视频大模型

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation

Sizhe Shan, Qiulin Li, Yutao Cui, Miles Yang, Yuehai Wang, Qun Yang, Jin Zhou, Zhao Zhong

专题命中 视频扩散模型 ：video generation(abstract)；分类 cs.CV

OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models

Huanpeng Chu, Wei Wu, Guanyu Fen, Yutao Zhang

机构 * Zhipu AI（智谱AI） 纠错

专题命中 视频扩散模型 ：video generation(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025