15sTokyo Summer Travel Vlog Montage with One Girl
A 15-second feel-good travel-vlog montage following the same girl through 10 summer scenes in Tokyo, cut as quick handheld phone shots at about 1.5 seconds each. It uses a reference grid image to keep her face, hairstyle, and per-scene outfits consistent, with an authentic smartphone look, natural ambient light, and subtle grain.
タナベ | 動画・音声生成AI解説 @tanabe_fragm
Prompt (original, unmodified)
Use the reference grid image as the source of the same girl and her 10 summer travel scenes in Tokyo. Create a single 15-second feel-good travel-vlog montage, 16:9 horizontal, flowing through all 10 scenes in order as quick handheld phone shots, about 1.5 seconds each, snappy cuts on the beat. The same girl in every shot with consistent face and hairstyle; in each shot her outfit matches that scene in the reference. Throughout, she radiates excitement and joy — bright eyes, easy smiles, playful energy — and each shot shows off what makes that spot special. Authentic smartphone look, natural ambient light, subtle grain, light handheld motion. Bright, joyful sightseeing music that conveys the fun of travel, around 125 bpm. Shot 1 — Inokashira pond swan boat: she laughs with delight and rocks the pedal boat, sparkling water and a swan boat gliding behind, warm sun flare. Shot 2 — cafe matcha kakigori: eyes lighting up, she lifts a spoonful of fluffy shaved ice toward the camera and beams, the towering dessert in frame. Shot 3 — Harmonica Yokocho alley at night: she strolls through the glowing red-lantern alley, glances back with an excited grin, lively izakaya signs around her. Shot 4 — hotel mirror selfie: a happy, relaxed mirror selfie, she tilts her head and smiles softly, calm window light, cozy room mood. Shot 5 — summer festival night: she bites a bright candy apple and bursts into a giggle, swaying paper lanterns and a buzzing crowd behind her. Shot 6 — golden-hour window selfie: an arm's-length selfie bathed in warm sunset light, soft hair movement, a contented joyful smile. Shot 7 — ivy-covered Ghibli-style museum: she gazes up in wonder, spinning slightly to take it all in as the camera tilts up the lush green facade. Shot 8 — Inokashira park path: she crouches with a delighted laugh and points as a small squirrel scampers by, dappled sunlight, playful energy. Shot 9 — Harajuku shop window with bubble tea: she sips happily through a straw, her reflection shimmering in the glass, the bustling colorful street behind. Shot 10 — on the train home: a calm, satisfied selfie, hand on her cheek, city skyline streaking past the window, a soft fulfilled smile. Smooth energetic flow from shot to shot, consistent color and grain throughout, upbeat happy travel-diary mood.
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
The techniques this prompt uses are more common in vlog prompts than in the library overall:
| Technique | In vlog | Library average | Lift |
|---|---|---|---|
| handheld | 55% | 24% | 2.29x |
| close-up | 52% | 40% | 1.3x |
| natural light | 56% | 28% | 1.97x |
Across all 5,926 prompts, the techniques used here appear at: close-up 40%, natural light 29%, handheld 24%, golden hour 17%.
The 15s duration is not arbitrary: 71% of the prompts in this library that state a duration ask for exactly 15 seconds — Seedance 2.0 accepts clips up to 15 seconds, so 15s is the model's ceiling and the most common choice.
