15-second photorealistic I2V video based strictly on the reference…

The prompt behind it

15-second photorealistic I2V video based strictly on the reference image. 9:16 vertical. ONE CONTINUOUS SHOT — NO CUTS. Preserve the same three students, positions, uniforms, faces, hairstyles, classroom, and the seated friend filming vertically in the foreground. The three students perform a cute, bright, cheerful and VERY tightly synchronized dance while looking toward the smartphone camera. CRITICAL SYNCHRONIZATION: All three perform EXACTLY the same choreography at EXACTLY the same time. The center student acts as the timing leader, while the left and right students match her timing perfectly with ZERO visible delay. Every step, hand gesture, arm movement, body sway and pose starts and finishes simultaneously. No individual improvisation and no random extra gestures. CHOREOGRAPHY: 0–5 sec: All three start simultaneously. Cute synchronized left-right steps with gentle body bounces and matching hand gestures near shoulder level. Steady synchronized tempo and natural cheerful smiles. 5–10 sec: Together, switch to playful synchronized left-right pointing gestures combined with simple side steps. Add small matching head tilts. All three remain perfectly synchronized and continue looking toward the camera. 10–13 sec: Switch simultaneously to cute synchronized hand waves and simple coordinated arm movements while continuing gentle side-to-side steps. 13–15 sec: All three perform one final cute movement, stop at EXACTLY the same moment, then finish in the SAME cheerful pose facing the camera and hold it naturally until the end. PERFORMANCE: Cute, lively and cheerful. Natural smiles and expressions. Simple school-friendly choreography. No spinning, jumping or complicated movements. Realistic balance, hands, arms, hair and clothing physics. FOREGROUND FRIEND: The seated friend remains seated throughout the entire 15 seconds and continuously records them with a vertically held smartphone. She never stands up or turns the camera away. Only subtle natural hand movement while filming. The smartphone never blocks the dancers. CAMERA: Mostly stable handheld smartphone footage. Very subtle realistic hand shake. One very slow, subtle push-in toward the three dancers during the performance. Keep all three dancers clearly visible. No sudden zoom, pan, angle change or focus shift. AUDIO: NO MUSIC. NO BACKGROUND MUSIC. NO SINGING. NO DIALOGUE. NO ARTIFICIAL SOUND EFFECTS. Only realistic classroom ambience, subtle footsteps, clothing movement, chair sounds and quiet natural background activity. Maintain stable faces, identities, uniforms and readable classroom text. Realistic Thai government junior-high-school classroom. Natural realistic lighting and shadows. Photorealistic motion and correct body physics. HIGHEST PRIORITY: Perfect synchronization of all three dancers. No delayed dancer. No independent choreography. No random gestures. No duplicated limbs or distorted hands.

Settings used

Length

≈ 10 seconds

Shape

Tall

Sound

With sound