AI · Web app
World Labs: Generating Worlds
Spatial AI generating persistent, navigable 3D worlds from single images.
World Labs' research demo showcases spatial intelligence AI that generates interactive 3D environments from single 2D images. Users can explore the generated worlds directly in the browser using standard camera and movement controls, viewing both color and underlying depth maps. It represents an early look at creating consistent, explorable 3D scenes without manual modeling.
What it's for
- Explore 3D spatial environments generated directly from still images
- Inspect scene geometry and depth mapping for computer vision research
- Prototype navigable backgrounds for games, VFX, and interactive media
Features
- Browser-based interactive 3D navigation using WASD and mouse controls
- Color and depth map view toggles to inspect spatial geometry
- Camera controls including depth of field adjustment
- Interactive scene effects such as sonar, spotlight, and ripple
Pricing
Free research demonstration
Details
- Type
- Web app
- Category
- AI
- Topic
- 3D Generation
- Open source
- No
- Platforms
- Web
- For
- Game developers, 3D artists, filmmakers, and AI researchers
- Alternative to
- Luma Dream Machine, Runway Gen-3
- Tags
- 3d generation, spatial ai, world models, computer vision, interactive 3d
Why it was saved
- @rpn: Enables creators, game developers, and filmmakers to turn any still picture into an explorable 3D environment complete with camera controls, depth mapping, and interactive movement.
Compare
Related
Turn text prompts and 2D images into textured, printable 3D models.
Turn freehand sketches into textured 3D models inside a Three.js scene
Rebuilds reference images as procedural, animation-ready Three.js models in code.
Open-source 4B flow-matching model generating textured 3D assets from single images.
AI model that generates textured 3D assets from single images
AI generator converting text and 2D images into 3D models.
Updated