diffusers
https://github.com/huggingface/diffusers
Python
đ¤ 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
- DiffusionPipeline.download() on Windows silently skips all subfolder config.json files with huggingface_hub>=1.22.0
- Add from_single_file() support for Ideogram4 transformer
- Flux2 pipelines: expose the hardcoded 1MP condition-image downscale threshold (max_area)
- `from_single_file()` support missing/incomplete for Ideogram4 and Krea2 transformers
- [Version 0.39.0]AttributeError: 'CLIPTextModel' object has no attribute 'text_model' WHEN SET CKIP_SKIP NOT NONE
- fix no text_model attribute bug when clip_skip is not None
- Add ReMDM remasking to DiscreteDDIMScheduler
- Fix typos across the codebase (concatingâconcatenating, tbeâthe, corrctâcorrect, etc.)
- fix: preserve method docstring through apply_forward_hook decorator
- Flux-family attention: flash-attn and other backends fail in an autocast context
- Docs
- Python not yet supported