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
Mirage 2
Mirage 2 is an AI-driven Generative World Engine that lets anyone instantly transform images or descriptions into fully playable, interactive game environments directly in the browser. Upload sketches, concept art, photos, or prompts, like “Ghibli-style village” or “Paris street scene”, and Mirage 2 builds immersive worlds you can explore in real time. The experience isn’t pre-scripted: you can modify your world mid-play using natural-language chat, evolving settings dynamically, from a cyberpunk city to a rainforest or a mountaintop castle, all with minimal latency (around 200 ms) on a single consumer GPU. Mirage 2 supports smooth rendering, real-time prompt control, and extended gameplay stretches beyond ten minutes. It outpaces earlier world-model systems by offering true general-domain generation, no upper limit on styles or genres, as well as seamless world adaptation and sharing features.
Learn more
Veo 3.1
Veo 3.1 builds on the capabilities of the previous model to enable longer and more versatile AI-generated videos. With this version, users can create multi-shot clips guided by multiple prompts, generate sequences from three reference images, and use frames in video workflows that transition between a start and end image, both with native, synchronized audio. The scene extension feature allows extension of a final second of a clip by up to a full minute of newly generated visuals and sound. Veo 3.1 supports editing of lighting and shadow parameters to improve realism and scene consistency, and offers advanced object removal that reconstructs backgrounds to remove unwanted items from generated footage. These enhancements make Veo 3.1 sharper in prompt-adherence, more cinematic in presentation, and broader in scale compared to shorter-clip models. Developers can access Veo 3.1 via the Gemini API or through the tool Flow, targeting professional video workflows.
Learn more
MiniMax H3
MiniMax H3 is a general-purpose omni-modal generation model that jointly understands multimodal contexts spanning text, images, video, and audio. It generates videos with native stereo sound at up to 2K resolution and 15 seconds in length, delivering content for advertising, branding, ecommerce, product design, UI/UX, gaming, and creative workflows. Users can combine reference types in one instruction, for example, transferring camera movement from a video, placing a character from an image into the scene, and matching vocals from an audio clip, while describing the relationships in natural language. H3 supports text-to-image, text-to-video with jointly generated audio, multi-shot modeling, text-to-audio, and generalized reference and editing across images, videos, and audio. Voice, sound effects, and music are modeled together. The model excels at instruction following, accurate text and brand presentation, and video-to-video motion transfer.
Learn more
