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
- Add Normalize Audio Loudness node
- Fix validation of legacy combo option subsets
- Add --preview-interval to decode live previews every N steps
- Check the custom node packs a stable release is judged on
- Expose LoRA alpha in TrainLoraNode
- Check the workflow templates this build ships against its own nodes
- RTX 5060 Ti (sm_120): quantized models (Qwen-Image, MiniMax H3) output pure noise via comfy-kitchen kernels — SD1.5 fp16 works fine
- Unable to Run Multiple Instances on Windows Portable
- Comfyui Rendering Issue.
- TextGenerate with mtp=auto: CUDA illegal memory access during decode (Flux 3 prompt upsampler, RTX 3090 Ti) — crash also kills the prompt_worker thread
- Docs
- Python not yet supported