Cosmos3-Super-Image2Video is an NVIDIA open-weight model for converting still images into generated video sequences. Developers and researchers can download and run the model locally using supported tooling such as Python or Docker.
Cosmos3 Super Image2Video sits in PulseGate's Image to video category. It focuses on generating video sequences from still images using an openly available model. It is built as an open-source project for AI developers and researchers. Cosmos3 Super Image2Video is open source under the Open Source license. Cosmos3 Super Image2Video is available on the web, the command line, and API, and it can be self-hosted.
NVIDIA builds and maintains Cosmos3 Super Image2Video, and it first shipped in 2026. Development happens publicly on GitHub with 11.7k stars and 81 commits in the last 90 days. Among its 5 catalogued features are image-to-video generation, open model weights, and local inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do