Short-form concepts
test the timing of a movement or visual reveal.
Video generation
Grok Imagine
Create short clips with included audio and image guidance.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
What can Grok Imagine do?
Grok Imagine is a video option for turning a prompt or image-led idea into a short clip. Audio is included in its supported workflow. Its broad duration range makes it useful for comparing a brief visual beat with a more developed shot while keeping the same scene direction.
02 / Choose it for
Where Grok Imagine fits best
Reference-led scenes
guide a subject with images while describing the desired motion.
Audio-inclusive drafts
review the generated sound together with the picture.
03 / Before you create
Grok Imagine specifications
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
- Inputs on this page
- Text prompt · Reference images · Start frame
- Aspect ratios
- Auto · 1:1 · 16:9 · 9:16 · 3:2 · 2:3
- Resolution
- 480p · 720p · 1080p
- Duration
- 1–15 seconds
- Audio
- Included; always enabled
- Visual references
- Up to 7 images
- Frame guidance
- Start frame only
- Default output
- 480p · 6s · 16:9
- • Reference limits by resolution: 1080p: 1 image(s)
04 / A closer look
Questions about Grok Imagine
Why does the reference limit change at 1080p?
The supported limit is resolution-dependent: the catalog allows fewer visual references at 1080p. Check the specification note and the composer before increasing resolution; an existing reference set may need to be reduced.
What can I use as input for Grok Imagine?
Text prompt · Reference images · Start frame. The input controls above show the options available for your selected mode.
Which formats does Grok Imagine support?
Auto · 1:1 · 16:9 · 9:16 · 3:2 · 2:3. 480p · 720p · 1080p. Reference limits by resolution: 1080p: 1 image(s)
How do I choose settings for Grok Imagine?
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.