ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2501.12202
75
19

Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

21 January 2025
Zibo Zhao
Zeqiang Lai
Qingxiang Lin
Yunfei Zhao
Haolin Liu
S. M. I. Simon X. Yang
Yifei Feng
M. Yang
Sheng Zhang
X. J. Yang
Huiwen Shi
Sicong Liu
J. Wu
Yihang Lian
Fan Yang
Ruining Tang
Z. He
X. Wang
Jian Liu
Xuhui Zuo
Zhuo Chen
Biwen Lei
Haohan Weng
Jing Xu
Yiling Zhu
Xinhai Liu
Lixin Xu
Changrong Hu
Tianyu Huang
Lifu Wang
Jihong Zhang
Meng Chen
Liang Dong
Yiwen Jia
Y. Cai
J. Yu
Yixuan Tang
Hao Zhang
Zheng Ye
Peng He
Runzhou Wu
C. Zhang
Yonghao Tan
Jie Xiao
Yangyu Tao
J. Zhu
J. Xue
Kai Liu
Chongqing Zhao
Xinming Wu
Zhichao Hu
L. Qin
Jianbing Peng
Z. Li
Minghui Chen
Xipeng Zhang
Lin Niu
Paige Wang
Y. Wang
Haozhao Kuang
Zhongyi Fan
Xu Zheng
Weihao Zhuang
Y. He
Tian Liu
Yong-Liang Yang
Di Wang
Y. Liu
Jie Jiang
Jingwei Huang
Chunchao Guo
Jie Jiang
Jingwei Huang
Chunchao Guo
ArXivPDFHTML
Abstract

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:this https URL

View on arXiv
@article{zhao2025_2501.12202,
  title={ Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation },
  author={ Zibo Zhao and Zeqiang Lai and Qingxiang Lin and Yunfei Zhao and Haolin Liu and Shuhui Yang and Yifei Feng and Mingxin Yang and Sheng Zhang and Xianghui Yang and Huiwen Shi and Sicong Liu and Junta Wu and Yihang Lian and Fan Yang and Ruining Tang and Zebin He and Xinzhou Wang and Jian Liu and Xuhui Zuo and Zhuo Chen and Biwen Lei and Haohan Weng and Jing Xu and Yiling Zhu and Xinhai Liu and Lixin Xu and Changrong Hu and Shaoxiong Yang and Song Zhang and Yang Liu and Tianyu Huang and Lifu Wang and Jihong Zhang and Meng Chen and Liang Dong and Yiwen Jia and Yulin Cai and Jiaao Yu and Yixuan Tang and Hao Zhang and Zheng Ye and Peng He and Runzhou Wu and Chao Zhang and Yonghao Tan and Jie Xiao and Yangyu Tao and Jianchen Zhu and Jinbao Xue and Kai Liu and Chongqing Zhao and Xinming Wu and Zhichao Hu and Lei Qin and Jianbing Peng and Zhan Li and Minghui Chen and Xipeng Zhang and Lin Niu and Paige Wang and Yingkai Wang and Haozhao Kuang and Zhongyi Fan and Xu Zheng and Weihao Zhuang and YingPing He and Tian Liu and Yong Yang and Di Wang and Yuhong Liu and Jie Jiang and Jingwei Huang and Chunchao Guo },
  journal={arXiv preprint arXiv:2501.12202},
  year={ 2025 }
}
Comments on this paper