Cheapest product video ad: six stills in a Timeline render for $0.30
Six product photos become a 15 s vertical ad with no video model: a $0.10 Timeline render plus $0.20 caption cues. $0.30 against $3.43 for five Wan clips.

The floor price of a product video ad on Sume is $0.30: six product photos placed in one Timeline render at $0.10, plus $0.20 for caption cues that carry the offer text. No video model is involved. A 15-second vertical ad built this way costs one-eleventh of the $3.425 five-clip version (five photos to one 15-second ad), and it is the right baseline to compare any motion clip against (prices read 2026-10-05).
What Timeline does with a still
The Timeline docs say stills are accepted in video[] as static holds; a motion field is accepted but ignored and reported as motion_ignored, so there is no pan or zoom on a still. What you do get is cuts and transitions: fade, wipeleft, wiperight, slideup, slidedown and dissolve, at 1 second or less, and four fit modes: cover, contain, stretch and blur. The output defaults to 1080x1920.
The docs list blur next to contain as a fit mode, so try contain or blur on square product shots to avoid cropping the product in a vertical frame; plan one test render to see how each looks.
The builder
This script builds a six-slot, 15-second body with a slideup transition between photos. Call POST /v1/timeline-1.0/plan first; it is unbilled and returns the segment count and estimated cost.
import json
def still_ad(photos, seconds_each=2.5):
video = []
for i, url in enumerate(photos):
slot = {"source_url": url, "start": i * seconds_each,
"duration": seconds_each, "fit": "blur"}
if i:
slot["transition"] = {"type": "slideup", "duration": 0.25}
video.append(slot)
return {"audio": {"mode": "silence",
"duration_seconds": seconds_each * len(photos)},
"video": video}
photos = ["https://media.sume.com/artifacts/demo/p%d.jpg" % n for n in range(1, 7)]
body = still_ad(photos)
print(body["audio"]["duration_seconds"], "s,", len(body["video"]), "slots")
print("render cost USD:", 0.10, "+ captions", 0.20)
Where stills win and where they do not
A still sequence is a slideshow, so it fits product ads where the picture is the point: sizes, colourways, bundles and offers. It does not show a garment move, a liquid pour or a gadget in use.
| Build | Lines | Total |
|---|---|---|
| Six stills in Timeline | $0.10 render + $0.20 cues | $0.30 |
| Five Wan 3.0 clips, 3 s each used | $3.125 + $0.10 + $0.20 | $3.425 |
| Five Seedance 2 clips | $9.45 + $0.10 + $0.20 | $9.75 |
A practical split for a holiday catalog is stills for the long tail and motion for the leaders, which is the idea behind ranking SKUs by profit. Hundred-SKU totals are simple: 100 still ads cost $30.00, 100 Wan ads cost $342.50. Caption cues must carry text with start and end, as in the promo code recipe.
Sources
Related posts
More in Media tools
- Check an AI pattern tiles seamlessly with ImageChops.offset
Shift a Sume pattern image by half its size with ImageChops.offset and measure the seam stripe. A pass or fail score before you ship a repeating background.
- Check on-screen text in a Wan 3.0 clip: video frames at exact seconds
Wan 3.0 claims text rendering in 12 languages. Before you ship, pull PNG stills at the seconds the text appears with Sume video frames and read them yourself.
- Coffee roaster brand video music: a 40-second lofi bed
Brief a warm 40-second lofi bed with vinyl texture for a coffee roaster brand video: one generation and a one-minute render, $0.225 on Sume.
- Coffee roaster holiday video: caption in your brand colour with design
Caption a roaster's holiday video in a brand colour with `design.colors.active`, then restyle twice without a second transcription: three looks for $0.60.
Written by Sume