FastVideoEdit：利用一致性模型实现高效文本到视频编辑
FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing
AI总结：
FastVideoEdit利用一致性模型的自一致性特性，实现零样本高效文本到视频编辑，无需反演或额外条件提取，在保持生成质量的同时显著提升编辑速度。
摘要：
扩散模型在文本到图像和文本到视频生成方面已展现出卓越能力，为基于文本输入的视频编辑开辟了可能。然而，扩散模型中顺序采样所带来的计算成本对高效视频编辑构成了挑战。现有依赖图像生成模型进行视频编辑的方法存在耗时的一次性微调、额外条件提取或DDIM反演等问题，使得实时应用难以实现。在本工作中，我们提出了FastVideoEdit，这是一种受一致性模型（CMs）启发的高效零样本视频编辑方法。通过利用一致性模型的自一致性特性，我们消除了耗时的反演或额外条件提取的需要，从而缩短了编辑时间。我们的方法利用特殊的方差调度，实现了从源视频到目标视频的直接映射，并具有较强的内容保持能力。这带来了速度优势的提升，因为可以在保持可比生成质量的同时使用更少的采样步骤。实验结果验证了FastVideoEdit在编辑速度、时间一致性和文本-视频对齐等评估指标上达到了最先进的性能和速度优势。
英文摘要：
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling in diffusion models poses challenges for efficient video editing. Existing approaches relying on image generation models for video editing suffer from time-consuming one-shot fine-tuning, additional condition extraction, or DDIM inversion, making real-time applications impractical. In this work, we propose FastVideoEdit, an efficient zero-shot video editing approach inspired by Consistency Models (CMs). By leveraging the self-consistency property of CMs, we eliminate the need for time-consuming inversion or additional condition extraction, reducing editing time. Our method enables direct mapping from source video to target video with strong preservation ability utilizing a special variance schedule. This results in improved speed advantages, as fewer sampling steps can be used while maintaining comparable generation quality. Experimental results validate the state-of-the-art performance and speed advantages of FastVideoEdit across evaluation metrics encompassing editing speed, temporal consistency, and text-video alignment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
