RepoTencent HunyuanTencent Hunyuanpublished Jan 21, 2025seen 5d

Tencent-Hunyuan/Hunyuan3D-2

Python

Open original ↗

Captured source

source ↗
published Jan 21, 2025seen 5dcaptured 10hhttp 200method plain

Tencent-Hunyuan/Hunyuan3D-2

Description: High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Language: Python

License: NOASSERTION

Stars: 13929

Forks: 1431

Open issues: 238

Created: 2025-01-21T05:21:35Z

Pushed: 2025-10-28T09:58:12Z

Default branch: main

Fork: no

Archived: no

README: [中文阅读](README_zh_cn.md) [日本語で読む](README_ja_jp.md)

[//]: # ( )

[//]: # ( )

[//]: # ( )

“ Living out everyone’s imagination on creating and manipulating 3D assets.”

https://github.com/user-attachments/assets/a2cbc5b8-be22-49d7-b1c3-7aa2b20ba460

🔥 News

  • July 26, 2025: 🤗 We release the first open-source, simulation-capable, immersive 3D world generation model, HunyuanWorld-1.0!
  • June 23, 2025: 📄 Release the system technical report of Hunyuan3D 2.5.
  • June 13, 2025: 🤗 Release Hunyuan3D-2.1, fully open-sourced with new PBR model, VAE encoder, and all training code.
  • Apr 1, 2025: 🤗 Release turbo paint model Hunyuan3D-Paint-v2-0-Turbo, and multiview texture generation pipeline, try it [here](examples/fast_texture_gen_multiview.py)! Stay tuned for our new texture generation model RomanTex and PBR material generation MaterialMVP!
  • Mar 19, 2025: 🤗 Release turbo model Hunyuan3D-2-Turbo, Hunyuan3D-2mini-Turbo and FlashVDM.
  • Mar 18, 2025: 🤗 Release multiview shape model Hunyuan3D-2mv and 0.6B

shape model Hunyuan3D-2mini.

  • Feb 14, 2025: 🛠️ Release texture enhancement module, please obtain high-definition textures

via [here](minimal_demo.py)!

  • Feb 3, 2025: 🐎

Release Hunyuan3D-DiT-v2-0-Fast, our guidance distillation model that could half the dit inference time, see [here](minimal_demo.py) for usage.

  • Jan 27, 2025: 🛠️ Release Blender addon for Hunyuan3D 2.0, Check it out [here](#blender-addon).
  • Jan 23, 2025: 💬 We thank community members for

creating Windows installation tool, ComfyUI support with ComfyUI-Hunyuan3DWrapper and ComfyUI-3D-Pack and other awesome [extensions](#community-resources).

  • Jan 21, 2025: 💬 Enjoy exciting 3D generation on our website Hunyuan3D Studio!
  • Jan 21, 2025: 🤗 Release inference code and pretrained models

of Hunyuan3D 2.0. Please give it a try via huggingface space and our official site!

> Join our [Wechat](#) and [Discord](https://discord.gg/dNBrdrGGMa) group to discuss and find help from us.

| Wechat Group | Xiaohongshu | X | Discord | |--------------------------------------------------|-------------------------------------------------------|---------------------------------------------|---------------------------------------------------| | | | | |

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 e.t.c.

☯️ Hunyuan3D 2.0

Architecture

Hunyuan3D 2.0 features a two-stage generation pipeline, starting with the creation of a bare mesh, followed by the synthesis of a texture map for that mesh. This strategy is effective for decoupling the difficulties of shape and texture generation and also provides flexibility for texturing either generated or handcrafted meshes.

Performance

We have evaluated Hunyuan3D 2.0 with other open-source as well as close-source 3d-generation methods. The numerical results indicate that Hunyuan3D 2.0 surpasses all baselines in the quality of generated textured 3D assets and the condition following ability.

| Model | CMMD(⬇) | FID_CLIP(⬇) | FID(⬇) | CLIP-score(⬆) | |-------------------------|-----------|-------------|-------------|---------------| | Top Open-source Model1 | 3.591 | 54.639 | 289.287 | 0.787 | | Top Close-source Model1 | 3.600 | 55.866 | 305.922 | 0.779 | | Top Close-source Model2 | 3.368 | 49.744 | 294.628 | 0.806 | | Top Close-source Model3 | 3.218 | 51.574 | 295.691 | 0.799 | | Hunyuan3D 2.0 | 3.193 | 49.165 | 282.429 | 0.809 |

Generation results of Hunyuan3D 2.0:

🎁 Models Zoo

It takes 6 GB VRAM for shape generation and 16 GB for shape and texture generation in total.

Hunyuan3D-2-1 Series

| Model | Description | Date | Size | Huggingface | |----------------------|-------------------------------|------------|------|-----------------------------------------------------------------------------------------| | Hunyuan3D-DiT-v2-1 | Mini Image to Shape Model | 2025-06-13 | 3.0B | Download | | Hunyuan3D-Paint-v2-1 | Texture Generation Model | 2025-06-13 | 1.3B |…

Excerpt shown — open the source for the full document.

Notability

notability 9.0/10

High stars, major company, notable 3D model release