Days after OpenAI and Google unveiled increasingly advanced text-to-video models, Elon Musk-owned xAI has now entered the competition with a major upgrade.

The company has launched Grok Imagine Video 1.5, now available through the Imagine API.

“We’ve also rolled out Video 1.5 Fast on grok.com/imagine and our iOS and Android apps,” the company said in a statement.

It added, “These are our best image-to-video models yet: better motion, better physics, better audio, and faster generation speeds. We’re also introducing new features to enhance the creative workflow in Grok Imagine.”

According to xAI, version 1.5 improves across all key areas required for real creative production compared to its predecessor.

The company highlighted that the model now generates sound effects, ambience, and dialogue in a single pass, with improved clarity and better lip-sync accuracy.

In terms of motion, it delivers more stable and realistic movement throughout video clips, with reduced visual distortions and improved physics, including better representation of weight and momentum.

xAI also stated that Grok Imagine Video 1.5 Fast nearly doubles generation speed, producing 6-second, 720p videos in about 25 seconds, compared to over 40 seconds in the previous version.