Question 1

What is Grok Imagine?

Accepted Answer

Grok Imagine is xAI's video model. In Phantra you write the idea, and each shot renders as its own Grok Imagine clip, with sound, that you can join into one MP4.

Question 2

How long can a Grok Imagine clip be?

Accepted Answer

Any whole number of seconds from 1 to 15 a take.

Question 3

What resolution does it render at?

Accepted Answer

480p, 720p or 1080p, picked on the scene's Render card. It starts at 720p.

Question 4

Which frame shapes does it make?

Accepted Answer

Seven on text-to-video: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4 and 9:16. From a start frame, the clip takes that picture's shape.

Question 5

Does Grok Imagine make sound?

Accepted Answer

Yes. Grok Imagine makes the sound in the same pass as the picture, and the clip comes back with it.

Question 6

What is the difference between 1.5 and 1.5 Lite?

Accepted Answer

Grok Imagine 1.5 is xAI's full model. 1.5 Lite is its quick tier, with sound and the same lengths, frames and resolutions. Both are on the Render card.

Question 7

Can I use my own photos as references?

Accepted Answer

Yes. Upload photos into the composer for one scene, or save a person, product or place as an element and reuse it. Every keyframe is drawn from the references attached to the scene, and a scene with no references cannot be rendered.

Question 8

Can I use the clips commercially?

Accepted Answer

What the studio generates for your account is yours to use, subject to the terms of the model that rendered it. The output is AI-made, so review it before you publish it.

Grok Imagine AI Video Generator

Grok in four numbers

Takes on the reel

Two Grok Models

Grok Imagine 1.5

Grok Imagine 1.5 Lite

Every model

FAQs about Grok Imagine

Tell Vesper the idea.