Enhance-A-Video：免费生成更好视频

Enhance-A-Video: Better Generated Video for Free

February 11, 2025

作者: Yang Luo, Xuanlei Zhao, Mengzhao Chen, Kaipeng Zhang, Wenqi Shao, Kai Wang, Zhangyang Wang, Yang You

cs.AI

摘要

基于DiT的视频生成取得了显著成果，但对于增强现有模型的研究仍相对未被探索。在这项工作中，我们介绍了一种无需训练的方法来增强基于DiT生成的视频的连贯性和质量，命名为Enhance-A-Video。核心思想是基于非对角线时间注意力分布增强帧间相关性。由于其简单设计，我们的方法可以轻松应用于大多数基于DiT的视频生成框架，无需重新训练或微调。在各种基于DiT的视频生成模型中，我们的方法展示了在时间一致性和视觉质量方面的有希望的改进。我们希望这项研究能激发未来在视频生成增强方面的探索。

English

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos, named Enhance-A-Video. The core idea is enhancing the cross-frame correlations based on non-diagonal temporal attention distributions. Thanks to its simple design, our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning. Across various DiT-based video generation models, our approach demonstrates promising improvements in both temporal consistency and visual quality. We hope this research can inspire future explorations in video generation enhancement.