Thank you for your interest in Cosmos.
The Cosmos project is now maintained at:
👉 https://github.com/NVIDIA/Cosmos
Please update your bookmarks and visit the new repository for:
We look forward to seeing you there.
New Home: https://github.com/NVIDIA/Cosmos
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…