April 23, 2024, 4:44 a.m. | Yash Jain, Anshul Nasery, Vibhav Vineet, Harkirat Behl

cs.LG updates on arXiv.org arxiv.org

arXiv:2312.07509v2 Announce Type: replace-cross
Abstract: Modern video generation models like Sora have achieved remarkable success in producing high-quality videos. However, a significant limitation is their inability to offer interactive control to users, a feature that promises to open up unprecedented applications and creativity. In this work, we introduce the first solution to equip diffusion-based video generation models with spatio-temporal control. We present Peekaboo, a novel masked attention module, which seamlessly integrates with current video generation models offering control without the …

abstract applications arxiv control creativity cs.cv cs.lg diffusion feature however interactive modern quality solution sora success type via video video generation videos work

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US