Physical AI

NVIDIA Cosmos

An open platform for physical AI with world foundation models (WFMs), video data processing libraries, video evaluation, and post-training frameworks.

Download from GitHub

Cookbook | Documentation | Discord

Models

Download Now

World Foundation Models

Open Models for World Generation and Understanding

Cosmos Predict

Leading world generation model, adaptable to any physical AI task or environment.

Generate 30s predictive video worlds from text, image, or video with 2B/14B models, or post-train on your data to create custom edge cases, closed-loop policies, and multiview, robot-centric simulations.

Get Started on GitHub

Cosmos Transfer

Multicontrol model for simulation to photoreal transformation.

Pair with physical AI simulation frameworks, such as CARLA or NVIDIA Isaac Sim™, to accelerate synthetic data generation across various environments and lighting conditions.

Get Started on GitHub

Cosmos Reason

Leading vision language model (VLM) enabling robots and vision AI agents to reason like humans.

Combines prior knowledge, physics, and common sense for real-time alerts and actionable insights across public safety, traffic monitoring, logistics, quality inspection, and physical AI.

Get Started on GitHub

Data Processing and Evaluation

Speed up efficient dataset processing and evaluation.

Cosmos Curator

Quickly filter, annotate, and deduplicate large amounts of sensor data with Cosmos Curator.

Download Cosmos Curator on GitHub

Cosmos Dataset Search

Instantly query datasets and retrieve scenarios with NVIDIA Cosmos Dataset Search (CDS).

Try Cosmos Dataset Search

Cosmos Evaluator

Review and score generative video outputs at scale using Cosmos Evaluator.

Download Cosmos Evaluator on GitHub

Use Cases

How Cosmos Accelerates AI Across Industries

Use Cosmos WFMs to simulate, reason, and generate data for downstream pipelines in robotics, autonomous vehicles, and industrial vision systems.

Robot Learning
Autonomous Vehicle Training
Video Analytics AI Agents

Robot Learning

Build custom world models for downstream tasks, environments, camera or sensor layouts, and policies.

Post-train Cosmos Predict for robot-specific views or control policies
Generate synthetic data across environments and lighting conditions with Cosmos Transfer
Post-train Cosmos Reason using the Cosmos RL framework to build vision-language-action (VLA) models
Create an end-to-end synthetic data augmentation and evaluation pipeline using the Physical AI Data Factory Blueprint built on Cosmos

See Examples

Autonomous Vehicle Training

Generate custom, diverse, and high-fidelity sensor data for safely training, testing, and validating autonomous vehicles.

Amplify existing data diversity with new weather, lighting, and geolocation data using Cosmos Transfer
Expand into multi-sensor views using Cosmos Predict
Create an end-to-end synthetic data augmentation and evaluation pipeline using the Physical AI Data Factory Blueprint built on Cosmos

See Examples

Video Analytics AI Agents

Enhance automation, safety, and operational efficiency across industrial and urban environments.

With Cosmos Reason, AI agents can analyze, summarize, and interact with real-time or recorded video streams to:

Deliver real-time question-answering and alerts
Provide rich contextual insights
Extract insights from large-scale video data with NVIDIA Blueprint for video search and summarization

Learn More

Worker in safety gear maintaining wind turbine

Starting Options

Get Started With NVIDIA Cosmos

1

Ready to build? Access open models and code directly.

View GitHub

2

Not ready to build yet? Try Cosmos models in our hosted catalog.

Try Now

3

Need help? Start quickly with our hands-on model recipes.

Browse Cookbook

Trustworthy AI

Supporting the Physical AI Community

Cosmos models, guardrails, and tokenizers are available on Hugging Face and GitHub, with resources to tackle data scarcity in training physical AI models.

AI Infrastructure

Get the Best Performance With NVIDIA Blackwell

NVIDIA RTX PRO 6000 Blackwell Series Servers accelerate physical AI development for robots, autonomous vehicles, and AI agents across training, synthetic data generation, simulation, and inference.

Unlock peak performance for Cosmos world foundation models on NVIDIA Blackwell GB200 for industrial post-training and inference workloads.

Learn More

Ecosystem

Adopted by Leading Physical AI Innovators

Model developers from the robotics, autonomous vehicles, and vision AI industries are using Cosmos to accelerate physical AI development.

Next Steps

Join the Cosmos Community

Connect with Cosmos experts, engage with fellow developers, provide model feedback, and access continued learning through livestreams and recipes.

Join Now

Cosmos Cookbook

A comprehensive guide for working with the NVIDIA Cosmos ecosystem for real-world, domain-specific applications across robotics, simulation, autonomous systems, and physical scene understanding.

Learn More

Build Video Analytics AI Agents

Use Cosmos Reason with NVIDIA Blueprint for video search and summarization (VSS) to build AI agents for scalable, real-time video understanding.

Try now

Resources

The Latest From Cosmos Developers

Latest News
Sessions
Demos

See All Tech Blogs See All Topic News

May 20, 2026

NVIDIA and Google Cloud Empower the Next Wave of AI Builders

At this year’s Google I/O conference, NVIDIA and Google Cloud are accelerating the work of more than 100,000 developers in the companies’ joint developer community, which provides curated learning paths, hands-on labs and events that help them build using the full-stack NVIDIA AI platform on Google Cloud. Launched at Google I/O last year, the community […]

April 28, 2026

Into the Omniverse: Manufacturing’s Simulation-First Era Has Arrived

Manufacturing’s traditional design-build-test cycle rested on a single assumption: Real-world testing was the only reliable test environment.

April 22, 2026

NVIDIA and Google Cloud Collaborate to Advance Agentic and Physical AI

NVIDIA and Google Cloud have collaborated for more than a decade, co‑engineering a full‑stack AI platform that spans every technology layer — from performance‑optimized libraries and frameworks to enterprise‑grade cloud services. This foundation enables developers, startups and enterprises to push agentic and physical AI out of the lab and into production — from agents that […]

See All

Ensuring Safe Autonomous Driving With NVIDIA Halos

Scaling AV Data With Omniverse and Cosmos

How Simulation Enables Safer Autonomous Vehicles | Foretellix

Accelerating AV Development With NVIDIA Omniverse and Cosmos

How Robots Learn to Be Robots: Training, Simulation, and Real World Deployment

How Robot Brains Dream and Explore Unseen Worlds

Build and Test Smart City AI Agents in Digital Twins

NVIDIA Cosmos: A World Foundation Model Platform for Physical AI

Generating Synthetic Data for Physical AI With NVIDIA Cosmos

Autonomous Vehicle Simulation With NVIDIA Omniverse and Cosmos

Using NVIDIA Cosmos World Foundation Models for Physical AI Development

Frequently Asked Questions

[January 22, 2026] Released research on Cosmos Policy that builds on Cosmos Predict-2 for visuomotor control and planning.

[February 9, 2026] Enhanced compute support, quantization and CUDA compatibility for new Cosmos Reason 2.

[December 19, 2025] Released Cosmos-Predict2.5-2B Diffusers support via Hugging Face, Cosmos-Predict2.5-2B Text2World distilled checkpoint on Hugging Face and Distillation guide.

[December 19, 2025] Released Image2Image and ImagePrompt capabilities for Cosmos Transfer 2.5. See the inference guide here.

Explore GitHub for more.

Yes, you can leverage Cosmos to build from scratch with your preferred foundation model or model architecture. You can start by using Cosmos Curator for video data preprocessing. Then compress and decode your data with Cosmos tokenizer. Once you have processed the data, you can train or fine-tune your model.

Using NVIDIA NIM™ microservices, you can easily integrate your physical AI models into your applications across cloud, data centers, and workstations.

You can also use NVIDIA DGX Cloud to train AI models and deploy them anywhere at scale.

All three are WFMs with distinct roles:

Cosmos Predict generates diverse video scenes from text, image, or video prompts—ideal for post-training on subjects like robots or self-driving cars.
Cosmos Transfer applies multi-control style transfer—changing lighting and environments—on physics-based videos, often created in simulators like NVIDIA Omniverse™.
Cosmos Reason answers queries by reasoning over video and image inputs. Cosmos Reason can generate new and diverse text prompts from one starting video for Cosmos Predict, or critique and annotate synthetic data from Predict and Transfer.

Omniverse creates realistic 3D simulations of real-world tasks by using different generative APIs, SDKs, and NVIDIA RTX rendering technology.

Developers can input Omniverse simulations as instruction videos to Cosmos Transfer models to generate controllable photoreal synthetic data.

Together, Omniverse provides the simulation environment before and after training, while Cosmos provides the foundation models to generate video data and train physical AI models.

Learn more about NVIDIA Omniverse.

NVIDIA Cosmos

Open Models for World Generation and Understanding

Cosmos Predict

Cosmos Transfer

Cosmos Reason

Data Processing and Evaluation

Cosmos Curator

Cosmos Dataset Search

Cosmos Evaluator

How Cosmos Accelerates AI Across Industries

Robot Learning

Get Started With NVIDIA Cosmos

1

2

3

Supporting the Physical AI Community

Get the Best Performance With NVIDIA Blackwell

Adopted by Leading Physical AI Innovators

Next Steps

Join the Cosmos Community

Cosmos Cookbook

Build Video Analytics AI Agents

The Latest From Cosmos Developers

Ensuring Safe Autonomous Driving With NVIDIA Halos

Frequently Asked Questions

What’s new in NVIDIA Cosmos WFMs?

What is the licensing model for Cosmos world foundation models?

How do I post-train Cosmos models for my downstream applications?

Can I build a world model from scratch using tools from the Cosmos platform and my custom or in-house foundation model?

What are the differences between Cosmos Predict, Cosmos Transfer, and Cosmos Reason, and how do they work together?

What is the difference between Cosmos and Omniverse?