Cover Image

HunyuanVideo 1.5 Technical Report

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Bing, Zou, Chang, Li, Changlin, Huang, Duojun, Yang, Fang, Tan, Hao, Peng, Jack, Wu, Jianbing, Xiong, Jiangfeng, Jiang, Jie, Linus, Patrol, Zhang, Peizhen, Chen, Peng, Zhao, Penghao, Tian, Qi, Liu, Songtao, Kong, Weijie, Wang, Weiyan, He, Xiao, Li, Xin, Deng, Xinchi, Zhe, Xuefei, Li, Yang, Long, Yanxin, Peng, Yuanbo, Wu, Yue, Liu, Yuhong, Wang, Zhenyu, Dai, Zuozhuo, Peng, Bo, Li, Coopers, Gong, Gu, Xiao, Guojian, Tian, Jiahe, Lin, Jiaxin, Liu, Jie, Zhang, Jihong, Lian, Jiesong, Pan, Kaihang, Wang, Lei, Niu, Lin, Chen, Mingtao, Chen, Mingyang, Zheng, Mingzhe, Yang, Miles, Hu, Qiangqiang, Yang, Qi, Xiao, Qiuyong, Wu, Runzhou, Xu, Ryan, Yuan, Rui, Sang, Shanshan, Huang, Shisheng, Gong, Siruis, Huang, Shuo, Guo, Weiting, Yuan, Xiang, Chen, Xiaojia, Hu, Xiawei, Sun, Wenzhi, Wu, Xiele, Ren, Xianshun, Yuan, Xiaoyan, Mi, Xiaoyue, Zhang, Yepeng, Sun, Yifu, Lu, Yiting, Li, Yitong, Huang, You, Tang, Yu, Li, Yixuan, Deng, Yuhang, Zhou, Yuan, Hu, Zhichao, Liu, Zhiguang, Yang, Zhihe, Yang, Zilin, Lu, Zhenzhi, Zhou, Zixiang, Zhong, Zhao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866918217202532352
author	Wu, Bing Zou, Chang Li, Changlin Huang, Duojun Yang, Fang Tan, Hao Peng, Jack Wu, Jianbing Xiong, Jiangfeng Jiang, Jie Linus Patrol Zhang, Peizhen Chen, Peng Zhao, Penghao Tian, Qi Liu, Songtao Kong, Weijie Wang, Weiyan He, Xiao Li, Xin Deng, Xinchi Zhe, Xuefei Li, Yang Long, Yanxin Peng, Yuanbo Wu, Yue Liu, Yuhong Wang, Zhenyu Dai, Zuozhuo Peng, Bo Li, Coopers Gong, Gu Xiao, Guojian Tian, Jiahe Lin, Jiaxin Liu, Jie Zhang, Jihong Lian, Jiesong Pan, Kaihang Wang, Lei Niu, Lin Chen, Mingtao Chen, Mingyang Zheng, Mingzhe Yang, Miles Hu, Qiangqiang Yang, Qi Xiao, Qiuyong Wu, Runzhou Xu, Ryan Yuan, Rui Sang, Shanshan Huang, Shisheng Gong, Siruis Huang, Shuo Guo, Weiting Yuan, Xiang Chen, Xiaojia Hu, Xiawei Sun, Wenzhi Wu, Xiele Ren, Xianshun Yuan, Xiaoyan Mi, Xiaoyue Zhang, Yepeng Sun, Yifu Lu, Yiting Li, Yitong Huang, You Tang, Yu Li, Yixuan Deng, Yuhang Zhou, Yuan Hu, Zhichao Liu, Zhiguang Yang, Zhihe Yang, Zilin Lu, Zhenzhi Zhou, Zixiang Zhong, Zhao
author_facet	Wu, Bing Zou, Chang Li, Changlin Huang, Duojun Yang, Fang Tan, Hao Peng, Jack Wu, Jianbing Xiong, Jiangfeng Jiang, Jie Linus Patrol Zhang, Peizhen Chen, Peng Zhao, Penghao Tian, Qi Liu, Songtao Kong, Weijie Wang, Weiyan He, Xiao Li, Xin Deng, Xinchi Zhe, Xuefei Li, Yang Long, Yanxin Peng, Yuanbo Wu, Yue Liu, Yuhong Wang, Zhenyu Dai, Zuozhuo Peng, Bo Li, Coopers Gong, Gu Xiao, Guojian Tian, Jiahe Lin, Jiaxin Liu, Jie Zhang, Jihong Lian, Jiesong Pan, Kaihang Wang, Lei Niu, Lin Chen, Mingtao Chen, Mingyang Zheng, Mingzhe Yang, Miles Hu, Qiangqiang Yang, Qi Xiao, Qiuyong Wu, Runzhou Xu, Ryan Yuan, Rui Sang, Shanshan Huang, Shisheng Gong, Siruis Huang, Shuo Guo, Weiting Yuan, Xiang Chen, Xiaojia Hu, Xiawei Sun, Wenzhi Wu, Xiele Ren, Xianshun Yuan, Xiaoyan Mi, Xiaoyue Zhang, Yepeng Sun, Yifu Lu, Yiting Li, Yitong Huang, You Tang, Yu Li, Yixuan Deng, Yuhang Zhou, Yuan Hu, Zhichao Liu, Zhiguang Yang, Zhihe Yang, Zilin Lu, Zhenzhi Zhou, Zixiang Zhong, Zhao
contents	We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.
format	Preprint
id	arxiv_https___arxiv_org_abs_2511_18870
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	HunyuanVideo 1.5 Technical Report Wu, Bing Zou, Chang Li, Changlin Huang, Duojun Yang, Fang Tan, Hao Peng, Jack Wu, Jianbing Xiong, Jiangfeng Jiang, Jie Linus Patrol Zhang, Peizhen Chen, Peng Zhao, Penghao Tian, Qi Liu, Songtao Kong, Weijie Wang, Weiyan He, Xiao Li, Xin Deng, Xinchi Zhe, Xuefei Li, Yang Long, Yanxin Peng, Yuanbo Wu, Yue Liu, Yuhong Wang, Zhenyu Dai, Zuozhuo Peng, Bo Li, Coopers Gong, Gu Xiao, Guojian Tian, Jiahe Lin, Jiaxin Liu, Jie Zhang, Jihong Lian, Jiesong Pan, Kaihang Wang, Lei Niu, Lin Chen, Mingtao Chen, Mingyang Zheng, Mingzhe Yang, Miles Hu, Qiangqiang Yang, Qi Xiao, Qiuyong Wu, Runzhou Xu, Ryan Yuan, Rui Sang, Shanshan Huang, Shisheng Gong, Siruis Huang, Shuo Guo, Weiting Yuan, Xiang Chen, Xiaojia Hu, Xiawei Sun, Wenzhi Wu, Xiele Ren, Xianshun Yuan, Xiaoyan Mi, Xiaoyue Zhang, Yepeng Sun, Yifu Lu, Yiting Li, Yitong Huang, You Tang, Yu Li, Yixuan Deng, Yuhang Zhou, Yuan Hu, Zhichao Liu, Zhiguang Yang, Zhihe Yang, Zilin Lu, Zhenzhi Zhou, Zixiang Zhong, Zhao Computer Vision and Pattern Recognition We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.
title	HunyuanVideo 1.5 Technical Report
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2511.18870