Cosmos3 Super · Text2Image
A large open-weight image generator aimed at physical-AI scenes, with structured prompt support and publisher-tested GB200 or multi-H100 deployment.
What do you want to do?
Choose a task. Get the software, files, settings, and steps to run it.
Open a guide for its software, hardware requirements, and setup steps.
At a glance
- Parameters
- 64B
- Architecture
- Mixture of Transformers
- License
- OpenMDW 1.1
- Software
- Diffusers, vLLM-Omni
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Structured image generation for physical-AI scene ideation.
Tradeoffs
- Outputs are not physically accurate simulations or safety-certified data.
- A substantial multi-GPU or GB200 setup makes this a specialist route rather than the default image recommendation.
Ways to run it
Diffusers Cosmos3OmniPipeline · Linux · GB200 server
Publisher says its Diffusers example was tested on GB200.
Official instructionsvLLM-Omni · Linux · 8× H100 server
Publisher documents an 8×H100 inference endpoint. Do not present this as a single consumer GPU setup.
Official instructionsExplore its uses
Sources and files
Primary sources and files behind this model page.
Keep exploring
Qwen-Image 2.1
Generate and edit images, including transparent images and edits guided by reference images.
FLUX.1 schnell
A 12-billion-parameter image model designed for generation in one to four steps.
FLUX.2 Klein
Explore 2 versions of FLUX.2 Klein. Compare model sizes, packages, hardware requirements, and available setups.