Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

In this report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.

@article{lai2025_2506.16504,
  title={ Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details },
  author={ Zeqiang Lai and Yunfei Zhao and Haolin Liu and Zibo Zhao and Qingxiang Lin and Huiwen Shi and Xianghui Yang and Mingxin Yang and Shuhui Yang and Yifei Feng and Sheng Zhang and Xin Huang and Di Luo and Fan Yang and Fang Yang and Lifu Wang and Sicong Liu and Yixuan Tang and Yulin Cai and Zebin He and Tian Liu and Yuhong Liu and Jie Jiang and Linus and Jingwei Huang and Chunchao Guo },
  journal={arXiv preprint arXiv:2506.16504},
  year={ 2025 }
}