Two photos in, one 10-second Omni transition out: $1.875 at 1080p
Gemini Omni first and last frame turns two stills into a transition. On Sume, image_url plus end_image_url for 10 seconds at 1080p costs $1.875.
Send the first photo as image_url and the second as end_image_url. Google's Omni 1.1 Flash lets you specify the starting and ending frames of a shot and generates continuous video between the two keyframes. On Sume a 10-second clip at 1080p is $1.875, and at 720p it is $1.25.
The request
Use POST /v1/video-router/generate with model: gemini-omni-flash-1.1, image_url, end_image_url, duration between 3 and 10, and a resolution. Sume routes the request by shape, so there is no separate endpoint for interpolation.
Do not send reference_*_urls alongside the frames. They are different modes, and Sume rejects the mix. Native audio is always on.
| Resolution | Per second | 10 s clip | 6 s clip |
|---|---|---|---|
| 360p | $0.0375 | $0.375 | $0.225 |
| 720p | $0.125 | $1.25 | $0.75 |
| 1080p | $0.1875 | $1.875 | $1.125 |
| 4K | $0.375 | $3.75 | $2.25 |
Where it helps
Before and after shots, a product at two angles and a location at two times of day all suit two keyframes. The model invents the in-between, so pick two images that share framing.
Match the aspect ratio of the images to the output; Omni takes 16:9 or 9:16 only.
What it does not do
The output is 3 to 10 seconds; for a longer run, chain clips by using the last frame of one as the first frame of the next. Check each pair before you pay for 4K, since the 360p price is a tenth of it.
Sources
Related posts
More in Media tools
- How many 6-second clips fill a 3-minute Short, Reel or TikTok ad?
A 3-minute Short needs 30 six-second clips, a 20-minute Reel 200, a 10-minute TikTok ad 100. Slot limits, chunked renders and Timeline cost for each.
- Instagram feed video ad 1% ratio tolerance in pixels at 1080 wide
Meta lists a 1% aspect ratio tolerance for Instagram feed video ads. Read as relative, at 1080 wide that is about 1902-1938 px tall; Sume's 1080x1920 is exact.
- Kling 3.0 Element Binding: a face close-up, and one still on Sume
Kling says 3.0 Motion Control wants a clear facial close-up for Element Binding. Sume's route takes one still or a ready avatar. What that means for faces.
- Kling motion control: 3 s minimum on Kling, 1 s field on Sume
Kling says action videos run 3 to 30 seconds. Sume's duration_seconds accepts 1 to 30. Why to keep the reference at 3 seconds or more, and what it costs.
Written by Sume