A Drawing Becomes a Storybook
A spare Gemini product demo turns a child's drawing into an illustrated, narrated book, then shows how to use it.
Field notes / why it works
The specific typed request and original drawing are both visible by 0:07, so the illustrated robot at 0:27 reads as a personal transformation. Nine on-screen state changes carry the 39-second sequence without hard cuts; the book's readable page and brief narration at 0:19 prove the output before share/print controls and the 0:35 CTA make it actionable.
Plate 01 / The format in one breath
An almost white product demo starts with a personalized greeting, slides into a prompt box, shows a personal source image, then turns that source into a finished storybook. The payoff is both an illustrated page and a short read-aloud sample; the final seconds show a practical action and a clear destination.
Why it works
- The viewer understands the input by 0:07: a visible prompt is followed by a child's robot drawing. That makes the later illustrated robot feel like a transformation rather than a generic asset.
- The result unfolds in stages: waiting at 0:12, first book glimpse around 0:17, narration and readable page at 0:19–0:26, full illustrated spread at 0:27. Each state answers a different question about the product.
- The final menu at 0:29–0:31 makes the book feel usable, then the 0:35 CTA points to a specific URL. There is little competition for attention because the background stays nearly white.
Plate 02 / Format card
| Platform · aspect · length | X · square 1:1 · 39.1 s · 720 × 720 at 29.97 fps |
| Pace | One continuous designed sequence; 0 detected hard cuts, 9 internal state changes, about 13.8 picture changes/min. The 39.1 s “shot” is a detector artifact of seamless UI animation, not a static hold. |
| Script | 20 recognized spoken words; 134 wpm during the speaking section; first speech at 0:18.7; speech covers about 23% of runtime. The recognition after the opening story line is uncertain. |
| Voice | Calm, medium-register, story-reader archetype with animated pitch during the book sample; no presenter. |
| On screen | Full-frame white UI/motion graphics; one hand-drawn source image; generated book/page artwork; no talking head. |
| Captions | No speech subtitles. UI copy and printed book text carry the meaning for silent viewers. |
| Sound | Silence before and after the brief read-aloud sample; no music bed evidenced. Measured −19.8 LUFS integrated, −6.3 dBFS true peak. |
| Structure | Greeting → prompt → source → generation → narration/page → illustrated spread → share/print → CTA → logo. Payoff begins about 0:19; CTA at 0:35. |
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