eBay listing clips from cutouts: remove background, then animate
For 20 eBay items, remove each photo's background at $0.0225, then make a 5-second clip with Wan 3.0. A request pair, a cost table, and a fidelity check.

Cutting out the product first gives the video model a clean first frame, and 20 items cost $12.95 on Sume: $0.45 for the cutouts and $12.50 for 5-second Wan 3.0 clips at 720p. Remove background is $0.0225 per image.
Why a cutout first
A cluttered kitchen counter in the source photo becomes moving clutter in the clip. A transparent-background PNG, composited onto a plain color you choose, keeps the motion on the item. The cutout also becomes a reusable asset for gallery images.
Cost for 10, 20 and 50 items
| Items | Cutouts | Clips (Wan 720p, 5 s) | Total | Clips at 480p instead |
|---|---|---|---|---|
| 10 | $0.225 | $6.25 | $6.475 | $3.35 |
| 20 | $0.45 | $12.50 | $12.95 | $6.70 |
| 50 | $1.125 | $31.25 | $32.375 | $16.75 |
The clip request
Host the flattened cutout on a public HTTPS URL, then send it as the first frame. Wan 3.0 takes first and last frame images and 2 to 30 seconds, and its 720p rate is what the table above prices.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: ebay-lot-07" \
-d '{
"model": "wan-3.0",
"prompt": "Camera orbits the watch slowly on a plain grey seamless",
"frame_images": [{
"type": "image_url",
"image_url": {"url": "https://example.com/lot07-flat.png"},
"frame_type": "first_frame"
}],
"resolution": "720p",
"duration": 5
}'Do not let the clip overstate the item
A listing video must match the object in the box. Do not animate wear, scratches or missing parts away, and keep the true photos in the gallery. Read eBay's own current video rules on its pages before upload; this post cites none.
What the cutout is for
A transparent PNG is not a good first frame by itself, because the video model needs a background to render. Place the cutout on a neutral color or a plain surface first, then send that flattened image as the first frame. Keep a copy of the unedited photo for the listing gallery. For items with fine edges such as jewelry or fur, inspect each cutout before it becomes a frame, since a ragged mask will show up as shimmer in the animation.
Related posts
More in Use cases
- Eight shots, 2 to 11 s: how each Sume video model bends the plan
A storyboard with shots of 2, 3, 4, 5, 6, 7, 9 and 11 s is 47 s on Wan 3.0 ($5.88 at 720p) but 50 s on Seedance 2.5 and 11 s is out for Omni.
- Esports team intro in 21:9: Seedance 2.5 at 720p, 8 s, with cost
Seedance 2.5 on Sume renders 21:9 at 1470 x 630 for 720p. An 8-second stream-banner intro costs $4.65 at 720p, $2.15 at 480p. Rates and limits.
- Esports team intro sting: 5 seconds with a logo reference
A 5-second team intro for a stream in 16:9: send the logo as a reference image to Omni Flash, $0.625 at 720p on Sume, and fix the text in a short edit.
- 300 Etsy photos: Nano Banana 2.1 vs GPT Image 2.5, cost on Sume
30 Etsy listings with 10 photos each is 300 images. At Sume rates that is $30.00 on Nano Banana 2.1 at 1K or $16.69 on GPT Image 2.5 medium.
Written by Sume