Gift-wrap pop-up promo clip: three cues and a pickup cutoff

For a gift-wrap pop-up, shoot one tidy photo of wrapped boxes, animate it for 5 to 8 seconds, and burn three caption cues onto the clip: the service, the price you charge, and the last drop-off time. The photo and the three lines are the whole job; the cutoff is the line that matters because customers will plan around it.

Why a cutoff-first clip?

A service business sells certainty. A clip that says "Drop off by Dec 22, 5 pm" tells a shopper whether you can help, and it saves your staff from answering the same question all week. Put the real date and time from your own schedule; this post does not know your hours.

What does the build look like?

The three steps use documented Sume endpoints. First, submit your photo as the first frame to POST /v1/videos, choosing a model and duration from GET /v1/videos/models. Second, poll the job and download the result. Third, send the finished video URL to POST /v1/video-captions with cues.

Cues take text, start and end. Keep each on screen for at least two seconds so it can be read, and leave the first half-second clean.

What should the three cues say?

Read the finished MP4 on a phone before posting. A cue that is cut off by the platform's interface is a wasted job.

• Line 1: "Gift wrapping, while you shop" (service).
• Line 2: your real price per item or per box.
• Line 3: "Last drop-off [date], [time]" (cutoff).

Can the same clip serve alterations or engraving?

Yes: swap the photo and the three lines. Because the cues are plain text in your request, one template can produce a clip per service. Submit each as its own job and keep the returned job ids so you can retrieve results later.

Which model should you pick, and how do you keep spend bounded?

Do not guess at model limits. The Sume video guide says to read GET /v1/videos/models before submitting, because limits differ per model: for example wan-3.0 accepts 2 to 30 seconds, seedance-2.5 accepts 4 to 30 seconds at 480p, 720p and 1080p, and gemini-omni-flash-1.1 accepts 3 to 10 seconds. The same catalog carries pricing_skus, so you can read the price of the length and resolution you want before you spend anything.

For a social story, a short clip at a modest resolution is enough; a higher tier costs more and a phone screen rarely shows the difference. Draft once at the lowest tier that looks right, check the cues and the dates, and only then decide whether a second render is worth it.

Keep the idempotency habit too. Where an endpoint requires an Idempotency-Key, reuse the same key when you retry the same request so a network error does not create a duplicate job.