Clean up erroniously added lines

## What type of PR is this? (check all applicable)

- [x] Refactor
- [x] Feature
- [x] Bug Fix
- [?] Optimization


## Have you discussed this change with the InvokeAI team?
- [x] No

     
## Description

- Fixed filter type select using `images` instead of `all` -- Probably
some merge conflict.
- Added loading state for model lists. Handy when the model list takes
longer than a second for any reason to fetch. Better to show this than
an empty screen.
- Refactored the render model list function so we modify the display
component in one area rather than have repeated code.

### Other Issues

- The list can get a bit laggy on initial load when you have a hundreds
of models / loras. This needs to be fixed. Will make another PR for
this.

.dev_scripts/diff_images.py

@@ -20,13 +20,13 @@ def calc_images_mean_L1(image1_path, image2_path):
 
 def parse_args():
     parser = argparse.ArgumentParser()
-    parser.add_argument('image1_path')
-    parser.add_argument('image2_path')
+    parser.add_argument("image1_path")
+    parser.add_argument("image2_path")
     args = parser.parse_args()
     return args
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     args = parse_args()
     mean_L1 = calc_images_mean_L1(args.image1_path, args.image2_path)
     print(mean_L1)

.git-blame-ignore-revs

@@ -1 +1,2 @@
 b3dccfaeb636599c02effc377cdd8a87d658256c
+218b6d0546b990fc449c876fb99f44b50c4daa35

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

@@ -1,11 +1,11 @@
 name: Close inactive issues
 on:
   schedule:
-    - cron: "00 6 * * *"
+    - cron: "00 4 * * *"
 
 env:
-  DAYS_BEFORE_ISSUE_STALE: 14
-  DAYS_BEFORE_ISSUE_CLOSE: 28
+  DAYS_BEFORE_ISSUE_STALE: 30
+  DAYS_BEFORE_ISSUE_CLOSE: 14
 
 jobs:
   close-issues:
@@ -14,7 +14,7 @@ jobs:
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/stale@v5
+      - uses: actions/stale@v8
         with:
           days-before-issue-stale: ${{ env.DAYS_BEFORE_ISSUE_STALE }}
           days-before-issue-close: ${{ env.DAYS_BEFORE_ISSUE_CLOSE }}
@@ -23,5 +23,6 @@ jobs:
           close-issue-message: "Due to inactivity, this issue was automatically closed. If you are still experiencing the issue, please recreate the issue."
           days-before-pr-stale: -1
           days-before-pr-close: -1
+          exempt-issue-labels: "Active Issue"
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           operations-per-run: 500

.github/workflows/lint-frontend.yml

@@ -2,8 +2,6 @@ name: Lint frontend
 
 on:
   pull_request:
-    paths:
-      - 'invokeai/frontend/web/**'
     types:
       - 'ready_for_review'
       - 'opened'
@@ -11,8 +9,6 @@ on:
   push:
     branches:
       - 'main'
-    paths:
-      - 'invokeai/frontend/web/**'
   merge_group:
   workflow_dispatch:
 

.github/workflows/mkdocs-material.yml

@@ -2,7 +2,7 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'refs/heads/v2.3'
+      - 'refs/heads/main'
 
 permissions:
     contents: write

.github/workflows/style-checks.yml

@@ -0,0 +1,27 @@
+name: Black  # TODO: add isort and flake8 later
+
+on:
+  pull_request: {}
+  push:
+    branches: master
+    tags: "*"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies with pip
+        run: |
+          pip install --upgrade pip wheel
+          pip install .[test]
+
+      # - run: isort --check-only .
+      - run: black --check .
+      # - run: flake8

.gitignore

@@ -38,7 +38,6 @@ develop-eggs/
 downloads/
 eggs/
 .eggs/
-lib/
 lib64/
 parts/
 sdist/

.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+# See https://pre-commit.com/ for usage and config
+repos:
+- repo: local
+  hooks:
+  - id: black
+    name: black
+    stages: [commit]
+    language: system
+    entry: black
+    types: [python]

LICENSE-SDXL.txt

@@ -0,0 +1,290 @@
+Copyright (c) 2023 Stability AI
+CreativeML Open RAIL++-M License dated July 26, 2023
+
+Section I: PREAMBLE
+
+Multimodal generative models are being widely adopted and used, and
+have the potential to transform the way artists, among other
+individuals, conceive and benefit from AI or ML technologies as a tool
+for content creation.
+
+Notwithstanding the current and potential benefits that these
+artifacts can bring to society at large, there are also concerns about
+potential misuses of them, either due to their technical limitations
+or ethical considerations.
+
+In short, this license strives for both the open and responsible
+downstream use of the accompanying model. When it comes to the open
+character, we took inspiration from open source permissive licenses
+regarding the grant of IP rights. Referring to the downstream
+responsible use, we added use-based restrictions not permitting the
+use of the model in very specific scenarios, in order for the licensor
+to be able to enforce the license in case potential misuses of the
+Model may occur. At the same time, we strive to promote open and
+responsible research on generative models for art and content
+generation.
+
+Even though downstream derivative versions of the model could be
+released under different licensing terms, the latter will always have
+to include - at minimum - the same use-based restrictions as the ones
+in the original license (this license). We believe in the intersection
+between open and responsible AI development; thus, this agreement aims
+to strike a balance between both in order to enable responsible
+open-science in the field of AI.
+
+This CreativeML Open RAIL++-M License governs the use of the model
+(and its derivatives) and is informed by the model card associated
+with the model.
+
+NOW THEREFORE, You and Licensor agree as follows:
+
+Definitions
+
+"License" means the terms and conditions for use, reproduction, and
+Distribution as defined in this document.
+
+"Data" means a collection of information and/or content extracted from
+the dataset used with the Model, including to train, pretrain, or
+otherwise evaluate the Model. The Data is not licensed under this
+License.
+
+"Output" means the results of operating a Model as embodied in
+informational content resulting therefrom.
+
+"Model" means any accompanying machine-learning based assemblies
+(including checkpoints), consisting of learnt weights, parameters
+(including optimizer states), corresponding to the model architecture
+as embodied in the Complementary Material, that have been trained or
+tuned, in whole or in part on the Data, using the Complementary
+Material.
+
+"Derivatives of the Model" means all modifications to the Model, works
+based on the Model, or any other model which is created or initialized
+by transfer of patterns of the weights, parameters, activations or
+output of the Model, to the other model, in order to cause the other
+model to perform similarly to the Model, including - but not limited
+to - distillation methods entailing the use of intermediate data
+representations or methods based on the generation of synthetic data
+by the Model for training the other model.
+
+"Complementary Material" means the accompanying source code and
+scripts used to define, run, load, benchmark or evaluate the Model,
+and used to prepare data for training or evaluation, if any. This
+includes any accompanying documentation, tutorials, examples, etc, if
+any.
+
+"Distribution" means any transmission, reproduction, publication or
+other sharing of the Model or Derivatives of the Model to a third
+party, including providing the Model as a hosted service made
+available by electronic or other remote means - e.g. API-based or web
+access.
+
+"Licensor" means the copyright owner or entity authorized by the
+copyright owner that is granting the License, including the persons or
+entities that may have rights in the Model and/or distributing the
+Model.
+
+"You" (or "Your") means an individual or Legal Entity exercising
+permissions granted by this License and/or making use of the Model for
+whichever purpose and in any field of use, including usage of the
+Model in an end-use application - e.g. chatbot, translator, image
+generator.
+
+"Third Parties" means individuals or legal entities that are not under
+common control with Licensor or You.
+
+"Contribution" means any work of authorship, including the original
+version of the Model and any modifications or additions to that Model
+or Derivatives of the Model thereof, that is intentionally submitted
+to Licensor for inclusion in the Model by the copyright owner or by an
+individual or Legal Entity authorized to submit on behalf of the
+copyright owner. For the purposes of this definition, "submitted"
+means any form of electronic, verbal, or written communication sent to
+the Licensor or its representatives, including but not limited to
+communication on electronic mailing lists, source code control
+systems, and issue tracking systems that are managed by, or on behalf
+of, the Licensor for the purpose of discussing and improving the
+Model, but excluding communication that is conspicuously marked or
+otherwise designated in writing by the copyright owner as "Not a
+Contribution."
+
+"Contributor" means Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Model.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+
+Both copyright and patent grants apply to the Model, Derivatives of
+the Model and Complementary Material. The Model and Derivatives of the
+Model are subject to additional terms as described in
+
+Section III.
+
+Grant of Copyright License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+copyright license to reproduce, prepare, publicly display, publicly
+perform, sublicense, and distribute the Complementary Material, the
+Model, and Derivatives of the Model.
+
+Grant of Patent License. Subject to the terms and conditions of this
+License and where and as applicable, each Contributor hereby grants to
+You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
+irrevocable (except as stated in this paragraph) patent license to
+make, have made, use, offer to sell, sell, import, and otherwise
+transfer the Model and the Complementary Material, where such license
+applies only to those patent claims licensable by such Contributor
+that are necessarily infringed by their Contribution(s) alone or by
+combination of their Contribution(s) with the Model to which such
+Contribution(s) was submitted. If You institute patent litigation
+against any entity (including a cross-claim or counterclaim in a
+lawsuit) alleging that the Model and/or Complementary Material or a
+Contribution incorporated within the Model and/or Complementary
+Material constitutes direct or contributory patent infringement, then
+any patent licenses granted to You under this License for the Model
+and/or Work shall terminate as of the date such litigation is asserted
+or filed.
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+Distribution and Redistribution. You may host for Third Party remote
+access purposes (e.g. software-as-a-service), reproduce and distribute
+copies of the Model or Derivatives of the Model thereof in any medium,
+with or without modifications, provided that You meet the following
+conditions: Use-based restrictions as referenced in paragraph 5 MUST
+be included as an enforceable provision by You in any type of legal
+agreement (e.g. a license) governing the use and/or distribution of
+the Model or Derivatives of the Model, and You shall give notice to
+subsequent users You Distribute to, that the Model or Derivatives of
+the Model are subject to paragraph 5. This provision does not apply to
+the use of Complementary Material. You must give any Third Party
+recipients of the Model or Derivatives of the Model a copy of this
+License; You must cause any modified files to carry prominent notices
+stating that You changed the files; You must retain all copyright,
+patent, trademark, and attribution notices excluding those notices
+that do not pertain to any part of the Model, Derivatives of the
+Model. You may add Your own copyright statement to Your modifications
+and may provide additional or different license terms and conditions -
+respecting paragraph 4.a. - for use, reproduction, or Distribution of
+Your modifications, or for any such Derivatives of the Model as a
+whole, provided Your use, reproduction, and Distribution of the Model
+otherwise complies with the conditions stated in this License.
+
+Use-based restrictions. The restrictions set forth in Attachment A are
+considered Use-based restrictions. Therefore You cannot use the Model
+and the Derivatives of the Model for the specified restricted
+uses. You may use the Model subject to this License, including only
+for lawful purposes and in accordance with the License. Use may
+include creating any content with, finetuning, updating, running,
+training, evaluating and/or reparametrizing the Model. You shall
+require all of Your users who use the Model or a Derivative of the
+Model to comply with the terms of this paragraph (paragraph 5).
+
+The Output You Generate.  Except as set forth herein, Licensor claims
+no rights in the Output You generate using the Model. You are
+accountable for the Output you generate and its subsequent uses. No
+use of the output can contravene any provision as stated in the
+License.
+
+Section IV: OTHER PROVISIONS
+
+Updates and Runtime Restrictions. To the maximum extent permitted by
+law, Licensor reserves the right to restrict (remotely or otherwise)
+usage of the Model in violation of this License.
+
+Trademarks and related. Nothing in this License permits You to make
+use of Licensors’ trademarks, trade names, logos or to otherwise
+suggest endorsement or misrepresent the relationship between the
+parties; and any rights not expressly granted herein are reserved by
+the Licensors.
+
+Disclaimer of Warranty. Unless required by applicable law or agreed to
+in writing, Licensor provides the Model and the Complementary Material
+(and each Contributor provides its Contributions) on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+implied, including, without limitation, any warranties or conditions
+of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Model, Derivatives of
+the Model, and the Complementary Material and assume any risks
+associated with Your exercise of permissions under this License.
+
+Limitation of Liability. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise, unless
+required by applicable law (such as deliberate and grossly negligent
+acts) or agreed to in writing, shall any Contributor be liable to You
+for damages, including any direct, indirect, special, incidental, or
+consequential damages of any character arising as a result of this
+License or out of the use or inability to use the Model and the
+Complementary Material (including but not limited to damages for loss
+of goodwill, work stoppage, computer failure or malfunction, or any
+and all other commercial damages or losses), even if such Contributor
+has been advised of the possibility of such damages.
+
+Accepting Warranty or Additional Liability. While redistributing the
+Model, Derivatives of the Model and the Complementary Material
+thereof, You may choose to offer, and charge a fee for, acceptance of
+support, warranty, indemnity, or other liability obligations and/or
+rights consistent with this License. However, in accepting such
+obligations, You may act only on Your own behalf and on Your sole
+responsibility, not on behalf of any other Contributor, and only if
+You agree to indemnify, defend, and hold each Contributor harmless for
+any liability incurred by, or claims asserted against, such
+Contributor by reason of your accepting any such warranty or
+additional liability.
+
+If any provision of this License is held to be invalid, illegal or
+unenforceable, the remaining provisions shall be unaffected thereby
+and remain valid as if such provision had not been set forth herein.
+
+
+END OF TERMS AND CONDITIONS
+
+Attachment A
+
+Use Restrictions
+
+You agree not to use the Model or Derivatives of the Model:
+
+* In any way that violates any applicable national, federal, state,
+local or international law or regulation;
+
+* For the purpose of exploiting, harming or attempting to exploit or
+harm minors in any way;
+
+* To generate or disseminate verifiably false information and/or
+  content with the purpose of harming others;
+
+* To generate or disseminate personal identifiable information that
+  can be used to harm an individual;
+
+* To defame, disparage or otherwise harass others;
+
+* For fully automated decision making that adversely impacts an
+  individual’s legal rights or otherwise creates or modifies a
+  binding, enforceable obligation;
+
+* For any use intended to or which has the effect of discriminating
+  against or harming individuals or groups based on online or offline
+  social behavior or known or predicted personal or personality
+  characteristics;
+
+* To exploit any of the vulnerabilities of a specific group of persons
+  based on their age, social, physical or mental characteristics, in
+  order to materially distort the behavior of a person pertaining to
+  that group in a manner that causes or is likely to cause that person
+  or another person physical or psychological harm;
+
+* For any use intended to or which has the effect of discriminating
+  against individuals or groups based on legally protected
+  characteristics or categories;
+
+* To provide medical advice and medical results interpretation;
+
+* To generate or disseminate information for the purpose to be used
+  for administration of justice, law enforcement, immigration or
+  asylum processes, such as predicting an individual will commit
+  fraud/crime commitment (e.g. by text profiling, drawing causal
+  relationships between assertions made in documents, indiscriminate
+  and arbitrarily-targeted use).
+

README.md

@@ -36,15 +36,6 @@
 
 </div>
 
-_**Note: This is an alpha release. Bugs are expected and not all
-features are fully implemented. Please use the GitHub [Issues
-pages](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen)
-to report unexpected problems. Also note that InvokeAI root directory
-which contains models, outputs and configuration files, has changed
-between the 2.x and 3.x release. If you wish to use your v2.3 root
-directory with v3.0, please follow the directions in [Migrating a 2.3
-root directory to 3.0](#migrating-to-3).**_
-
 InvokeAI is a leading creative engine built to empower professionals
 and enthusiasts alike. Generate and create stunning visual media using
 the latest AI-driven technologies. InvokeAI offers an industry leading
@@ -132,7 +123,7 @@ and go to http://localhost:9090.
 
 ### Command-Line Installation (for developers and users familiar with Terminals)
 
-You must have Python 3.9 or 3.10 installed on your machine. Earlier or
+You must have Python 3.9 through 3.11 installed on your machine. Earlier or
 later versions are not supported.
 Node.js also needs to be installed along with yarn (can be installed with
 the command `npm install -g yarn` if needed)
@@ -264,19 +255,24 @@ old models directory (which contains the models selected at install
 time) will be renamed `models.orig` and can be deleted once you have
 confirmed that the migration was successful.
 
+ If you wish, you can pass the 2.3 root directory to both `--from` and
+`--to` in order to update in place. Warning: this directory will no
+longer be usable with InvokeAI 2.3.
+
 #### Migrating in place
 
 For the adventurous, you may do an in-place upgrade from 2.3 to 3.0
-without touching the command line. The recipe is as follows>
+without touching the command line. ***This recipe does not work on
+Windows platforms due to a bug in the Windows version of the 2.3
+upgrade script.** See the next section for a Windows recipe.
+
+##### For Mac and Linux Users:
 
 1. Launch the InvokeAI launcher script in your current v2.3 root directory.
 
 2. Select option [9] "Update InvokeAI" to bring up the updater dialog.
 
-3a. During the alpha release phase, select option [3] and manually
-enter the tag name `v3.0.0+a2`.
-
-3b. Once 3.0 is released, select option [1] to upgrade to the latest release.
+3. Select option [1] to upgrade to the latest release.
 
 4. Once the upgrade is finished you will be returned to the launcher
 menu. Select option [7] "Re-run the configure script to fix a broken
@@ -295,14 +291,33 @@ worked, you can safely remove these files. Alternatively you can
 restore a working v2.3 directory by removing the new files and
 restoring the ".orig" files' original names.
 
+##### For Windows Users:
+
+Windows Users can upgrade with the
+
+1. Enter the 2.3 root directory you wish to upgrade
+2. Launch `invoke.sh` or `invoke.bat`
+3. Select the "Developer's console" option [8]
+4. Type the following commands
+
+```
+pip install "invokeai @ https://github.com/invoke-ai/InvokeAI/archive/refs/tags/v3.0.0" --use-pep517 --upgrade
+invokeai-configure --root .
+```
+(Replace `v3.0.0` with the current release number if this document is out of date).
+
+The first command will install and upgrade new software to run
+InvokeAI. The second will prepare the 2.3 directory for use with 3.0.
+You may now launch the WebUI in the usual way, by selecting option [1]
+from the launcher script
+
 #### Migration Caveats
 
 The migration script will migrate your invokeai settings and models,
 including textual inversion models, LoRAs and merges that you may have
 installed previously. However it does **not** migrate the generated
-images stored in your 2.3-format outputs directory. The released
-version of 3.0 is expected to have an interface for importing an
-entire directory of image files as a batch.
+images stored in your 2.3-format outputs directory. You will need to
+manually import selected images into the 3.0 gallery via drag-and-drop.
 
 ## Hardware Requirements
 
@@ -314,9 +329,12 @@ AMD card (using the ROCm driver).
 
 You will need one of the following:
 
-- An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+- An NVIDIA-based graphics card with 4 GB or more VRAM memory. 6-8 GB
+  of VRAM is highly recommended for rendering using the Stable
+  Diffusion XL models
 - An Apple computer with an M1 chip.
-- An AMD-based graphics card with 4GB or more VRAM memory. (Linux only)
+- An AMD-based graphics card with 4GB or more VRAM memory (Linux
+  only), 6-8 GB for XL rendering.
 
 We do not recommend the GTX 1650 or 1660 series video cards. They are
 unable to run in half-precision mode and do not have sufficient VRAM
@@ -349,13 +367,12 @@ Invoke AI provides an organized gallery system for easily storing, accessing, an
 ### Other features
 
 - *Support for both ckpt and diffusers models*
-- *SD 2.0, 2.1 support*
+- *SD 2.0, 2.1, XL support*
 - *Upscaling Tools*
 - *Embedding Manager & Support*
 - *Model Manager & Support*
 - *Node-Based Architecture*
 - *Node-Based Plug-&-Play UI (Beta)*
-- *SDXL Support* (Coming soon)
 
 ### Latest Changes
 

docs/contributing/CONTRIBUTING.md

@@ -1,42 +1,38 @@
+# How to Contribute
+
 ## Welcome to Invoke AI
-
-We're thrilled to have you here and we're excited for you to contribute. 
-
 Invoke AI originated as a project built by the community, and that vision carries forward today as we aim to build the best pro-grade tools available. We work together to incorporate the latest in AI/ML research, making these tools available in over 20 languages to artists and creatives around the world as part of our fully permissive OSS project designed for individual users to self-host and use.
 
-Here are some guidelines to help you get started:
 
-### Technical Prerequisites
+## 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.
 
-Front-end: You'll need a working knowledge of React and TypeScript.
+To join, just raise your hand on the InvokeAI Discord server (#dev-chat) or the GitHub discussion board.
 
-Back-end: Depending on the scope of your contribution, you may need to know SQLite, FastAPI, Python, and Socketio. Also, a good majority of the backend logic involved in processing images is built in a modular way using a concept called "Nodes", which are isolated functions that carry out individual, discrete operations. This design allows for easy contributions of novel pipelines and capabilities.
+### Areas of contribution: 
 
-### How to Submit Contributions
+#### 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.
 
-To start contributing, please follow these steps:
+#### Documentation
+If you’d like to help with documentation, please see our [documentation guide](contribution_guides/documenation.md).
 
-1. Familiarize yourself with our roadmap and open projects to see where your skills and interests align. These documents can serve as a source of inspiration.
-2. Open a Pull Request (PR) with a clear description of the feature you're adding or the problem you're solving. Make sure your contribution aligns with the project's vision.
-3. Adhere to general best practices. This includes assuming interoperability with other nodes, keeping the scope of your functions as small as possible, and organizing your code according to our architecture documents.
+#### Translation
+If you'd like to help with translation, please see our [translation guide](docs/contributing/.contribution_guides/translation.md).
 
-### Types of Contributions We're Looking For
+#### Tutorials 
+Please reach out to @imic or @hipsterusername on [Discord](https://discord.gg/ZmtBAhwWhy) to help create tutorials for InvokeAI.
 
-We welcome all contributions that improve the project. Right now, we're especially looking for:
+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.
 
-1. Quality of life (QOL) enhancements on the front-end.
-2. New backend capabilities added through nodes.
-3. Incorporating additional optimizations from the broader open-source software community.
 
-### Communication and Decision-making Process
+### Contributors
 
-Project maintainers and code owners review PRs to ensure they align with the project's goals. They may provide design or architectural guidance, suggestions on user experience, or provide more significant feedback on the contribution itself. Expect to receive feedback on your submissions, and don't hesitate to ask questions or propose changes.
+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.
 
-For more robust discussions, or if you're planning to add capabilities not currently listed on our roadmap, please reach out to us on our Discord server. That way, we can ensure your proposed contribution aligns with the project's direction before you start writing code.
+### Code of Conduct
 
-### Code of Conduct and Contribution Expectations
-
-We want everyone in our community to have a positive experience. To facilitate this, we've established a code of conduct and a statement of values that we expect all contributors to adhere to. Please take a moment to review these documents—they're essential to maintaining a respectful and inclusive environment.
+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.
 
 By making a contribution to this project, you certify that:
 
@@ -49,6 +45,12 @@ This disclaimer is not a license and does not grant any rights or permissions. Y
 
 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
+
+For support, please use this repository's [GitHub Issues](https://github.com/invoke-ai/InvokeAI/issues), or join the [Discord](https://discord.gg/ZmtBAhwWhy).
+
+Original portions of the software are Copyright (c) 2023 by respective contributors.
+
 ---
 
 Remember, your contributions help make this project great. We're excited to see what you'll bring to our community!

docs/contributing/contribution_guides/development.md

@@ -0,0 +1,91 @@
+# Development
+
+## **What do I need to know to help?**
+
+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. 
+
+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) or [translation](translation.md).
+
+There are two paths to making a development contribution: 
+
+1. Choosing an open issue to address. Open issues can be found in the [Issues](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen) section of the InvokeAI repository. These are tagged by the issue type (bug, enhancement, etc.) along with the “good first issues” tag denoting if they are suitable for first time contributors.
+    1. Additional items can be found on our [roadmap](https://github.com/orgs/invoke-ai/projects/7). The roadmap is organized in terms of priority, and contains features of varying size and complexity. If there is an inflight item you’d like to help with, reach out to the contributor assigned to the item to see how you can help. 
+2. Opening a new issue or feature to add. **Please make sure you have searched through existing issues before creating new ones.**
+
+*Regardless of what you choose, please post in the  [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord before you start development in order to confirm that the issue or feature is aligned with the current direction of the project. We value our contributors time and effort and want to ensure that no one’s time is being misspent.*
+
+## Best Practices: 
+* Keep your pull requests small. Smaller pull requests are more likely to be accepted and merged
+* Comments! Commenting your code helps reviwers easily understand your contribution
+* Use Python and Typescript’s typing systems, and consider using an editor with [LSP](https://microsoft.github.io/language-server-protocol/) support to streamline development
+* Make all communications public. This ensure knowledge is shared with the whole community
+
+## **How do I make a contribution?**
+
+Never made an open source contribution before? Wondering how contributions work in our project? Here's a quick rundown!
+
+Before starting these steps, ensure you have your local environment [configured for development](../LOCAL_DEVELOPMENT.md).
+
+1.  Find a [good first issue](https://github.com/invoke-ai/InvokeAI/contribute) that you are interested in addressing or a feature that you would like to add. Then, reach out to our team in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord to ensure you are  setup for success. 
+2. Fork the [InvokeAI](https://github.com/invoke-ai/InvokeAI) repository to your GitHub profile. This means that you will have a copy of the repository under **your-GitHub-username/InvokeAI**.
+3. Clone the repository to your local machine using:
+
+```bash
+git clone https://github.com/your-GitHub-username/InvokeAI.git
+```
+
+If you're unfamiliar with using Git through the commandline, [GitHub Desktop](https://desktop.github.com) is a easy-to-use alternative with a UI. You can do all the same steps listed here, but through the interface. 
+
+4. Create a new branch for your fix using:
+
+```bash
+git checkout -b branch-name-here
+```
+
+5. Make the appropriate changes for the issue you are trying to address or the feature that you want to add.
+6. Add the file contents of the changed files to the "snapshot" git uses to manage the state of the project, also known as the index:
+
+```bash
+git add insert-paths-of-changed-files-here
+```
+
+7. Store the contents of the index with a descriptive message.
+
+```bash
+git commit -m "Insert a short message of the changes made here"
+```
+
+8. Push the changes to the remote repository using
+
+```markdown
+git push origin branch-name-here
+```
+
+9. Submit a pull request to the **main** branch of the InvokeAI repository.
+10. Title the pull request with a short description of the changes made and the issue or bug number associated with your change. For example, you can title an issue like so "Added more log outputting to resolve #1234".
+11. In the description of the pull request, explain the changes that you made, any issues you think exist with the pull request you made, and any questions you have for the maintainer. It's OK if your pull request is not perfect (no pull request is), the reviewer will be able to help you fix any problems and improve it!
+12. Wait for the pull request to be reviewed by other collaborators.
+13. Make changes to the pull request if the reviewer(s) recommend them.
+14. Celebrate your success after your pull request is merged!
+
+If you’d like to learn more about contributing to Open Source projects, here is a [Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github). 
+
+## **Where can I go for help?**
+
+If you need help, you can ask questions in the [#dev-chat](https://discord.com/channels/1020123559063990373/1049495067846524939) channel of the Discord.
+
+For frontend related work, **@pyschedelicious** is the best person to reach out to. 
+
+For backend related work, please reach out to **@blessedcoolant**, **@lstein**, **@StAlKeR7779** or **@pyschedelicious**.
+
+## **What does the Code of Conduct mean for me?**
+
+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/development_guides/contributingToFrontend.md

@@ -0,0 +1,75 @@
+# Contributing to the Frontend
+
+# InvokeAI Web UI
+
+- [InvokeAI Web UI](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#invokeai-web-ui)
+    - [Stack](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#stack)
+    - [Contributing](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#contributing)
+        - [Dev Environment](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#dev-environment)
+        - [Production builds](https://github.com/invoke-ai/InvokeAI/tree/main/invokeai/frontend/web/docs#production-builds)
+
+The UI is a fairly straightforward Typescript React app, with the Unified Canvas being more complex.
+
+Code is located in `invokeai/frontend/web/` for review.
+
+## Stack
+
+State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). We lean heavily on RTK:
+
+- `createAsyncThunk` for HTTP requests
+- `createEntityAdapter` for fetching images and models
+- `createListenerMiddleware` for workflows
+
+The API client and associated types are generated from the OpenAPI schema. See API_CLIENT.md.
+
+Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a simple socket.io redux middleware to help).
+
+[Chakra-UI](https://github.com/chakra-ui/chakra-ui) & [Mantine](https://github.com/mantinedev/mantine) for components and styling.
+
+[Konva](https://github.com/konvajs/react-konva) for the canvas, but we are pushing the limits of what is feasible with it (and HTML canvas in general). We plan to rebuild it with [PixiJS](https://github.com/pixijs/pixijs) to take advantage of WebGL's improved raster handling.
+
+[Vite](https://vitejs.dev/) for bundling.
+
+Localisation is via [i18next](https://github.com/i18next/react-i18next), but translation happens on our [Weblate](https://hosted.weblate.org/engage/invokeai/) project. Only the English source strings should be changed on this repo.
+
+## Contributing
+
+Thanks for your interest in contributing to the InvokeAI Web UI!
+
+We encourage you to ping @psychedelicious and @blessedcoolant on [Discord](https://discord.gg/ZmtBAhwWhy) if you want to contribute, just to touch base and ensure your work doesn't conflict with anything else going on. The project is very active.
+
+### Dev Environment
+
+**Setup** 
+
+1. Install [node](https://nodejs.org/en/download/). You can confirm node is installed with:
+```bash
+node --version
+```
+2. Install [yarn classic](https://classic.yarnpkg.com/lang/en/) and confirm it is installed by running this:
+```bash
+npm install --global yarn
+yarn --version
+```
+
+From `invokeai/frontend/web/` run `yarn install` to get everything set up.
+
+Start everything in dev mode:
+1. Ensure your virtual environment is running
+2. Start the dev server: `yarn dev`
+3. Start the InvokeAI Nodes backend: `python scripts/invokeai-web.py # run from the repo root`
+4. Point your browser to the dev server address e.g. [http://localhost:5173/](http://localhost:5173/)
+
+### VSCode Remote Dev
+
+We've noticed an intermittent issue with the VSCode Remote Dev port forwarding. If you use this feature of VSCode, you may intermittently click the Invoke button and then get nothing until the request times out. Suggest disabling the IDE's port forwarding feature and doing it manually via SSH:
+
+`ssh -L 9090:localhost:9090 -L 5173:localhost:5173 user@host`
+
+### Production builds
+
+For a number of technical and logistical reasons, we need to commit UI build artefacts to the repo.
+
+If you submit a PR, there is a good chance we will ask you to include a separate commit with a build of the app.
+
+To build for production, run `yarn build`.

docs/contributing/contribution_guides/documentation.md

@@ -0,0 +1,13 @@
+# Documentation
+
+Documentation is an important part of any open source project. It provides a clear and concise way to communicate how the software works, how to use it, and how to troubleshoot issues. Without proper documentation, it can be difficult for users to understand the purpose and functionality of the project. 
+
+## Contributing
+
+All documentation is maintained in the InvokeAI GitHub repository. If you come across documentation that is out of date or incorrect, please submit a pull request with the necessary changes. 
+
+When updating or creating documentation, please keep in mind InvokeAI is a tool for everyone, not just those who have familiarity with generative art. 
+
+## Help & Questions
+
+Please ping @imic1 or @hipsterusername in the [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.

docs/contributing/contribution_guides/translation.md

@@ -0,0 +1,19 @@
+# Translation
+
+InvokeAI uses [Weblate](https://weblate.org/) for translation. Weblate is a FOSS project providing a scalable translation service. Weblate automates the tedious parts of managing translation of a growing project, and the service is generously provided at no cost to FOSS projects like InvokeAI.
+
+## Contributing
+
+If you'd like to contribute by adding or updating a translation, please visit our [Weblate project](https://hosted.weblate.org/engage/invokeai/). You'll need to sign in with your GitHub account (a number of other accounts are supported, including Google).
+
+Once signed in, select a language and then the Web UI component. From here you can Browse and Translate strings from English to your chosen language. Zen mode offers a simpler translation experience.
+
+Your changes will be attributed to you in the automated PR process; you don't need to do anything else.
+
+## Help & Questions
+
+Please check Weblate's [documentation](https://docs.weblate.org/en/latest/index.html) or ping @Harvestor on [Discord](https://discord.com/channels/1020123559063990373/1049495067846524939) if you have any questions.
+
+## Thanks
+
+Thanks to the InvokeAI community for their efforts to translate the project!

docs/contributing/contribution_guides/tutorials.md

@@ -0,0 +1,11 @@
+# Tutorials
+
+Tutorials help new & existing users expand their abilty to use InvokeAI to the full extent of our features and services.  
+
+Currently, we have a set of tutorials available on our [YouTube channel](https://www.youtube.com/@invokeai), but as InvokeAI continues to evolve with new updates, we want to ensure that we are giving our users the resources they need to succeed. 
+
+Tutorials can be in the form of videos or article walkthroughs on a subject of your choice. We recommend focusing tutorials on the key image generation methods, or on a specific component within one of the image generation methods.
+
+## Contributing
+
+Please reach out to @imic or @hipsterusername on [Discord](https://discord.gg/ZmtBAhwWhy) to help create tutorials for InvokeAI.

docs/features/CONCEPTS.md

@@ -1,8 +1,8 @@
 ---
-title: Concepts 
+title: Textual Inversion Embeddings and LoRAs
 ---
 
-# :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
+# :material-library-shelves: Textual Inversions and LoRAs
 
 With the advances in research, many new capabilities are available to customize the knowledge and understanding of novel concepts not originally contained in the base model. 
 
@@ -64,21 +64,25 @@ select the embedding you'd like to use. This UI has type-ahead support, so you c
 
 ## Using LoRAs
 
-LoRA files are models that customize the output of Stable Diffusion image generation.
-Larger than embeddings, but much smaller than full models, they augment SD with improved
-understanding of subjects and artistic styles.
+LoRA files are models that customize the output of Stable Diffusion
+image generation.  Larger than embeddings, but much smaller than full
+models, they augment SD with improved understanding of subjects and
+artistic styles.
 
-Unlike TI files, LoRAs do not introduce novel vocabulary into the model's known tokens. Instead,
-LoRAs augment the model's weights that are applied to generate imagery. LoRAs may be supplied
-with a "trigger" word that they have been explicitly trained on, or may simply apply their 
-effect without being triggered.
+Unlike TI files, LoRAs do not introduce novel vocabulary into the
+model's known tokens. Instead, LoRAs augment the model's weights that
+are applied to generate imagery. LoRAs may be supplied with a
+"trigger" word that they have been explicitly trained on, or may
+simply apply their effect without being triggered.
 
-LoRAs are typically stored in .safetensors files, which are the most secure way to store and transmit
-these types of weights. You may install any number of `.safetensors` LoRA files simply by copying them into
-the `lora` directory of the corresponding InvokeAI models directory (usually `invokeai`
-in your home directory). For example, you can simply move a Stable Diffusion 1.5 LoRA file to
-the `sd-1/lora` folder.
+LoRAs are typically stored in .safetensors files, which are the most
+secure way to store and transmit these types of weights. You may
+install any number of `.safetensors` LoRA files simply by copying them
+into the `autoimport/lora` directory of the corresponding InvokeAI models
+directory (usually `invokeai` in your home directory).
 
-To use these when generating, open the LoRA menu item in the options panel, select the LoRAs you want to apply
-and ensure that they have the appropriate weight recommended by the model provider. Typically, most LoRAs perform best at a weight of .75-1. 
+To use these when generating, open the LoRA menu item in the options
+panel, select the LoRAs you want to apply and ensure that they have
+the appropriate weight recommended by the model provider. Typically,
+most LoRAs perform best at a weight of .75-1.
 

docs/features/CONFIGURATION.md

@@ -65,7 +65,6 @@ InvokeAI:
     esrgan: true
     internet_available: true
     log_tokenization: false
-    nsfw_checker: false
     patchmatch: true
     restore: true
 ...
@@ -136,19 +135,16 @@ command-line options by giving the `--help` argument:
 
 ```
 (.venv) > invokeai-web --help
-usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials]
-                [--allow_methods [ALLOW_METHODS ...]] [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan]
-                [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
-                [--nsfw_checker | --no-nsfw_checker] [--patchmatch | --no-patchmatch] [--restore | --no-restore]
-                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_cache_size MAX_CACHE_SIZE]
-                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--precision {auto,float16,float32,autocast}]
-                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled]
-                [--tiled_decode | --no-tiled_decode] [--root ROOT] [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR]
-                [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH] [--models_dir MODELS_DIR]
-                [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
-                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]]
-                [--log_format {plain,color,syslog,legacy}] [--log_level {debug,info,warning,error,critical}]
-...
+usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials] [--allow_methods [ALLOW_METHODS ...]]
+                [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan] [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
+                [--patchmatch | --no-patchmatch] [--restore | --no-restore]
+                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_loaded_models MAX_LOADED_MODELS] [--max_cache_size MAX_CACHE_SIZE]
+                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--gpu_mem_reserved GPU_MEM_RESERVED] [--precision {auto,float16,float32,autocast}]
+                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled] [--tiled_decode | --no-tiled_decode] [--root ROOT]
+                [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR] [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH]
+                [--models_dir MODELS_DIR] [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
+                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]] [--log_format {plain,color,syslog,legacy}]
+                [--log_level {debug,info,warning,error,critical}] [--version | --no-version]
 ```
 
 ## The Configuration Settings
@@ -178,7 +174,6 @@ These configuration settings allow you to enable and disable various InvokeAI fe
 | `esrgan`     | `true`      | Activate the ESRGAN upscaling options|
 | `internet_available` | `true`     | When a resource is not available locally, try to fetch it via the internet |
 | `log_tokenization` | `false`      | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
-| `nsfw_checker` | `true`     | Activate the NSFW checker to blur out risque images |
 | `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) |
 

docs/features/CONTROLNET.md

@@ -8,20 +8,64 @@ title: ControlNet
 
 ControlNet
 
-ControlNet is a powerful set of features developed by the open-source community (notably, Stanford researcher [**@ilyasviel**](https://github.com/lllyasviel)) that allows you to apply a secondary neural network model to your image generation process in Invoke.
+ControlNet is a powerful set of features developed by the open-source
+community (notably, Stanford researcher
+[**@ilyasviel**](https://github.com/lllyasviel)) that allows you to
+apply a secondary neural network model to your image generation
+process in Invoke.
 
-With ControlNet, you can get more control over the output of your image generation, providing you with a way to direct the network towards generating images that better fit your desired style or outcome.
+With ControlNet, you can get more control over the output of your
+image generation, providing you with a way to direct the network
+towards generating images that better fit your desired style or
+outcome.
 
 
 ### How it works
 
-ControlNet works by analyzing an input image, pre-processing that image to identify relevant information that can be interpreted by each specific ControlNet model, and then inserting that control information into the generation process. This can be used to adjust the style, composition, or other aspects of the image to better achieve a specific result.
+ControlNet works by analyzing an input image, pre-processing that
+image to identify relevant information that can be interpreted by each
+specific ControlNet model, and then inserting that control information
+into the generation process. This can be used to adjust the style,
+composition, or other aspects of the image to better achieve a
+specific result.
 
 
 ### Models
 
-As part of the model installation, ControlNet models can be selected including a variety of pre-trained models that have been added to achieve different effects or styles in your generated images. Further ControlNet models may require additional code functionality to also be incorporated into Invoke's Invocations folder. You should expect to follow any installation instructions for ControlNet models loaded  outside the default models provided by Invoke. The default models include:
+InvokeAI provides access to a series of ControlNet models that provide
+different effects or styles in your generated images.  Currently
+InvokeAI only supports "diffuser" style ControlNet models. These are
+folders that contain the files `config.json` and/or
+`diffusion_pytorch_model.safetensors` and
+`diffusion_pytorch_model.fp16.safetensors`. The name of the folder is
+the name of the model.
 
+***InvokeAI does not currently support checkpoint-format
+ControlNets. These come in the form of a single file with the
+extension `.safetensors`.***
+
+Diffuser-style ControlNet models are available at HuggingFace
+(http://huggingface.co) and accessed via their repo IDs (identifiers
+in the format "author/modelname"). The easiest way to install them is
+to use the InvokeAI model installer application. Use the
+`invoke.sh`/`invoke.bat` launcher to select item [5] and then navigate
+to the CONTROLNETS section. Select the models you wish to install and
+press "APPLY CHANGES". You may also enter additional HuggingFace
+repo_ids in the "Additional models" textbox:
+
+![Model Installer -
+Controlnetl](../assets/installing-models/model-installer-controlnet.png){:width="640px"}
+
+Command-line users can launch the model installer using the command
+`invokeai-model-install`.
+
+_Be aware that some ControlNet models require additional code
+functionality in order to work properly, so just installing a
+third-party ControlNet model may not have the desired effect._ Please
+read and follow the documentation for installing a third party model
+not currently included among InvokeAI's default list.
+
+The models currently supported include:
 
 **Canny**:
 

docs/features/NODES.md

@@ -61,11 +61,13 @@ A noise scheduler (eg. DPM++ 2M Karras) schedules the subtraction of noise from
 | 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 |
@@ -116,49 +118,49 @@ There are several node grouping concepts that can be examined with a narrow focu
 
 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.  
 
-<img width="654" alt="groupsnoise" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/2e8d297e-ad55-4d27-bc93-c119dad2a2c5">
+![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.
 
-<img width="1024" alt="groupsconditioning" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/f8f7ad8a-8d9c-418e-b5ad-1437b774b27e">
+![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.
 
-<img width="637" alt="groupsimgvae" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/dd99969c-e0a8-4f78-9b17-3ffe179cef9a">
+![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.
 
-<img width="922" alt="groupsrandseed" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/af55bc20-60f6-438e-aba5-3ec871443710">
+![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.
 
-<img width="805" alt="groupscontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/cc9c5de7-23a7-46c8-bbad-1f3609d999a6">
+![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.
 
-<img width="993" alt="groupslora" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/630962b0-d914-4505-b3ea-ccae9b0269da">
+![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.
 
-<img width="644" alt="groupsallscale" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/99314f05-dd9f-4b6d-b378-31de55346a13">
+![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.
 
-<img width="788" alt="groupsiterate" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/4af5ca27-82c9-4018-8c5b-024d3ee0a121">
+![groupsiterate](../assets/nodes/groupsiterate.png)
 
 ### Multiple Image Generation + Random Seeds
 
@@ -166,7 +168,7 @@ Multiple image generation in the node editor is done using the RandomRange node.
 
 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.
 
-<img width="1027" alt="groupsmultigenseeding" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/518d1b2b-fed1-416b-a052-ab06552521b3">
+![groupsmultigenseeding](../assets/nodes/groupsmultigenseeding.png)
 
 ## Examples
 
@@ -174,7 +176,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic text-to-image Node Graph
 
-<img width="875" alt="nodest2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/17c67720-c376-4db8-94f0-5e00381a61ee">
+![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.
@@ -184,7 +186,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic image-to-image Node Graph
 
-<img width="998" alt="nodesi2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/3f2c95d5-cee7-4415-9b79-b46ee60a92fe">
+![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.
@@ -195,7 +197,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic ControlNet Node Graph
 
-<img width="703" alt="nodescontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/b02ded86-ceb4-44a2-9910-e19ad184d471">
+![nodescontrol](../assets/nodes/nodescontrol.png)
 
 - Model Loader
 - Prompt (Compel)

docs/features/OTHER.md

@@ -16,21 +16,24 @@ Output Example:
 
 ---
 
-## **Seamless Tiling**
+## **Invisible Watermark**
 
-The seamless tiling mode causes generated images to seamlessly tile
-with itself creating repetitive wallpaper-like patterns. To use it,
-activate the Seamless Tiling option in the Web GUI and then select
-whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
-will then be active for the next set of generations.
+In keeping with the principles for responsible AI generation, and to
+help AI researchers avoid synthetic images contaminating their
+training sets, InvokeAI adds an invisible watermark to each of the
+final images it generates. The watermark consists of the text
+"InvokeAI" and can be viewed using the
+[invisible-watermarks](https://github.com/ShieldMnt/invisible-watermark)
+tool.
 
-A nice prompt to test seamless tiling with is:
+Watermarking is controlled using the `invisible-watermark` setting in
+`invokeai.yaml`. To turn it off, add the following line under the `Features`
+category.
 
 ```
-pond garden with lotus by claude monet"
+invisible_watermark: false
 ```
 
----
 
 ## **Weighted Prompts**
 
@@ -39,34 +42,10 @@ priority to them, by adding `:<percent>` to the end of the section you wish to u
 example consider this prompt:
 
 ```bash
-tabby cat:0.25 white duck:0.75 hybrid
+(tabby cat):0.25 (white duck):0.75 hybrid
 ```
 
 This will tell the sampler to invest 25% of its effort on the tabby cat aspect of the image and 75%
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
-## **Thresholding and Perlin Noise Initialization Options**
-
-Under the Noise section of the Web UI, you will find two options named
-Perlin Noise and Noise Threshold. [Perlin
-noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
-structured noise used to simulate terrain and other natural
-textures. The slider controls the percentage of perlin noise that will
-be mixed into the image at the beginning of generation. Adding a little
-perlin noise to a generation will alter the image substantially.
-
-The noise threshold limits the range of the latent values during
-sampling and helps combat the oversharpening seem with higher CFG
-scale values.
-
-For better intuition into what these options do in practice:
-
-![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
-
-In generating this graphic, perlin noise at initialization was
-programmatically varied going across on the diagram by values 0.0,
-0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
-going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
-fixed using the prompt "a portrait of a beautiful young lady" a CFG of
-20, 100 steps, and a seed of 1950357039.

docs/features/WATERMARK+NSFW.md

@@ -1,12 +1,40 @@
 ---
-title: The NSFW Checker
+title: Watermarking, NSFW Image Checking
 ---
 
-# :material-image-off: NSFW Checker
+# :material-image-off: Invisible Watermark and the NSFW Checker
+
+## Watermarking
+
+InvokeAI does not apply watermarking to images by default. However,
+many computer scientists working in the field of generative AI worry
+that a flood of computer-generated imagery will contaminate the image
+data sets needed to train future generations of generative models.
+
+InvokeAI offers an optional watermarking mode that writes a small bit
+of text, **InvokeAI**, into each image that it generates using an
+"invisible" watermarking library that spreads the information
+throughout the image in a way that is not perceptible to the human
+eye. If you are planning to share your generated images on
+internet-accessible services, we encourage you to activate the
+invisible watermark mode in order to help preserve the digital image
+environment.
+
+The downside of watermarking is that it increases the size of the
+image moderately, and has been reported by some individuals to degrade
+image quality. Your mileage may vary.
+
+To read the watermark in an image, activate the InvokeAI virtual
+environment (called the "developer's console" in the launcher) and run
+the command:
+
+```
+invisible-watermark -a decode -t bytes -m dwtDct -l 64 /path/to/image.png
+```
 
 ## The NSFW ("Safety") Checker
 
-The Stable Diffusion image generation models will produce sexual
+Stable Diffusion 1.5-based image generation models will produce sexual
 imagery if deliberately prompted, and will occasionally produce such
 images when this is not intended. Such images are colloquially known
 as "Not Safe for Work" (NSFW). This behavior is due to the nature of
@@ -18,35 +46,17 @@ jurisdictions it may be illegal to publicly distribute such imagery,
 including mounting a publicly-available server that provides
 unfiltered images to the public. Furthermore, the [Stable Diffusion
 weights
-License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-ModelWeights.txt)
-forbids the model from being used to "exploit any of the
+License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SD1+SD2.txt),
+and the [Stable Diffusion XL
+License][https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SDXL.txt]
+both forbid the models from being used to "exploit any of the
 vulnerabilities of a specific group of persons."
 
 For these reasons Stable Diffusion offers a "safety checker," a
 machine learning model trained to recognize potentially disturbing
 imagery. When a potentially NSFW image is detected, the checker will
 blur the image and paste a warning icon on top. The checker can be
-turned on and off on the command line using `--nsfw_checker` and
-`--no-nsfw_checker`.
-
-At installation time, InvokeAI will ask whether the checker should be
-activated by default (neither argument given on the command line). The
-response is stored in the InvokeAI initialization file
-(`invokeai.yaml` in the InvokeAI root directory).  You can change the
-default at any time by opening this file in a text editor and
-changing the line `nsfw_checker:` from true to false or vice-versa:
-
-
-```
-...
-  Features:
-    esrgan: true
-    internet_available: true
-    log_tokenization: false
-    nsfw_checker: true
-    patchmatch: true
-    restore: true
-```
+turned on and off in the Web interface under Settings.
 
 ## Caveats
 
@@ -84,10 +94,3 @@ are encouraged to turn **off** intermediate image rendering when you
 are using the checker. Future versions of InvokeAI will apply
 additional blurring to intermediate images when the checker is active.
 
-### Watermarking
-
-InvokeAI does not apply any sort of watermark to images it
-generates. However, it does write metadata into the PNG data area,
-including the prompt used to generate the image and relevant parameter
-settings. These fields can be examined using the `sd-metadata.py`
-script that comes with the InvokeAI package.

docs/features/WEB.md

@@ -4,15 +4,19 @@ title: InvokeAI Web Server
 
 # :material-web: InvokeAI Web Server
 
-As of version 2.0.0, this distribution comes with a full-featured web server
-(see screenshot).
+## Quick guided walkthrough of the WebUI's features
 
-To use it, launch the `invoke.sh`/`invoke.bat` script and select
-option (2). Alternatively, with the InvokeAI environment active, run
-the `invokeai` script by adding the `--web` option:
+While most of the WebUI's features are intuitive, here is a guided walkthrough
+through its various components.
+
+### Launching the WebUI
+
+To run the InvokeAI web server, start the `invoke.sh`/`invoke.bat`
+script and select option (1). Alternatively, with the InvokeAI
+environment active, run `invokeai-web`:
 
 ```bash
-invokeai --web
+invokeai-web
 ```
 
 You can then connect to the server by pointing your web browser at
@@ -28,33 +32,32 @@ invoke.sh --host 0.0.0.0
 or
 
 ```bash
-invokeai --web --host 0.0.0.0
+invokeai-web --host 0.0.0.0
 ```
 
-## Quick guided walkthrough of the WebUI's features
-
-While most of the WebUI's features are intuitive, here is a guided walkthrough
-through its various components.
+### The InvokeAI Web Interface
 
 ![Invoke Web Server - Major Components](../assets/invoke-web-server-1.png){:width="640px"}
 
 The screenshot above shows the Text to Image tab of the WebUI. There are three
 main sections:
 
-1. A **control panel** on the left, which contains various settings for text to
-   image generation. The most important part is the text field (currently
-   showing `strawberry sushi`) for entering the text prompt, and the camera icon
-   directly underneath that will render the image. We'll call this the _Invoke_
-   button from now on.
+1. A **control panel** on the left, which contains various settings
+   for text to image generation. The most important part is the text
+   field (currently showing `fantasy painting, horned demon`) for
+   entering the positive text prompt, another text field right below it for an
+   optional negative text prompt (concepts to exclude), and a _Invoke_ button 
+   to begin the image rendering process.
 
-2. The **current image** section in the middle, which shows a large format
-   version of the image you are currently working on. A series of buttons at the
-   top ("image to image", "Use All", "Use Seed", etc) lets you modify the image
-   in various ways.
+2. The **current image** section in the middle, which shows a large
+   format version of the image you are currently working on. A series
+   of buttons at the top lets you modify and manipulate the image in
+   various ways.
 
-3. A \*_gallery_ section on the left that contains a history of the images you
+3. A **gallery** section on the left that contains a history of the images you
    have generated. These images are read and written to the directory specified
-   at launch time in `--outdir`.
+   in the `INVOKEAIROOT/invokeai.yaml` initialization file, usually a directory
+   named `outputs` in `INVOKEAIROOT`.
 
 In addition to these three elements, there are a series of icons for changing
 global settings, reporting bugs, and changing the theme on the upper right.
@@ -76,15 +79,11 @@ From top to bottom, these are:
    with outpainting,and modify interior portions of the image with
    inpainting, erase portions of a starting image and have the AI fill in
    the erased region from a text prompt.
-4. Node Editor - this panel allows you to create
+4. Node Editor - (experimental) this panel allows you to create
    pipelines of common operations and combine them into workflows.
 5. Model Manager - this panel allows you to import and configure new
    models using URLs, local paths, or HuggingFace diffusers repo_ids.
 
-The inpainting, outpainting and postprocessing tabs are currently in
-development. However, limited versions of their features can already be accessed
-through the Text to Image and Image to Image tabs.
-
 ## Walkthrough
 
 The following walkthrough will exercise most (but not all) of the WebUI's
@@ -92,43 +91,54 @@ feature set.
 
 ### Text to Image
 
-1. Launch the WebUI using `python scripts/invoke.py --web` and connect to it
-   with your browser by accessing `http://localhost:9090`. If the browser and
-   server are running on different machines on your LAN, add the option
-   `--host 0.0.0.0` to the launch command line and connect to the machine
-   hosting the web server using its IP address or domain name.
+1. Launch the WebUI using launcher option [1] and connect to it with
+   your browser by accessing `http://localhost:9090`. If the browser
+   and server are running on different machines on your LAN, add the
+   option `--host 0.0.0.0` to the `invoke.sh` launch command line and connect to
+   the machine hosting the web server using its IP address or domain
+   name.
 
-2. If all goes well, the WebUI should come up and you'll see a green
-   `connected` message on the upper right.
+2. If all goes well, the WebUI should come up and you'll see a green dot
+   meaning `connected`  on the upper right.
+
+![Invoke Web Server - Control Panel](../assets/invoke-control-panel-1.png){ align=right width=300px }
 
 #### Basics
 
-1.  Generate an image by typing _strawberry sushi_ into the large prompt field
-    on the upper left and then clicking on the Invoke button (the one with the
-    Camera icon). After a short wait, you'll see a large image of sushi in the
+1.  Generate an image by typing _bluebird_ into the large prompt field
+    on the upper left and then clicking on the Invoke button or pressing
+	the return button.
+	After a short wait, you'll see a large image of a bluebird in the
     image panel, and a new thumbnail in the gallery on the right.
 
-    If you need more room on the screen, you can turn the gallery off by
-    clicking on the **x** to the right of "Your Invocations". You can turn it
-    back on later by clicking the image icon that appears in the gallery's
-    place.
+    If you need more room on the screen, you can turn the gallery off
+    by typing the **g** hotkey. You can turn it back on later by clicking the
+    image icon that appears in the gallery's place. The list of hotkeys can
+	be found by clicking on the keyboard icon above the image gallery.
 
-    The images are written into the directory indicated by the `--outdir` option
-    provided at script launch time. By default, this is `outputs/img-samples`
-    under the InvokeAI directory.
-
-2.  Generate a bunch of strawberry sushi images by increasing the number of
-    requested images by adjusting the Images counter just below the Camera
+2.  Generate a bunch of bluebird images by increasing the number of
+    requested images by adjusting the Images counter just below the Invoke
     button. As each is generated, it will be added to the gallery. You can
     switch the active image by clicking on the gallery thumbnails.
+	
+	If you'd like to watch the image generation progress, click the hourglass
+	icon above the main image area. As generation progresses, you'll see
+	increasingly detailed versions of the ultimate image.
 
-3.  Try playing with different settings, including image width and height, the
-    Sampler, the Steps and the CFG scale.
+3.  Try playing with different settings, including changing the main
+    model, the image width and height, the Scheduler, the Steps and
+    the CFG scale.
+	
+	The _Model_ changes the main model. Thousands of custom models are
+	now available, which generate a variety of image styles and
+	subjects. While InvokeAI comes with a few starter models, it is
+	easy to import new models into the application. See [Installing
+	Models](../installation/050_INSTALLING_MODELS.md) for more details.
 
     Image _Width_ and _Height_ do what you'd expect. However, be aware that
     larger images consume more VRAM memory and take longer to generate.
 
-    The _Sampler_ controls how the AI selects the image to display. Some
+    The _Scheduler_ controls how the AI selects the image to display. Some
     samplers are more "creative" than others and will produce a wider range of
     variations (see next section). Some samplers run faster than others.
 
@@ -142,17 +152,27 @@ feature set.
     to the input prompt. You can go as high or low as you like, but generally
     values greater than 20 won't improve things much, and values lower than 5
     will produce unexpected images. There are complex interactions between
-    _Steps_, _CFG Scale_ and the _Sampler_, so experiment to find out what works
+    _Steps_, _CFG Scale_ and the _Scheduler_, so experiment to find out what works
     for you.
+	
+	The _Seed_ controls the series of values returned by InvokeAI's
+    random number generator. Each unique seed value will generate a different
+	image. To regenerate a previous image, simply use the original image's
+	seed value. A slider to the right of the _Seed_ field will change the
+	seed each time an image is generated.
 
-4.  To regenerate a previously-generated image, select the image you want and
-    click _Use All_. This loads the text prompt and other original settings into
-    the control panel. If you then press _Invoke_ it will regenerate the image
-    exactly. You can also selectively modify the prompt or other settings to
-    tweak the image.
+![Invoke Web Server - Control Panel 2](../assets/control-panel-2.png){ align=right width=400px }
 
-    Alternatively, you may click on _Use Seed_ to load just the image's seed,
-    and leave other settings unchanged.
+4.  To regenerate a previously-generated image, select the image you
+    want and click the asterisk ("*") button at the top of the
+    image. This loads the text prompt and other original settings into
+    the control panel. If you then press _Invoke_ it will regenerate
+    the image exactly. You can also selectively modify the prompt or
+    other settings to tweak the image.
+
+    Alternatively, you may click on the "sprouting plant icon" to load
+    just the image's seed, and leave other settings unchanged or the
+    quote icon to load just the positive and negative prompts.
 
 5.  To regenerate a Stable Diffusion image that was generated by another SD
     package, you need to know its text prompt and its _Seed_. Copy-paste the
@@ -161,62 +181,22 @@ feature set.
     you Invoke, you will get something similar to the original image. It will
     not be exact unless you also set the correct values for the original
     sampler, CFG, steps and dimensions, but it will (usually) be close.
+	
+6.  To save an image, right click on it to bring up a menu that will
+	let you download the image, save it to a named image gallery, and
+	copy it to the clipboard, among other things.
 
-#### Variations on a theme
+#### Upscaling
 
-1.  Let's try generating some variations. Select your favorite sushi image from
-    the gallery to load it. Then select "Use All" from the list of buttons
-    above. This will load up all the settings used to generate this image,
-    including its unique seed.
+![Invoke Web Server - Upscaling](../assets/upscaling.png){ align=right width=400px }
 
-    Go down to the Variations section of the Control Panel and set the button to
-    On. Set Variation Amount to 0.2 to generate a modest number of variations on
-    the image, and also set the Image counter to `4`. Press the `invoke` button.
-    This will generate a series of related images. To obtain smaller variations,
-    just lower the Variation Amount. You may also experiment with changing the
-    Sampler. Some samplers generate more variability than others. _k_euler_a_ is
-    particularly creative, while _ddim_ is pretty conservative.
-
-2.  For even more variations, experiment with increasing the setting for
-    _Perlin_. This adds a bit of noise to the image generation process. Note
-    that values of Perlin noise greater than 0.15 produce poor images for
-    several of the samplers.
-
-#### Facial reconstruction and upscaling
-
-Stable Diffusion frequently produces mangled faces, particularly when there are
-multiple figures in the same scene. Stable Diffusion has particular issues with
-generating reallistic eyes. InvokeAI provides the ability to reconstruct faces
-using either the GFPGAN or CodeFormer libraries. For more information see
-[POSTPROCESS](POSTPROCESS.md).
-
-1.  Invoke a prompt that generates a mangled face. A prompt that often gives
-    this is "portrait of a lawyer, 3/4 shot" (this is not intended as a slur
-    against lawyers!) Once you have an image that needs some touching up, load
-    it into the Image panel, and press the button with the face icon
-    (highlighted in the first screenshot below). A dialog box will appear. Leave
-    _Strength_ at 0.8 and press \*Restore Faces". If all goes well, the eyes and
-    other aspects of the face will be improved (see the second screenshot)
-
-    ![Invoke Web Server - Original Image](../assets/invoke-web-server-3.png)
-
-    ![Invoke Web Server - Retouched Image](../assets/invoke-web-server-4.png)
-
-    The facial reconstruction _Strength_ field adjusts how aggressively the face
-    library will try to alter the face. It can be as high as 1.0, but be aware
-    that this often softens the face airbrush style, losing some details. The
-    default 0.8 is usually sufficient.
-
-2.  "Upscaling" is the process of increasing the size of an image while
-    retaining the sharpness. InvokeAI uses an external library called "ESRGAN"
-    to do this. To invoke upscaling, simply select an image and press the _HD_
-    button above it. You can select between 2X and 4X upscaling, and adjust the
-    upscaling strength, which has much the same meaning as in facial
-    reconstruction. Try running this on one of your previously-generated images.
-
-3.  Finally, you can run facial reconstruction and/or upscaling automatically
-    after each Invocation. Go to the Advanced Options section of the Control
-    Panel and turn on _Restore Face_ and/or _Upscale_.
+"Upscaling" is the process of increasing the size of an image while
+    retaining the sharpness. InvokeAI uses an external library called
+    "ESRGAN" to do this. To invoke upscaling, simply select an image
+    and press the "expanding arrows" button above it. You can select
+    between 2X and 4X upscaling, and adjust the upscaling strength,
+    which has much the same meaning as in facial reconstruction. Try
+    running this on one of your previously-generated images.
 
 ### Image to Image
 
@@ -224,24 +204,14 @@ InvokeAI lets you take an existing image and use it as the basis for a new
 creation. You can use any sort of image, including a photograph, a scanned
 sketch, or a digital drawing, as long as it is in PNG or JPEG format.
 
-For this tutorial, we'll use files named
-[Lincoln-and-Parrot-512.png](../assets/Lincoln-and-Parrot-512.png), and
-[Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png).
-Download these images to your local machine now to continue with the
-walkthrough.
+For this tutorial, we'll use the file named
+[Lincoln-and-Parrot-512.png](../assets/Lincoln-and-Parrot-512.png).
 
-1.  Click on the _Image to Image_ tab icon, which is the second icon from the
-    top on the left-hand side of the screen:
+1.  Click on the _Image to Image_ tab icon, which is the second icon
+    from the top on the left-hand side of the screen. This will bring
+    you to a screen similar to the one shown here:
 
-    <figure markdown>
-    ![Invoke Web Server - Image to Image Icon](../assets/invoke-web-server-5.png)
-    </figure>
-
-    This will bring you to a screen similar to the one shown here:
-
-    <figure markdown>
-    ![Invoke Web Server - Image to Image Tab](../assets/invoke-web-server-6.png){:width="640px"}
-    </figure>
+    ![Invoke Web Server - Image to Image Tab](../assets/invoke-web-server-6.png){ width="640px" }
 
 2.  Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or click
     the blank area to get an upload dialog. The image will load into an area
@@ -255,120 +225,99 @@ walkthrough.
     ![Invoke Web Server - Image to Image example](../assets/invoke-web-server-7.png){:width="640px"}
 
 4.  Experiment with the different settings. The most influential one in Image to
-    Image is _Image to Image Strength_ located about midway down the control
+    Image is _Denoising Strength_ located about midway down the control
     panel. By default it is set to 0.75, but can range from 0.0 to 0.99. The
     higher the value, the more of the original image the AI will replace. A
     value of 0 will leave the initial image completely unchanged, while 0.99
-    will replace it completely. However, the Sampler and CFG Scale also
+    will replace it completely. However, the _Scheduler_ and _CFG Scale_ also
     influence the final result. You can also generate variations in the same way
     as described in Text to Image.
 
-5.  What if we only want to change certain part(s) of the image and leave the
-    rest intact? This is called Inpainting, and a future version of the InvokeAI
-    web server will provide an interactive painting canvas on which you can
-    directly draw the areas you wish to Inpaint into. For now, you can achieve
-    this effect by using an external photoeditor tool to make one or more
-    regions of the image transparent as described in [INPAINTING.md] and
-    uploading that.
-
-    The file
-    [Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png)
-    is a version of the earlier image in which the area around the parrot has
-    been replaced with transparency. Click on the "x" in the upper right of the
-    Initial Image and upload the transparent version. Using the same prompt "old
-    sea captain with raven on shoulder" try Invoking an image. This time, only
-    the parrot will be replaced, leaving the rest of the original image intact:
-
-    <figure markdown>
-    ![Invoke Web Server - Inpainting](../assets/invoke-web-server-8.png){:width="640px"}
-    </figure>
+5.  What if we only want to change certain part(s) of the image and
+    leave the rest intact? This is called Inpainting, and you can do
+    it in the [Unified Canvas](UNIFIED_CANVAS.md). The Unified Canvas
+    also allows you to extend borders of the image and fill in the
+    blank areas, a process called outpainting.
 
 6.  Would you like to modify a previously-generated image using the Image to
-    Image facility? Easy! While in the Image to Image panel, hover over any of
-    the gallery images to see a little menu of icons pop up. Click the picture
-    icon to instantly send the selected image to Image to Image as the initial
-    image.
+    Image facility? Easy! While in the Image to Image panel, drag and drop any
+	image in the gallery into the Initial Image area, and it will be ready for
+	use. You can do the same thing with the main image display. Click on the
+	_Send to_ icon to get a menu of
+	commands and choose "Send to Image to Image".
+	
+	![Send To Icon](../assets/send-to-icon.png) 
 
-You can do the same from the Text to Image tab by clicking on the picture icon
-above the central image panel. The screenshot below shows where the "use as
-initial image" icons are located.
+### Textual Inversion, LoRA and ControlNet
 
-![Invoke Web Server - Use as Image Links](../assets/invoke-web-server-9.png){:width="640px"}
+InvokeAI supports several different types of model files that
+extending the capabilities of the main model by adding artistic
+styles, special effects, or subjects. By mixing and matching textual
+inversion, LoRA and ControlNet models, you can achieve many
+interesting and beautiful effects.
 
-### Unified Canvas
+We will give an example using a LoRA model named "Ink Scenery". This
+LoRA, which can be downloaded from Civitai (civitai.com), is
+specialized to paint landscapes that look like they were made with
+dripping india ink. To install this LoRA, we first download it and 
+put it into the `autoimport/lora` folder located inside the
+`invokeai` root directory. After restarting the web server, the
+LoRA will now become available for use.
 
-See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
+To see this LoRA at work, we'll first generate an image without it
+using the standard `stable-diffusion-v1-5` model. Choose this
+model and enter the prompt "mountains, ink". Here is a typical
+generated image, a mountain range rendered in ink and watercolor
+wash:
 
-## Reference
+![Ink Scenery without LoRA](../assets/lora-example-0.png){ width=512px }
 
-### Additional Options
+Now let's install and activate the Ink Scenery LoRA. Go to
+https://civitai.com/models/78605/ink-scenery-or and download the LoRA
+model file to `invokeai/autoimport/lora` and restart the web
+server. (Alternatively, you can use [InvokeAI's Web Model
+Manager](../installation/050_INSTALLING_MODELS.md) to download and
+install the LoRA directly by typing its URL into the _Import
+Models_->_Location_ field).
 
-| parameter <img width=160 align="right"> | effect                                                                                                                                     |
-| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
-| `--web_develop`                         | Starts the web server in development mode.                                                                                                 |
-| `--web_verbose`                         | Enables verbose logging                                                                                                                    |
-| `--cors [CORS ...]`                     | Additional allowed origins, comma-separated                                                                                                |
-| `--host HOST`                           | Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.                                  |
-| `--port PORT`                           | Web server: Port to listen on                                                                                                              |
-| `--certfile CERTFILE`                   | Web server: Path to certificate file to use for SSL. Use together with --keyfile                                                           |
-| `--keyfile KEYFILE`                     | Web server: Path to private key file to use for SSL. Use together with --certfile'                                                         |
-| `--gui`                                 | Start InvokeAI GUI - This is the "desktop mode" version of the web app. It uses Flask to create a desktop app experience of the webserver. |
+Scroll down the control panel until you get to the LoRA accordion
+section, and open it:
 
-### Web Specific Features
+![LoRA Section](../assets/lora-example-1.png){ width=512px }
 
-The web experience offers an incredibly easy-to-use experience for interacting
-with the InvokeAI toolkit. For detailed guidance on individual features, see the
-Feature-specific help documents available in this directory. Note that the
-latest functionality available in the CLI may not always be available in the Web
-interface.
+Click the popup menu and select "Ink scenery". (If it isn't there, then
+the model wasn't installed to the right place, or perhaps you forgot
+to restart the web server.) The LoRA section will change to look like this:
 
-#### Dark Mode & Light Mode
+![LoRA Section Loaded](../assets/lora-example-2.png){ width=512px }
 
-The InvokeAI interface is available in a nano-carbon black & purple Dark Mode,
-and a "burn your eyes out Nosferatu" Light Mode. These can be toggled by
-clicking the Sun/Moon icons at the top right of the interface.
+Note that there is now a slider control for _Ink scenery_. The slider
+controls how much influence the LoRA model will have on the generated
+image.
 
-![InvokeAI Web Server - Dark Mode](../assets/invoke_web_dark.png)
+Run the "mountains, ink" prompt again and observe the change in style:
 
-![InvokeAI Web Server - Light Mode](../assets/invoke_web_light.png)
+![Ink Scenery](../assets/lora-example-3.png){ width=512px }
 
-#### Invocation Toolbar
+Try adjusting the weight slider for larger and smaller weights and
+generate the image after each adjustment. The higher the weight, the
+more influence the LoRA will have.
 
-The left side of the InvokeAI interface is available for customizing the prompt
-and the settings used for invoking your new image. Typing your prompt into the
-open text field and clicking the Invoke button will produce the image based on
-the settings configured in the toolbar.
+To remove the LoRA completely, just click on its trash can icon.
 
-See below for additional documentation related to each feature:
+Multiple LoRAs can be added simultaneously and combined with textual
+inversions and ControlNet models. Please see [Textual Inversions and
+LoRAs](CONCEPTS.md) and [Using ControlNet](CONTROLNET.md) for details.
 
-- [Variations](./VARIATIONS.md)
-- [Upscaling](./POSTPROCESS.md#upscaling)
-- [Image to Image](./IMG2IMG.md)
-- [Other](./OTHER.md)
+## Summary
 
-#### Invocation Gallery
-
-The currently selected --outdir (or the default outputs folder) will display all
-previously generated files on load. As new invocations are generated, these will
-be dynamically added to the gallery, and can be previewed by selecting them.
-Each image also has a simple set of actions (e.g., Delete, Use Seed, Use All
-Parameters, etc.) that can be accessed by hovering over the image.
-
-#### Image Workspace
-
-When an image from the Invocation Gallery is selected, or is generated, the
-image will be displayed within the center of the interface. A quickbar of common
-image interactions are displayed along the top of the image, including:
-
-- Use image in the `Image to Image` workflow
-- Initialize Face Restoration on the selected file
-- Initialize Upscaling on the selected file
-- View File metadata and details
-- Delete the file
+This walkthrough just skims the surface of the many things InvokeAI
+can do. Please see [Features](index.md) for more detailed reference
+guides.
 
 ## Acknowledgements
 
-A huge shout-out to the core team working to make this vision a reality,
+A huge shout-out to the core team working to make the Web GUI a reality,
 including [psychedelicious](https://github.com/psychedelicious),
 [Kyle0654](https://github.com/Kyle0654) and
 [blessedcoolant](https://github.com/blessedcoolant).

docs/features/index.md

@@ -4,6 +4,9 @@ title: Overview
 
 Here you can find the documentation for InvokeAI's various features.
 
+## The [Getting Started Guide](../help/gettingStartedWithAI) 
+A getting started guide for those new to AI image generation. 
+
 ## The Basics
 ### * The [Web User Interface](WEB.md)
 Guide to the Web interface. Also see the [WebUI Hotkeys Reference Guide](WEBUIHOTKEYS.md)
@@ -17,8 +20,12 @@ a single convenient digital artist-optimized user interface.
 ### * [Prompt Engineering](PROMPTS.md)
 Get the images you want with the InvokeAI  prompt engineering language.
 
-## * The [Concepts Library](CONCEPTS.md)
-Add custom subjects and styles using HuggingFace's repository of embeddings.
+### * The [LoRA, LyCORIS and Textual Inversion Models](CONCEPTS.md)
+Add custom subjects and styles using a variety of fine-tuned models.
+
+### * [ControlNet](CONTROLNET.md)
+Learn how to install and use ControlNet models for fine control over
+image output.
 
 ### * [Image-to-Image Guide](IMG2IMG.md)
 Use a seed image to build new creations in the CLI.
@@ -29,26 +36,28 @@ are the ticket.
 
 ## Model Management
 
-## * [Model Installation](../installation/050_INSTALLING_MODELS.md)
+### * [Model Installation](../installation/050_INSTALLING_MODELS.md)
 Learn how to import third-party models and switch among them. This
 guide also covers optimizing models to load quickly.
 
-## * [Merging Models](MODEL_MERGING.md)
+### * [Merging Models](MODEL_MERGING.md)
 Teach an old model new tricks. Merge 2-3 models together to create a
 new model that combines characteristics of the originals.
 
-## * [Textual Inversion](TRAINING.md)
+### * [Textual Inversion](TRAINING.md)
 Personalize models by adding your own style or subjects.
 
-# Other Features
+## Other Features
 
-## * [The NSFW Checker](NSFW.md)
+### * [The NSFW Checker](WATERMARK+NSFW.md)
 Prevent InvokeAI from displaying unwanted racy images.
 
-## * [Controlling Logging](LOGGING.md)
+### * [Controlling Logging](LOGGING.md)
 Control how InvokeAI logs status messages.
 
-## * [Miscellaneous](OTHER.md)
+<!-- OUT OF DATE
+### * [Miscellaneous](OTHER.md)
 Run InvokeAI on Google Colab, generate images with repeating patterns,
 batch process a file of prompts, increase the "creativity" of image
 generation by adding initial noise, and more!
+-->

docs/help/gettingStartedWithAI.md

@@ -0,0 +1,95 @@
+# Getting Started with AI Image Generation
+
+New to image generation with AI? You’re in the right place! 
+
+This is a high level walkthrough of some of the concepts and terms you’ll see as you start using InvokeAI. Please note, this is not an exhaustive guide and may be out of date due to the rapidly changing nature of the space. 
+
+## Using InvokeAI
+
+### **Prompt Crafting**
+
+- Prompts are the basis of using InvokeAI, providing the models directions on what to generate. As a general rule of thumb, the more detailed your prompt is, the better your result will be.
+
+ *To get started, here’s an easy template to use for structuring your prompts:*
+
+- Subject, Style, Quality, Aesthetic
+    - **Subject:** What your image will be about. E.g. “a futuristic city with trains”,  “penguins floating on icebergs”, “friends sharing beers”
+    - **Style:** The style or medium in which your image will be in. E.g. “photograph”, “pencil sketch”, “oil paints”, or “pop art”, “cubism”, “abstract”
+    - **Quality:** A particular aspect or trait that you would like to see emphasized in your image. E.g. "award-winning", "featured in {relevant set of high quality works}", "professionally acclaimed". Many people often use "masterpiece".
+    - **Aesthetics:** The visual impact and design of the artwork. This can be colors, mood, lighting, setting, etc.
+- There are two prompt boxes: *Positive Prompt* & *Negative Prompt*.
+    - A **Positive** Prompt includes words you want the model to reference when creating an image.
+    - Negative Prompt is for anything you want the model to eliminate when creating an image. It doesn’t always interpret things exactly the way you would, but helps control the generation process. Always try to include a few terms - you can typically use lower quality image terms like “blurry” or “distorted” with good success.
+- Some examples prompts you can try on your own:
+    - A detailed oil painting of a tranquil forest at sunset with vibrant+ colors and soft, golden light filtering through the trees
+    - friends sharing beers in a busy city, realistic colored pencil sketch, twilight, masterpiece, bright, lively
+
+### Generation Workflows
+
+- Invoke offers a number of different workflows for interacting with models to produce images. Each is extremely powerful on its own, but together provide you an unparalleled way of producing high quality creative outputs that align with your vision.
+    - **Text to Image:** The text to image tab focuses on the key workflow of using a prompt to generate a new image. It includes other features that help control the generation process as well.
+    - **Image to Image:** With image to image, you provide an image as a reference (called the “initial image”), which provides more guidance around color and structure to the AI as it generates a new image. This is provided alongside the same features as Text to Image.
+    - **Unified Canvas:** The Unified Canvas is an advanced AI-first image editing tool that is easy to use, but hard to master. Drag an image onto the canvas from your gallery in order to regenerate certain elements, edit content or colors (known as inpainting), or extend the image with an exceptional degree of consistency and clarity (called outpainting).
+
+### Improving Image Quality
+
+- Fine tuning your prompt - the more specific you are, the closer the image will turn out to what is in your head!  Adding more details in the Positive Prompt or Negative Prompt can help add / remove pieces of your image to improve it - You can also use advanced techniques like upweighting and downweighting to control the influence of certain words. [Learn more here](https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#prompt-syntax-features).
+    - **Tip: If you’re seeing poor results, try adding the things you don’t like about the image to your negative prompt may help. E.g. distorted, low quality, unrealistic, etc.**
+- Explore different models - Other models can produce different results due to the data they’ve been trained on. Each model has specific language and settings it works best with; a model’s documentation is your friend here.  Play around with some and see what works best for you!
+- Increasing Steps - The number of steps used controls how much time the model is given to produce an image, and depends on the “Scheduler” used. The schedule controls how each step is processed by the model. More steps tends to mean better results, but will take longer - We recommend at least 30 steps for most
+- Tweak and Iterate - Remember, it’s best to change one thing at a time so you know what is working and what isn't. Sometimes you just need to try a new image, and other times using a new prompt might be the ticket. For testing, consider turning off the “random” Seed - Using the same seed with the same settings will produce the same image, which makes it the perfect way to learn exactly what your changes are doing.
+- Explore Advanced Settings - InvokeAI has a full suite of tools available to allow you complete control over your image creation process - Check out our [docs if you want to learn more](https://invoke-ai.github.io/InvokeAI/features/).
+
+
+## Terms & Concepts
+
+If you're interested in learning more, check out [this presentation](https://docs.google.com/presentation/d/1IO78i8oEXFTZ5peuHHYkVF-Y3e2M6iM5tCnc-YBfcCM/edit?usp=sharing) from one of our maintainers (@lstein). 
+
+### Stable Diffusion
+
+Stable Diffusion is deep learning, text-to-image model that is the foundation of the capabilities found in InvokeAI. Since the release of Stable Diffusion, there have been many subsequent models created based on Stable Diffusion that are designed to generate specific types of images. 
+
+### Prompts
+
+Prompts provide the models directions on what to generate. As a general rule of thumb, the more detailed your prompt is, the better your result will be.
+
+### Models
+
+Models are the magic that power InvokeAI. These files represent the output of training a machine on understanding massive amounts of images - providing them with the capability to generate new images using just a text description of what you’d like to see. (Like Stable Diffusion!)
+
+Invoke offers a simple way to download several different models upon installation, but many more can be discovered online, including at ****. Each model can produce a unique style of output, based on the images it was trained on - Try out different models to see which best fits your creative vision!
+
+- *Models that contain “inpainting” in the name are designed for use with the inpainting feature of the Unified Canvas*
+
+### Scheduler
+
+Schedulers guide the process of removing noise (de-noising) from data. They determine:
+
+1. The number of steps to take to remove the noise.
+2. Whether the steps are random (stochastic) or predictable (deterministic).
+3. The specific method (algorithm) used for de-noising.
+
+Experimenting with different schedulers is recommended as each will produce different outputs!
+
+### Steps
+
+The number of de-noising steps each generation through. 
+
+Schedulers can be intricate and there's often a balance to strike between how quickly they can de-noise data and how well they can do it. It's typically advised to experiment with different schedulers to see which one gives the best results. There has been a lot written on the internet about different schedulers, as well as exploring what the right level of "steps" are for each. You can save generation time by reducing the number of steps used, but you'll want to make sure that you are satisfied with the quality of images produced!
+
+### Low-Rank Adaptations / LoRAs
+
+Low-Rank Adaptations (LoRAs) are like a smaller, more focused version of models, intended to focus on training a better understanding of how a specific character, style, or concept looks.
+
+### Textual Inversion Embeddings
+
+Textual Inversion Embeddings, like LoRAs, assist with more easily prompting for certain characters, styles, or concepts. However, embeddings are trained to update the relationship between a specific word (known as the “trigger”) and the intended output. 
+
+### ControlNet
+
+ControlNets are neural network models that are able to extract key features from an existing image and use these features to guide the output of the image generation model. 
+
+### VAE
+
+Variational auto-encoder (VAE) is a encode/decode model that translates the "latents" image produced during the image generation procees to the large pixel images that we see. 
+

docs/index.md

@@ -11,6 +11,33 @@ title: Home
   ```
 -->
 
+<!-- CSS styling -->
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@6.2.1/css/fontawesome.min.css">
+<style>
+    .button {
+      width: 300px;
+      height: 50px;
+      background-color: #448AFF;
+      color: #fff;
+      font-size: 16px;
+      border: none;
+      cursor: pointer;
+      border-radius: 0.2rem;
+    }
+
+    .button-container {
+      display: grid;
+      grid-template-columns: repeat(3, 300px);
+      gap: 20px;
+    }
+
+    .button:hover {
+      background-color: #526CFE;
+    }
+</style>
+
+
+
 <div align="center" markdown>
 
 
@@ -24,7 +51,7 @@ title: Home
 
 [![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]
@@ -54,10 +81,10 @@ title: Home
 [github stars badge]:
   https://flat.badgen.net/github/stars/invoke-ai/InvokeAI?icon=github
 [github stars link]: https://github.com/invoke-ai/InvokeAI/stargazers
-[latest commit to dev badge]:
+<!-- [latest commit to dev badge]:
   https://flat.badgen.net/github/last-commit/invoke-ai/InvokeAI/development?icon=github&color=yellow&label=last%20dev%20commit&cache=900
 [latest commit to dev link]:
-  https://github.com/invoke-ai/InvokeAI/commits/development
+  https://github.com/invoke-ai/InvokeAI/commits/main -->
 [latest release badge]:
   https://flat.badgen.net/github/release/invoke-ai/InvokeAI/development?icon=github
 [latest release link]: https://github.com/invoke-ai/InvokeAI/releases
@@ -70,61 +97,24 @@ image-to-image generator. It provides a streamlined process with various new
 features and options to aid the image generation process. It runs on Windows,
 Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
 
-**Quick links**: [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>]
-[<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a
-href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a
-href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas &
-Q&A</a>]
-
 <div align="center"><img src="assets/invoke-web-server-1.png" width=640></div>
 
-!!! note
+!!! Note
 
-    This fork is rapidly evolving. Please use the [Issues tab](https://github.com/invoke-ai/InvokeAI/issues) to report bugs and make feature requests. Be sure to use the provided templates. They will help aid diagnose issues faster.
+    This project is rapidly evolving. Please use the [Issues tab](https://github.com/invoke-ai/InvokeAI/issues) to report bugs and make feature requests. Be sure to use the provided templates as it will help aid response time.
 
-## :fontawesome-solid-computer: Hardware Requirements
+## :octicons-link-24: Quick Links
 
-### :octicons-cpu-24: System
+<div class="button-container">
+    <a href="installation/INSTALLATION"> <button class="button">Installation</button> </a>
+    <a href="features/"> <button class="button">Features</button> </a>
+    <a href="help/gettingStartedWithAI/"> <button class="button">Getting Started</button> </a>
+    <a href="contributing/CONTRIBUTING/"> <button class="button">Contributing</button> </a>
+    <a href="https://github.com/invoke-ai/InvokeAI/"> <button class="button">Code and Downloads</button> </a>
+    <a href="https://github.com/invoke-ai/InvokeAI/issues"> <button class="button">Bug Reports </button> </a>
+    <a href="https://discord.gg/ZmtBAhwWhy"> <button class="button"> Join the Discord Server!</button> </a>
+</div>
 
-You wil need one of the following:
-
-- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
-- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
-  only)
-- :fontawesome-brands-apple: An Apple computer with an M1 chip.
-
-We do **not recommend** the following video cards due to issues with their
-running in half-precision mode and having insufficient VRAM to render 512x512
-images in full-precision mode:
-
-- NVIDIA 10xx series cards such as the 1080ti
-- GTX 1650 series cards
-- GTX 1660 series cards
-
-### :fontawesome-solid-memory: Memory and Disk
-
-- At least 12 GB Main Memory RAM.
-- At least 18 GB of free disk space for the machine learning model, Python, and
-  all its dependencies.
-
-## :octicons-package-dependencies-24: Installation
-
-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).
-
-### [Installation Getting Started Guide](installation)
-#### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
-This method is recommended for 1st time users
-#### [Manual Installation](installation/020_INSTALL_MANUAL.md)
-This method is recommended for experienced users and developers
-#### [Docker Installation](installation/040_INSTALL_DOCKER.md)
-This method is recommended for those familiar with running Docker containers
-### Other Installation Guides
-  - [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
-  - [XFormers](installation/070_INSTALL_XFORMERS.md)
-  - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
-  - [Installing New Models](installation/050_INSTALLING_MODELS.md)
 
 ## :octicons-gift-24: InvokeAI Features
 
@@ -145,8 +135,9 @@ This method is recommended for those familiar with running Docker containers
 ### Model Management
 - [Installing](installation/050_INSTALLING_MODELS.md)
 - [Model Merging](features/MODEL_MERGING.md)
+- [ControlNet Models](features/CONTROLNET.md)
 - [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
-- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
+- [Watermarking and the Not Safe for Work (NSFW) Checker](features/WATERMARK+NSFW.md)
 <!-- seperator -->
 ### Prompt Engineering
 - [Prompt Syntax](features/PROMPTS.md)
@@ -221,18 +212,14 @@ get solutions for common installation problems and other issues.
 
 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. If you are unfamiliar with how to contribute to GitHub
-projects, here is a
-[Getting Started Guide](https://opensource.com/article/19/7/create-pull-request-github).
+encouraged to do so. 
 
-A full set of contribution guidelines, along with templates, are in progress,
-but for now the most important thing is to **make your pull request against the
-"development" branch**, and not against "main". This will help keep public
-breakage to a minimum and will allow you to propose more radical changes.
+[Please take a look at our Contribution documentation to learn more about contributing to InvokeAI. 
+](contributing/CONTRIBUTING.md)
 
 ## :octicons-person-24: Contributors
 
-This fork is a combined effort of various people from across the world.
+This software is a combined effort of various people from across the world.
 [Check out the list of all these amazing people](other/CONTRIBUTORS.md). We
 thank them for their time, hard work and effort.
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -40,10 +40,8 @@ experimental versions later.
     this, open up a command-line window ("Terminal" on Linux and
     Macintosh, "Command" or "Powershell" on Windows) and type `python
     --version`. If Python is installed, it will print out the version
-    number. If it is version `3.9.*` or `3.10.*`, you meet
-    requirements. We do not recommend using Python 3.11 or higher,
-    as not all the libraries that InvokeAI depends on work properly
-    with this version.
+    number. If it is version `3.9.*`, `3.10.*` or `3.11.*` you meet
+    requirements.
 
     !!! warning "What to do if you have an unsupported version"
 
@@ -124,9 +122,9 @@ experimental versions later.
     [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),
     and look for a file named:
 
-    - InvokeAI-installer-v2.X.X.zip
+    - InvokeAI-installer-v3.X.X.zip
 
-    where "2.X.X" is the latest released version. The file is located
+    where "3.X.X" is the latest released version. The file is located
     at the very bottom of the release page, under **Assets**.
 
 4.  **Unpack the installer**: Unpack the zip file into a convenient directory. This will create a new
@@ -215,17 +213,6 @@ experimental versions later.
     Generally the defaults are fine, and you can come back to this screen at
     any time to tweak your system. Here are the options you can adjust:
 
-    - ***Output directory for images***
-      This is the path to a directory in which InvokeAI will store all its
-      generated images.
-
-    - ***NSFW checker***
-      If checked, InvokeAI will test images for potential sexual content
-      and blur them out if found. Note that the NSFW checker consumes
-      an additional 0.6 GB of VRAM on top of the 2-3 GB of VRAM used
-      by most image models. If you have a low VRAM GPU (4-6 GB), you
-      can reduce out of memory errors by disabling the checker.
-
     - ***HuggingFace Access Token***
       InvokeAI has the ability to download embedded styles and subjects
       from the HuggingFace Concept Library on-demand. However, some of
@@ -257,20 +244,30 @@ experimental versions later.
 	and graphics cards. The "autocast" option is deprecated and
 	shouldn't be used unless you are asked to by a member of the team.
 
-    - ***Number of models to cache in CPU memory***
+    - **Size of the RAM cache used for fast model switching***
         This allows you to keep models in memory and switch rapidly among
 	them rather than having them load from disk each time. This slider
-	controls how many models to keep loaded at once. Each
-	model will use 2-4 GB of RAM, so use this cautiously
+	controls how many models to keep loaded at once. A typical SD-1 or SD-2 model
+	uses 2-3 GB of memory. A typical SDXL model uses 6-7 GB. Providing more
+	RAM will allow more models to be co-resident.
 
-    - ***Directory containing embedding/textual inversion files***
-        This is the directory in which you can place custom embedding
-	files (.pt or .bin). During startup, this directory will be
-	scanned and InvokeAI will print out the text terms that
-	are available to trigger the embeddings.
+    - ***Output directory for images***
+      This is the path to a directory in which InvokeAI will store all its
+      generated images.
+
+    - ***Autoimport Folder***
+      This is the directory in which you can place models you have
+	  downloaded and wish to load into InvokeAI. You can place a variety
+	  of models in this directory, including diffusers folders, .ckpt files,
+	  .safetensors files, as well as LoRAs, ControlNet and Textual Inversion
+	  files (both folder and file versions). To help organize this folder,
+	  you can create several levels of subfolders and drop your models into
+      whichever ones you want.
+	
+    - ***Autoimport FolderLICENSE***     
 
     At the bottom of the screen you will see a checkbox for accepting
-    the CreativeML Responsible AI License. You need to accept the license
+    the CreativeML Responsible AI Licenses. You need to accept the license
     in order to download Stable Diffusion models from the next screen.
 
     _You can come back to the startup options form_ as many times as you like.
@@ -375,8 +372,71 @@ experimental versions later.
         Once InvokeAI is installed, do not move or remove this directory."
 
 
+<a name="troubleshooting"></a>
 ## Troubleshooting
 
+### _OSErrors on Windows while installing dependencies_
+
+During a zip file installation or an online update, installation stops
+with an error like this:
+
+![broken-dependency-screenshot](../assets/troubleshooting/broken-dependency.png){:width="800px"}
+
+This seems to happen particularly often with the `pydantic` and
+`numpy` packages. The most reliable solution requires several manual
+steps to complete installation.
+
+Open up a Powershell window and navigate to the `invokeai` directory
+created by the installer. Then give the following series of commands:
+
+```cmd
+rm .\.venv -r -force
+python -mvenv .venv
+.\.venv\Scripts\activate
+pip install invokeai
+invokeai-configure --yes --root .
+```
+
+If you see anything marked as an error during this process please stop
+and seek help on the Discord [installation support
+channel](https://discord.com/channels/1020123559063990373/1041391462190956654). A
+few warning messages are OK.
+
+If you are updating from a previous version, this should restore your
+system to a working state. If you are installing from scratch, there
+is one additional command to give:
+
+```cmd
+wget -O invoke.bat https://raw.githubusercontent.com/invoke-ai/InvokeAI/main/installer/templates/invoke.bat.in
+```
+
+This will create the `invoke.bat` script needed to launch InvokeAI and
+its related programs.
+
+
+### _Stable Diffusion XL Generation Fails after Trying to Load unet_
+
+InvokeAI is working in other respects, but when trying to generate
+images with Stable Diffusion XL you get a "Server Error". The text log
+in the launch window contains this log line above several more lines of
+error messages:
+
+```INFO --> Loading model:D:\LONG\PATH\TO\MODEL, type sdxl:main:unet```
+
+This failure mode occurs when there is a network glitch during
+downloading the very large SDXL model.
+
+To address this, first go to the Web Model Manager and delete the
+Stable-Diffusion-XL-base-1.X model. Then navigate to HuggingFace and
+manually download the .safetensors version of the model. The 1.0
+version is located at
+https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main
+and the file is named `sd_xl_base_1.0.safetensors`.
+
+Save this file to disk and then reenter the Model Manager. Navigate to
+Import Models->Add Model, then type (or drag-and-drop) the path to the
+.safetensors file. Press "Add Model".
+
 ### _Package dependency conflicts_
 
 If you have previously installed InvokeAI or another Stable Diffusion

docs/installation/020_INSTALL_MANUAL.md

@@ -32,7 +32,7 @@ gaming):
 
 * **Python**
 
-    version 3.9 or 3.10 (3.11 is not recommended).
+    version 3.9 through 3.11
 
 * **CUDA Tools**
 
@@ -65,7 +65,7 @@ gaming):
 To install InvokeAI with virtual environments and the PIP package
 manager, please follow these steps:
 
-1.  Please make sure you are using Python 3.9 or 3.10. The rest of the install
+1.  Please make sure you are using Python 3.9 through 3.11. The rest of the install
     procedure depends on this and will not work with other versions:
 
     ```bash

docs/installation/INSTALLATION.md

@@ -1,6 +1,4 @@
----
-title: Overview
----
+# Overview
 
 We offer several ways to install InvokeAI, each one suited to your
 experience and preferences. We suggest that everyone start by
@@ -15,7 +13,57 @@ See the [troubleshooting
 section](010_INSTALL_AUTOMATED.md#troubleshooting) of the automated
 install guide for frequently-encountered installation issues.
 
-## Main Application
+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).
+
+### [Installation Getting Started Guide](installation)
+#### **[Automated Installer](010_INSTALL_AUTOMATED.md)**
+✅ This is the recommended installation method for first-time users. 
+#### [Manual Installation](020_INSTALL_MANUAL.md)
+This method is recommended for experienced users and developers
+#### [Docker Installation](040_INSTALL_DOCKER.md)
+This method is recommended for those familiar with running Docker containers
+### Other Installation Guides
+  - [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
+  - [XFormers](installation/070_INSTALL_XFORMERS.md)
+  - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
+  - [Installing New Models](installation/050_INSTALLING_MODELS.md)
+
+## :fontawesome-solid-computer: Hardware Requirements
+
+### :octicons-cpu-24: System
+
+You wil need one of the following:
+
+- :simple-nvidia: An NVIDIA-based graphics card with 4 GB or more VRAM memory.
+- :simple-amd: An AMD-based graphics card with 4 GB or more VRAM memory (Linux
+  only)
+- :fontawesome-brands-apple: An Apple computer with an M1 chip.
+
+** SDXL 1.0 Requirements*
+To use SDXL, user must have one of the following: 
+- :simple-nvidia: An NVIDIA-based graphics card with 8 GB or more VRAM memory.
+- :simple-amd: An AMD-based graphics card with 16 GB or more VRAM memory (Linux
+  only)
+- :fontawesome-brands-apple: An Apple computer with an M1 chip.
+
+
+### :fontawesome-solid-memory: Memory and Disk
+
+- At least 12 GB Main Memory RAM.
+- At least 18 GB of free disk space for the machine learning model, Python, and
+  all its dependencies.
+
+We do **not recommend** the following video cards due to issues with their
+running in half-precision mode and having insufficient VRAM to render 512x512
+images in full-precision mode:
+
+- NVIDIA 10xx series cards such as the 1080ti
+- GTX 1650 series cards
+- GTX 1660 series cards
+
+## Installation options
 
 1. [Automated Installer](010_INSTALL_AUTOMATED.md)
 
@@ -24,6 +72,9 @@ install guide for frequently-encountered installation issues.
     "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

docs/nodes/communityNodes.md

@@ -0,0 +1,53 @@
+# Community Nodes
+
+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](./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. Along with the node, an example node graph should be provided to help you get started with the node. 
+
+To use a community node graph, download the the `.json` node graph file and load it into Invoke AI via the **Load Nodes** button on the Node Editor. 
+
+## Disclaimer
+
+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
+
+**Description:** FaceTools is a collection of nodes created to manipulate faces as you would in Unified Canvas. It includes FaceMask, FaceOff, and FacePlace. FaceMask autodetects a face in the image using MediaPipe and creates a mask from it. FaceOff similarly detects a face, then takes the face off of the image by adding a square bounding box around it and cropping/scaling it. FacePlace puts the bounded face image from FaceOff back onto the original image. Using these nodes with other inpainting node(s), you can put new faces on existing things, put new things around existing faces, and work closer with a face as a bounded image. Additionally, you can supply X and Y offset values to scale/change the shape of the mask for finer control on FaceMask and FaceOff. See GitHub repository below for usage examples.
+
+**Node Link:** https://github.com/ymgenesis/FaceTools/
+
+**FaceMask Output Examples** 
+
+![5cc8abce-53b0-487a-b891-3bf94dcc8960](https://github.com/invoke-ai/InvokeAI/assets/25252829/43f36d24-1429-4ab1-bd06-a4bedfe0955e)
+![b920b710-1882-49a0-8d02-82dff2cca907](https://github.com/invoke-ai/InvokeAI/assets/25252829/7660c1ed-bf7d-4d0a-947f-1fc1679557ba)
+![71a91805-fda5-481c-b380-264665703133](https://github.com/invoke-ai/InvokeAI/assets/25252829/f8f6a2ee-2b68-4482-87da-b90221d5c3e2)
+
+<hr>
+
+### Ideal Size
+
+**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
+
+**Node Link:** https://github.com/JPPhoto/ideal-size-node
+
+--------------------------------
+### Example 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** 
+
+![Example Image](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png){: style="height:115px;width:240px"}
+
+## Help
+If you run into any issues with a node, please post in the [InvokeAI Discord](https://discord.gg/ZmtBAhwWhy). 
+
+

docs/nodes/overview.md

@@ -0,0 +1,42 @@
+# Nodes
+
+## What are Nodes?
+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.
+
+This means nodes can be used to easily extend the image generation capabilities of InvokeAI, and allow you build workflows to suit your needs. 
+
+You can read more about nodes and the node editor [here](../features/NODES.md). 
+
+
+## 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/other/CONTRIBUTORS.md

@@ -17,67 +17,267 @@ We thank them for all of their time and hard work.
 
 * @lstein (Lincoln Stein) - Co-maintainer
 * @blessedcoolant - Co-maintainer
-* @hipsterusername (Kent Keirsey) - Product Manager
-* @psychedelicious - Web Team Leader
+* @hipsterusername (Kent Keirsey) - Co-maintainer, CEO, Positive Vibes
+* @psychedelicious (Spencer Mabrito) - Web Team Leader
 * @Kyle0654 (Kyle Schouviller) - Node Architect and General Backend Wizard
-* @damian0815 - Attention Systems and Gameplay Engineer
-* @mauwii (Matthias Wild) - Continuous integration and product maintenance engineer
-* @Netsvetaev (Artur Netsvetaev) - UI/UX Developer
-* @tildebyte - General gadfly and resident (self-appointed) know-it-all
-* @keturn - Lead for Diffusers port
+* @damian0815 - Attention Systems and Compel Maintainer
 * @ebr (Eugene Brodsky) - Cloud/DevOps/Sofware engineer; your friendly neighbourhood cluster-autoscaler
-* @jpphoto (Jonathan Pollack) - Inference and rendering engine optimization
-* @genomancer (Gregg Helt) - Model training and merging
+* @genomancer (Gregg Helt) - Controlnet support
+* @StAlKeR7779 (Sergey Borisov) - Torch stack, ONNX, model management, optimization
+* @cheerio (Mary Rogers) - Lead Engineer & Web App Development
+* @brandon (Brandon Rising) - Platform, Infrastructure, Backend Systems
+* @ryanjdick (Ryan Dick) - Machine Learning & Training
+* @millu (Millun Atluri) - Community Manager, Documentation, Node-wrangler
+* @chainchompa (Jennifer Player) - Web Development & Chain-Chomping
+* @keturn (Kevin Turner) - Diffusers
+* @gogurt enjoyer - Discord moderator and end user support
+* @whosawhatsis - Discord moderator and end user support
+* @dwinrger - Discord moderator and end user support
+* @526christian - Discord moderator and end user support
 
-## **Contributions by**
+## **Full List of Contributors by Commit Name**
 
-- [Sean McLellan](https://github.com/Oceanswave)
-- [Kevin Gibbons](https://github.com/bakkot)
-- [Tesseract Cat](https://github.com/TesseractCat)
-- [blessedcoolant](https://github.com/blessedcoolant)
-- [David Ford](https://github.com/david-ford)
-- [yunsaki](https://github.com/yunsaki)
-- [James Reynolds](https://github.com/magnusviri)
-- [David Wager](https://github.com/maddavid123)
-- [Jason Toffaletti](https://github.com/toffaletti)
-- [tildebyte](https://github.com/tildebyte)
-- [Cragin Godley](https://github.com/cgodley)
-- [BlueAmulet](https://github.com/BlueAmulet)
-- [Benjamin Warner](https://github.com/warner-benjamin)
-- [Cora Johnson-Roberson](https://github.com/corajr)
-- [veprogames](https://github.com/veprogames)
-- [JigenD](https://github.com/JigenD)
-- [Niek van der Maas](https://github.com/Niek)
-- [Henry van Megen](https://github.com/hvanmegen)
-- [Håvard Gulldahl](https://github.com/havardgulldahl)
-- [greentext2](https://github.com/greentext2)
-- [Simon Vans-Colina](https://github.com/simonvc)
-- [Gabriel Rotbart](https://github.com/gabrielrotbart)
-- [Eric Khun](https://github.com/erickhun)
-- [Brent Ozar](https://github.com/BrentOzar)
-- [nderscore](https://github.com/nderscore)
-- [Mikhail Tishin](https://github.com/tishin)
-- [Tom Elovi Spruce](https://github.com/ilovecomputers)
-- [spezialspezial](https://github.com/spezialspezial)
-- [Yosuke Shinya](https://github.com/shinya7y)
-- [Andy Pilate](https://github.com/Cubox)
-- [Muhammad Usama](https://github.com/SMUsamaShah)
-- [Arturo Mendivil](https://github.com/artmen1516)
-- [Paul Sajna](https://github.com/sajattack)
-- [Samuel Husso](https://github.com/shusso)
-- [nicolai256](https://github.com/nicolai256)
-- [Mihai](https://github.com/mh-dm)
-- [Any Winter](https://github.com/any-winter-4079)
-- [Doggettx](https://github.com/doggettx)
-- [Matthias Wild](https://github.com/mauwii)
-- [Kyle Schouviller](https://github.com/kyle0654)
-- [rabidcopy](https://github.com/rabidcopy)
-- [Dominic Letz](https://github.com/dominicletz)
-- [Dmitry T.](https://github.com/ArDiouscuros)
-- [Kent Keirsey](https://github.com/hipsterusername)
-- [psychedelicious](https://github.com/psychedelicious)
-- [damian0815](https://github.com/damian0815)
-- [Eugene Brodsky](https://github.com/ebr)
+- AbdBarho
+- ablattmann
+- AdamOStark
+- Adam Rice
+- Airton Silva
+- Alexander Eichhorn
+- Alexandre D. Roberge
+- Andreas Rozek
+- Andre LaBranche
+- Andy Bearman
+- Andy Luhrs
+- Andy Pilate
+- Any-Winter-4079
+- apolinario
+- ArDiouscuros
+- Armando C. Santisbon
+- Arthur Holstvoogd
+- artmen1516
+- Artur
+- Arturo Mendivil
+- Ben Alkov
+- Benjamin Warner
+- Bernard Maltais
+- blessedcoolant
+- blhook
+- BlueAmulet
+- Bouncyknighter
+- Brandon Rising
+- Brent Ozar
+- Brian Racer
+- bsilvereagle
+- c67e708d
+- CapableWeb
+- Carson Katri
+- Chloe
+- Chris Dawson
+- Chris Hayes
+- Chris Jones
+- chromaticist
+- Claus F. Strasburger
+- cmdr2
+- cody
+- Conor Reid
+- Cora Johnson-Roberson
+- coreco
+- cosmii02
+- cpacker
+- Cragin Godley
+- creachec
+- Damian Stewart
+- Daniel Manzke
+- Danny Beer
+- Dan Sully
+- David Burnett
+- David Ford
+- David Regla
+- David Wager
+- Daya Adianto
+- db3000
+- Denis Olshin
+- Dennis
+- Dominic Letz
+- DrGunnarMallon
+- Edward Johan
+- elliotsayes
+- Elrik
+- ElrikUnderlake
+- Eric Khun
+- Eric Wolf
+- Eugene Brodsky
+- ExperimentalCyborg
+- Fabian Bahl
+- Fabio 'MrWHO' Torchetti
+- fattire
+- Felipe Nogueira
+- Félix Sanz
+- figgefigge
+- Gabriel Mackievicz Telles
+- gabrielrotbart
+- gallegonovato
+- Gérald LONLAS
+- GitHub Actions Bot
+- gogurtenjoyer
+- greentext2
+- Gregg Helt
+- H4rk
+- Håvard Gulldahl
+- henry
+- Henry van Megen
+- hipsterusername
+- hj
+- Hosted Weblate
+- Iman Karim
+- ismail ihsan bülbül
+- Ivan Efimov
+- jakehl
+- Jakub Kolčář
+- JamDon2
+- James Reynolds
+- Jan Skurovec
+- Jari Vetoniemi
+- Jason Toffaletti
+- Jaulustus
+- Jeff Mahoney
+- jeremy
+- Jeremy Clark
+- JigenD
+- Jim Hays
+- Johan Roxendal
+- Johnathon Selstad
+- Jonathan
+- Joseph Dries III
+- JPPhoto
+- jspraul
+- Justin Wong
+- Juuso V
+- Kaspar Emanuel
+- Katsuyuki-Karasawa
+- Kent Keirsey
+- Kevin Coakley
+- Kevin Gibbons
+- Kevin Schaul
+- Kevin Turner
+- krummrey
+- Kyle Lacy
+- Kyle Schouviller
+- Lawrence Norton
+- LemonDouble
+- Leo Pasanen
+- Lincoln Stein
+- LoganPederson
+- Lynne Whitehorn
+- majick
+- Marco Labarile
+- Martin Kristiansen
+- Mary Hipp Rogers
+- mastercaster9000
+- Matthias Wild
+- michaelk71
+- mickr777
+- Mihai
+- Mihail Dumitrescu
+- Mikhail Tishin
+- Millun Atluri
+- Minjune Song
+- mitien
+- mofuzz
+- Muhammad Usama
+- Name
+- _nderscore
+- Netzer R
+- Nicholas Koh
+- Nicholas Körfer
+- nicolai256
+- Niek van der Maas
+- noodlebox
+- Nuno Coração
+- ofirkris
+- Olivier Louvignes
+- owenvincent
+- Patrick Esser
+- Patrick Tien
+- Patrick von Platen
+- Paul Sajna
+- pejotr
+- Peter Baylies
+- Peter Lin
+- plucked
+- prixt
+- psychedelicious
+- Rainer Bernhardt
+- Riccardo Giovanetti
+- Rich Jones
+- rmagur1203
+- Rob Baines
+- Robert Bolender
+- Robin Rombach
+- Rohan Barar
+- rpagliuca
+- rromb
+- Rupesh Sreeraman
+- Ryan Cao
+- Saifeddine
+- Saifeddine ALOUI
+- SammCheese
+- Sammy
+- sammyf
+- Samuel Husso
+- Scott Lahteine
+- Sean McLellan
+- Sebastian Aigner
+- Sergey Borisov
+- Sergey Krashevich
+- Shapor Naghibzadeh
+- Shawn Zhong
+- Simon Vans-Colina
+- skunkworxdark
+- slashtechno
+- spezialspezial
+- ssantos
+- StAlKeR7779
+- Stephan Koglin-Fischer
+- SteveCaruso
+- Steve Martinelli
+- Steven Frank
+- System X - Files
+- Taylor Kems
+- techicode
+- techybrain-dev
+- tesseractcat
+- thealanle
+- Thomas
+- tildebyte
+- Tim Cabbage
+- Tom
+- Tom Elovi Spruce
+- Tom Gouville
+- tomosuto
+- Travco
+- Travis Palmer
+- tyler
+- unknown
+- user1
+- Vedant Madane
+- veprogames
+- wa.code
+- wfng92
+- whosawhatsis
+- Will
+- William Becher
+- William Chong
+- xra
+- Yeung Yiu Hung
+- ymgenesis
+- Yorzaren
+- Yosuke Shinya
+- yun saki
+- Zadagu
+- zeptofine
+- 冯不游
+- 唐澤 克幸
 
 ## **Original CompVis Authors**
 

flake.lock

@@ -0,0 +1,25 @@
+{
+  "nodes": {
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1690630721,
+        "narHash": "sha256-Y04onHyBQT4Erfr2fc82dbJTfXGYrf4V0ysLUYnPOP8=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "d2b52322f35597c62abf56de91b0236746b2a03d",
+        "type": "github"
+      },
+      "original": {
+        "id": "nixpkgs",
+        "type": "indirect"
+      }
+    },
+    "root": {
+      "inputs": {
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,91 @@
+# Important note: this flake does not attempt to create a fully isolated, 'pure'
+# Python environment for InvokeAI. Instead, it depends on local invocations of
+# virtualenv/pip to install the required (binary) packages, most importantly the
+# prebuilt binary pytorch packages with CUDA support.
+# ML Python packages with CUDA support, like pytorch, are notoriously expensive
+# to compile so it's purposefuly not what this flake does.
+
+{
+  description = "An (impure) flake to develop on InvokeAI.";
+
+  outputs = { self, nixpkgs }:
+    let
+      system = "x86_64-linux";
+      pkgs = import nixpkgs {
+        inherit system;
+        config.allowUnfree = true;
+      };
+
+      python = pkgs.python310;
+
+      mkShell = { dir, install }:
+        let
+          setupScript = pkgs.writeScript "setup-invokai" ''
+            # This must be sourced using 'source', not executed.
+            ${python}/bin/python -m venv ${dir}
+            ${dir}/bin/python -m pip install ${install}
+            # ${dir}/bin/python -c 'import torch; assert(torch.cuda.is_available())'
+            source ${dir}/bin/activate
+          '';
+        in
+        pkgs.mkShell rec {
+          buildInputs = with pkgs; [
+            # Backend: graphics, CUDA.
+            cudaPackages.cudnn
+            cudaPackages.cuda_nvrtc
+            cudatoolkit
+            pkgconfig
+            libconfig
+            cmake
+            blas
+            freeglut
+            glib
+            gperf
+            procps
+            libGL
+            libGLU
+            linuxPackages.nvidia_x11
+            python
+            (opencv4.override {
+              enableGtk3 = true;
+              enableFfmpeg = true;
+              enableCuda = true;
+              enableUnfree = true;
+            })
+            stdenv.cc
+            stdenv.cc.cc.lib
+            xorg.libX11
+            xorg.libXext
+            xorg.libXi
+            xorg.libXmu
+            xorg.libXrandr
+            xorg.libXv
+            zlib
+
+            # Pre-commit hooks.
+            black
+
+            # Frontend.
+            yarn
+            nodejs
+          ];
+          LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath buildInputs;
+          CUDA_PATH = pkgs.cudatoolkit;
+          EXTRA_LDFLAGS = "-L${pkgs.linuxPackages.nvidia_x11}/lib";
+          shellHook = ''
+            if [[ -f "${dir}/bin/activate" ]]; then
+              source "${dir}/bin/activate"
+              echo "Using Python: $(which python)"
+            else
+              echo "Use 'source ${setupScript}' to set up the environment."
+            fi
+          '';
+        };
+    in
+    {
+      devShells.${system} = rec {
+        develop = mkShell { dir = "venv"; install = "-e '.[xformers]' --extra-index-url https://download.pytorch.org/whl/cu118"; };
+        default = develop;
+      };
+    };
+}

installer/install.sh.in

@@ -9,16 +9,20 @@ cd $scriptdir
 function version { echo "$@" | awk -F. '{ printf("%d%03d%03d%03d\n", $1,$2,$3,$4); }'; }
 
 MINIMUM_PYTHON_VERSION=3.9.0
-MAXIMUM_PYTHON_VERSION=3.11.0
+MAXIMUM_PYTHON_VERSION=3.11.100
 PYTHON=""
-for candidate in python3.10 python3.9 python3 python ; do
+for candidate in python3.11 python3.10 python3.9 python3 python ; do
     if ppath=`which $candidate`; then
+        # when using `pyenv`, the executable for an inactive Python version will exist but will not be operational
+        # we check that this found executable can actually run
+        if [ $($candidate --version &>/dev/null; echo ${PIPESTATUS}) -gt 0 ]; then continue; fi
+
         python_version=$($ppath -V | awk '{ print $2 }')
         if [ $(version $python_version) -ge $(version "$MINIMUM_PYTHON_VERSION") ]; then
-	    if [ $(version $python_version) -lt $(version "$MAXIMUM_PYTHON_VERSION") ]; then
-		PYTHON=$ppath
-		break
-	    fi
+            if [ $(version $python_version) -le $(version "$MAXIMUM_PYTHON_VERSION") ]; then
+                PYTHON=$ppath
+                break
+            fi
         fi
     fi
 done

installer/lib/installer.py

@@ -13,7 +13,7 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 from typing import Union
 
-SUPPORTED_PYTHON = ">=3.9.0,<3.11"
+SUPPORTED_PYTHON = ">=3.9.0,<=3.11.100"
 INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
 BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
 
@@ -141,15 +141,16 @@ class Installer:
 
         # upgrade pip in Python 3.9 environments
         if int(platform.python_version_tuple()[1]) == 9:
-
             from plumbum import FG, local
 
             pip = local[get_pip_from_venv(venv_dir)]
-            pip[ "install", "--upgrade", "pip"] & FG
+            pip["install", "--upgrade", "pip"] & FG
 
         return venv_dir
 
-    def install(self, root: str = "~/invokeai-3", version: str = "latest", yes_to_all=False, find_links: Path = None) -> None:
+    def install(
+        self, root: str = "~/invokeai", version: str = "latest", yes_to_all=False, find_links: Path = None
+    ) -> None:
         """
         Install the InvokeAI application into the given runtime path
 
@@ -167,7 +168,8 @@ class Installer:
 
         messages.welcome()
 
-        self.dest = Path(root).expanduser().resolve() if yes_to_all else messages.dest_path(root)
+        default_path = os.environ.get("INVOKEAI_ROOT") or Path(root).expanduser().resolve()
+        self.dest = default_path if yes_to_all else messages.dest_path(root)
 
         # create the venv for the app
         self.venv = self.app_venv()
@@ -175,7 +177,7 @@ class Installer:
         self.instance = InvokeAiInstance(runtime=self.dest, venv=self.venv, version=version)
 
         # install dependencies and the InvokeAI application
-        (extra_index_url,optional_modules) = get_torch_source() if not yes_to_all else (None,None)
+        (extra_index_url, optional_modules) = get_torch_source() if not yes_to_all else (None, None)
         self.instance.install(
             extra_index_url,
             optional_modules,
@@ -188,6 +190,7 @@ class Installer:
         # run through the configuration flow
         self.instance.configure()
 
+
 class InvokeAiInstance:
     """
     Manages an installed instance of InvokeAI, comprising a virtual environment and a runtime directory.
@@ -196,7 +199,6 @@ class InvokeAiInstance:
     """
 
     def __init__(self, runtime: Path, venv: Path, version: str) -> None:
-
         self.runtime = runtime
         self.venv = venv
         self.pip = get_pip_from_venv(venv)
@@ -247,6 +249,9 @@ class InvokeAiInstance:
             pip[
                 "install",
                 "--require-virtualenv",
+                "numpy~=1.24.0",  # choose versions that won't be uninstalled during phase 2
+                "urllib3~=1.26.0",
+                "requests~=2.28.0",
                 "torch~=2.0.0",
                 "torchmetrics==0.11.4",
                 "torchvision>=0.14.1",
@@ -312,7 +317,7 @@ class InvokeAiInstance:
                 "install",
                 "--require-virtualenv",
                 "--use-pep517",
-                str(src)+(optional_modules if optional_modules else ''),
+                str(src) + (optional_modules if optional_modules else ""),
                 "--find-links" if find_links is not None else None,
                 find_links,
                 "--extra-index-url" if extra_index_url is not None else None,
@@ -329,15 +334,15 @@ class InvokeAiInstance:
 
         # set sys.argv to a consistent state
         new_argv = [sys.argv[0]]
-        for i in range(1,len(sys.argv)):
+        for i in range(1, len(sys.argv)):
             el = sys.argv[i]
-            if el in ['-r','--root']:
+            if el in ["-r", "--root"]:
                 new_argv.append(el)
-                new_argv.append(sys.argv[i+1])
-            elif el in ['-y','--yes','--yes-to-all']:
+                new_argv.append(sys.argv[i + 1])
+            elif el in ["-y", "--yes", "--yes-to-all"]:
                 new_argv.append(el)
         sys.argv = new_argv
-        
+
         import requests  # to catch download exceptions
         from messages import introduction
 
@@ -353,16 +358,16 @@ class InvokeAiInstance:
             invokeai_configure()
             succeeded = True
         except requests.exceptions.ConnectionError as e:
-            print(f'\nA network error was encountered during configuration and download: {str(e)}')
+            print(f"\nA network error was encountered during configuration and download: {str(e)}")
         except OSError as e:
-            print(f'\nAn OS error was encountered during configuration and download: {str(e)}')
+            print(f"\nAn OS error was encountered during configuration and download: {str(e)}")
         except Exception as e:
-            print(f'\nA problem was encountered during the configuration and download steps: {str(e)}')
+            print(f"\nA problem was encountered during the configuration and download steps: {str(e)}")
         finally:
             if not succeeded:
                 print('To try again, find the "invokeai" directory, run the script "invoke.sh" or "invoke.bat"')
-                print('and choose option 7 to fix a broken install, optionally followed by option 5 to install models.')
-                print('Alternatively you can relaunch the installer.')
+                print("and choose option 7 to fix a broken install, optionally followed by option 5 to install models.")
+                print("Alternatively you can relaunch the installer.")
 
     def install_user_scripts(self):
         """
@@ -371,11 +376,11 @@ class InvokeAiInstance:
 
         ext = "bat" if OS == "Windows" else "sh"
 
-        #scripts = ['invoke', 'update']
-        scripts = ['invoke']
-        
+        # scripts = ['invoke', 'update']
+        scripts = ["invoke"]
+
         for script in scripts:
-            src = Path(__file__).parent / '..' / "templates" / f"{script}.{ext}.in"
+            src = Path(__file__).parent / ".." / "templates" / f"{script}.{ext}.in"
             dest = self.runtime / f"{script}.{ext}"
             shutil.copy(src, dest)
             os.chmod(dest, 0o0755)
@@ -420,11 +425,7 @@ def set_sys_path(venv_path: Path) -> None:
     # filter out any paths in sys.path that may be system- or user-wide
     # but leave the temporary bootstrap virtualenv as it contains packages we
     # temporarily need at install time
-    sys.path = list(filter(
-        lambda p: not p.endswith("-packages")
-        or p.find(BOOTSTRAP_VENV_PREFIX) != -1,
-        sys.path
-    ))
+    sys.path = list(filter(lambda p: not p.endswith("-packages") or p.find(BOOTSTRAP_VENV_PREFIX) != -1, sys.path))
 
     # determine site-packages/lib directory location for the venv
     lib = "Lib" if OS == "Windows" else f"lib/python{sys.version_info.major}.{sys.version_info.minor}"
@@ -433,7 +434,7 @@ def set_sys_path(venv_path: Path) -> None:
     sys.path.append(str(Path(venv_path, lib, "site-packages").expanduser().resolve()))
 
 
-def get_torch_source() -> (Union[str, None],str):
+def get_torch_source() -> (Union[str, None], str):
     """
     Determine the extra index URL for pip to use for torch installation.
     This depends on the OS and the graphics accelerator in use.
@@ -454,16 +455,19 @@ def get_torch_source() -> (Union[str, None],str):
     device = graphical_accelerator()
 
     url = None
-    optional_modules = None
+    optional_modules = "[onnx]"
     if OS == "Linux":
         if device == "rocm":
             url = "https://download.pytorch.org/whl/rocm5.4.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
-    if device == 'cuda':
-        url = 'https://download.pytorch.org/whl/cu117'
-        optional_modules = '[xformers]'
+    if device == "cuda":
+        url = "https://download.pytorch.org/whl/cu117"
+        optional_modules = "[xformers,onnx-cuda]"
+    if device == "cuda_and_dml":
+        url = "https://download.pytorch.org/whl/cu117"
+        optional_modules = "[xformers,onnx-directml]"
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/lib/main.py

@@ -3,6 +3,7 @@ InvokeAI Installer
 """
 
 import argparse
+import os
 from pathlib import Path
 from installer import Installer
 
@@ -15,7 +16,7 @@ if __name__ == "__main__":
         dest="root",
         type=str,
         help="Destination path for installation",
-        default="~/invokeai",
+        default=os.environ.get("INVOKEAI_ROOT") or "~/invokeai",
     )
     parser.add_argument(
         "-y",
@@ -41,7 +42,7 @@ if __name__ == "__main__":
         type=Path,
         default=None,
     )
-    
+
     args = parser.parse_args()
 
     inst = Installer()

installer/lib/messages.py

@@ -36,13 +36,15 @@ else:
 
 
 def welcome():
-
     @group()
     def text():
         if (platform_specific := _platform_specific_help()) != "":
             yield platform_specific
             yield ""
-        yield Text.from_markup("Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.", justify="center")
+        yield Text.from_markup(
+            "Some of the installation steps take a long time to run. Please be patient. If the script appears to hang for more than 10 minutes, please interrupt with [i]Control-C[/] and retry.",
+            justify="center",
+        )
 
     console.rule()
     print(
@@ -58,6 +60,7 @@ def welcome():
     )
     console.line()
 
+
 def confirm_install(dest: Path) -> bool:
     if dest.exists():
         print(f":exclamation: Directory {dest} already exists :exclamation:")
@@ -92,7 +95,6 @@ def dest_path(dest=None) -> Path:
     dest_confirmed = confirm_install(dest)
 
     while not dest_confirmed:
-
         # if the given destination already exists, the starting point for browsing is its parent directory.
         # the user may have made a typo, or otherwise wants to place the root dir next to an existing one.
         # if the destination dir does NOT exist, then the user must have changed their mind about the selection.
@@ -165,6 +167,10 @@ def graphical_accelerator():
         "an [gold1 b]NVIDIA[/] GPU (using CUDA™)",
         "cuda",
     )
+    nvidia_with_dml = (
+        "an [gold1 b]NVIDIA[/] GPU (using CUDA™, and DirectML™ for ONNX) -- ALPHA",
+        "cuda_and_dml",
+    )
     amd = (
         "an [gold1 b]AMD[/] GPU (using ROCm™)",
         "rocm",
@@ -179,7 +185,7 @@ def graphical_accelerator():
     )
 
     if OS == "Windows":
-        options = [nvidia, cpu]
+        options = [nvidia, nvidia_with_dml, cpu]
     if OS == "Linux":
         options = [nvidia, amd, cpu]
     elif OS == "Darwin":
@@ -300,15 +306,20 @@ def introduction() -> None:
     )
     console.line(2)
 
-def _platform_specific_help()->str:
+
+def _platform_specific_help() -> str:
     if OS == "Darwin":
-        text = Text.from_markup("""[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/].""")
+        text = Text.from_markup(
+            """[b wheat1]macOS Users![/]\n\nPlease be sure you have the [b wheat1]Xcode command-line tools[/] installed before continuing.\nIf not, cancel with [i]Control-C[/] and follow the Xcode install instructions at [deep_sky_blue1]https://www.freecodecamp.org/news/install-xcode-command-line-tools/[/]."""
+        )
     elif OS == "Windows":
-        text = Text.from_markup("""[b wheat1]Windows Users![/]\n\nBefore you start, please do the following:
+        text = Text.from_markup(
+            """[b wheat1]Windows Users![/]\n\nBefore you start, please do the following:
   1. Double-click on the file [b wheat1]WinLongPathsEnabled.reg[/] in order to
      enable long path support on your system.
   2. Make sure you have the [b wheat1]Visual C++ core libraries[/] installed. If not, install from
-     [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]""")
+     [deep_sky_blue1]https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170[/]"""
+        )
     else:
         text = ""
     return text

installer/templates/invoke.bat.in

@@ -41,7 +41,7 @@ IF /I "%choice%" == "1" (
     python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
 ) ELSE IF /I "%choice%" == "7" (
     echo Running invokeai-configure...
-    python .venv\Scripts\invokeai-configure.exe --yes --default_only
+    python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
 ) ELSE IF /I "%choice%" == "8" (
     echo Developer Console
     echo Python command is:

installer/templates/invoke.sh.in

@@ -82,7 +82,7 @@ do_choice() {
     7)
         clear
         printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
-        invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
+        invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only --skip-sd-weights
         ;;
     8)
         clear

invokeai/app/api/dependencies.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+from typing import Optional
 from logging import Logger
 import os
 from invokeai.app.services.board_image_record_storage import (
@@ -29,6 +30,8 @@ from ..services.invoker import Invoker
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
 from ..services.model_manager_service import ModelManagerService
+from ..services.batch_manager import BatchManager
+from ..services.batch_manager_storage import SqliteBatchProcessStorage
 from .events import FastAPIEventService
 
 
@@ -54,11 +57,12 @@ logger = InvokeAILogger.getLogger()
 class ApiDependencies:
     """Contains and initializes all dependencies for the API"""
 
-    invoker: Invoker = None
+    invoker: Optional[Invoker] = None
 
     @staticmethod
     def initialize(config: InvokeAIAppConfig, event_handler_id: int, logger: Logger = logger):
-        logger.debug(f"InvokeAI version {__version__}")
+        logger.info(f"InvokeAI version {__version__}")
+        logger.info(f"Root directory = {str(config.root_path)}")
         logger.debug(f"Internet connectivity is {config.internet_available}")
 
         events = FastAPIEventService(event_handler_id)
@@ -77,9 +81,7 @@ class ApiDependencies:
         image_record_storage = SqliteImageRecordStorage(db_location)
         image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
         names = SimpleNameService()
-        latents = ForwardCacheLatentsStorage(
-            DiskLatentsStorage(f"{output_folder}/latents")
-        )
+        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents"))
 
         board_record_storage = SqliteBoardRecordStorage(db_location)
         board_image_record_storage = SqliteBoardImageRecordStorage(db_location)
@@ -116,17 +118,19 @@ class ApiDependencies:
             )
         )
 
+        batch_manager_storage = SqliteBatchProcessStorage(db_location)
+        batch_manager = BatchManager(batch_manager_storage)
+
         services = InvocationServices(
             model_manager=ModelManagerService(config, logger),
             events=events,
             latents=latents,
             images=images,
+            batch_manager=batch_manager,
             boards=boards,
             board_images=board_images,
             queue=MemoryInvocationQueue(),
-            graph_library=SqliteItemStorage[LibraryGraph](
-                filename=db_location, table_name="graphs"
-            ),
+            graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
             graph_execution_manager=graph_execution_manager,
             processor=DefaultInvocationProcessor(),
             configuration=config,

invokeai/app/api/routers/app_info.py

@@ -1,9 +1,35 @@
+import typing
+from enum import Enum
+from fastapi import Body
 from fastapi.routing import APIRouter
+from pathlib import Path
 from pydantic import BaseModel, Field
 
 from invokeai.backend.image_util.patchmatch import PatchMatch
+from invokeai.backend.image_util.safety_checker import SafetyChecker
+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):
+    NotSet = logging.NOTSET
+    Debug = logging.DEBUG
+    Info = logging.INFO
+    Warning = logging.WARNING
+    Error = logging.ERROR
+    Critical = logging.CRITICAL
+
+
+class Upscaler(BaseModel):
+    upscaling_method: str = Field(description="Name of upscaling method")
+    upscaling_models: list[str] = Field(description="List of upscaling models for this method")
+
+
 app_router = APIRouter(prefix="/v1/app", tags=["app"])
 
 
@@ -17,20 +43,63 @@ class AppConfig(BaseModel):
     """App Config Response"""
 
     infill_methods: list[str] = Field(description="List of available infill methods")
+    upscaling_methods: list[Upscaler] = Field(description="List of upscaling methods")
+    nsfw_methods: list[str] = Field(description="List of NSFW checking methods")
+    watermarking_methods: list[str] = Field(description="List of invisible watermark methods")
 
 
-@app_router.get(
-    "/version", operation_id="app_version", status_code=200, response_model=AppVersion
-)
+@app_router.get("/version", operation_id="app_version", status_code=200, response_model=AppVersion)
 async def get_version() -> AppVersion:
     return AppVersion(version=__version__)
 
 
-@app_router.get(
-    "/config", operation_id="get_config", status_code=200, response_model=AppConfig
-)
+@app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
 async def get_config() -> AppConfig:
-    infill_methods = ['tile']
+    infill_methods = ["tile"]
     if PatchMatch.patchmatch_available():
-        infill_methods.append('patchmatch')
-    return AppConfig(infill_methods=infill_methods)
+        infill_methods.append("patchmatch")
+
+    upscaling_models = []
+    for model in typing.get_args(ESRGAN_MODELS):
+        upscaling_models.append(str(Path(model).stem))
+    upscaler = Upscaler(upscaling_method="esrgan", upscaling_models=upscaling_models)
+
+    nsfw_methods = []
+    if SafetyChecker.safety_checker_available():
+        nsfw_methods.append("nsfw_checker")
+
+    watermarking_methods = []
+    if InvisibleWatermark.invisible_watermark_available():
+        watermarking_methods.append("invisible_watermark")
+
+    return AppConfig(
+        infill_methods=infill_methods,
+        upscaling_methods=[upscaler],
+        nsfw_methods=nsfw_methods,
+        watermarking_methods=watermarking_methods,
+    )
+
+
+@app_router.get(
+    "/logging",
+    operation_id="get_log_level",
+    responses={200: {"description": "The operation was successful"}},
+    response_model=LogLevel,
+)
+async def get_log_level() -> LogLevel:
+    """Returns the log level"""
+    return LogLevel(ApiDependencies.invoker.services.logger.level)
+
+
+@app_router.post(
+    "/logging",
+    operation_id="set_log_level",
+    responses={200: {"description": "The operation was successful"}},
+    response_model=LogLevel,
+)
+async def set_log_level(
+    level: LogLevel = Body(description="New log verbosity level"),
+) -> LogLevel:
+    """Sets the log verbosity level"""
+    ApiDependencies.invoker.services.logger.setLevel(level)
+    return LogLevel(ApiDependencies.invoker.services.logger.level)

invokeai/app/api/routers/board_images.py

@@ -24,11 +24,14 @@ async def create_board_image(
 ):
     """Creates a board_image"""
     try:
-        result = ApiDependencies.invoker.services.board_images.add_image_to_board(board_id=board_id, image_name=image_name)
+        result = ApiDependencies.invoker.services.board_images.add_image_to_board(
+            board_id=board_id, image_name=image_name
+        )
         return result
     except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to add to board")
-    
+
+
 @board_images_router.delete(
     "/",
     operation_id="remove_board_image",
@@ -43,27 +46,9 @@ async def remove_board_image(
 ):
     """Deletes a board_image"""
     try:
-        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(board_id=board_id, image_name=image_name)
+        result = ApiDependencies.invoker.services.board_images.remove_image_from_board(
+            board_id=board_id, image_name=image_name
+        )
         return result
     except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to update board")
-
-
-
-@board_images_router.get(
-    "/{board_id}",
-    operation_id="list_board_images",
-    response_model=OffsetPaginatedResults[ImageDTO],
-)
-async def list_board_images(
-    board_id: str = Path(description="The id of the board"),
-    offset: int = Query(default=0, description="The page offset"),
-    limit: int = Query(default=10, description="The number of boards per page"),
-) -> OffsetPaginatedResults[ImageDTO]:
-    """Gets a list of images for a board"""
-
-    results = ApiDependencies.invoker.services.board_images.get_images_for_board(
-        board_id,
-    )
-    return results
-

invokeai/app/api/routers/boards.py

@@ -1,16 +1,26 @@
 from typing import Optional, Union
+
 from fastapi import Body, HTTPException, Path, Query
 from fastapi.routing import APIRouter
+from pydantic import BaseModel, Field
+
 from invokeai.app.services.board_record_storage import BoardChanges
 from invokeai.app.services.image_record_storage import OffsetPaginatedResults
 from invokeai.app.services.models.board_record import BoardDTO
 
-
 from ..dependencies import ApiDependencies
 
 boards_router = APIRouter(prefix="/v1/boards", tags=["boards"])
 
 
+class DeleteBoardResult(BaseModel):
+    board_id: str = Field(description="The id of the board that was deleted.")
+    deleted_board_images: list[str] = Field(
+        description="The image names of the board-images relationships that were deleted."
+    )
+    deleted_images: list[str] = Field(description="The names of the images that were deleted.")
+
+
 @boards_router.post(
     "/",
     operation_id="create_board",
@@ -61,33 +71,42 @@ async def update_board(
 ) -> BoardDTO:
     """Updates a board"""
     try:
-        result = ApiDependencies.invoker.services.boards.update(
-            board_id=board_id, changes=changes
-        )
+        result = ApiDependencies.invoker.services.boards.update(board_id=board_id, changes=changes)
         return result
     except Exception as e:
         raise HTTPException(status_code=500, detail="Failed to update board")
 
 
-@boards_router.delete("/{board_id}", operation_id="delete_board")
+@boards_router.delete("/{board_id}", operation_id="delete_board", response_model=DeleteBoardResult)
 async def delete_board(
     board_id: str = Path(description="The id of board to delete"),
-    include_images: Optional[bool] = Query(
-        description="Permanently delete all images on the board", default=False
-    ),
-) -> None:
+    include_images: Optional[bool] = Query(description="Permanently delete all images on the board", default=False),
+) -> DeleteBoardResult:
     """Deletes a board"""
     try:
         if include_images is True:
-            ApiDependencies.invoker.services.images.delete_images_on_board(
+            deleted_images = ApiDependencies.invoker.services.board_images.get_all_board_image_names_for_board(
+                board_id=board_id
+            )
+            ApiDependencies.invoker.services.images.delete_images_on_board(board_id=board_id)
+            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+            return DeleteBoardResult(
+                board_id=board_id,
+                deleted_board_images=[],
+                deleted_images=deleted_images,
+            )
+        else:
+            deleted_board_images = ApiDependencies.invoker.services.board_images.get_all_board_image_names_for_board(
                 board_id=board_id
             )
             ApiDependencies.invoker.services.boards.delete(board_id=board_id)
-        else:
-            ApiDependencies.invoker.services.boards.delete(board_id=board_id)
+            return DeleteBoardResult(
+                board_id=board_id,
+                deleted_board_images=deleted_board_images,
+                deleted_images=[],
+            )
     except Exception as e:
-        # TODO: Does this need any exception handling at all?
-        pass
+        raise HTTPException(status_code=500, detail="Failed to delete board")
 
 
 @boards_router.get(
@@ -98,9 +117,7 @@ async def delete_board(
 async def list_boards(
     all: Optional[bool] = Query(default=None, description="Whether to list all boards"),
     offset: Optional[int] = Query(default=None, description="The page offset"),
-    limit: Optional[int] = Query(
-        default=None, description="The number of boards per page"
-    ),
+    limit: Optional[int] = Query(default=None, description="The number of boards per page"),
 ) -> Union[OffsetPaginatedResults[BoardDTO], list[BoardDTO]]:
     """Gets a list of boards"""
     if all:
@@ -115,3 +132,19 @@ async def list_boards(
             status_code=400,
             detail="Invalid request: Must provide either 'all' or both 'offset' and 'limit'",
         )
+
+
+@boards_router.get(
+    "/{board_id}/image_names",
+    operation_id="list_all_board_image_names",
+    response_model=list[str],
+)
+async def list_all_board_image_names(
+    board_id: str = Path(description="The id of the board"),
+) -> list[str]:
+    """Gets a list of images for a board"""
+
+    image_names = ApiDependencies.invoker.services.board_images.get_all_board_image_names_for_board(
+        board_id,
+    )
+    return image_names

invokeai/app/api/routers/images.py

@@ -1,8 +1,7 @@
 import io
 from typing import Optional
 
-from fastapi import (Body, HTTPException, Path, Query, Request, Response,
-                     UploadFile)
+from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
 from fastapi.responses import FileResponse
 from fastapi.routing import APIRouter
 from PIL import Image
@@ -11,9 +10,11 @@ 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.item_storage import PaginatedResults
-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
 
@@ -39,9 +40,9 @@ async def upload_image(
     response: Response,
     image_category: ImageCategory = Query(description="The category of the image"),
     is_intermediate: bool = Query(description="Whether this is an intermediate image"),
-    session_id: Optional[str] = Query(
-        default=None, description="The session ID associated with this upload, if any"
-    ),
+    board_id: Optional[str] = Query(default=None, description="The board to add this image to, if any"),
+    session_id: Optional[str] = Query(default=None, description="The session ID associated with this upload, if any"),
+    crop_visible: Optional[bool] = Query(default=False, description="Whether to crop the image"),
 ) -> ImageDTO:
     """Uploads an image"""
     if not file.content_type.startswith("image"):
@@ -51,6 +52,9 @@ async def upload_image(
 
     try:
         pil_image = Image.open(io.BytesIO(contents))
+        if crop_visible:
+            bbox = pil_image.getbbox()
+            pil_image = pil_image.crop(bbox)
     except:
         # Error opening the image
         raise HTTPException(status_code=415, detail="Failed to read image")
@@ -61,6 +65,7 @@ async def upload_image(
             image_origin=ResourceOrigin.EXTERNAL,
             image_category=image_category,
             session_id=session_id,
+            board_id=board_id,
             is_intermediate=is_intermediate,
         )
 
@@ -85,6 +90,18 @@ async def delete_image(
         pass
 
 
+@images_router.post("/clear-intermediates", operation_id="clear_intermediates")
+async def clear_intermediates() -> int:
+    """Clears all intermediates"""
+
+    try:
+        count_deleted = ApiDependencies.invoker.services.images.delete_intermediates()
+        return count_deleted
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="Failed to clear intermediates")
+        pass
+
+
 @images_router.patch(
     "/{image_name}",
     operation_id="update_image",
@@ -92,9 +109,7 @@ async def delete_image(
 )
 async def update_image(
     image_name: str = Path(description="The name of the image to update"),
-    image_changes: ImageRecordChanges = Body(
-        description="The changes to apply to the image"
-    ),
+    image_changes: ImageRecordChanges = Body(description="The changes to apply to the image"),
 ) -> ImageDTO:
     """Updates an image"""
 
@@ -119,6 +134,7 @@ async def get_image_dto(
     except Exception as e:
         raise HTTPException(status_code=404)
 
+
 @images_router.get(
     "/{image_name}/metadata",
     operation_id="get_image_metadata",
@@ -188,15 +204,11 @@ async def get_image_thumbnail(
     """Gets a thumbnail image file"""
 
     try:
-        path = ApiDependencies.invoker.services.images.get_path(
-            image_name, thumbnail=True
-        )
+        path = ApiDependencies.invoker.services.images.get_path(image_name, thumbnail=True)
         if not ApiDependencies.invoker.services.images.validate_path(path):
             raise HTTPException(status_code=404)
 
-        response = FileResponse(
-            path, media_type="image/webp", content_disposition_type="inline"
-        )
+        response = FileResponse(path, media_type="image/webp", content_disposition_type="inline")
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
         return response
     except Exception as e:
@@ -215,9 +227,7 @@ async def get_image_urls(
 
     try:
         image_url = ApiDependencies.invoker.services.images.get_url(image_name)
-        thumbnail_url = ApiDependencies.invoker.services.images.get_url(
-            image_name, thumbnail=True
-        )
+        thumbnail_url = ApiDependencies.invoker.services.images.get_url(image_name, thumbnail=True)
         return ImageUrlsDTO(
             image_name=image_name,
             image_url=image_url,
@@ -233,17 +243,12 @@ async def get_image_urls(
     response_model=OffsetPaginatedResults[ImageDTO],
 )
 async def list_image_dtos(
-    image_origin: Optional[ResourceOrigin] = Query(
-        default=None, description="The origin of images to list"
-    ),
-    categories: Optional[list[ImageCategory]] = Query(
-        default=None, description="The categories of image to include"
-    ),
-    is_intermediate: Optional[bool] = Query(
-        default=None, description="Whether to list intermediate images"
-    ),
+    image_origin: Optional[ResourceOrigin] = Query(default=None, description="The origin of images to list."),
+    categories: Optional[list[ImageCategory]] = Query(default=None, description="The categories of image to include."),
+    is_intermediate: Optional[bool] = Query(default=None, description="Whether to list intermediate images."),
     board_id: Optional[str] = Query(
-        default=None, description="The board id to filter by"
+        default=None,
+        description="The board id to filter by. Use 'none' to find images without a board.",
     ),
     offset: int = Query(default=0, description="The page offset"),
     limit: int = Query(default=10, description="The number of images per page"),

invokeai/app/api/routers/models.py

@@ -28,49 +28,52 @@ ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
 
+
 class ModelsList(BaseModel):
     models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
 
+
 @models_router.get(
     "/",
     operation_id="list_models",
-    responses={200: {"model": ModelsList }},
+    responses={200: {"model": ModelsList}},
 )
 async def list_models(
     base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
     model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
 ) -> ModelsList:
     """Gets a list of models"""
-    if base_models and len(base_models)>0:
+    if base_models and len(base_models) > 0:
         models_raw = list()
         for base_model in base_models:
             models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
     else:
         models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
-    models = parse_obj_as(ModelsList, { "models": models_raw })
+    models = parse_obj_as(ModelsList, {"models": models_raw})
     return models
 
+
 @models_router.patch(
     "/{base_model}/{model_type}/{model_name}",
     operation_id="update_model",
-    responses={200: {"description" : "The model was updated successfully"},
-               400: {"description" : "Bad request"},
-               404: {"description" : "The model could not be found"},
-               409: {"description" : "There is already a model corresponding to the new name"},
-               },
-    status_code = 200,
-    response_model = UpdateModelResponse,
+    responses={
+        200: {"description": "The model was updated successfully"},
+        400: {"description": "Bad request"},
+        404: {"description": "The model could not be found"},
+        409: {"description": "There is already a model corresponding to the new name"},
+    },
+    status_code=200,
+    response_model=UpdateModelResponse,
 )
 async def update_model(
-        base_model: BaseModelType = Path(description="Base model"),
-        model_type: ModelType = Path(description="The type of model"),
-        model_name: str = Path(description="model name"),
-        info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
+    base_model: BaseModelType = Path(description="Base model"),
+    model_type: ModelType = Path(description="The type of model"),
+    model_name: str = Path(description="model name"),
+    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
 ) -> UpdateModelResponse:
-    """ Update model contents with a new config. If the model name or base fields are changed, then the model is renamed. """
+    """Update model contents with a new config. If the model name or base fields are changed, then the model is renamed."""
     logger = ApiDependencies.invoker.services.logger
 
-    
     try:
         previous_info = ApiDependencies.invoker.services.model_manager.list_model(
             model_name=model_name,
@@ -81,13 +84,13 @@ async def update_model(
         # rename operation requested
         if info.model_name != model_name or info.base_model != base_model:
             ApiDependencies.invoker.services.model_manager.rename_model(
-                base_model = base_model,
-                model_type = model_type,
-                model_name = model_name,
-                new_name = info.model_name,
-                new_base = info.base_model,
+                base_model=base_model,
+                model_type=model_type,
+                model_name=model_name,
+                new_name=info.model_name,
+                new_base=info.base_model,
             )
-            logger.info(f'Successfully renamed {base_model}/{model_name}=>{info.base_model}/{info.model_name}')
+            logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
             # update information to support an update of attributes
             model_name = info.model_name
             base_model = info.base_model
@@ -96,16 +99,15 @@ async def update_model(
                 base_model=base_model,
                 model_type=model_type,
             )
-            if new_info.get('path') != previous_info.get('path'):  # model manager moved model path during rename - don't overwrite it
-                info.path = new_info.get('path')
-            
+            if new_info.get("path") != previous_info.get(
+                "path"
+            ):  # model manager moved model path during rename - don't overwrite it
+                info.path = new_info.get("path")
+
         ApiDependencies.invoker.services.model_manager.update_model(
-            model_name=model_name,
-            base_model=base_model,
-            model_type=model_type,
-            model_attributes=info.dict()
+            model_name=model_name, base_model=base_model, model_type=model_type, model_attributes=info.dict()
         )
-            
+
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
             model_name=model_name,
             base_model=base_model,
@@ -123,49 +125,48 @@ async def update_model(
 
     return model_response
 
+
 @models_router.post(
     "/import",
     operation_id="import_model",
-    responses= {
-        201: {"description" : "The model imported successfully"},
-        404: {"description" : "The model could not be found"},
-        415: {"description" : "Unrecognized file/folder format"},
-        424: {"description" : "The model appeared to import successfully, but could not be found in the model manager"},
-        409: {"description" : "There is already a model corresponding to this path or repo_id"},
+    responses={
+        201: {"description": "The model imported successfully"},
+        404: {"description": "The model could not be found"},
+        415: {"description": "Unrecognized file/folder format"},
+        424: {"description": "The model appeared to import successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
     },
     status_code=201,
-    response_model=ImportModelResponse
+    response_model=ImportModelResponse,
 )
 async def import_model(
-        location: str = Body(description="A model path, repo_id or URL to import"),
-        prediction_type: Optional[Literal['v_prediction','epsilon','sample']] = \
-                Body(description='Prediction type for SDv2 checkpoint files', default="v_prediction"),
+    location: str = Body(description="A model path, repo_id or URL to import"),
+    prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
+        description="Prediction type for SDv2 checkpoint files", default="v_prediction"
+    ),
 ) -> ImportModelResponse:
-    """ Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically """
-    
+    """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
+
     items_to_import = {location}
-    prediction_types = { x.value: x for x in SchedulerPredictionType }
+    prediction_types = {x.value: x for x in SchedulerPredictionType}
     logger = ApiDependencies.invoker.services.logger
 
     try:
         installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
-            items_to_import = items_to_import,
-            prediction_type_helper = lambda x: prediction_types.get(prediction_type)
+            items_to_import=items_to_import, prediction_type_helper=lambda x: prediction_types.get(prediction_type)
         )
         info = installed_models.get(location)
 
         if not info:
             logger.error("Import failed")
             raise HTTPException(status_code=415)
-        
-        logger.info(f'Successfully imported {location}, got {info}')
+
+        logger.info(f"Successfully imported {location}, got {info}")
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.name,
-            base_model=info.base_model,
-            model_type=info.model_type
+            model_name=info.name, base_model=info.base_model, model_type=info.model_type
         )
         return parse_obj_as(ImportModelResponse, model_raw)
-    
+
     except ModelNotFoundException as e:
         logger.error(str(e))
         raise HTTPException(status_code=404, detail=str(e))
@@ -175,38 +176,34 @@ async def import_model(
     except ValueError as e:
         logger.error(str(e))
         raise HTTPException(status_code=409, detail=str(e))
-        
+
+
 @models_router.post(
     "/add",
     operation_id="add_model",
-    responses= {
-        201: {"description" : "The model added successfully"},
-        404: {"description" : "The model could not be found"},
-        424: {"description" : "The model appeared to add successfully, but could not be found in the model manager"},
-        409: {"description" : "There is already a model corresponding to this path or repo_id"},
+    responses={
+        201: {"description": "The model added successfully"},
+        404: {"description": "The model could not be found"},
+        424: {"description": "The model appeared to add successfully, but could not be found in the model manager"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
     },
     status_code=201,
-    response_model=ImportModelResponse
+    response_model=ImportModelResponse,
 )
 async def add_model(
-        info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
+    info: Union[tuple(OPENAPI_MODEL_CONFIGS)] = Body(description="Model configuration"),
 ) -> ImportModelResponse:
-    """ Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
-    
+    """Add a model using the configuration information appropriate for its type. Only local models can be added by path"""
+
     logger = ApiDependencies.invoker.services.logger
 
     try:
         ApiDependencies.invoker.services.model_manager.add_model(
-            info.model_name,
-            info.base_model,
-            info.model_type,
-            model_attributes = info.dict()
+            info.model_name, info.base_model, info.model_type, model_attributes=info.dict()
         )
-        logger.info(f'Successfully added {info.model_name}')
+        logger.info(f"Successfully added {info.model_name}")
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-            model_name=info.model_name,
-            base_model=info.base_model,
-            model_type=info.model_type
+            model_name=info.model_name, base_model=info.base_model, model_type=info.model_type
         )
         return parse_obj_as(ImportModelResponse, model_raw)
     except ModelNotFoundException as e:
@@ -216,66 +213,66 @@ async def add_model(
         logger.error(str(e))
         raise HTTPException(status_code=409, detail=str(e))
 
-    
+
 @models_router.delete(
     "/{base_model}/{model_type}/{model_name}",
     operation_id="del_model",
-    responses={
-        204: { "description": "Model deleted successfully" }, 
-        404: { "description": "Model not found" }
-    },
-    status_code = 204,
-    response_model = None,
+    responses={204: {"description": "Model deleted successfully"}, 404: {"description": "Model not found"}},
+    status_code=204,
+    response_model=None,
 )
 async def delete_model(
-        base_model: BaseModelType = Path(description="Base model"),
-        model_type: ModelType = Path(description="The type of model"),
-        model_name: str = Path(description="model name"),
+    base_model: BaseModelType = Path(description="Base model"),
+    model_type: ModelType = Path(description="The type of model"),
+    model_name: str = Path(description="model name"),
 ) -> Response:
     """Delete Model"""
     logger = ApiDependencies.invoker.services.logger
-    
+
     try:
-        ApiDependencies.invoker.services.model_manager.del_model(model_name,
-                                                                 base_model = base_model,
-                                                                 model_type = model_type
-                                                                 )
+        ApiDependencies.invoker.services.model_manager.del_model(
+            model_name, base_model=base_model, model_type=model_type
+        )
         logger.info(f"Deleted model: {model_name}")
         return Response(status_code=204)
     except ModelNotFoundException as e:
         logger.error(str(e))
         raise HTTPException(status_code=404, detail=str(e))
 
+
 @models_router.put(
     "/convert/{base_model}/{model_type}/{model_name}",
     operation_id="convert_model",
     responses={
-        200: { "description": "Model converted successfully" },
-        400: {"description" : "Bad request"  },
-        404: { "description": "Model not found"  },
+        200: {"description": "Model converted successfully"},
+        400: {"description": "Bad request"},
+        404: {"description": "Model not found"},
     },
-    status_code = 200,
-    response_model = ConvertModelResponse,
+    status_code=200,
+    response_model=ConvertModelResponse,
 )
 async def convert_model(
-        base_model: BaseModelType = Path(description="Base model"),
-        model_type: ModelType = Path(description="The type of model"),
-        model_name: str = Path(description="model name"),
-        convert_dest_directory: Optional[str] = Query(default=None, description="Save the converted model to the designated directory"),
+    base_model: BaseModelType = Path(description="Base model"),
+    model_type: ModelType = Path(description="The type of model"),
+    model_name: str = Path(description="model name"),
+    convert_dest_directory: Optional[str] = Query(
+        default=None, description="Save the converted model to the designated directory"
+    ),
 ) -> ConvertModelResponse:
     """Convert a checkpoint model into a diffusers model, optionally saving to the indicated destination directory, or `models` if none."""
     logger = ApiDependencies.invoker.services.logger
     try:
         logger.info(f"Converting model: {model_name}")
         dest = pathlib.Path(convert_dest_directory) if convert_dest_directory else None
-        ApiDependencies.invoker.services.model_manager.convert_model(model_name,
-                                                                     base_model = base_model,
-                                                                     model_type = model_type,
-                                                                     convert_dest_directory = dest,
-                                                                     )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(model_name,
-                                                                              base_model = base_model,
-                                                                              model_type = model_type)
+        ApiDependencies.invoker.services.model_manager.convert_model(
+            model_name,
+            base_model=base_model,
+            model_type=model_type,
+            convert_dest_directory=dest,
+        )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            model_name, base_model=base_model, model_type=model_type
+        )
         response = parse_obj_as(ConvertModelResponse, model_raw)
     except ModelNotFoundException as e:
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
@@ -283,140 +280,104 @@ async def convert_model(
         raise HTTPException(status_code=400, detail=str(e))
     return response
 
+
 @models_router.get(
     "/search",
     operation_id="search_for_models",
     responses={
-        200: { "description": "Directory searched successfully" },
-        404: { "description": "Invalid directory path"  },
+        200: {"description": "Directory searched successfully"},
+        404: {"description": "Invalid directory path"},
     },
-    status_code = 200,
-    response_model = List[pathlib.Path]
+    status_code=200,
+    response_model=List[pathlib.Path],
 )
 async def search_for_models(
-        search_path: pathlib.Path = Query(description="Directory path to search for models")
-)->List[pathlib.Path]:
+    search_path: pathlib.Path = Query(description="Directory path to search for models"),
+) -> List[pathlib.Path]:
     if not search_path.is_dir():
-        raise HTTPException(status_code=404, detail=f"The search path '{search_path}' does not exist or is not directory")
-    return ApiDependencies.invoker.services.model_manager.search_for_models([search_path])
+        raise HTTPException(
+            status_code=404, detail=f"The search path '{search_path}' does not exist or is not directory"
+        )
+    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
+
 
 @models_router.get(
     "/ckpt_confs",
     operation_id="list_ckpt_configs",
     responses={
-        200: { "description" : "paths retrieved successfully" },
+        200: {"description": "paths retrieved successfully"},
     },
-    status_code = 200,
-    response_model = List[pathlib.Path]
+    status_code=200,
+    response_model=List[pathlib.Path],
 )
-async def list_ckpt_configs(
-)->List[pathlib.Path]:
+async def list_ckpt_configs() -> List[pathlib.Path]:
     """Return a list of the legacy checkpoint configuration files stored in `ROOT/configs/stable-diffusion`, relative to ROOT."""
     return ApiDependencies.invoker.services.model_manager.list_checkpoint_configs()
-    
-        
-@models_router.get(
+
+
+@models_router.post(
     "/sync",
     operation_id="sync_to_config",
     responses={
-        201: { "description": "synchronization successful" },
+        201: {"description": "synchronization successful"},
     },
-    status_code = 201,
-    response_model = None
+    status_code=201,
+    response_model=bool,
 )
-async def sync_to_config(
-)->None:
+async def sync_to_config() -> bool:
     """Call after making changes to models.yaml, autoimport directories or models directory to synchronize
     in-memory data structures with disk data structures."""
-    return ApiDependencies.invoker.services.model_manager.sync_to_config()
-        
+    ApiDependencies.invoker.services.model_manager.sync_to_config()
+    return True
+
+
 @models_router.put(
     "/merge/{base_model}",
     operation_id="merge_models",
     responses={
-        200: { "description": "Model converted successfully" },
-        400: { "description": "Incompatible models"  },
-        404: { "description": "One or more models not found"  },
+        200: {"description": "Model converted successfully"},
+        400: {"description": "Incompatible models"},
+        404: {"description": "One or more models not found"},
     },
-    status_code = 200,
-    response_model = MergeModelResponse,
+    status_code=200,
+    response_model=MergeModelResponse,
 )
 async def merge_models(
-        base_model: BaseModelType                  = Path(description="Base model"),
-        model_names: List[str]                     = Body(description="model name", min_items=2, max_items=3),
-        merged_model_name: Optional[str]           = Body(description="Name of destination model"),
-        alpha: Optional[float]                     = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
-        interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
-        force: Optional[bool]                      = Body(description="Force merging of models created with different versions of diffusers", default=False),
-        merge_dest_directory: Optional[str]       = Body(description="Save the merged model to the designated directory (with 'merged_model_name' appended)", default=None)
+    base_model: BaseModelType = Path(description="Base model"),
+    model_names: List[str] = Body(description="model name", min_items=2, max_items=3),
+    merged_model_name: Optional[str] = Body(description="Name of destination model"),
+    alpha: Optional[float] = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
+    interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
+    force: Optional[bool] = Body(
+        description="Force merging of models created with different versions of diffusers", default=False
+    ),
+    merge_dest_directory: Optional[str] = Body(
+        description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
+        default=None,
+    ),
 ) -> MergeModelResponse:
     """Convert a checkpoint model into a diffusers model"""
     logger = ApiDependencies.invoker.services.logger
     try:
         logger.info(f"Merging models: {model_names} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
         dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
-        result = ApiDependencies.invoker.services.model_manager.merge_models(model_names,
-                                                                             base_model,
-                                                                             merged_model_name=merged_model_name or "+".join(model_names),
-                                                                             alpha=alpha,
-                                                                             interp=interp,
-                                                                             force=force,
-                                                                             merge_dest_directory = dest
-                                                                             )
-        model_raw = ApiDependencies.invoker.services.model_manager.list_model(result.name,
-                                                                              base_model = base_model,
-                                                                              model_type = ModelType.Main,
-                                                                              )
+        result = ApiDependencies.invoker.services.model_manager.merge_models(
+            model_names,
+            base_model,
+            merged_model_name=merged_model_name or "+".join(model_names),
+            alpha=alpha,
+            interp=interp,
+            force=force,
+            merge_dest_directory=dest,
+        )
+        model_raw = ApiDependencies.invoker.services.model_manager.list_model(
+            result.name,
+            base_model=base_model,
+            model_type=ModelType.Main,
+        )
         response = parse_obj_as(ConvertModelResponse, model_raw)
     except ModelNotFoundException:
         raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
     return response
-
-# The rename operation is now supported by update_model and no longer needs to be
-# a standalone route.
-# @models_router.post(
-#     "/rename/{base_model}/{model_type}/{model_name}",
-#     operation_id="rename_model",
-#     responses= {
-#         201: {"description" : "The model was renamed successfully"},
-#         404: {"description" : "The model could not be found"},
-#         409: {"description" : "There is already a model corresponding to the new name"},
-#     },
-#     status_code=201,
-#     response_model=ImportModelResponse
-# )
-# async def rename_model(
-#         base_model: BaseModelType = Path(description="Base model"),
-#         model_type: ModelType = Path(description="The type of model"),
-#         model_name: str = Path(description="current model name"),
-#         new_name: Optional[str] = Query(description="new model name", default=None),
-#         new_base: Optional[BaseModelType] = Query(description="new model base", default=None),
-# ) -> ImportModelResponse:
-#     """ Rename a model"""
-    
-#     logger = ApiDependencies.invoker.services.logger
-
-#     try:
-#         result = ApiDependencies.invoker.services.model_manager.rename_model(
-#             base_model = base_model,
-#             model_type = model_type,
-#             model_name = model_name,
-#             new_name = new_name,
-#             new_base = new_base,
-#         )
-#         logger.debug(result)
-#         logger.info(f'Successfully renamed {model_name}=>{new_name}')
-#         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
-#             model_name=new_name or model_name,
-#             base_model=new_base or base_model,
-#             model_type=model_type
-#         )
-#         return parse_obj_as(ImportModelResponse, model_raw)
-#     except ModelNotFoundException as e:
-#         logger.error(str(e))
-#         raise HTTPException(status_code=404, detail=str(e))
-#     except ValueError as e:
-#         logger.error(str(e))
-#         raise HTTPException(status_code=409, detail=str(e))

invokeai/app/api/routers/sessions.py

@@ -15,6 +15,7 @@ from ...services.graph import (
     GraphExecutionState,
     NodeAlreadyExecutedError,
 )
+from ...services.batch_manager import Batch, BatchProcess
 from ...services.item_storage import PaginatedResults
 from ..dependencies import ApiDependencies
 
@@ -30,15 +31,44 @@ session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
     },
 )
 async def create_session(
-    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(graph)
     return session
 
 
+@session_router.post(
+    "/batch",
+    operation_id="create_batch",
+    responses={
+        200: {"model": BatchProcess},
+        400: {"description": "Invalid json"},
+    },
+)
+async def create_batch(
+    graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
+    batches: list[Batch] = Body(description="Batch config to apply to the given graph"),
+) -> BatchProcess:
+    """Creates and starts a new new batch process"""
+    batch_id = ApiDependencies.invoker.services.batch_manager.create_batch_process(batches, graph)
+    ApiDependencies.invoker.services.batch_manager.run_batch_process(batch_id)
+    return {"batch_id":batch_id}
+
+
+@session_router.delete(
+    "{batch_process_id}/batch",
+    operation_id="cancel_batch",
+    responses={202: {"description": "The batch is canceled"}},
+)
+async def cancel_batch(
+    batch_process_id: str = Path(description="The id of the batch process to cancel"),
+) -> Response:
+    """Creates and starts a new new batch process"""
+    ApiDependencies.invoker.services.batch_manager.cancel_batch_process(batch_process_id)
+    return Response(status_code=202)
+
+
 @session_router.get(
     "/",
     operation_id="list_sessions",
@@ -51,13 +81,9 @@ async def list_sessions(
 ) -> PaginatedResults[GraphExecutionState]:
     """Gets a list of sessions, optionally searching"""
     if query == "":
-        result = ApiDependencies.invoker.services.graph_execution_manager.list(
-            page, per_page
-        )
+        result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
     else:
-        result = ApiDependencies.invoker.services.graph_execution_manager.search(
-            query, page, per_page
-        )
+        result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
     return result
 
 
@@ -91,9 +117,9 @@ async def get_session(
 )
 async def add_node(
     session_id: str = Path(description="The id of the session"),
-    node: Annotated[
-        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
-    ] = Body(description="The node to add"),
+    node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
+        description="The node to add"
+    ),
 ) -> str:
     """Adds a node to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
@@ -124,9 +150,9 @@ async def add_node(
 async def update_node(
     session_id: str = Path(description="The id of the session"),
     node_path: str = Path(description="The path to the node in the graph"),
-    node: Annotated[
-        Union[BaseInvocation.get_invocations()], Field(discriminator="type") # type: ignore
-    ] = Body(description="The new node"),
+    node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body(  # type: ignore
+        description="The new node"
+    ),
 ) -> GraphExecutionState:
     """Updates a node in the graph and removes all linked edges"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
@@ -230,7 +256,7 @@ async def delete_edge(
     try:
         edge = Edge(
             source=EdgeConnection(node_id=from_node_id, field=from_field),
-            destination=EdgeConnection(node_id=to_node_id, field=to_field)
+            destination=EdgeConnection(node_id=to_node_id, field=to_field),
         )
         session.delete_edge(edge)
         ApiDependencies.invoker.services.graph_execution_manager.set(
@@ -255,9 +281,7 @@ async def delete_edge(
 )
 async def invoke_session(
     session_id: str = Path(description="The id of the session to invoke"),
-    all: bool = Query(
-        default=False, description="Whether or not to invoke all remaining invocations"
-    ),
+    all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
 ) -> Response:
     """Invokes a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
@@ -274,9 +298,7 @@ async def invoke_session(
 @session_router.delete(
     "/{session_id}/invoke",
     operation_id="cancel_session_invoke",
-    responses={
-        202: {"description": "The invocation is canceled"}
-    },
+    responses={202: {"description": "The invocation is canceled"}},
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),

invokeai/app/api/sockets.py

@@ -16,9 +16,7 @@ class SocketIO:
         self.__sio.on("subscribe", handler=self._handle_sub)
         self.__sio.on("unsubscribe", handler=self._handle_unsub)
 
-        local_handler.register(
-            event_name=EventServiceBase.session_event, _func=self._handle_session_event
-        )
+        local_handler.register(event_name=EventServiceBase.session_event, _func=self._handle_session_event)
 
     async def _handle_session_event(self, event: Event):
         await self.__sio.emit(

invokeai/app/api_app.py

@@ -3,7 +3,9 @@ import asyncio
 import sys
 from inspect import signature
 
+import logging
 import uvicorn
+import socket
 
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
@@ -15,9 +17,10 @@ from fastapi_events.middleware import EventHandlerASGIMiddleware
 from pathlib import Path
 from pydantic.schema import schema
 
-#This should come early so that modules can log their initialization properly
+# This should come early so that modules can log their initialization properly
 from .services.config import InvokeAIAppConfig
 from ..backend.util.logging import InvokeAILogger
+
 app_config = InvokeAIAppConfig.get_config()
 app_config.parse_args()
 logger = InvokeAILogger.getLogger(config=app_config)
@@ -26,7 +29,7 @@ from invokeai.version.invokeai_version import __version__
 # we call this early so that the message appears before
 # other invokeai initialization messages
 if app_config.version:
-    print(f'InvokeAI version {__version__}')
+    print(f"InvokeAI version {__version__}")
     sys.exit(0)
 
 import invokeai.frontend.web as web_dir
@@ -36,17 +39,18 @@ from .api.dependencies import ApiDependencies
 from .api.routers import sessions, models, images, boards, board_images, app_info
 from .api.sockets import SocketIO
 from .invocations.baseinvocation import BaseInvocation
-    
+
 
 import torch
 import invokeai.backend.util.hotfixes
+
 if torch.backends.mps.is_available():
     import invokeai.backend.util.mps_fixes
 
 # fix for windows mimetypes registry entries being borked
 # see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
-mimetypes.add_type('application/javascript', '.js')
-mimetypes.add_type('text/css', '.css')
+mimetypes.add_type("application/javascript", ".js")
+mimetypes.add_type("text/css", ".css")
 
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
@@ -56,14 +60,13 @@ app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)
 event_handler_id: int = id(app)
 app.add_middleware(
     EventHandlerASGIMiddleware,
-    handlers=[
-        local_handler
-    ],  # TODO: consider doing this in services to support different configurations
+    handlers=[local_handler],  # TODO: consider doing this in services to support different configurations
     middleware_id=event_handler_id,
 )
 
 socket_io = SocketIO(app)
 
+
 # Add startup event to load dependencies
 @app.on_event("startup")
 async def startup_event():
@@ -75,9 +78,7 @@ async def startup_event():
         allow_headers=app_config.allow_headers,
     )
 
-    ApiDependencies.initialize(
-        config=app_config, event_handler_id=event_handler_id, logger=logger
-    )
+    ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
 
 
 # Shut down threads
@@ -102,7 +103,8 @@ app.include_router(boards.boards_router, prefix="/api")
 
 app.include_router(board_images.board_images_router, prefix="/api")
 
-app.include_router(app_info.app_router, prefix='/api')
+app.include_router(app_info.app_router, prefix="/api")
+
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -143,6 +145,7 @@ def custom_openapi():
         invoker_schema["output"] = outputs_ref
 
     from invokeai.backend.model_management.models import get_model_config_enums
+
     for model_config_format_enum in set(get_model_config_enums()):
         name = model_config_format_enum.__qualname__
 
@@ -165,7 +168,8 @@ def custom_openapi():
 app.openapi = custom_openapi
 
 # Override API doc favicons
-app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], 'static/dream_web')), name="static")
+app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], "static/dream_web")), name="static")
+
 
 @app.get("/docs", include_in_schema=False)
 def overridden_swagger():
@@ -186,19 +190,48 @@ def overridden_redoc():
 
 
 # Must mount *after* the other routes else it borks em
-app.mount("/", 
-          StaticFiles(directory=Path(web_dir.__path__[0],"dist"), 
-                      html=True
-                     ), name="ui"
-         )
+app.mount("/", StaticFiles(directory=Path(web_dir.__path__[0], "dist"), html=True), name="ui")
+
 
 def invoke_api():
+    def find_port(port: int):
+        """Find a port not in use starting at given port"""
+        # Taken from https://waylonwalker.com/python-find-available-port/, thanks Waylon!
+        # https://github.com/WaylonWalker
+        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+            if s.connect_ex(("localhost", port)) == 0:
+                return find_port(port=port + 1)
+            else:
+                return port
+
+    from invokeai.backend.install.check_root import check_invokeai_root
+
+    check_invokeai_root(app_config)  # note, may exit with an exception if root not set up
+
+    port = find_port(app_config.port)
+    if port != app_config.port:
+        logger.warn(f"Port {app_config.port} in use, using port {port}")
+
     # Start our own event loop for eventing usage
     loop = asyncio.new_event_loop()
-    config = uvicorn.Config(app=app, host=app_config.host, port=app_config.port, loop=loop)
-    # Use access_log to turn off logging
+    config = uvicorn.Config(
+        app=app,
+        host=app_config.host,
+        port=port,
+        loop=loop,
+        log_level=app_config.log_level,
+    )
     server = uvicorn.Server(config)
+
+    # replace uvicorn's loggers with InvokeAI's for consistent appearance
+    for logname in ["uvicorn.access", "uvicorn"]:
+        l = logging.getLogger(logname)
+        l.handlers.clear()
+        for ch in logger.handlers:
+            l.addHandler(ch)
+
     loop.run_until_complete(server.serve())
 
+
 if __name__ == "__main__":
     invoke_api()

invokeai/app/cli/commands.py

@@ -14,8 +14,14 @@ from ..services.graph import GraphExecutionState, LibraryGraph, Edge
 from ..services.invoker import Invoker
 
 
-def add_field_argument(command_parser, name: str, field, default_override = None):
-    default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+def add_field_argument(command_parser, name: str, field, default_override=None):
+    default = (
+        default_override
+        if default_override is not None
+        else field.default
+        if field.default_factory is None
+        else field.default_factory()
+    )
     if get_origin(field.type_) == Literal:
         allowed_values = get_args(field.type_)
         allowed_types = set()
@@ -47,8 +53,8 @@ def add_parsers(
     commands: list[type],
     command_field: str = "type",
     exclude_fields: list[str] = ["id", "type"],
-    add_arguments: Union[Callable[[argparse.ArgumentParser], None],None] = None
-    ):
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None,
+):
     """Adds parsers for each command to the subparsers"""
 
     # Create subparsers for each command
@@ -61,7 +67,7 @@ def add_parsers(
             add_arguments(command_parser)
 
         # Convert all fields to arguments
-        fields = command.__fields__ # type: ignore
+        fields = command.__fields__  # type: ignore
         for name, field in fields.items():
             if name in exclude_fields:
                 continue
@@ -70,13 +76,11 @@ def add_parsers(
 
 
 def add_graph_parsers(
-    subparsers,
-    graphs: list[LibraryGraph],
-    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
+    subparsers, graphs: list[LibraryGraph], add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
 ):
     for graph in graphs:
         command_parser = subparsers.add_parser(graph.name, help=graph.description)
-        
+
         if add_arguments is not None:
             add_arguments(command_parser)
 
@@ -128,6 +132,7 @@ class CliContext:
 
 class ExitCli(Exception):
     """Exception to exit the CLI"""
+
     pass
 
 
@@ -155,7 +160,7 @@ class BaseCommand(ABC, BaseModel):
     @classmethod
     def get_commands_map(cls):
         # Get the type strings out of the literals and into a dictionary
-        return dict(map(lambda t: (get_args(get_type_hints(t)['type'])[0], t),BaseCommand.get_all_subclasses()))
+        return dict(map(lambda t: (get_args(get_type_hints(t)["type"])[0], t), BaseCommand.get_all_subclasses()))
 
     @abstractmethod
     def run(self, context: CliContext) -> None:
@@ -165,7 +170,8 @@ class BaseCommand(ABC, BaseModel):
 
 class ExitCommand(BaseCommand):
     """Exits the CLI"""
-    type: Literal['exit'] = 'exit'
+
+    type: Literal["exit"] = "exit"
 
     def run(self, context: CliContext) -> None:
         raise ExitCli()
@@ -173,7 +179,8 @@ class ExitCommand(BaseCommand):
 
 class HelpCommand(BaseCommand):
     """Shows help"""
-    type: Literal['help'] = 'help'
+
+    type: Literal["help"] = "help"
 
     def run(self, context: CliContext) -> None:
         context.parser.print_help()
@@ -183,11 +190,7 @@ def get_graph_execution_history(
     graph_execution_state: GraphExecutionState,
 ) -> Iterable[str]:
     """Gets the history of fully-executed invocations for a graph execution"""
-    return (
-        n
-        for n in reversed(graph_execution_state.executed_history)
-        if n in graph_execution_state.graph.nodes
-    )
+    return (n for n in reversed(graph_execution_state.executed_history) if n in graph_execution_state.graph.nodes)
 
 
 def get_invocation_command(invocation) -> str:
@@ -218,7 +221,8 @@ def get_invocation_command(invocation) -> str:
 
 class HistoryCommand(BaseCommand):
     """Shows the invocation history"""
-    type: Literal['history'] = 'history'
+
+    type: Literal["history"] = "history"
 
     # Inputs
     # fmt: off
@@ -235,7 +239,8 @@ class HistoryCommand(BaseCommand):
 
 class SetDefaultCommand(BaseCommand):
     """Sets a default value for a field"""
-    type: Literal['default'] = 'default'
+
+    type: Literal["default"] = "default"
 
     # Inputs
     # fmt: off
@@ -253,7 +258,8 @@ class SetDefaultCommand(BaseCommand):
 
 class DrawGraphCommand(BaseCommand):
     """Debugs a graph"""
-    type: Literal['draw_graph'] = 'draw_graph'
+
+    type: Literal["draw_graph"] = "draw_graph"
 
     def run(self, context: CliContext) -> None:
         session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
@@ -271,7 +277,8 @@ class DrawGraphCommand(BaseCommand):
 
 class DrawExecutionGraphCommand(BaseCommand):
     """Debugs an execution graph"""
-    type: Literal['draw_xgraph'] = 'draw_xgraph'
+
+    type: Literal["draw_xgraph"] = "draw_xgraph"
 
     def run(self, context: CliContext) -> None:
         session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
@@ -286,6 +293,7 @@ class DrawExecutionGraphCommand(BaseCommand):
         plt.axis("off")
         plt.show()
 
+
 class SortedHelpFormatter(argparse.HelpFormatter):
     def _iter_indented_subactions(self, action):
         try:

invokeai/app/cli/completer.py

@@ -19,8 +19,8 @@ from ..services.invocation_services import InvocationServices
 # singleton object, class variable
 completer = None
 
+
 class Completer(object):
-    
     def __init__(self, model_manager: ModelManager):
         self.commands = self.get_commands()
         self.matches = None
@@ -43,7 +43,7 @@ class Completer(object):
             except IndexError:
                 pass
             options = options or list(self.parse_commands().keys())
-            
+
             if not text:  # first time
                 self.matches = options
             else:
@@ -56,17 +56,17 @@ class Completer(object):
         return match
 
     @classmethod
-    def get_commands(self)->List[object]:
+    def get_commands(self) -> List[object]:
         """
         Return a list of all the client commands and invocations.
         """
         return BaseCommand.get_commands() + BaseInvocation.get_invocations()
 
-    def get_current_command(self, buffer: str)->tuple[str, str]:
+    def get_current_command(self, buffer: str) -> tuple[str, str]:
         """
         Parse the readline buffer to find the most recent command and its switch.
         """
-        if len(buffer)==0:
+        if len(buffer) == 0:
             return None, None
         tokens = shlex.split(buffer)
         command = None
@@ -78,11 +78,11 @@ class Completer(object):
             else:
                 switch = t
         # don't try to autocomplete switches that are already complete
-        if switch and buffer.endswith(' '):
-            switch=None
-        return command or '', switch or ''
+        if switch and buffer.endswith(" "):
+            switch = None
+        return command or "", switch or ""
 
-    def parse_commands(self)->Dict[str, List[str]]:
+    def parse_commands(self) -> Dict[str, List[str]]:
         """
         Return a dict in which the keys are the command name
         and the values are the parameters the command takes.
@@ -90,11 +90,11 @@ class Completer(object):
         result = dict()
         for command in self.commands:
             hints = get_type_hints(command)
-            name = get_args(hints['type'])[0]
-            result.update({name:hints})
+            name = get_args(hints["type"])[0]
+            result.update({name: hints})
         return result
 
-    def get_command_options(self, command: str, switch: str)->List[str]:
+    def get_command_options(self, command: str, switch: str) -> List[str]:
         """
         Return all the parameters that can be passed to the command as
         command-line switches. Returns None if the command is unrecognized.
@@ -102,42 +102,46 @@ class Completer(object):
         parsed_commands = self.parse_commands()
         if command not in parsed_commands:
             return None
-        
+
         # handle switches in the format "-foo=bar"
         argument = None
-        if switch and '=' in switch:
-            switch, argument = switch.split('=')
-            
-        parameter = switch.strip('-')
+        if switch and "=" in switch:
+            switch, argument = switch.split("=")
+
+        parameter = switch.strip("-")
         if parameter in parsed_commands[command]:
             if argument is None:
                 return self.get_parameter_options(parameter, parsed_commands[command][parameter])
             else:
-                return [f"--{parameter}={x}" for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])]
+                return [
+                    f"--{parameter}={x}"
+                    for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])
+                ]
         else:
             return [f"--{x}" for x in parsed_commands[command].keys()]
 
-    def get_parameter_options(self, parameter: str, typehint)->List[str]:
+    def get_parameter_options(self, parameter: str, typehint) -> List[str]:
         """
         Given a parameter type (such as Literal), offers autocompletions.
         """
         if get_origin(typehint) == Literal:
             return get_args(typehint)
-        if parameter == 'model':
+        if parameter == "model":
             return self.manager.model_names()
-        
+
     def _pre_input_hook(self):
         if self.linebuffer:
             readline.insert_text(self.linebuffer)
             readline.redisplay()
             self.linebuffer = None
-    
+
+
 def set_autocompleter(services: InvocationServices) -> Completer:
     global completer
-    
+
     if completer:
         return completer
-    
+
     completer = Completer(services.model_manager)
 
     readline.set_completer(completer.complete)
@@ -162,8 +166,6 @@ def set_autocompleter(services: InvocationServices) -> Completer:
         pass
     except OSError:  # file likely corrupted
         newname = f"{histfile}.old"
-        logger.error(
-            f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
-        )
+        logger.error(f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}")
         histfile.replace(Path(newname))
     atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -13,6 +13,7 @@ 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
+
 config = InvokeAIAppConfig.get_config()
 config.parse_args()
 logger = InvokeAILogger().getLogger(config=config)
@@ -20,7 +21,7 @@ from invokeai.version.invokeai_version import __version__
 
 # we call this early so that the message appears before other invokeai initialization messages
 if config.version:
-    print(f'InvokeAI version {__version__}')
+    print(f"InvokeAI version {__version__}")
     sys.exit(0)
 
 from invokeai.app.services.board_image_record_storage import (
@@ -36,18 +37,23 @@ 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 .services.default_graphs import (default_text_to_image_graph_id,
-                                      create_system_graphs)
+from invokeai.app.services.batch_manager import BatchManager
+from invokeai.app.services.batch_manager_storage import SqliteBatchProcessStorage
+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.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.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
@@ -58,6 +64,7 @@ from .services.sqlite import SqliteItemStorage
 
 import torch
 import invokeai.backend.util.hotfixes
+
 if torch.backends.mps.is_available():
     import invokeai.backend.util.mps_fixes
 
@@ -69,6 +76,7 @@ class CliCommand(BaseModel):
 class InvalidArgs(Exception):
     pass
 
+
 def add_invocation_args(command_parser):
     # Add linking capability
     command_parser.add_argument(
@@ -113,7 +121,7 @@ def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
     return parser
 
 
-class NodeField():
+class NodeField:
     alias: str
     node_path: str
     field: str
@@ -126,15 +134,20 @@ class NodeField():
         self.field_type = field_type
 
 
-def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str,NodeField]:
-    return {k:NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
+def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str, NodeField]:
+    return {k: NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
 
 
 def get_node_input_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
     """Gets the node field for the specified field alias"""
     exposed_input = next(e for e in graph.exposed_inputs if e.alias == field_alias)
     node_type = type(graph.graph.get_node(exposed_input.node_path))
-    return NodeField(alias=exposed_input.alias, node_path=f'{node_id}.{exposed_input.node_path}', field=exposed_input.field, field_type=get_type_hints(node_type)[exposed_input.field])
+    return NodeField(
+        alias=exposed_input.alias,
+        node_path=f"{node_id}.{exposed_input.node_path}",
+        field=exposed_input.field,
+        field_type=get_type_hints(node_type)[exposed_input.field],
+    )
 
 
 def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
@@ -142,7 +155,12 @@ def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -
     exposed_output = next(e for e in graph.exposed_outputs if e.alias == field_alias)
     node_type = type(graph.graph.get_node(exposed_output.node_path))
     node_output_type = node_type.get_output_type()
-    return NodeField(alias=exposed_output.alias, node_path=f'{node_id}.{exposed_output.node_path}', field=exposed_output.field, field_type=get_type_hints(node_output_type)[exposed_output.field])
+    return NodeField(
+        alias=exposed_output.alias,
+        node_path=f"{node_id}.{exposed_output.node_path}",
+        field=exposed_output.field,
+        field_type=get_type_hints(node_output_type)[exposed_output.field],
+    )
 
 
 def get_node_inputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
@@ -165,9 +183,7 @@ def get_node_outputs(invocation: BaseInvocation, context: CliContext) -> dict[st
         return {e.alias: get_node_output_field(graph, e.alias, invocation.id) for e in graph.exposed_outputs}
 
 
-def generate_matching_edges(
-    a: BaseInvocation, b: BaseInvocation, context: CliContext
-) -> list[Edge]:
+def generate_matching_edges(a: BaseInvocation, b: BaseInvocation, context: CliContext) -> list[Edge]:
     """Generates all possible edges between two invocations"""
     afields = get_node_outputs(a, context)
     bfields = get_node_inputs(b, context)
@@ -179,12 +195,14 @@ def generate_matching_edges(
     matching_fields = matching_fields.difference(invalid_fields)
 
     # Validate types
-    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)]
+    matching_fields = [
+        f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)
+    ]
 
     edges = [
         Edge(
             source=EdgeConnection(node_id=afields[alias].node_path, field=afields[alias].field),
-            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field)
+            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field),
         )
         for alias in matching_fields
     ]
@@ -193,6 +211,7 @@ def generate_matching_edges(
 
 class SessionError(Exception):
     """Raised when a session error has occurred"""
+
     pass
 
 
@@ -209,22 +228,23 @@ def invoke_all(context: CliContext):
             context.invoker.services.logger.error(
                 f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
             )
-        
+
         raise SessionError()
 
+
 def invoke_cli():
-    logger.info(f'InvokeAI version {__version__}')
+    logger.info(f"InvokeAI version {__version__}")
     # get the optional list of invocations to execute on the command line
     parser = config.get_parser()
-    parser.add_argument('commands',nargs='*')
+    parser.add_argument("commands", nargs="*")
     invocation_commands = parser.parse_args().commands
 
     # get the optional file to read commands from.
     # Simplest is to use it for STDIN
     if infile := config.from_file:
-        sys.stdin = open(infile,"r")
-    
-    model_manager = ModelManagerService(config,logger)
+        sys.stdin = open(infile, "r")
+
+    model_manager = ModelManagerService(config, logger)
 
     events = EventServiceBase()
     output_folder = config.output_path
@@ -234,13 +254,13 @@ def invoke_cli():
         db_location = ":memory:"
     else:
         db_location = config.db_path
-        db_location.parent.mkdir(parents=True,exist_ok=True)
+        db_location.parent.mkdir(parents=True, exist_ok=True)
 
     logger.info(f'InvokeAI database location is "{db_location}"')
 
     graph_execution_manager = SqliteItemStorage[GraphExecutionState](
-            filename=db_location, table_name="graph_executions"
-        )
+        filename=db_location, table_name="graph_executions"
+    )
 
     urls = LocalUrlService()
     image_record_storage = SqliteImageRecordStorage(db_location)
@@ -281,24 +301,25 @@ def invoke_cli():
             graph_execution_manager=graph_execution_manager,
         )
     )
-        
+
+    batch_manager_storage = SqliteBatchProcessStorage(db_location)
+    batch_manager = BatchManager(batch_manager_storage)
+
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
+        latents=ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents")),
         images=images,
         boards=boards,
+        batch_manager=batch_manager,
         board_images=board_images,
         queue=MemoryInvocationQueue(),
-        graph_library=SqliteItemStorage[LibraryGraph](
-            filename=db_location, table_name="graphs"
-        ),
+        graph_library=SqliteItemStorage[LibraryGraph](filename=db_location, table_name="graphs"),
         graph_execution_manager=graph_execution_manager,
         processor=DefaultInvocationProcessor(),
         logger=logger,
         configuration=config,
     )
-    
 
     system_graphs = create_system_graphs(services.graph_library)
     system_graph_names = set([g.name for g in system_graphs])
@@ -308,7 +329,7 @@ def invoke_cli():
     session: GraphExecutionState = invoker.create_execution_state()
     parser = get_command_parser(services)
 
-    re_negid = re.compile('^-[0-9]+$')
+    re_negid = re.compile("^-[0-9]+$")
 
     # Uncomment to print out previous sessions at startup
     # print(services.session_manager.list())
@@ -318,7 +339,7 @@ def invoke_cli():
 
     command_line_args_exist = len(invocation_commands) > 0
     done = False
-    
+
     while not done:
         try:
             if command_line_args_exist:
@@ -332,7 +353,7 @@ def invoke_cli():
 
         try:
             # Refresh the state of the session
-            #history = list(get_graph_execution_history(context.session))
+            # history = list(get_graph_execution_history(context.session))
             history = list(reversed(context.nodes_added))
 
             # Split the command for piping
@@ -353,17 +374,17 @@ def invoke_cli():
                         args[field_name] = field_default
 
                 # Parse invocation
-                command: CliCommand = None # type:ignore
+                command: CliCommand = None  # type:ignore
                 system_graph: Optional[LibraryGraph] = None
-                if args['type'] in system_graph_names:
-                    system_graph = next(filter(lambda g: g.name == args['type'], system_graphs))
+                if args["type"] in system_graph_names:
+                    system_graph = next(filter(lambda g: g.name == args["type"], system_graphs))
                     invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))
                     for exposed_input in system_graph.exposed_inputs:
                         if exposed_input.alias in args:
                             node = invocation.graph.get_node(exposed_input.node_path)
                             field = exposed_input.field
                             setattr(node, field, args[exposed_input.alias])
-                    command = CliCommand(command = invocation)
+                    command = CliCommand(command=invocation)
                     context.graph_nodes[invocation.id] = system_graph.id
                 else:
                     args["id"] = current_id
@@ -385,17 +406,13 @@ def invoke_cli():
                 # Pipe previous command output (if there was a previous command)
                 edges: list[Edge] = list()
                 if len(history) > 0 or current_id != start_id:
-                    from_id = (
-                        history[0] if current_id == start_id else str(current_id - 1)
-                    )
+                    from_id = history[0] if current_id == start_id else str(current_id - 1)
                     from_node = (
                         next(filter(lambda n: n[0].id == from_id, new_invocations))[0]
                         if current_id != start_id
                         else context.session.graph.get_node(from_id)
                     )
-                    matching_edges = generate_matching_edges(
-                        from_node, command.command, context
-                    )
+                    matching_edges = generate_matching_edges(from_node, command.command, context)
                     edges.extend(matching_edges)
 
                 # Parse provided links
@@ -406,16 +423,18 @@ def invoke_cli():
                             node_id = str(current_id + int(node_id))
 
                         link_node = context.session.graph.get_node(node_id)
-                        matching_edges = generate_matching_edges(
-                            link_node, command.command, context
-                        )
+                        matching_edges = generate_matching_edges(link_node, command.command, context)
                         matching_destinations = [e.destination for e in matching_edges]
                         edges = [e for e in edges if e.destination not in matching_destinations]
                         edges.extend(matching_edges)
 
                 if "link" in args and args["link"]:
                     for link in args["link"]:
-                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
+                        edges = [
+                            e
+                            for e in edges
+                            if e.destination.node_id != command.command.id or e.destination.field != link[2]
+                        ]
 
                         node_id = link[0]
                         if re_negid.match(node_id):
@@ -428,7 +447,7 @@ def invoke_cli():
                         edges.append(
                             Edge(
                                 source=EdgeConnection(node_id=node_output.node_path, field=node_output.field),
-                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field)
+                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field),
                             )
                         )
 

invokeai/app/invocations/__init__.py

@@ -4,9 +4,5 @@ __all__ = []
 
 dirname = os.path.dirname(os.path.abspath(__file__))
 for f in os.listdir(dirname):
-    if (
-        f != "__init__.py"
-        and os.path.isfile("%s/%s" % (dirname, f))
-        and f[-3:] == ".py"
-    ):
+    if f != "__init__.py" and os.path.isfile("%s/%s" % (dirname, f)) and f[-3:] == ".py":
         __all__.append(f[:-3])

invokeai/app/invocations/baseinvocation.py

@@ -4,8 +4,7 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import (TYPE_CHECKING, Dict, List, Literal, TypedDict, get_args,
-                    get_type_hints)
+from typing import TYPE_CHECKING, Dict, List, Literal, TypedDict, get_args, get_type_hints
 
 from pydantic import BaseConfig, BaseModel, Field
 

invokeai/app/invocations/collections.py

@@ -8,8 +8,7 @@ from pydantic import Field, validator
 from invokeai.app.models.image import ImageField
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext, UIConfig)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext, UIConfig
 
 
 class IntCollectionOutput(BaseInvocationOutput):
@@ -27,8 +26,7 @@ class FloatCollectionOutput(BaseInvocationOutput):
     type: Literal["float_collection"] = "float_collection"
 
     # Outputs
-    collection: list[float] = Field(
-        default=[], description="The float collection")
+    collection: list[float] = Field(default=[], description="The float collection")
 
 
 class ImageCollectionOutput(BaseInvocationOutput):
@@ -37,8 +35,7 @@ class ImageCollectionOutput(BaseInvocationOutput):
     type: Literal["image_collection"] = "image_collection"
 
     # Outputs
-    collection: list[ImageField] = Field(
-        default=[], description="The output images")
+    collection: list[ImageField] = Field(default=[], description="The output images")
 
     class Config:
         schema_extra = {"required": ["type", "collection"]}
@@ -56,10 +53,7 @@ class RangeInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Range",
-                "tags": ["range", "integer", "collection"]
-            },
+            "ui": {"title": "Range", "tags": ["range", "integer", "collection"]},
         }
 
     @validator("stop")
@@ -69,9 +63,7 @@ class RangeInvocation(BaseInvocation):
         return v
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(
-            collection=list(range(self.start, self.stop, self.step))
-        )
+        return IntCollectionOutput(collection=list(range(self.start, self.stop, self.step)))
 
 
 class RangeOfSizeInvocation(BaseInvocation):
@@ -86,18 +78,11 @@ class RangeOfSizeInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Sized Range",
-                "tags": ["range", "integer", "size", "collection"]
-            },
+            "ui": {"title": "Sized Range", "tags": ["range", "integer", "size", "collection"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(
-            collection=list(
-                range(
-                    self.start, self.start + self.size,
-                    self.step)))
+        return IntCollectionOutput(collection=list(range(self.start, self.start + self.size, self.step)))
 
 
 class RandomRangeInvocation(BaseInvocation):
@@ -107,9 +92,7 @@ class RandomRangeInvocation(BaseInvocation):
 
     # Inputs
     low: int = Field(default=0, description="The inclusive low value")
-    high: int = Field(
-        default=np.iinfo(np.int32).max, description="The exclusive high value"
-    )
+    high: int = Field(default=np.iinfo(np.int32).max, description="The exclusive high value")
     size: int = Field(default=1, description="The number of values to generate")
     seed: int = Field(
         ge=0,
@@ -120,19 +103,12 @@ class RandomRangeInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Random Range",
-                "tags": ["range", "integer", "random", "collection"]
-            },
+            "ui": {"title": "Random Range", "tags": ["range", "integer", "random", "collection"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:
         rng = np.random.default_rng(self.seed)
-        return IntCollectionOutput(
-            collection=list(
-                rng.integers(
-                    low=self.low, high=self.high,
-                    size=self.size)))
+        return IntCollectionOutput(collection=list(rng.integers(low=self.low, high=self.high, size=self.size)))
 
 
 class ImageCollectionInvocation(BaseInvocation):

invokeai/app/invocations/compel.py

@@ -1,66 +1,73 @@
 from typing import Literal, Optional, Union, List, Annotated
 from pydantic import BaseModel, Field
 import re
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+from .model import ClipField
+
+from ...backend.util.devices import torch_dtype
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from ...backend.model_management import BaseModelType, ModelType, SubModelType, ModelPatcher
+
 import torch
 from compel import Compel, ReturnedEmbeddingsType
-from compel.prompt_parser import (Blend, Conjunction,
-                                  CrossAttentionControlSubstitute,
-                                  FlattenedPrompt, Fragment)
+from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 from ...backend.util.devices import torch_dtype
 from ...backend.model_management import ModelType
 from ...backend.model_management.models import ModelNotFoundException
 from ...backend.model_management.lora import ModelPatcher
 from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 from .model import ClipField
 from dataclasses import dataclass
 
 
 class ConditioningField(BaseModel):
-    conditioning_name: Optional[str] = Field(
-        default=None, description="The name of conditioning data")
+    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
 
     class Config:
         schema_extra = {"required": ["conditioning_name"]}
 
+
 @dataclass
 class BasicConditioningInfo:
-    #type: Literal["basic_conditioning"] = "basic_conditioning"
+    # type: Literal["basic_conditioning"] = "basic_conditioning"
     embeds: torch.Tensor
     extra_conditioning: Optional[InvokeAIDiffuserComponent.ExtraConditioningInfo]
     # weight: float
     # mode: ConditioningAlgo
 
+
 @dataclass
 class SDXLConditioningInfo(BasicConditioningInfo):
-    #type: Literal["sdxl_conditioning"] = "sdxl_conditioning"
+    # type: Literal["sdxl_conditioning"] = "sdxl_conditioning"
     pooled_embeds: torch.Tensor
     add_time_ids: torch.Tensor
 
-ConditioningInfoType = Annotated[
-    Union[BasicConditioningInfo, SDXLConditioningInfo],
-    Field(discriminator="type")
-]
+
+ConditioningInfoType = Annotated[Union[BasicConditioningInfo, SDXLConditioningInfo], Field(discriminator="type")]
+
 
 @dataclass
 class ConditioningFieldData:
     conditionings: List[Union[BasicConditioningInfo, SDXLConditioningInfo]]
-    #unconditioned: Optional[torch.Tensor]
+    # unconditioned: Optional[torch.Tensor]
 
-#class ConditioningAlgo(str, Enum):
+
+# class ConditioningAlgo(str, Enum):
 #    Compose = "compose"
 #    ComposeEx = "compose_ex"
 #    PerpNeg = "perp_neg"
 
+
 class CompelOutput(BaseInvocationOutput):
     """Compel parser output"""
 
-    #fmt: off
+    # fmt: off
     type: Literal["compel_output"] = "compel_output"
 
     conditioning: ConditioningField = Field(default=None, description="Conditioning")
-    #fmt: on
+    # fmt: on
 
 
 class CompelInvocation(BaseInvocation):
@@ -74,33 +81,28 @@ class CompelInvocation(BaseInvocation):
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Prompt (Compel)",
-                "tags": ["prompt", "compel"],
-                "type_hints": {
-                    "model": "model"
-                }
-            },
+            "ui": {"title": "Prompt (Compel)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
         }
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> CompelOutput:
         tokenizer_info = context.services.model_manager.get_model(
-            **self.clip.tokenizer.dict(), context=context,
+            **self.clip.tokenizer.dict(),
+            context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **self.clip.text_encoder.dict(), context=context,
+            **self.clip.text_encoder.dict(),
+            context=context,
         )
 
         def _lora_loader():
             for lora in self.clip.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}))
+                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
@@ -116,15 +118,18 @@ class CompelInvocation(BaseInvocation):
                 )
             except ModelNotFoundException:
                 # print(e)
-                #import traceback
-                #print(traceback.format_exc())
-                print(f"Warn: trigger: \"{trigger}\" not found")
-
-        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
-                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
-                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),\
-                text_encoder_info as text_encoder:
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
 
+        with ModelPatcher.apply_lora_text_encoder(
+            text_encoder_info.context.model, _lora_loader()
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, self.clip.skipped_layers
+        ), text_encoder_info as text_encoder:
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
@@ -139,14 +144,12 @@ class CompelInvocation(BaseInvocation):
             if context.services.configuration.log_tokenization:
                 log_tokenization_for_prompt_object(prompt, tokenizer)
 
-            c, options = compel.build_conditioning_tensor_for_prompt_object(
-                prompt)
+            c, options = compel.build_conditioning_tensor_for_prompt_object(prompt)
 
             ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(
-                    tokenizer, conjunction),
-                cross_attention_control_args=options.get(
-                    "cross_attention_control", None),)
+                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
+                cross_attention_control_args=options.get("cross_attention_control", None),
+            )
 
         c = c.detach().to("cpu")
 
@@ -168,24 +171,26 @@ class CompelInvocation(BaseInvocation):
             ),
         )
 
+
 class SDXLPromptInvocationBase:
     def run_clip_raw(self, context, clip_field, prompt, get_pooled):
         tokenizer_info = context.services.model_manager.get_model(
             **clip_field.tokenizer.dict(),
+            context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
             **clip_field.text_encoder.dict(),
+            context=context,
         )
 
         def _lora_loader():
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}))
+                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
@@ -196,19 +201,23 @@ class SDXLPromptInvocationBase:
                         model_name=name,
                         base_model=clip_field.text_encoder.base_model,
                         model_type=ModelType.TextualInversion,
+                        context=context,
                     ).context.model
                 )
             except ModelNotFoundException:
                 # print(e)
-                #import traceback
-                #print(traceback.format_exc())
-                print(f"Warn: trigger: \"{trigger}\" not found")
-
-        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
-                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
-                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),\
-                text_encoder_info as text_encoder:
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
 
+        with ModelPatcher.apply_lora_text_encoder(
+            text_encoder_info.context.model, _lora_loader()
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, clip_field.skipped_layers
+        ), text_encoder_info as text_encoder:
             text_inputs = tokenizer(
                 prompt,
                 padding="max_length",
@@ -241,20 +250,21 @@ class SDXLPromptInvocationBase:
     def run_clip_compel(self, context, clip_field, prompt, get_pooled):
         tokenizer_info = context.services.model_manager.get_model(
             **clip_field.tokenizer.dict(),
+            context=context,
         )
         text_encoder_info = context.services.model_manager.get_model(
             **clip_field.text_encoder.dict(),
+            context=context,
         )
 
         def _lora_loader():
             for lora in clip_field.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}))
+                lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
 
-        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+        # loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
 
         ti_list = []
         for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
@@ -265,26 +275,30 @@ class SDXLPromptInvocationBase:
                         model_name=name,
                         base_model=clip_field.text_encoder.base_model,
                         model_type=ModelType.TextualInversion,
+                        context=context,
                     ).context.model
                 )
             except ModelNotFoundException:
                 # print(e)
-                #import traceback
-                #print(traceback.format_exc())
-                print(f"Warn: trigger: \"{trigger}\" not found")
-
-        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
-                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
-                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),\
-                text_encoder_info as text_encoder:
+                # import traceback
+                # print(traceback.format_exc())
+                print(f'Warn: trigger: "{trigger}" not found')
 
+        with ModelPatcher.apply_lora_text_encoder(
+            text_encoder_info.context.model, _lora_loader()
+        ), ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
+            tokenizer,
+            ti_manager,
+        ), ModelPatcher.apply_clip_skip(
+            text_encoder_info.context.model, clip_field.skipped_layers
+        ), text_encoder_info as text_encoder:
             compel = Compel(
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
                 dtype_for_device_getter=torch_dtype,
                 truncate_long_prompts=True,  # TODO:
-                returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, # TODO: clip skip
+                returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,  # TODO: clip skip
                 requires_pooled=True,
             )
 
@@ -318,6 +332,7 @@ class SDXLPromptInvocationBase:
 
         return c, c_pooled, ec
 
+
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
@@ -337,13 +352,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "SDXL Prompt (Compel)",
-                "tags": ["prompt", "compel"],
-                "type_hints": {
-                    "model": "model"
-                }
-            },
+            "ui": {"title": "SDXL Prompt (Compel)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
         }
 
     @torch.no_grad()
@@ -358,9 +367,7 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         crop_coords = (self.crop_top, self.crop_left)
         target_size = (self.target_height, self.target_width)
 
-        add_time_ids = torch.tensor([
-            original_size + crop_coords + target_size
-        ])
+        add_time_ids = torch.tensor([original_size + crop_coords + target_size])
 
         conditioning_data = ConditioningFieldData(
             conditionings=[
@@ -382,12 +389,13 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ),
         )
 
+
 class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
     type: Literal["sdxl_refiner_compel_prompt"] = "sdxl_refiner_compel_prompt"
 
-    style: str = Field(default="", description="Style prompt") # TODO: ?
+    style: str = Field(default="", description="Style prompt")  # TODO: ?
     original_width: int = Field(1024, description="")
     original_height: int = Field(1024, description="")
     crop_top: int = Field(0, description="")
@@ -401,9 +409,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             "ui": {
                 "title": "SDXL Refiner Prompt (Compel)",
                 "tags": ["prompt", "compel"],
-                "type_hints": {
-                    "model": "model"
-                }
+                "type_hints": {"model": "model"},
             },
         }
 
@@ -414,9 +420,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
 
-        add_time_ids = torch.tensor([
-            original_size + crop_coords + (self.aesthetic_score,)
-        ])
+        add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
         conditioning_data = ConditioningFieldData(
             conditionings=[
@@ -424,7 +428,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
                     embeds=c2,
                     pooled_embeds=c2_pooled,
                     add_time_ids=add_time_ids,
-                    extra_conditioning=ec2, # or None
+                    extra_conditioning=ec2,  # or None
                 )
             ]
         )
@@ -438,6 +442,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
             ),
         )
 
+
 class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Pass unmodified prompt to conditioning without compel processing."""
 
@@ -457,13 +462,7 @@ class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "SDXL Prompt (Raw)",
-                "tags": ["prompt", "compel"],
-                "type_hints": {
-                    "model": "model"
-                }
-            },
+            "ui": {"title": "SDXL Prompt (Raw)", "tags": ["prompt", "compel"], "type_hints": {"model": "model"}},
         }
 
     @torch.no_grad()
@@ -478,9 +477,7 @@ class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         crop_coords = (self.crop_top, self.crop_left)
         target_size = (self.target_height, self.target_width)
 
-        add_time_ids = torch.tensor([
-            original_size + crop_coords + target_size
-        ])
+        add_time_ids = torch.tensor([original_size + crop_coords + target_size])
 
         conditioning_data = ConditioningFieldData(
             conditionings=[
@@ -502,12 +499,13 @@ class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             ),
         )
 
+
 class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
 
     type: Literal["sdxl_refiner_raw_prompt"] = "sdxl_refiner_raw_prompt"
 
-    style: str = Field(default="", description="Style prompt") # TODO: ?
+    style: str = Field(default="", description="Style prompt")  # TODO: ?
     original_width: int = Field(1024, description="")
     original_height: int = Field(1024, description="")
     crop_top: int = Field(0, description="")
@@ -521,9 +519,7 @@ class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
             "ui": {
                 "title": "SDXL Refiner Prompt (Raw)",
                 "tags": ["prompt", "compel"],
-                "type_hints": {
-                    "model": "model"
-                }
+                "type_hints": {"model": "model"},
             },
         }
 
@@ -534,9 +530,7 @@ class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
 
-        add_time_ids = torch.tensor([
-            original_size + crop_coords + (self.aesthetic_score,)
-        ])
+        add_time_ids = torch.tensor([original_size + crop_coords + (self.aesthetic_score,)])
 
         conditioning_data = ConditioningFieldData(
             conditionings=[
@@ -544,7 +538,7 @@ class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
                     embeds=c2,
                     pooled_embeds=c2_pooled,
                     add_time_ids=add_time_ids,
-                    extra_conditioning=ec2, # or None
+                    extra_conditioning=ec2,  # or None
                 )
             ]
         )
@@ -561,11 +555,14 @@ class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
 
 class ClipSkipInvocationOutput(BaseInvocationOutput):
     """Clip skip node output"""
+
     type: Literal["clip_skip_output"] = "clip_skip_output"
     clip: ClipField = Field(None, description="Clip with skipped layers")
 
+
 class ClipSkipInvocation(BaseInvocation):
     """Skip layers in clip text_encoder model."""
+
     type: Literal["clip_skip"] = "clip_skip"
 
     clip: ClipField = Field(None, description="Clip to use")
@@ -573,10 +570,7 @@ class ClipSkipInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "CLIP Skip",
-                "tags": ["clip", "skip"]
-            },
+            "ui": {"title": "CLIP Skip", "tags": ["clip", "skip"]},
         }
 
     def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
@@ -587,46 +581,26 @@ class ClipSkipInvocation(BaseInvocation):
 
 
 def get_max_token_count(
-        tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction],
-        truncate_if_too_long=False) -> int:
+    tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
+) -> int:
     if type(prompt) is Blend:
         blend: Blend = prompt
-        return max(
-            [
-                get_max_token_count(tokenizer, p, truncate_if_too_long)
-                for p in blend.prompts
-            ]
-        )
+        return max([get_max_token_count(tokenizer, p, truncate_if_too_long) for p in blend.prompts])
     elif type(prompt) is Conjunction:
         conjunction: Conjunction = prompt
-        return sum(
-            [
-                get_max_token_count(tokenizer, p, truncate_if_too_long)
-                for p in conjunction.prompts
-            ]
-        )
+        return sum([get_max_token_count(tokenizer, p, truncate_if_too_long) for p in conjunction.prompts])
     else:
-        return len(
-            get_tokens_for_prompt_object(
-                tokenizer, prompt, truncate_if_too_long))
+        return len(get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long))
 
 
-def get_tokens_for_prompt_object(
-    tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True
-) -> List[str]:
+def get_tokens_for_prompt_object(tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True) -> List[str]:
     if type(parsed_prompt) is Blend:
-        raise ValueError(
-            "Blend is not supported here - you need to get tokens for each of its .children"
-        )
+        raise ValueError("Blend is not supported here - you need to get tokens for each of its .children")
 
     text_fragments = [
         x.text
         if type(x) is Fragment
-        else (
-            " ".join([f.text for f in x.original])
-            if type(x) is CrossAttentionControlSubstitute
-            else str(x)
-        )
+        else (" ".join([f.text for f in x.original]) if type(x) is CrossAttentionControlSubstitute else str(x))
         for x in parsed_prompt.children
     ]
     text = " ".join(text_fragments)
@@ -637,25 +611,17 @@ def get_tokens_for_prompt_object(
     return tokens
 
 
-def log_tokenization_for_conjunction(
-    c: Conjunction, tokenizer, display_label_prefix=None
-):
+def log_tokenization_for_conjunction(c: Conjunction, tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     for i, p in enumerate(c.prompts):
         if len(c.prompts) > 1:
             this_display_label_prefix = f"{display_label_prefix}(conjunction part {i + 1}, weight={c.weights[i]})"
         else:
             this_display_label_prefix = display_label_prefix
-        log_tokenization_for_prompt_object(
-            p,
-            tokenizer,
-            display_label_prefix=this_display_label_prefix
-        )
+        log_tokenization_for_prompt_object(p, tokenizer, display_label_prefix=this_display_label_prefix)
 
 
-def log_tokenization_for_prompt_object(
-    p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None
-):
+def log_tokenization_for_prompt_object(p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None):
     display_label_prefix = display_label_prefix or ""
     if type(p) is Blend:
         blend: Blend = p
@@ -692,13 +658,10 @@ def log_tokenization_for_prompt_object(
             )
         else:
             text = " ".join([x.text for x in flattened_prompt.children])
-            log_tokenization_for_text(
-                text, tokenizer, display_label=display_label_prefix
-            )
+            log_tokenization_for_text(text, tokenizer, display_label=display_label_prefix)
 
 
-def log_tokenization_for_text(
-        text, tokenizer, display_label=None, truncate_if_too_long=False):
+def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
     """shows how the prompt is tokenized
     # usually tokens have '</w>' to indicate end-of-word,
     # but for readability it has been replaced with ' '

invokeai/app/invocations/controlnet_image_processors.py

@@ -6,21 +6,30 @@ from typing import Dict, List, Literal, Optional, Union
 
 import cv2
 import numpy as np
-from controlnet_aux import (CannyDetector, ContentShuffleDetector, HEDdetector,
-                            LeresDetector, LineartAnimeDetector,
-                            LineartDetector, MediapipeFaceDetector,
-                            MidasDetector, MLSDdetector, NormalBaeDetector,
-                            OpenposeDetector, PidiNetDetector, SamDetector,
-                            ZoeDetector)
+from controlnet_aux import (
+    CannyDetector,
+    ContentShuffleDetector,
+    HEDdetector,
+    LeresDetector,
+    LineartAnimeDetector,
+    LineartDetector,
+    MediapipeFaceDetector,
+    MidasDetector,
+    MLSDdetector,
+    NormalBaeDetector,
+    OpenposeDetector,
+    PidiNetDetector,
+    SamDetector,
+    ZoeDetector,
+)
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
 from pydantic import BaseModel, Field, validator
 
 from ...backend.model_management import BaseModelType, ModelType
 from ..models.image import ImageCategory, ImageField, ResourceOrigin
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
-from .image import ImageOutput, PILInvocationConfig
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
+from ..models.image import ImageOutput, PILInvocationConfig
 
 CONTROLNET_DEFAULT_MODELS = [
     ###########################################
@@ -34,7 +43,6 @@ CONTROLNET_DEFAULT_MODELS = [
     "lllyasviel/sd-controlnet-scribble",
     "lllyasviel/sd-controlnet-normal",
     "lllyasviel/sd-controlnet-mlsd",
-
     #############################################
     # lllyasviel sd v1.5, ControlNet v1.1 models
     #############################################
@@ -56,7 +64,6 @@ CONTROLNET_DEFAULT_MODELS = [
     "lllyasviel/control_v11e_sd15_shuffle",
     "lllyasviel/control_v11e_sd15_ip2p",
     "lllyasviel/control_v11f1e_sd15_tile",
-
     #################################################
     #  thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
     ##################################################
@@ -71,7 +78,6 @@ CONTROLNET_DEFAULT_MODELS = [
     "thibaud/controlnet-sd21-lineart-diffusers",
     "thibaud/controlnet-sd21-normalbae-diffusers",
     "thibaud/controlnet-sd21-ade20k-diffusers",
-
     ##############################################
     #  ControlNetMediaPipeface, ControlNet v1.1
     ##############################################
@@ -83,10 +89,17 @@ CONTROLNET_DEFAULT_MODELS = [
 ]
 
 CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
-CONTROLNET_MODE_VALUES = Literal[tuple(
-    ["balanced", "more_prompt", "more_control", "unbalanced"])]
-# crop and fill options not ready yet
-# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
+CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])]
+CONTROLNET_RESIZE_VALUES = Literal[
+    tuple(
+        [
+            "just_resize",
+            "crop_resize",
+            "fill_resize",
+            "just_resize_simple",
+        ]
+    )
+]
 
 
 class ControlNetModelField(BaseModel):
@@ -98,20 +111,17 @@ class ControlNetModelField(BaseModel):
 
 class ControlField(BaseModel):
     image: ImageField = Field(default=None, description="The control image")
-    control_model: Optional[ControlNetModelField] = Field(
-        default=None, description="The ControlNet model to use")
+    control_model: Optional[ControlNetModelField] = Field(default=None, description="The ControlNet model to use")
     # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
-    control_weight: Union[float, List[float]] = Field(
-        default=1, description="The weight given to the ControlNet")
+    control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
     begin_step_percent: float = Field(
-        default=0, ge=0, le=1,
-        description="When the ControlNet is first applied (% of total steps)")
+        default=0, ge=0, le=1, description="When the ControlNet is first applied (% of total steps)"
+    )
     end_step_percent: float = Field(
-        default=1, ge=0, le=1,
-        description="When the ControlNet is last applied (% of total steps)")
-    control_mode: CONTROLNET_MODE_VALUES = Field(
-        default="balanced", description="The control mode to use")
-    # resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
+        default=1, ge=0, le=1, description="When the ControlNet is last applied (% of total steps)"
+    )
+    control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
 
     @validator("control_weight")
     def validate_control_weight(cls, v):
@@ -119,11 +129,10 @@ class ControlField(BaseModel):
         if isinstance(v, list):
             for i in v:
                 if i < -1 or i > 2:
-                    raise ValueError(
-                        'Control weights must be within -1 to 2 range')
+                    raise ValueError("Control weights must be within -1 to 2 range")
         else:
             if v < -1 or v > 2:
-                raise ValueError('Control weights must be within -1 to 2 range')
+                raise ValueError("Control weights must be within -1 to 2 range")
         return v
 
     class Config:
@@ -135,12 +144,13 @@ class ControlField(BaseModel):
                     "control_model": "controlnet_model",
                     # "control_weight": "number",
                 }
-            }
+            },
         }
 
 
 class ControlOutput(BaseInvocationOutput):
     """node output for ControlNet info"""
+
     # fmt: off
     type: Literal["control_output"] = "control_output"
     control: ControlField = Field(default=None, description="The control info")
@@ -149,6 +159,7 @@ class ControlOutput(BaseInvocationOutput):
 
 class ControlNetInvocation(BaseInvocation):
     """Collects ControlNet info to pass to other nodes"""
+
     # fmt: off
     type: Literal["controlnet"] = "controlnet"
     # Inputs
@@ -161,6 +172,7 @@ class ControlNetInvocation(BaseInvocation):
     end_step_percent: float = Field(default=1, ge=0, le=1,
                                     description="When the ControlNet is last applied (% of total steps)")
     control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode used")
+    resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode used")
     # fmt: on
 
     class Config(InvocationConfig):
@@ -174,7 +186,7 @@ class ControlNetInvocation(BaseInvocation):
                     # "cfg_scale": "float",
                     "cfg_scale": "number",
                     "control_weight": "float",
-                }
+                },
             },
         }
 
@@ -187,6 +199,7 @@ class ControlNetInvocation(BaseInvocation):
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
                 control_mode=self.control_mode,
+                resize_mode=self.resize_mode,
             ),
         )
 
@@ -202,10 +215,7 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Image Processor",
-                "tags": ["image", "processor"]
-            },
+            "ui": {"title": "Image Processor", "tags": ["image", "processor"]},
         }
 
     def run_processor(self, image):
@@ -230,7 +240,7 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
             image_category=ImageCategory.CONTROL,
             session_id=context.graph_execution_state_id,
             node_id=self.id,
-            is_intermediate=self.is_intermediate
+            is_intermediate=self.is_intermediate,
         )
 
         """Builds an ImageOutput and its ImageField"""
@@ -245,9 +255,9 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
         )
 
 
-class CannyImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Canny edge detection for ControlNet"""
+
     # fmt: off
     type: Literal["canny_image_processor"] = "canny_image_processor"
     # Input
@@ -257,22 +267,18 @@ class CannyImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Canny Processor",
-                "tags": ["controlnet", "canny", "image", "processor"]
-            },
+            "ui": {"title": "Canny Processor", "tags": ["controlnet", "canny", "image", "processor"]},
         }
 
     def run_processor(self, image):
         canny_processor = CannyDetector()
-        processed_image = canny_processor(
-            image, self.low_threshold, self.high_threshold)
+        processed_image = canny_processor(image, self.low_threshold, self.high_threshold)
         return processed_image
 
 
-class HedImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies HED edge detection to image"""
+
     # fmt: off
     type: Literal["hed_image_processor"] = "hed_image_processor"
     # Inputs
@@ -285,27 +291,25 @@ class HedImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Softedge(HED) Processor",
-                "tags": ["controlnet", "softedge", "hed", "image", "processor"]
-            },
+            "ui": {"title": "Softedge(HED) Processor", "tags": ["controlnet", "softedge", "hed", "image", "processor"]},
         }
 
     def run_processor(self, image):
         hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = hed_processor(image,
-                                        detect_resolution=self.detect_resolution,
-                                        image_resolution=self.image_resolution,
-                                        # safe not supported in controlnet_aux v0.0.3
-                                        # safe=self.safe,
-                                        scribble=self.scribble,
-                                        )
+        processed_image = hed_processor(
+            image,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+            # safe not supported in controlnet_aux v0.0.3
+            # safe=self.safe,
+            scribble=self.scribble,
+        )
         return processed_image
 
 
-class LineartImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies line art processing to image"""
+
     # fmt: off
     type: Literal["lineart_image_processor"] = "lineart_image_processor"
     # Inputs
@@ -316,24 +320,20 @@ class LineartImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Lineart Processor",
-                "tags": ["controlnet", "lineart", "image", "processor"]
-            },
+            "ui": {"title": "Lineart Processor", "tags": ["controlnet", "lineart", "image", "processor"]},
         }
 
     def run_processor(self, image):
-        lineart_processor = LineartDetector.from_pretrained(
-            "lllyasviel/Annotators")
+        lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = lineart_processor(
-            image, detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution, coarse=self.coarse)
+            image, detect_resolution=self.detect_resolution, image_resolution=self.image_resolution, coarse=self.coarse
+        )
         return processed_image
 
 
-class LineartAnimeImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies line art anime processing to image"""
+
     # fmt: off
     type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
     # Inputs
@@ -345,23 +345,23 @@ class LineartAnimeImageProcessorInvocation(
         schema_extra = {
             "ui": {
                 "title": "Lineart Anime Processor",
-                "tags": ["controlnet", "lineart", "anime", "image", "processor"]
+                "tags": ["controlnet", "lineart", "anime", "image", "processor"],
             },
         }
 
     def run_processor(self, image):
-        processor = LineartAnimeDetector.from_pretrained(
-            "lllyasviel/Annotators")
-        processed_image = processor(image,
-                                    detect_resolution=self.detect_resolution,
-                                    image_resolution=self.image_resolution,
-                                    )
+        processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
+        processed_image = processor(
+            image,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+        )
         return processed_image
 
 
-class OpenposeImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Openpose processing to image"""
+
     # fmt: off
     type: Literal["openpose_image_processor"] = "openpose_image_processor"
     # Inputs
@@ -372,25 +372,23 @@ class OpenposeImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Openpose Processor",
-                "tags": ["controlnet", "openpose", "image", "processor"]
-            },
+            "ui": {"title": "Openpose Processor", "tags": ["controlnet", "openpose", "image", "processor"]},
         }
 
     def run_processor(self, image):
-        openpose_processor = OpenposeDetector.from_pretrained(
-            "lllyasviel/Annotators")
+        openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = openpose_processor(
-            image, detect_resolution=self.detect_resolution,
+            image,
+            detect_resolution=self.detect_resolution,
             image_resolution=self.image_resolution,
-            hand_and_face=self.hand_and_face,)
+            hand_and_face=self.hand_and_face,
+        )
         return processed_image
 
 
-class MidasDepthImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Midas depth processing to image"""
+
     # fmt: off
     type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
     # Inputs
@@ -402,26 +400,24 @@ class MidasDepthImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Midas (Depth) Processor",
-                "tags": ["controlnet", "midas", "depth", "image", "processor"]
-            },
+            "ui": {"title": "Midas (Depth) Processor", "tags": ["controlnet", "midas", "depth", "image", "processor"]},
         }
 
     def run_processor(self, image):
         midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
-        processed_image = midas_processor(image,
-                                          a=np.pi * self.a_mult,
-                                          bg_th=self.bg_th,
-                                          # dept_and_normal not supported in controlnet_aux v0.0.3
-                                          # depth_and_normal=self.depth_and_normal,
-                                          )
+        processed_image = midas_processor(
+            image,
+            a=np.pi * self.a_mult,
+            bg_th=self.bg_th,
+            # dept_and_normal not supported in controlnet_aux v0.0.3
+            # depth_and_normal=self.depth_and_normal,
+        )
         return processed_image
 
 
-class NormalbaeImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies NormalBae processing to image"""
+
     # fmt: off
     type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
     # Inputs
@@ -431,24 +427,20 @@ class NormalbaeImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Normal BAE Processor",
-                "tags": ["controlnet", "normal", "bae", "image", "processor"]
-            },
+            "ui": {"title": "Normal BAE Processor", "tags": ["controlnet", "normal", "bae", "image", "processor"]},
         }
 
     def run_processor(self, image):
-        normalbae_processor = NormalBaeDetector.from_pretrained(
-            "lllyasviel/Annotators")
+        normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = normalbae_processor(
-            image, detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution)
+            image, detect_resolution=self.detect_resolution, image_resolution=self.image_resolution
+        )
         return processed_image
 
 
-class MlsdImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies MLSD processing to image"""
+
     # fmt: off
     type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
     # Inputs
@@ -460,24 +452,24 @@ class MlsdImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "MLSD Processor",
-                "tags": ["controlnet", "mlsd", "image", "processor"]
-            },
+            "ui": {"title": "MLSD Processor", "tags": ["controlnet", "mlsd", "image", "processor"]},
         }
 
     def run_processor(self, image):
         mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
         processed_image = mlsd_processor(
-            image, detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution, thr_v=self.thr_v,
-            thr_d=self.thr_d)
+            image,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+            thr_v=self.thr_v,
+            thr_d=self.thr_d,
+        )
         return processed_image
 
 
-class PidiImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies PIDI processing to image"""
+
     # fmt: off
     type: Literal["pidi_image_processor"] = "pidi_image_processor"
     # Inputs
@@ -489,25 +481,24 @@ class PidiImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "PIDI Processor",
-                "tags": ["controlnet", "pidi", "image", "processor"]
-            },
+            "ui": {"title": "PIDI Processor", "tags": ["controlnet", "pidi", "image", "processor"]},
         }
 
     def run_processor(self, image):
-        pidi_processor = PidiNetDetector.from_pretrained(
-            "lllyasviel/Annotators")
+        pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = pidi_processor(
-            image, detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution, safe=self.safe,
-            scribble=self.scribble)
+            image,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+            safe=self.safe,
+            scribble=self.scribble,
+        )
         return processed_image
 
 
-class ContentShuffleImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies content shuffle processing to image"""
+
     # fmt: off
     type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
     # Inputs
@@ -522,48 +513,45 @@ class ContentShuffleImageProcessorInvocation(
         schema_extra = {
             "ui": {
                 "title": "Content Shuffle Processor",
-                "tags": ["controlnet", "contentshuffle", "image", "processor"]
+                "tags": ["controlnet", "contentshuffle", "image", "processor"],
             },
         }
 
     def run_processor(self, image):
         content_shuffle_processor = ContentShuffleDetector()
-        processed_image = content_shuffle_processor(image,
-                                                    detect_resolution=self.detect_resolution,
-                                                    image_resolution=self.image_resolution,
-                                                    h=self.h,
-                                                    w=self.w,
-                                                    f=self.f
-                                                    )
+        processed_image = content_shuffle_processor(
+            image,
+            detect_resolution=self.detect_resolution,
+            image_resolution=self.image_resolution,
+            h=self.h,
+            w=self.w,
+            f=self.f,
+        )
         return processed_image
 
 
 # should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
-class ZoeDepthImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies Zoe depth processing to image"""
+
     # fmt: off
     type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
     # fmt: on
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Zoe (Depth) Processor",
-                "tags": ["controlnet", "zoe", "depth", "image", "processor"]
-            },
+            "ui": {"title": "Zoe (Depth) Processor", "tags": ["controlnet", "zoe", "depth", "image", "processor"]},
         }
 
     def run_processor(self, image):
-        zoe_depth_processor = ZoeDetector.from_pretrained(
-            "lllyasviel/Annotators")
+        zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = zoe_depth_processor(image)
         return processed_image
 
 
-class MediapipeFaceProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies mediapipe face processing to image"""
+
     # fmt: off
     type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
     # Inputs
@@ -573,26 +561,22 @@ class MediapipeFaceProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Mediapipe Processor",
-                "tags": ["controlnet", "mediapipe", "image", "processor"]
-            },
+            "ui": {"title": "Mediapipe Processor", "tags": ["controlnet", "mediapipe", "image", "processor"]},
         }
 
     def run_processor(self, image):
         # MediaPipeFaceDetector throws an error if image has alpha channel
         #     so convert to RGB if needed
-        if image.mode == 'RGBA':
-            image = image.convert('RGB')
+        if image.mode == "RGBA":
+            image = image.convert("RGB")
         mediapipe_face_processor = MediapipeFaceDetector()
-        processed_image = mediapipe_face_processor(
-            image, max_faces=self.max_faces, min_confidence=self.min_confidence)
+        processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence)
         return processed_image
 
 
-class LeresImageProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies leres processing to image"""
+
     # fmt: off
     type: Literal["leres_image_processor"] = "leres_image_processor"
     # Inputs
@@ -605,24 +589,23 @@ class LeresImageProcessorInvocation(
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Leres (Depth) Processor",
-                "tags": ["controlnet", "leres", "depth", "image", "processor"]
-            },
+            "ui": {"title": "Leres (Depth) Processor", "tags": ["controlnet", "leres", "depth", "image", "processor"]},
         }
 
     def run_processor(self, image):
         leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = leres_processor(
-            image, thr_a=self.thr_a, thr_b=self.thr_b, boost=self.boost,
+            image,
+            thr_a=self.thr_a,
+            thr_b=self.thr_b,
+            boost=self.boost,
             detect_resolution=self.detect_resolution,
-            image_resolution=self.image_resolution)
+            image_resolution=self.image_resolution,
+        )
         return processed_image
 
 
-class TileResamplerProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
-
+class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     # fmt: off
     type: Literal["tile_image_processor"] = "tile_image_processor"
     # Inputs
@@ -634,16 +617,17 @@ class TileResamplerProcessorInvocation(
         schema_extra = {
             "ui": {
                 "title": "Tile Resample Processor",
-                "tags": ["controlnet", "tile", "resample", "image", "processor"]
+                "tags": ["controlnet", "tile", "resample", "image", "processor"],
             },
         }
 
     # tile_resample copied from sd-webui-controlnet/scripts/processor.py
-    def tile_resample(self,
-                      np_img: np.ndarray,
-                      res=512,   # never used?
-                      down_sampling_rate=1.0,
-                      ):
+    def tile_resample(
+        self,
+        np_img: np.ndarray,
+        res=512,  # never used?
+        down_sampling_rate=1.0,
+    ):
         np_img = HWC3(np_img)
         if down_sampling_rate < 1.1:
             return np_img
@@ -655,36 +639,41 @@ class TileResamplerProcessorInvocation(
 
     def run_processor(self, img):
         np_img = np.array(img, dtype=np.uint8)
-        processed_np_image = self.tile_resample(np_img,
-                                                # res=self.tile_size,
-                                                down_sampling_rate=self.down_sampling_rate
-                                                )
+        processed_np_image = self.tile_resample(
+            np_img,
+            # res=self.tile_size,
+            down_sampling_rate=self.down_sampling_rate,
+        )
         processed_image = Image.fromarray(processed_np_image)
         return processed_image
 
 
-class SegmentAnythingProcessorInvocation(
-        ImageProcessorInvocation, PILInvocationConfig):
+class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
     """Applies segment anything processing to image"""
+
     # fmt: off
     type: Literal["segment_anything_processor"] = "segment_anything_processor"
     # fmt: on
 
     class Config(InvocationConfig):
-        schema_extra = {"ui": {"title": "Segment Anything Processor", "tags": [
-            "controlnet", "segment", "anything", "sam", "image", "processor"]}, }
+        schema_extra = {
+            "ui": {
+                "title": "Segment Anything Processor",
+                "tags": ["controlnet", "segment", "anything", "sam", "image", "processor"],
+            },
+        }
 
     def run_processor(self, image):
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
-            "ybelkada/segment-anything", subfolder="checkpoints")
+            "ybelkada/segment-anything", subfolder="checkpoints"
+        )
         np_img = np.array(image, dtype=np.uint8)
         processed_image = segment_anything_processor(np_img)
         return processed_image
 
 
 class SamDetectorReproducibleColors(SamDetector):
-
     # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
     #     base class show_anns() method randomizes colors,
     #     which seems to also lead to non-reproducible image generation
@@ -692,19 +681,15 @@ class SamDetectorReproducibleColors(SamDetector):
     def show_anns(self, anns: List[Dict]):
         if len(anns) == 0:
             return
-        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
-        h, w = anns[0]['segmentation'].shape
-        final_img = Image.fromarray(
-            np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
+        sorted_anns = sorted(anns, key=(lambda x: x["area"]), reverse=True)
+        h, w = anns[0]["segmentation"].shape
+        final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
         palette = ade_palette()
         for i, ann in enumerate(sorted_anns):
-            m = ann['segmentation']
+            m = ann["segmentation"]
             img = np.empty((m.shape[0], m.shape[1], 3), dtype=np.uint8)
             # doing modulo just in case number of annotated regions exceeds number of colors in palette
             ann_color = palette[i % len(palette)]
             img[:, :] = ann_color
-            final_img.paste(
-                Image.fromarray(img, mode="RGB"),
-                (0, 0),
-                Image.fromarray(np.uint8(m * 255)))
+            final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255)))
         return np.array(final_img, dtype=np.uint8)

invokeai/app/invocations/cv.py

@@ -37,10 +37,7 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "OpenCV Inpaint",
-                "tags": ["opencv", "inpaint"]
-            },
+            "ui": {"title": "OpenCV Inpaint", "tags": ["opencv", "inpaint"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:

invokeai/app/invocations/generate.py

@@ -6,8 +6,7 @@ from typing import Literal, Optional, get_args
 import torch
 from pydantic import Field
 
-from invokeai.app.models.image import (ColorField, ImageCategory, ImageField,
-                                       ResourceOrigin)
+from invokeai.app.models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
 from invokeai.app.util.misc import SEED_MAX, get_random_seed
 from invokeai.backend.generator.inpaint import infill_methods
 
@@ -25,13 +24,12 @@ from contextlib import contextmanager, ExitStack, ContextDecorator
 
 SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
 INFILL_METHODS = Literal[tuple(infill_methods())]
-DEFAULT_INFILL_METHOD = (
-    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
-)
+DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
 from .latent import get_scheduler
 
+
 class OldModelContext(ContextDecorator):
     model: StableDiffusionGeneratorPipeline
 
@@ -44,6 +42,7 @@ class OldModelContext(ContextDecorator):
     def __exit__(self, *exc):
         return False
 
+
 class OldModelInfo:
     name: str
     hash: str
@@ -64,20 +63,34 @@ class InpaintInvocation(BaseInvocation):
 
     positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
     negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
-    seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
-    steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    seed: int = Field(
+        ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed
+    )
+    steps: int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
+    width: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The width of the resulting image",
+    )
+    height: int = Field(
+        default=512,
+        multiple_of=8,
+        gt=0,
+        description="The height of the resulting image",
+    )
+    cfg_scale: float = Field(
+        default=7.5,
+        ge=1,
+        description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt",
+    )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use")
     unet: UNetField = Field(default=None, description="UNet model")
     vae: VaeField = Field(default=None, description="Vae model")
 
     # Inputs
     image: Optional[ImageField] = Field(description="The input image")
-    strength: float = Field(
-        default=0.75, gt=0, le=1, description="The strength of the original image"
-    )
+    strength: float = Field(default=0.75, gt=0, le=1, description="The strength of the original image")
     fit: bool = Field(
         default=True,
         description="Whether or not the result should be fit to the aspect ratio of the input image",
@@ -86,18 +99,10 @@ class InpaintInvocation(BaseInvocation):
     # Inputs
     mask: Optional[ImageField] = Field(description="The mask")
     seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
-    seam_blur: int = Field(
-        default=16, ge=0, description="The seam inpaint blur radius (px)"
-    )
-    seam_strength: float = Field(
-        default=0.75, gt=0, le=1, description="The seam inpaint strength"
-    )
-    seam_steps: int = Field(
-        default=30, ge=1, description="The number of steps to use for seam inpaint"
-    )
-    tile_size: int = Field(
-        default=32, ge=1, description="The tile infill method size (px)"
-    )
+    seam_blur: int = Field(default=16, ge=0, description="The seam inpaint blur radius (px)")
+    seam_strength: float = Field(default=0.75, gt=0, le=1, description="The seam inpaint strength")
+    seam_steps: int = Field(default=30, ge=1, description="The number of steps to use for seam inpaint")
+    tile_size: int = Field(default=32, ge=1, description="The tile infill method size (px)")
     infill_method: INFILL_METHODS = Field(
         default=DEFAULT_INFILL_METHOD,
         description="The method used to infill empty regions (px)",
@@ -128,10 +133,7 @@ class InpaintInvocation(BaseInvocation):
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "tags": ["stable-diffusion", "image"],
-                "title": "Inpaint"
-            },
+            "ui": {"tags": ["stable-diffusion", "image"], "title": "Inpaint"},
         }
 
     def dispatch_progress(
@@ -162,18 +164,23 @@ class InpaintInvocation(BaseInvocation):
         def _lora_loader():
             for lora in self.unet.loras:
                 lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context,)
+                    **lora.dict(exclude={"weight"}),
+                    context=context,
+                )
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
-        
-        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict(), context=context,)
-        vae_info = context.services.model_manager.get_model(**self.vae.vae.dict(), context=context,)
 
-        with vae_info as vae,\
-                ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
-                unet_info as unet:
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict(),
+            context=context,
+        )
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+            context=context,
+        )
 
+        with vae_info as vae, ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()), unet_info as unet:
             device = context.services.model_manager.mgr.cache.execution_device
             dtype = context.services.model_manager.mgr.cache.precision
 
@@ -197,21 +204,11 @@ class InpaintInvocation(BaseInvocation):
             )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = (
-            None
-            if self.image is None
-            else context.services.images.get_pil_image(self.image.image_name)
-        )
-        mask = (
-            None
-            if self.mask is None
-            else context.services.images.get_pil_image(self.mask.image_name)
-        )
+        image = None if self.image is None else context.services.images.get_pil_image(self.image.image_name)
+        mask = None if self.mask is None else context.services.images.get_pil_image(self.mask.image_name)
 
         # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(
-            context.graph_execution_state_id
-        )
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
         source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
         scheduler = get_scheduler(

invokeai/app/invocations/image.py

@@ -4,60 +4,25 @@ from typing import Literal, Optional
 
 import numpy
 from PIL import Image, ImageFilter, ImageOps, ImageChops
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pathlib import Path
 from typing import Union
-
-from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from invokeai.app.invocations.metadata import CoreMetadata
+from ..models.image import (
+    ImageCategory,
+    ImageField,
+    ResourceOrigin,
+    PILInvocationConfig,
+    ImageOutput,
+    MaskOutput,
+)
 from .baseinvocation import (
     BaseInvocation,
-    BaseInvocationOutput,
     InvocationContext,
     InvocationConfig,
 )
-
-
-class PILInvocationConfig(BaseModel):
-    """Helper class to provide all PIL invocations with additional config"""
-
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["PIL", "image"],
-            },
-        }
-
-
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    # fmt: off
-    type: Literal["image_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"]}
-
-
-class MaskOutput(BaseInvocationOutput):
-    """Base class for invocations that output a mask"""
-
-    # fmt: off
-    type: Literal["mask"] = "mask"
-    mask:      ImageField = Field(default=None, description="The output mask")
-    width:            int = Field(description="The width of the mask in pixels")
-    height:           int = Field(description="The height of the mask in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {
-            "required": [
-                "type",
-                "mask",
-            ]
-        }
+from invokeai.backend.image_util.safety_checker import SafetyChecker
+from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 
 
 class LoadImageInvocation(BaseInvocation):
@@ -74,10 +39,7 @@ class LoadImageInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Load Image",
-                "tags": ["image", "load"]
-            },
+            "ui": {"title": "Load Image", "tags": ["image", "load"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -96,16 +58,11 @@ class ShowImageInvocation(BaseInvocation):
     type: Literal["show_image"] = "show_image"
 
     # Inputs
-    image: Optional[ImageField] = Field(
-        default=None, description="The image to show"
-    )
+    image: Optional[ImageField] = Field(default=None, description="The image to show")
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Show Image",
-                "tags": ["image", "show"]
-            },
+            "ui": {"title": "Show Image", "tags": ["image", "show"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -138,18 +95,13 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Crop Image",
-                "tags": ["image", "crop"]
-            },
+            "ui": {"title": "Crop Image", "tags": ["image", "crop"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
-        image_crop = Image.new(
-            mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
-        )
+        image_crop = Image.new(mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0))
         image_crop.paste(image, (-self.x, -self.y))
 
         image_dto = context.services.images.create(
@@ -184,21 +136,14 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Paste Image",
-                "tags": ["image", "paste"]
-            },
+            "ui": {"title": "Paste Image", "tags": ["image", "paste"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         base_image = context.services.images.get_pil_image(self.base_image.image_name)
         image = context.services.images.get_pil_image(self.image.image_name)
         mask = (
-            None
-            if self.mask is None
-            else ImageOps.invert(
-                context.services.images.get_pil_image(self.mask.image_name)
-            )
+            None if self.mask is None else ImageOps.invert(context.services.images.get_pil_image(self.mask.image_name))
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
 
@@ -207,9 +152,7 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
         max_x = max(base_image.width, image.width + self.x)
         max_y = max(base_image.height, image.height + self.y)
 
-        new_image = Image.new(
-            mode="RGBA", size=(max_x - min_x, max_y - min_y), color=(0, 0, 0, 0)
-        )
+        new_image = Image.new(mode="RGBA", size=(max_x - min_x, max_y - min_y), color=(0, 0, 0, 0))
         new_image.paste(base_image, (abs(min_x), abs(min_y)))
         new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
 
@@ -242,10 +185,7 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Mask From Alpha",
-                "tags": ["image", "mask", "alpha"]
-            },
+            "ui": {"title": "Mask From Alpha", "tags": ["image", "mask", "alpha"]},
         }
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
@@ -284,10 +224,7 @@ class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Multiply Images",
-                "tags": ["image", "multiply"]
-            },
+            "ui": {"title": "Multiply Images", "tags": ["image", "multiply"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -328,10 +265,7 @@ class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Image Channel",
-                "tags": ["image", "channel"]
-            },
+            "ui": {"title": "Image Channel", "tags": ["image", "channel"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -371,10 +305,7 @@ class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Convert Image",
-                "tags": ["image", "convert"]
-            },
+            "ui": {"title": "Convert Image", "tags": ["image", "convert"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -412,19 +343,14 @@ class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Blur Image",
-                "tags": ["image", "blur"]
-            },
+            "ui": {"title": "Blur Image", "tags": ["image", "blur"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
         blur = (
-            ImageFilter.GaussianBlur(self.radius)
-            if self.blur_type == "gaussian"
-            else ImageFilter.BoxBlur(self.radius)
+            ImageFilter.GaussianBlur(self.radius) if self.blur_type == "gaussian" else ImageFilter.BoxBlur(self.radius)
         )
         blur_image = image.filter(blur)
 
@@ -479,10 +405,7 @@ class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Resize Image",
-                "tags": ["image", "resize"]
-            },
+            "ui": {"title": "Resize Image", "tags": ["image", "resize"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -525,10 +448,7 @@ class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Scale Image",
-                "tags": ["image", "scale"]
-            },
+            "ui": {"title": "Scale Image", "tags": ["image", "scale"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -573,10 +493,7 @@ class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Image Linear Interpolation",
-                "tags": ["image", "linear", "interpolation", "lerp"]
-            },
+            "ui": {"title": "Image Linear Interpolation", "tags": ["image", "linear", "interpolation", "lerp"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -619,7 +536,7 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
         schema_extra = {
             "ui": {
                 "title": "Image Inverse Linear Interpolation",
-                "tags": ["image", "linear", "interpolation", "inverse"]
+                "tags": ["image", "linear", "interpolation", "inverse"],
             },
         }
 
@@ -627,12 +544,7 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
         image = context.services.images.get_pil_image(self.image.image_name)
 
         image_arr = numpy.asarray(image, dtype=numpy.float32)
-        image_arr = (
-            numpy.minimum(
-                numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1
-            )
-            * 255
-        )
+        image_arr = numpy.minimum(numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1) * 255
 
         ilerp_image = Image.fromarray(numpy.uint8(image_arr))
 
@@ -650,3 +562,91 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
             width=image_dto.width,
             height=image_dto.height,
         )
+
+
+class ImageNSFWBlurInvocation(BaseInvocation, PILInvocationConfig):
+    """Add blur to NSFW-flagged images"""
+
+    # fmt: off
+    type: Literal["img_nsfw"] = "img_nsfw"
+
+    # Inputs
+    image: Optional[ImageField]  = Field(default=None, description="The image to check")
+    metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")    
+    # fmt: on
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {"title": "Blur NSFW Images", "tags": ["image", "nsfw", "checker"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+
+        logger = context.services.logger
+        logger.debug("Running NSFW checker")
+        if SafetyChecker.has_nsfw_concept(image):
+            logger.info("A potentially NSFW image has been detected. Image will be blurred.")
+            blurry_image = image.filter(filter=ImageFilter.GaussianBlur(radius=32))
+            caution = self._get_caution_img()
+            blurry_image.paste(caution, (0, 0), caution)
+            image = blurry_image
+
+        image_dto = context.services.images.create(
+            image=image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            metadata=self.metadata.dict() if self.metadata else None,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+    def _get_caution_img(self) -> Image:
+        import invokeai.app.assets.images as image_assets
+
+        caution = Image.open(Path(image_assets.__path__[0]) / "caution.png")
+        return caution.resize((caution.width // 2, caution.height // 2))
+
+
+class ImageWatermarkInvocation(BaseInvocation, PILInvocationConfig):
+    """Add an invisible watermark to an image"""
+
+    # fmt: off
+    type: Literal["img_watermark"] = "img_watermark"
+
+    # Inputs
+    image: Optional[ImageField]  = Field(default=None, description="The image to check")
+    text: str = Field(default='InvokeAI', description="Watermark text")
+    metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")    
+    # fmt: on
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {"title": "Add Invisible Watermark", "tags": ["image", "watermark", "invisible"]},
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get_pil_image(self.image.image_name)
+        new_image = InvisibleWatermark.add_watermark(image, self.text)
+        image_dto = context.services.images.create(
+            image=new_image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            metadata=self.metadata.dict() if self.metadata else None,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )

invokeai/app/invocations/infill.py

@@ -30,9 +30,7 @@ def infill_methods() -> list[str]:
 
 
 INFILL_METHODS = Literal[tuple(infill_methods())]
-DEFAULT_INFILL_METHOD = (
-    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
-)
+DEFAULT_INFILL_METHOD = "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
 
 
 def infill_patchmatch(im: Image.Image) -> Image.Image:
@@ -44,9 +42,7 @@ def infill_patchmatch(im: Image.Image) -> Image.Image:
         return im
 
     # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
-    im_patched_np = PatchMatch.inpaint(
-        im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3
-    )
+    im_patched_np = PatchMatch.inpaint(im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3)
     im_patched = Image.fromarray(im_patched_np, mode="RGB")
     return im_patched
 
@@ -68,9 +64,7 @@ def get_tile_images(image: np.ndarray, width=8, height=8):
     )
 
 
-def tile_fill_missing(
-    im: Image.Image, tile_size: int = 16, seed: Optional[int] = None
-) -> Image.Image:
+def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int] = None) -> Image.Image:
     # Only fill if there's an alpha layer
     if im.mode != "RGBA":
         return im
@@ -103,9 +97,7 @@ def tile_fill_missing(
     # Find all invalid tiles and replace with a random valid tile
     replace_count = (tiles_mask == False).sum()
     rng = np.random.default_rng(seed=seed)
-    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[
-        rng.choice(filtered_tiles.shape[0], replace_count), :, :, :
-    ]
+    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[rng.choice(filtered_tiles.shape[0], replace_count), :, :, :]
 
     # Convert back to an image
     tiles_all = tiles_all.reshape(tshape)
@@ -126,9 +118,7 @@ class InfillColorInvocation(BaseInvocation):
     """Infills transparent areas of an image with a solid color"""
 
     type: Literal["infill_rgba"] = "infill_rgba"
-    image: Optional[ImageField] = Field(
-        default=None, description="The image to infill"
-    )
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
     color: ColorField = Field(
         default=ColorField(r=127, g=127, b=127, a=255),
         description="The color to use to infill",
@@ -136,10 +126,7 @@ class InfillColorInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Color Infill",
-                "tags": ["image", "inpaint", "color", "infill"]
-            },
+            "ui": {"title": "Color Infill", "tags": ["image", "inpaint", "color", "infill"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
@@ -171,9 +158,7 @@ class InfillTileInvocation(BaseInvocation):
 
     type: Literal["infill_tile"] = "infill_tile"
 
-    image: Optional[ImageField] = Field(
-        default=None, description="The image to infill"
-    )
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
     tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
     seed: int = Field(
         ge=0,
@@ -184,18 +169,13 @@ class InfillTileInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Tile Infill",
-                "tags": ["image", "inpaint", "tile", "infill"]
-            },
+            "ui": {"title": "Tile Infill", "tags": ["image", "inpaint", "tile", "infill"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get_pil_image(self.image.image_name)
 
-        infilled = tile_fill_missing(
-            image.copy(), seed=self.seed, tile_size=self.tile_size
-        )
+        infilled = tile_fill_missing(image.copy(), seed=self.seed, tile_size=self.tile_size)
         infilled.paste(image, (0, 0), image.split()[-1])
 
         image_dto = context.services.images.create(
@@ -219,16 +199,11 @@ class InfillPatchMatchInvocation(BaseInvocation):
 
     type: Literal["infill_patchmatch"] = "infill_patchmatch"
 
-    image: Optional[ImageField] = Field(
-        default=None, description="The image to infill"
-    )
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Patch Match Infill",
-                "tags": ["image", "inpaint", "patchmatch", "infill"]
-            },
+            "ui": {"title": "Patch Match Infill", "tags": ["image", "inpaint", "patchmatch", "infill"]},
         }
 
     def invoke(self, context: InvocationContext) -> ImageOutput:

invokeai/app/invocations/latent.py

@@ -12,24 +12,27 @@ from pydantic import BaseModel, Field, validator
 
 from invokeai.app.invocations.metadata import CoreMetadata
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
-from invokeai.backend.model_management.models.base import ModelType
+from invokeai.backend.model_management.models import ModelType, SilenceWarnings
 
 from ...backend.model_management.lora import ModelPatcher
 from ...backend.stable_diffusion import PipelineIntermediateState
 from ...backend.stable_diffusion.diffusers_pipeline import (
-    ConditioningData, ControlNetData, StableDiffusionGeneratorPipeline,
-    image_resized_to_grid_as_tensor)
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import \
-    PostprocessingSettings
+    ConditioningData,
+    ControlNetData,
+    StableDiffusionGeneratorPipeline,
+    image_resized_to_grid_as_tensor,
+)
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
-from ...backend.util.devices import torch_dtype
+from ...backend.model_management import ModelPatcher
+from ...backend.util.devices import choose_torch_device, torch_dtype, choose_precision
 from ..models.image import ImageCategory, ImageField, ResourceOrigin
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 from .compel import ConditioningField
 from .controlnet_image_processors import ControlField
 from .image import ImageOutput
 from .model import ModelInfo, UNetField, VaeField
+from invokeai.app.util.controlnet_utils import prepare_control_image
 
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
@@ -39,11 +42,13 @@ from diffusers.models.attention_processor import (
 )
 
 
+DEFAULT_PRECISION = choose_precision(choose_torch_device())
+
+
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
 
-    latents_name: Optional[str] = Field(
-        default=None, description="The name of the latents")
+    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
 
     class Config:
         schema_extra = {"required": ["latents_name"]}
@@ -51,14 +56,15 @@ class LatentsField(BaseModel):
 
 class LatentsOutput(BaseInvocationOutput):
     """Base class for invocations that output latents"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["latents_output"] = "latents_output"
 
     # Inputs
     latents: LatentsField          = Field(default=None, description="The output latents")
     width:                     int = Field(description="The width of the latents in pixels")
     height:                    int = Field(description="The height of the latents in pixels")
-    #fmt: on
+    # fmt: on
 
 
 def build_latents_output(latents_name: str, latents: torch.Tensor):
@@ -69,9 +75,7 @@ def build_latents_output(latents_name: str, latents: torch.Tensor):
     )
 
 
-SAMPLER_NAME_VALUES = Literal[
-    tuple(list(SCHEDULER_MAP.keys()))
-]
+SAMPLER_NAME_VALUES = Literal[tuple(list(SCHEDULER_MAP.keys()))]
 
 
 def get_scheduler(
@@ -79,11 +83,10 @@ def get_scheduler(
     scheduler_info: ModelInfo,
     scheduler_name: str,
 ) -> Scheduler:
-    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(
-        scheduler_name, SCHEDULER_MAP['ddim']
-    )
+    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
     orig_scheduler_info = context.services.model_manager.get_model(
-        **scheduler_info.dict(), context=context,
+        **scheduler_info.dict(),
+        context=context,
     )
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
@@ -98,7 +101,7 @@ def get_scheduler(
     scheduler = scheduler_class.from_config(scheduler_config)
 
     # hack copied over from generate.py
-    if not hasattr(scheduler, 'uses_inpainting_model'):
+    if not hasattr(scheduler, "uses_inpainting_model"):
         scheduler.uses_inpainting_model = lambda: False
     return scheduler
 
@@ -119,8 +122,8 @@ class TextToLatentsInvocation(BaseInvocation):
     scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
     unet: UNetField = Field(default=None, description="UNet submodel")
     control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
-    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    # seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    # seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
     # fmt: on
 
     @validator("cfg_scale")
@@ -129,10 +132,10 @@ class TextToLatentsInvocation(BaseInvocation):
         if isinstance(v, list):
             for i in v:
                 if i < 1:
-                    raise ValueError('cfg_scale must be greater than 1')
+                    raise ValueError("cfg_scale must be greater than 1")
         else:
             if v < 1:
-                raise ValueError('cfg_scale must be greater than 1')
+                raise ValueError("cfg_scale must be greater than 1")
         return v
 
     # Schema customisation
@@ -145,8 +148,8 @@ class TextToLatentsInvocation(BaseInvocation):
                     "model": "model",
                     "control": "control",
                     # "cfg_scale": "float",
-                    "cfg_scale": "number"
-                }
+                    "cfg_scale": "number",
+                },
             },
         }
 
@@ -186,16 +189,14 @@ class TextToLatentsInvocation(BaseInvocation):
                 threshold=0.0,  # threshold,
                 warmup=0.2,  # warmup,
                 h_symmetry_time_pct=None,  # h_symmetry_time_pct,
-                v_symmetry_time_pct=None  # v_symmetry_time_pct,
+                v_symmetry_time_pct=None,  # v_symmetry_time_pct,
             ),
         )
 
         conditioning_data = conditioning_data.add_scheduler_args_if_applicable(
             scheduler,
-
             # for ddim scheduler
             eta=0.0,  # ddim_eta
-
             # for ancestral and sde schedulers
             generator=torch.Generator(device=unet.device).manual_seed(0),
         )
@@ -243,7 +244,6 @@ class TextToLatentsInvocation(BaseInvocation):
         exit_stack: ExitStack,
         do_classifier_free_guidance: bool = True,
     ) -> List[ControlNetData]:
-
         # assuming fixed dimensional scaling of 8:1 for image:latents
         control_height_resize = latents_shape[2] * 8
         control_width_resize = latents_shape[3] * 8
@@ -257,7 +257,7 @@ class TextToLatentsInvocation(BaseInvocation):
             control_list = control_input
         else:
             control_list = None
-        if (control_list is None):
+        if control_list is None:
             control_data = None
             # from above handling, any control that is not None should now be of type list[ControlField]
         else:
@@ -277,15 +277,13 @@ class TextToLatentsInvocation(BaseInvocation):
 
                 control_models.append(control_model)
                 control_image_field = control_info.image
-                input_image = context.services.images.get_pil_image(
-                    control_image_field.image_name
-                )
+                input_image = context.services.images.get_pil_image(control_image_field.image_name)
                 # self.image.image_type, self.image.image_name
                 # FIXME: still need to test with different widths, heights, devices, dtypes
                 #        and add in batch_size, num_images_per_prompt?
                 #        and do real check for classifier_free_guidance?
                 # prepare_control_image should return torch.Tensor of shape(batch_size, 3, height, width)
-                control_image = model.prepare_control_image(
+                control_image = prepare_control_image(
                     image=input_image,
                     do_classifier_free_guidance=do_classifier_free_guidance,
                     width=control_width_resize,
@@ -295,13 +293,18 @@ class TextToLatentsInvocation(BaseInvocation):
                     device=control_model.device,
                     dtype=control_model.dtype,
                     control_mode=control_info.control_mode,
+                    resize_mode=control_info.resize_mode,
                 )
                 control_item = ControlNetData(
-                    model=control_model, image_tensor=control_image,
+                    model=control_model,
+                    image_tensor=control_image,
                     weight=control_info.control_weight,
                     begin_step_percent=control_info.begin_step_percent,
                     end_step_percent=control_info.end_step_percent,
                     control_mode=control_info.control_mode,
+                    # any resizing needed should currently be happening in prepare_control_image(),
+                    #    but adding resize_mode to ControlNetData in case needed in the future
+                    resize_mode=control_info.resize_mode,
                 )
                 control_data.append(control_item)
                 # MultiControlNetModel has been refactored out, just need list[ControlNetData]
@@ -309,69 +312,71 @@ class TextToLatentsInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
+        with SilenceWarnings():
+            noise = context.services.latents.get(self.noise.latents_name)
 
-        # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(
-            context.graph_execution_state_id
-        )
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+            # Get the source node id (we are invoking the prepared node)
+            graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+            source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, source_node_id, state)
+            def step_callback(state: PipelineIntermediateState):
+                self.dispatch_progress(context, source_node_id, state)
 
-        def _lora_loader():
-            for lora in self.unet.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context,
-                )
-                yield (lora_info.context.model, lora.weight)
-                del lora_info
-            return
+            def _lora_loader():
+                for lora in self.unet.loras:
+                    lora_info = context.services.model_manager.get_model(
+                        **lora.dict(exclude={"weight"}),
+                        context=context,
+                    )
+                    yield (lora_info.context.model, lora.weight)
+                    del lora_info
+                return
 
-        unet_info = context.services.model_manager.get_model(
-            **self.unet.unet.dict(), context=context,
-        )
-        with ExitStack() as exit_stack,\
-                ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
-                unet_info as unet:
-
-            noise = noise.to(device=unet.device, dtype=unet.dtype)
-
-            scheduler = get_scheduler(
+            unet_info = context.services.model_manager.get_model(
+                **self.unet.unet.dict(),
                 context=context,
-                scheduler_info=self.unet.scheduler,
-                scheduler_name=self.scheduler,
             )
+            with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
+                unet_info.context.model, _lora_loader()
+            ), unet_info as unet:
+                noise = noise.to(device=unet.device, dtype=unet.dtype)
 
-            pipeline = self.create_pipeline(unet, scheduler)
-            conditioning_data = self.get_conditioning_data(context, scheduler, unet)
+                scheduler = get_scheduler(
+                    context=context,
+                    scheduler_info=self.unet.scheduler,
+                    scheduler_name=self.scheduler,
+                )
 
-            control_data = self.prep_control_data(
-                model=pipeline, context=context, control_input=self.control,
-                latents_shape=noise.shape,
-                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                do_classifier_free_guidance=True,
-                exit_stack=exit_stack,
-            )
+                pipeline = self.create_pipeline(unet, scheduler)
+                conditioning_data = self.get_conditioning_data(context, scheduler, unet)
 
-            # TODO: Verify the noise is the right size
-            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
-                latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
-                noise=noise,
-                num_inference_steps=self.steps,
-                conditioning_data=conditioning_data,
-                control_data=control_data,  # list[ControlNetData]
-                callback=step_callback,
-            )
+                control_data = self.prep_control_data(
+                    model=pipeline,
+                    context=context,
+                    control_input=self.control,
+                    latents_shape=noise.shape,
+                    # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                    do_classifier_free_guidance=True,
+                    exit_stack=exit_stack,
+                )
 
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        result_latents = result_latents.to("cpu")
-        torch.cuda.empty_cache()
+                # TODO: Verify the noise is the right size
+                result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                    latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
+                    noise=noise,
+                    num_inference_steps=self.steps,
+                    conditioning_data=conditioning_data,
+                    control_data=control_data,  # list[ControlNetData]
+                    callback=step_callback,
+                )
 
-        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)
+            # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+            result_latents = result_latents.to("cpu")
+            torch.cuda.empty_cache()
+
+            name = f"{context.graph_execution_state_id}__{self.id}"
+            context.services.latents.save(name, result_latents)
+            return build_latents_output(latents_name=name, latents=result_latents)
 
 
 class LatentsToLatentsInvocation(TextToLatentsInvocation):
@@ -380,11 +385,8 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
     type: Literal["l2l"] = "l2l"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(
-        description="The latents to use as a base image")
-    strength: float = Field(
-        default=0.7, ge=0, le=1,
-        description="The strength of the latents to use")
+    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
+    strength: float = Field(default=0.7, ge=0, le=1, description="The strength of the latents to use")
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -396,87 +398,89 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
                     "model": "model",
                     "control": "control",
                     "cfg_scale": "number",
-                }
+                },
             },
         }
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-        latent = context.services.latents.get(self.latents.latents_name)
+        with SilenceWarnings():  # this quenches NSFW nag from diffusers
+            noise = context.services.latents.get(self.noise.latents_name)
+            latent = context.services.latents.get(self.latents.latents_name)
 
-        # Get the source node id (we are invoking the prepared node)
-        graph_execution_state = context.services.graph_execution_manager.get(
-            context.graph_execution_state_id
-        )
-        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+            # Get the source node id (we are invoking the prepared node)
+            graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+            source_node_id = graph_execution_state.prepared_source_mapping[self.id]
 
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, source_node_id, state)
+            def step_callback(state: PipelineIntermediateState):
+                self.dispatch_progress(context, source_node_id, state)
 
-        def _lora_loader():
-            for lora in self.unet.loras:
-                lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context,
-                )
-                yield (lora_info.context.model, lora.weight)
-                del lora_info
-            return
+            def _lora_loader():
+                for lora in self.unet.loras:
+                    lora_info = context.services.model_manager.get_model(
+                        **lora.dict(exclude={"weight"}),
+                        context=context,
+                    )
+                    yield (lora_info.context.model, lora.weight)
+                    del lora_info
+                return
 
-        unet_info = context.services.model_manager.get_model(
-            **self.unet.unet.dict(), context=context,
-        )
-        with ExitStack() as exit_stack,\
-                ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),\
-                unet_info as unet:
-
-            noise = noise.to(device=unet.device, dtype=unet.dtype)
-            latent = latent.to(device=unet.device, dtype=unet.dtype)
-
-            scheduler = get_scheduler(
+            unet_info = context.services.model_manager.get_model(
+                **self.unet.unet.dict(),
                 context=context,
-                scheduler_info=self.unet.scheduler,
-                scheduler_name=self.scheduler,
             )
+            with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
+                unet_info.context.model, _lora_loader()
+            ), unet_info as unet:
+                noise = noise.to(device=unet.device, dtype=unet.dtype)
+                latent = latent.to(device=unet.device, dtype=unet.dtype)
 
-            pipeline = self.create_pipeline(unet, scheduler)
-            conditioning_data = self.get_conditioning_data(context, scheduler, unet)
+                scheduler = get_scheduler(
+                    context=context,
+                    scheduler_info=self.unet.scheduler,
+                    scheduler_name=self.scheduler,
+                )
 
-            control_data = self.prep_control_data(
-                model=pipeline, context=context, control_input=self.control,
-                latents_shape=noise.shape,
-                # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
-                do_classifier_free_guidance=True,
-                exit_stack=exit_stack,
-            )
+                pipeline = self.create_pipeline(unet, scheduler)
+                conditioning_data = self.get_conditioning_data(context, scheduler, unet)
 
-            # TODO: Verify the noise is the right size
-            initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-                latent, device=unet.device, dtype=latent.dtype
-            )
+                control_data = self.prep_control_data(
+                    model=pipeline,
+                    context=context,
+                    control_input=self.control,
+                    latents_shape=noise.shape,
+                    # do_classifier_free_guidance=(self.cfg_scale >= 1.0))
+                    do_classifier_free_guidance=True,
+                    exit_stack=exit_stack,
+                )
 
-            timesteps, _ = pipeline.get_img2img_timesteps(
-                self.steps,
-                self.strength,
-                device=unet.device,
-            )
+                # TODO: Verify the noise is the right size
+                initial_latents = (
+                    latent if self.strength < 1.0 else torch.zeros_like(latent, device=unet.device, dtype=latent.dtype)
+                )
 
-            result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
-                latents=initial_latents,
-                timesteps=timesteps,
-                noise=noise,
-                num_inference_steps=self.steps,
-                conditioning_data=conditioning_data,
-                control_data=control_data,  # list[ControlNetData]
-                callback=step_callback
-            )
+                timesteps, _ = pipeline.get_img2img_timesteps(
+                    self.steps,
+                    self.strength,
+                    device=unet.device,
+                )
 
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        result_latents = result_latents.to("cpu")
-        torch.cuda.empty_cache()
+                result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
+                    latents=initial_latents,
+                    timesteps=timesteps,
+                    noise=noise,
+                    num_inference_steps=self.steps,
+                    conditioning_data=conditioning_data,
+                    control_data=control_data,  # list[ControlNetData]
+                    callback=step_callback,
+                )
 
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.save(name, result_latents)
+            # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+            result_latents = result_latents.to("cpu")
+            torch.cuda.empty_cache()
+
+            name = f"{context.graph_execution_state_id}__{self.id}"
+            context.services.latents.save(name, result_latents)
         return build_latents_output(latents_name=name, latents=result_latents)
 
 
@@ -487,14 +491,13 @@ class LatentsToImageInvocation(BaseInvocation):
     type: Literal["l2i"] = "l2i"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(
-        description="The latents to generate an image from")
+    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
     vae: VaeField = Field(default=None, description="Vae submodel")
-    tiled: bool = Field(
-        default=False,
-        description="Decode latents by overlaping tiles(less memory consumption)")
-    fp32: bool = Field(False, description="Decode in full precision")
-    metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")
+    tiled: bool = Field(default=False, description="Decode latents by overlaping tiles (less memory consumption)")
+    fp32: bool = Field(DEFAULT_PRECISION == "float32", description="Decode in full precision")
+    metadata: Optional[CoreMetadata] = Field(
+        default=None, description="Optional core metadata to be written to the image"
+    )
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -510,7 +513,8 @@ class LatentsToImageInvocation(BaseInvocation):
         latents = context.services.latents.get(self.latents.latents_name)
 
         vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(), context=context,
+            **self.vae.vae.dict(),
+            context=context,
         )
 
         with vae_info as vae:
@@ -577,8 +581,7 @@ class LatentsToImageInvocation(BaseInvocation):
         )
 
 
-LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear",
-                                     "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
+LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
 
 
 class ResizeLatentsInvocation(BaseInvocation):
@@ -587,36 +590,30 @@ class ResizeLatentsInvocation(BaseInvocation):
     type: Literal["lresize"] = "lresize"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(
-        description="The latents to resize")
-    width:                         Union[int, None] = Field(default=512,
-        ge=64, multiple_of=8, description="The width to resize to (px)")
-    height:                        Union[int, None] = Field(default=512,
-        ge=64, multiple_of=8, description="The height to resize to (px)")
-    mode:   LATENTS_INTERPOLATION_MODE = Field(
-        default="bilinear", description="The interpolation mode")
+    latents: Optional[LatentsField] = Field(description="The latents to resize")
+    width: Union[int, None] = Field(default=512, ge=64, multiple_of=8, description="The width to resize to (px)")
+    height: Union[int, None] = Field(default=512, ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode: LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
     antialias: bool = Field(
-        default=False,
-        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
-    
+        default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)"
+    )
+
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Resize Latents",
-                "tags": ["latents", "resize"]
-            },
+            "ui": {"title": "Resize Latents", "tags": ["latents", "resize"]},
         }
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
         # TODO:
-        device=choose_torch_device()
+        device = choose_torch_device()
 
         resized_latents = torch.nn.functional.interpolate(
-            latents.to(device), size=(self.height // 8, self.width // 8),
-            mode=self.mode, antialias=self.antialias
-            if self.mode in ["bilinear", "bicubic"] else False,
+            latents.to(device),
+            size=(self.height // 8, self.width // 8),
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
         )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
@@ -635,35 +632,30 @@ class ScaleLatentsInvocation(BaseInvocation):
     type: Literal["lscale"] = "lscale"
 
     # Inputs
-    latents: Optional[LatentsField] = Field(
-        description="The latents to scale")
-    scale_factor:               float = Field(
-        gt=0, description="The factor by which to scale the latents")
-    mode:  LATENTS_INTERPOLATION_MODE = Field(
-        default="bilinear", description="The interpolation mode")
+    latents: Optional[LatentsField] = Field(description="The latents to scale")
+    scale_factor: float = Field(gt=0, description="The factor by which to scale the latents")
+    mode: LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
     antialias: bool = Field(
-        default=False,
-        description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
-    
+        default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)"
+    )
+
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Scale Latents",
-                "tags": ["latents", "scale"]
-            },
+            "ui": {"title": "Scale Latents", "tags": ["latents", "scale"]},
         }
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents = context.services.latents.get(self.latents.latents_name)
 
         # TODO:
-        device=choose_torch_device()
+        device = choose_torch_device()
 
         # resizing
         resized_latents = torch.nn.functional.interpolate(
-            latents.to(device), scale_factor=self.scale_factor, mode=self.mode,
-            antialias=self.antialias
-            if self.mode in ["bilinear", "bicubic"] else False,
+            latents.to(device),
+            scale_factor=self.scale_factor,
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
         )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
@@ -684,19 +676,13 @@ class ImageToLatentsInvocation(BaseInvocation):
     # Inputs
     image: Optional[ImageField] = Field(description="The image to encode")
     vae: VaeField = Field(default=None, description="Vae submodel")
-    tiled: bool = Field(
-        default=False,
-        description="Encode latents by overlaping tiles(less memory consumption)")
-    fp32: bool = Field(False, description="Decode in full precision")
-
+    tiled: bool = Field(default=False, description="Encode latents by overlaping tiles(less memory consumption)")
+    fp32: bool = Field(DEFAULT_PRECISION == "float32", description="Decode in full precision")
 
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Image To Latents",
-                "tags": ["latents", "image"]
-            },
+            "ui": {"title": "Image To Latents", "tags": ["latents", "image"]},
         }
 
     @torch.no_grad()
@@ -706,9 +692,10 @@ class ImageToLatentsInvocation(BaseInvocation):
         # )
         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())
         vae_info = context.services.model_manager.get_model(
-            **self.vae.vae.dict(), context=context,
+            **self.vae.vae.dict(),
+            context=context,
         )
 
         image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
@@ -735,12 +722,12 @@ class ImageToLatentsInvocation(BaseInvocation):
                     vae.post_quant_conv.to(orig_dtype)
                     vae.decoder.conv_in.to(orig_dtype)
                     vae.decoder.mid_block.to(orig_dtype)
-                #else:
+                # else:
                 #    latents = latents.float()
 
             else:
                 vae.to(dtype=torch.float16)
-                #latents = latents.half()
+                # latents = latents.half()
 
             if self.tiled:
                 vae.enable_tiling()
@@ -751,11 +738,9 @@ class ImageToLatentsInvocation(BaseInvocation):
             image_tensor = image_tensor.to(device=vae.device, dtype=vae.dtype)
             with torch.inference_mode():
                 image_tensor_dist = vae.encode(image_tensor).latent_dist
-                latents = image_tensor_dist.sample().to(
-                    dtype=vae.dtype
-                )  # FIXME: uses torch.randn. make reproducible!
+                latents = image_tensor_dist.sample().to(dtype=vae.dtype)  # FIXME: uses torch.randn. make reproducible!
 
-            latents = 0.18215 * latents
+            latents = vae.config.scaling_factor * latents
             latents = latents.to(dtype=orig_dtype)
 
         name = f"{context.graph_execution_state_id}__{self.id}"

invokeai/app/invocations/math.py

@@ -54,10 +54,7 @@ class AddInvocation(BaseInvocation, MathInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Add",
-                "tags": ["math", "add"]
-            },
+            "ui": {"title": "Add", "tags": ["math", "add"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntOutput:
@@ -75,10 +72,7 @@ class SubtractInvocation(BaseInvocation, MathInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Subtract",
-                "tags": ["math", "subtract"]
-            },
+            "ui": {"title": "Subtract", "tags": ["math", "subtract"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntOutput:
@@ -96,10 +90,7 @@ class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Multiply",
-                "tags": ["math", "multiply"]
-            },
+            "ui": {"title": "Multiply", "tags": ["math", "multiply"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntOutput:
@@ -117,10 +108,7 @@ class DivideInvocation(BaseInvocation, MathInvocationConfig):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Divide",
-                "tags": ["math", "divide"]
-            },
+            "ui": {"title": "Divide", "tags": ["math", "divide"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntOutput:
@@ -140,10 +128,7 @@ class RandomIntInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Random Integer",
-                "tags": ["math", "random", "integer"]
-            },
+            "ui": {"title": "Random Integer", "tags": ["math", "random", "integer"]},
         }
 
     def invoke(self, context: InvocationContext) -> IntOutput:

invokeai/app/invocations/metadata.py

@@ -2,16 +2,19 @@ from typing import Literal, Optional, Union
 
 from pydantic import BaseModel, Field
 
-from invokeai.app.invocations.baseinvocation import (BaseInvocation,
-                                                     BaseInvocationOutput, InvocationConfig,
-                                                     InvocationContext)
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationConfig,
+    InvocationContext,
+)
 from invokeai.app.invocations.controlnet_image_processors import ControlField
-from invokeai.app.invocations.model import (LoRAModelField, MainModelField,
-                                            VAEModelField)
+from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
 
 
 class LoRAMetadataField(BaseModel):
     """LoRA metadata for an image generated in InvokeAI."""
+
     lora: LoRAModelField = Field(description="The LoRA model")
     weight: float = Field(description="The weight of the LoRA model")
 
@@ -19,7 +22,9 @@ class LoRAMetadataField(BaseModel):
 class CoreMetadata(BaseModel):
     """Core generation metadata for an image generated in InvokeAI."""
 
-    generation_mode: str = Field(description="The generation mode that output this image",)
+    generation_mode: str = Field(
+        description="The generation mode that output this 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")
@@ -29,22 +34,41 @@ class CoreMetadata(BaseModel):
     cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
     steps: int = Field(description="The number of steps used for inference")
     scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: int = Field(description="The number of skipped CLIP layers",)
+    clip_skip: int = Field(
+        description="The number of skipped CLIP layers",
+    )
     model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField]= Field(description="The ControlNets used for inference")
+    controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
     loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
-    strength: Union[float, None] = Field(
-        default=None,
-        description="The strength used for latents-to-latents",
-    )
-    init_image: Union[str, None] = Field(
-        default=None, description="The name of the initial image"
-    )
     vae: Union[VAEModelField, None] = Field(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
+    # Latents-to-Latents
+    strength: Union[float, None] = Field(
+        default=None,
+        description="The strength used for latents-to-latents",
+    )
+    init_image: Union[str, None] = Field(default=None, description="The name of the initial image")
+
+    # SDXL
+    positive_style_prompt: Union[str, None] = Field(default=None, description="The positive style prompt parameter")
+    negative_style_prompt: Union[str, None] = Field(default=None, description="The negative style prompt parameter")
+
+    # SDXL Refiner
+    refiner_model: Union[MainModelField, None] = Field(default=None, description="The SDXL Refiner model used")
+    refiner_cfg_scale: Union[float, None] = Field(
+        default=None,
+        description="The classifier-free guidance scale parameter used for the refiner",
+    )
+    refiner_steps: Union[int, None] = Field(default=None, description="The number of steps used for the refiner")
+    refiner_scheduler: Union[str, None] = Field(default=None, description="The scheduler used for the refiner")
+    refiner_aesthetic_store: Union[float, None] = Field(
+        default=None, description="The aesthetic score used for the refiner"
+    )
+    refiner_start: Union[float, None] = Field(default=None, description="The start value used for refiner denoising")
+
 
 class ImageMetadata(BaseModel):
     """An image's generation metadata"""
@@ -53,9 +77,7 @@ class ImageMetadata(BaseModel):
         default=None,
         description="The image's core metadata, if it was created in the Linear or Canvas UI",
     )
-    graph: Optional[dict] = Field(
-        default=None, description="The graph that created the image"
-    )
+    graph: Optional[dict] = Field(default=None, description="The graph that created the image")
 
 
 class MetadataAccumulatorOutput(BaseInvocationOutput):
@@ -71,7 +93,9 @@ class MetadataAccumulatorInvocation(BaseInvocation):
 
     type: Literal["metadata_accumulator"] = "metadata_accumulator"
 
-    generation_mode: str = Field(description="The generation mode that output this image",)
+    generation_mode: str = Field(
+        description="The generation mode that output this 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")
@@ -81,52 +105,48 @@ class MetadataAccumulatorInvocation(BaseInvocation):
     cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
     steps: int = Field(description="The number of steps used for inference")
     scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: int = Field(description="The number of skipped CLIP layers",)
+    clip_skip: int = Field(
+        description="The number of skipped CLIP layers",
+    )
     model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField]= Field(description="The ControlNets used for inference")
+    controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
     loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
     strength: Union[float, None] = Field(
         default=None,
         description="The strength used for latents-to-latents",
     )
-    init_image: Union[str, None] = Field(
-        default=None, description="The name of the initial image"
-    )
+    init_image: Union[str, None] = Field(default=None, description="The name of the initial image")
     vae: Union[VAEModelField, None] = Field(
         default=None,
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
+    # SDXL
+    positive_style_prompt: Union[str, None] = Field(default=None, description="The positive style prompt parameter")
+    negative_style_prompt: Union[str, None] = Field(default=None, description="The negative style prompt parameter")
+
+    # SDXL Refiner
+    refiner_model: Union[MainModelField, None] = Field(default=None, description="The SDXL Refiner model used")
+    refiner_cfg_scale: Union[float, None] = Field(
+        default=None,
+        description="The classifier-free guidance scale parameter used for the refiner",
+    )
+    refiner_steps: Union[int, None] = Field(default=None, description="The number of steps used for the refiner")
+    refiner_scheduler: Union[str, None] = Field(default=None, description="The scheduler used for the refiner")
+    refiner_aesthetic_store: Union[float, None] = Field(
+        default=None, description="The aesthetic score used for the refiner"
+    )
+    refiner_start: Union[float, None] = Field(default=None, description="The start value used for refiner denoising")
+
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "title": "Metadata Accumulator",
-                "tags": ["image", "metadata", "generation"]
+                "tags": ["image", "metadata", "generation"],
             },
         }
 
-
     def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataAccumulatorOutput(
-            metadata=CoreMetadata(
-                generation_mode=self.generation_mode,
-                positive_prompt=self.positive_prompt,
-                negative_prompt=self.negative_prompt,
-                width=self.width,
-                height=self.height,
-                seed=self.seed,
-                rand_device=self.rand_device,
-                cfg_scale=self.cfg_scale,
-                steps=self.steps,
-                scheduler=self.scheduler,
-                model=self.model,
-                strength=self.strength,
-                init_image=self.init_image,
-                vae=self.vae,
-                controlnets=self.controlnets,
-                loras=self.loras,
-                clip_skip=self.clip_skip,
-            )
-        )
+        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.dict()))

invokeai/app/invocations/model.py

@@ -4,17 +4,14 @@ from typing import List, Literal, Optional, Union
 from pydantic import BaseModel, Field
 
 from ...backend.model_management import BaseModelType, ModelType, SubModelType
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 
 
 class ModelInfo(BaseModel):
     model_name: str = Field(description="Info to load submodel")
     base_model: BaseModelType = Field(description="Base model")
     model_type: ModelType = Field(description="Info to load submodel")
-    submodel: Optional[SubModelType] = Field(
-        default=None, description="Info to load submodel"
-    )
+    submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
 
 
 class LoraInfo(ModelInfo):
@@ -33,6 +30,7 @@ class ClipField(BaseModel):
     skipped_layers: int = Field(description="Number of skipped layers in text_encoder")
     loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
 
+
 class VaeField(BaseModel):
     # TODO: better naming?
     vae: ModelInfo = Field(description="Info to load vae submodel")
@@ -49,11 +47,13 @@ class ModelLoaderOutput(BaseInvocationOutput):
     vae: VaeField = Field(default=None, description="Vae submodel")
     # fmt: on
 
+
 class MainModelField(BaseModel):
     """Main model field"""
 
     model_name: str = Field(description="Name of the model")
     base_model: BaseModelType = Field(description="Base model")
+    model_type: ModelType = Field(description="Model Type")
 
 
 class LoRAModelField(BaseModel):
@@ -62,6 +62,7 @@ class LoRAModelField(BaseModel):
     model_name: str = Field(description="Name of the LoRA model")
     base_model: BaseModelType = Field(description="Base model")
 
+
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
@@ -180,7 +181,7 @@ class MainModelLoaderInvocation(BaseInvocation):
             ),
         )
 
-    
+
 class LoraLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 
@@ -197,9 +198,7 @@ class LoraLoaderInvocation(BaseInvocation):
 
     type: Literal["lora_loader"] = "lora_loader"
 
-    lora: Union[LoRAModelField, None] = Field(
-        default=None, description="Lora model name"
-    )
+    lora: Union[LoRAModelField, None] = Field(default=None, description="Lora model name")
     weight: float = Field(default=0.75, description="With what weight to apply lora")
 
     unet: Optional[UNetField] = Field(description="UNet model for applying lora")
@@ -228,14 +227,10 @@ class LoraLoaderInvocation(BaseInvocation):
         ):
             raise Exception(f"Unkown lora name: {lora_name}!")
 
-        if self.unet is not None and any(
-            lora.model_name == lora_name for lora in self.unet.loras
-        ):
+        if self.unet is not None and any(lora.model_name == lora_name for lora in self.unet.loras):
             raise Exception(f'Lora "{lora_name}" already applied to unet')
 
-        if self.clip is not None and any(
-            lora.model_name == lora_name for lora in self.clip.loras
-        ):
+        if self.clip is not None and any(lora.model_name == lora_name for lora in self.clip.loras):
             raise Exception(f'Lora "{lora_name}" already applied to clip')
 
         output = LoraLoaderOutput()

invokeai/app/invocations/noise.py

@@ -119,8 +119,8 @@ class NoiseInvocation(BaseInvocation):
 
     @validator("seed", pre=True)
     def modulo_seed(cls, v):
-        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
-        return v % SEED_MAX
+        """Returns the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
+        return v % (SEED_MAX + 1)
 
     def invoke(self, context: InvocationContext) -> NoiseOutput:
         noise = get_noise(

invokeai/app/invocations/onnx.py

@@ -0,0 +1,578 @@
+# Copyright (c) 2023 Borisov Sergey (https://github.com/StAlKeR7779)
+
+from contextlib import ExitStack
+from typing import List, Literal, Optional, Union
+
+import re
+import inspect
+
+from pydantic import BaseModel, Field, validator
+import torch
+import numpy as np
+from diffusers import ControlNetModel, DPMSolverMultistepScheduler
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.schedulers import SchedulerMixin as Scheduler
+
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
+from ...backend.model_management import ONNXModelPatcher
+from ...backend.util import choose_torch_device
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
+from .compel import ConditioningField
+from .controlnet_image_processors import ControlField
+from .image import ImageOutput
+from .model import ModelInfo, UNetField, VaeField
+
+from invokeai.app.invocations.metadata import CoreMetadata
+from invokeai.backend import BaseModelType, ModelType, SubModelType
+from invokeai.app.util.step_callback import stable_diffusion_step_callback
+from ...backend.stable_diffusion import PipelineIntermediateState
+
+from tqdm import tqdm
+from .model import ClipField
+from .latent import LatentsField, LatentsOutput, build_latents_output, get_scheduler, SAMPLER_NAME_VALUES
+from .compel import CompelOutput
+
+
+ORT_TO_NP_TYPE = {
+    "tensor(bool)": np.bool_,
+    "tensor(int8)": np.int8,
+    "tensor(uint8)": np.uint8,
+    "tensor(int16)": np.int16,
+    "tensor(uint16)": np.uint16,
+    "tensor(int32)": np.int32,
+    "tensor(uint32)": np.uint32,
+    "tensor(int64)": np.int64,
+    "tensor(uint64)": np.uint64,
+    "tensor(float16)": np.float16,
+    "tensor(float)": np.float32,
+    "tensor(double)": np.float64,
+}
+
+PRECISION_VALUES = Literal[tuple(list(ORT_TO_NP_TYPE.keys()))]
+
+
+class ONNXPromptInvocation(BaseInvocation):
+    type: Literal["prompt_onnx"] = "prompt_onnx"
+
+    prompt: str = Field(default="", description="Prompt")
+    clip: ClipField = Field(None, description="Clip to use")
+
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        tokenizer_info = context.services.model_manager.get_model(
+            **self.clip.tokenizer.dict(),
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **self.clip.text_encoder.dict(),
+        )
+        with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder, ExitStack() as stack:
+            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.clip.loras]
+            loras = [
+                (context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
+                for lora in self.clip.loras
+            ]
+
+            ti_list = []
+            for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", self.prompt):
+                name = trigger[1:-1]
+                try:
+                    ti_list.append(
+                        # stack.enter_context(
+                        #    context.services.model_manager.get_model(
+                        #        model_name=name,
+                        #        base_model=self.clip.text_encoder.base_model,
+                        #        model_type=ModelType.TextualInversion,
+                        #    )
+                        # )
+                        context.services.model_manager.get_model(
+                            model_name=name,
+                            base_model=self.clip.text_encoder.base_model,
+                            model_type=ModelType.TextualInversion,
+                        ).context.model
+                    )
+                except Exception:
+                    # print(e)
+                    # import traceback
+                    # print(traceback.format_exc())
+                    print(f'Warn: trigger: "{trigger}" not found')
+            if loras or ti_list:
+                text_encoder.release_session()
+            with ONNXModelPatcher.apply_lora_text_encoder(text_encoder, loras), ONNXModelPatcher.apply_ti(
+                orig_tokenizer, text_encoder, ti_list
+            ) as (tokenizer, ti_manager):
+                text_encoder.create_session()
+
+                # copy from
+                # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L153
+                text_inputs = tokenizer(
+                    self.prompt,
+                    padding="max_length",
+                    max_length=tokenizer.model_max_length,
+                    truncation=True,
+                    return_tensors="np",
+                )
+                text_input_ids = text_inputs.input_ids
+                """
+                untruncated_ids = tokenizer(prompt, padding="max_length", return_tensors="np").input_ids
+
+                if not np.array_equal(text_input_ids, untruncated_ids):
+                    removed_text = self.tokenizer.batch_decode(
+                        untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
+                    )
+                    logger.warning(
+                        "The following part of your input was truncated because CLIP can only handle sequences up to"
+                        f" {self.tokenizer.model_max_length} tokens: {removed_text}"
+                    )
+                """
+
+                prompt_embeds = text_encoder(input_ids=text_input_ids.astype(np.int32))[0]
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+
+        # TODO: hacky but works ;D maybe rename latents somehow?
+        context.services.latents.save(conditioning_name, (prompt_embeds, None))
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+# Text to image
+class ONNXTextToLatentsInvocation(BaseInvocation):
+    """Generates latents from conditionings."""
+
+    type: Literal["t2l_onnx"] = "t2l_onnx"
+
+    # Inputs
+    # fmt: off
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    precision: PRECISION_VALUES = Field(default = "tensor(float16)", description="The precision to use when generating latents")
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
+    # seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    # seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    # fmt: on
+
+    @validator("cfg_scale")
+    def ge_one(cls, v):
+        """validate that all cfg_scale values are >= 1"""
+        if isinstance(v, list):
+            for i in v:
+                if i < 1:
+                    raise ValueError("cfg_scale must be greater than 1")
+        else:
+            if v < 1:
+                raise ValueError("cfg_scale must be greater than 1")
+        return v
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                    "model": "model",
+                    "control": "control",
+                    # "cfg_scale": "float",
+                    "cfg_scale": "number",
+                },
+            },
+        }
+
+    # based on
+    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        c, _ = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+        if isinstance(c, torch.Tensor):
+            c = c.cpu().numpy()
+        if isinstance(uc, torch.Tensor):
+            uc = uc.cpu().numpy()
+        device = torch.device(choose_torch_device())
+        prompt_embeds = np.concatenate([uc, c])
+
+        latents = context.services.latents.get(self.noise.latents_name)
+        if isinstance(latents, torch.Tensor):
+            latents = latents.cpu().numpy()
+
+        # TODO: better execution device handling
+        latents = latents.astype(ORT_TO_NP_TYPE[self.precision])
+
+        # get the initial random noise unless the user supplied it
+        do_classifier_free_guidance = True
+        # latents_dtype = prompt_embeds.dtype
+        # latents_shape = (batch_size * num_images_per_prompt, 4, height // 8, width // 8)
+        # if latents.shape != latents_shape:
+        #    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
+
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
+        )
+
+        def torch2numpy(latent: torch.Tensor):
+            return latent.cpu().numpy()
+
+        def numpy2torch(latent, device):
+            return torch.from_numpy(latent).to(device)
+
+        def dispatch_progress(
+            self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
+        ) -> None:
+            stable_diffusion_step_callback(
+                context=context,
+                intermediate_state=intermediate_state,
+                node=self.dict(),
+                source_node_id=source_node_id,
+            )
+
+        scheduler.set_timesteps(self.steps)
+        latents = latents * np.float64(scheduler.init_noise_sigma)
+
+        extra_step_kwargs = dict()
+        if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
+            extra_step_kwargs.update(
+                eta=0.0,
+            )
+
+        unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
+
+        with unet_info as unet, ExitStack() as stack:
+            # loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
+            loras = [
+                (context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
+                for lora in self.unet.loras
+            ]
+
+            if loras:
+                unet.release_session()
+            with ONNXModelPatcher.apply_lora_unet(unet, loras):
+                # TODO:
+                _, _, h, w = latents.shape
+                unet.create_session(h, w)
+
+                timestep_dtype = next(
+                    (input.type for input in unet.session.get_inputs() if input.name == "timestep"), "tensor(float16)"
+                )
+                timestep_dtype = ORT_TO_NP_TYPE[timestep_dtype]
+                for i in tqdm(range(len(scheduler.timesteps))):
+                    t = scheduler.timesteps[i]
+                    # expand the latents if we are doing classifier free guidance
+                    latent_model_input = np.concatenate([latents] * 2) if do_classifier_free_guidance else latents
+                    latent_model_input = scheduler.scale_model_input(numpy2torch(latent_model_input, device), t)
+                    latent_model_input = latent_model_input.cpu().numpy()
+
+                    # predict the noise residual
+                    timestep = np.array([t], dtype=timestep_dtype)
+                    noise_pred = unet(sample=latent_model_input, timestep=timestep, encoder_hidden_states=prompt_embeds)
+                    noise_pred = noise_pred[0]
+
+                    # perform guidance
+                    if do_classifier_free_guidance:
+                        noise_pred_uncond, noise_pred_text = np.split(noise_pred, 2)
+                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
+
+                    # compute the previous noisy sample x_t -> x_t-1
+                    scheduler_output = scheduler.step(
+                        numpy2torch(noise_pred, device), t, numpy2torch(latents, device), **extra_step_kwargs
+                    )
+                    latents = torch2numpy(scheduler_output.prev_sample)
+
+                    state = PipelineIntermediateState(
+                        run_id="test", step=i, timestep=timestep, latents=scheduler_output.prev_sample
+                    )
+                    dispatch_progress(self, context=context, source_node_id=source_node_id, intermediate_state=state)
+
+                    # call the callback, if provided
+                    # if callback is not None and i % callback_steps == 0:
+                    #    callback(i, t, latents)
+
+        torch.cuda.empty_cache()
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.save(name, latents)
+        return build_latents_output(latents_name=name, latents=torch.from_numpy(latents))
+
+
+# Latent to image
+class ONNXLatentsToImageInvocation(BaseInvocation):
+    """Generates an image from latents."""
+
+    type: Literal["l2i_onnx"] = "l2i_onnx"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    metadata: Optional[CoreMetadata] = Field(
+        default=None, description="Optional core metadata to be written to the image"
+    )
+    # tiled: bool = Field(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        if self.vae.vae.submodel != SubModelType.VaeDecoder:
+            raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
+
+        vae_info = context.services.model_manager.get_model(
+            **self.vae.vae.dict(),
+        )
+
+        # clear memory as vae decode can request a lot
+        torch.cuda.empty_cache()
+
+        with vae_info as vae:
+            vae.create_session()
+
+            # copied from
+            # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L427
+            latents = 1 / 0.18215 * latents
+            # image = self.vae_decoder(latent_sample=latents)[0]
+            # it seems likes there is a strange result for using half-precision vae decoder if batchsize>1
+            image = np.concatenate([vae(latent_sample=latents[i : i + 1])[0] for i in range(latents.shape[0])])
+
+            image = np.clip(image / 2 + 0.5, 0, 1)
+            image = image.transpose((0, 2, 3, 1))
+            image = VaeImageProcessor.numpy_to_pil(image)[0]
+
+        torch.cuda.empty_cache()
+
+        image_dto = context.services.images.create(
+            image=image,
+            image_origin=ResourceOrigin.INTERNAL,
+            image_category=ImageCategory.GENERAL,
+            node_id=self.id,
+            session_id=context.graph_execution_state_id,
+            is_intermediate=self.is_intermediate,
+            metadata=self.metadata.dict() if self.metadata else None,
+        )
+
+        return ImageOutput(
+            image=ImageField(image_name=image_dto.image_name),
+            width=image_dto.width,
+            height=image_dto.height,
+        )
+
+
+class ONNXModelLoaderOutput(BaseInvocationOutput):
+    """Model loader output"""
+
+    # fmt: off
+    type: Literal["model_loader_output_onnx"] = "model_loader_output_onnx"
+
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae_decoder: VaeField = Field(default=None, description="Vae submodel")
+    vae_encoder: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
+
+
+class ONNXSD1ModelLoaderInvocation(BaseInvocation):
+    """Loading submodels of selected model."""
+
+    type: Literal["sd1_model_loader_onnx"] = "sd1_model_loader_onnx"
+
+    model_name: str = Field(default="", description="Model to load")
+    # TODO: precision?
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {"tags": ["model", "loader"], "type_hints": {"model_name": "model"}},  # TODO: rename to model_name?
+        }
+
+    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
+        model_name = "stable-diffusion-v1-5"
+        base_model = BaseModelType.StableDiffusion1
+
+        # TODO: not found exceptions
+        if not context.services.model_manager.model_exists(
+            model_name=model_name,
+            base_model=BaseModelType.StableDiffusion1,
+            model_type=ModelType.ONNX,
+        ):
+            raise Exception(f"Unkown model name: {model_name}!")
+
+        return ONNXModelLoaderOutput(
+            unet=UNetField(
+                unet=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.UNet,
+                ),
+                scheduler=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.Scheduler,
+                ),
+                loras=[],
+            ),
+            clip=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.Tokenizer,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.TextEncoder,
+                ),
+                loras=[],
+            ),
+            vae_decoder=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.VaeDecoder,
+                ),
+            ),
+            vae_encoder=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=ModelType.ONNX,
+                    submodel=SubModelType.VaeEncoder,
+                ),
+            ),
+        )
+
+
+class OnnxModelField(BaseModel):
+    """Onnx model field"""
+
+    model_name: str = Field(description="Name of the model")
+    base_model: BaseModelType = Field(description="Base model")
+    model_type: ModelType = Field(description="Model Type")
+
+
+class OnnxModelLoaderInvocation(BaseInvocation):
+    """Loads a main model, outputting its submodels."""
+
+    type: Literal["onnx_model_loader"] = "onnx_model_loader"
+
+    model: OnnxModelField = Field(description="The model to load")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Onnx Model Loader",
+                "tags": ["model", "loader"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> ONNXModelLoaderOutput:
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.ONNX
+
+        # TODO: not found exceptions
+        if not context.services.model_manager.model_exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+
+        """
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.Tokenizer,
+        ):
+            raise Exception(
+                f"Failed to find tokenizer submodel in {self.model_name}! Check if model corrupted"
+            )
+
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.TextEncoder,
+        ):
+            raise Exception(
+                f"Failed to find text_encoder submodel in {self.model_name}! Check if model corrupted"
+            )
+
+        if not context.services.model_manager.model_exists(
+            model_name=self.model_name,
+            model_type=SDModelType.Diffusers,
+            submodel=SDModelType.UNet,
+        ):
+            raise Exception(
+                f"Failed to find unet submodel from {self.model_name}! Check if model corrupted"
+            )
+        """
+
+        return ONNXModelLoaderOutput(
+            unet=UNetField(
+                unet=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
+                ),
+                scheduler=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
+                ),
+                loras=[],
+            ),
+            clip=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
+            vae_decoder=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.VaeDecoder,
+                ),
+            ),
+            vae_encoder=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.VaeEncoder,
+                ),
+            ),
+        )

invokeai/app/invocations/param_easing.py

@@ -12,16 +12,37 @@ import matplotlib.pyplot as plt
 
 from easing_functions import (
     LinearInOut,
-    QuadEaseInOut, QuadEaseIn, QuadEaseOut,
-    CubicEaseInOut, CubicEaseIn, CubicEaseOut,
-    QuarticEaseInOut, QuarticEaseIn, QuarticEaseOut,
-    QuinticEaseInOut, QuinticEaseIn, QuinticEaseOut,
-    SineEaseInOut, SineEaseIn, SineEaseOut,
-    CircularEaseIn, CircularEaseInOut, CircularEaseOut,
-    ExponentialEaseInOut, ExponentialEaseIn, ExponentialEaseOut,
-    ElasticEaseIn, ElasticEaseInOut, ElasticEaseOut,
-    BackEaseIn, BackEaseInOut, BackEaseOut,
-    BounceEaseIn, BounceEaseInOut, BounceEaseOut)
+    QuadEaseInOut,
+    QuadEaseIn,
+    QuadEaseOut,
+    CubicEaseInOut,
+    CubicEaseIn,
+    CubicEaseOut,
+    QuarticEaseInOut,
+    QuarticEaseIn,
+    QuarticEaseOut,
+    QuinticEaseInOut,
+    QuinticEaseIn,
+    QuinticEaseOut,
+    SineEaseInOut,
+    SineEaseIn,
+    SineEaseOut,
+    CircularEaseIn,
+    CircularEaseInOut,
+    CircularEaseOut,
+    ExponentialEaseInOut,
+    ExponentialEaseIn,
+    ExponentialEaseOut,
+    ElasticEaseIn,
+    ElasticEaseInOut,
+    ElasticEaseOut,
+    BackEaseIn,
+    BackEaseInOut,
+    BackEaseOut,
+    BounceEaseIn,
+    BounceEaseInOut,
+    BounceEaseOut,
+)
 
 from .baseinvocation import (
     BaseInvocation,
@@ -45,17 +66,12 @@ class FloatLinearRangeInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Linear Range (Float)",
-                "tags": ["math", "float", "linear", "range"]
-            },
+            "ui": {"title": "Linear Range (Float)", "tags": ["math", "float", "linear", "range"]},
         }
 
     def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
         param_list = list(np.linspace(self.start, self.stop, self.steps))
-        return FloatCollectionOutput(
-            collection=param_list
-        )
+        return FloatCollectionOutput(collection=param_list)
 
 
 EASING_FUNCTIONS_MAP = {
@@ -92,9 +108,7 @@ EASING_FUNCTIONS_MAP = {
     "BounceInOut": BounceEaseInOut,
 }
 
-EASING_FUNCTION_KEYS: Any = Literal[
-    tuple(list(EASING_FUNCTIONS_MAP.keys()))
-]
+EASING_FUNCTION_KEYS: Any = Literal[tuple(list(EASING_FUNCTIONS_MAP.keys()))]
 
 
 # actually I think for now could just use CollectionOutput (which is list[Any]
@@ -123,13 +137,9 @@ class StepParamEasingInvocation(BaseInvocation):
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Param Easing By Step",
-                "tags": ["param", "step", "easing"]
-            },
+            "ui": {"title": "Param Easing By Step", "tags": ["param", "step", "easing"]},
         }
 
-
     def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
         log_diagnostics = False
         # convert from start_step_percent to nearest step <= (steps * start_step_percent)
@@ -170,12 +180,13 @@ class StepParamEasingInvocation(BaseInvocation):
             # and create reverse copy of list[1:end-1]
             # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
 
-            base_easing_duration = int(np.ceil(num_easing_steps/2.0))
-            if log_diagnostics: context.services.logger.debug("base easing duration: " + str(base_easing_duration))
-            even_num_steps = (num_easing_steps % 2 == 0)  # even number of steps
-            easing_function = easing_class(start=self.start_value,
-                                           end=self.end_value,
-                                           duration=base_easing_duration - 1)
+            base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
+            if log_diagnostics:
+                context.services.logger.debug("base easing duration: " + str(base_easing_duration))
+            even_num_steps = num_easing_steps % 2 == 0  # even number of steps
+            easing_function = easing_class(
+                start=self.start_value, end=self.end_value, duration=base_easing_duration - 1
+            )
             base_easing_vals = list()
             for step_index in range(base_easing_duration):
                 easing_val = easing_function.ease(step_index)
@@ -214,9 +225,7 @@ class StepParamEasingInvocation(BaseInvocation):
         #
 
         else:  # no mirroring (default)
-            easing_function = easing_class(start=self.start_value,
-                                           end=self.end_value,
-                                           duration=num_easing_steps - 1)
+            easing_function = easing_class(start=self.start_value, end=self.end_value, duration=num_easing_steps - 1)
             for step_index in range(num_easing_steps):
                 step_val = easing_function.ease(step_index)
                 easing_list.append(step_val)
@@ -240,13 +249,11 @@ class StepParamEasingInvocation(BaseInvocation):
             ax = plt.gca()
             ax.xaxis.set_major_locator(MaxNLocator(integer=True))
             buf = io.BytesIO()
-            plt.savefig(buf, format='png')
+            plt.savefig(buf, format="png")
             buf.seek(0)
             im = PIL.Image.open(buf)
             im.show()
             buf.close()
 
         # output array of size steps, each entry list[i] is param value for step i
-        return FloatCollectionOutput(
-            collection=param_list
-        )
+        return FloatCollectionOutput(collection=param_list)

invokeai/app/invocations/params.py

@@ -4,67 +4,80 @@ from typing import Literal
 
 from pydantic import Field
 
-from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
-                             InvocationConfig, InvocationContext)
+from invokeai.app.invocations.prompt import PromptOutput
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 from .math import FloatOutput, IntOutput
 
 # Pass-through parameter nodes - used by subgraphs
 
+
 class ParamIntInvocation(BaseInvocation):
     """An integer parameter"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["param_int"] = "param_int"
     a: int = Field(default=0, description="The integer value")
-    #fmt: on
+    # fmt: on
 
     class Config(InvocationConfig):
-      schema_extra = {
-          "ui": {
-              "tags": ["param", "integer"],
-              "title": "Integer Parameter"
-          },
-      }
+        schema_extra = {
+            "ui": {"tags": ["param", "integer"], "title": "Integer Parameter"},
+        }
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a)
 
+
 class ParamFloatInvocation(BaseInvocation):
     """A float parameter"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["param_float"] = "param_float"
     param: float = Field(default=0.0, description="The float value")
-    #fmt: on
+    # fmt: on
 
     class Config(InvocationConfig):
-      schema_extra = {
-          "ui": {
-              "tags": ["param", "float"],
-              "title": "Float Parameter"
-          },
-      }
+        schema_extra = {
+            "ui": {"tags": ["param", "float"], "title": "Float Parameter"},
+        }
 
     def invoke(self, context: InvocationContext) -> FloatOutput:
         return FloatOutput(param=self.param)
 
+
 class StringOutput(BaseInvocationOutput):
     """A string output"""
+
     type: Literal["string_output"] = "string_output"
     text: str = Field(default=None, description="The output string")
 
 
 class ParamStringInvocation(BaseInvocation):
     """A string parameter"""
-    type: Literal['param_string'] = 'param_string'
-    text: str = Field(default='', description='The string value')
+
+    type: Literal["param_string"] = "param_string"
+    text: str = Field(default="", description="The string value")
 
     class Config(InvocationConfig):
-      schema_extra = {
-          "ui": {
-              "tags": ["param", "string"],
-              "title": "String Parameter"
-          },
-      }
+        schema_extra = {
+            "ui": {"tags": ["param", "string"], "title": "String Parameter"},
+        }
 
     def invoke(self, context: InvocationContext) -> StringOutput:
         return StringOutput(text=self.text)
-    
+
+
+class ParamPromptInvocation(BaseInvocation):
+    """A prompt input parameter"""
+
+    type: Literal["param_prompt"] = "param_prompt"
+    prompt: str = Field(default="", description="The prompt value")
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {"tags": ["param", "prompt"], "title": "Prompt"},
+        }
+
+    def invoke(self, context: InvocationContext) -> PromptOutput:
+        return PromptOutput(prompt=self.prompt)

invokeai/app/invocations/prompt.py

@@ -7,19 +7,21 @@ from pydantic import Field, validator
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
 from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator
 
+
 class PromptOutput(BaseInvocationOutput):
     """Base class for invocations that output a prompt"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["prompt"] = "prompt"
 
     prompt: str = Field(default=None, description="The output prompt")
-    #fmt: on
+    # fmt: on
 
     class Config:
         schema_extra = {
-            'required': [
-                'type',
-                'prompt',
+            "required": [
+                "type",
+                "prompt",
             ]
         }
 
@@ -44,16 +46,11 @@ class DynamicPromptInvocation(BaseInvocation):
     type: Literal["dynamic_prompt"] = "dynamic_prompt"
     prompt: str = Field(description="The prompt to parse with dynamicprompts")
     max_prompts: int = Field(default=1, description="The number of prompts to generate")
-    combinatorial: bool = Field(
-        default=False, description="Whether to use the combinatorial generator"
-    )
+    combinatorial: bool = Field(default=False, description="Whether to use the combinatorial generator")
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Dynamic Prompt",
-                "tags": ["prompt", "dynamic"]
-            },
+            "ui": {"title": "Dynamic Prompt", "tags": ["prompt", "dynamic"]},
         }
 
     def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
@@ -65,10 +62,11 @@ class DynamicPromptInvocation(BaseInvocation):
             prompts = generator.generate(self.prompt, num_images=self.max_prompts)
 
         return PromptCollectionOutput(prompt_collection=prompts, count=len(prompts))
-    
+
 
 class PromptsFromFileInvocation(BaseInvocation):
-    '''Loads prompts from a text file'''
+    """Loads prompts from a text file"""
+
     # fmt: off
     type: Literal['prompt_from_file'] = 'prompt_from_file'
 
@@ -78,14 +76,11 @@ class PromptsFromFileInvocation(BaseInvocation):
     post_prompt: Optional[str] = Field(description="String to append to each prompt")
     start_line: int = Field(default=1, ge=1, description="Line in the file to start start from")
     max_prompts: int = Field(default=1, ge=0, description="Max lines to read from file (0=all)")
-    #fmt: on
+    # fmt: on
 
     class Config(InvocationConfig):
         schema_extra = {
-            "ui": {
-                "title": "Prompts From File",
-                "tags": ["prompt", "file"]
-            },
+            "ui": {"title": "Prompts From File", "tags": ["prompt", "file"]},
         }
 
     @validator("file_path")
@@ -103,11 +98,13 @@ class PromptsFromFileInvocation(BaseInvocation):
         with open(file_path) as f:
             for i, line in enumerate(f):
                 if i >= start_line and i < end_line:
-                    prompts.append((pre_prompt or '') + line.strip() + (post_prompt or ''))
+                    prompts.append((pre_prompt or "") + line.strip() + (post_prompt or ""))
                 if i >= end_line:
                     break
         return prompts
 
     def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
-        prompts = self.promptsFromFile(self.file_path, self.pre_prompt, self.post_prompt, self.start_line, self.max_prompts)
+        prompts = self.promptsFromFile(
+            self.file_path, self.pre_prompt, self.post_prompt, self.start_line, self.max_prompts
+        )
         return PromptCollectionOutput(prompt_collection=prompts, count=len(prompts))