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 TorchAO group offload CPU cache aliasing
- Fix NaN attention scores on MPS from uninitialized baddbmm buffer
- Docs: cuda windows arm64 update installation guidelines
- Compare full pipeline outputs in the modular tester mixin
- [modular] `guider` should be an optional component for text encoder blocks
- `register_to_config` mislabels positional `__init__` args as `_use_default_values`, so `from_config` round trips silently revert them to defaults
- Modular pipelines: variant blocksets sharing a `model_name` init the wrong pipeline class
- pipe.to(device) corrupts custom quantized (uint8 packed) module buffers
- Fix LDM3D NumPy batch preprocessing
- SDXL: enable_attention_slicing() + enable_model_cpu_offload() produces all-black images on MPS (Apple Silicon)
- Docs
- Python not yet supported