Poppy Appeal 2026 collection clip: 22 Oct launch to 8 Nov cues

A branch, school or shop that wants a Poppy Appeal reminder clip has until the national launch on Thursday 22 October 2026 to get one ready, and the Royal British Legion's own page gives every date you need. The cheapest build on Sume is one photo of your collection tin or stall turned into a short image-to-video clip, then a second job that burns the dates onto it as caption cues. The clip is silent, so the cues are authored text, not speech-to-text.

The dates and the donation wording come from the Legion's Poppy Appeal page, read on 2026-10-13. Everything about Sume comes from the docs pages listed under sources. A clip like this is a reminder for your own group; it does not speak for the Legion, so check the charity's own guidance before you use its logo.

What dates does the Royal British Legion list for 2026?

The page lists a national launch on 22 October, London Poppy Day on 29 October, the Festival of Remembrance at the Royal Albert Hall on 7 November, the march past the Cenotaph on Remembrance Sunday, 8 November, and Armistice Day with the Two-Minute Silence on 11 November. It says poppies are available from local supermarkets, high street shops and train stations and from the online Poppy Shop, and that there is no set donation amount: people give what they can.

Your clip should repeat only what you know. If your branch collects at a station on a set Saturday, say that, not the national list.

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 each cue short enough to read in two seconds. A five-cue plan for a 10-second clip that a local branch could post from 22 October:

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, "Poppy Appeal launches 22 October"),
    (2, 4, "Find us at the station stall"),
    (4, 6, "Give what you can"),
    (6, 8, "Remembrance Sunday is 8 November"),
    (8, 10, "Two-Minute Silence, 11 November")
]
payload = {
    "video_url": "https://example.com/poppy-appeal.mp4",
    "cues": [{"text": t, "start": s, "end": e} for s, e, t in cues],
}
print(json.dumps(payload, indent=2))

What can go wrong?

The video URL must be public HTTPS, so host the finished clip before the caption job. Look at the generated motion before you caption it: a photo of a tin or a poppy display should not gain invented lettering or a different emblem. If it does, pick another still. A subject as solemn as Remembrance is better served by a plain, slow clip than a busy one.

Last, the national dates are the Legion's. Your collection times, tin locations and any card-payment option belong in cues only if you have confirmed them locally.