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 supported11 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Starting from ComfyUI 0.21.0, dragging an image into the interface no longer loads the workflow. I would like to revert to the original behavior where dragging an image automatically loads the workflow.
- Add validation for invalid HiDream input dimensions
- 严重 Bug 报告：Web 根目录指向错误、DWPose 加载失败及 API 模块导入异常
- Update comfyui, Can't load workflow
- Support for newer pixel space models (HiDream O1 Image, SenseNova-U1, LLaDA2.0-Uni, etc)
- New UI is real awkward
- LTX 2.3 FP8/Q4KM stalls during `Requested to load LTXAV` on RX 7900 XTX + ROCm unless dynamic VRAM / pinned memory / async offload are disabled
- fix: use module attributes to check if cuda is available.
- impossible to drag and drop the workflow to the comfyui web interface.
- feat: Time-to-Move sampling
- Docs
- Python not yet supported