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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Motamed, Saman, Van Gansbeke, Wouter, Van Gool, Luc
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2404.05519