diffusers
https://github.com/huggingface/diffusers
Python
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
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 supported1 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Fix CogVideoX dynamic CFG to use loop index instead of timestep value
- [attention backends] remove non-hub attention backends.
- Wan I2V expand_timesteps: why hard-clamp only first frame (no last-frame clamp)?
- GGUF + `torch.compile` is not compatible with Hub Kernels
- [tests] refactor UNet model tests to align with the new pattern
- Allows DDPM Scheduler to have Zero Variance on Generation Runs
- Add Claude Diffusers skill and Claude Code plugin scaffold (#12935)
- Fix CogVideoX scheduler prev_timestep for non-leading spacing
- fix: freeze shared transformer modules in ZImageControlNet.from_transformer
- Fix missing .unsqueeze(1) in attention mask for HunyuanVideo VAE
- Docs
- Python not yet supported