Video Gen Editor

Grok Imagine Video 1.5: xAI's Image to Video Model

Grok Imagine Video 1.5 is xAI's image-to-video model. Give it a still and it produces lively, cinematic motion from that single starting frame. It can also perform speech with up to three preset voices, which you place in your prompt.

Free sign-up · see the cost before you generate

Grok Imagine Video 1.5 specs

Made by
xAI
Clip length
1 to 15 seconds
Resolutions
480p, 720p, 1080p
Shapes
1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
Starts from
Image
Extra inputs
A first frame, up to 7 reference images
Sound
Generated with the video

Grok Imagine Video 1.5 pricing

Grok Imagine Video 1.5 price per resolution
ResolutionPer second5-second clip10-second clip
480p$0.08$0.40$0.80
720p$0.14$0.70$1.40
1080p$0.25$1.25$2.50

These are the published per-second rates. The composer shows the exact estimate for your settings before you generate, and failed generations aren't charged. Prices last checked September 24, 2026. Credits come with our plans.

What it's good at

  • Built for image-to-video from a single starting frame.
  • Speech with up to three preset voices.
  • Up to 7 reference images, as an alternative to a first frame.
  • Clips of 1 to 15 seconds.
  • 480p, 720p or 1080p, in seven shapes including 3:2 and 2:3.

Best for

  • Animating a still

    Characters, art and product shots in the AI image to video tool.

  • Talking characters

    Give a character a voice and a line.

  • Short social clips

    Punchy motion in a few seconds.

  • Ads

    Product images brought to life for the AI UGC video generator.

Things to know

  • Each input image adds $0.01.
  • A first frame and reference images can't be used together.
  • Without a first frame, pick an exact size.
  • It costs more than the Lite version ($0.14 vs $0.03 a second at 720p).

A Grok Imagine Video 1.5 prompt to try

The fox in the illustration lifts its head, looks straight at the camera and says “You're late again,” then trots off into the autumn leaves.

Choose a voice in the composer and reference it in the prompt where the line is spoken.

Alternatives to Grok Imagine Video 1.5

Compare every AI video model

Use Grok Imagine Video 1.5 for

Frequently asked questions

Can Grok Imagine Video 1.5 make characters talk?

Yes. Pick up to three preset voices and reference them in your prompt, and the video includes the speech.

What's the difference between Grok Imagine Video 1.5 and 1.5 Lite?

The full version is aimed at image-to-video, takes reference images and supports preset voices. Lite is the low-cost tier: text or a single starting frame, with native audio.

How much does Grok Imagine Video 1.5 cost?

From $0.08 a second at 480p to $0.25 at 1080p. A 5-second 480p clip costs about $0.40.