Reel teardown #10: an AI macro science reel with slow push-ins and small soft-fade captions
We took apart one Instagram reel by @duziano, an AI macro science reel with slow push-ins and small soft-fade captions. It had 416,258 plays on 5 Nov 2026, 8.7x its page's median. Length, cuts, pace and loudness were measured by script, and the frames were read one by one.
The reel in numbers
Reel by @duziano on Instagram. Watch the original reel. We link to it and do not copy it.
Posted on 23 Oct 2026. Plays and followers as shown on Instagram on 5 Nov 2026.
| Measure | Value | What it means |
|---|---|---|
| Length | 61.5 s | Length of the file we measured. |
| Plays when measured on 5 Nov 2026 | 416,258 | Plays as shown on Instagram that day. They include replays. |
| The page's median plays over its last ~10 reels | 47,968 | Plays of a typical recent reel on this page. |
| This reel against that median | 8.7x | This reel's plays divided by the page median. |
| Followers | 27,975 | Followers of the page on 5 Nov 2026. |
| Hard cuts per minute | 4.9 | Hard cuts counted by script. Fast dissolves are not counted. |
| Median shot length | 9.13 s | Median time between hard cuts. |
| First hard cut at | 12.83 s | Time of the first hard cut the script found. |
| Hard cuts in the first 3 s | 0 | Hard cuts found before the 3 s mark. |
| Big visual changes per minute | 23.4 | Hard cuts plus large camera travel or scene changes. |
| Integrated loudness | -14.2 LUFS | Integrated loudness of the audio track, in LUFS. |
| Speech | 2.75 words per second, language guess: English | Words per second and a language guess from a speech-to-text pass. |
The first three seconds
What we saw frame by frame: Frame 0 mid-action: macro photoreal golden retriever with a cut-away nose cross-section showing glowing airflow; at 0.5 s mist exhales and the first caption words 'did you' appear.
By script, the first hard cut comes at 12.83 s, with 0 hard cuts in the first 3 s and 1 big visual change in the first 3 s.
The reel opens mid-action on a close macro shot and the first caption words appear at 0.5 s. The first hard cut is well after the first three seconds.
Captions and on-screen text
What we saw frame by frame: Small white lowercase serif captions mid-lower, 2-4 words karaoke-like with soft fade; faint 'DUZIANO' watermark bottom-centre. No emphasis colour. English.
Captions are small, lowercase and serif, two to four words at a time, with a soft fade and no emphasis colour. They are quiet by design: the picture is the main thing on screen.
Shots and pace
What we saw frame by frame: Slow push-ins on the same dog with dissolve-like changes.
By script: 6 shots, 4.9 hard cuts a minute, a median shot of 9.13 s, and 23.4 big visual changes a minute.
Long shots with slow push-ins on the same subject. The big-visual-change count is much higher than the hard-cut count, which suggests the changes are dissolve-like and the hard-cut script does not see them.
Sound
What we saw frame by frame: Original audio, calm English narration, soft music.
Measured loudness: -14.2 LUFS. Speech: 2.75 words per second, language guess: English.
A calm English narration over soft music. Loudness is in the table above.
Structure and ending
- Structure: Did-you-know hook then nose splits airflow then back chamber collects scents then exhale lets new scent in then continual sampling.
- Ending: Ends on dog in forest light; caption invites the next animal.
A did-you-know opening, then the fact explained in a few steps. It ends on a calm shot and a caption inviting the next animal.
Effects we have for this
Each row is a match to something the notes say the reel shows. We never claim the creator used our effect; it is our closest effect.
| What the reel does | Our closest effect | Note |
|---|---|---|
| Small lowercase captions, two to four words, karaoke-like with a soft fade. | Karaoke pill captions | Our closest effect for short synced captions. The reel's fade is softer than a pill. |
The notes describe dissolve-like changes between shots. We do not map them, because the notes do not say which transition it is.
Method and limits
- Length, size and frame rate: read from the file.
- Hard cuts, shot length and first cut: a script that finds hard cuts between frames. Fast dissolves are missed.
- Big visual changes: hard cuts plus large camera travel or scene changes.
- Loudness: integrated loudness of the audio track in LUFS. It is blank when the file had no audio track.
- Speech: words per second and a language guess from a speech-to-text pass.
- Plays, followers and the page median: collected by Apify on 5 Nov 2026.
- What we saw frame by frame: a model read a contact sheet of the reel. Treat these as observations, not measurements.
- Hard-cut counts miss dissolves, so a reel built on dissolves can show close to zero hard cuts.
- The big visual change count also counts camera travel and scene changes, so it is not the same as the cut count. We show both.
- Some full-HD files had no audio track, so loudness and speech are blank for those reels.
- Plays include replays. Shares and follower conversion cannot be seen from outside.
- Ten reels from one page are not ten independent tests.
- Hashtag discovery favours pages that already had a hit, so breakout pages are over-represented.
- Plays per follower favours small, newer pages; it measures reach health, not size.
- Formats measured on only one to three pages are hypotheses.
- No number here is a promise about what a new reel will do.
Plays and followers as shown on Instagram on 5 Nov 2026. We link to the reel and do not copy or embed it.
Page checked on Nov 4, 2026.