Small business year in review video from 10 photos and cues
Turn a year of shop photos into a thank-you recap: image-to-video clips from first frames, trimmed, then burned with your real numbers as caption cues.

A small business year-in-review video works best as ten short clips, each started from a real photo, with your actual numbers burned in as caption cues. Use frame_images with frame_type: "first_frame" on POST /v1/videos so each clip begins on the photo you took, then add text with POST /v1/video-captions. The AI adds motion; you supply the facts.
Why start from photos?
Sume's video docs say the mode is inferred from which field you send: frame_images means image-to-video, and a pinned opening frame goes in with frame_type: "first_frame". That keeps your shopfront, products and people recognizable, which a text-only prompt cannot do. A year recap that shows invented storefronts would read as fake.
What does the pipeline look like?
Run ten video jobs, one per photo, each with a callback so you are told when it finishes. Trim any that run long, caption each with one line, and join them in the order of the year. Sume documents the job flow and webhooks on its jobs and webhooks pages.
| Step | Endpoint | Docs |
|---|---|---|
| Photo to clip | POST /v1/videos with frame_images | models/videos |
| Trim to length | POST /v1/video-trim | models/video-trim |
| One line per clip | POST /v1/video-captions with cues | models/video-captions |
| Know when done | callback_url or job polling | workflows/jobs-and-results |
Which numbers belong in the cues?
Only numbers you can show from your own books or counts: orders packed, classes taught, new locations opened. Do not let a video model draw statistics; put them in as cue text, which the captions page describes as authored overlay text. Keep each cue to a few words so it is readable in two seconds.
- Month label plus one event ("March: second oven")
- One thank-you line to customers near the end
- Your site or phone number on the final clip
When should you post it?
Late December and early January are common for recaps, but pick the day that suits your audience. Make a vertical cut first if you post to phones, and keep the total short enough that people watch to the thank-you.
Sources
Related posts
More in Use cases
- Zoom video background: MP4 or MOV, 360p to 1080p, from Sume
Zoom accepts an MP4 or MOV video background between 480x360 and 1920x1080. Generate a 16:9 clip on Sume at 720p or 1080p and skip the 4K trap.
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
- AI avatar for online course videos: build and update lessons
Use an AI avatar as your online course instructor: one reusable avatar, a short talking video per section, captions, and one Timeline join per lesson.
- Talking avatar for PowerPoint presentations, slide by slide
Make a talking avatar presenter for PowerPoint: one Sume clip per slide, up to 60 seconds each, in 16:9 or 4:3 to match the slide, inserted as MP4.
Written by Sume