World Labs, the AI startup co-founded by Stanford AI luminary Fei-Fei Li, unveiled Atlas on September 1, 2026. This model, described as an « omni world model, » generates and reconstructs 3D images and videos with full camera control at resolutions up to 1440p for durations of up to one minute. Technically, Atlas is a multimodal autoregressive diffusion transformer capable of processing and generating across text, images, video, and 3D data simultaneously. World Labs claims the model’s spatial reconstruction capabilities outpace existing specialized 3D models. The startup has raised a total of $1.23 billion, with Autodesk alone contributing $200 million, alongside backing from AMD, NVIDIA, and Fidelity.
Source: Read the original article
