Grok Imagine Video
Grok Imagine image-to-video at 480p or 720p, 1-15s. Output is billed per second of generated video and the source image per input image.
Examples
representative generations · starting points to seed the playground
A pale panna-cotta dessert in a footed coupe glass topped with a single glossy cherry on a soft blue ground, playful product Bring it to life. Camera: the camera flies into the scene and sweeps around the subject in a graceful 180-to-360 degree orbit, elegant and precise. Impressive, well-directed cinematic motion with real depth and life — a living film scene, not a moving still. Soft muted slightly-desaturated editorial palette, soft lighting, subtle film grain, refined, dreamy, premium, highly detailed.
A colossal mirror-chrome sphere half-buried in golden desert dunes, tiny footprints, surreal scale, cinematic. — animate as a video. Cinematic subtle motion: gentle camera push-in, natural life in the scene (light shifts, soft breeze, fine movement), the subject stays coherent and photoreal. Elegant, filmic, high quality.
A short-haired girl stands on the sunny platform at Kamakurakōkō-mae Station. She's wearing a navy coat, a white scarf, a plaid skirt, and a dark brown backpack. She turns to the camera, casually throws up a peace sign, smiles, and blinks naturally. Everything feels easy and relaxed.
Per-model pricing
Transparent, usage-based rates for every xAI model.
Grok Imagine Video 1.5
Video
Image to Video
Grok Imagine Video
Video
Text to Video
Image to VideoCurrent
Reference to Video
Video to Video
Grok Imagine Image Quality
Image
Text to Image
Image to Image
Grok Imagine
Image
Text to Image
Image to Image