Tags: travel-vlog storyboard ai-video Video Template: Text Input: storyboard_reference_image (image) Output: storyboard_image (image) Output: travel_vlog_video (video) openai-gpt-image-2 bytedance-seedance-2-0

Tokyo Travel Vlog Storyboard and 15-Second Video

Create a 13-frame candid Tokyo travel storyboard, then use it as the visual reference for a fast-cut, 15-second music-video-style travel vlog with Korean subtitles and dialogue.

By Threads — Published on

Example results

Download video result 1

Prompt template

## 1. Storyboard image prompt

Generate a detailed sketch image as a 13-frame grid collage, arranged in three rows: Row 1 has 4 frames, Row 2 has 5 frames, and Row 3 has 4 frames. Show the same young female travel vlogger across candid moments on a relaxing holiday in Japan. She is a 22-year-old K-pop idol with long, straight black hair, one side tucked behind her ear, stylish Japanese-inspired oversized streetwear, and an expressive, spontaneous personality. Make each frame feel like an imperfect casual phone capture, with natural inconsistencies in framing and exposure.

### Row 1
1. **Tokyo Tower:** Low-angle selfie with Tokyo Tower behind her; slightly tilted horizon, nearly white overexposed sky, natural smile as she adjusts into frame, small lens smudge in a corner, candid arrival energy.
2. **Shibuya street level:** Walking through Shibuya Crossing at night; handheld motion blur, glancing back mid-step, neon reflections on wet pavement, slightly shaky framing and imperfect crop.
3. **Convenience store:** Inside a brightly lit convenience store, holding onigiri close to the camera with playful raised eyebrows; harsh fluorescent light flattens the scene, whites are slightly overexposed, shelves softly blurred behind her.
4. **Yoyogi Park:** Sitting on a bench under trees and looking away from the camera; quiet candid moment, soft dappled daylight, slight focus miss on her eyes, subtle lens smudge in a bottom corner.

### Row 2
5. **Takoyaki reaction:** Close-up as she eats one takoyaki, reacting mid-bite with laughter; slight motion blur, warm lantern light behind her, face slightly out of focus from movement.
6. **Vending machine at night:** Standing in front of a glowing vending machine and casually pressing a button; uneven blue and pink light on her face, visible high-ISO grain.
7. **Train reflection:** Her face reflected in a train window at night, with city lights streaking behind; layered reflection, slight ghosting on the glass, looking away from the camera.
8. **Torii gate:** Low-angle view from slightly behind as she walks through a torii gate; motion blur in her movement and mild lens flare from a bright sky.
9. **Digital art exhibit:** Inside an immersive light exhibit, looking upward in awe as blue, violet, and gold light falls across her face; slight motion blur and visible low-light noise.

### Row 3
10. **Gundam statue:** Low-angle wide shot; she appears small beneath the towering statue, with slight phone-lens barrel distortion and a slightly blown-out sky.
11. **Lantern alley:** Walking through a narrow alley lit by warm lanterns, shot from behind as she briefly glances back; underexposed shadows and grainy night detail.
12. **Rooftop skyline:** Selfie with the Tokyo skyline behind her, arm extended and wind blowing hair partly across the lens; slightly tilted horizon and distant city glow overexposed.
13. **Nara deer park:** Crouching in a park and offering a deer cracker to a deer. The deer bows its head toward her; she bursts into genuine laughter, surprised and leaning slightly back. Another deer nudges her from behind, making her lose her balance a little. Capture the moment imperfectly with slight shake and off-center framing, in soft natural daylight with trees and open park space. Keep the energy unscripted and chaotic.

Overall, depict a beautiful, expressive young female travel vlogger with long straight black hair tucked behind one ear, stylish Japanese streetwear, and a relaxed holiday mood. Make the images feel like authentic handheld iPhone photos with natural ambient lighting and subtle imperfections such as tilt, motion blur, grain, and imperfect focus.

## 2. Video prompt

Create a 15-second Tokyo travel vlog music cut with Korean subtitles. Use the generated storyboard image as the visual reference: @img. Keep the same girl as in the reference images: a young Korean idol-like woman in her early 20s, with long straight black hair and soft natural volume, fair porcelain skin, large bright expressive eyes, a delicate V-line face, small nose, natural glossy lips, fresh minimal makeup, and a cute, approachable expression. Dress her in casual Japanese streetwear such as a white hoodie, dark oversized hoodie, or oversized jacket.

Use a 26mm phone lens, deep focus, realistic skin texture, mild HDR, neutral iPhone color science, and an unedited candid look. Avoid cinematic color grading, studio lighting, light trails, and artificial motion-blur effects. Use quick cuts timed to music, following this timeline:

- **0:00–0:01 — Tokyo Tower reveal:** Low-angle walking selfie; reveal the tower behind her. The sky is overexposed; she smiles naturally in neutral daylight with deep focus. Dialogue: “드디어 도쿄에 왔어요...!” Hard cut on the beat drop.
- **0:01–0:02 — Shibuya Crossing:** Mid-stride in the crowd; she turns her head toward the camera. Neon signs remain sharp behind her with realistic night exposure. Fast cut on the beat.
- **0:02–0:03 — Convenience store:** She holds onigiri up to the camera with raised eyebrows. Harsh fluorescent interior lighting, cool white light, realistic skin. Snap cut on the beat.
- **0:03–0:04 — Yoyogi Park:** Seated and looking away, in dappled light with a visible lens smudge. Let the music drop out for one beat so wind and birds are heard, then bring it back. Cut on natural movement.
- **0:04–0:06 — Takoyaki reaction:** She takes a bite, widens her eyes, then pulls back laughing. Warm practical lantern light and realistic amber skin tones. Dialogue: “뜨거워! 진짜 맛있어!” Cut at the end of her laugh.
- **0:06–0:07 — Vending machine at night:** She stands before a glowing vending machine with mixed LED light on her face and a slight smirk. No glow effects. Single-beat cut.
- **0:07–0:08 — Train window:** Her face is reflected in the window as the city passes naturally blurred outside. She looks out, not at the camera. Snap cut.
- **0:08–0:09 — Torii gate:** Low angle as she walks toward and through the shrine gate; the gate fills the top of frame. Natural daylight. Snap cut.
- **0:09–0:11 — Digital light exhibit, signature moment:** She slowly looks upward as blue, violet, and gold projections fall across her face. Rack focus so her face is sharp and the lights are diffused. Keep the effect to projected light on skin, with no bloom. Use about 60% slow motion. Soft cut during the upward movement.
- **0:11–0:12 — Gundam reveal:** Start on her face, tilt the camera up to reveal the full statue. She gives a small, impressed smile. Wide angle, natural daylight. Sharp cut after the smile.
- **0:12–0:13 — Lantern alley:** Follow from behind as she walks through warm lantern light and dark shadows. She glances back once. Keep the low-light look natural. Cut as she moves forward.
- **0:13–0:14 — Rooftop skyline:** Start with a close selfie, then extend her arm to reveal the skyline. Wind moves her hair; use natural night phone exposure. Dialogue: “이런 야경은 처음 보는 것 같아요.” Hard cut on the last word.
- **0:14–0:15 — Nara deer park:** She crouches and offers a deer cracker. The deer bows; she laughs, and another deer nudges her from behind so she nearly topples. Keep the handheld framing slightly off-balance and the moment natural. Dialogue: “잠깐! 진짜 절했어!” Fade to black.

Comments — 0

Related prompts