AnimateDiff-Lightning: Cross-Model Diffusion Distillation

Peter Lin, Xiao Yang

AnimateDiff-Lightning: Cross-Model Diffusion Distillation: 18 upvotes on Hugging Face Daily Papers, #3 of 13 papers on 2024-03-20. Day-by-day upvote history.

We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video generation. We discuss our modifications to adapt it for the video modality. Furthermore, we propose to simultaneously distill the probability flow of multiple base diffusion models, resulting in a single distilled motion module with broader style compatibility. We are pleased to release our distilled AnimateDiff-Lightning model for the community's use.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.