One scene, five editable expressions
A 28-second product preview compares five emotional performances in one fixed scene, then reveals a minimal product card.
Field notes / why it works
From 0:00 to 0:22.4, five emotion states reuse the same character and room, so viewers can compare one changed variable. The selector begins large, shrinks into a persistent legend, and each state change lands on a measured cut; a quiet ivory claim card at 22.4 and URL at 25.8 turn the proof into a product message.
Plate 01 / The format in one breath
A character in one locked, cinematic scene performs five different emotional states while a small radial selector labels each one. The video demonstrates post-generation control through direct comparison, then replaces the scene with a plain product card and URL. The product promise is visible from the opening selector and becomes explicit in the end card at 22.4 s.
Why it works
- The same character, wardrobe and room persist across five states from 0:00–0:22.4, making the changed performance the only variable to inspect.
- A dark six-choice wheel starts large on the right and shrinks toward the character's shoulder within the opening second; this shows the interaction before any explanatory voiceover.
- The expressions progress from neutral to angry, disgusted, sad and happy; the 22.4 s ivory card turns that proof into a product proposition, followed by a URL at 25.8 s.
Plate 02 / Format card
| Reference | |
|---|---|
| Platform · aspect · length | X · 16:9 · 1280×720 · 30 fps · 28.0 s |
| Pace | 6 measured shots, 5 cuts, 10.7 cuts/min; 1 internal picture step; 12.9 picture changes/min; mean shot 4.67 s |
| Script | 61 spoken words; 165 wpm over full runtime, about 237 wpm during speech; 11 short sentences, averaging 5.5 words |
| Voice | One animated adult masculine character voice, medium register; acted emotional dialogue, not a narrator |
| On screen | ~80% one staged character scene and its product overlay; ~20% ivory motion-graphic end card |
| Captions | Small static white feature descriptors near bottom centre; tiny state label at bottom right. They are UI copy, not transcribed speech. |
| Sound | Tonal bed detected about 13.9 dB below voice; no clear cut accents; measured −13.5 LUFS integrated |
| Structure | Selector introduction → five state demonstrations → product card → URL |
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