CampaignReel

Ad placement specs against what generators output

Ten minutes against thirty, and a nested ceiling

One page states a maximum duration of ten minutes. The other states thirty minutes per scene with fifty scenes per video. Both are far beyond anything an advertisement needs, so the useful difference is not the size of the figure but its shape. As of 2026-09-22.

A nested ceiling survives the scaleBoth figures are far beyond anything an advertisement needs. Only one of them says how many setups a single job assembles, which is a statement about workflow.Three figures in minutesTen minutesOne continuous run, bounded by file handlingThirty minutes per sceneOne continuous run, on the other pageFifty scenes per videoThe joining step is inside the job, not in an editOnly the third changes a plan
Fig. 1 Reading either figure as headroom teaches nothing; the second figure is the useful one.
What each page puts in writingFilled where the page states something in that column, hollow where it does not address it.What each page puts in writingHedraHeyGenOne continuous runOne continuous run — Hedra: 10 minutesOne continuous run — HeyGen: 30 minutesHow many runs one job holdsHow many runs one job holds — Hedra: Not statedHow many runs one job holds — HeyGen: 50 scenesWhere assembly happensWhere assembly happens — Hedra: Outside the stated figureWhere assembly happens — HeyGen: Inside the job
Fig. 2 Filled where the page states something in that column, hollow where it does not address it.
The two ceilings, and what each covers. Recorded 2026-09-22.
What the pages stateHedraHeyGen
One continuous run10 minutes30 minutes
How many runs one job holdsNot stated50 scenes
Where assembly happensOutside the stated figureInside the job

Inclusion rule. Length figures each page states. The product of the nested pair is not computed, because neither page performs that multiplication. Order. The continuous figure first, then the container around it.

1Both figures are inert for advertising, one usefully so

The longest slot this register reads is sixty seconds. Ten minutes and thirty minutes are both accurate and both irrelevant to it, and reading either as headroom teaches nothing about the campaign.

The nested figure is different. Fifty scenes per video says the joining step is inside the product, so a piece made of four setups is one job rather than four jobs and three seams. That is a statement about workflow, and it survives the scale.

2What decides the length on each row

Both animate a performance from supplied audio, so in both cases the output runs as long as the speech. The ceilings are statements about file handling rather than about how long a generated scene holds together.

That is why neither belongs in an ordering with the prompt-driven rows. A table that sorted thirty minutes above thirty seconds would be publishing a category error as a finding, and these sheets refuse to rank the column for that reason.

3The columns beside them diverge much more than the length does

One page publishes seven shapes including two ultrawides; the other publishes two. One publishes three named rungs; the other publishes dimensions free between 128 and 4,096 pixels a side.

So a choice between these two rows is almost never a choice about length. It is a choice about whether the campaign needs unusual shapes or exact pixel sizes, and the length column these two share is the least informative thing on either page.

4The rest of the column behind these two

Duration across the registerHedra is marked; HeyGen sits at thirty minutes per scene, with fifty scenes in one job in the same column. Recorded 2026-09-22.Duration across the registerDurationAmazon Nova Reel — Duration: 6 s increments, up to two minutesAmazon Nova ReelCogVideoX — Duration: 6 s, at 49 framesCogVideoXGoogle Veo — Duration: 4, 6 or 8 sGoogle VeoGrok Imagine — Duration: 1 to 15 sGrok ImagineHedra — Duration: 10 minutesHedraHeyGen — Duration: 30 minutes per sceneHeyGenKling AI — Duration: Not statedKling AILTX-Video — Duration: Frames, never secondsLTX-VideoMiniMax — Duration: 4 to 15 sMiniMaxPika — Duration: 5 s and 10 s, 20-25 s on PikaframesPikaPixVerse — Duration: 1 to 15 s on version 6PixVerseRunway — Duration: 5 to 15 s on Gen-4.5RunwaySceneMixer — Duration: Thirty seconds on the Wan tiers, fifteen on H3SceneMixerVidu — Duration: Not statedViduWan 3.0 — Duration: 2 to 30 sWan 3.0
Fig. 3 Hedra is marked; HeyGen sits at thirty minutes per scene, with fifty scenes in one job in the same column. Recorded 2026-09-22.
Every generator in the register on the duration column, with Hedra marked. Recorded 2026-09-22.
GeneratorDuration
Amazon Nova Reel6 s increments, up to two minutes
CogVideoX6 s, at 49 frames
Google Veo4, 6 or 8 s
Grok Imagine1 to 15 s
Hedra10 minutes
HeyGen30 minutes per scene
Kling AINot stated
LTX-VideoFrames, never seconds
MiniMax4 to 15 s
Pika5 s and 10 s, 20-25 s on Pikaframes
PixVerse1 to 15 s on version 6
Runway5 to 15 s on Gen-4.5
SceneMixerThirty seconds on the Wan tiers, fifteen on H3
ViduNot stated
Wan 3.02 to 30 s

Inclusion rule. Every generator this register carries, on the one column this pair disagrees about. Rows that state nothing keep their place and are marked hollow. Order. Alphabetical by generator name.

Why these two. Two ceilings in minutes look like the same kind of fact. One of them says how many setups a single job assembles, which is the only part of either figure an advertisement under a minute could ever use.

5Sources

Read from the Hedra Character-3 model page and the HeyGen usage limits page, both checked 2026-09-22. The column is described on duration, and each entry has its own cell page at Hedra and HeyGen, and the rule that keeps surfaces and generators apart is on method. Nearby pairs: Nova Reel and Grok Imagine, Veo and Grok Imagine.