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
- Wan: fit 720p x 81-frame context in 8GB VRAM, lower peak VRAM by token-chunking attention and FFN
- Return the error from /upload/mask when the original image is rejected or missing
- Add Unpack Bounding Box node
- Add model_name output to Load Upscale Model
- Wan 2.1 VAE: adopt comfy_has_chunked_io to remove whole-video VRAM residency
- feat: Add image_a pass-through output to Compare Images node
- Run Detect Edges (Canny) one frame at a time
- Add --custom-nodes-directory launch flag
- Skip CUDA quant capability checks for CPU devices
- Fix get_frame_count counting the demuxer flush packet as a frame
- Docs
- Python not yet supported