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 supported24 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- fix(nodes): close PIL image handle in LoadImage / Painter / dataset loaders
- Prefer fp16 over bf16 for VAEs on Apple GPUs
- [WARNING] On windows we are currently forcing single GPU mode in ComfyUI due to a Nvidia related issue
- Recognize MPS allocator out-of-memory errors in `is_oom`
- Generated previews for EXR assets, decoded with OpenEXR
- Fix tensor cache slot promotion
- [Intel XPU] Qwen3-VL DeepStack multi-image boolean indexing selects wrong token count (1059 vs 2061); CPU-index workaround
- Fix Qwen3-VL DeepStack multi-image writes on Intel XPU
- Qwen Fun ControlNet: use QwenImage inference dtypes (no fp16)
- Serve the raw file from /view?preview= when PIL can't identify it
- Docs
- Python not yet supported