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 supported1 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- Train LoRA node with dtype "none" causes error
- JOB QUEUE sidebar: Hide Finished
- Feature Request: Support for GAIR/daVinci-MagiHuman (text-image-audio → video)
- every operation triggers a "Failed to save workflow draft" error. This error persists even after manually disabling "Show error tab in side panel" in Settings > Error System.
- 节点“Qwen Multiangle Camera”每次刷新或重启 ComfyUI 时，高度会不断增加。
- Node VHS Video Combine and asset library does not display the generated video
- TypeError: patched_forward_orig() got an unexpected keyword argument 'timestep_zero_index'
- Incomfy ui my ltx 2.3 is not generating
- How to fix "Failed to save workflow draft" error?
- [Trainer/Dev] Dev run mode in lora trainer for behavior debugging
- Docs
- Python not yet supported