← Search

Kapil Krishnakumar

1 accepted papers

2024

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

CVPR 2024poster

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 ensur…

Cited by 25SourcePDFScholar