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 supported3 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Text-to-image example updates EMA when AMP skips the optimizer step
- Add Hy-Nomas support with a modular pipeline
- `encode_video` truncates a fractional `fps`, so the video runs longer than its audio
- [Model integration] Add Hy-Nomas support to Diffusers
- load_video returns mixed-mode frames for GIFs, breaking preprocess_video and AnimateDiff video-to-video
- Convert load_video frames to RGB when convert_method is None
- [chore] update return type annotations for models.
- DEIS coefficient precision causes increasing error as inference steps increase
- Warn when add_noise is called before set_timesteps
- lr_scheduler step bug in examples code
- Docs
- Python not yet supported