Welcome to use OpenS2V-Nexus to evaluate your latest models #2
Description
@wangqiang9 Thanks for great work! We recently tackle the core challenges of Subject-to-Video Generation (S2V) by systematically building the first complete infrastructure—featuring an evaluation benchmark and a million-scale dataset! ✨Welcom to try it!
🧠 Introducing OpenS2V-Eval—the first fine-grained S2V benchmark, with 180 multi-domain prompts + real/synthetic test pairs. We propose NexusScore, NaturalScore, and GmeScore to precisely quantify model performance across subject consistency, naturalness, and text alignment ✔
📊 Using this framework, we conduct a comprehensive evaluation of 16 leading S2V models, revealing their strengths/weaknesses in complex scenarios! (including Fantasy-ID)
🔥 OpenS2V-5M dataset now available! A 5.4M 720P HD collection of subject-text-video triplets, enabled by cross-video association segmentation + multi-view synthesis for diverse subjects & high-quality annotations 🚀
All resources open-sourced: Paper, Code, Data, and Evaluation Tools 📄
Let's advance S2V research together! 💡
🔗 Links:
Code: https://github.com/PKU-YuanGroup/OpenS2V-Nexus
Project: https://pku-yuangroup.github.io/OpenS2V-Nexus
LeaderBoard: https://huggingface.co/spaces/BestWishYsh/OpenS2V-Eval
OpenS2V-5M: https://huggingface.co/datasets/BestWishYsh/OpenS2V-5M