AnimateDiff-Lightning: Cross-Model Diffusion Distillation

arXiv:2403.12706v1 Announce Type: new
Abstract: 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.

abstract adapt adversarial art arxiv cs.ai cs.cv diffusion diffusion models discuss distillation flow lightning multiple probability state type video video generation