xAI · video
Grok Imagine Reference
Grok Imagine from up to 7 reference images: 1 to 10 seconds with native sound, at 480p or 720p.
ReferencesNative audio
- Length
- 1 to 10 s
- Resolution
- 480p, 720p
- Aspect ratio
- 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3
- References
- Up to 7 image files
About Grok Imagine Reference
Grok Imagine Reference is the reference mode of xAI's Grok Imagine, priced at $0.13 per second. You give it up to 7 images and a prompt, and it makes a clip with native sound of up to 10 seconds, at 480p and 720p and 16:9, 9:16, 1:1, 4:3, 3:4, 3:2 and 2:3.
A default clip costs $0.76 at 480p and $1.06 at 720p. A typical generation takes about 2 min.
Good for
- Short clips with sound built from up to 7 images used as style and content references
Getting good results
- Point at a specific image in the prompt with
@Imageand its number, counting in upload order, as the provider's format does. - Each reference image adds a small amount on top of the rate per second.
Grok Imagine Reference questions
How is it different from Grok Imagine?
Grok Imagine starts from text or a still image. Grok Imagine Reference takes up to 7 images as references and runs up to 10 seconds, against 15 seconds for Grok Imagine.