- Video duration:
- 16s
- Video dimensions:
- 720 × 1280
Selfies across New York, Istanbul and Dubai
A woman films herself against street scenes in three cities, creating a travel-location montage.
- Video model
- MiniMax H3
- Video duration
- 16s
- Aspect ratio
- 9:16
- Generation mode
- Not specified
Prompt
Create a 15-second ultra-realistic cinematic travel vlog filmed entirely as natural handheld smartphone footage. Keep the exact same young woman throughout all three locations with identical face, facial proportions, skin tone, long dark-brown hair and natural expressions. No beauty filters, no subtitles, no music. Use realistic objects passing directly in front of the camera to create seamless transitions. 0:00–0:02.5 — NEW YORK CITY, USA 🇺🇸 Early morning in Manhattan. The woman walks along a busy downtown sidewalk while filming herself in selfie mode. Yellow taxis, tall buildings, steam rising from a street grate and realistic pedestrians fill the background. She holds a paper coffee cup and says: “New York mornings!” 0:02.5–0:05 — TRANSITION A yellow taxi passes extremely close in front of the camera, completely blocking the frame. As the taxi fills the screen, the scene transitions naturally. 0:05–0:07.5 — ISTANBUL, TURKEY 🇹🇷 The taxi clears to reveal a lively Istanbul street near the Bosphorus. The woman is wearing casual modest travel clothing and holds a warm Turkish simit. Ferries and historic architecture appear behind her. She takes a bite and says: “So good!” 0:07.5–0:10 — TRANSITION A large red-and-white Turkish flag carried by a passing pedestrian moves directly across the camera lens, completely covering the frame. 0:10–0:12.5 — DUBAI, UAE 🇦🇪 The flag clears to reveal a modern Dubai evening scene with illuminated skyscrapers, luxury architecture and busy pedestrian areas. The woman walks toward the camera holding a small cup of Arabic coffee and says with a smile: “Dubai at night hits different.” 0:12.5–0:15 — FINAL TRANSITION / ENDING She turns the camera toward the illuminated skyline, then brings her hand toward the lens until her palm completely covers the screen. Cut to black. Visual style: photorealistic live-action, authentic smartphone travel vlog, realistic skin texture, natural facial expressions, documentary realism, subtle handheld movement, cinematic but believable lighting, realistic crowds and environmental details. Audio: natural location sounds only — New York traffic and footsteps, Istanbul street ambience and ferry sounds, Dubai city ambience and distant conversations. No music, no subtitles, no artificial sound effects.
Prepare inputs and revise the prompt
- Check the subject and crop for the intended viewing format.
- Change one action or camera direction at a time and retain the other settings.
- These are revision and inspection suggestions; the source video is not evidence that the Studio reproduced these changes.