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.

翻译：我们提出AnimateDiff-Lightning以实现闪电般的视频生成。该模型采用渐进式对抗扩散蒸馏技术，在少步视频生成中取得了当前最优性能。我们讨论了针对视频模态的改进适配方案。此外，我们提出同时蒸馏多个基础扩散模型的概率流，由此得到的单一蒸馏运动模块具有更广泛的风格兼容性。我们很高兴向社区发布经蒸馏的AnimateDiff-Lightning模型。