Skip to main content
Generate text-to-video, frames-to-video, and reference-to-video clips with Google’s Gemini Omni 1.2 Flash, released November 6, 2026. Compared with 1.1 it takes any whole-second length from 3 to 15 seconds, follows character and scene references more closely, gives better control over jump cuts, and renders sharper visuals. The request body is the same as Gemini Omni Flash 1.1 Video, so moving over is a change of the model string. Try it in the browser: Gemini Omni Flash 1.2 API playground.

Model

Parameters

Price depends on duration and resolution: every whole second from 3 to 15 has its own price at each resolution. 360p is the cheapest draft tier. See current rates on the pricing page.
Frame mode and reference mode are separate generation modes. Do not combine start_image_url/end_image_url with reference_image_urls or reference_characters.

Character References

Each character must be an object with image_urls. Even one-image characters must use an array.
*image_urls must contain at least one URL.

Example — 7 Second Character Clip

Example — 360p Draft

Example — First + Last Frame

Provide both frames and the clip animates from start_image_url to end_image_url.

Prompt References

Rejected Combinations

Response

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.