_version_ 1866911477064007680
author Zheng, Zangwei
Peng, Xiangyu
Lou, Yuxuan
Shen, Chenhui
Young, Tom
Guo, Xinying
Wang, Binluo
Xu, Hang
Liu, Hongxin
Jiang, Mingyan
Li, Wenjun
Wang, Yuhui
Ye, Anbang
Ren, Gang
Ma, Qianran
Liang, Wanying
Lian, Xiang
Wu, Xiwen
Zhong, Yuting
Li, Zhuangyan
Gong, Chaoyu
Lei, Guojun
Cheng, Leijun
Zhang, Limin
Li, Minghao
Zhang, Ruijie
Hu, Silan
Huang, Shijie
Wang, Xiaokang
Zhao, Yuanheng
Wang, Yuqi
Wei, Ziang
You, Yang
author_facet Zheng, Zangwei
Peng, Xiangyu
Lou, Yuxuan
Shen, Chenhui
Young, Tom
Guo, Xinying
Wang, Binluo
Xu, Hang
Liu, Hongxin
Jiang, Mingyan
Li, Wenjun
Wang, Yuhui
Ye, Anbang
Ren, Gang
Ma, Qianran
Liang, Wanying
Lian, Xiang
Wu, Xiwen
Zhong, Yuting
Li, Zhuangyan
Gong, Chaoyu
Lei, Guojun
Cheng, Leijun
Zhang, Limin
Li, Minghao
Zhang, Ruijie
Hu, Silan
Huang, Shijie
Wang, Xiaokang
Zhao, Yuanheng
Wang, Yuqi
Wei, Ziang
You, Yang
contents Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only $200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
Zheng, Zangwei
Peng, Xiangyu
Lou, Yuxuan
Shen, Chenhui
Young, Tom
Guo, Xinying
Wang, Binluo
Xu, Hang
Liu, Hongxin
Jiang, Mingyan
Li, Wenjun
Wang, Yuhui
Ye, Anbang
Ren, Gang
Ma, Qianran
Liang, Wanying
Lian, Xiang
Wu, Xiwen
Zhong, Yuting
Li, Zhuangyan
Gong, Chaoyu
Lei, Guojun
Cheng, Leijun
Zhang, Limin
Li, Minghao
Zhang, Ruijie
Hu, Silan
Huang, Shijie
Wang, Xiaokang
Zhao, Yuanheng
Wang, Yuqi
Wei, Ziang
You, Yang
Graphics
Artificial Intelligence
Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only $200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.
title Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2503.09642