Grok Imagine in Motion Studio

Grok Imagine: xAI’s video and images, for your release

Grok Imagine is xAI’s family of generation models. Motion Studio has Grok Imagine Video 1.5 for clips of 1 to 15 seconds and Grok Image 2.0 for images and edits, next to Seedance, Kling and Soul.

Start free See pricing

Each generation shows its cost in credits before you confirm it.

At a glance

Made byxAI
VideoGrok Imagine Video 1.5: 1 to 15 s, up to 1080p
Video inputsText · image · up to 7 images and an audio
ImageGrok Image 2.0: 1K or 2K, edits with up to 10 images
Video formatsAuto · 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3

What it does

Grok Imagine in Motion Studio

Text to video

A clip of 1 to 15 seconds from a description, at 480p, 720p or 1080p.

Image to video

Start from a photo or the cover and describe what moves.

References and audio

Up to 7 reference images and an audio file, so the clip follows the look and the sound you give it.

Images

Grok Image 2.0 makes images at 1K or 2K, in ten formats.

Image edits

Combine or change images: up to 10 at a time.

Short clips

Durations from 1 second: useful for quick cuts, loops and transitions in a music video.

When to choose Grok Imagine

Grok Imagine Video starts at 1 second, like PixVerse V6, which helps for flash cuts on the beat, and takes an audio file as a reference. For longer shots, Seedance 2.5 reaches 30 seconds; for 4K, Seedance 2.0 or Kling 3.0 4K.

All models side by side in AI video models compared.