Modelpublic

ByteDance/BindWeave

sourceHugging Faceapache-2.0updated 10mo agoView on Hugging Face

91likes412downloads

Model Card

<h1 align="center"> BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration </h1>

![arXiv](https://arxiv.org/pdf/2510.00438)  ![project page](https://lzy-dot.github.io/BindWeave/)  <a href="https://huggingface.co/ByteDance/BindWeave"><img src="https://img.shields.io/static/v1?label=%F0%9F%A4%97%20Hugging%20Face&message=Model&color=orange"></a> </div>

<a href="https://arxiv.org/abs/2502.11079">BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration</a>

<div align="center"> <a href="https://scholar.google.com/citations?user=WelDcqkAAAAJ&hl=zh-CN">Zhaoyang Li</a> 1,2, <a href="https://openreview.net/profile?id=~DongjunQian1">Dongjun Qian</a> 2, <a href="https://scholar.google.com/citations?user=Kp3XAToAAAAJ&hl=zh-CN">Kai Su</a> 2*, <a href="https://scholar.google.com/citations?user=G6xrfhYAAAAJ&hl=zh-CN">Qishuai Diao</a> 2, <a href="https://openreview.net/profile?id=~XiangyangXia1">Xiangyang Xia</a> 2, <a href="https://openreview.net/profile?id=~Chang_Liu71">Chang Liu</a> 2, <a href="https://scholar.google.com/citations?user=rtO5VmQAAAAJ&hl=zh-CN">Wenfei Yang</a> 1, <a href="https://scholar.google.com/citations?user=9sCGe-gAAAAJ&hl=en">Tianzhu Zhang</a> 1, <a href="https://shallowyuan.github.io/">Zehuan Yuan</a> 2 1University of Science and Technology of China 2ByteDance Corresponding Author </div>

📖 Overview

BindWeave is a unified subject-consistent video generation framework for single- and multi-subject prompts, built on an MLLM-DiT architecture that couples a pretrained multimodal large language model with a diffusion transformer. It achieves cross-modal integration via entity grounding and representation alignment, leveraging the MLLM to parse complex prompts and produce subject-aware hidden states that condition the DiT for high-fidelity generation. For more details or tutorials refer to ByteDance/BindWeave

OpenS2V-Eval Performance 🏆

BindWeave achieves a solid score of 57.61 on the OpenS2V-Eval benchmark, highlighting its robust capabilities across multiple evaluation dimensions and demonstrating competitive performance against several leading open-source and commercial systems.

Model	TotalScore↑	AestheticScore↑	MotionSmoothness↑	MotionAmplitude↑	FaceSim↑	GmeScore↑	NexusScore↑	NaturalScore↑
BindWeave	57.61%	45.55%	95.90%	13.91%	53.71%	67.79%	46.84%	66.85%
VACE-14B	57.55%	47.21%	94.97%	15.02%	55.09%	67.27%	44.08%	67.04%
Phantom-14B	56.77%	46.39%	96.31%	33.42%	51.46%	70.65%	37.43%	69.35%
Kling1.6(20250503)	56.23%	44.59%	86.93%	41.6%	40.1%	66.2%	45.89%	74.59%
Phantom-1.3B	54.89%	46.67%	93.3%	14.29%	48.56%	69.43%	42.48%	62.5%
MAGREF-480P	52.51%	45.02%	93.17%	21.81%	30.83%	70.47%	43.04%	66.9%
SkyReels-A2-P14B	52.25%	39.41%	87.93%	25.6%	45.95%	64.54%	43.75%	60.32%
Vidu2.0(20250503)	51.95%	41.48%	90.45%	13.52%	35.11%	67.57%	43.37%	65.88%
Pika2.1(20250503)	51.88%	46.88%	87.06%	24.71%	30.38%	69.19%	45.4%	63.32%
VACE-1.3B	49.89%	48.24%	97.2%	18.83%	20.57%	71.26%	37.91%	65.46%
VACE-P1.3B	48.98%	47.34%	96.8%	12.03%	16.59%	71.38%	40.19%	64.31%

BibTeX

bibtex

@article{li2025bindweave,
  title={BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration},
  author={Li, Zhaoyang and Qian, Dongjun and Su, Kai and Diao, Qishuai and Xia, Xiangyang and Liu, Chang and Yang, Wenfei and Zhang, Tianzhu and Yuan, Zehuan},
  journal={arXiv preprint arXiv:2510.00438},
  year={2025}
}