Gemini Omni Flash 1.2 Image to Video

Gemini Omni Flash 1.2 Image to Video by Google animates a still image into a 3–15 second clip with synchronized audio, with an optional end frame for interpolation.
API docs
google/gemini-omni-flash/1.2/image-to-video

Gemini Omni Flash 1.2 Image to Video by Google animates a still image into a 3–15 second clip with synchronized audio, with an optional end frame for interpolation.

Try the model

Playground

Open playground
Input
The text prompt describing how the first image should be animated or interpolated into the optional end image.

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the first frame to animate.
The resolution of the generated video. Allowed values: 360p, 720p, 1080p, 4k.
315
The duration of the generated video, in seconds. At most 10 seconds when an end image is provided. Range: 3 to 15.
The aspect ratio of the generated video. Allowed values: 16:9, 9:16.
Advanced settings

PNG, JPEG, WebP, or GIF · 20 MiB maximum

Optional URL of the end frame. When provided, the model interpolates between the two images in their listed order and the duration is capped at 10 seconds.
Result
Idle

Your output will appear here

Complete the inputs, then click Run.

Displayed run estimate: $0.56. Final charges follow the model’s billing rules below.

Gemini Omni Flash 1.2 Image to Video

Gemini Omni Flash 1.2 image-to-video: animate a picture into a 3–15 second clip with synchronized audio. Add end_image to interpolate between two frames (up to 10 seconds).

Fields

FieldTypeDefaultNotes
promptstring, required—Up to 20,000 characters.
imageimage URL, required—First frame. JPEG, PNG, or WebP URL.
end_imageimage URL—Optional last frame. Caps duration at 10 seconds.
resolution360p / 720p / 1080p / 4k720pSets the per-second rate.
durationinteger 3–158Output length in seconds.
aspect_ratio16:9 / 9:1616:9Output frame shape.

Billing

You pay for output seconds: $0.023 at 360p, $0.07 at 720p, $0.105 at 1080p, and $0.21 at 4K.

Output360p720p1080p4k
3s$0.07$0.21$0.32$0.63
8s (default)$0.18$0.56$0.84$1.68
10s$0.23$0.70$1.05$2.10
15s$0.34$1.05$1.57$3.15

Failed runs are not charged.

Prompting

  • Describe what moves and what it sounds like, not what is already visible.

Limits

  • 16:9 or 9:16 only.
  • With end_image, duration is capped at 10 seconds.

Also on SandBase

Other Gemini Omni Flash 1.2 endpoints: google/gemini-omni-flash/1.2/text-to-video, google/gemini-omni-flash/1.2/reference-to-video, google/gemini-omni-flash/1.2/edit, google/gemini-omni-flash/1.1/image-to-video (previous version).