# Tencent-Hunyuan/Hunyuan3D-2

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

Repository: https://github.com/Tencent-Hunyuan/Hunyuan3D-2
Canonical: https://ross.abutalabs.com/products/hunyuan3d-2
Homepage: https://3d.hunyuan.tencent.com/
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d, 3d-aigc, 3d-generation, image-to-3d, text-to-3d, texture-generation, hunyuan3d, diffusion-models, shape-generation, shape
Last push: 2025-10-28T09:58:12+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 49, release rhythm 35, longevity 42
- inputs: {"age_days": 589, "days_push": 309, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14646, forks 1517 (observed 2026-08-28T04:11:07.369885+00:00)

## What it is
Tencent's open-source Hunyuan3D-2 system for generating high-resolution 3D assets using large-scale diffusion models, supporting image-to-3D and text-to-3D generation with shape and texture synthesis. It provides Python pipelines, turbo variants for faster inference, and Hugging Face model releases.

## Use cases
- generate 3d models from a single image
- create 3d assets from text prompts
- add textures to generated 3d meshes
- produce game-ready 3d assets with ai
- convert photos into 3d meshes
- batch generate textured 3d models for prototyping

## When to choose
- you need AI-generated 3D meshes and textures from images or text
- you want a state-of-the-art open-source image-to-3D pipeline with GPU inference
- you need turbo variants for faster 3D asset generation

## When to avoid
- you need precise, artist-controlled CAD modeling
- you have no GPU available for diffusion model inference
- you need a no-code end-user tool rather than a Python pipeline

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, llm-inference
- domain: artificial-intelligence, deep-learning, graphics
- platform: python, cross-platform
- tags: 3d-generation, image-to-3d, text-to-3d, diffusion-models, texture-generation, shape-generation, hunyuan3d, 3d-assets, game-development, gpu, linux

## Member repositories
- Tencent-Hunyuan/Hunyuan3D-2 (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.369885+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:26.447400+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/Hunyuan3D-2 (fetched 2026-08-28T04:11:07.369885+00:00, sha fa99f3722f64)
  - homepage: https://3d.hunyuan.tencent.com/ (fetched 2026-08-29T08:05:37.806419+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.