Christmas Photobooth Trend AI: Put Your Faces on the Last Christmas Strip

Recreate the reference video [Video 1] shot for shot: one continuous handheld phone shot that glides slowly along two printed black-and-white photo booth strips on a grey stone table beside a brass knob and a glass bauble, the same camera path, framing, timing and motion blur. Every printed photo shows two people side by side in a photo booth in front of a pale pleated curtain, a new pose in each photo. The ONLY change: the woman on the LEFT of every photo is now the person in [Image 1], and the woman on the RIGHT of every photo is now the person in [Image 2]. LEFT = the person in [Image 1], in EVERY photo: 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, in black and white like the strip. They wear the clothes from [Image 1]. NO fluffy fur coat and no white fur collar unless [Image 1] shows them. RIGHT = the person in [Image 2], in EVERY photo: 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, in black and white like the strip. They wear the clothes from [Image 2]. NO fur coat, no hair bun and no rings unless [Image 2] shows them. The same two real people in every photo of both strips, so their friends instantly recognize them. Never morph, never drift back to the faces of the two women in the video. Do not mix the two faces: [Image 1] is only LEFT, [Image 2] is only RIGHT. Both change: no one from the video stays, also in the small photos at the edges of the frame and in the blurred slide. The poses, second by second, one printed photo each, each with its white caption line exactly as in the video: 0-2 s, photo 1: LEFT touches a fingertip to the lips; RIGHT holds a fingertip at the chin and looks to the side. 2-4 s, photo 2: both hide the mouth and cheeks behind both hands, fingers spread, eyes peeking over them. 4-6 s, photo 3: both hold an open palm out toward the camera. 6-8.5 s, photo 4: LEFT makes a ring with finger and thumb around one eye; RIGHT rests a finger on the cheek. 8.5-9 s: the camera slides to the second strip. 9-11 s, photo 5: RIGHT cups a hand and whispers into LEFT's ear; LEFT looks up. 11-13 s, photo 6: heads together, RIGHT winks, both hands at the chin. 13-15 s, photo 7: together they make one heart with their hands; RIGHT sticks the tongue out with the eyes closed. The photos are still, printed black-and-white photos: the people inside them never move, only the camera moves. One head per person, on that person's own shoulders; hands with five fingers. A face never appears on hands or clothes. Exactly two people in each photo. No dialogue throughout the entire video. No background music. No extra people, no logos, no watermark, no new words.

Recreate the reference video [Video 1] shot for shot: one continuous handheld phone shot that glides slowly along two printed black-and-white photo booth strips on a grey stone table beside a brass knob and a glass bauble, the same camera path, framing, timing and motion blur. Every printed photo shows two people side by side in a photo booth in front of a pale pleated curtain, a new pose in each photo. The ONLY change: the woman on the LEFT of every photo is now the person in [Image 1], and the woman on the RIGHT of every photo is now the pet in [Image 2]. LEFT = the person in [Image 1], in EVERY photo: 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, in black and white like the strip. They wear the clothes from [Image 1]. NO fluffy fur coat and no white fur collar unless [Image 1] shows them. RIGHT = the pet in [Image 2], whole head and body, in EVERY photo: the same species and breed, head shape, muzzle, eyes, ears, fur length, markings and body shape as in [Image 2], in black and white like the strip, with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything. It sits upright beside the other one and does the poses with its front paws: paws with fur and claws, never human hands. The same person and the same pet in every photo of both strips, so they are instantly recognized. Never drift back to the faces of the two women in the video. Only one person in each photo: no woman from the video stays, also in the small photos at the edges of the frame and in the blurred slide. The poses, second by second, one printed photo each, each with its white caption line exactly as in the video: 0-2 s, photo 1: LEFT touches a fingertip to the lips; RIGHT holds a fingertip at the chin and looks to the side. 2-4 s, photo 2: both hide the mouth and cheeks behind both hands, fingers spread, eyes peeking over them. 4-6 s, photo 3: both hold an open palm out toward the camera. 6-8.5 s, photo 4: LEFT makes a ring with finger and thumb around one eye; RIGHT rests a finger on the cheek. 8.5-9 s: the camera slides to the second strip. 9-11 s, photo 5: RIGHT leans its muzzle to LEFT's ear; LEFT looks up. 11-13 s, photo 6: heads together, RIGHT winks, both hands at the chin. 13-15 s, photo 7: together they make one heart with their hands; RIGHT sticks the tongue out with the eyes closed. The photos are still, printed black-and-white photos: the people inside them never move, only the camera moves. One head per person or pet; the person has hands with five fingers, the pet has paws. Exactly one person and one pet in each photo. No dialogue throughout the entire video. No background music. No extra people or animals, no logos, no watermark, no new words.

Recreate the reference video [Video 1] shot for shot: one continuous handheld phone shot that glides slowly along two printed black-and-white photo booth strips on a grey stone table beside a brass knob and a glass bauble, the same camera path, framing, timing and motion blur. Every printed photo shows two people side by side in a photo booth in front of a pale pleated curtain, a new pose in each photo. The ONLY change: the woman on the LEFT of every photo is now the pet in [Image 1], and the woman on the RIGHT of every photo is now the pet in [Image 2]. LEFT = the pet in [Image 1], whole head and body, in EVERY photo: the same species and breed, head shape, muzzle, eyes, ears, fur length, markings and body shape as in [Image 1], in black and white like the strip, with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything. It sits upright beside the other one and does the poses with its front paws: paws with fur and claws, never human hands. RIGHT = the pet in [Image 2], whole head and body, in EVERY photo: the same species and breed, head shape, muzzle, eyes, ears, fur length, markings and body shape as in [Image 2], in black and white like the strip, with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything. It sits upright beside the other one and does the poses with its front paws: paws with fur and claws, never human hands. So their owner instantly recognizes both pets in every photo. Do not mix the two pets: [Image 1] is only LEFT, [Image 2] is only RIGHT. No people at all: no one from the video stays, also in the small photos at the edges of the frame and in the blurred slide. If an image shows a person, that person takes the place in the same way, with the exact face from the photo. The poses, second by second, one printed photo each, each with its white caption line exactly as in the video: 0-2 s, photo 1: LEFT touches a fingertip to the lips; RIGHT holds a fingertip at the chin and looks to the side. 2-4 s, photo 2: both hide the mouth and cheeks behind both hands, fingers spread, eyes peeking over them. 4-6 s, photo 3: both hold an open palm out toward the camera. 6-8.5 s, photo 4: LEFT makes a ring with finger and thumb around one eye; RIGHT rests a finger on the cheek. 8.5-9 s: the camera slides to the second strip. 9-11 s, photo 5: RIGHT cups a hand and whispers into LEFT's ear; LEFT looks up. 11-13 s, photo 6: heads together, RIGHT winks, both hands at the chin. 13-15 s, photo 7: together they make one heart with their hands; RIGHT sticks the tongue out with the eyes closed. The photos are still, printed black-and-white photos: the people inside them never move, only the camera moves. One head and one body per pet, two front paws each. No extra animals, no human hands, no clothes unless the photo shows them. No dialogue throughout the entire video. No background music. No logos, no watermark, no new words.