# ZiYang-xie/WorldGen

🌍 WorldGen - Generate Any 3D Scene in Seconds

Repository: https://github.com/ZiYang-xie/WorldGen
Canonical: https://ross.abutalabs.com/products/worldgen
Language: Python
License: Apache-2.0
License Family: permissive
Topics: 3d-generation, 3d-reconstruction, generative-ai, scene-generation, worldgen, worldmodel, graphics, image-to-3d, text-to-3d
Last push: 2026-04-12T01:08:44+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 76, release rhythm 35, longevity 35
- inputs: {"age_days": 503, "days_push": 144, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2076, forks 197 (observed 2026-08-28T04:06:11.233340+00:00)

## What it is
WorldGen is a Python library that generates full 3D scenes in seconds from text prompts or images, supporting 360-degree consistent exploration and flexible real-time rendering. It targets creation of 3D environments for games, simulations, robotics, and VR applications.

## Use cases
- generate a 3D scene from a text prompt
- convert an image or painting into an explorable 3D scene
- create 3D environments for game development
- build simulation scenes for robotics testing
- render 3D scenes with custom camera trajectories
- generate VR-ready 3D worlds quickly

## When to choose
- you need fast text-to-3D or image-to-3D scene generation
- you want 360-degree explorable scenes with loop closure
- you need scenes for games, robotics simulation, or VR
- you want flexible rendering at any resolution and camera setting

## When to avoid
- you need precise, artist-controlled 3D modeling rather than generative output
- you lack a GPU or cannot run large generative models
- you need production-grade game assets with clean topology and PBR materials
- you need a lightweight tool without heavy ML dependencies

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, graphics, simulation, image-processing
- domain: artificial-intelligence, graphics, simulation, computer-vision
- platform: python, cross-platform
- tags: 3d-generation, text-to-3d, image-to-3d, scene-generation, generative-ai, world-model, gaussian-splatting, 3d-reconstruction, game-development, gpu

## Member repositories
- ZiYang-xie/WorldGen (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.233340+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 2026-08-30T02:56:10.838192+00:00, confidence not recorded.
  - readme: https://github.com/ZiYang-xie/WorldGen (fetched 2026-08-28T04:06:11.233340+00:00, sha e76d2062a948)
- Data as of 2026-08-30T08:39:29.467469+00:00.