OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

If you like our project, please give us a star ⭐ on GitHub for the latest update.

✨ Summary

OpenS2V-Eval introduces 180 prompts from seven major categories of S2V, which incorporate both real and synthetic test data. Furthermore, to accurately align human preferences with S2V benchmarks, we propose three automatic metrics: NexusScore, NaturalScore, GmeScore to separately quantify subject consistency, naturalness, and text relevance in generated videos. Building on this, we conduct a comprehensive evaluation of 18 representative S2V models, highlighting their strengths and weaknesses across different content.

📣 Evaluate Your Own Models

For how to evaluate your customized model like OpenS2V-Eval in the OpenS2V-Nexus paper, please refer to here.

⚙️ Get Videos Generated by Different S2V models

For more details, please refer to here.

💡 Description

• Repository: Code, Page, Dataset, Benchmark
• Paper: https://huggingface.co/papers/2505.20292
• Point of Contact: Shenghai Yuan

✏️ Citation

If you find our paper and code useful in your research, please consider giving a star and citation.

@article{yuan2025opens2v,
  title={OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation},
  author={Yuan, Shenghai and He, Xianyi and Deng, Yufan and Ye, Yang and Huang, Jinfa and Lin, Bin and Luo, Jiebo and Yuan, Li},
  journal={arXiv preprint arXiv:2505.20292},
  year={2025}
}