Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

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.

Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

A New Padding Scheme: Partial Convolution based Padding

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Synthesizing and manipulating 2048x1024 images with conditional GANs