Product demo from one packshot: Omni Flash first-frame request
Turn a product photo into an 8-second demo clip with sound using Gemini Omni Flash 1.1 on Sume: the frame_images request, 1080p price, prompt tips.

Send the packshot as a first_frame and describe the motion: an 8-second 1080p product demo on Gemini Omni Flash 1.1 costs $1.50 on Sume, $1.00 at 720p. The model supports image-to-video in the same 3 to 10 second envelope, and native audio is always generated.
The request
frame_images puts the photo on the first frame; the docs describe this as image-to-video.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: demo-kettle-001" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "The kettle on the counter, lid lifts, steam curls up, soft click and water-boil sound",
"duration": 8,
"resolution": "1080p",
"aspect_ratio": "16:9",
"frame_images": [{
"type": "image_url",
"image_url": {"url": "https://example.com/kettle.png"},
"frame_type": "first_frame"
}]
}'What to put in the prompt
- One action per clip: open, pour, rotate. Eight seconds holds one beat well.
- Name the sound you expect next to the action, since audio comes with the video.
- Keep the product unchanged in the sentence; describe the camera, not the product.
Cost of a small demo set
| Set | Resolution | Clips | Total |
|---|---|---|---|
| Draft hero shot options | 360p, 8 s | 6 | $1.80 |
| Pick 2 at 720p | 720p, 8 s | 2 | $2.00 |
| Final | 1080p, 8 s | 1 | $1.50 |
| Total | 9 | $5.30 |
Check before you scale
Media inputs must be fetchable public HTTPS URLs, so open the image link in a private window and run one clip before you queue a whole catalog.
Sources
Related posts
More in Use cases
- Recipe step clips: six 5 s Kling 3 shots, $4.20 silent, $6.30 sound
Six 5-second Kling 3 step clips for a recipe page cost $0.70 each silent, $1.05 with sound on Sume. When sound is worth it and where to cut costs.
- One set of clips for Reels and TikTok: three hook orders, one script
Generate five clips once, then render three opening orders with Timeline 1.0 to test which hook holds. A Python slot generator and the cost of each variant.
- Restaurant weekly special: one 10-second Omni clip, 52 weeks priced
A weekly 10-second video for a restaurant special on Gemini Omni Flash 1.1, with native audio, priced at 360p, 720p and 1080p for 52 weeks on Sume.
- School open-day teaser: three 10 s MiniMax H3 Max takes cost $3.00
Three 10-second H3 Max takes at 768p are $1.00 each on Sume, with reference photos of your building. H3 and 1080p comparisons and the limits.
Written by Sume