Charter boat listing video from ten photos: Wan 3.0 vertical and wide
One set of ten boat photos, two Wan 3.0 jobs: 9:16 for stories and 16:9 for the listing page. $3.75 each at 720p for 30 s, $7.50 for both, with a shot order.

A charter operator can turn ten photos into two 30-second wan-3.0 jobs, one at 9:16 for stories and one at 16:9 for the listing page, for $7.50 in total at 720p on Sume (2 x $3.75). Ratio does not change the Wan price, because Wan 3.0 is billed per second and resolution, not per pixel, so the second ratio costs the same as the first.
| Deliverable | Ratio | Length | 720p | 1080p |
|---|---|---|---|---|
| Story clip | 9:16 | 30 s | $3.75 | $7.50 |
| Listing clip | 16:9 | 30 s | $3.75 | $7.50 |
| Both | 60 s | $7.50 | $15.00 |
Ten photos, in sailing order
- Dock and exterior from the water side.
- Deck layout from the stern, then the helm.
- Salon, galley and one cabin.
- Two photos of the water and shoreline the trip covers.
- One crew or guests photo, if you have releases for it.
Why two jobs and not a crop
Cropping a landscape clip to vertical keeps the centre third of the frame and throws away the sides, which on a boat tends to be the deck rail and the water. Wan 3.0's catalog entry lists 16:9, 9:16, 1:1, 4:3 and 3:4, so you can generate the vertical version natively and let the model compose for it. Use the same ten references and change only the ratio and one line in the prompt about framing.
A vertical clip should keep the subject in the middle two-thirds and place the boat low in the frame so the sky stays for a caption added later.
Prompt and checks
Give the clip a route: leaving the dock, open water, anchor at a quiet bay, golden hour. Thirty seconds suits four beats of around seven seconds. Name the boat's visible features from the photos in words, because Sume documents no tag syntax for references and describes them as visual guidance.
Check the hull, rails and sails against the photos before you publish. A listing that shows a feature the boat lacks is a customer-service problem. Sails, rigging and text on the transom are the likeliest places for drift.
Joining the two cuts and the music
Because the two ratios are separate jobs, the audio will differ between them if generate_audio is on. For a listing where the two clips sit side by side on different pages that is fine. If you want one soundtrack, set generate_audio to false on both jobs and lay one audio track under each clip in a timeline, which takes a spine of audio plus ordered video slots and returns an MP4.
Before you submit, check that photos are free of identifiable guests unless you hold their permission, and that every deck, helm and cabin photo shows the boat as it is today. Reference images shape the output but the clip is only as accurate as the references are current.
Draft first
A 480p draft of each ratio is $1.88, so $3.76 for both. If the draft shows the references being ignored, change the prompt before you spend $15.00 on two 1080p renders.
Sources
Related posts
More in Use cases
- ChatGPT Images 2.5 Poster and Merch templates as API prompts
ChatGPT Images 2.5 added Poster and Merch templates. The API has no template field, so write the layout into the prompt and call openai/gpt-image-2.5 on Sume.
- Livestream service intro: 10 seconds of Wan 3.0, 63 cents to $2.50
A 10-second intro bumper for a livestream or service costs 63 cents at 480p, $1.25 at 720p and $2.50 at 1080p on Sume's wan-3.0. When 1080p pays off.
- Classroom science explainer clips: six 10-second AI shots, priced
Plan six 10-second text-to-video shots for a lesson on Sume: $6.00 on H3 Max, $7.50 on Wan 3.0 or Omni Flash, $34.68 on Seedance 2.5. Accuracy limits too.
- Claymation stop-motion look: a Gemini Omni prompt that holds
Prompt Gemini Omni for a claymation or stop-motion look: material words, a choppy-frame cue, and sound. Includes a 6-second Sume request and the cost per take.
Written by Sume