Shichi-Go-San Sun 15 Nov 2026: a photo studio booking clip

Shichi-Go-San is traditionally observed on 15 November, which is a Sunday in 2026, and many families visit a shrine or a photo studio on a nearby weekend instead. A family photo studio can turn one photo of its portrait room into a short silent clip and burn a booking reminder onto it with caption cues.

The tradition's details come from Nippon.com, read on 2026-10-13. Everything about Sume comes from the docs pages under sources.

What does Nippon.com say about the day?

The article says Shichi-Go-San is traditionally observed on 15 November, though families often visit on a nearby weekend. It describes three- or seven-year-old girls and five-year-old boys visiting a shrine or temple to pray for their growth, with formal ceremonies where priests recite prayers or simpler visits with an offering, and photo sessions at studios as an increasingly popular option. Children receive bags of chitose ame, a long thin red and white candy that symbolises longevity and health.

Ages and customs differ by region and family, so a studio clip should not tell families what they must do.

Which Sume calls build the clip?

Step one is a video job at POST /v1/videos. Put your photo in frame_images with frame_type set to first_frame and Sume treats the job as image-to-video; send no photo and it is text-to-video. Before you pick a model, call GET /v1/videos/models and read supported_durations, supported_frame_images and supported_aspect_ratios for it, because limits differ by model. The docs state, for example, that wan-3.0 accepts 2 to 30 seconds.

Step two is POST /v1/video-captions with the finished clip's public HTTPS URL as video_url and a cues array of text, start and end. Because you send cues, Sume does not run speech-to-text and burns your text at those times. A silent clip with no cues fails with caption_no_speech, so the cues are not optional for a silent clip. Both calls are asynchronous jobs; poll or take a webhook for the result.

What should the cues say?

Keep cues short; a family reads them on a phone. A five-cue plan for a 10-second clip:

How do you send the caption job?

This script builds the cue payload and prints it, so you can check the JSON before you post it with your own API key and the real clip URL.

import json

cues = [
    (0, 2, "Shichi-Go-San, Sunday 15 November"),
    (2, 4, "Family portraits in kimono"),
    (4, 6, "Book a weekend slot now"),
    (6, 8, "Chitose ame for every child"),
    (8, 10, "We are open Saturday and Sunday")
]
payload = {
    "video_url": "https://example.com/shichi-go-san.mp4",
    "cues": [{"text": t, "start": s, "end": e} for s, e, t in cues],
}
print(json.dumps(payload, indent=2))

What can go wrong?

Host the clip at a public HTTPS URL first. Do not use a photo of a real child in a public clip without a parent's permission; an empty set or a kimono on a stand is a safer still. Generated motion can bend patterns on fabric, so check the result before you caption it.

If you offer chitose ame, say so; if you do not, drop that cue. The article describes the custom, not your studio.