Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models

arXiv:2404.05519v1 Announce Type: cross
Abstract: With recent advances in image and video diffusion models for content creation, a plethora of techniques have been proposed for customizing their generated content. In particular, manipulating the cross-attention layers of Text-to-Image (T2I) diffusion models has shown great promise in controlling the shape and location of objects in the scene. Transferring image-editing techniques to the video domain, however, is extremely challenging as object motion and temporal consistency are difficult to capture accurately. In this work, …

abstract advances arxiv attention cs.cv cs.lg diffusion diffusion models editing generated image text text-to-image text-to-video type video video diffusion zero-shot