NVIDIA releases four open-weight Cosmos 3 Nano checkpoints
Hugging Face, reporting NVIDIA's announcement, says the Cosmos 3 family gained four downloadable, open-weight checkpoints with 16 billion trainable parameters each. The models target multi-view driving-data generation, synchronized camera and LiDAR streaming, simulator-to-video conversion, and video prediction from bimanual robot or camera actions; NVIDIA's quality, realism, and synchronization claims have not been independently evaluated in the report.
The release gives developers downloadable open-weight models and post-training recipes for building interactive driving, robotics, and embodied-agent simulations.
TL;DR
NVIDIA Cosmos world model development platform adds four new open-weight checkpoints to its Cosmos 3 model family for generating interactive world simulation and multi-sensor multi-view driving scenes:
- 🌦️ Cosmos3-Nano-Transfer-Auto : Generate multi-view driving data with varied weather, lighting, and time of day.
- 🚗 Cosmos3-Nano-Sim-Auto : Stream synchronized camera and LiDAR observations for driving simulation.
- 🎨 Cosmos3-Nano-Sim-Transfer : Turn simulator controls and a text prompt into photorealistic video.
- 🤖 Cosmos3-Nano-Sim-Bimanual : Predict video from robot or camera actions.
All four models are post-trained examples of Cosmos 3 Nano and have 16B trainable parameters. The models use OpenMDW1.1, permitting commercial and non-commercial use under its terms.
Download the checkpoints · Read the technical report . Watch the demos
Why do you need these checkpoints?
🦾 Robotics needs environments that can answer this across changing scenes and viewpoints. These checkpoints offer complementary ways to build them: Sim-Bimanual predicts visual consequences from actions, while Sim-Transfer turns a physics simulator’s controls into generated observations.
#NVIDIA#Cosmos3-Nano-Transfer-Auto#Cosmos3-Nano-Sim-Auto#Cosmos3-Nano-Sim-Transfer#Cosmos3-Nano-Sim-Bimanual#Cosmos 3 Nano