World Labs unveils Atlas, an omni world model for spatial intelligence, early access soon
theworldlabs · x · 2026-09-02
World Labs introduces Atlas, its next-generation omni world model for spatial intelligence, with early access opening in the coming weeks.
Architecture
- A multimodal autoregressive diffusion transformer pretrained from scratch, natively operating on text, images, video, and 3D. All inputs combine into a shared spatial context; generation stays consistent in 3D with everything seen.
- Performance improves with training compute, and the team expects this scaling trend to hold.
Four task families
- Camera-controlled generation: images and video from one or more images with pixel-perfect camera control, up to 1 minute at 1440p.
- Spatial reconstruction: real-world scenes from 1 to dozens of images, outputting novel-view frames and explicit 3D, beating specialized 3D-reconstruction SOTA.
- Space-time simulation: models space and time from input video, enabling dramatic reframing and Real-to-Sim workflows for robotics.
- Image generation: text-to-image and 360 panoramas, complex prompts, text rendering, varied styles.
Atlas will power future versions of Marble and other products.
Related event: World Labs Unveils Atlas, an Omni World Model for Spatial Intelligence(13 posts)→
More from Models
- Fable 5.1 benchmarks show insane jumps on Terminal/Science — kimmonismus · 2026-09-02
- Anthropic Fable 5.1 is now available in Claude Code v2.1 — BLUECOW009 · 2026-09-02
- Anthropic Releases Claude Fable 5.1 and Mythos 5.1: Lower Costs and Enhanced Privacy — TFenrir · 2026-09-02
- Quasar 438B tops European LLM charts but remains closed-source — BarisSayit · 2026-09-02
- Anthropic Launches Claude Fable 5.1 and Mythos 5.1 Models — AI_Andrew · 2026-09-02
- Claude Fable 5.1 Launches: High Usage Hints at Major Compute Jump — VraserX · 2026-09-02