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
- Qwen3.5 text generation attends over the full KV capacity every step, so decode speed drops with max_length
- RuntimeError in PoseBranchCache.select when slots with different key shapes coexist
- Qwen-Image 2.1 : Flash Attantion falls back to SDPA
- AMD ROCm / DynamicVRAM: performance degrades after first generation; /free restores full speed
- Please support new ControlNet "Qwen Image 2.1 ControlNet"
- [HIP] Use Conv2d for single-frame BF16 VAE convolutions
- Support fp16 inference for MiniMax H3 on GPUs without bf16
- MiniMax H3 inpainting latent masking example workflow omits Reference-to-Video conditioning, reducing reference fidelity
- Fix RuntimeError in PoseBranchCache.select when slots have different key shapes
- Support fp16 inference for MiniMax H3
- Docs
- Python not yet supported