# Tencent-Hunyuan/HunyuanWorld-1.0

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Repository: https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0
Canonical: https://ross.abutalabs.com/products/hunyuanworld-10
Homepage: https://3d.hunyuan.tencent.com/sceneTo3D
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d, 3d-generation, hunyuan3d, scene-generation, aigc, image-to-3d, text-to-3d, world-model, world-models
Last push: 2026-04-15T17:27:25+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 35, longevity 29
- inputs: {"age_days": 411, "days_push": 140, "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 2918, forks 263 (observed 2026-08-28T04:07:30.159656+00:00)

## What it is
Tencent HunyuanWorld-1.0 is an open-source 3D world generation model that creates immersive, explorable, and interactive 3D worlds from text prompts or images. It is the first open-source, simulation-capable 3D world model, released with a technical report and a quantized lite version for consumer GPUs.

## Use cases
- generate explorable 3D worlds from text descriptions
- create 3D scenes from a single image
- build simulation environments for AI training
- generate game-ready 3D environments from prompts
- convert photos into interactive 3D worlds
- run 3D world generation on a consumer GPU like a 4090

## When to choose
- you need to generate explorable 3D scenes from text or images
- you want an open-source, simulation-capable world model
- you need 3D content generation for games, VR, or simulation
- you want to run world generation locally on consumer GPUs with the lite version

## When to avoid
- you need real-time interactive world play (consider HunyuanWorld-1.5/WorldPlay)
- you need 3D generation from videos or multi-view images (consider HunyuanWorld-1.1/Mirror)
- you need a permissively licensed model for commercial use without checking the custom license
- you lack a capable GPU and cannot use the quantized lite version

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, graphics, simulation
- platform: python
- tags: 3d-generation, text-to-3d, image-to-3d, world-model, scene-generation, aigc, 3dgs, hunyuan, game-development, gpu, linux

## Member repositories
- Tencent-Hunyuan/HunyuanWorld-1.0 (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.159656+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 2026-08-30T07:34:01.452834+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0 (fetched 2026-08-28T04:07:30.159656+00:00, sha f230f22d6b19)
  - homepage: https://3d.hunyuan.tencent.com/sceneTo3D (fetched 2026-08-29T09:49:12.766155+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.