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 supported21 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- ComfyUI with comfy-kitchen fails to start on PyTorch < 2.7 (for legacy GPUs)
- Wan 2.2 14B (I2V) sampler emits NaN latents → every frame one flat colour on AMD gfx1201 (Radeon AI PRO R9700), ROCm 7.2.4, torch 2.14/2.15 — 5B renders correctly through the same graph nodes
- Shape mismatch in MiniMax H3 audio conditioning when combining video continuation ("OG Video Has Audio") with a standalone audio-timbre reference
- ci: enforce the python 3.10 floor with vermin and a 3.10 test-collection job
- Draft: Add seamless tiling nodes for DiT
- Add video-frame strength easing to MiniMax H3 Fun ControlNet
- feat: add accumulate toggle to SaveImage and PreviewImage nodes
- fix: let an incompatible comfy_kitchen degrade instead of killing startup
- Fix RAM cache evaluating lazy mappings
- Fix fallback video frame counts and durations
- Docs
- Python not yet supported