Qwen image context control #833
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @mi804, 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 introduces significant enhancements to the Qwen image generation capabilities by integrating new models for advanced image context control and improved image generation. It enables users to leverage structural control conditions and an updated EliGen model for better image alignment and style.
Highlights
- Expanded Model Support: Integration of Qwen-Image-Context-Control and Qwen-Image-EliGen-V2 models, broadening the range of image generation and manipulation functionalities.
- Contextual Image Control: Introduction of a context_image parameter in the QwenImagePipeline, allowing for precise structural control over generated images using various conditions like Canny, Depth, and OpenPose.
- Pipeline and Model Adaptations: Core pipeline components (QwenImagePipeline) and the Diffusion Transformer (DiT) model (qwen_image_dit.py) have been updated to seamlessly process and incorporate the new context image inputs.
- Comprehensive Documentation & Examples: Updated English and Chinese READMEs, along with new inference and training scripts, provide clear guidance and practical examples for utilizing the newly added image control features and models.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request introduces support for Qwen image context control by adding a new QwenImageUnit_ContextImageEmbedder pipeline unit and updating the core model logic to handle context latents. It also adds several new example scripts for both the new context control feature and for EliGen-V2, along with updates to the documentation. The implementation of the context control feature appears solid. My review focuses on the new example scripts, where I've identified a missing dependency download that would cause the scripts to fail. I've provided suggestions to fix this.
| from diffsynth.controlnets.processors import Annotator | ||
| from diffsynth import download_models | ||
|
|
||
| download_models(["Annotators:Depth"]) |
There was a problem hiding this comment.
The script downloads only the 'Depth' annotator model, but the loop on line 26 iterates over several other annotators (openpose, canny, lineart, softedge, normal) which require their own models. This will cause errors when the script tries to use an annotator whose model has not been downloaded.
To fix this, you should download all necessary annotator models.
| download_models(["Annotators:Depth"]) | |
| download_models(["Annotators:Depth", "Annotators:OpenPose", "Annotators:Lineart", "Annotators:SoftEdge", "Annotators:NormalBAE"]) |
| from diffsynth.controlnets.processors import Annotator | ||
| from diffsynth import download_models | ||
|
|
||
| download_models(["Annotators:Depth"]) |
There was a problem hiding this comment.
Similar to the other example script, this one only downloads the 'Depth' annotator model. The script will fail for other annotators like 'openpose', 'lineart', etc., because their models are missing. Please download all required models for the annotators used in the script.
| download_models(["Annotators:Depth"]) | |
| download_models(["Annotators:Depth", "Annotators:OpenPose", "Annotators:Lineart", "Annotators:SoftEdge", "Annotators:NormalBAE"]) |
No description provided.