World Labs releases Atlas world model with 3D spatial-time control
kdexd · x · 2026-09-02
World Labs has introduced Atlas, a next-generation world model pretrained from scratch to natively support text, images, video, and 3D. As a multimodal autoregressive diffusion transformer, Atlas combines inputs into a shared spatial context to generate consistent 3D outputs. Key capabilities include:
- Camera-Controlled Generation: Generates videos with pixel-perfect camera control from images (up to 1 min at 1440p).
- Spatial Reconstruction: Reconstructs real-world scenes from sparse inputs, outputting novel views and explicit 3D structures, outperforming specialized SOTA models.
- Space-Time Simulation: Models space and time from video, enabling "bullet time" effects and Real-to-Sim workflows for robotics.
- Image Generation: Creates images and 360 panoramas from complex prompts with text rendering.
Atlas will power future versions of Marble and other products.
More from Embodied
- Microduck site technical breakdown: Real 3D models and gait data driven rendering — RachelVT42 · 2026-09-02
- China’s real robot revolution is not about humanoids, but industrial application — zijing_wu · 2026-09-02
- Gemini-powered Spatial OS turns 8 photos into 3D digital twins — AI_Andrew · 2026-09-02
- Robot Training Video: Squire Model Shows New Skills — MocaPoka · 2026-09-02
- Open-source humanoid robot Asimov 1 starts shipping to 20+ countries — MikeBirdTech · 2026-09-02
- Physical AI Deep Dive: From Static Programming to Imitation Learning and Edge Compute — ShawnHymel · 2026-09-02