Skip to main content
POST
Gemini Omni R2V
gemini-omni-r2v uses one to five reference images to guide identity, objects, composition, or style across a 10-second result.
string
required
Set to gemini-omni-r2v.
string
required
Refer to the supplied visual material clearly and describe the intended shot.
string
required
Set to "10".
string
default:"1280x720"
Use a landscape, portrait, or square pixel size. The gateway selects the matching 720p or 1080p output tier.
string[]
required
One to five publicly reachable reference-image URLs.

Request

The response returns a queued task id. Follow the Video API workflow to poll and download.
Use I2V when one image is the opening source frame. Use R2V when the images are visual guidance rather than a strict first frame.