comfyui
https://github.com/comfyanonymous/comfyui
Python
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported13 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Black image (NaN) with int8_convrot diffusion models on gfx1201 / ROCm, but int8_convrot text encoder works fine
- Fix OFT/BOFT constraint scaling when loading lycoris models
- Not even running prompts at all
- The Mage Flow model produces quality issues when generating 2K resolution images. Is this a problem with the model itself??
- Subgraph flatten queues wrong widget values (off-by-one) - 113 shipping templates carry the defect, some corrupt silently (fix included)
- fix(server): return 400 for unknown /upload/image type instead of 500
- Fix mask ndim handling in QwenImageDiffsynthControlnet.
- Mess with stable versions
- Fix lazy V3 dynamic input scheduling
- model_patcher: preserve lazy weights when saving
- Docs
- Python not yet supported