Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts

arXiv:2305.08850v2 Announce Type: replace
Abstract: The text-driven image and video diffusion models have achieved unprecedented success in generating realistic and diverse content. Recently, the editing and variation of existing images and videos in diffusion-based generative models have garnered significant attention. However, previous works are limited to editing content with text or providing coarse personalization using a single visual clue, rendering them unsuitable for indescribable content that requires fine-grained and detailed control. In this regard, we propose a generic video editing …

abstract arxiv attention cs.cv diffusion diffusion models diverse editing ensemble experts generative generative models image images success text type variation video video diffusion videos