AI Edit style selection launch
A fast live-action-to-motion-design launch that turns one source clip into a question, three style choices, feature proof, and a calm result card.
Field notes / why it works
The first 2.5 seconds establish a plain presenter clip, so the glitch, collage, and monochrome treatments register as a transformation. The question resolves by about 5.6 seconds; three sub-second style looks at 9.5–11.5 seconds and two capability examples through 19.9 seconds make the promise concrete. A 4.8-second final title slows the 29.2-cuts-per-minute pace enough to retain the outcome.
Plate 01 / The format in one breath
A plain, personable source clip is transformed in front of the viewer. The opening establishes the unedited input; a short burst of extreme treatments proves the product's power; large typographic cards then ask a question, present style choices, show the same material in different looks, and end with a simple outcome line.
Why it works
- The first 2.5 seconds give a clean baseline: one medium shot of a seated presenter. The noisy effects that follow read as a transformation because the viewer has seen the original.
- Around 3.7–6.9 seconds, the picture becomes a dark collage and the question appears in two installments. The visual proof arrives before a conventional explanation.
- From 7.0–13.5 seconds, a command-like card and three named styles turn an abstract editing promise into choices viewers can imagine using.
Plate 02 / Format card
| Platform · aspect · length | X · 1280×720, 16:9 · 24.7 s · 23.98 fps |
| Pace | 13 measured shots, 12 cuts, 29.2–31.6 cuts/min allowing one uncertain change; 31.6 picture changes/min; mean shot 1.9 s, median 1.59 s |
| Script | Primarily on-screen copy. The automatic 36-word speech transcript is unreliable: 22 words have low confidence and the phrases conflict with the images. No defensible spoken WPM. |
| Voice | No narration can be confirmed from the supplied evidence; make the reusable version legible without speech. |
| On screen | Roughly 0–3.7 s presenter transformation; 3.7–9.5 s dark question, command and style selection graphics; 9.5–19.9 s edited examples; 19.9–24.7 s closing typography. These are functional ranges, not exact shot-type shares. |
| Captions | No continuous subtitles. Use short headline cards and one-word style labels. |
| Sound | Continuous tonal/music-like bed, approximately 117 BPM by rough estimate; −15.1 LUFS integrated, −0.6 dBFS true peak. Cut-linked SFX are not established. |
| Structure | 5 beats: input, question, action, proof/feature examples, final outcome. No in-video spoken CTA established; the X post carries the try-now link. |
Pro / 13 plates + recipe
The first plates are open. The full dissection is Pro.
Get the timed shots, type and sound specs, and the runnable recipe.
Open the full blueprint- Plate 03 / The hook, frame by frame (first 3 seconds)Pro
- Plate 04 / Structure (beat sheet)Pro
- Plate 05 / Shot grammarPro
- Plate 06 / Visual style guidePro
- Plate 07 / Voice and deliveryPro
- Plate 08 / Sound designPro
- Plate 09 / PackagingPro
- Plate 10 / Script templatePro
- Plate 11 / Production planPro
- Plate 12 / PromptsPro
- Plate 13 / Edit recipePro
- Plate 14 / QA checklistPro
- Plate 15 / Make it yoursPro
- Recipe / runnable promptPro