Skip to content

Conversation

@qzzz95
Copy link
Contributor

@qzzz95 qzzz95 commented Aug 21, 2025

No description provided.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary of Changes

Hello @qzzz95, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the flexibility of several Flux tools within the diffsynth_engine by enabling their initialization directly from pre-existing model state dictionaries. This change is particularly useful for scenarios where model weights are already loaded in memory or need to be managed outside of direct file paths. The existing model loading logic has been cleanly refactored into from_pretrained class methods, ensuring a consistent and intuitive API for users whether they are loading models from disk or from in-memory state dictionaries.

Highlights

  • New Initialization Method: Introduced a new class method, from_state_dict, to allow initialization of the Flux Inpainting, Outpainting, Reference, and ReplaceByControl tools directly from pre-loaded model state dictionaries.
  • API Refactoring: The existing __init__ methods in these tools have been refactored into from_pretrained class methods, providing a clear and consistent API for loading models either from a path or from state dictionaries.
  • Type Hinting and Imports: Updated necessary imports across the modified files to include FluxStateDicts and Dict for proper type hinting and functionality related to state dictionary handling.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in issue comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request refactors several Flux...Tool classes to support initialization from state dictionaries, in addition to loading from pretrained model paths. This is achieved by moving the model loading logic from __init__ to a new from_pretrained classmethod, and adding a new from_state_dict classmethod. This is a good architectural improvement that increases the flexibility of these tools.

My review has identified a critical bug in FluxReplaceByControlTool where an incorrect model path is used, and a minor inconsistency in variable naming. Please see the detailed comments.

@akaitsuki-ii akaitsuki-ii merged commit 924c6c4 into main Aug 21, 2025
@akaitsuki-ii akaitsuki-ii deleted the dev/flux_tool_from_state_dict branch August 21, 2025 06:23
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants