Cosmos3 Inference

Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling. Use when the user asks "how do I run inference", "how do I generate a video", "how do I serve the model", "what parameters should I use", or any question about running the model to produce outputs.

NVIDIA Updated 23k repo stars
NVIDIA Cosmos

File contents

nvidia/cosmos-framework commit 314b6c513d

Frequently asked questions

npx get-skill add nvidia/cosmos3-inference