Days after OpenAI and Google unveiled increasingly sophisticated text-to-video conversion models, Elon Musk-owned xAI has entered the fray with a major upgrade.
The company has released Grok Imagine Video 1.5, now available through the Imagine API.
“We’ve also rolled out Video 1.5 Fast at grok.com/imagine and in our iOS and Android apps,” the company said in a statement.
“These are our best image-to-video models to date: better motion, better physics, better audio, and faster generation speeds. We’re also introducing new features to enhance creative workflows in Grok Imagine.”
According to xAI, version 1.5 improves in all key areas needed for real-world creative production compared to previous versions.
The company highlighted that this model generates sound effects, ambience, and dialogue in a single pass, with improved clarity and improved lip-sync accuracy.
When it comes to movement, we’ve improved physics, including reduced visual distortion and better representation of weight and momentum, resulting in more stable and realistic movement throughout your video clips.
xAI also says that Grok Imagine Video 1.5 Fast nearly doubles the production speed, producing a 6-second 720p video in about 25 seconds, compared to more than 40 seconds with the previous version.
