Home Projects Hunyuan3D-2
Hunyuan3D-2
Python

Hunyuan3D-2

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

by Tencent-Hunyuan · GitHub
Stars
Forks
Created
Last commit
Category
Language
3d3d-aigc3d-generationPython
View on GitHub
In plain words

Generate high-resolution 3D assets and worlds using advanced diffusion models.

From the README

Install
pip install -r requirements.txt
pip install -e .
# for texture

Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Hunyuan3D-2 — GitHub preview card
📈 Star history
14.3k14.1k
2026-06-282026-08-31
📈 Track Hunyuan3D-2

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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

Hunyuan3D-2 has 14.3k stars on GitHub. It has been forked 1.5k times. Hunyuan3D-2 is written mainly in Python. It has been in active development since 2025. Its main topics are 3d, 3d-aigc, 3d-generation, diffusion-models.

Frequently asked questions

What is Hunyuan3D-2?

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

Is Hunyuan3D-2 open source?

Hunyuan3D-2 is an open-source project.

Is Hunyuan3D-2 free?

Yes. Hunyuan3D-2 is free and open source — you can use, modify and self-host it.

What language is Hunyuan3D-2 written in?

Hunyuan3D-2 is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Hunyuan3D-2

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=tencent-hunyuan-hunyuan3d-2)](https://olud.ai/project/tencent-hunyuan-hunyuan3d-2.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.