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
- fix(server): prefix Content-Disposition with inline; on /view image responses
- [gfx1151 / Strix Halo] MiniMax H3 (int8_convrot) fails with "CUDA error: out of memory" at first sampling step when Dynamic VRAM is enabled; works with --disable-dynamic-vram
- Why is comfyUI now suddenly downloading all my assets in a ZIP and putting every asset in a folde if its own?
- fix(nodes): drop the trailing-underscore placeholder in save-node filenames
- TrimAudioDuration retains the entire source waveform allocation
- Slow generation H3 Oct 12
- Fix PNG parameter metadata EXIF limit
- Support original legacy PyTorch weights in SDK verification
- Add model-owned latent channel normalization
- Preserve latent normalization order and vector metadata in V2 guests
- Docs
- Python not yet supported