Video
Grok Imagine Video 1.5 R2V
Use it ↗Reference-to-video from xAI: guide people, objects, and clothing with 1 to 3 reference images tagged @image1 in your prompt, without locking the first frame. Native audio, up to 15 seconds at 720p.
Grok Imagine Video 1.5 R2V by xAI turns 1 to 3 reference images plus a prompt into subject-consistent video with native audio. Unlike a first-frame image, references guide people, objects, and clothing across the shot without locking the opening frame: tag them in the prompt as @image1, @image2, and @image3. Combine a character, a product, and a scene into one shot, or use frames of a sequence for controlled motion. Up to 15 seconds at 480p or 720p. Ideal for character consistency, product placement, and ads.