World Labs just pulled the curtain back on Atlas, a model the company is calling an “omni world model” for spatial intelligence. It generates and reconstructs 3D images and videos with full camera control, pushing the boundaries of what AI can do when it actually understands physical space.
The model, unveiled on September 1, 2026, represents a major leap for the startup co-founded by Stanford AI luminary Fei-Fei Li. Atlas can produce pixel-perfect, camera-controlled imagery and video at resolutions up to 1440p, running for durations of up to one minute.
What Atlas actually does
Technically, Atlas is a multimodal autoregressive diffusion transformer. In plainer terms, it’s a single model that can process and generate across text, images, video, and 3D data simultaneously, all within a unified spatial framework.
World Labs claims the model’s spatial reconstruction capabilities outpace existing specialized 3D models.
The road from Marble to Atlas
Atlas didn’t materialize out of thin air. It builds on Marble, World Labs’ first commercial multimodal model, which went public in November 2025. Marble supported 3D world creation from multimodal inputs and served as the proving ground for the spatial intelligence framework that Atlas now supercharges.
The company followed Marble with the launch of its World API in January 2026, giving developers programmatic access to spatial intelligence tools.
In July 2026, just weeks before the Atlas announcement, World Labs acquired SceniX to strengthen its capabilities in robotics-related spatial intelligence.
$1.23 billion in backing and some very notable names
World Labs has raised a total of $1.23 billion across its funding rounds. The company secured $230 million when it was established in 2024, reaching an estimated valuation of $1 billion. Then came February 2026, when World Labs closed an additional $1 billion round. Autodesk alone contributed $200 million to that raise.
AMD, NVIDIA, and Fidelity have all backed the company.