_version_ 1866911684584538112
author Zhao, Zibo
Lai, Zeqiang
Lin, Qingxiang
Zhao, Yunfei
Liu, Haolin
Yang, Shuhui
Feng, Yifei
Yang, Mingxin
Zhang, Sheng
Yang, Xianghui
Shi, Huiwen
Liu, Sicong
Wu, Junta
Lian, Yihang
Yang, Fan
Tang, Ruining
He, Zebin
Wang, Xinzhou
Liu, Jian
Zuo, Xuhui
Chen, Zhuo
Lei, Biwen
Weng, Haohan
Xu, Jing
Zhu, Yiling
Liu, Xinhai
Xu, Lixin
Hu, Changrong
Yang, Shaoxiong
Zhang, Song
Liu, Yang
Huang, Tianyu
Wang, Lifu
Zhang, Jihong
Chen, Meng
Dong, Liang
Jia, Yiwen
Cai, Yulin
Yu, Jiaao
Tang, Yixuan
Zhang, Hao
Ye, Zheng
He, Peng
Wu, Runzhou
Zhang, Chao
Tan, Yonghao
Xiao, Jie
Tao, Yangyu
Zhu, Jianchen
Xue, Jinbao
Liu, Kai
Zhao, Chongqing
Wu, Xinming
Hu, Zhichao
Qin, Lei
Peng, Jianbing
Li, Zhan
Chen, Minghui
Zhang, Xipeng
Niu, Lin
Wang, Paige
Wang, Yingkai
Kuang, Haozhao
Fan, Zhongyi
Zheng, Xu
Zhuang, Weihao
He, YingPing
Liu, Tian
Yang, Yong
Wang, Di
Liu, Yuhong
Jiang, Jie
Huang, Jingwei
Guo, Chunchao
author_facet Zhao, Zibo
Lai, Zeqiang
Lin, Qingxiang
Zhao, Yunfei
Liu, Haolin
Yang, Shuhui
Feng, Yifei
Yang, Mingxin
Zhang, Sheng
Yang, Xianghui
Shi, Huiwen
Liu, Sicong
Wu, Junta
Lian, Yihang
Yang, Fan
Tang, Ruining
He, Zebin
Wang, Xinzhou
Liu, Jian
Zuo, Xuhui
Chen, Zhuo
Lei, Biwen
Weng, Haohan
Xu, Jing
Zhu, Yiling
Liu, Xinhai
Xu, Lixin
Hu, Changrong
Yang, Shaoxiong
Zhang, Song
Liu, Yang
Huang, Tianyu
Wang, Lifu
Zhang, Jihong
Chen, Meng
Dong, Liang
Jia, Yiwen
Cai, Yulin
Yu, Jiaao
Tang, Yixuan
Zhang, Hao
Ye, Zheng
He, Peng
Wu, Runzhou
Zhang, Chao
Tan, Yonghao
Xiao, Jie
Tao, Yangyu
Zhu, Jianchen
Xue, Jinbao
Liu, Kai
Zhao, Chongqing
Wu, Xinming
Hu, Zhichao
Qin, Lei
Peng, Jianbing
Li, Zhan
Chen, Minghui
Zhang, Xipeng
Niu, Lin
Wang, Paige
Wang, Yingkai
Kuang, Haozhao
Fan, Zhongyi
Zheng, Xu
Zhuang, Weihao
He, YingPing
Liu, Tian
Yang, Yong
Wang, Di
Liu, Yuhong
Jiang, Jie
Huang, Jingwei
Guo, Chunchao
contents We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
format Preprint
id arxiv_https___arxiv_org_abs_2501_12202
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Zhao, Zibo
Lai, Zeqiang
Lin, Qingxiang
Zhao, Yunfei
Liu, Haolin
Yang, Shuhui
Feng, Yifei
Yang, Mingxin
Zhang, Sheng
Yang, Xianghui
Shi, Huiwen
Liu, Sicong
Wu, Junta
Lian, Yihang
Yang, Fan
Tang, Ruining
He, Zebin
Wang, Xinzhou
Liu, Jian
Zuo, Xuhui
Chen, Zhuo
Lei, Biwen
Weng, Haohan
Xu, Jing
Zhu, Yiling
Liu, Xinhai
Xu, Lixin
Hu, Changrong
Yang, Shaoxiong
Zhang, Song
Liu, Yang
Huang, Tianyu
Wang, Lifu
Zhang, Jihong
Chen, Meng
Dong, Liang
Jia, Yiwen
Cai, Yulin
Yu, Jiaao
Tang, Yixuan
Zhang, Hao
Ye, Zheng
He, Peng
Wu, Runzhou
Zhang, Chao
Tan, Yonghao
Xiao, Jie
Tao, Yangyu
Zhu, Jianchen
Xue, Jinbao
Liu, Kai
Zhao, Chongqing
Wu, Xinming
Hu, Zhichao
Qin, Lei
Peng, Jianbing
Li, Zhan
Chen, Minghui
Zhang, Xipeng
Niu, Lin
Wang, Paige
Wang, Yingkai
Kuang, Haozhao
Fan, Zhongyi
Zheng, Xu
Zhuang, Weihao
He, YingPing
Liu, Tian
Yang, Yong
Wang, Di
Liu, Yuhong
Jiang, Jie
Huang, Jingwei
Guo, Chunchao
Computer Vision and Pattern Recognition
We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model -- Hunyuan3D-DiT, and a large-scale texture synthesis model -- Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio -- a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and etc. Hunyuan3D 2.0 is publicly released in order to fill the gaps in the open-source 3D community for large-scale foundation generative models. The code and pre-trained weights of our models are available at: https://github.com/Tencent/Hunyuan3D-2
title Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.12202