Nvidia · GitHub · AI Reasoning · Hugging Face
This release of Cosmos 3 includes two model sizes, optimized for different deployment scenarios
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
◎ Multiple-sources
Cosmos 3 supports multiple input and generation modalities through a single unified model: For video generation, Hugging Face recommend using detailed prompts in the form of narrative paragraphs.
Key facts
- As part of the Cosmos 3 launch, NVIDIA is releasing a set of Synthetic Data Generation (SDG) datasets to help the physical AI community train and evaluate world foundation models
- Cosmos 3 is integrated with the Hugging Face Diffusers library, making it easy to use world generation pipelines with a few lines of code
- Cosmos Framework is an end-to-end framework for training and serving WFMs like Cosmos 3
- Cosmos 3 helps build physical AI systems capable of understanding the real world
Summary
Whether you're building for robotics, autonomous vehicles, or smart spaces, Cosmos 3 gives you the foundation to simulate and understand the physical world. Cosmos 3 Super and Cosmos 3 Nano on Hugging Face with model cards and licensing. Post-training scripts for training Cosmos 3 on your own data (on GitHub) The biggest change in Cosmos 3 compared to previous Cosmos releases is that it's an omni-model, built on a Mixture-of-Transformers (MoT) architecture. Generate realistic and physically plausible video worlds from text, images, videos or action inputs.