xAI / Video model

Grok Imagine Video

xAI's fast video model for clips from 1 to 15 seconds with audio, in seven aspect ratios and up to 1080p.

Meet Grok Imagine Video

Grok Imagine is xAI's video model. It is quick to return, accepts clips as short as one second, and covers more aspect ratios than most video models, including 3:2 and 2:3.

It generates from text, animates a start frame, or builds a shot from up to four reference images. Audio is generated with the picture.

Available in Advibly

Settings and estimated costs from Advibly's live model configuration.

Inputs
Text, Start frame, Up to 4 reference images
Durations
1s to 15s
Aspect ratios
9:16, 16:9, 4:3, 3:4, 1:1, 3:2, 2:3
Output options
480p, 720p, 1080p
Audio
Generated with the video
Estimated cost
$0.12 to $0.38 / secondOne credit costs $1. The range spans the cheapest and the most expensive settings this model offers; the composer shows the exact amount before you generate.0.12 to 0.38 credits / second

When to use it

Grok Imagine suits volume: many short variations, in whatever format the placement needs.

  • Short hooks and loops for social
  • Unusual formats such as 3:2 and 2:3
  • Fast variations on one idea

Things to keep in mind

Reference-image renders top out at 720p, whatever resolution you pick.

In image-to-video the aspect ratio comes from your start frame.

Get more from your prompt

  1. 1.Keep prompts short and concrete: subject, action, setting, camera.
  2. 2.Use the shortest duration that tells the idea; it keeps cost and wait down.
  3. 3.Generate several variations and keep the best one rather than over-writing one prompt.
  4. 4.State the mood and the sound you want to hear.

Common questions

What is Grok Imagine Video best used for?

Grok Imagine Video is particularly useful for short hooks and loops for social, unusual formats such as 3:2 and 2:3, fast variations on one idea. The right choice still depends on your input assets, delivery format, turnaround and credit budget.

What inputs does Grok Imagine Video support in Advibly?

Grok Imagine Video works from text, start frame and up to 4 reference images. Advibly only shows the controls a model actually supports once it is selected, so you are never offered a combination it cannot render.

How many credits does Grok Imagine Video use?

The current estimate is 0.12 to 0.38 credits / second ($0.12 to $0.38 / second, at $1 per credit). The exact amount follows the options you pick, and Advibly shows it on the generate button before anything is charged.

Reviewed September 29, 2026 against Advibly's model configuration and xAI's published material.

Developer source

Create with Grok Imagine Video

Open a new video workspace with this model selected.

Create with Grok Imagine Video
Back to video models