|国家预印本平台
首页|Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

来源:Arxiv_logoArxiv
英文摘要

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/

Li Sun、Manlin Zhang、Renfei Sun、Xiaobin Zhuang、Xiaojie Li、Xin Xia、Xuyan Chi、Yanghua Peng、Yuping Wang、Yuxuan Wang、Zhongkai Zhao、Zhuo Chen、Zuquan Song、Zhenheng Yang、Jiashi Feng、Jianchao Yang、Lu Jiang、Team Seawead、Ceyuan Yang、Zhijie Lin、Yang Zhao、Shanchuan Lin、Zhibei Ma、Haoyuan Guo、Hao Chen、Lu Qi、Sen Wang、Feng Cheng、Feilong Zuo、Xuejiao Zeng、Ziyan Yang、Fangyuan Kong、Meng Wei、Zhiwu Qing、Fei Xiao、Tuyen Hoang、Siyu Zhang、Peihao Zhu、Qi Zhao、Jiangqiao Yan、Liangke Gui、Sheng Bi、Jiashi Li、Yuxi Ren、Rui Wang、Huixia Li、Xuefeng Xiao、Shu Liu、Feng Ling、Heng Zhang、Houmin Wei、Huafeng Kuang、Jerry Duncan、Junda Zhang、Junru Zheng

计算技术、计算机技术

Li Sun,Manlin Zhang,Renfei Sun,Xiaobin Zhuang,Xiaojie Li,Xin Xia,Xuyan Chi,Yanghua Peng,Yuping Wang,Yuxuan Wang,Zhongkai Zhao,Zhuo Chen,Zuquan Song,Zhenheng Yang,Jiashi Feng,Jianchao Yang,Lu Jiang,Team Seawead,Ceyuan Yang,Zhijie Lin,Yang Zhao,Shanchuan Lin,Zhibei Ma,Haoyuan Guo,Hao Chen,Lu Qi,Sen Wang,Feng Cheng,Feilong Zuo,Xuejiao Zeng,Ziyan Yang,Fangyuan Kong,Meng Wei,Zhiwu Qing,Fei Xiao,Tuyen Hoang,Siyu Zhang,Peihao Zhu,Qi Zhao,Jiangqiao Yan,Liangke Gui,Sheng Bi,Jiashi Li,Yuxi Ren,Rui Wang,Huixia Li,Xuefeng Xiao,Shu Liu,Feng Ling,Heng Zhang,Houmin Wei,Huafeng Kuang,Jerry Duncan,Junda Zhang,Junru Zheng.Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model[EB/OL].(2025-04-11)[2025-06-06].https://arxiv.org/abs/2504.08685.点此复制

评论