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 supported1 Subscribers
Add a CodeTriage badge to diffusers
Help out
- Issues
- Custom timesteps and sigmas for img2img inpaint controlnet pipelines
- [Community] Help us fix the LR schedulers when `num_train_epochs` is passed in a distributed training env
- support TextDiffuser pipelines natively in Diffusers
- [SD3] Incorrect stochastic sampling implementation
- global, eager model weight GPU unloading
- Error in train_cm_ct_unconditional.py (Even after new commit)
- Sequential offloading bug with Stable Audio
- Formulation of reverse diffusion process in DDPM ( 1 - alpha_prod_t = beta_prod_t assumption)
- Support LinFusion
- [Schedulers] Add methods for conversion between noise and denoised predictions
- Docs
- Python not yet supported