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
- cuDNN attention CP path consumes a bool attn_mask as an additive 0/1 bias
- [Modular] support group offloading in auto offloading
- [Bug] low_cpu_mem_usage=True is not thread-safe and can leak the global nn.Module.register_parameter patch
- Fix double transpose of K/V in templated attention backward
- Two ONNX Docker images are missing from build_docker_images.yml, so their :latest tags have been frozen since June 2025
- [modular] Migrate ComponentsManager offload hooks to ModelHook / HookRegistry
- Fix attention backend leaking across models
- cuDNN attention backward corrupts gradients: K/V transposed twice, Q once
- Migrate qwenimage pipeline docstrings from torch_dtype to dtype
- Fix LTX-2 context parallel plan and Ulysses attn mask head sharding
- Docs
- Python not yet supported