A woman casually records herself at a lively Japanese summer festival, unexpectedly encountering traditional performers carrying a decorated mikoshi shrine.
Create ultra-realistic spontaneous vertical iPhone footage inside a lively Japanese summer festival during a bright, sunny afternoon.
Use the provided reference image ONLY as the identity reference for the main woman. Keep her facial identity, hairstyle, skin tone, proportions, and overall appearance perfectly consistent throughout the video.
The footage must feel like a real friend casually recording her during a vacation. Natural handheld camera shake, imperfect framing, occasional autofocus hunting, realistic exposure adaptation in strong daylight, authentic smartphone dynamic range, and genuine environmental audio. No staged acting.
0–3s
The woman walks through a crowded Japanese summer festival street under a bright blue sky, casually eating colorful kakigori (Japanese shaved ice). Colorful paper decorations, traditional festival stalls, and people in summer yukata fill the background. She notices something approaching from behind the crowd and slows down curiously.
3–6s
The camera quickly shifts over her shoulder, revealing a large group of traditional Japanese festival performers approaching with a portable mikoshi shrine decorated with colorful ornaments. The crowd parts naturally as the performers chant and move forward together. She widens her eyes in genuine surprise and instinctively steps aside.
6–9s
One cheerful performer notices her and briefly offers her a small traditional festival fan while continuing with the parade. She accepts it with a surprised laugh, looks at the camera as if sharing an unexpected moment with her friend, then turns back toward the procession.
9–12s
The performers pass very close to the camera, creating a brief, chaotic view of moving shoulders, colorful costumes, and the decorated shrine. The camera operator instinctively steps backward to avoid the crowd. Sunlight flickers naturally across the frame as people move past.
12–15s
The camera finds the woman again. She waves the fan excitedly, laughs, and takes a few quick steps to follow the parade. A festival visitor carrying a large colorful balloon briefly blocks the camera before the recording cuts off naturally.
Visual style: Bright natural midday sunlight, blue summer sky, colorful Japanese matsuri decorations, realistic skin pores, natural facial expressions, authentic crowd movement, ordinary vacation clothing and traditional yukata in the background, handheld iPhone footage, spontaneous travel memories.
Audio: Natural crowd chatter, festival drums, performers chanting in the distance, footsteps, and the woman's genuine laughter. No background music, no artificial sound effects, no scripted dialogue.
Avoid: Cinematic camera movements, slow motion, commercial advertising aesthetics, beauty filters, overacting, artificial facial expressions, duplicated people, distorted hands, floating objects, inconsistent character identity, changing clothes, unnatural crowd physics, oversaturated colors, and AI-generated visual artifacts.
Includes a consistency lock: a trait the prompt asks the model to hold constant.