What is Grok Imagine 1.5?

Grok Imagine 1.5 is xAI's video model. It generates picture and sound together, starting from a text prompt, a still image, or a set of subject and voice references.

Is Grok Imagine 1.5 text-to-video?

Yes. On Sceneform you can generate from a prompt alone, animate a starting image, or direct the shot with references. Text-to-video is the only mode that reaches 1080p.

What inputs does it support on Sceneform?

A text prompt on its own, a starting image plus a motion prompt, or up to seven reference images with one voice clip. A starting image and references cannot be combined in the same clip.

What resolution and duration can I use?

Durations run from 1 to 15 seconds. Text-to-video generates at 480p, 720p, or 1080p, while a starting image or references cap output at 720p. Aspect ratios include 16:9, 1:1, and 9:16, and image-to-video follows the starting image.

When should I choose Grok Imagine 1.5?

Choose it when you want a short clip with sound in one pass, whether you start from a written idea, a still you already have, or references that hold a subject and voice steady.

Generate short clips with picture and sound

Grok Imagine 1.5 writes video and audio together. Start from a text prompt at up to 1080p, animate a still image, or hold a subject and voice steady with references.

Text or image to videoUp to 1080p1-15s clips with sound

Start generating View pricing

Move the image without losing the idea

Turn product stills, keyframes, character portraits, and campaign concepts into short videos guided by motion and camera language.

Why Grok Imagine 1.5

Use it when a short clip needs believable motion and its own audio, from a written idea or a frame you already have.

How to create with Grok Imagine 1.5

Choose how the clip starts, then use direct motion and camera language to shape it.

Choose how to start

Write a prompt on its own, upload a still to animate, or add up to seven reference images and one voice clip.

Motion prompt

A couple in eveningwear on a misty road at night, slow dolly in, cinematic

Dolly inNightCinematic

Write the motion prompt

Describe camera movement, subject action, atmosphere, lighting shifts, and physics.

10s1080p30fps

Set the output

Choose aspect ratio, duration from 1-15 seconds, and 480p, 720p, or 1080p. 1080p is text-to-video only.

Final cut

Generate variants

Try alternate motion language until the clip feels natural, cinematic, and usable.

Built for short clips with sound

Grok Imagine 1.5 fits work where a clip needs believable motion and its own audio in a single pass, whether it starts from a prompt or a frame.

Subject fidelity

Anchor the clip to an uploaded still, or hold a product, character, or style steady with reference images.

Camera and motion direction

Prompt dolly moves, orbit shots, handheld energy, depth changes, and environmental motion.

Short-form output control

Create 1-15 second clips with sound in common aspect ratios, at up to 1080p for text-to-video.

Where Grok Imagine 1.5 works best

Use it for short clips that need motion and sound, whether you start from a prompt or from a still you already have.

Animate product stills into short launch clips with camera moves, light shifts, and atmosphere.

1 imageSource-frame workflow

720pImage-to-video output

Simple pricing that scales with you.

Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.

Creator

~~Originally $19~~$15.83/month

$190 billed annually

For solo creators posting every week

500 credits every month

Up to 250 AI images
Up to 62 AI videos
Up to 1.5 hours of AI voiceover
Roll over up to 1,000 credits

Save $38 a year

Pro

Studio

~~Originally $99~~$82.50/month

$990 billed annually

For brands and production teams

2,700 credits every month

Up to 1,350 AI images
Up to 337 AI videos
Up to 9 hours of AI voiceover
Roll over up to 5,400 credits

Save $198 a year

Scale

~~Originally $199~~$165.83/month

$1,990 billed annually

For agencies running always-on content

5,500 credits every month

Up to 2,750 AI images
Up to 687 AI videos
Up to 18 hours of AI voiceover
Roll over up to 11,000 credits

Save $398 a year

Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights

Credit use varies by model and settings. Exact credits are shown before every generation.

Your selection

Pro plan

1,300 credits added monthly

$40.83/month

$490 due now · billed annually

Secure Stripe checkout · Cancel anytime · 3-day refund policy · Terms

Need more than Scale?

Custom volume and invoicing for businesses and agencies.

Frequently asked questions about Grok Imagine 1.5

Start creating with Grok Imagine 1.5 today

Turn a written idea or a still you already have into a short, directed clip with sound.

Start creating