Visionary-Laboratory/visionary
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Supports plug-and-play neural algorithms via a standardized Gaussian Generator contract with per-frame ONNX inference, enabling dynamic variants like 4DGS, neural avatars, and post-processing networks—all rendered natively in WebGPU with GPU-based primitive sorting. Integrates seamlessly with three.js through a TypeScript API and provides a universal asset loader for static Gaussians (PLY, SPLAT, KSplat), meshes (GLB, GLTF, FBX, OBJ), and dynamic models exported as ONNX.
456 stars.
Stars
456
Forks
29
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Visionary-Laboratory/visionary"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...