Advent calendar video series: 24 doors, one teaser, one bulk run
An advent calendar has 24 doors from December 1. Make 24 door stills and a 48-second teaser for about $1.43 on Sume, or 24 daily clips for about $3.73.

An advent calendar video series has 24 doors starting on Tuesday 1 December 2026. Two ways to build it on Sume: a 48-second teaser of all 24 doors from 24 stills for about $1.43, or 24 separate daily 4-second clips for about $3.73. Pick the teaser first, since it also works as the announcement.
Facts are from Wikipedia's Advent calendar article, read 2026-10-03: the calendar counts the days of Advent before Christmas; traditional ones have a door for each day up to 24 December; many reusable ones start on 1 December while others start on the first Sunday of Advent; it began with German Lutherans; and behind each door is an image, a poem, part of a religious story or a small gift. Our Hanukkah eight-night post covers the shorter sibling.
Decide what is behind each door
The doors are the content. A bakery can show a different biscuit; a bookshop a different line from a book; a clinic a different winter tip. Write 24 one-line prompts first. A spreadsheet with day, door line and image prompt is all the plan you need.
Option A: one 48-second teaser
Generate 24 stills with bytedance-seed/seedream-4.5 ($0.05 each, $1.20). Timeline accepts up to 200 video slots and chunks the render itself past 12 segments, so 24 slots of 2 seconds is fine; the output is 48 seconds, billed as one ceil minute ($0.10). Add a music bed ($0.125). Total: 1.20 + 0.10 + 0.125 = $1.425.
| Plan | What you get | Cost |
|---|---|---|
| Teaser | One 48 s video, 24 doors, 2 s each | 24 x $0.05 + $0.10 + $0.125 = $1.425 |
| Daily clips | 24 separate 4 s MP4s, one per day | $1.20 + 24 x $0.10 + $0.125 = $3.725 |
| Daily clips with a door line burned in | Same, plus one caption job each | $3.725 + 24 x $0.20 = $8.525 |
Option B: 24 daily clips
Render each day as its own Timeline job with the same music bed as soundtrack, submitted a week ahead. Every job needs an Idempotency-Key. If each door is a Format run instead, a bulk queue takes up to 100 items with a concurrency window, so 24 items is one request; give each run a generation_spend_cap_usd so one bad door cannot run away. The sample below burns one door line onto a finished clip with the standalone caption job; authored cues need no speech.
import os, sys, uuid, requests
def main():
key = os.environ.get("SUME_API_KEY", "")
if not key:
sys.exit("Set SUME_API_KEY first")
body = {
"video_url": "https://media.sume.com/artifacts/YOUR_ARTIFACT/clean.mp4",
"style": "slam",
"cues": [
{"text": "Door 7: peppermint bark", "start": 0.0, "end": 3.5},
],
}
resp = requests.post(
"https://api.sume.com/v1/video-captions",
json=body,
timeout=60,
headers={"Authorization": "Bearer " + key,
"Idempotency-Key": str(uuid.uuid4())},
)
print(resp.status_code, resp.json())
if __name__ == "__main__":
main()
What Sume does and does not do
- Does: generate the 24 stills, the music and the MP4s, with the numbers burned in if you want them.
- Does not: publish one per day or lock a door until its date. Scheduling lives in your social tool.
- Does not: judge whether a door's content suits your audience's beliefs. Some calendars are religious, with Bible verses and prayers, and some are chocolate.
Sources
Related posts
More in Use cases
- Affiliate link on Instagram: does it need the paid partnership label?
Meta says content with an affiliate link should carry the Paid partnership label, even with no business partner tagged. What that means for AI clips.
- AI airport sign photos: set arrows and words in code, not the model
Image models still bend arrows and misspell wayfinding text. Generate a sign with no text, then set the exact arrows and words in Pillow. Runnable script.
- AI app icon via API: generate 1:1, add a transparent option, resize
App icon art from the Sume image API: 1:1 text-free art, ChatGPT Image 2.5 for a transparent background, and a Pillow loop that exports the sizes you need.
- AI architecture concept render from a sketch via API on Sume
Turn a massing sketch or photo of a model into a concept render: reference edit rows on Sume from $0.025, 16:9 framing, and why you should label it a concept.
Written by Sume