In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implicitly propagates diffusion features across frames, ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models, including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine transformations in both source and target images. Remarkably efficient, Fairy generates 120-frame 512x384 videos (4-second duration at 30 FPS) in just 14 seconds, outpacing prior works by at least 44x. A comprehensive user study, involving 1000 generated samples, confirms that our approach delivers superior quality, decisively outperforming established methods.
@article{arxiv.2312.13834,
title = {Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis},
author = {Bichen Wu and Ching-Yao Chuang and Xiaoyan Wang and Yichen Jia and Kapil Krishnakumar and Tong Xiao and Feng Liang and Licheng Yu and Peter Vajda},
journal= {arXiv preprint arXiv:2312.13834},
year = {2023}
}