metadata
license: other
license_name: openmdw1.1-license
license_link: https://openmdw.ai/license/1-1/
library_name: cosmos
tags:
- nvidia
- cosmos
- cosmos3
- vllm
- vllm-omni
- diffusers
- text, image, video, audio, and action generation
- omnimodel
Description
Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs. It serves as a foundational building block for a broad range of Physical AI applications and research spanning world understanding, world generation, simulation, and embodied policy learning.
This model is ready for commercial and non-commercial use.
Model Developer: NVIDIA
This model has been converted to FP8 and has a modified VAE (HDR VAE) and Vision Model