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
- Fix: FLUX.2 encode_prompt dtype and add bitsandbytes int8+bfloat16 warning
- Fix from_pretrain typo in StableCascade and Wuerstchen docstrings
- UNet2DModel dtype property fails under nn.DataParallel with UnboundLocalError in get_parameter_dtype
- loading Cosmos2 pipeline also disabled gradient tracking globally
- Fix FlowMatchEulerDiscreteScheduler.index_for_timestep float precision lookup
- Bad image output for Flux.2-dev, rocm, quantization and separate prompt encoding sequence
- feat: have claude open issues for forked branch PRs.
- Bump diffusers from 0.9.0 to 0.38.0 in /examples/research_projects/dreambooth_inpaint
- [core] Refactor condition embedders (and others) modules from `pipelines`
- properly check for ftfy and warn if unavailable in all pipelines
- Docs
- Python not yet supported