Grok Imagine Video 1.5

xAI's second-generation video model, generally available on June 16 after a short preview. It turns a still image into a clip with sound effects, ambience and lip-synced dialogue generated in the same pass, with steadier motion and more believable weight than Grok Imagine 1.0, and a Fast version that makes a six-second 720p clip in about 25 seconds. It took the top spot on the Image-to-Video Arena leaderboard at launch, ahead of Sora 2, Veo 3.1, Seedance 2.0 and Kling, at a price well below Sora 2 Pro, arriving weeks after OpenAI had shut down the Sora app.

On July 31 xAI added what filmmakers needed for continuity: up to seven reference images per generation to lock a face, a product or a location, a voice reference so a character keeps the same voice from scene to scene, text-to-video and native 1080p. In October a Lite tier dropped the price to two cents a second. Together with xAI's Odyssey contest in August, 1.5 made Grok Imagine a real contender alongside Seedance, Kling and Veo.