AnimateDiff-Lightning: Cross-Model Diffusion Distillation
This addresses the bottleneck of slow video generation for AI and creative applications, though it is incremental as it builds on existing diffusion distillation methods.
The paper tackles the problem of slow video generation by introducing AnimateDiff-Lightning, which uses progressive adversarial diffusion distillation to achieve state-of-the-art performance in few-step video generation, resulting in a fast and broadly compatible model.
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.