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 1280x720 or 1920x1080 for 16:9 output. Use 720x1280 or 1080x1920 for 9:16 output. Other sizes are not supported.
string[]
required
One to five publicly reachable http or https reference-image URLs. Each reference image must be no larger than 5 MiB.

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.