Toc Toc Dance AI: Make the Viral Jean Phil Dance From One Photo

Use the reference image as the sole character identity reference and the reference video as the motion reference. Animate exactly one adult dancer, in the place from the reference image. Preserve the person's recognizable face, hairstyle, skin tone, body proportions, outfit, shoes, and accessories throughout the video. Follow the reference dancer's movement order and timing, including the rhythmic one-foot hops, raised bent leg, fist-knocking gestures, and any turns visible in the clip. Do not invent additional moves. Keep the entire body visible from head to shoes, with enough space around both hands and feet. Follow the reference framing and camera movement. Maintain natural balance, believable landings, stable ground contact, and consistent shadows. Keep the face recognizable during turns. No extra dancers, duplicate bodies, extra limbs, fused fingers, outfit changes, new camera cuts, text, or watermark. Use a vertical 9:16 reference and output when supported. No big platinum wig, no round gold glasses, no goatee, no white suit and no white shoes unless the reference image shows them.

Recreate the reference video [Video 1] shot for shot: the same bright living room with the light grey stone floor, the white walls, the grey slatted wall panel, the TV and the dried pampas grass, the same fixed phone camera, framing, timing and dance moves. The ONLY change: the man in black with the big yellow boots who starts the dance is now the person in [Image 1], and the woman in the snake-print top and brown flared trousers who skips in and dances beside him is now the person in [Image 2]. Dancer 1 = the person in [Image 1], in EVERY frame: copy the exact face from [Image 1] - 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 exactly as in the photo. They wear the clothes and shoes from [Image 1]. NO big yellow boots and no all-black outfit unless [Image 1] shows them. Dancer 2 = the person in [Image 2], in EVERY frame: copy the exact face from [Image 2] - 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 exactly as in the photo. They wear the clothes and shoes from [Image 2]. NO snake-print top, no brown flared trousers and no hair band unless [Image 2] shows them. The same real people in every frame, from the first second to the last, so their friends instantly recognize them, also when they swap places and turn. Never morph, never drift back to the original dancers' faces, never add or remove facial hair. Do not mix the two faces: [Image 1] is only dancer 1, [Image 2] is only dancer 2. Both change: no one from the video stays, also when only the back of a head shows. The dance, matching the reference second by second, on the beat: the rhythmic one-foot hops, raised bent leg, fist-knocking gestures, and any turns visible in the clip. Do not invent additional moves. 0-1.5 s: dancer 1 hops toward the camera alone, one knee raised high, arms loose. 1.5-4 s: dancer 2 skips in from behind and both dance side by side, swapping front and back. 4-5.5 s: dancer 1 dances in front with the arms spread, dancer 2 behind. 5.5-7.5 s: dancer 2 comes to the front with high knee lifts, dancer 1 behind. 7.5-11 s: both dance side by side and swap places on the beat until the end. Anatomy rules: one head per person, on that person's own shoulders. A face never appears on knees, legs, hands or clothes. Exactly two people. Natural balance, believable landings, stable ground contact. No extra dancers, duplicate bodies, extra limbs, fused fingers, text, logos or watermark.