arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.09642cs.GRcs.AI
收藏

Open-Sora 2.0:在20万美元内训练一个商业级视频生成模型

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Department of XXX, University of YYY, Location, Country(XXX系,YYY大学,地点,国家);School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,地点,国家)
Zangwei Zheng, Xiangyu Peng, Yuxuan Lou, Chenhui Shen, Tom Young, Xinying Guo, Binluo Wang, Hang Xu, Hongxin Liu, Mingyan Jiang, Wenjun Li, Yuhui Wang, Anbang Y… 展开作者

Zangwei Zheng, Xiangyu Peng, Yuxuan Lou, Chenhui Shen, Tom Young, Xinying Guo, Binluo Wang, Hang Xu, Hongxin Liu, Mingyan Jiang, Wenjun Li, Yuhui Wang, Anbang Ye, Gang Ren, Qianran Ma, Wanying Liang, Xiang Lian, Xiwen Wu, Yuting Zhong, Zhuangyan Li, Chaoyu Gong, Guojun Lei, Leijun Cheng, Limin Zhang, Minghao Li, Ruijie Zhang, Silan Hu, Shijie Huang, Xiaokang Wang, Yuanheng Zhao, Yuqi Wang, Ziang Wei, Yang You

AI总结:

Open-Sora 2.0通过低成本训练实现了商业级视频生成模型,展示了训练成本的可控性,并开源促进视频生成技术的普及与创新。

摘要:

视频生成模型在过去一年中取得了显著进展。AI视频的质量持续提升,但代价是更大的模型规模、更多的数据量以及更高的训练计算需求。在本报告中,我们介绍了Open-Sora 2.0,这是一个仅用20万美元训练出的商业级视频生成模型。通过该模型,我们证明了训练顶级视频生成模型的成本具有高度可控性。我们详细介绍了所有促成这一效率突破的技术,包括数据整理、模型架构、训练策略和系统优化。根据人类评估结果和VBench分数,Open-Sora 2.0与全球领先的视频生成模型,包括开源的HunyuanVideo和闭源的Runway Gen-3 Alpha相当。通过将Open-Sora 2.0完全开源,我们旨在普及先进的视频生成技术,促进内容创作领域更广泛创新和创造力。所有资源均在:https://github.com/hpcaitech/Open-Sora 上公开。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑