Snowman Dance AI: Do the Viral Sia Couple Dance From Two Photos

Replace the two dancers in [Video 1] with the people in the photos: [Image 1] takes the place of the dancer on the left at the start of [Video 1] and [Image 2] the dancer on the right. Keep each person's face, hair, skin tone, age and build from their own photo, dressed in the outfit of the dancer they replace in [Video 1]. They do exactly the same couple dance as in [Video 1], every spin, swing, turn and lift landing on the same beat of the music. Keep the room, the light, the camera, the framing and the timing of [Video 1] exactly as they are. Recreate the reference video [Video 1] shot for shot, as one continuous take: the same living room with the fireplace, the lit Christmas tree and the dark wood floor, the same fixed camera, framing, timing and moves. The ONLY change: the woman on the left who jumps onto his back at the end is now the person in [Image 1], and the man on the right who catches and carries her is now the person in [Image 2]. Both wear the reel's red plaid pajama trousers, black tops and white socks, never the clothes from the photos. Dancer on the left = 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. NO long blond hair unless [Image 1] shows it. Dancer on the right = 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. NO bleached curly hair, no goatee and no silver chain unless [Image 2] shows them. The same real people in every frame, so their friends instantly recognize them, also in the spins, in the lift and while they laugh. Never drift back to the original dancers' faces, never add or remove facial hair, never mix the two faces. 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: 0-2 s: they start side by side facing the camera with their hands behind their backs, bobbing to the beat. 2-3 s: they turn to face each other and take hands. 3-5 s: arms up high, the dancer on the left spins under the other's raised arm. 5-8 s: they swing and twirl around each other, hand in hand. 8-9.5 s: one more twirl, then the dancer on the left turns away. 9.5-12 s: the dancer on the left jumps up, the other catches them, swings them onto their back and carries them piggyback, both laughing at the camera. If an image shows an animal, that dancer is that animal standing upright, with its own face, fur and markings, not a person. Anatomy rules: one head per dancer, on its own shoulders. Exactly two dancers. Natural balance, believable jumps and landings. No dialogue throughout the entire video. No background music. No extra people, extra limbs, text, logos or watermark.

Replace the two dancers in [Video 1] with the pets in the photos: [Image 1] takes the place of the dancer on the left at the start of [Video 1] and [Image 2] the dancer on the right. They do exactly the same couple dance as in [Video 1], every spin, swing, turn and lift landing on the same beat of the music. Keep the room, the light, the camera, the framing and the timing of [Video 1] exactly as they are. Recreate the reference video [Video 1] shot for shot, as one continuous take: the same living room with the fireplace, the lit Christmas tree and the dark wood floor, the same fixed camera, framing, timing and moves. The ONLY change: the woman on the left who jumps onto his back at the end is now the pet in [Image 1], and the man on the right who catches and carries her is now the pet in [Image 2]. Both pets stand upright on their hind legs like people the whole time and wear small red plaid pajama trousers like the dancers in the video. Pet on the left = the pet in [Image 1], whole body, in EVERY frame: the same species and breed, head shape, muzzle, eyes, ears, fur colors, fur length, markings and body shape as in [Image 1], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything, so its owner instantly recognizes it. Pet on the right = the pet in [Image 2], whole body, in EVERY frame: the same species and breed, head shape, muzzle, eyes, ears, fur colors, fur length, markings and body shape as in [Image 2], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything, so its owner instantly recognizes it. Never mix the two pets: each keeps its own coat, also when both are the same kind of animal. Both change: no person from the video stays, no human face. If an image shows a person, that dancer is that person with the exact face, hair and skin tone from that image, in the same pajamas. The dance, matching the reference second by second, on the beat: 0-2 s: the two pets stand side by side facing the camera with their front paws behind their backs, bobbing to the beat. 2-3 s: they turn to face each other and hold paws. 3-5 s: front legs up high, the pet on the left spins under the raised paw of the pet on the right. 5-8 s: they swing and twirl around each other, paw in paw. 8-9.5 s: one more twirl, then the pet on the left turns away. 9.5-12 s: the pet on the left jumps up, the pet on the right catches it and swings it round onto its back and carries it piggyback, both happy, looking at the camera. Anatomy rules: one head and one tail per pet, two hind legs and two front legs, no human hands. Natural balance, believable jumps and landings. No dialogue throughout the entire video. No background music. No extra animals, no text, logos or watermark.