Hunyuan3D 2.0 is an advanced large-scale 3D synthesis system designed to generate high-resolution textured 3D assets. It consists of two core components Hunyuan3D-DiT, a scalable flow-based diffusion transformer for shape generation that ensures alignment with input conditions, and Hunyuan3D-Paint, a texture synthesis model that produces high-quality, vibrant textures using geometric and diffusion priors. Additionally, Hunyuan3D-Studio provides a user-friendly platform for asset creation, manipulation, and animation, catering to both professionals and amateurs. Evaluations demonstrate that Hunyuan3D 2.0 surpasses previous state-of-the-art models (both open- and closed-source) in geometry detail, condition alignment, and texture quality. The system is publicly released to advance the open-source 3D generative modeling community.

We propose a two-stage approach named Hunyuan3D-1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multiview RGB in approximately 4 seconds. In the second stage, we introduce a feedforward reconstruction model that rapidly and faithfully reconstructs the 3D asset given the generated multi-view images in approximately 7 seconds.