# Tencent-Hunyuan/Hunyuan3D-2.1

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Repository: https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1
Canonical: https://ross.abutalabs.com/products/hunyuan3d-21
Homepage: https://3d.hunyuan.tencent.com/
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d, 3d-aigc, 3d-generation, hunyuan3d, image-to-3d, shape, shape-generation, text-to-3d, texture-genertaion
Last push: 2025-10-17T10:10:07+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 47, release rhythm 35, longevity 31
- inputs: {"age_days": 446, "days_push": 320, "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 3917, forks 587 (observed 2026-08-28T04:08:28.935027+00:00)

## What it is
Tencent's open-source 3D asset generation model that creates high-fidelity 3D meshes with production-ready PBR materials from single images or text prompts. It is a Python-based deep learning system released with pretrained weights on Hugging Face.

## Use cases
- generate 3d models from images
- create game assets from a single photo
- text to 3d mesh generation
- generate pbr textured 3d assets
- build 3d models for ar/vr applications
- automate 3d asset creation pipeline

## When to choose
- you need production-ready 3D assets with PBR textures from images or text
- you want an open-source state-of-the-art image-to-3D model with pretrained weights
- you need programmable 3D generation integrated into a Python or ComfyUI pipeline

## When to avoid
- you need precise, CAD-quality parametric modeling rather than generated meshes
- you lack a GPU or cannot run large diffusion models locally
- you need permissively licensed assets for commercial use without checking the custom license

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

## Member repositories
- Tencent-Hunyuan/Hunyuan3D-2.1 (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:28.935027+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 2026-08-29T18:25:02.217674+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/Hunyuan3D-2.1 (fetched 2026-08-28T04:08:28.935027+00:00, sha f5022fe78acc)
  - homepage: https://3d.hunyuan.tencent.com/ (fetched 2026-08-29T09:18:52.960931+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.