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
- MIOpen (cudnn) is disabled by default on RDNA3 and newer, convolutions fall back to the slow path
- ComfyUI Qwen Image 2.1 generation stalls with no error (UI still responsive)
- Machine Type Mismatch
- Add the max_tokens budget to Trellis2UpsampleStage
- Trellis2 / Pixal3D VAE decode nodes ignore --cpu-vae (inputs sent to get_torch_device(), not vae.device)
- Agent
- A100-80G, Error in ComfyUI OOM
- A question regarding the voice cloning capabilities of Minimax-H3 and ltx2.5.
- [Bug] HostBuffer.truncate failed during pin eviction on AMD ROCm (Windows) - comfy-aimdo 0.6.0 + comfy-kitchen 0.2.40, MiniMaxH3 dynamic VRAM
- [Bug] HostBuffer.truncate failed during pin eviction on AMD ROCm (Windows) - comfy-aimdo 0.6.0 + comfy-kitchen 0.2.40, MiniMaxH3 dynamic VRAM
- Docs
- Python not yet supported