Gangnam Style Dance AI: Put Your Face in the Viral Trio Reel

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the friend in the middle is now the person in [Image 1]. Use [Image 1] as adult Person A at center in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep Person A's face, hairstyle, outfit, body proportions and screen position consistent. [Image 1] replaces the woman in the middle with the wavy, shoulder-length dark-brown bob and bangs in the black leather jacket, in EVERY shot: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 1]. NO black leather jacket and no bob with bangs unless [Image 1] shows them. The same real person from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original woman's face. The friend on the left (black baseball cap, white turtleneck) and the friend on the right (long straight black hair, white lace camisole) stay exactly as in the video, with their own faces, also in their solo shots. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the friend in the middle is now the person in [Image 1], and the friend on the left is now the person in [Image 2]. Use [Image 1] as adult Person A at center, [Image 2] as adult Person B at screen-left, in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep each person's face, hairstyle, outfit, body proportions and screen position consistent; do not swap roles or merge identities. Person A: [Image 1] replaces the woman in the middle with the wavy, shoulder-length dark-brown bob and bangs in the black leather jacket, in EVERY shot: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 1]. NO black leather jacket and no bob with bangs unless [Image 1] shows them. Person B: [Image 2] replaces the woman on the left in the black baseball cap and the white turtleneck, in EVERY shot, also in the left solo: copy the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles). They wear the clothes from [Image 2]. NO black cap and no white turtleneck unless [Image 2] shows them. The same real people from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original women's faces. The friend on the right (long straight black hair, white lace camisole) stays exactly as in the video, with her own face, also in her solo shot. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.

Recreate the reference video [Video 1] shot for shot: the same wide handheld selfie video at sunset on a city sidewalk between glass towers, flags on tall poles, cars and a few people passing, the same arm's-length selfie camera, cuts, framing, timing and moves. The ONLY change: the three friends are now the people in [Image 1], [Image 2] and [Image 3]. Use [Image 1] as adult Person A at center, [Image 2] as adult Person B at screen-left, [Image 3] as adult Person C at screen-right, in [Video 1]. Follow the exact reference sequence: group, center close-up, right solo, left solo, center return. Keep each face, hairstyle, outfit and screen position; do not swap roles or merge identities. A: [Image 1] replaces the woman in the middle (dark-brown bob with bangs, black leather jacket) in EVERY shot: the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 1]. NO leather jacket, no bob unless [Image 1] shows them. B: [Image 2] replaces the woman on the left (black cap, white turtleneck) in EVERY shot: the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 2]. NO cap, no turtleneck unless [Image 2] shows them. C: [Image 3] replaces the woman on the right (long straight black hair, white lace camisole) in EVERY shot: the exact face from [Image 3] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), the clothes from [Image 3]. NO long black hair, no camisole unless [Image 3] shows them. The same real people from the first second to the last, so their friends recognize them at once. Never morph, never drift back to the original women's faces. All three change: no one from the video stays, also in the solos. Shots, matching the reference second by second: 0-2 s: group selfie, the three side by side, smiling and singing along. 2-4.9 s: the middle friend alone, sings to the lens, points at it, sways. 4.9-8.4 s: the right friend alone by the road, a hair flip and a wave. 8.4-12.3 s: the left friend alone on a side street with orange cones, hands on the head, then a finger heart. 12.3-15 s: the middle friend again, close to the lens, sings and dances. One head per person, on that person's own shoulders. Never a fourth friend; the people passing far behind stay small strangers. No text, no logos, no watermark.