Goku: Flow Based Video Generative Foundation Models

Shoufa Chen, Chongjian Ge, Yuqi Zhang, Yida Zhang, Fengda Zhu, Hao Yang, Hongxiang Hao, Hui Wu, Zhichao Lai, Yifei Hu, Ting-Che Lin, Shilong Zhang, Fu Li, Chuan Li, Xing Wang, Yanghua Peng, Peize Sun, Ping Luo, Yi Jiang, Zehuan Yuan, Bingyue Peng, Xiaobing Liu; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 23516-23527

Abstract

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality visual generation, including the data curation pipeline, model architecture design, flow formulation, and advanced infrastructure for efficient and robust large-scale training. The Goku models demonstrate superior performance in both qualitative and quantitative evaluations, setting new benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and 83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for text-to-video tasks. We believe that this work provides valuable insights and practical advancements for the research community in developing joint image-and-video generation models.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_CVPR, author = {Chen, Shoufa and Ge, Chongjian and Zhang, Yuqi and Zhang, Yida and Zhu, Fengda and Yang, Hao and Hao, Hongxiang and Wu, Hui and Lai, Zhichao and Hu, Yifei and Lin, Ting-Che and Zhang, Shilong and Li, Fu and Li, Chuan and Wang, Xing and Peng, Yanghua and Sun, Peize and Luo, Ping and Jiang, Yi and Yuan, Zehuan and Peng, Bingyue and Liu, Xiaobing}, title = {Goku: Flow Based Video Generative Foundation Models}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {23516-23527} }