Etsy listing video from one photo: Wan 3.0, 5 seconds, 63 cents
Turn one product photo into a 5-second listing video with wan-3.0 on Sume: 32 cents at 480p, 63 cents at 720p, $1.25 at 1080p. Prompt and settings.

To make a 5-second listing video from one product photo, send the photo as a first frame to wan-3.0 with a one-sentence motion prompt. It costs $0.32 at 480p, $0.63 at 720p and $1.25 at 1080p on Sume. For a marketplace thumbnail-sized player, 720p is the sensible default.
The listing photo does the work of keeping your product accurate. The prompt should describe only what moves.
The request
Use frame_images with frame_type: first_frame. The model animates away from your photo instead of inventing a product, and you set duration to 5 and resolution to 720p explicitly (video generation docs). Always send the resolution: leaving it out leaves the price to the runtime default.
curl -X POST "https://api.sume.com/v1/videos" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3.0",
"prompt": "Slow turntable rotation of the ceramic mug on a wooden table, soft window light",
"duration": 5,
"resolution": "720p",
"generate_audio": false,
"frame_images": [{
"type": "image_url",
"image_url": {"url": "https://example.com/mug.jpg"},
"frame_type": "first_frame"
}]
}'What it costs
Wan 3.0 lists at $0.05, $0.10 and $0.20 per second by resolution. Sume bills list times 1.25 and rounds up to the cent (video router docs).
| Resolution | Rate per second | 5-second clip | 20 listings |
|---|---|---|---|
| 480p | $0.0625 | $0.32 | $6.40 |
| 720p | $0.125 | $0.63 | $12.60 |
| 1080p | $0.25 | $1.25 | $25.00 |
Settings that save a re-run
Set generate_audio to false if the listing will be silent or you will add music later. Keep motion small: a turntable, a light shift, a hand placing the item. Large camera moves are where a product's shape drifts.
Compare the first and last frame of every result against your photo before you upload. Logos and small print are the details most likely to change.
Know the limits
Sume does not edit the product inside a video, and wan-3.0 is a generator, not a guarantee of fidelity. If the item must be exact, treat the clip as a lifestyle shot and keep the still photos as the source of truth in the listing.
Practical notes
Batch behavior matters if you have a catalog. Each listing is its own job, so submit them in sequence, store the job id next to the listing id, and poll later. A shop with 40 listings at 720p spends $25.20 for one pass, so test the prompt on three listings first.
Check marketplace rules before you upload. Some require that video show the actual item, and an animated photo may or may not meet that rule for your category.
Sources
Related posts
More in Use cases
- Etsy seller listing video from one photo with Wan 3.0 on Sume
Make a short handmade-product listing video from one photo with Wan 3.0 on Sume: 2 to 30 seconds, reference inputs, an async job, and a pre-upload check.
- Event recap from 200 phone clips: Timeline's 200 slots, $0.50 render
Sume Timeline takes 1 to 200 video slots and up to 1800 seconds. A 5-minute recap of 200 attendee clips is one $0.50 render, with no per-clip trim needed.
- How do I make AI announcer intros for conference speakers?
Ten 25-second speaker intros with one shared sting cost about 43 cents on Sume: 2 cents of TTS and a 1-cent join each, plus a $0.125 track made once.
- Event storyboard animatic: ten 3-second Omni shots at 360p cost $1.13
Ten 3-second Gemini Omni Flash 1.1 shots at 360p cost $1.13 on Sume, $1.23 with a Timeline join. A cheap moving storyboard of an event for a client review.
Written by Sume