NVIDIA Cosmos
NVIDIA Cosmos is a developer-first platform of state-of-the-art generative World Foundation Models (WFMs), advanced video tokenizers, guardrails, and an accelerated data processing and curation pipeline designed to supercharge physical AI development. It enables developers working on autonomous vehicles, robotics, and video analytics AI agents to generate photorealistic, physics-aware synthetic video data, trained on an immense dataset including 20 million hours of real-world and simulated video, to rapidly simulate future scenarios, train world models, and fine‑tune custom behaviors. It includes three core WFM types; Cosmos Predict, capable of generating up to 30 seconds of continuous video from multimodal inputs; Cosmos Transfer, which adapts simulations across environments and lighting for versatile domain augmentation; and Cosmos Reason, a vision-language model that applies structured reasoning to interpret spatial-temporal data for planning and decision-making.
Learn more
Seedance
Seedance 1.0 API is officially live, giving creators and developers direct access to the world’s most advanced generative video model. Ranked #1 globally on the Artificial Analysis benchmark, Seedance delivers unmatched performance in both text-to-video and image-to-video generation. It supports multi-shot storytelling, allowing characters, styles, and scenes to remain consistent across transitions. Users can expect smooth motion, precise prompt adherence, and diverse stylistic rendering across photorealistic, cinematic, and creative outputs. The API provides a generous free trial with 2 million tokens and affordable pay-as-you-go pricing from just $1.8 per million tokens. With scalability and high concurrency support, Seedance enables studios, marketers, and enterprises to generate 5–10 second cinematic-quality videos in seconds.
Learn more
Marble
Marble is an experimental AI model internally tested by World Labs, a variant and extension of their Large World Model technology. It is a web service that turns a single 2D image into a navigable spatial environment. Marble offers two generation modes: a smaller, fast model for rough previews that’s quick to iterate on, and a larger, high-fidelity model that takes longer (around ten minutes in the example) but produces a significantly more convincing result. The value proposition is instant, photogrammetry-like image-to-world creation without a full capture rig, turning a single shot into an explorable space for memory capture, mood boards, archviz previews, or creative experiments.
Learn more
Genie 3
Genie 3 is DeepMind’s next-generation, general-purpose world model capable of generating richly interactive 3D environments in real time at 24 frames per second and 720p resolution that remain consistent for several minutes. Prompted by text input, the system constructs dynamic virtual worlds where users (or embodied agents) can navigate and interact with natural phenomena from multiple perspectives, like first-person or isometric. A standout feature is its emergent long-horizon visual memory: Genie 3 maintains environmental consistency over extended durations, preserving off-screen elements and spatial coherence across revisits. It also supports “promptable world events,” enabling users to modify scenes, such as changing weather or introducing new objects, on the fly. Designed to support embodied agent research, Genie 3 seamlessly integrates with agents like SIMA, facilitating goal-based navigation and complex task accomplishment.
Learn more
