Search papers, labs, and topics across Lattice.
Hunyuan3D 2.0 is presented as a large-scale 3D synthesis system comprising Hunyuan3D-DiT, a shape generation model based on a flow-based diffusion transformer, and Hunyuan3D-Paint, a texture synthesis model leveraging geometric and diffusion priors. The system generates high-resolution textured 3D assets and includes Hunyuan3D-Studio, a user-friendly platform for manipulating and animating meshes. Evaluations demonstrate that Hunyuan3D 2.0 surpasses existing state-of-the-art models in geometry detail, condition alignment, and texture quality.
Open-source 3D asset generation just leveled up: Hunyuan3D 2.0 delivers high-resolution, textured 3D models that outperform both open and closed-source alternatives.
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
