Amazon product video shows in the main block only under six images
Per Amazon's seller guide, a shoppable video shows in the main media block only if the listing has fewer than six images. Plan gallery and clip together.

Amazon's seller guide says a shoppable video appears in the main media block only when the product has fewer than six images. If you upload a six-image gallery, the video does not take that slot. Decide the image count before you spend on the clip. The rule comes from Amazon's product video guide, read 2026-10-03.
The rule and the spec around it
The guide gives the file and display rules in one place. The rule that most affects planning is the image count.
| Item | Value |
|---|---|
| Formats | .mov or .mp4 |
| Resolution | up to 1080p |
| File size | 5 GB maximum |
| Length | 1 to 12 minutes |
| Main media block | only if the product has fewer than six images |
| Display after approval | typically within three days |
The tradeoff: image five versus the video
A listing with five images and a video gets the video in the main media block. A listing with six or more does not. So the sixth lifestyle image has a cost: it removes the clip from the most visible placement. If you are generating images in bulk, cap the gallery at five for any ASIN where the video is the priority.
The guide describes the main media block only. It does not say where a video goes when the product has six images, so do not assume a fallback location. Check a live listing after approval.
Build the pair on Sume
Generate the five stills first with Sume's image API and use one of them as the first frame for the clip, so image and video match. The video generation API accepts frame_images with a frame_type of first_frame for image-to-video, on models whose supported_frame_images lists it.
Note the length mismatch. Amazon's minimum is one minute, and a single generated clip is far shorter: models in Sume's catalog top out at 15 seconds, with a few reaching 30. Reaching one minute means assembling several clips on the timeline, whose audio.duration_seconds runs from 1 to 1800 seconds.
{
"model": "seedance-2",
"prompt": "Slow push-in on the product on a kitchen counter, natural light",
"frame_images": [
{
"type": "image_url",
"image_url": {"url": "https://example.com/image-01.png"},
"frame_type": "first_frame"
}
],
"resolution": "1080p"
}Checklist before upload
- Count the ASIN's images: five or fewer if the video must lead.
- Confirm the clip is at least one minute and at most 12.
- Export .mp4 at 1080p or lower.
- After approval, wait up to about three days and then check the listing.
Sources
Related posts
More in Use cases
- Amazon Sponsored Brands video: 1 Mbps and 96 kbps audio minimums
Amazon Sponsored Brands video needs at least 1 Mbps video, 96 kbps audio at 44.1 kHz, and 16:9 only. What to check on an AI-generated clip before upload.
- Article 50(2): the provider duty to mark AI outputs machine-readably
Article 50(2) makes providers mark synthetic outputs in machine-readable form. What the wording says, what is exempt, and what to ask a generator vendor.
- Article 50(2) assistive editing: trim and crop vs generate
Article 50(2) exempts assistive editing that does not substantially alter input. Sort your Sume outputs into generated and file-processed before you rely on it.
- Clean a transcript with a 2,000-character instruction, then caption
ElevenLabs speech to text can edit a transcript from a natural-language instruction up to 2,000 characters. A cleanup then captions workflow with Sume captions.
Written by Sume