ZiYang-xie/WorldGen
🌍 WorldGen - Generate Any 3D Scene in Seconds
Leverages diffusion models and gaussian splatting to generate 360° consistent 3D scenes from text or image inputs, with optional mesh output for production rendering. Supports both text-to-scene and image-to-scene generation modes, integrates with PyTorch3D and Viser for real-time visualization, and offers low-VRAM operation (~10GB) for accessibility. Outputs are exportable as .ply files compatible with standard gaussian splatting viewers or mesh applications.
1,568 stars. Actively maintained with 1 commit in the last 30 days.
Stars
1,568
Forks
127
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 11, 2026
Commits (30d)
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/ZiYang-xie/WorldGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
aioz-ai/AIOZ-GDANCE
AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)
Kobaayyy/Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2024-AIGC
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
worldbench/WorldLens
[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
nv-tlabs/XCube
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
worldbench/LiDARCrafter
[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences