xai/grok-imagine-r2v

Generate videos guided by reference images using xAI's Grok Imagine Video model

Capabilities

Reference Images

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt` *	string	Text prompt describing the video to generate	`—`	—
`reference_images` *	array	Reference images to guide the video generation (1-7 images). These are used as style and content references, not as starting frames.	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video.	`"16:9"`	16:9 4:3 1:1 9:16 3:4 3:2 2:3
`duration`	integer	Duration of the video in seconds (1-10).	`8`	min: 1, max: 10
`resolution`	string	Resolution of the generated video.	`"480p"`	480p 720p

prompt required string

Text prompt describing the video to generate

reference_images required array

Reference images to guide the video generation (1-7 images). These are used as style and content references, not as starting frames.

aspect_ratio string

Aspect ratio of the generated video.

Default: "16:9"

16:9 4:3 1:1 9:16 3:4 3:2 2:3

duration integer

Duration of the video in seconds (1-10).

Default: 8 min: 1, max: 10

resolution string

Resolution of the generated video.

Default: "480p"

480p 720p

Version: 5b9a836f1999 Updated: 6/26/2026 60.3K runs