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
- Modular pipelines: variant blocksets sharing a `model_name` init the wrong pipeline class
- [ai] fix locations in the skills.
- 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] Fix broken pipeline links in pipelines/README
- [docs] Fix broken Wuerstchen example links in en training docs
- [core] pass diffusers library name to kernels calls
- Equip the UniPC Solver with the capability of using customed timesteps and provide a precise document to explain the parameters.
- Fix variable typos in the code example in kandinsky5_video.md
- Docs
- Python not yet supported