15 @@ class ShowImageInvocation(BaseInvocation):
         )
 
 
-@invocation("blank_image", title="Blank Image", tags=["image"], category="image", version="1.0.0")
-class BlankImageInvocation(BaseInvocation):
-    """Creates a blank image and forwards it to the pipeline"""
-
-    width: int = InputField(default=512, description="The width of the image")
-    height: int = InputField(default=512, description="The height of the image")
-    mode: Literal["RGB", "RGBA"] = InputField(default="RGB", description="The mode of the image")
-    color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=255), description="The color of the image")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = Image.new(mode=self.mode, size=(self.width, self.height), color=self.color.tuple())
-
-        image_dto = context.services.images.create(
-            image=image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            session_id=context.graph_execution_state_id,
-            is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation("img_crop", title="Crop Image", tags=["image", "crop"], category="image", version="1.0.0")
+@title("Crop Image")
+@tags("image", "crop")
 class ImageCropInvocation(BaseInvocation):
     """Crops an image to a specified box. The box can be outside of the image."""
 
+    # Metadata
+    type: Literal["img_crop"] = "img_crop"
+
+    # Inputs
     image: ImageField = InputField(description="The image to crop")
     x: int = InputField(default=0, description="The left x coordinate of the crop rectangle")
     y: int = InputField(default=0, description="The top y coordinate of the crop rectangle")
@@ -88,7 +69,6 @@ class ImageCropInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -98,10 +78,15 @@ class ImageCropInvocation(BaseInvocation):
         )
 
 
-@invocation("img_paste", title="Paste Image", tags=["image", "paste"], category="image", version="1.0.1")
+@title("Paste Image")
+@tags("image", "paste")
 class ImagePasteInvocation(BaseInvocation):
     """Pastes an image into another image."""
 
+    # Metadata
+    type: Literal["img_paste"] = "img_paste"
+
+    # Inputs
     base_image: ImageField = InputField(description="The base image")
     image: ImageField = InputField(description="The image to paste")
     mask: Optional[ImageField] = InputField(
@@ -110,7 +95,6 @@ class ImagePasteInvocation(BaseInvocation):
     )
     x: int = InputField(default=0, description="The left x coordinate at which to paste the image")
     y: int = InputField(default=0, description="The top y coordinate at which to paste the image")
-    crop: bool = InputField(default=False, description="Crop to base image dimensions")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         base_image = context.services.images.get_pil_image(self.base_image.image_name)
@@ -130,10 +114,6 @@ class ImagePasteInvocation(BaseInvocation):
         new_image.paste(base_image, (abs(min_x), abs(min_y)))
         new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
 
-        if self.crop:
-            base_w, base_h = base_image.size
-            new_image = new_image.crop((abs(min_x), abs(min_y), abs(min_x) + base_w, abs(min_y) + base_h))
-
         image_dto = context.services.images.create(
             image=new_image,
             image_origin=ResourceOrigin.INTERNAL,
@@ -141,7 +121,6 @@ class ImagePasteInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -151,10 +130,15 @@ class ImagePasteInvocation(BaseInvocation):
         )
 
 
-@invocation("tomask", title="Mask from Alpha", tags=["image", "mask"], category="image", version="1.0.0")
+@title("Mask from Alpha")
+@tags("image", "mask")
 class MaskFromAlphaInvocation(BaseInvocation):
     """Extracts the alpha channel of an image as a mask."""
 
+    # Metadata
+    type: Literal["tomask"] = "tomask"
+
+    # Inputs
     image: ImageField = InputField(description="The image to create the mask from")
     invert: bool = InputField(default=False, description="Whether or not to invert the mask")
 
@@ -172,7 +156,6 @@ class MaskFromAlphaInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -182,10 +165,15 @@ class MaskFromAlphaInvocation(BaseInvocation):
         )
 
 
-@invocation("img_mul", title="Multiply Images", tags=["image", "multiply"], category="image", version="1.0.0")
+@title("Multiply Images")
+@tags("image", "multiply")
 class ImageMultiplyInvocation(BaseInvocation):
     """Multiplies two images together using `PIL.ImageChops.multiply()`."""
 
+    # Metadata
+    type: Literal["img_mul"] = "img_mul"
+
+    # Inputs
     image1: ImageField = InputField(description="The first image to multiply")
     image2: ImageField = InputField(description="The second image to multiply")
 
@@ -202,7 +190,6 @@ class ImageMultiplyInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -215,10 +202,15 @@ class ImageMultiplyInvocation(BaseInvocation):
 IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
 
 
-@invocation("img_chan", title="Extract Image Channel", tags=["image", "channel"], category="image", version="1.0.0")
+@title("Extract Image Channel")
+@tags("image", "channel")
 class ImageChannelInvocation(BaseInvocation):
     """Gets a channel from an image."""
 
+    # Metadata
+    type: Literal["img_chan"] = "img_chan"
+
+    # Inputs
     image: ImageField = InputField(description="The image to get the channel from")
     channel: IMAGE_CHANNELS = InputField(default="A", description="The channel to get")
 
@@ -234,7 +226,6 @@ class ImageChannelInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -247,10 +238,15 @@ class ImageChannelInvocation(BaseInvocation):
 IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
 
 
-@invocation("img_conv", title="Convert Image Mode", tags=["image", "convert"], category="image", version="1.0.0")
+@title("Convert Image Mode")
+@tags("image", "convert")
 class ImageConvertInvocation(BaseInvocation):
     """Converts an image to a different mode."""
 
+    # Metadata
+    type: Literal["img_conv"] = "img_conv"
+
+    # Inputs
     image: ImageField = InputField(description="The image to convert")
     mode: IMAGE_MODES = InputField(default="L", description="The mode to convert to")
 
@@ -266,7 +262,6 @@ class ImageConvertInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -276,10 +271,15 @@ class ImageConvertInvocation(BaseInvocation):
         )
 
 
-@invocation("img_blur", title="Blur Image", tags=["image", "blur"], category="image", version="1.0.0")
+@title("Blur Image")
+@tags("image", "blur")
 class ImageBlurInvocation(BaseInvocation):
     """Blurs an image"""
 
+    # Metadata
+    type: Literal["img_blur"] = "img_blur"
+
+    # Inputs
     image: ImageField = InputField(description="The image to blur")
     radius: float = InputField(default=8.0, ge=0, description="The blur radius")
     # Metadata
@@ -300,7 +300,6 @@ class ImageBlurInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -330,17 +329,19 @@ PIL_RESAMPLING_MAP = {
 }
 
 
-@invocation("img_resize", title="Resize Image", tags=["image", "resize"], category="image", version="1.0.0")
+@title("Resize Image")
+@tags("image", "resize")
 class ImageResizeInvocation(BaseInvocation):
     """Resizes an image to specific dimensions"""
 
+    # Metadata
+    type: Literal["img_resize"] = "img_resize"
+
+    # Inputs
     image: ImageField = InputField(description="The image to resize")
-    width: int = InputField(default=512, gt=0, description="The width to resize to (px)")
-    height: int = InputField(default=512, gt=0, description="The height to resize to (px)")
+    width: int = InputField(default=512, ge=64, multiple_of=8, description="The width to resize to (px)")
+    height: int = InputField(default=512, ge=64, multiple_of=8, description="The height to resize to (px)")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
-    metadata: Optional[CoreMetadata] = InputField(
-        default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
-    )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
@@ -359,8 +360,6 @@ class ImageResizeInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -370,10 +369,15 @@ class ImageResizeInvocation(BaseInvocation):
         )
 
 
-@invocation("img_scale", title="Scale Image", tags=["image", "scale"], category="image", version="1.0.0")
+@title("Scale Image")
+@tags("image", "scale")
 class ImageScaleInvocation(BaseInvocation):
     """Scales an image by a factor"""
 
+    # Metadata
+    type: Literal["img_scale"] = "img_scale"
+
+    # Inputs
     image: ImageField = InputField(description="The image to scale")
     scale_factor: float = InputField(
         default=2.0,
@@ -401,7 +405,6 @@ class ImageScaleInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -411,10 +414,15 @@ class ImageScaleInvocation(BaseInvocation):
         )
 
 
-@invocation("img_lerp", title="Lerp Image", tags=["image", "lerp"], category="image", version="1.0.0")
+@title("Lerp Image")
+@tags("image", "lerp")
 class ImageLerpInvocation(BaseInvocation):
     """Linear interpolation of all pixels of an image"""
 
+    # Metadata
+    type: Literal["img_lerp"] = "img_lerp"
+
+    # Inputs
     image: ImageField = InputField(description="The image to lerp")
     min: int = InputField(default=0, ge=0, le=255, description="The minimum output value")
     max: int = InputField(default=255, ge=0, le=255, description="The maximum output value")
@@ -434,7 +442,6 @@ class ImageLerpInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -444,10 +451,15 @@ class ImageLerpInvocation(BaseInvocation):
         )
 
 
-@invocation("img_ilerp", title="Inverse Lerp Image", tags=["image", "ilerp"], category="image", version="1.0.0")
+@title("Inverse Lerp Image")
+@tags("image", "ilerp")
 class ImageInverseLerpInvocation(BaseInvocation):
     """Inverse linear interpolation of all pixels of an image"""
 
+    # Metadata
+    type: Literal["img_ilerp"] = "img_ilerp"
+
+    # Inputs
     image: ImageField = InputField(description="The image to lerp")
     min: int = InputField(default=0, ge=0, le=255, description="The minimum input value")
     max: int = InputField(default=255, ge=0, le=255, description="The maximum input value")
@@ -467,7 +479,6 @@ class ImageInverseLerpInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -477,10 +488,15 @@ class ImageInverseLerpInvocation(BaseInvocation):
         )
 
 
-@invocation("img_nsfw", title="Blur NSFW Image", tags=["image", "nsfw"], category="image", version="1.0.0")
+@title("Blur NSFW Image")
+@tags("image", "nsfw")
 class ImageNSFWBlurInvocation(BaseInvocation):
     """Add blur to NSFW-flagged images"""
 
+    # Metadata
+    type: Literal["img_nsfw"] = "img_nsfw"
+
+    # Inputs
     image: ImageField = InputField(description="The image to check")
     metadata: Optional[CoreMetadata] = InputField(
         default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
@@ -506,7 +522,6 @@ class ImageNSFWBlurInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
             metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -522,12 +537,15 @@ class ImageNSFWBlurInvocation(BaseInvocation):
         return caution.resize((caution.width // 2, caution.height // 2))
 
 
-@invocation(
-    "img_watermark", title="Add Invisible Watermark", tags=["image", "watermark"], category="image", version="1.0.0"
-)
+@title("Add Invisible Watermark")
+@tags("image", "watermark")
 class ImageWatermarkInvocation(BaseInvocation):
     """Add an invisible watermark to an image"""
 
+    # Metadata
+    type: Literal["img_watermark"] = "img_watermark"
+
+    # Inputs
     image: ImageField = InputField(description="The image to check")
     text: str = InputField(default="InvokeAI", description="Watermark text")
     metadata: Optional[CoreMetadata] = InputField(
@@ -545,7 +563,6 @@ class ImageWatermarkInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
             metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -555,10 +572,14 @@ class ImageWatermarkInvocation(BaseInvocation):
         )
 
 
-@invocation("mask_edge", title="Mask Edge", tags=["image", "mask", "inpaint"], category="image", version="1.0.0")
+@title("Mask Edge")
+@tags("image", "mask", "inpaint")
 class MaskEdgeInvocation(BaseInvocation):
     """Applies an edge mask to an image"""
 
+    type: Literal["mask_edge"] = "mask_edge"
+
+    # Inputs
     image: ImageField = InputField(description="The image to apply the mask to")
     edge_size: int = InputField(description="The size of the edge")
     edge_blur: int = InputField(description="The amount of blur on the edge")
@@ -568,7 +589,7 @@ class MaskEdgeInvocation(BaseInvocation):
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        mask = context.services.images.get_pil_image(self.image.image_name).convert("L")
+        mask = context.services.images.get_pil_image(self.image.image_name)
 
         npimg = numpy.asarray(mask, dtype=numpy.uint8)
         npgradient = numpy.uint8(255 * (1.0 - numpy.floor(numpy.abs(0.5 - numpy.float32(npimg) / 255.0) * 2.0)))
@@ -590,7 +611,6 @@ class MaskEdgeInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -600,12 +620,14 @@ class MaskEdgeInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "mask_combine", title="Combine Masks", tags=["image", "mask", "multiply"], category="image", version="1.0.0"
-)
+@title("Combine Mask")
+@tags("image", "mask", "multiply")
 class MaskCombineInvocation(BaseInvocation):
     """Combine two masks together by multiplying them using `PIL.ImageChops.multiply()`."""
 
+    type: Literal["mask_combine"] = "mask_combine"
+
+    # Inputs
     mask1: ImageField = InputField(description="The first mask to combine")
     mask2: ImageField = InputField(description="The second image to combine")
 
@@ -622,7 +644,6 @@ class MaskCombineInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -632,13 +653,17 @@ class MaskCombineInvocation(BaseInvocation):
         )
 
 
-@invocation("color_correct", title="Color Correct", tags=["image", "color"], category="image", version="1.0.0")
+@title("Color Correct")
+@tags("image", "color")
 class ColorCorrectInvocation(BaseInvocation):
     """
     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.
     """
 
+    type: Literal["color_correct"] = "color_correct"
+
+    # Inputs
     image: ImageField = InputField(description="The image to color-correct")
     reference: ImageField = InputField(description="Reference image for color-correction")
     mask: Optional[ImageField] = InputField(default=None, description="Mask to use when applying color-correction")
@@ -705,13 +730,8 @@ class ColorCorrectInvocation(BaseInvocation):
         # Blur the mask out (into init image) by specified amount
         if self.mask_blur_radius > 0:
             nm = numpy.asarray(pil_init_mask, dtype=numpy.uint8)
-            inverted_nm = 255 - nm
-            dilation_size = int(round(self.mask_blur_radius) + 20)
-            dilating_kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (dilation_size, dilation_size))
-            inverted_dilated_nm = cv2.dilate(inverted_nm, dilating_kernel)
-            dilated_nm = 255 - inverted_dilated_nm
             nmd = cv2.erode(
-                dilated_nm,
+                nm,
                 kernel=numpy.ones((3, 3), dtype=numpy.uint8),
                 iterations=int(self.mask_blur_radius / 2),
             )
@@ -732,7 +752,6 @@ class ColorCorrectInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -742,10 +761,14 @@ class ColorCorrectInvocation(BaseInvocation):
         )
 
 
-@invocation("img_hue_adjust", title="Adjust Image Hue", tags=["image", "hue"], category="image", version="1.0.0")
+@title("Image Hue Adjustment")
+@tags("image", "hue", "hsl")
 class ImageHueAdjustmentInvocation(BaseInvocation):
     """Adjusts the Hue of an image."""
 
+    type: Literal["img_hue_adjust"] = "img_hue_adjust"
+
+    # Inputs
     image: ImageField = InputField(description="The image to adjust")
     hue: int = InputField(default=0, description="The degrees by which to rotate the hue, 0-360")
 
@@ -771,7 +794,6 @@ class ImageHueAdjustmentInvocation(BaseInvocation):
             node_id=self.id,
             is_intermediate=self.is_intermediate,
             session_id=context.graph_execution_state_id,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -783,224 +805,99 @@ class ImageHueAdjustmentInvocation(BaseInvocation):
         )
 
 
-COLOR_CHANNELS = Literal[
-    "Red (RGBA)",
-    "Green (RGBA)",
-    "Blue (RGBA)",
-    "Alpha (RGBA)",
-    "Cyan (CMYK)",
-    "Magenta (CMYK)",
-    "Yellow (CMYK)",
-    "Black (CMYK)",
-    "Hue (HSV)",
-    "Saturation (HSV)",
-    "Value (HSV)",
-    "Luminosity (LAB)",
-    "A (LAB)",
-    "B (LAB)",
-    "Y (YCbCr)",
-    "Cb (YCbCr)",
-    "Cr (YCbCr)",
-]
+@title("Image Luminosity Adjustment")
+@tags("image", "luminosity", "hsl")
+class ImageLuminosityAdjustmentInvocation(BaseInvocation):
+    """Adjusts the Luminosity (Value) of an image."""
 
-CHANNEL_FORMATS = {
-    "Red (RGBA)": ("RGBA", 0),
-    "Green (RGBA)": ("RGBA", 1),
-    "Blue (RGBA)": ("RGBA", 2),
-    "Alpha (RGBA)": ("RGBA", 3),
-    "Cyan (CMYK)": ("CMYK", 0),
-    "Magenta (CMYK)": ("CMYK", 1),
-    "Yellow (CMYK)": ("CMYK", 2),
-    "Black (CMYK)": ("CMYK", 3),
-    "Hue (HSV)": ("HSV", 0),
-    "Saturation (HSV)": ("HSV", 1),
-    "Value (HSV)": ("HSV", 2),
-    "Luminosity (LAB)": ("LAB", 0),
-    "A (LAB)": ("LAB", 1),
-    "B (LAB)": ("LAB", 2),
-    "Y (YCbCr)": ("YCbCr", 0),
-    "Cb (YCbCr)": ("YCbCr", 1),
-    "Cr (YCbCr)": ("YCbCr", 2),
-}
-
-
-@invocation(
-    "img_channel_offset",
-    title="Offset Image Channel",
-    tags=[
-        "image",
-        "offset",
-        "red",
-        "green",
-        "blue",
-        "alpha",
-        "cyan",
-        "magenta",
-        "yellow",
-        "black",
-        "hue",
-        "saturation",
-        "luminosity",
-        "value",
-    ],
-    category="image",
-    version="1.0.0",
-)
-class ImageChannelOffsetInvocation(BaseInvocation):
-    """Add or subtract a value from a specific color channel of an image."""
+    type: Literal["img_luminosity_adjust"] = "img_luminosity_adjust"
 
+    # Inputs
     image: ImageField = InputField(description="The image to adjust")
-    channel: COLOR_CHANNELS = InputField(description="Which channel to adjust")
-    offset: int = InputField(default=0, ge=-255, le=255, description="The amount to adjust the channel by")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        pil_image = context.services.images.get_pil_image(self.image.image_name)
-
-        # extract the channel and mode from the input and reference tuple
-        mode = CHANNEL_FORMATS[self.channel][0]
-        channel_number = CHANNEL_FORMATS[self.channel][1]
-
-        # Convert PIL image to new format
-        converted_image = numpy.array(pil_image.convert(mode)).astype(int)
-        image_channel = converted_image[:, :, channel_number]
-
-        # Adjust the value, clipping to 0..255
-        image_channel = numpy.clip(image_channel + self.offset, 0, 255)
-
-        # Put the channel back into the image
-        converted_image[:, :, channel_number] = image_channel
-
-        # Convert back to RGBA format and output
-        pil_image = Image.fromarray(converted_image.astype(numpy.uint8), mode=mode).convert("RGBA")
-
-        image_dto = context.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            session_id=context.graph_execution_state_id,
-            workflow=self.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation(
-    "img_channel_multiply",
-    title="Multiply Image Channel",
-    tags=[
-        "image",
-        "invert",
-        "scale",
-        "multiply",
-        "red",
-        "green",
-        "blue",
-        "alpha",
-        "cyan",
-        "magenta",
-        "yellow",
-        "black",
-        "hue",
-        "saturation",
-        "luminosity",
-        "value",
-    ],
-    category="image",
-    version="1.0.0",
-)
-class ImageChannelMultiplyInvocation(BaseInvocation):
-    """Scale a specific color channel of an image."""
-
-    image: ImageField = InputField(description="The image to adjust")
-    channel: COLOR_CHANNELS = InputField(description="Which channel to adjust")
-    scale: float = InputField(default=1.0, ge=0.0, description="The amount to scale the channel by.")
-    invert_channel: bool = InputField(default=False, description="Invert the channel after scaling")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        pil_image = context.services.images.get_pil_image(self.image.image_name)
-
-        # extract the channel and mode from the input and reference tuple
-        mode = CHANNEL_FORMATS[self.channel][0]
-        channel_number = CHANNEL_FORMATS[self.channel][1]
-
-        # Convert PIL image to new format
-        converted_image = numpy.array(pil_image.convert(mode)).astype(float)
-        image_channel = converted_image[:, :, channel_number]
-
-        # Adjust the value, clipping to 0..255
-        image_channel = numpy.clip(image_channel * self.scale, 0, 255)
-
-        # Invert the channel if requested
-        if self.invert_channel:
-            image_channel = 255 - image_channel
-
-        # Put the channel back into the image
-        converted_image[:, :, channel_number] = image_channel
-
-        # Convert back to RGBA format and output
-        pil_image = Image.fromarray(converted_image.astype(numpy.uint8), mode=mode).convert("RGBA")
-
-        image_dto = context.services.images.create(
-            image=pil_image,
-            image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
-            node_id=self.id,
-            is_intermediate=self.is_intermediate,
-            session_id=context.graph_execution_state_id,
-            workflow=self.workflow,
-        )
-
-        return ImageOutput(
-            image=ImageField(
-                image_name=image_dto.image_name,
-            ),
-            width=image_dto.width,
-            height=image_dto.height,
-        )
-
-
-@invocation(
-    "save_image",
-    title="Save Image",
-    tags=["primitives", "image"],
-    category="primitives",
-    version="1.0.0",
-    use_cache=False,
-)
-class SaveImageInvocation(BaseInvocation):
-    """Saves an image. Unlike an image primitive, this invocation stores a copy of the image."""
-
-    image: ImageField = InputField(description="The image to load")
-    metadata: CoreMetadata = InputField(
-        default=None,
-        description=FieldDescriptions.core_metadata,
-        ui_hidden=True,
+    luminosity: float = InputField(
+        default=1.0, ge=0, le=1, description="The factor by which to adjust the luminosity (value)"
     )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
+        pil_image = context.services.images.get_pil_image(self.image.image_name)
+
+        # Convert PIL image to OpenCV format (numpy array), note color channel
+        # ordering is changed from RGB to BGR
+        image = numpy.array(pil_image.convert("RGB"))[:, :, ::-1]
+
+        # Convert image to HSV color space
+        hsv_image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
+
+        # Adjust the luminosity (value)
+        hsv_image[:, :, 2] = numpy.clip(hsv_image[:, :, 2] * self.luminosity, 0, 255)
+
+        # Convert image back to BGR color space
+        image = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2BGR)
+
+        # Convert back to PIL format and to original color mode
+        pil_image = Image.fromarray(image[:, :, ::-1], "RGB").convert("RGBA")
 
         image_dto = context.services.images.create(
-            image=image,
+            image=pil_image,
             image_origin=ResourceOrigin.INTERNAL,
             image_category=ImageCategory.GENERAL,
             node_id=self.id,
-            session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
+            session_id=context.graph_execution_state_id,
         )
 
         return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
+            image=ImageField(
+                image_name=image_dto.image_name,
+            ),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+@title("Image Saturation Adjustment")
+@tags("image", "saturation", "hsl")
+class ImageSaturationAdjustmentInvocation(BaseInvocation):
+    """Adjusts the Saturation of an image."""
+
+    type: Literal["img_saturation_adjust"] = "img_saturation_adjust"
+
+    # Inputs
+    image: ImageField = InputField(description="The image to adjust")
+    saturation: float = InputField(default=1.0, ge=0, le=1, description="The factor by which to adjust the saturation")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        pil_image = context.services.images.get_pil_image(self.image.image_name)
+
+        # Convert PIL image to OpenCV format (numpy array), note color channel
+        # ordering is changed from RGB to BGR
+        image = numpy.array(pil_image.convert("RGB"))[:, :, ::-1]
+
+        # Convert image to HSV color space
+        hsv_image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
+
+        # Adjust the saturation
+        hsv_image[:, :, 1] = numpy.clip(hsv_image[:, :, 1] * self.saturation, 0, 255)
+
+        # Convert image back to BGR color space
+        image = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2BGR)
+
+        # Convert back to PIL format and to original color mode
+        pil_image = Image.fromarray(image[:, :, ::-1], "RGB").convert("RGBA")
+
+        image_dto = context.services.images.create(
+            image=pil_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            is_intermediate=self.is_intermediate,
+            session_id=context.graph_execution_state_id,
+        )
+
+        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 +1,24 @@
 # 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 invokeai.app.invocations.primitives import ImageField, ImageOutput, ColorField
 
-from invokeai.app.invocations.primitives import ColorField, ImageField, 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 .baseinvocation import BaseInvocation, InputField, InvocationContext, title, tags
 
 
 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 +28,6 @@ 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 +42,6 @@ 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 +90,7 @@ 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 is 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), :, :, :]
 
@@ -118,10 +109,14 @@ 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")
+@title("Solid Color Infill")
+@tags("image", "inpaint")
 class InfillColorInvocation(BaseInvocation):
     """Infills transparent areas of an image with a solid color"""
 
+    type: Literal["infill_rgba"] = "infill_rgba"
+
+    # Inputs
     image: ImageField = InputField(description="The image to infill")
     color: ColorField = InputField(
         default=ColorField(r=127, g=127, b=127, a=255),
@@ -143,7 +138,6 @@ class InfillColorInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -153,10 +147,14 @@ class InfillColorInvocation(BaseInvocation):
         )
 
 
-@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
+@title("Tile Infill")
+@tags("image", "inpaint")
 class InfillTileInvocation(BaseInvocation):
     """Infills transparent areas of an image with tiles of the image"""
 
+    type: Literal["infill_tile"] = "infill_tile"
+
+    # Input
     image: ImageField = InputField(description="The image to infill")
     tile_size: int = InputField(default=32, ge=1, description="The tile size (px)")
     seed: int = InputField(
@@ -179,7 +177,6 @@ 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 +186,24 @@ class InfillTileInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0"
-)
+@title("PatchMatch Infill")
+@tags("image", "inpaint")
 class InfillPatchMatchInvocation(BaseInvocation):
     """Infills transparent areas of an image using the PatchMatch algorithm"""
 
+    type: Literal["infill_patchmatch"] = "infill_patchmatch"
+
+    # Inputs
     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")
 
     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")
-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/latent.py

@@ -4,7 +4,6 @@ from contextlib import ExitStack
 from typing import List, Literal, Optional, Union
 
 import einops
-import numpy as np
 import torch
 import torchvision.transforms as T
 from diffusers.image_processor import VaeImageProcessor
@@ -21,8 +20,6 @@ from torchvision.transforms.functional import resize as tv_resize
 
 from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.invocations.primitives import (
-    DenoiseMaskField,
-    DenoiseMaskOutput,
     ImageField,
     ImageOutput,
     LatentsField,
@@ -33,9 +30,8 @@ from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.model_management.models import ModelType, SilenceWarnings
 
-from ...backend.model_management.lora import ModelPatcher
 from ...backend.model_management.models import BaseModelType
-from ...backend.model_management.seamless import set_seamless
+from ...backend.model_management.lora import ModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ConditioningData,
@@ -49,109 +45,24 @@ from ...backend.util.devices import choose_precision, choose_torch_device
 from ..models.image import ImageCategory, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
-    BaseInvocationOutput,
     FieldDescriptions,
     Input,
     InputField,
     InvocationContext,
-    OutputField,
     UIType,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 from .compel import ConditioningField
 from .controlnet_image_processors import ControlField
 from .model import ModelInfo, UNetField, VaeField
 
-if choose_torch_device() == torch.device("mps"):
-    from torch import mps
-
 DEFAULT_PRECISION = choose_precision(choose_torch_device())
 
 
 SAMPLER_NAME_VALUES = Literal[tuple(list(SCHEDULER_MAP.keys()))]
 
 
-@invocation_output("scheduler_output")
-class SchedulerOutput(BaseInvocationOutput):
-    scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
-
-
-@invocation("scheduler", title="Scheduler", tags=["scheduler"], category="latents", version="1.0.0")
-class SchedulerInvocation(BaseInvocation):
-    """Selects a scheduler."""
-
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
-    )
-
-    def invoke(self, context: InvocationContext) -> SchedulerOutput:
-        return SchedulerOutput(scheduler=self.scheduler)
-
-
-@invocation(
-    "create_denoise_mask", title="Create Denoise Mask", tags=["mask", "denoise"], category="latents", version="1.0.0"
-)
-class CreateDenoiseMaskInvocation(BaseInvocation):
-    """Creates mask for denoising model run."""
-
-    vae: VaeField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
-    image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
-    mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
-    tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
-    fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32, ui_order=4)
-
-    def prep_mask_tensor(self, mask_image):
-        if mask_image.mode != "L":
-            mask_image = mask_image.convert("L")
-        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
-        if mask_tensor.dim() == 3:
-            mask_tensor = mask_tensor.unsqueeze(0)
-        # if shape is not None:
-        #    mask_tensor = tv_resize(mask_tensor, shape, T.InterpolationMode.BILINEAR)
-        return mask_tensor
-
-    @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
-        if self.image is not None:
-            image = context.services.images.get_pil_image(self.image.image_name)
-            image = image_resized_to_grid_as_tensor(image.convert("RGB"))
-            if image.dim() == 3:
-                image = image.unsqueeze(0)
-        else:
-            image = None
-
-        mask = self.prep_mask_tensor(
-            context.services.images.get_pil_image(self.mask.image_name),
-        )
-
-        if image is not None:
-            vae_info = context.services.model_manager.get_model(
-                **self.vae.vae.dict(),
-                context=context,
-            )
-
-            img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-            masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
-            # TODO:
-            masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
-
-            masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
-            context.services.latents.save(masked_latents_name, masked_latents)
-        else:
-            masked_latents_name = None
-
-        mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
-        context.services.latents.save(mask_name, mask)
-
-        return DenoiseMaskOutput(
-            denoise_mask=DenoiseMaskField(
-                mask_name=mask_name,
-                masked_latents_name=masked_latents_name,
-            ),
-        )
-
-
 def get_scheduler(
     context: InvocationContext,
     scheduler_info: ModelInfo,
@@ -186,42 +97,36 @@ def get_scheduler(
     return scheduler
 
 
-@invocation(
-    "denoise_latents",
-    title="Denoise Latents",
-    tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
-    category="latents",
-    version="1.0.0",
-)
+@title("Denoise Latents")
+@tags("latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l")
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
 
+    type: Literal["denoise_latents"] = "denoise_latents"
+
+    # Inputs
     positive_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.positive_cond, input=Input.Connection, ui_order=0
+        description=FieldDescriptions.positive_cond, input=Input.Connection
     )
     negative_conditioning: ConditioningField = InputField(
-        description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
+        description=FieldDescriptions.negative_cond, input=Input.Connection
     )
-    noise: Optional[LatentsField] = InputField(description=FieldDescriptions.noise, input=Input.Connection, ui_order=3)
+    noise: Optional[LatentsField] = InputField(description=FieldDescriptions.noise, input=Input.Connection)
     steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
     cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, ui_type=UIType.Float, title="CFG Scale"
+        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, ui_type=UIType.Float
     )
     denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
-    )
-    unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection, title="UNet", ui_order=2)
+    scheduler: SAMPLER_NAME_VALUES = InputField(default="euler", description=FieldDescriptions.scheduler)
+    unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection)
     control: Union[ControlField, list[ControlField]] = InputField(
-        default=None,
-        description=FieldDescriptions.control,
-        input=Input.Connection,
-        ui_order=5,
+        default=None, description=FieldDescriptions.control, input=Input.Connection
     )
     latents: Optional[LatentsField] = InputField(description=FieldDescriptions.latents, input=Input.Connection)
-    denoise_mask: Optional[DenoiseMaskField] = InputField(
-        default=None, description=FieldDescriptions.mask, input=Input.Connection, ui_order=6
+    mask: Optional[ImageField] = InputField(
+        default=None,
+        description=FieldDescriptions.mask,
     )
 
     @validator("cfg_scale")
@@ -325,7 +230,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         context: InvocationContext,
         # really only need model for dtype and device
         model: StableDiffusionGeneratorPipeline,
-        control_input: Union[ControlField, List[ControlField]],
+        control_input: List[ControlField],
         latents_shape: List[int],
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
@@ -399,46 +304,52 @@ class DenoiseLatentsInvocation(BaseInvocation):
     # original idea by https://github.com/AmericanPresidentJimmyCarter
     # TODO: research more for second order schedulers timesteps
     def init_scheduler(self, scheduler, device, steps, denoising_start, denoising_end):
+        num_inference_steps = steps
         if scheduler.config.get("cpu_only", False):
-            scheduler.set_timesteps(steps, device="cpu")
+            scheduler.set_timesteps(num_inference_steps, device="cpu")
             timesteps = scheduler.timesteps.to(device=device)
         else:
-            scheduler.set_timesteps(steps, device=device)
+            scheduler.set_timesteps(num_inference_steps, device=device)
             timesteps = scheduler.timesteps
 
-        # skip greater order timesteps
-        _timesteps = timesteps[:: scheduler.order]
-
-        # get start timestep index
+        # apply denoising_start
         t_start_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_start)))
-        t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, _timesteps)))
+        t_start_idx = len(list(filter(lambda ts: ts >= t_start_val, timesteps)))
+        timesteps = timesteps[t_start_idx:]
+        if scheduler.order == 2 and t_start_idx > 0:
+            timesteps = timesteps[1:]
 
-        # get end timestep index
+        # save start timestep to apply noise
+        init_timestep = timesteps[:1]
+
+        # apply denoising_end
         t_end_val = int(round(scheduler.config.num_train_timesteps * (1 - denoising_end)))
-        t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, _timesteps[t_start_idx:])))
+        t_end_idx = len(list(filter(lambda ts: ts >= t_end_val, timesteps)))
+        if scheduler.order == 2 and t_end_idx > 0:
+            t_end_idx += 1
+        timesteps = timesteps[:t_end_idx]
 
-        # apply order to indexes
-        t_start_idx *= scheduler.order
-        t_end_idx *= scheduler.order
-
-        init_timestep = timesteps[t_start_idx : t_start_idx + 1]
-        timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
-        num_inference_steps = len(timesteps) // scheduler.order
+        # calculate step count based on scheduler order
+        num_inference_steps = len(timesteps)
+        if scheduler.order == 2:
+            num_inference_steps += num_inference_steps % 2
+            num_inference_steps = num_inference_steps // 2
 
         return num_inference_steps, timesteps, init_timestep
 
-    def prep_inpaint_mask(self, context, latents):
-        if self.denoise_mask is None:
-            return None, None
+    def prep_mask_tensor(self, mask, context, lantents):
+        if mask is None:
+            return None
 
-        mask = context.services.latents.get(self.denoise_mask.mask_name)
-        mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-        if self.denoise_mask.masked_latents_name is not None:
-            masked_latents = context.services.latents.get(self.denoise_mask.masked_latents_name)
-        else:
-            masked_latents = None
-
-        return 1 - mask, masked_latents
+        mask_image = context.services.images.get_pil_image(mask.image_name)
+        if mask_image.mode != "L":
+            # FIXME: why do we get passed an RGB image here? We can only use single-channel.
+            mask_image = mask_image.convert("L")
+        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        if mask_tensor.dim() == 3:
+            mask_tensor = mask_tensor.unsqueeze(0)
+        mask_tensor = tv_resize(mask_tensor, lantents.shape[-2:], T.InterpolationMode.BILINEAR)
+        return 1 - mask_tensor
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -453,19 +364,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 latents = context.services.latents.get(self.latents.latents_name)
                 if seed is None:
                     seed = self.latents.seed
-
-                if noise is not None and noise.shape[1:] != latents.shape[1:]:
-                    raise Exception(f"Incompatable 'noise' and 'latents' shapes: {latents.shape=} {noise.shape=}")
-
-            elif noise is not None:
-                latents = torch.zeros_like(noise)
             else:
-                raise Exception("'latents' or 'noise' must be provided!")
+                latents = torch.zeros_like(noise)
 
             if seed is None:
                 seed = 0
 
-            mask, masked_latents = self.prep_inpaint_mask(context, latents)
+            mask = self.prep_mask_tensor(self.mask, context, latents)
 
             # 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)
@@ -490,14 +395,12 @@ class DenoiseLatentsInvocation(BaseInvocation):
             )
             with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
                 unet_info.context.model, _lora_loader()
-            ), set_seamless(unet_info.context.model, self.unet.seamless_axes), unet_info as unet:
+            ), unet_info as unet:
                 latents = latents.to(device=unet.device, dtype=unet.dtype)
                 if noise is not None:
                     noise = noise.to(device=unet.device, dtype=unet.dtype)
                 if mask is not None:
                     mask = mask.to(device=unet.device, dtype=unet.dtype)
-                if masked_latents is not None:
-                    masked_latents = masked_latents.to(device=unet.device, dtype=unet.dtype)
 
                 scheduler = get_scheduler(
                     context=context,
@@ -534,7 +437,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     noise=noise,
                     seed=seed,
                     mask=mask,
-                    masked_latents=masked_latents,
                     num_inference_steps=num_inference_steps,
                     conditioning_data=conditioning_data,
                     control_data=control_data,  # list[ControlNetData]
@@ -544,20 +446,20 @@ class DenoiseLatentsInvocation(BaseInvocation):
             # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
             result_latents = result_latents.to("cpu")
             torch.cuda.empty_cache()
-            if choose_torch_device() == torch.device("mps"):
-                mps.empty_cache()
 
             name = f"{context.graph_execution_state_id}__{self.id}"
             context.services.latents.save(name, result_latents)
         return build_latents_output(latents_name=name, latents=result_latents, seed=seed)
 
 
-@invocation(
-    "l2i", title="Latents to Image", tags=["latents", "image", "vae", "l2i"], category="latents", version="1.0.0"
-)
+@title("Latents to Image")
+@tags("latents", "image", "vae")
 class LatentsToImageInvocation(BaseInvocation):
     """Generates an image from latents."""
 
+    type: Literal["l2i"] = "l2i"
+
+    # Inputs
     latents: LatentsField = InputField(
         description=FieldDescriptions.latents,
         input=Input.Connection,
@@ -583,7 +485,7 @@ class LatentsToImageInvocation(BaseInvocation):
             context=context,
         )
 
-        with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
+        with vae_info as vae:
             latents = latents.to(vae.device)
             if self.fp32:
                 vae.to(dtype=torch.float32)
@@ -617,8 +519,6 @@ class LatentsToImageInvocation(BaseInvocation):
 
             # clear memory as vae decode can request a lot
             torch.cuda.empty_cache()
-            if choose_torch_device() == torch.device("mps"):
-                mps.empty_cache()
 
             with torch.inference_mode():
                 # copied from diffusers pipeline
@@ -631,8 +531,6 @@ class LatentsToImageInvocation(BaseInvocation):
                 image = VaeImageProcessor.numpy_to_pil(np_image)[0]
 
         torch.cuda.empty_cache()
-        if choose_torch_device() == torch.device("mps"):
-            mps.empty_cache()
 
         image_dto = context.services.images.create(
             image=image,
@@ -642,7 +540,6 @@ class LatentsToImageInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
             metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -655,10 +552,14 @@ class LatentsToImageInvocation(BaseInvocation):
 LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
 
 
-@invocation("lresize", title="Resize Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
+@title("Resize Latents")
+@tags("latents", "resize")
 class ResizeLatentsInvocation(BaseInvocation):
     """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
 
+    type: Literal["lresize"] = "lresize"
+
+    # Inputs
     latents: LatentsField = InputField(
         description=FieldDescriptions.latents,
         input=Input.Connection,
@@ -692,8 +593,6 @@ class ResizeLatentsInvocation(BaseInvocation):
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         resized_latents = resized_latents.to("cpu")
         torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
 
         name = f"{context.graph_execution_state_id}__{self.id}"
         # context.services.latents.set(name, resized_latents)
@@ -701,10 +600,14 @@ class ResizeLatentsInvocation(BaseInvocation):
         return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
-@invocation("lscale", title="Scale Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
+@title("Scale Latents")
+@tags("latents", "resize")
 class ScaleLatentsInvocation(BaseInvocation):
     """Scales latents by a given factor."""
 
+    type: Literal["lscale"] = "lscale"
+
+    # Inputs
     latents: LatentsField = InputField(
         description=FieldDescriptions.latents,
         input=Input.Connection,
@@ -730,8 +633,6 @@ class ScaleLatentsInvocation(BaseInvocation):
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         resized_latents = resized_latents.to("cpu")
         torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
 
         name = f"{context.graph_execution_state_id}__{self.id}"
         # context.services.latents.set(name, resized_latents)
@@ -739,12 +640,14 @@ class ScaleLatentsInvocation(BaseInvocation):
         return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
 
 
-@invocation(
-    "i2l", title="Image to Latents", tags=["latents", "image", "vae", "i2l"], category="latents", version="1.0.0"
-)
+@title("Image to Latents")
+@tags("latents", "image", "vae")
 class ImageToLatentsInvocation(BaseInvocation):
     """Encodes an image into latents."""
 
+    type: Literal["i2l"] = "i2l"
+
+    # Inputs
     image: ImageField = InputField(
         description="The image to encode",
     )
@@ -755,11 +658,26 @@ class ImageToLatentsInvocation(BaseInvocation):
     tiled: bool = InputField(default=False, description=FieldDescriptions.tiled)
     fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
 
-    @staticmethod
-    def vae_encode(vae_info, upcast, tiled, image_tensor):
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        # image = context.services.images.get(
+        #     self.image.image_type, self.image.image_name
+        # )
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        # vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+            context=context,
+        )
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
         with vae_info as vae:
             orig_dtype = vae.dtype
-            if upcast:
+            if self.fp32:
                 vae.to(dtype=torch.float32)
 
                 use_torch_2_0_or_xformers = isinstance(
@@ -784,7 +702,7 @@ class ImageToLatentsInvocation(BaseInvocation):
                 vae.to(dtype=torch.float16)
                 # latents = latents.half()
 
-            if tiled:
+            if self.tiled:
                 vae.enable_tiling()
             else:
                 vae.disable_tiling()
@@ -798,100 +716,7 @@ class ImageToLatentsInvocation(BaseInvocation):
             latents = vae.config.scaling_factor * latents
             latents = latents.to(dtype=orig_dtype)
 
-        return latents
-
-    @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-
-        vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(),
-            context=context,
-        )
-
-        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
-        if image_tensor.dim() == 3:
-            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
-
-        latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
-
         name = f"{context.graph_execution_state_id}__{self.id}"
         latents = latents.to("cpu")
         context.services.latents.save(name, latents)
         return build_latents_output(latents_name=name, latents=latents, seed=None)
-
-
-@invocation("lblend", title="Blend Latents", tags=["latents", "blend"], category="latents", version="1.0.0")
-class BlendLatentsInvocation(BaseInvocation):
-    """Blend two latents using a given alpha. Latents must have same size."""
-
-    latents_a: LatentsField = InputField(
-        description=FieldDescriptions.latents,
-        input=Input.Connection,
-    )
-    latents_b: LatentsField = InputField(
-        description=FieldDescriptions.latents,
-        input=Input.Connection,
-    )
-    alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        latents_a = context.services.latents.get(self.latents_a.latents_name)
-        latents_b = context.services.latents.get(self.latents_b.latents_name)
-
-        if latents_a.shape != latents_b.shape:
-            raise "Latents to blend must be the same size."
-
-        # TODO:
-        device = choose_torch_device()
-
-        def slerp(t, v0, v1, DOT_THRESHOLD=0.9995):
-            """
-            Spherical linear interpolation
-            Args:
-                t (float/np.ndarray): Float value between 0.0 and 1.0
-                v0 (np.ndarray): Starting vector
-                v1 (np.ndarray): Final vector
-                DOT_THRESHOLD (float): Threshold for considering the two vectors as
-                                    colineal. Not recommended to alter this.
-            Returns:
-                v2 (np.ndarray): Interpolation vector between v0 and v1
-            """
-            inputs_are_torch = False
-            if not isinstance(v0, np.ndarray):
-                inputs_are_torch = True
-                v0 = v0.detach().cpu().numpy()
-            if not isinstance(v1, np.ndarray):
-                inputs_are_torch = True
-                v1 = v1.detach().cpu().numpy()
-
-            dot = np.sum(v0 * v1 / (np.linalg.norm(v0) * np.linalg.norm(v1)))
-            if np.abs(dot) > DOT_THRESHOLD:
-                v2 = (1 - t) * v0 + t * v1
-            else:
-                theta_0 = np.arccos(dot)
-                sin_theta_0 = np.sin(theta_0)
-                theta_t = theta_0 * t
-                sin_theta_t = np.sin(theta_t)
-                s0 = np.sin(theta_0 - theta_t) / sin_theta_0
-                s1 = sin_theta_t / sin_theta_0
-                v2 = s0 * v0 + s1 * v1
-
-            if inputs_are_torch:
-                v2 = torch.from_numpy(v2).to(device)
-
-            return v2
-
-        # blend
-        blended_latents = slerp(self.alpha, latents_a, latents_b)
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        blended_latents = blended_latents.to("cpu")
-        torch.cuda.empty_cache()
-        if device == torch.device("mps"):
-            mps.empty_cache()
-
-        name = f"{context.graph_execution_state_id}__{self.id}"
-        # context.services.latents.set(name, resized_latents)
-        context.services.latents.save(name, blended_latents)
-        return build_latents_output(latents_name=name, latents=blended_latents)

invokeai/app/invocations/math.py

@@ -3,268 +3,82 @@
 from typing import Literal
 
 import numpy as np
-from pydantic import validator
 
-from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
+from invokeai.app.invocations.primitives import IntegerOutput
 
-from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, tags, title
 
 
-@invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")
+@title("Add Integers")
+@tags("math")
 class AddInvocation(BaseInvocation):
     """Adds two numbers"""
 
+    type: Literal["add"] = "add"
+
+    # Inputs
     a: int = InputField(default=0, description=FieldDescriptions.num_1)
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=self.a + self.b)
+        return IntegerOutput(a=self.a + self.b)
 
 
-@invocation("sub", title="Subtract Integers", tags=["math", "subtract"], category="math", version="1.0.0")
+@title("Subtract Integers")
+@tags("math")
 class SubtractInvocation(BaseInvocation):
     """Subtracts two numbers"""
 
+    type: Literal["sub"] = "sub"
+
+    # Inputs
     a: int = InputField(default=0, description=FieldDescriptions.num_1)
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=self.a - self.b)
+        return IntegerOutput(a=self.a - self.b)
 
 
-@invocation("mul", title="Multiply Integers", tags=["math", "multiply"], category="math", version="1.0.0")
+@title("Multiply Integers")
+@tags("math")
 class MultiplyInvocation(BaseInvocation):
     """Multiplies two numbers"""
 
+    type: Literal["mul"] = "mul"
+
+    # Inputs
     a: int = InputField(default=0, description=FieldDescriptions.num_1)
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=self.a * self.b)
+        return IntegerOutput(a=self.a * self.b)
 
 
-@invocation("div", title="Divide Integers", tags=["math", "divide"], category="math", version="1.0.0")
+@title("Divide Integers")
+@tags("math")
 class DivideInvocation(BaseInvocation):
     """Divides two numbers"""
 
+    type: Literal["div"] = "div"
+
+    # Inputs
     a: int = InputField(default=0, description=FieldDescriptions.num_1)
     b: int = InputField(default=0, description=FieldDescriptions.num_2)
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=int(self.a / self.b))
+        return IntegerOutput(a=int(self.a / self.b))
 
 
-@invocation(
-    "rand_int",
-    title="Random Integer",
-    tags=["math", "random"],
-    category="math",
-    version="1.0.0",
-    use_cache=False,
-)
+@title("Random Integer")
+@tags("math")
 class RandomIntInvocation(BaseInvocation):
     """Outputs a single random integer."""
 
+    type: Literal["rand_int"] = "rand_int"
+
+    # Inputs
     low: int = InputField(default=0, description="The inclusive low value")
     high: int = InputField(default=np.iinfo(np.int32).max, description="The exclusive high value")
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=np.random.randint(self.low, self.high))
-
-
-@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"
-    )
-
-    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)
-
-
-@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))
+        return IntegerOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/metadata.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Literal, Optional
 
 from pydantic import Field
 
@@ -8,8 +8,8 @@ from invokeai.app.invocations.baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 from invokeai.app.invocations.controlnet_image_processors import ControlField
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
@@ -32,7 +32,6 @@ 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")
@@ -72,10 +71,10 @@ class CoreMetadata(BaseModelExcludeNull):
     )
     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_positive_aesthetic_store: Optional[float] = Field(
         default=None, description="The aesthetic score used for the refiner"
     )
-    refiner_negative_aesthetic_score: Optional[float] = Field(
+    refiner_negative_aesthetic_store: 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")
@@ -91,19 +90,21 @@ 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"""
 
+    type: Literal["metadata_accumulator_output"] = "metadata_accumulator_output"
+
     metadata: CoreMetadata = OutputField(description="The core metadata for the image")
 
 
-@invocation(
-    "metadata_accumulator", title="Metadata Accumulator", tags=["metadata"], category="metadata", version="1.0.0"
-)
+@title("Metadata Accumulator")
+@tags("metadata")
 class MetadataAccumulatorInvocation(BaseInvocation):
     """Outputs a Core Metadata Object"""
 
+    type: Literal["metadata_accumulator"] = "metadata_accumulator"
+
     generation_mode: str = InputField(
         description="The generation mode that output this image",
     )
@@ -162,11 +163,11 @@ class MetadataAccumulatorInvocation(BaseInvocation):
         default=None,
         description="The scheduler used for the refiner",
     )
-    refiner_positive_aesthetic_score: Optional[float] = InputField(
+    refiner_positive_aesthetic_store: Optional[float] = InputField(
         default=None,
         description="The aesthetic score used for the refiner",
     )
-    refiner_negative_aesthetic_score: Optional[float] = InputField(
+    refiner_negative_aesthetic_store: Optional[float] = InputField(
         default=None,
         description="The aesthetic score used for the refiner",
     )

invokeai/app/invocations/model.py

@@ -1,5 +1,5 @@
 import copy
-from typing import List, Optional
+from typing import List, Literal, Optional
 
 from pydantic import BaseModel, Field
 
@@ -8,13 +8,13 @@ from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     FieldDescriptions,
-    Input,
     InputField,
+    Input,
     InvocationContext,
     OutputField,
     UIType,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 
 
@@ -33,7 +33,6 @@ 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):
@@ -46,13 +45,13 @@ 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"""
 
+    type: Literal["model_loader_output"] = "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")
@@ -73,10 +72,14 @@ 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")
+@title("Main Model Loader")
+@tags("model")
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
+    type: Literal["main_model_loader"] = "main_model_loader"
+
+    # Inputs
     model: MainModelField = InputField(description=FieldDescriptions.main_model, input=Input.Direct)
     # TODO: precision?
 
@@ -165,18 +168,25 @@ class MainModelLoaderInvocation(BaseInvocation):
         )
 
 
-@invocation_output("lora_loader_output")
 class LoraLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
+    # fmt: off
+    type: Literal["lora_loader_output"] = "lora_loader_output"
+
     unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
     clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
+    # fmt: on
 
 
-@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.0")
+@title("LoRA Loader")
+@tags("lora", "model")
 class LoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
+    type: Literal["lora_loader"] = "lora_loader"
+
+    # Inputs
     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(
@@ -235,28 +245,34 @@ class LoraLoaderInvocation(BaseInvocation):
         return output
 
 
-@invocation_output("sdxl_lora_loader_output")
 class SDXLLoraLoaderOutput(BaseInvocationOutput):
     """SDXL LoRA Loader Output"""
 
+    # fmt: off
+    type: Literal["sdxl_lora_loader_output"] = "sdxl_lora_loader_output"
+
     unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
     clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
     clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
+    # fmt: on
 
 
-@invocation("sdxl_lora_loader", title="SDXL LoRA", tags=["lora", "model"], category="model", version="1.0.0")
+@title("SDXL LoRA Loader")
+@tags("sdxl", "lora", "model")
 class SDXLLoraLoaderInvocation(BaseInvocation):
     """Apply selected lora to unet and text_encoder."""
 
+    type: Literal["sdxl_lora_loader"] = "sdxl_lora_loader"
+
     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"
+    weight: float = Field(default=0.75, description=FieldDescriptions.lora_weight)
+    unet: Optional[UNetField] = Field(
+        default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNET"
     )
-    clip: Optional[ClipField] = InputField(
+    clip: Optional[ClipField] = Field(
         default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1"
     )
-    clip2: Optional[ClipField] = InputField(
+    clip2: Optional[ClipField] = Field(
         default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2"
     )
 
@@ -331,17 +347,23 @@ class VAEModelField(BaseModel):
     base_model: BaseModelType = Field(description="Base model")
 
 
-@invocation_output("vae_loader_output")
 class VaeLoaderOutput(BaseInvocationOutput):
-    """VAE output"""
+    """Model loader output"""
 
+    type: Literal["vae_loader_output"] = "vae_loader_output"
+
+    # Outputs
     vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
+@title("VAE Loader")
+@tags("vae", "model")
 class VaeLoaderInvocation(BaseInvocation):
     """Loads a VAE model, outputting a VaeLoaderOutput"""
 
+    type: Literal["vae_loader"] = "vae_loader"
+
+    # Inputs
     vae_model: VAEModelField = InputField(
         description=FieldDescriptions.vae_model, input=Input.Direct, ui_type=UIType.VaeModel, title="VAE"
     )
@@ -366,44 +388,3 @@ 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

@@ -1,5 +1,6 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) & the InvokeAI Team
 
+from typing import Literal
 
 import torch
 from pydantic import validator
@@ -15,8 +16,8 @@ from .baseinvocation import (
     InputField,
     InvocationContext,
     OutputField,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 
 """
@@ -61,10 +62,12 @@ Nodes
 """
 
 
-@invocation_output("noise_output")
 class NoiseOutput(BaseInvocationOutput):
     """Invocation noise output"""
 
+    type: Literal["noise_output"] = "noise_output"
+
+    # Inputs
     noise: LatentsField = OutputField(default=None, description=FieldDescriptions.noise)
     width: int = OutputField(description=FieldDescriptions.width)
     height: int = OutputField(description=FieldDescriptions.height)
@@ -78,10 +81,14 @@ def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
     )
 
 
-@invocation("noise", title="Noise", tags=["latents", "noise"], category="latents", version="1.0.0")
+@title("Noise")
+@tags("latents", "noise")
 class NoiseInvocation(BaseInvocation):
     """Generates latent noise."""
 
+    type: Literal["noise"] = "noise"
+
+    # Inputs
     seed: int = InputField(
         ge=0,
         le=SEED_MAX,

invokeai/app/invocations/onnx.py

@@ -25,14 +25,14 @@ from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
     FieldDescriptions,
-    Input,
     InputField,
+    Input,
     InvocationContext,
     OutputField,
     UIComponent,
     UIType,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 from .controlnet_image_processors import ControlField
 from .latent import SAMPLER_NAME_VALUES, LatentsField, LatentsOutput, build_latents_output, get_scheduler
@@ -56,8 +56,11 @@ ORT_TO_NP_TYPE = {
 PRECISION_VALUES = Literal[tuple(list(ORT_TO_NP_TYPE.keys()))]
 
 
-@invocation("prompt_onnx", title="ONNX Prompt (Raw)", tags=["prompt", "onnx"], category="conditioning", version="1.0.0")
+@title("ONNX Prompt (Raw)")
+@tags("onnx", "prompt")
 class ONNXPromptInvocation(BaseInvocation):
+    type: Literal["prompt_onnx"] = "prompt_onnx"
+
     prompt: str = InputField(default="", description=FieldDescriptions.raw_prompt, ui_component=UIComponent.Textarea)
     clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
 
@@ -138,16 +141,14 @@ class ONNXPromptInvocation(BaseInvocation):
 
 
 # Text to image
-@invocation(
-    "t2l_onnx",
-    title="ONNX Text to Latents",
-    tags=["latents", "inference", "txt2img", "onnx"],
-    category="latents",
-    version="1.0.0",
-)
+@title("ONNX Text to Latents")
+@tags("latents", "inference", "txt2img", "onnx")
 class ONNXTextToLatentsInvocation(BaseInvocation):
     """Generates latents from conditionings."""
 
+    type: Literal["t2l_onnx"] = "t2l_onnx"
+
+    # Inputs
     positive_conditioning: ConditioningField = InputField(
         description=FieldDescriptions.positive_cond,
         input=Input.Connection,
@@ -168,7 +169,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
         ui_type=UIType.Float,
     )
     scheduler: SAMPLER_NAME_VALUES = InputField(
-        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct, ui_type=UIType.Scheduler
+        default="euler", description=FieldDescriptions.scheduler, input=Input.Direct
     )
     precision: PRECISION_VALUES = InputField(default="tensor(float16)", description=FieldDescriptions.precision)
     unet: UNetField = InputField(
@@ -315,16 +316,14 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
 
 
 # Latent to image
-@invocation(
-    "l2i_onnx",
-    title="ONNX Latents to Image",
-    tags=["latents", "image", "vae", "onnx"],
-    category="image",
-    version="1.0.0",
-)
+@title("ONNX Latents to Image")
+@tags("latents", "image", "vae", "onnx")
 class ONNXLatentsToImageInvocation(BaseInvocation):
     """Generates an image from latents."""
 
+    type: Literal["l2i_onnx"] = "l2i_onnx"
+
+    # Inputs
     latents: LatentsField = InputField(
         description=FieldDescriptions.denoised_latents,
         input=Input.Connection,
@@ -377,7 +376,6 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
             metadata=self.metadata.dict() if self.metadata else None,
-            workflow=self.workflow,
         )
 
         return ImageOutput(
@@ -387,14 +385,17 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
         )
 
 
-@invocation_output("model_loader_output_onnx")
 class ONNXModelLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
+    # fmt: off
+    type: Literal["model_loader_output_onnx"] = "model_loader_output_onnx"
+
     unet: UNetField = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
     clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
     vae_decoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Decoder")
     vae_encoder: VaeField = OutputField(default=None, description=FieldDescriptions.vae, title="VAE Encoder")
+    # fmt: on
 
 
 class OnnxModelField(BaseModel):
@@ -405,10 +406,14 @@ class OnnxModelField(BaseModel):
     model_type: ModelType = Field(description="Model Type")
 
 
-@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
+@title("ONNX Model Loader")
+@tags("onnx", "model")
 class OnnxModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
+    type: Literal["onnx_model_loader"] = "onnx_model_loader"
+
+    # Inputs
     model: OnnxModelField = InputField(
         description=FieldDescriptions.onnx_main_model, input=Input.Direct, ui_type=UIType.ONNXModel
     )

invokeai/app/invocations/param_easing.py

@@ -3,6 +3,7 @@ from typing import Literal, Optional
 
 import matplotlib.pyplot as plt
 import numpy as np
+
 import PIL.Image
 from easing_functions import (
     BackEaseIn,
@@ -41,13 +42,17 @@ from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.primitives import FloatCollectionOutput
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, tags, title
 
 
-@invocation("float_range", title="Float Range", tags=["math", "range"], category="math", version="1.0.0")
+@title("Float Range")
+@tags("math", "range")
 class FloatLinearRangeInvocation(BaseInvocation):
     """Creates a range"""
 
+    type: Literal["float_range"] = "float_range"
+
+    # Inputs
     start: float = InputField(default=5, description="The first value of the range")
     stop: float = InputField(default=10, description="The last value of the range")
     steps: int = InputField(default=30, description="number of values to interpolate over (including start and stop)")
@@ -95,10 +100,14 @@ EASING_FUNCTION_KEYS = Literal[tuple(list(EASING_FUNCTIONS_MAP.keys()))]
 
 
 # actually I think for now could just use CollectionOutput (which is list[Any]
-@invocation("step_param_easing", title="Step Param Easing", tags=["step", "easing"], category="step", version="1.0.0")
+@title("Step Param Easing")
+@tags("step", "easing")
 class StepParamEasingInvocation(BaseInvocation):
     """Experimental per-step parameter easing for denoising steps"""
 
+    type: Literal["step_param_easing"] = "step_param_easing"
+
+    # Inputs
     easing: EASING_FUNCTION_KEYS = InputField(default="Linear", description="The easing function to use")
     num_steps: int = InputField(default=20, description="number of denoising steps")
     start_value: float = InputField(default=0.0, description="easing starting value")

invokeai/app/invocations/primitives.py

@@ -1,9 +1,9 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Optional, Tuple
+from typing import Literal, Optional, Tuple
 
-import torch
 from pydantic import BaseModel, Field
+import torch
 
 from .baseinvocation import (
     BaseInvocation,
@@ -14,8 +14,9 @@ from .baseinvocation import (
     InvocationContext,
     OutputField,
     UIComponent,
-    invocation,
-    invocation_output,
+    UIType,
+    tags,
+    title,
 )
 
 """
@@ -28,45 +29,49 @@ Primitives: Boolean, Integer, Float, String, Image, Latents, Conditioning, Color
 # region Boolean
 
 
-@invocation_output("boolean_output")
 class BooleanOutput(BaseInvocationOutput):
     """Base class for nodes that output a single boolean"""
 
-    value: bool = OutputField(description="The output boolean")
+    type: Literal["boolean_output"] = "boolean_output"
+    a: bool = OutputField(description="The output boolean")
 
 
-@invocation_output("boolean_collection_output")
 class BooleanCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of booleans"""
 
+    type: Literal["boolean_collection_output"] = "boolean_collection_output"
+
+    # Outputs
     collection: list[bool] = OutputField(
-        description="The output boolean collection",
+        default_factory=list, description="The output boolean collection", ui_type=UIType.BooleanCollection
     )
 
 
-@invocation(
-    "boolean", title="Boolean Primitive", tags=["primitives", "boolean"], category="primitives", version="1.0.0"
-)
+@title("Boolean Primitive")
+@tags("primitives", "boolean")
 class BooleanInvocation(BaseInvocation):
     """A boolean primitive value"""
 
-    value: bool = InputField(default=False, description="The boolean value")
+    type: Literal["boolean"] = "boolean"
+
+    # Inputs
+    a: bool = InputField(default=False, description="The boolean value")
 
     def invoke(self, context: InvocationContext) -> BooleanOutput:
-        return BooleanOutput(value=self.value)
+        return BooleanOutput(a=self.a)
 
 
-@invocation(
-    "boolean_collection",
-    title="Boolean Collection Primitive",
-    tags=["primitives", "boolean", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Boolean Primitive Collection")
+@tags("primitives", "boolean", "collection")
 class BooleanCollectionInvocation(BaseInvocation):
     """A collection of boolean primitive values"""
 
-    collection: list[bool] = InputField(default_factory=list, description="The collection of boolean values")
+    type: Literal["boolean_collection"] = "boolean_collection"
+
+    # Inputs
+    collection: list[bool] = InputField(
+        default=False, description="The collection of boolean values", ui_type=UIType.BooleanCollection
+    )
 
     def invoke(self, context: InvocationContext) -> BooleanCollectionOutput:
         return BooleanCollectionOutput(collection=self.collection)
@@ -77,45 +82,49 @@ class BooleanCollectionInvocation(BaseInvocation):
 # region Integer
 
 
-@invocation_output("integer_output")
 class IntegerOutput(BaseInvocationOutput):
     """Base class for nodes that output a single integer"""
 
-    value: int = OutputField(description="The output integer")
+    type: Literal["integer_output"] = "integer_output"
+    a: int = OutputField(description="The output integer")
 
 
-@invocation_output("integer_collection_output")
 class IntegerCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of integers"""
 
+    type: Literal["integer_collection_output"] = "integer_collection_output"
+
+    # Outputs
     collection: list[int] = OutputField(
-        description="The int collection",
+        default_factory=list, description="The int collection", ui_type=UIType.IntegerCollection
     )
 
 
-@invocation(
-    "integer", title="Integer Primitive", tags=["primitives", "integer"], category="primitives", version="1.0.0"
-)
+@title("Integer Primitive")
+@tags("primitives", "integer")
 class IntegerInvocation(BaseInvocation):
     """An integer primitive value"""
 
-    value: int = InputField(default=0, description="The integer value")
+    type: Literal["integer"] = "integer"
+
+    # Inputs
+    a: int = InputField(default=0, description="The integer value")
 
     def invoke(self, context: InvocationContext) -> IntegerOutput:
-        return IntegerOutput(value=self.value)
+        return IntegerOutput(a=self.a)
 
 
-@invocation(
-    "integer_collection",
-    title="Integer Collection Primitive",
-    tags=["primitives", "integer", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Integer Primitive Collection")
+@tags("primitives", "integer", "collection")
 class IntegerCollectionInvocation(BaseInvocation):
     """A collection of integer primitive values"""
 
-    collection: list[int] = InputField(default_factory=list, description="The collection of integer values")
+    type: Literal["integer_collection"] = "integer_collection"
+
+    # Inputs
+    collection: list[int] = InputField(
+        default=0, description="The collection of integer values", ui_type=UIType.IntegerCollection
+    )
 
     def invoke(self, context: InvocationContext) -> IntegerCollectionOutput:
         return IntegerCollectionOutput(collection=self.collection)
@@ -126,43 +135,49 @@ class IntegerCollectionInvocation(BaseInvocation):
 # region Float
 
 
-@invocation_output("float_output")
 class FloatOutput(BaseInvocationOutput):
     """Base class for nodes that output a single float"""
 
-    value: float = OutputField(description="The output float")
+    type: Literal["float_output"] = "float_output"
+    a: float = OutputField(description="The output float")
 
 
-@invocation_output("float_collection_output")
 class FloatCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of floats"""
 
+    type: Literal["float_collection_output"] = "float_collection_output"
+
+    # Outputs
     collection: list[float] = OutputField(
-        description="The float collection",
+        default_factory=list, description="The float collection", ui_type=UIType.FloatCollection
     )
 
 
-@invocation("float", title="Float Primitive", tags=["primitives", "float"], category="primitives", version="1.0.0")
+@title("Float Primitive")
+@tags("primitives", "float")
 class FloatInvocation(BaseInvocation):
     """A float primitive value"""
 
-    value: float = InputField(default=0.0, description="The float value")
+    type: Literal["float"] = "float"
+
+    # Inputs
+    param: float = InputField(default=0.0, description="The float value")
 
     def invoke(self, context: InvocationContext) -> FloatOutput:
-        return FloatOutput(value=self.value)
+        return FloatOutput(a=self.param)
 
 
-@invocation(
-    "float_collection",
-    title="Float Collection Primitive",
-    tags=["primitives", "float", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Float Primitive Collection")
+@tags("primitives", "float", "collection")
 class FloatCollectionInvocation(BaseInvocation):
     """A collection of float primitive values"""
 
-    collection: list[float] = InputField(default_factory=list, description="The collection of float values")
+    type: Literal["float_collection"] = "float_collection"
+
+    # Inputs
+    collection: list[float] = InputField(
+        default=0, description="The collection of float values", ui_type=UIType.FloatCollection
+    )
 
     def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
         return FloatCollectionOutput(collection=self.collection)
@@ -173,43 +188,49 @@ class FloatCollectionInvocation(BaseInvocation):
 # region String
 
 
-@invocation_output("string_output")
 class StringOutput(BaseInvocationOutput):
     """Base class for nodes that output a single string"""
 
-    value: str = OutputField(description="The output string")
+    type: Literal["string_output"] = "string_output"
+    text: str = OutputField(description="The output string")
 
 
-@invocation_output("string_collection_output")
 class StringCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of strings"""
 
+    type: Literal["string_collection_output"] = "string_collection_output"
+
+    # Outputs
     collection: list[str] = OutputField(
-        description="The output strings",
+        default_factory=list, description="The output strings", ui_type=UIType.StringCollection
     )
 
 
-@invocation("string", title="String Primitive", tags=["primitives", "string"], category="primitives", version="1.0.0")
+@title("String Primitive")
+@tags("primitives", "string")
 class StringInvocation(BaseInvocation):
     """A string primitive value"""
 
-    value: str = InputField(default="", description="The string value", ui_component=UIComponent.Textarea)
+    type: Literal["string"] = "string"
+
+    # Inputs
+    text: str = InputField(default="", description="The string value", ui_component=UIComponent.Textarea)
 
     def invoke(self, context: InvocationContext) -> StringOutput:
-        return StringOutput(value=self.value)
+        return StringOutput(text=self.text)
 
 
-@invocation(
-    "string_collection",
-    title="String Collection Primitive",
-    tags=["primitives", "string", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("String Primitive Collection")
+@tags("primitives", "string", "collection")
 class StringCollectionInvocation(BaseInvocation):
     """A collection of string primitive values"""
 
-    collection: list[str] = InputField(default_factory=list, description="The collection of string values")
+    type: Literal["string_collection"] = "string_collection"
+
+    # Inputs
+    collection: list[str] = InputField(
+        default=0, description="The collection of string values", ui_type=UIType.StringCollection
+    )
 
     def invoke(self, context: InvocationContext) -> StringCollectionOutput:
         return StringCollectionOutput(collection=self.collection)
@@ -226,28 +247,35 @@ class ImageField(BaseModel):
     image_name: str = Field(description="The name of the image")
 
 
-@invocation_output("image_output")
 class ImageOutput(BaseInvocationOutput):
     """Base class for nodes that output a single image"""
 
+    type: Literal["image_output"] = "image_output"
     image: ImageField = OutputField(description="The output image")
     width: int = OutputField(description="The width of the image in pixels")
     height: int = OutputField(description="The height of the image in pixels")
 
 
-@invocation_output("image_collection_output")
 class ImageCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of images"""
 
+    type: Literal["image_collection_output"] = "image_collection_output"
+
+    # Outputs
     collection: list[ImageField] = OutputField(
-        description="The output images",
+        default_factory=list, description="The output images", ui_type=UIType.ImageCollection
     )
 
 
-@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
+@title("Image Primitive")
+@tags("primitives", "image")
 class ImageInvocation(BaseInvocation):
     """An image primitive value"""
 
+    # Metadata
+    type: Literal["image"] = "image"
+
+    # Inputs
     image: ImageField = InputField(description="The image to load")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -260,41 +288,22 @@ class ImageInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "image_collection",
-    title="Image Collection Primitive",
-    tags=["primitives", "image", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Image Primitive Collection")
+@tags("primitives", "image", "collection")
 class ImageCollectionInvocation(BaseInvocation):
     """A collection of image primitive values"""
 
-    collection: list[ImageField] = InputField(description="The collection of image values")
+    type: Literal["image_collection"] = "image_collection"
+
+    # Inputs
+    collection: list[ImageField] = InputField(
+        default=0, description="The collection of image values", ui_type=UIType.ImageCollection
+    )
 
     def invoke(self, context: InvocationContext) -> ImageCollectionOutput:
         return ImageCollectionOutput(collection=self.collection)
 
 
-# endregion
-
-# region DenoiseMask
-
-
-class DenoiseMaskField(BaseModel):
-    """An inpaint mask field"""
-
-    mask_name: str = Field(description="The name of the mask image")
-    masked_latents_name: Optional[str] = Field(description="The name of the masked image latents")
-
-
-@invocation_output("denoise_mask_output")
-class DenoiseMaskOutput(BaseInvocationOutput):
-    """Base class for nodes that output a single image"""
-
-    denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
-
-
 # endregion
 
 # region Latents
@@ -307,10 +316,11 @@ class LatentsField(BaseModel):
     seed: Optional[int] = Field(default=None, description="Seed used to generate this latents")
 
 
-@invocation_output("latents_output")
 class LatentsOutput(BaseInvocationOutput):
     """Base class for nodes that output a single latents tensor"""
 
+    type: Literal["latents_output"] = "latents_output"
+
     latents: LatentsField = OutputField(
         description=FieldDescriptions.latents,
     )
@@ -318,21 +328,26 @@ class LatentsOutput(BaseInvocationOutput):
     height: int = OutputField(description=FieldDescriptions.height)
 
 
-@invocation_output("latents_collection_output")
 class LatentsCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of latents tensors"""
 
+    type: Literal["latents_collection_output"] = "latents_collection_output"
+
     collection: list[LatentsField] = OutputField(
+        default_factory=list,
         description=FieldDescriptions.latents,
+        ui_type=UIType.LatentsCollection,
     )
 
 
-@invocation(
-    "latents", title="Latents Primitive", tags=["primitives", "latents"], category="primitives", version="1.0.0"
-)
+@title("Latents Primitive")
+@tags("primitives", "latents")
 class LatentsInvocation(BaseInvocation):
     """A latents tensor primitive value"""
 
+    type: Literal["latents"] = "latents"
+
+    # Inputs
     latents: LatentsField = InputField(description="The latents tensor", input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
@@ -341,18 +356,16 @@ class LatentsInvocation(BaseInvocation):
         return build_latents_output(self.latents.latents_name, latents)
 
 
-@invocation(
-    "latents_collection",
-    title="Latents Collection Primitive",
-    tags=["primitives", "latents", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Latents Primitive Collection")
+@tags("primitives", "latents", "collection")
 class LatentsCollectionInvocation(BaseInvocation):
     """A collection of latents tensor primitive values"""
 
+    type: Literal["latents_collection"] = "latents_collection"
+
+    # Inputs
     collection: list[LatentsField] = InputField(
-        description="The collection of latents tensors",
+        default=0, description="The collection of latents tensors", ui_type=UIType.LatentsCollection
     )
 
     def invoke(self, context: InvocationContext) -> LatentsCollectionOutput:
@@ -384,26 +397,32 @@ class ColorField(BaseModel):
         return (self.r, self.g, self.b, self.a)
 
 
-@invocation_output("color_output")
 class ColorOutput(BaseInvocationOutput):
     """Base class for nodes that output a single color"""
 
+    type: Literal["color_output"] = "color_output"
     color: ColorField = OutputField(description="The output color")
 
 
-@invocation_output("color_collection_output")
 class ColorCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of colors"""
 
+    type: Literal["color_collection_output"] = "color_collection_output"
+
+    # Outputs
     collection: list[ColorField] = OutputField(
-        description="The output colors",
+        default_factory=list, description="The output colors", ui_type=UIType.ColorCollection
     )
 
 
-@invocation("color", title="Color Primitive", tags=["primitives", "color"], category="primitives", version="1.0.0")
+@title("Color Primitive")
+@tags("primitives", "color")
 class ColorInvocation(BaseInvocation):
     """A color primitive value"""
 
+    type: Literal["color"] = "color"
+
+    # Inputs
     color: ColorField = InputField(default=ColorField(r=0, g=0, b=0, a=255), description="The color value")
 
     def invoke(self, context: InvocationContext) -> ColorOutput:
@@ -421,51 +440,50 @@ class ConditioningField(BaseModel):
     conditioning_name: str = Field(description="The name of conditioning tensor")
 
 
-@invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
 
+    type: Literal["conditioning_output"] = "conditioning_output"
+
     conditioning: ConditioningField = OutputField(description=FieldDescriptions.cond)
 
 
-@invocation_output("conditioning_collection_output")
 class ConditioningCollectionOutput(BaseInvocationOutput):
     """Base class for nodes that output a collection of conditioning tensors"""
 
+    type: Literal["conditioning_collection_output"] = "conditioning_collection_output"
+
+    # Outputs
     collection: list[ConditioningField] = OutputField(
+        default_factory=list,
         description="The output conditioning tensors",
+        ui_type=UIType.ConditioningCollection,
     )
 
 
-@invocation(
-    "conditioning",
-    title="Conditioning Primitive",
-    tags=["primitives", "conditioning"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Conditioning Primitive")
+@tags("primitives", "conditioning")
 class ConditioningInvocation(BaseInvocation):
     """A conditioning tensor primitive value"""
 
+    type: Literal["conditioning"] = "conditioning"
+
     conditioning: ConditioningField = InputField(description=FieldDescriptions.cond, input=Input.Connection)
 
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         return ConditioningOutput(conditioning=self.conditioning)
 
 
-@invocation(
-    "conditioning_collection",
-    title="Conditioning Collection Primitive",
-    tags=["primitives", "conditioning", "collection"],
-    category="primitives",
-    version="1.0.0",
-)
+@title("Conditioning Primitive Collection")
+@tags("primitives", "conditioning", "collection")
 class ConditioningCollectionInvocation(BaseInvocation):
     """A collection of conditioning tensor primitive values"""
 
+    type: Literal["conditioning_collection"] = "conditioning_collection"
+
+    # Inputs
     collection: list[ConditioningField] = InputField(
-        default_factory=list,
-        description="The collection of conditioning tensors",
+        default=0, description="The collection of conditioning tensors", ui_type=UIType.ConditioningCollection
     )
 
     def invoke(self, context: InvocationContext) -> ConditioningCollectionOutput:

invokeai/app/invocations/prompt.py

@@ -1,5 +1,5 @@
 from os.path import exists
-from typing import Optional, Union
+from typing import Literal, Optional, Union
 
 import numpy as np
 from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
@@ -7,20 +7,17 @@ from pydantic import validator
 
 from invokeai.app.invocations.primitives import StringCollectionOutput
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, UIType, tags, title
 
 
-@invocation(
-    "dynamic_prompt",
-    title="Dynamic Prompt",
-    tags=["prompt", "collection"],
-    category="prompt",
-    version="1.0.0",
-    use_cache=False,
-)
+@title("Dynamic Prompt")
+@tags("prompt", "collection")
 class DynamicPromptInvocation(BaseInvocation):
     """Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
 
+    type: Literal["dynamic_prompt"] = "dynamic_prompt"
+
+    # Inputs
     prompt: str = InputField(description="The prompt to parse with dynamicprompts", ui_component=UIComponent.Textarea)
     max_prompts: int = InputField(default=1, description="The number of prompts to generate")
     combinatorial: bool = InputField(default=False, description="Whether to use the combinatorial generator")
@@ -36,11 +33,15 @@ class DynamicPromptInvocation(BaseInvocation):
         return StringCollectionOutput(collection=prompts)
 
 
-@invocation("prompt_from_file", title="Prompts from File", tags=["prompt", "file"], category="prompt", version="1.0.0")
+@title("Prompts from File")
+@tags("prompt", "file")
 class PromptsFromFileInvocation(BaseInvocation):
     """Loads prompts from a text file"""
 
-    file_path: str = InputField(description="Path to prompt text file")
+    type: Literal["prompt_from_file"] = "prompt_from_file"
+
+    # Inputs
+    file_path: str = InputField(description="Path to prompt text file", ui_type=UIType.FilePath)
     pre_prompt: Optional[str] = InputField(
         default=None, description="String to prepend to each prompt", ui_component=UIComponent.Textarea
     )

invokeai/app/invocations/sdxl.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from ...backend.model_management import ModelType, SubModelType
 from .baseinvocation import (
     BaseInvocation,
@@ -8,35 +10,41 @@ from .baseinvocation import (
     InvocationContext,
     OutputField,
     UIType,
-    invocation,
-    invocation_output,
+    tags,
+    title,
 )
 from .model import ClipField, MainModelField, ModelInfo, UNetField, VaeField
 
 
-@invocation_output("sdxl_model_loader_output")
 class SDXLModelLoaderOutput(BaseInvocationOutput):
     """SDXL base model loader output"""
 
+    type: Literal["sdxl_model_loader_output"] = "sdxl_model_loader_output"
+
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
     clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 1")
     clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
     vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation_output("sdxl_refiner_model_loader_output")
 class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
     """SDXL refiner model loader output"""
 
+    type: Literal["sdxl_refiner_model_loader_output"] = "sdxl_refiner_model_loader_output"
+
     unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
     clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
     vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
 
 
-@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.0")
+@title("SDXL Main Model Loader")
+@tags("model", "sdxl")
 class SDXLModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl base model, outputting its submodels."""
 
+    type: Literal["sdxl_model_loader"] = "sdxl_model_loader"
+
+    # Inputs
     model: MainModelField = InputField(
         description=FieldDescriptions.sdxl_main_model, input=Input.Direct, ui_type=UIType.SDXLMainModel
     )
@@ -114,16 +122,14 @@ class SDXLModelLoaderInvocation(BaseInvocation):
         )
 
 
-@invocation(
-    "sdxl_refiner_model_loader",
-    title="SDXL Refiner Model",
-    tags=["model", "sdxl", "refiner"],
-    category="model",
-    version="1.0.0",
-)
+@title("SDXL Refiner Model Loader")
+@tags("model", "sdxl", "refiner")
 class SDXLRefinerModelLoaderInvocation(BaseInvocation):
     """Loads an sdxl refiner model, outputting its submodels."""
 
+    type: Literal["sdxl_refiner_model_loader"] = "sdxl_refiner_model_loader"
+
+    # Inputs
     model: MainModelField = InputField(
         description=FieldDescriptions.sdxl_refiner_model,
         input=Input.Direct,

invokeai/app/invocations/strings.py

@@ -1,139 +0,0 @@
-# 2023 skunkworxdark (https://github.com/skunkworxdark)
-
-import re
-
-from .baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InputField,
-    InvocationContext,
-    OutputField,
-    UIComponent,
-    invocation,
-    invocation_output,
-)
-from .primitives import StringOutput
-
-
-@invocation_output("string_pos_neg_output")
-class StringPosNegOutput(BaseInvocationOutput):
-    """Base class for invocations that output a positive and negative string"""
-
-    positive_string: str = OutputField(description="Positive string")
-    negative_string: str = OutputField(description="Negative string")
-
-
-@invocation(
-    "string_split_neg",
-    title="String Split Negative",
-    tags=["string", "split", "negative"],
-    category="string",
-    version="1.0.0",
-)
-class StringSplitNegInvocation(BaseInvocation):
-    """Splits string into two strings, inside [] goes into negative string everthing else goes into positive string. Each [ and ] character is replaced with a space"""
-
-    string: str = InputField(default="", description="String to split", ui_component=UIComponent.Textarea)
-
-    def invoke(self, context: InvocationContext) -> StringPosNegOutput:
-        p_string = ""
-        n_string = ""
-        brackets_depth = 0
-        escaped = False
-
-        for char in self.string or "":
-            if char == "[" and not escaped:
-                n_string += " "
-                brackets_depth += 1
-            elif char == "]" and not escaped:
-                brackets_depth -= 1
-                char = " "
-            elif brackets_depth > 0:
-                n_string += char
-            else:
-                p_string += char
-
-            # keep track of the escape char but only if it isn't escaped already
-            if char == "\\" and not escaped:
-                escaped = True
-            else:
-                escaped = False
-
-        return StringPosNegOutput(positive_string=p_string, negative_string=n_string)
-
-
-@invocation_output("string_2_output")
-class String2Output(BaseInvocationOutput):
-    """Base class for invocations that output two strings"""
-
-    string_1: str = OutputField(description="string 1")
-    string_2: str = OutputField(description="string 2")
-
-
-@invocation("string_split", title="String Split", tags=["string", "split"], category="string", version="1.0.0")
-class StringSplitInvocation(BaseInvocation):
-    """Splits string into two strings, based on the first occurance of the delimiter. The delimiter will be removed from the string"""
-
-    string: str = InputField(default="", description="String to split", ui_component=UIComponent.Textarea)
-    delimiter: str = InputField(
-        default="", description="Delimiter to spilt with. blank will split on the first whitespace"
-    )
-
-    def invoke(self, context: InvocationContext) -> String2Output:
-        result = self.string.split(self.delimiter, 1)
-        if len(result) == 2:
-            part1, part2 = result
-        else:
-            part1 = result[0]
-            part2 = ""
-
-        return String2Output(string_1=part1, string_2=part2)
-
-
-@invocation("string_join", title="String Join", tags=["string", "join"], category="string", version="1.0.0")
-class StringJoinInvocation(BaseInvocation):
-    """Joins string left to string right"""
-
-    string_left: str = InputField(default="", description="String Left", ui_component=UIComponent.Textarea)
-    string_right: str = InputField(default="", description="String Right", ui_component=UIComponent.Textarea)
-
-    def invoke(self, context: InvocationContext) -> StringOutput:
-        return StringOutput(value=((self.string_left or "") + (self.string_right or "")))
-
-
-@invocation("string_join_three", title="String Join Three", tags=["string", "join"], category="string", version="1.0.0")
-class StringJoinThreeInvocation(BaseInvocation):
-    """Joins string left to string middle to string right"""
-
-    string_left: str = InputField(default="", description="String Left", ui_component=UIComponent.Textarea)
-    string_middle: str = InputField(default="", description="String Middle", ui_component=UIComponent.Textarea)
-    string_right: str = InputField(default="", description="String Right", ui_component=UIComponent.Textarea)
-
-    def invoke(self, context: InvocationContext) -> StringOutput:
-        return StringOutput(value=((self.string_left or "") + (self.string_middle or "") + (self.string_right or "")))
-
-
-@invocation(
-    "string_replace", title="String Replace", tags=["string", "replace", "regex"], category="string", version="1.0.0"
-)
-class StringReplaceInvocation(BaseInvocation):
-    """Replaces the search string with the replace string"""
-
-    string: str = InputField(default="", description="String to work on", ui_component=UIComponent.Textarea)
-    search_string: str = InputField(default="", description="String to search for", ui_component=UIComponent.Textarea)
-    replace_string: str = InputField(
-        default="", description="String to replace the search", ui_component=UIComponent.Textarea
-    )
-    use_regex: bool = InputField(
-        default=False, description="Use search string as a regex expression (non regex is case insensitive)"
-    )
-
-    def invoke(self, context: InvocationContext) -> StringOutput:
-        pattern = self.search_string or ""
-        new_string = self.string or ""
-        if len(pattern) > 0:
-            if not self.use_regex:
-                # None regex so make case insensitve
-                pattern = "(?i)" + re.escape(pattern)
-            new_string = re.sub(pattern, (self.replace_string or ""), new_string)
-        return StringOutput(value=new_string)

invokeai/app/invocations/upscale.py

@@ -7,11 +7,11 @@ import numpy as np
 from basicsr.archs.rrdbnet_arch import RRDBNet
 from PIL import Image
 from realesrgan import RealESRGANer
-
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
+
 from invokeai.app.models.image import ImageCategory, ResourceOrigin
 
-from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, title, tags
 
 # TODO: Populate this from disk?
 # TODO: Use model manager to load?
@@ -23,10 +23,14 @@ ESRGAN_MODELS = Literal[
 ]
 
 
-@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.0.0")
+@title("Upscale (RealESRGAN)")
+@tags("esrgan", "upscale")
 class ESRGANInvocation(BaseInvocation):
     """Upscales an image using RealESRGAN."""
 
+    type: Literal["esrgan"] = "esrgan"
+
+    # Inputs
     image: ImageField = InputField(description="The input image")
     model_name: ESRGAN_MODELS = InputField(default="RealESRGAN_x4plus.pth", description="The Real-ESRGAN model to use")
 
@@ -106,7 +110,6 @@ class ESRGANInvocation(BaseInvocation):
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            workflow=self.workflow,
         )
 
         return ImageOutput(

invokeai/app/services/board_image_record_storage.py

@@ -1,10 +1,13 @@
+from abc import ABC, abstractmethod
 import sqlite3
 import threading
-from abc import ABC, abstractmethod
 from typing import Optional, cast
 
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.image_record import ImageRecord, deserialize_image_record
+from invokeai.app.services.models.image_record import (
+    ImageRecord,
+    deserialize_image_record,
+)
 
 
 class BoardImageRecordStorageBase(ABC):
@@ -53,20 +56,24 @@ class BoardImageRecordStorageBase(ABC):
 
 
 class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
+    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
     _lock: threading.Lock
 
-    def __init__(self, conn: sqlite3.Connection, lock: threading.Lock) -> None:
+    def __init__(self, filename: str) -> None:
         super().__init__()
-        self._conn = conn
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = lock
+        self._lock = threading.Lock()
 
         try:
             self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:

invokeai/app/services/board_images.py

@@ -1,9 +1,12 @@
 from abc import ABC, abstractmethod
 from logging import Logger
 from typing import Optional
-
 from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
-from invokeai.app.services.board_record_storage import BoardRecord, BoardRecordStorageBase
+from invokeai.app.services.board_record_storage import (
+    BoardRecord,
+    BoardRecordStorageBase,
+)
+
 from invokeai.app.services.image_record_storage import ImageRecordStorageBase
 from invokeai.app.services.models.board_record import BoardDTO
 from invokeai.app.services.urls import UrlServiceBase

invokeai/app/services/board_record_storage.py

@@ -1,13 +1,15 @@
-import sqlite3
 import threading
+import uuid
 from abc import ABC, abstractmethod
 from typing import Optional, Union, cast
 
-from pydantic import BaseModel, Extra, Field
-
+import sqlite3
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
-from invokeai.app.services.models.board_record import BoardRecord, deserialize_board_record
-from invokeai.app.util.misc import uuid_string
+from invokeai.app.services.models.board_record import (
+    BoardRecord,
+    deserialize_board_record,
+)
+from pydantic import BaseModel, Field, Extra
 
 
 class BoardChanges(BaseModel, extra=Extra.forbid):
@@ -87,20 +89,24 @@ class BoardRecordStorageBase(ABC):
 
 
 class SqliteBoardRecordStorage(BoardRecordStorageBase):
+    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
     _lock: threading.Lock
 
-    def __init__(self, conn: sqlite3.Connection, lock: threading.Lock) -> None:
+    def __init__(self, filename: str) -> None:
         super().__init__()
-        self._conn = conn
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = lock
+        self._lock = threading.Lock()
 
         try:
             self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:
@@ -170,7 +176,7 @@ class SqliteBoardRecordStorage(BoardRecordStorageBase):
         board_name: str,
     ) -> BoardRecord:
         try:
-            board_id = uuid_string()
+            board_id = str(uuid.uuid4())
             self._lock.acquire()
             self._cursor.execute(
                 """--sql

invokeai/app/services/boards.py

@@ -1,10 +1,17 @@
 from abc import ABC, abstractmethod
-from logging import Logger
 
+from logging import Logger
 from invokeai.app.services.board_image_record_storage import BoardImageRecordStorageBase
 from invokeai.app.services.board_images import board_record_to_dto
-from invokeai.app.services.board_record_storage import BoardChanges, BoardRecordStorageBase
-from invokeai.app.services.image_record_storage import ImageRecordStorageBase, OffsetPaginatedResults
+
+from invokeai.app.services.board_record_storage import (
+    BoardChanges,
+    BoardRecordStorageBase,
+)
+from invokeai.app.services.image_record_storage import (
+    ImageRecordStorageBase,
+    OffsetPaginatedResults,
+)
 from invokeai.app.services.models.board_record import BoardDTO
 from invokeai.app.services.urls import UrlServiceBase
 

invokeai/app/services/config.py

@@ -10,49 +10,37 @@ categories returned by `invokeai --help`. The file looks like this:
 [file: invokeai.yaml]
 
 InvokeAI:
+  Paths:
+    root: /home/lstein/invokeai-main
+    conf_path: configs/models.yaml
+    legacy_conf_dir: configs/stable-diffusion
+    outdir: outputs
+    autoimport_dir: null
+  Models:
+    model: stable-diffusion-1.5
+    embeddings: true
+  Memory/Performance:
+    xformers_enabled: false
+    sequential_guidance: false
+    precision: float16
+    max_cache_size: 6
+    max_vram_cache_size: 0.5
+    always_use_cpu: false
+    free_gpu_mem: false
+  Features:
+    esrgan: true
+    patchmatch: true
+    internet_available: true
+    log_tokenization: false
   Web Server:
     host: 127.0.0.1
-    port: 9090
+    port: 8081
     allow_origins: []
     allow_credentials: true
     allow_methods:
     - '*'
     allow_headers:
     - '*'
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    patchmatch: true
-    ignore_missing_core_models: false
-  Paths:
-    autoimport_dir: autoimport
-    lora_dir: null
-    embedding_dir: null
-    controlnet_dir: null
-    conf_path: configs/models.yaml
-    models_dir: models
-    legacy_conf_dir: configs/stable-diffusion
-    db_dir: databases
-    outdir: /home/lstein/invokeai-main/outputs
-    use_memory_db: false
-  Logging:
-    log_handlers:
-    - console
-    log_format: plain
-    log_level: info
-  Model Cache:
-    ram: 13.5
-    vram: 0.25
-    lazy_offload: true
-  Device:
-    device: auto
-    precision: auto
-  Generation:
-    sequential_guidance: false
-    attention_type: xformers
-    attention_slice_size: auto
-    force_tiled_decode: false
 
 The default name of the configuration file is `invokeai.yaml`, located
 in INVOKEAI_ROOT. You can replace supersede this by providing any
@@ -66,23 +54,24 @@ InvokeAIAppConfig.parse_args() will parse the contents of `sys.argv`
 at initialization time. You may pass a list of strings in the optional
 `argv` argument to use instead of the system argv:
 
- conf.parse_args(argv=['--log_tokenization'])
+ conf.parse_args(argv=['--xformers_enabled'])
 
 It is also possible to set a value at initialization time. However, if
 you call parse_args() it may be overwritten.
 
- conf = InvokeAIAppConfig(log_tokenization=True)
- conf.parse_args(argv=['--no-log_tokenization'])
- conf.log_tokenization
+ conf = InvokeAIAppConfig(xformers_enabled=True)
+ conf.parse_args(argv=['--no-xformers'])
+ conf.xformers_enabled
  # False
 
+
 To avoid this, use `get_config()` to retrieve the application-wide
 configuration object. This will retain any properties set at object
 creation time:
 
- conf = InvokeAIAppConfig.get_config(log_tokenization=True)
- conf.parse_args(argv=['--no-log_tokenization'])
- conf.log_tokenization
+ conf = InvokeAIAppConfig.get_config(xformers_enabled=True)
+ conf.parse_args(argv=['--no-xformers'])
+ conf.xformers_enabled
  # True
 
 Any setting can be overwritten by setting an environment variable of
@@ -104,7 +93,7 @@ Typical usage at the top level file:
  # get global configuration and print its cache size
  conf = InvokeAIAppConfig.get_config()
  conf.parse_args()
- print(conf.ram_cache_size)
+ print(conf.max_cache_size)
 
 Typical usage in a backend module:
 
@@ -112,7 +101,8 @@ Typical usage in a backend module:
 
  # get global configuration and print its cache size value
  conf = InvokeAIAppConfig.get_config()
- print(conf.ram_cache_size)
+ print(conf.max_cache_size)
+
 
 Computed properties:
 
@@ -169,15 +159,15 @@ two configs are kept in separate sections of the config file:
 
 """
 from __future__ import annotations
-
+import argparse
+import pydoc
 import os
+import sys
+from argparse import ArgumentParser
+from omegaconf import OmegaConf, DictConfig, ListConfig
 from pathlib import Path
-from typing import ClassVar, Dict, List, Literal, Optional, Union, get_type_hints
-
-from omegaconf import DictConfig, OmegaConf
-from pydantic import Field, parse_obj_as
-
-from .base import InvokeAISettings
+from pydantic import BaseSettings, Field, parse_obj_as
+from typing import ClassVar, Dict, List, Literal, Union, get_origin, get_type_hints, get_args
 
 INIT_FILE = Path("invokeai.yaml")
 DB_FILE = Path("invokeai.db")
@@ -185,6 +175,195 @@ LEGACY_INIT_FILE = Path("invokeai.init")
 DEFAULT_MAX_VRAM = 0.5
 
 
+class InvokeAISettings(BaseSettings):
+    """
+    Runtime configuration settings in which default values are
+    read from an omegaconf .yaml file.
+    """
+
+    initconf: ClassVar[DictConfig] = None
+    argparse_groups: ClassVar[Dict] = {}
+
+    def parse_args(self, argv: list = sys.argv[1:]):
+        parser = self.get_parser()
+        opt = parser.parse_args(argv)
+        for name in self.__fields__:
+            if name not in self._excluded():
+                value = getattr(opt, name)
+                if isinstance(value, ListConfig):
+                    value = list(value)
+                elif isinstance(value, DictConfig):
+                    value = dict(value)
+                setattr(self, name, value)
+
+    def to_yaml(self) -> str:
+        """
+        Return a YAML string representing our settings. This can be used
+        as the contents of `invokeai.yaml` to restore settings later.
+        """
+        cls = self.__class__
+        type = get_args(get_type_hints(cls)["type"])[0]
+        field_dict = dict({type: dict()})
+        for name, field in self.__fields__.items():
+            if name in cls._excluded_from_yaml():
+                continue
+            category = field.field_info.extra.get("category") or "Uncategorized"
+            value = getattr(self, name)
+            if category not in field_dict[type]:
+                field_dict[type][category] = dict()
+            # keep paths as strings to make it easier to read
+            field_dict[type][category][name] = str(value) if isinstance(value, Path) else value
+        conf = OmegaConf.create(field_dict)
+        return OmegaConf.to_yaml(conf)
+
+    @classmethod
+    def add_parser_arguments(cls, parser):
+        if "type" in get_type_hints(cls):
+            settings_stanza = get_args(get_type_hints(cls)["type"])[0]
+        else:
+            settings_stanza = "Uncategorized"
+
+        env_prefix = cls.Config.env_prefix if hasattr(cls.Config, "env_prefix") else settings_stanza.upper()
+
+        initconf = (
+            cls.initconf.get(settings_stanza)
+            if cls.initconf and settings_stanza in cls.initconf
+            else OmegaConf.create()
+        )
+
+        # create an upcase version of the environment in
+        # order to achieve case-insensitive environment
+        # variables (the way Windows does)
+        upcase_environ = dict()
+        for key, value in os.environ.items():
+            upcase_environ[key.upper()] = value
+
+        fields = cls.__fields__
+        cls.argparse_groups = {}
+
+        for name, field in fields.items():
+            if name not in cls._excluded():
+                current_default = field.default
+
+                category = field.field_info.extra.get("category", "Uncategorized")
+                env_name = env_prefix + "_" + name
+                if category in initconf and name in initconf.get(category):
+                    field.default = initconf.get(category).get(name)
+                if env_name.upper() in upcase_environ:
+                    field.default = upcase_environ[env_name.upper()]
+                cls.add_field_argument(parser, name, field)
+
+                field.default = current_default
+
+    @classmethod
+    def cmd_name(self, command_field: str = "type") -> str:
+        hints = get_type_hints(self)
+        if command_field in hints:
+            return get_args(hints[command_field])[0]
+        else:
+            return "Uncategorized"
+
+    @classmethod
+    def get_parser(cls) -> ArgumentParser:
+        parser = PagingArgumentParser(
+            prog=cls.cmd_name(),
+            description=cls.__doc__,
+        )
+        cls.add_parser_arguments(parser)
+        return parser
+
+    @classmethod
+    def add_subparser(cls, parser: argparse.ArgumentParser):
+        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
+
+    @classmethod
+    def _excluded(self) -> List[str]:
+        # internal fields that shouldn't be exposed as command line options
+        return ["type", "initconf"]
+
+    @classmethod
+    def _excluded_from_yaml(self) -> List[str]:
+        # combination of deprecated parameters and internal ones that shouldn't be exposed as invokeai.yaml options
+        return [
+            "type",
+            "initconf",
+            "version",
+            "from_file",
+            "model",
+            "root",
+        ]
+
+    class Config:
+        env_file_encoding = "utf-8"
+        arbitrary_types_allowed = True
+        case_sensitive = True
+
+    @classmethod
+    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
+        field_type = get_type_hints(cls).get(name)
+        default = (
+            default_override
+            if default_override is not None
+            else field.default
+            if field.default_factory is None
+            else field.default_factory()
+        )
+        if category := field.field_info.extra.get("category"):
+            if category not in cls.argparse_groups:
+                cls.argparse_groups[category] = command_parser.add_argument_group(category)
+            argparse_group = cls.argparse_groups[category]
+        else:
+            argparse_group = command_parser
+
+        if get_origin(field_type) == Literal:
+            allowed_values = get_args(field.type_)
+            allowed_types = set()
+            for val in allowed_values:
+                allowed_types.add(type(val))
+            allowed_types_list = list(allowed_types)
+            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field_type,
+                default=default,
+                choices=allowed_values,
+                help=field.field_info.description,
+            )
+
+        elif get_origin(field_type) == list:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                nargs="*",
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
+                help=field.field_info.description,
+            )
+        else:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
+                help=field.field_info.description,
+            )
+
+
+def _find_root() -> Path:
+    venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
+    if os.environ.get("INVOKEAI_ROOT"):
+        root = Path(os.environ["INVOKEAI_ROOT"])
+    elif any([(venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]]):
+        root = (venv.parent).resolve()
+    else:
+        root = Path("~/invokeai").expanduser().resolve()
+    return root
+
+
 class InvokeAIAppConfig(InvokeAISettings):
     """
     Generate images using Stable Diffusion. Use "invokeai" to launch
@@ -194,13 +373,11 @@ class InvokeAIAppConfig(InvokeAISettings):
     setting environment variables INVOKEAI_<setting>.
     """
 
-    singleton_config: ClassVar[Optional[InvokeAIAppConfig]] = None
-    singleton_init: ClassVar[Optional[Dict]] = None
+    singleton_config: ClassVar[InvokeAIAppConfig] = None
+    singleton_init: ClassVar[Dict] = None
 
     # fmt: off
     type: Literal["InvokeAI"] = "InvokeAI"
-
-    # WEB
     host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
     port                : int = Field(default=9090, description="Port to bind to", category='Web Server')
     allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
@@ -208,14 +385,20 @@ class InvokeAIAppConfig(InvokeAISettings):
     allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
     allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
 
-    # FEATURES
     esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
     internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
     log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
     patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
-    ignore_missing_core_models : bool = Field(default=False, description='Ignore missing models in models/core/convert', category='Features')
 
-    # PATHS
+    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
+    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
+    max_cache_size      : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
+    max_vram_cache_size : float = Field(default=2.75, ge=0, description="Amount of VRAM reserved for model storage", category='Memory/Performance')
+    precision           : Literal['auto', 'float16', 'float32', 'autocast'] = Field(default='auto', description='Floating point precision', category='Memory/Performance')
+    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
+    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
+
     root                : Path = Field(default=None, description='InvokeAI runtime root directory', category='Paths')
     autoimport_dir      : Path = Field(default='autoimport', description='Path to a directory of models files to be imported on startup.', category='Paths')
     lora_dir            : Path = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', category='Paths')
@@ -226,59 +409,22 @@ class InvokeAIAppConfig(InvokeAISettings):
     legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
     db_dir              : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
     outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
-    use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
     from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
+    use_memory_db       : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
+    ignore_missing_core_models : bool = Field(default=False, description='Ignore missing models in models/core/convert', category='Features')
 
-    # LOGGING
     log_handlers        : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
     # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
     log_format          : Literal['plain', 'color', 'syslog', 'legacy'] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
     log_level           : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or  higher", category="Logging")
-    log_sql             : bool = Field(default=False, description="Log SQL queries", category="Logging")
-
-    dev_reload          : bool = Field(default=False, description="Automatically reload when Python sources are changed.", category="Development")
 
     version             : bool = Field(default=False, description="Show InvokeAI version and exit", category="Other")
-
-    # CACHE
-    ram                 : Union[float, Literal["auto"]] = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number or 'auto')", category="Model Cache", )
-    vram                : Union[float, Literal["auto"]] = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number or 'auto')", category="Model Cache", )
-    lazy_offload        : bool = Field(default=True, description="Keep models in VRAM until their space is needed", category="Model Cache", )
-
-    # DEVICE
-    device              : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", category="Device", )
-    precision           : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", category="Device", )
-
-    # GENERATION
-    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category="Generation", )
-    attention_type      : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", category="Generation", )
-    attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', category="Generation", )
-    force_tiled_decode  : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
-    force_tiled_decode: bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
-
-    # QUEUE
-    max_queue_size      : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", category="Queue", )
-
-    # NODES
-    allow_nodes         : Optional[List[str]] = Field(default=None, description="List of nodes to allow. Omit to allow all.", category="Nodes")
-    deny_nodes          : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", category="Nodes")
-    node_cache_size     : int = Field(default=512, description="How many cached nodes to keep in memory", category="Nodes", )
-
-    # DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
-    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
-    free_gpu_mem        : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
-    max_cache_size      : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
-    max_vram_cache_size : Optional[float] = Field(default=None, ge=0, description="Amount of VRAM reserved for model storage", category='Memory/Performance')
-    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
-    tiled_decode        : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
-
-    # See InvokeAIAppConfig subclass below for CACHE and DEVICE categories
     # fmt: on
 
     class Config:
         validate_assignment = True
 
-    def parse_args(self, argv: Optional[list[str]] = None, conf: Optional[DictConfig] = None, clobber=False):
+    def parse_args(self, argv: List[str] = None, conf: DictConfig = None, clobber=False):
         """
         Update settings with contents of init file, environment, and
         command-line settings.
@@ -289,16 +435,12 @@ class InvokeAIAppConfig(InvokeAISettings):
         # Set the runtime root directory. We parse command-line switches here
         # in order to pick up the --root_dir option.
         super().parse_args(argv)
-        loaded_conf = None
         if conf is None:
             try:
-                loaded_conf = OmegaConf.load(self.root_dir / INIT_FILE)
+                conf = OmegaConf.load(self.root_dir / INIT_FILE)
             except Exception:
                 pass
-        if isinstance(loaded_conf, DictConfig):
-            InvokeAISettings.initconf = loaded_conf
-        else:
-            InvokeAISettings.initconf = conf
+        InvokeAISettings.initconf = conf
 
         # parse args again in order to pick up settings in configuration file
         super().parse_args(argv)
@@ -386,12 +528,24 @@ class InvokeAIAppConfig(InvokeAISettings):
         """
         return self._resolve(self.models_dir)
 
+    @property
+    def autoconvert_path(self) -> Path:
+        """
+        Path to the directory containing models to be imported automatically at startup.
+        """
+        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
+
     # the following methods support legacy calls leftover from the Globals era
     @property
     def full_precision(self) -> bool:
         """Return true if precision set to float32"""
         return self.precision == "float32"
 
+    @property
+    def disable_xformers(self) -> bool:
+        """Return true if xformers_enabled is false"""
+        return not self.xformers_enabled
+
     @property
     def try_patchmatch(self) -> bool:
         """Return true if patchmatch true"""
@@ -407,27 +561,6 @@ class InvokeAIAppConfig(InvokeAISettings):
         """invisible watermark node is always active and disabled from Web UIe"""
         return True
 
-    @property
-    def ram_cache_size(self) -> Union[Literal["auto"], float]:
-        return self.max_cache_size or self.ram
-
-    @property
-    def vram_cache_size(self) -> Union[Literal["auto"], float]:
-        return self.max_vram_cache_size or self.vram
-
-    @property
-    def use_cpu(self) -> bool:
-        return self.always_use_cpu or self.device == "cpu"
-
-    @property
-    def disable_xformers(self) -> bool:
-        """
-        Return true if enable_xformers is false (reversed logic)
-        and attention type is not set to xformers.
-        """
-        disabled_in_config = not self.xformers_enabled
-        return disabled_in_config and self.attention_type != "xformers"
-
     @staticmethod
     def find_root() -> Path:
         """
@@ -437,19 +570,19 @@ class InvokeAIAppConfig(InvokeAISettings):
         return _find_root()
 
 
+class PagingArgumentParser(argparse.ArgumentParser):
+    """
+    A custom ArgumentParser that uses pydoc to page its output.
+    It also supports reading defaults from an init file.
+    """
+
+    def print_help(self, file=None):
+        text = self.format_help()
+        pydoc.pager(text)
+
+
 def get_invokeai_config(**kwargs) -> InvokeAIAppConfig:
     """
     Legacy function which returns InvokeAIAppConfig.get_config()
     """
     return InvokeAIAppConfig.get_config(**kwargs)
-
-
-def _find_root() -> Path:
-    venv = Path(os.environ.get("VIRTUAL_ENV") or ".")
-    if os.environ.get("INVOKEAI_ROOT"):
-        root = Path(os.environ["INVOKEAI_ROOT"])
-    elif any([(venv.parent / x).exists() for x in [INIT_FILE, LEGACY_INIT_FILE]]):
-        root = (venv.parent).resolve()
-    else:
-        root = Path("~/invokeai").expanduser().resolve()
-    return root

invokeai/app/services/config/__init__.py

@@ -1,6 +0,0 @@
-"""
-Init file for InvokeAI configure package
-"""
-
-from .base import PagingArgumentParser  # noqa F401
-from .invokeai_config import InvokeAIAppConfig, get_invokeai_config  # noqa F401

invokeai/app/services/config/base.py

@@ -1,240 +0,0 @@
-# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
-
-"""
-Base class for the InvokeAI configuration system.
-It defines a type of pydantic BaseSettings object that
-is able to read and write from an omegaconf-based config file,
-with overriding of settings from environment variables and/or
-the command line.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import pydoc
-import sys
-from argparse import ArgumentParser
-from pathlib import Path
-from typing import ClassVar, Dict, List, Literal, Optional, Union, get_args, get_origin, get_type_hints
-
-from omegaconf import DictConfig, ListConfig, OmegaConf
-from pydantic import BaseSettings
-
-
-class PagingArgumentParser(argparse.ArgumentParser):
-    """
-    A custom ArgumentParser that uses pydoc to page its output.
-    It also supports reading defaults from an init file.
-    """
-
-    def print_help(self, file=None):
-        text = self.format_help()
-        pydoc.pager(text)
-
-
-class InvokeAISettings(BaseSettings):
-    """
-    Runtime configuration settings in which default values are
-    read from an omegaconf .yaml file.
-    """
-
-    initconf: ClassVar[Optional[DictConfig]] = None
-    argparse_groups: ClassVar[Dict] = {}
-
-    def parse_args(self, argv: Optional[list] = sys.argv[1:]):
-        parser = self.get_parser()
-        opt, unknown_opts = parser.parse_known_args(argv)
-        if len(unknown_opts) > 0:
-            print("Unknown args:", unknown_opts)
-        for name in self.__fields__:
-            if name not in self._excluded():
-                value = getattr(opt, name)
-                if isinstance(value, ListConfig):
-                    value = list(value)
-                elif isinstance(value, DictConfig):
-                    value = dict(value)
-                setattr(self, name, value)
-
-    def to_yaml(self) -> str:
-        """
-        Return a YAML string representing our settings. This can be used
-        as the contents of `invokeai.yaml` to restore settings later.
-        """
-        cls = self.__class__
-        type = get_args(get_type_hints(cls)["type"])[0]
-        field_dict = dict({type: dict()})
-        for name, field in self.__fields__.items():
-            if name in cls._excluded_from_yaml():
-                continue
-            category = field.field_info.extra.get("category") or "Uncategorized"
-            value = getattr(self, name)
-            if category not in field_dict[type]:
-                field_dict[type][category] = dict()
-            # keep paths as strings to make it easier to read
-            field_dict[type][category][name] = str(value) if isinstance(value, Path) else value
-        conf = OmegaConf.create(field_dict)
-        return OmegaConf.to_yaml(conf)
-
-    @classmethod
-    def add_parser_arguments(cls, parser):
-        if "type" in get_type_hints(cls):
-            settings_stanza = get_args(get_type_hints(cls)["type"])[0]
-        else:
-            settings_stanza = "Uncategorized"
-
-        env_prefix = getattr(cls.Config, "env_prefix", None)
-        env_prefix = env_prefix if env_prefix is not None else settings_stanza.upper()
-
-        initconf = (
-            cls.initconf.get(settings_stanza)
-            if cls.initconf and settings_stanza in cls.initconf
-            else OmegaConf.create()
-        )
-
-        # create an upcase version of the environment in
-        # order to achieve case-insensitive environment
-        # variables (the way Windows does)
-        upcase_environ = dict()
-        for key, value in os.environ.items():
-            upcase_environ[key.upper()] = value
-
-        fields = cls.__fields__
-        cls.argparse_groups = {}
-
-        for name, field in fields.items():
-            if name not in cls._excluded():
-                current_default = field.default
-
-                category = field.field_info.extra.get("category", "Uncategorized")
-                env_name = env_prefix + "_" + name
-                if category in initconf and name in initconf.get(category):
-                    field.default = initconf.get(category).get(name)
-                if env_name.upper() in upcase_environ:
-                    field.default = upcase_environ[env_name.upper()]
-                cls.add_field_argument(parser, name, field)
-
-                field.default = current_default
-
-    @classmethod
-    def cmd_name(cls, command_field: str = "type") -> str:
-        hints = get_type_hints(cls)
-        if command_field in hints:
-            return get_args(hints[command_field])[0]
-        else:
-            return "Uncategorized"
-
-    @classmethod
-    def get_parser(cls) -> ArgumentParser:
-        parser = PagingArgumentParser(
-            prog=cls.cmd_name(),
-            description=cls.__doc__,
-        )
-        cls.add_parser_arguments(parser)
-        return parser
-
-    @classmethod
-    def _excluded(cls) -> List[str]:
-        # internal fields that shouldn't be exposed as command line options
-        return ["type", "initconf"]
-
-    @classmethod
-    def _excluded_from_yaml(cls) -> List[str]:
-        # combination of deprecated parameters and internal ones that shouldn't be exposed as invokeai.yaml options
-        return [
-            "type",
-            "initconf",
-            "version",
-            "from_file",
-            "model",
-            "root",
-            "max_cache_size",
-            "max_vram_cache_size",
-            "always_use_cpu",
-            "free_gpu_mem",
-            "xformers_enabled",
-            "tiled_decode",
-        ]
-
-    class Config:
-        env_file_encoding = "utf-8"
-        arbitrary_types_allowed = True
-        case_sensitive = True
-
-    @classmethod
-    def add_field_argument(cls, command_parser, name: str, field, default_override=None):
-        field_type = get_type_hints(cls).get(name)
-        default = (
-            default_override
-            if default_override is not None
-            else field.default
-            if field.default_factory is None
-            else field.default_factory()
-        )
-        if category := field.field_info.extra.get("category"):
-            if category not in cls.argparse_groups:
-                cls.argparse_groups[category] = command_parser.add_argument_group(category)
-            argparse_group = cls.argparse_groups[category]
-        else:
-            argparse_group = command_parser
-
-        if get_origin(field_type) == Literal:
-            allowed_values = get_args(field.type_)
-            allowed_types = set()
-            for val in allowed_values:
-                allowed_types.add(type(val))
-            allowed_types_list = list(allowed_types)
-            field_type = allowed_types_list[0] if len(allowed_types) == 1 else int_or_float_or_str
-
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field_type,
-                default=default,
-                choices=allowed_values,
-                help=field.field_info.description,
-            )
-
-        elif get_origin(field_type) == Union:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=int_or_float_or_str,
-                default=default,
-                help=field.field_info.description,
-            )
-
-        elif get_origin(field_type) == list:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                nargs="*",
-                type=field.type_,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
-                help=field.field_info.description,
-            )
-        else:
-            argparse_group.add_argument(
-                f"--{name}",
-                dest=name,
-                type=field.type_,
-                default=default,
-                action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
-                help=field.field_info.description,
-            )
-
-
-def int_or_float_or_str(value: str) -> Union[int, float, str]:
-    """
-    Workaround for argparse type checking.
-    """
-    try:
-        return int(value)
-    except Exception as e:  # noqa F841
-        pass
-    try:
-        return float(value)
-    except Exception as e:  # noqa F841
-        pass
-    return str(value)

invokeai/app/services/default_graphs.py

@@ -1,73 +1,73 @@
-from ..invocations.compel import CompelInvocation
+from ..invocations.latent import LatentsToImageInvocation, DenoiseLatentsInvocation
 from ..invocations.image import ImageNSFWBlurInvocation
-from ..invocations.latent import DenoiseLatentsInvocation, LatentsToImageInvocation
 from ..invocations.noise import NoiseInvocation
+from ..invocations.compel import CompelInvocation
 from ..invocations.primitives import IntegerInvocation
 from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
 from .item_storage import ItemStorageABC
 
+
 default_text_to_image_graph_id = "539b2af5-2b4d-4d8c-8071-e54a3255fc74"
 
 
 def create_text_to_image() -> LibraryGraph:
-    graph = Graph(
-        nodes={
-            "width": IntegerInvocation(id="width", value=512),
-            "height": IntegerInvocation(id="height", value=512),
-            "seed": IntegerInvocation(id="seed", value=-1),
-            "3": NoiseInvocation(id="3"),
-            "4": CompelInvocation(id="4"),
-            "5": CompelInvocation(id="5"),
-            "6": DenoiseLatentsInvocation(id="6"),
-            "7": LatentsToImageInvocation(id="7"),
-            "8": ImageNSFWBlurInvocation(id="8"),
-        },
-        edges=[
-            Edge(
-                source=EdgeConnection(node_id="width", field="value"),
-                destination=EdgeConnection(node_id="3", field="width"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="height", field="value"),
-                destination=EdgeConnection(node_id="3", field="height"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="seed", field="value"),
-                destination=EdgeConnection(node_id="3", field="seed"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="3", field="noise"),
-                destination=EdgeConnection(node_id="6", field="noise"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="6", field="latents"),
-                destination=EdgeConnection(node_id="7", field="latents"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="4", field="conditioning"),
-                destination=EdgeConnection(node_id="6", field="positive_conditioning"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="5", field="conditioning"),
-                destination=EdgeConnection(node_id="6", field="negative_conditioning"),
-            ),
-            Edge(
-                source=EdgeConnection(node_id="7", field="image"),
-                destination=EdgeConnection(node_id="8", field="image"),
-            ),
-        ],
-    )
     return LibraryGraph(
         id=default_text_to_image_graph_id,
         name="t2i",
         description="Converts text to an image",
-        graph=graph,
+        graph=Graph(
+            nodes={
+                "width": IntegerInvocation(id="width", a=512),
+                "height": IntegerInvocation(id="height", a=512),
+                "seed": IntegerInvocation(id="seed", a=-1),
+                "3": NoiseInvocation(id="3"),
+                "4": CompelInvocation(id="4"),
+                "5": CompelInvocation(id="5"),
+                "6": DenoiseLatentsInvocation(id="6"),
+                "7": LatentsToImageInvocation(id="7"),
+                "8": ImageNSFWBlurInvocation(id="8"),
+            },
+            edges=[
+                Edge(
+                    source=EdgeConnection(node_id="width", field="a"),
+                    destination=EdgeConnection(node_id="3", field="width"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="height", field="a"),
+                    destination=EdgeConnection(node_id="3", field="height"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="seed", field="a"),
+                    destination=EdgeConnection(node_id="3", field="seed"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="3", field="noise"),
+                    destination=EdgeConnection(node_id="6", field="noise"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="6", field="latents"),
+                    destination=EdgeConnection(node_id="7", field="latents"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="4", field="conditioning"),
+                    destination=EdgeConnection(node_id="6", field="positive_conditioning"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="5", field="conditioning"),
+                    destination=EdgeConnection(node_id="6", field="negative_conditioning"),
+                ),
+                Edge(
+                    source=EdgeConnection(node_id="7", field="image"),
+                    destination=EdgeConnection(node_id="8", field="image"),
+                ),
+            ],
+        ),
         exposed_inputs=[
             ExposedNodeInput(node_path="4", field="prompt", alias="positive_prompt"),
             ExposedNodeInput(node_path="5", field="prompt", alias="negative_prompt"),
-            ExposedNodeInput(node_path="width", field="value", alias="width"),
-            ExposedNodeInput(node_path="height", field="value", alias="height"),
-            ExposedNodeInput(node_path="seed", field="value", alias="seed"),
+            ExposedNodeInput(node_path="width", field="a", alias="width"),
+            ExposedNodeInput(node_path="height", field="a", alias="height"),
+            ExposedNodeInput(node_path="seed", field="a", alias="seed"),
         ],
         exposed_outputs=[ExposedNodeOutput(node_path="8", field="image", alias="image")],
     )

invokeai/app/services/events.py

@@ -1,26 +1,28 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from typing import Any, Optional
-
 from invokeai.app.models.image import ProgressImage
-from invokeai.app.services.model_manager_service import BaseModelType, ModelInfo, ModelType, SubModelType
-from invokeai.app.services.session_queue.session_queue_common import EnqueueBatchResult, SessionQueueItem
 from invokeai.app.util.misc import get_timestamp
+from invokeai.app.services.model_manager_service import (
+    BaseModelType,
+    ModelType,
+    SubModelType,
+    ModelInfo,
+)
 
 
 class EventServiceBase:
-    queue_event: str = "queue_event"
+    session_event: str = "session_event"
 
     """Basic event bus, to have an empty stand-in when not needed"""
 
     def dispatch(self, event_name: str, payload: Any) -> None:
         pass
 
-    def __emit_queue_event(self, event_name: str, payload: dict) -> None:
-        """Queue events are emitted to a room with queue_id as the room name"""
+    def __emit_session_event(self, event_name: str, payload: dict) -> None:
         payload["timestamp"] = get_timestamp()
         self.dispatch(
-            event_name=EventServiceBase.queue_event,
+            event_name=EventServiceBase.session_event,
             payload=dict(event=event_name, data=payload),
         )
 
@@ -28,8 +30,6 @@ class EventServiceBase:
     # This will make them easier to integrate until we find a schema generator.
     def emit_generator_progress(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
@@ -39,13 +39,11 @@ class EventServiceBase:
         total_steps: int,
     ) -> None:
         """Emitted when there is generation progress"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="generator_progress",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
-                node_id=node.get("id"),
+                node=node,
                 source_node_id=source_node_id,
                 progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
@@ -56,19 +54,15 @@ class EventServiceBase:
 
     def emit_invocation_complete(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         result: dict,
         node: dict,
         source_node_id: str,
     ) -> None:
         """Emitted when an invocation has completed"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="invocation_complete",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
@@ -78,8 +72,6 @@ class EventServiceBase:
 
     def emit_invocation_error(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
@@ -87,11 +79,9 @@ class EventServiceBase:
         error: str,
     ) -> None:
         """Emitted when an invocation has completed"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="invocation_error",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
@@ -100,36 +90,28 @@ class EventServiceBase:
             ),
         )
 
-    def emit_invocation_started(
-        self, queue_id: str, queue_item_id: str, graph_execution_state_id: str, node: dict, source_node_id: str
-    ) -> None:
+    def emit_invocation_started(self, graph_execution_state_id: str, node: dict, source_node_id: str) -> None:
         """Emitted when an invocation has started"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="invocation_started",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
             ),
         )
 
-    def emit_graph_execution_complete(self, queue_id: str, queue_item_id: str, graph_execution_state_id: str) -> None:
+    def emit_graph_execution_complete(self, graph_execution_state_id: str) -> None:
         """Emitted when a session has completed all invocations"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="graph_execution_state_complete",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
             ),
         )
 
     def emit_model_load_started(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         model_name: str,
         base_model: BaseModelType,
@@ -137,11 +119,9 @@ class EventServiceBase:
         submodel: SubModelType,
     ) -> None:
         """Emitted when a model is requested"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="model_load_started",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
@@ -152,8 +132,6 @@ class EventServiceBase:
 
     def emit_model_load_completed(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         model_name: str,
         base_model: BaseModelType,
@@ -162,11 +140,9 @@ class EventServiceBase:
         model_info: ModelInfo,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="model_load_completed",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 model_name=model_name,
                 base_model=base_model,
@@ -180,18 +156,14 @@ class EventServiceBase:
 
     def emit_session_retrieval_error(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         error_type: str,
         error: str,
     ) -> None:
         """Emitted when session retrieval fails"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="session_retrieval_error",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 error_type=error_type,
                 error=error,
@@ -200,74 +172,18 @@ class EventServiceBase:
 
     def emit_invocation_retrieval_error(
         self,
-        queue_id: str,
-        queue_item_id: str,
         graph_execution_state_id: str,
         node_id: str,
         error_type: str,
         error: str,
     ) -> None:
         """Emitted when invocation retrieval fails"""
-        self.__emit_queue_event(
+        self.__emit_session_event(
             event_name="invocation_retrieval_error",
             payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
                 graph_execution_state_id=graph_execution_state_id,
                 node_id=node_id,
                 error_type=error_type,
                 error=error,
             ),
         )
-
-    def emit_session_canceled(
-        self,
-        queue_id: str,
-        queue_item_id: str,
-        graph_execution_state_id: str,
-    ) -> None:
-        """Emitted when a session is canceled"""
-        self.__emit_queue_event(
-            event_name="session_canceled",
-            payload=dict(
-                queue_id=queue_id,
-                queue_item_id=queue_item_id,
-                graph_execution_state_id=graph_execution_state_id,
-            ),
-        )
-
-    def emit_queue_item_status_changed(self, session_queue_item: SessionQueueItem) -> None:
-        """Emitted when a queue item's status changes"""
-        self.__emit_queue_event(
-            event_name="queue_item_status_changed",
-            payload=dict(
-                queue_id=session_queue_item.queue_id,
-                queue_item_id=session_queue_item.item_id,
-                status=session_queue_item.status,
-                batch_id=session_queue_item.batch_id,
-                session_id=session_queue_item.session_id,
-                error=session_queue_item.error,
-                created_at=str(session_queue_item.created_at) if session_queue_item.created_at else None,
-                updated_at=str(session_queue_item.updated_at) if session_queue_item.updated_at else None,
-                started_at=str(session_queue_item.started_at) if session_queue_item.started_at else None,
-                completed_at=str(session_queue_item.completed_at) if session_queue_item.completed_at else None,
-            ),
-        )
-
-    def emit_batch_enqueued(self, enqueue_result: EnqueueBatchResult) -> None:
-        """Emitted when a batch is enqueued"""
-        self.__emit_queue_event(
-            event_name="batch_enqueued",
-            payload=dict(
-                queue_id=enqueue_result.queue_id,
-                batch_id=enqueue_result.batch.batch_id,
-                enqueued=enqueue_result.enqueued,
-            ),
-        )
-
-    def emit_queue_cleared(self, queue_id: str) -> None:
-        """Emitted when the queue is cleared"""
-        self.__emit_queue_event(
-            event_name="queue_cleared",
-            payload=dict(queue_id=queue_id),
-        )

invokeai/app/services/graph.py

@@ -2,14 +2,13 @@
 
 import copy
 import itertools
-from typing import Annotated, Any, Optional, Union, cast, get_args, get_origin, get_type_hints
+import uuid
+from typing import Annotated, Any, Literal, Optional, Union, get_args, get_origin, get_type_hints
 
 import networkx as nx
 from pydantic import BaseModel, root_validator, validator
 from pydantic.fields import Field
 
-from invokeai.app.util.misc import uuid_string
-
 # Importing * is bad karma but needed here for node detection
 from ..invocations import *  # noqa: F401 F403
 from ..invocations.baseinvocation import (
@@ -20,8 +19,6 @@ from ..invocations.baseinvocation import (
     InvocationContext,
     OutputField,
     UIType,
-    invocation,
-    invocation_output,
 )
 
 # in 3.10 this would be "from types import NoneType"
@@ -113,10 +110,6 @@ def are_connection_types_compatible(from_type: Any, to_type: Any) -> bool:
         if to_type in get_args(from_type):
             return True
 
-        # allow int -> float, pydantic will cast for us
-        if from_type is int and to_type is float:
-            return True
-
         # if not issubclass(from_type, to_type):
         if not is_union_subtype(from_type, to_type):
             return False
@@ -138,45 +131,41 @@ def are_connections_compatible(
     return are_connection_types_compatible(from_node_field, to_node_field)
 
 
-class NodeAlreadyInGraphError(ValueError):
+class NodeAlreadyInGraphError(Exception):
     pass
 
 
-class InvalidEdgeError(ValueError):
+class InvalidEdgeError(Exception):
     pass
 
 
-class NodeNotFoundError(ValueError):
+class NodeNotFoundError(Exception):
     pass
 
 
-class NodeAlreadyExecutedError(ValueError):
-    pass
-
-
-class DuplicateNodeIdError(ValueError):
-    pass
-
-
-class NodeFieldNotFoundError(ValueError):
-    pass
-
-
-class NodeIdMismatchError(ValueError):
+class NodeAlreadyExecutedError(Exception):
     pass
 
 
 # TODO: Create and use an Empty output?
-@invocation_output("graph_output")
 class GraphInvocationOutput(BaseInvocationOutput):
-    pass
+    type: Literal["graph_output"] = "graph_output"
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "type",
+                "image",
+            ]
+        }
 
 
 # TODO: Fill this out and move to invocations
-@invocation("graph")
 class GraphInvocation(BaseInvocation):
     """Execute a graph"""
 
+    type: Literal["graph"] = "graph"
+
     # TODO: figure out how to create a default here
     graph: "Graph" = Field(description="The graph to run", default=None)
 
@@ -185,20 +174,22 @@ class GraphInvocation(BaseInvocation):
         return GraphInvocationOutput()
 
 
-@invocation_output("iterate_output")
 class IterateInvocationOutput(BaseInvocationOutput):
     """Used to connect iteration outputs. Will be expanded to a specific output."""
 
+    type: Literal["iterate_output"] = "iterate_output"
+
     item: Any = OutputField(
         description="The item being iterated over", title="Collection Item", ui_type=UIType.CollectionItem
     )
 
 
 # TODO: Fill this out and move to invocations
-@invocation("iterate", version="1.0.0")
 class IterateInvocation(BaseInvocation):
     """Iterates over a list of items"""
 
+    type: Literal["iterate"] = "iterate"
+
     collection: list[Any] = InputField(
         description="The list of items to iterate over", default_factory=list, ui_type=UIType.Collection
     )
@@ -209,17 +200,19 @@ class IterateInvocation(BaseInvocation):
         return IterateInvocationOutput(item=self.collection[self.index])
 
 
-@invocation_output("collect_output")
 class CollectInvocationOutput(BaseInvocationOutput):
+    type: Literal["collect_output"] = "collect_output"
+
     collection: list[Any] = OutputField(
         description="The collection of input items", title="Collection", ui_type=UIType.Collection
     )
 
 
-@invocation("collect", version="1.0.0")
 class CollectInvocation(BaseInvocation):
     """Collects values into a collection"""
 
+    type: Literal["collect"] = "collect"
+
     item: Any = InputField(
         description="The item to collect (all inputs must be of the same type)",
         ui_type=UIType.CollectionItem,
@@ -240,7 +233,7 @@ InvocationOutputsUnion = Union[BaseInvocationOutput.get_all_subclasses_tuple()]
 
 
 class Graph(BaseModel):
-    id: str = Field(description="The id of this graph", default_factory=uuid_string)
+    id: str = Field(description="The id of this graph", default_factory=lambda: uuid.uuid4().__str__())
     # TODO: use a list (and never use dict in a BaseModel) because pydantic/fastapi hates me
     nodes: dict[str, Annotated[InvocationsUnion, Field(discriminator="type")]] = Field(
         description="The nodes in this graph", default_factory=dict
@@ -250,59 +243,6 @@ class Graph(BaseModel):
         default_factory=list,
     )
 
-    @root_validator
-    def validate_nodes_and_edges(cls, values):
-        """Validates that all edges match nodes in the graph"""
-        nodes = cast(Optional[dict[str, BaseInvocation]], values.get("nodes"))
-        edges = cast(Optional[list[Edge]], values.get("edges"))
-
-        if nodes is not None:
-            # Validate that all node ids are unique
-            node_ids = [n.id for n in nodes.values()]
-            duplicate_node_ids = set([node_id for node_id in node_ids if node_ids.count(node_id) >= 2])
-            if duplicate_node_ids:
-                raise DuplicateNodeIdError(f"Node ids must be unique, found duplicates {duplicate_node_ids}")
-
-            # Validate that all node ids match the keys in the nodes dict
-            for k, v in nodes.items():
-                if k != v.id:
-                    raise NodeIdMismatchError(f"Node ids must match, got {k} and {v.id}")
-
-        if edges is not None and nodes is not None:
-            # Validate that all edges match nodes in the graph
-            node_ids = set([e.source.node_id for e in edges] + [e.destination.node_id for e in edges])
-            missing_node_ids = [node_id for node_id in node_ids if node_id not in nodes]
-            if missing_node_ids:
-                raise NodeNotFoundError(
-                    f"All edges must reference nodes in the graph, missing nodes: {missing_node_ids}"
-                )
-
-            # Validate that all edge fields match node fields in the graph
-            for edge in edges:
-                source_node = nodes.get(edge.source.node_id, None)
-                if source_node is None:
-                    raise NodeFieldNotFoundError(f"Edge source node {edge.source.node_id} does not exist in the graph")
-
-                destination_node = nodes.get(edge.destination.node_id, None)
-                if destination_node is None:
-                    raise NodeFieldNotFoundError(
-                        f"Edge destination node {edge.destination.node_id} does not exist in the graph"
-                    )
-
-                # output fields are not on the node object directly, they are on the output type
-                if edge.source.field not in source_node.get_output_type().__fields__:
-                    raise NodeFieldNotFoundError(
-                        f"Edge source field {edge.source.field} does not exist in node {edge.source.node_id}"
-                    )
-
-                # input fields are on the node
-                if edge.destination.field not in destination_node.__fields__:
-                    raise NodeFieldNotFoundError(
-                        f"Edge destination field {edge.destination.field} does not exist in node {edge.destination.node_id}"
-                    )
-
-        return values
-
     def add_node(self, node: BaseInvocation) -> None:
         """Adds a node to a graph
 
@@ -763,7 +703,8 @@ class Graph(BaseModel):
 class GraphExecutionState(BaseModel):
     """Tracks the state of a graph execution"""
 
-    id: str = Field(description="The id of the execution state", default_factory=uuid_string)
+    id: str = Field(description="The id of the execution state", default_factory=lambda: uuid.uuid4().__str__())
+
     # TODO: Store a reference to the graph instead of the actual graph?
     graph: Graph = Field(description="The graph being executed")
 
@@ -912,7 +853,7 @@ class GraphExecutionState(BaseModel):
             new_node = copy.deepcopy(node)
 
             # Create the node id (use a random uuid)
-            new_node.id = uuid_string()
+            new_node.id = str(uuid.uuid4())
 
             # Set the iteration index for iteration invocations
             if isinstance(new_node, IterateInvocation):
@@ -1147,7 +1088,7 @@ class ExposedNodeOutput(BaseModel):
 
 
 class LibraryGraph(BaseModel):
-    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid_string)
+    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid.uuid4)
     graph: Graph = Field(description="The graph")
     name: str = Field(description="The name of the graph")
     description: str = Field(description="The description of the graph")

invokeai/app/services/image_file_storage.py

@@ -60,7 +60,7 @@ class ImageFileStorageBase(ABC):
         image: PILImageType,
         image_name: str,
         metadata: Optional[dict] = None,
-        workflow: Optional[str] = None,
+        graph: Optional[dict] = None,
         thumbnail_size: int = 256,
     ) -> None:
         """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""
@@ -110,7 +110,7 @@ class DiskImageFileStorage(ImageFileStorageBase):
         image: PILImageType,
         image_name: str,
         metadata: Optional[dict] = None,
-        workflow: Optional[str] = None,
+        graph: Optional[dict] = None,
         thumbnail_size: int = 256,
     ) -> None:
         try:
@@ -119,23 +119,12 @@ class DiskImageFileStorage(ImageFileStorageBase):
 
             pnginfo = PngImagePlugin.PngInfo()
 
-            if metadata is not None or workflow is not None:
-                if metadata is not None:
-                    pnginfo.add_text("invokeai_metadata", json.dumps(metadata))
-                if workflow is not None:
-                    pnginfo.add_text("invokeai_workflow", workflow)
-            else:
-                # For uploaded images, we want to retain metadata. PIL strips it on save; manually add it back
-                # TODO: retain non-invokeai metadata on save...
-                original_metadata = image.info.get("invokeai_metadata", None)
-                if original_metadata is not None:
-                    pnginfo.add_text("invokeai_metadata", original_metadata)
-                original_workflow = image.info.get("invokeai_workflow", None)
-                if original_workflow is not None:
-                    pnginfo.add_text("invokeai_workflow", original_workflow)
+            if metadata is not None:
+                pnginfo.add_text("invokeai_metadata", json.dumps(metadata))
+            if graph is not None:
+                pnginfo.add_text("invokeai_graph", json.dumps(graph))
 
             image.save(image_path, "PNG", pnginfo=pnginfo)
-
             thumbnail_name = get_thumbnail_name(image_name)
             thumbnail_path = self.get_path(thumbnail_name, thumbnail=True)
             thumbnail_image = make_thumbnail(image, thumbnail_size)

invokeai/app/services/image_record_storage.py

@@ -9,7 +9,11 @@ from pydantic import BaseModel, Field
 from pydantic.generics import GenericModel
 
 from invokeai.app.models.image import ImageCategory, ResourceOrigin
-from invokeai.app.services.models.image_record import ImageRecord, ImageRecordChanges, deserialize_image_record
+from invokeai.app.services.models.image_record import (
+    ImageRecord,
+    ImageRecordChanges,
+    deserialize_image_record,
+)
 
 T = TypeVar("T", bound=BaseModel)
 
@@ -148,20 +152,24 @@ class ImageRecordStorageBase(ABC):
 
 
 class SqliteImageRecordStorage(ImageRecordStorageBase):
+    _filename: str
     _conn: sqlite3.Connection
     _cursor: sqlite3.Cursor
     _lock: threading.Lock
 
-    def __init__(self, conn: sqlite3.Connection, lock: threading.Lock) -> None:
+    def __init__(self, filename: str) -> None:
         super().__init__()
-        self._conn = conn
+        self._filename = filename
+        self._conn = sqlite3.connect(filename, check_same_thread=False)
         # Enable row factory to get rows as dictionaries (must be done before making the cursor!)
         self._conn.row_factory = sqlite3.Row
         self._cursor = self._conn.cursor()
-        self._lock = lock
+        self._lock = threading.Lock()
 
         try:
             self._lock.acquire()
+            # Enable foreign keys
+            self._conn.execute("PRAGMA foreign_keys = ON;")
             self._create_tables()
             self._conn.commit()
         finally:

invokeai/app/services/images.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from logging import Logger
-from typing import TYPE_CHECKING, Callable, Optional
+from typing import TYPE_CHECKING, Optional
 
 from PIL.Image import Image as PILImageType
 
@@ -26,7 +26,12 @@ from invokeai.app.services.image_record_storage import (
     OffsetPaginatedResults,
 )
 from invokeai.app.services.item_storage import ItemStorageABC
-from invokeai.app.services.models.image_record import ImageDTO, ImageRecord, ImageRecordChanges, image_record_to_dto
+from invokeai.app.services.models.image_record import (
+    ImageDTO,
+    ImageRecord,
+    ImageRecordChanges,
+    image_record_to_dto,
+)
 from invokeai.app.services.resource_name import NameServiceBase
 from invokeai.app.services.urls import UrlServiceBase
 from invokeai.app.util.metadata import get_metadata_graph_from_raw_session
@@ -38,27 +43,6 @@ if TYPE_CHECKING:
 class ImageServiceABC(ABC):
     """High-level service for image management."""
 
-    _on_changed_callbacks: list[Callable[[ImageDTO], None]]
-    _on_deleted_callbacks: list[Callable[[str], None]]
-
-    @abstractmethod
-    def on_changed(self, on_changed: Callable[[ImageDTO], None]) -> None:
-        """Register a callback for when an item is changed"""
-        pass
-
-    @abstractmethod
-    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
-        """Register a callback for when an item is deleted"""
-        pass
-
-    @abstractmethod
-    def _on_changed(self, item: ImageDTO) -> None:
-        pass
-
-    @abstractmethod
-    def _on_deleted(self, item_id: str) -> None:
-        pass
-
     @abstractmethod
     def create(
         self,
@@ -70,7 +54,6 @@ class ImageServiceABC(ABC):
         board_id: Optional[str] = None,
         is_intermediate: bool = False,
         metadata: Optional[dict] = None,
-        workflow: Optional[str] = None,
     ) -> ImageDTO:
         """Creates an image, storing the file and its metadata."""
         pass
@@ -180,24 +163,6 @@ class ImageServiceDependencies:
 
 class ImageService(ImageServiceABC):
     _services: ImageServiceDependencies
-    _on_changed_callbacks: list[Callable[[ImageDTO], None]] = list()
-    _on_deleted_callbacks: list[Callable[[str], None]] = list()
-
-    def on_changed(self, on_changed: Callable[[ImageDTO], None]) -> None:
-        """Register a callback for when an item is changed"""
-        self._on_changed_callbacks.append(on_changed)
-
-    def on_deleted(self, on_deleted: Callable[[str], None]) -> None:
-        """Register a callback for when an item is deleted"""
-        self._on_deleted_callbacks.append(on_deleted)
-
-    def _on_changed(self, item: ImageDTO) -> None:
-        for callback in self._on_changed_callbacks:
-            callback(item)
-
-    def _on_deleted(self, item_id: str) -> None:
-        for callback in self._on_deleted_callbacks:
-            callback(item_id)
 
     def __init__(self, services: ImageServiceDependencies):
         self._services = services
@@ -212,7 +177,6 @@ class ImageService(ImageServiceABC):
         board_id: Optional[str] = None,
         is_intermediate: bool = False,
         metadata: Optional[dict] = None,
-        workflow: Optional[str] = None,
     ) -> ImageDTO:
         if image_origin not in ResourceOrigin:
             raise InvalidOriginException
@@ -222,16 +186,16 @@ class ImageService(ImageServiceABC):
 
         image_name = self._services.names.create_image_name()
 
-        # TODO: Do we want to store the graph in the image at all? I don't think so...
-        # graph = None
-        # if session_id is not None:
-        #     session_raw = self._services.graph_execution_manager.get_raw(session_id)
-        #     if session_raw is not None:
-        #         try:
-        #             graph = get_metadata_graph_from_raw_session(session_raw)
-        #         except Exception as e:
-        #             self._services.logger.warn(f"Failed to parse session graph: {e}")
-        #             graph = None
+        graph = None
+
+        if session_id is not None:
+            session_raw = self._services.graph_execution_manager.get_raw(session_id)
+            if session_raw is not None:
+                try:
+                    graph = get_metadata_graph_from_raw_session(session_raw)
+                except Exception as e:
+                    self._services.logger.warn(f"Failed to parse session graph: {e}")
+                    graph = None
 
         (width, height) = image.size
 
@@ -253,10 +217,9 @@ class ImageService(ImageServiceABC):
             )
             if board_id is not None:
                 self._services.board_image_records.add_image_to_board(board_id=board_id, image_name=image_name)
-            self._services.image_files.save(image_name=image_name, image=image, metadata=metadata, workflow=workflow)
+            self._services.image_files.save(image_name=image_name, image=image, metadata=metadata, graph=graph)
             image_dto = self.get_dto(image_name)
 
-            self._on_changed(image_dto)
             return image_dto
         except ImageRecordSaveException:
             self._services.logger.error("Failed to save image record")
@@ -275,9 +238,7 @@ class ImageService(ImageServiceABC):
     ) -> ImageDTO:
         try:
             self._services.image_records.update(image_name, changes)
-            image_dto = self.get_dto(image_name)
-            self._on_changed(image_dto)
-            return image_dto
+            return self.get_dto(image_name)
         except ImageRecordSaveException:
             self._services.logger.error("Failed to update image record")
             raise
@@ -416,7 +377,6 @@ class ImageService(ImageServiceABC):
         try:
             self._services.image_files.delete(image_name)
             self._services.image_records.delete(image_name)
-            self._on_deleted(image_name)
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image record")
             raise
@@ -433,8 +393,6 @@ class ImageService(ImageServiceABC):
             for image_name in image_names:
                 self._services.image_files.delete(image_name)
             self._services.image_records.delete_many(image_names)
-            for image_name in image_names:
-                self._on_deleted(image_name)
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image records")
             raise
@@ -451,7 +409,6 @@ class ImageService(ImageServiceABC):
             count = len(image_names)
             for image_name in image_names:
                 self._services.image_files.delete(image_name)
-                self._on_deleted(image_name)
             return count
         except ImageRecordDeleteException:
             self._services.logger.error("Failed to delete image records")