
Grok Imagine Video
xAI · Video generation
Text or image to video, up to 15 seconds, with optional generated sound.
Our own image-to-video model. A router sends camera moves and region cinemagraphs to fast depth-parallax and flow pipelines, and faces, bodies, vehicles and anything described in words to a generative tier we run on our own GPU. Every clip is checked so nothing appears that the still does not show.
id vidmoat-image-live-1

The still a sample of this model is being made from. The clip itself is not shown yet.
A test key answers with a sample and spends nothing. Every parameter and error is in the API reference.