3D world model
A spatial camera drifts through a generated room that feels editable, explorable, and physically present.
What people can do
Start from the practical surface before reading sources and boundaries.
Create persistent 3D worlds from prompts, images, video, or spatial inputs for scenes that can be explored and reused.
A spatial camera drifts through a generated room that feels editable, explorable, and physically present.
Spatially consistent 3D worlds for creative and design workflows.
Marble has a public product surface and documentation; current quotas, billing, and API limits should be verified in World Labs' account and docs before quoting exact pricing.
Source: World Labs Marble documentation
Scene explainer
The page starts with the experience, then moves toward source-backed details.
01First impression
Marble turns images, text, video, or spatial layouts into persistent 3D worlds that can be edited and explored.
02Capability
Clear consumer-facing expression of world models as editable 3D spaces.
03Boundary
The public product focus is creation-oriented, not a full robotics simulator.
Marble is a generated 3D-world creation product, not a robotics simulator or a many-agent civilization environment.
Primary-source dossier with multiple public references.
Release signals
The company profile stays stable. These short signals explain what changed and point back to sources.
World Labs launched Marble as a visible product surface for creating, editing, and exploring generated 3D worlds.
PlatformWorld Labs described a programmable World API direction, shifting part of the Marble story from product demo toward developer platform.
FAQ
Use these notes to keep model comments grounded in official sources and careful category boundaries.
The site tracks systems that model environments, actions, spatial structure, or persistent simulated state. Pure text chatbots and ordinary video generators are only included when they provide a clear bridge toward interactive or physical world modeling.
Video models are included only when they help explain the path from generated clips to controllable spaces, physics-aware prediction, or agent-ready simulation. The site keeps that distinction explicit so video generation is not overstated as a finished world simulator.
Primary sources carry the most weight: official product pages, research posts, papers, documentation, code repositories, and company announcements. Secondary media can be referenced, but it stays labeled as reported or adjacent unless independently confirmed.
Useful comments add source links, corrections, release-status notes, comparison questions, or concrete reader context. Comments are public immediately, so readers should avoid private information and unsupported promotional claims.
Discussion
Add source-backed corrections, questions, or notes for this page.
Loading comments...