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 supported13 Subscribers
Add a CodeTriage badge to comfyui
Help out
- Issues
- a way to evoide ^C lack of cpu ram please create argument to it for example reactor and or liveportrait doesnt use my highvram L4 22.5GB VRAM instead all goes to cpu and i would like to know how to evoice crashing please?
- The unstable nightly PyTorch package version 0.2.3 has not yet been released.
- VAE decoding becomes very slow when the batch_number in the decode method is large.
- /v0.2.3/ComfyUI_windows_portable_nvidia.7z startup script not working
- Save output node ID in file metadata
- Aux集成预处理器 尝试在 Hub 上查找文件时发生错误，我们无法在本地缓存中找到请求的文件。请检查您的连接并重试，或确保您的互联网连接已打开。
- Node for Blending Sigmas
- Add optional webhook after job finished
- Add on hold for "loading checkpoint or unet or so on" only start when running their own function to save VRAM
- [Feat] Show sizes of model / lora / clip / etc
- Docs
- Python not yet supported