Island Boy Meme AI: Put Your Friends in the Pool

Recreate the reference video [Video 1] shot for shot: the same small tropical garden pool with the light stone edge, the banana plants and palms behind it, the clear blue water, the daylight, the same handheld phone camera with its subtle horizontal pan, framing, timing and gestures. The ONLY change: the man sitting on the LEFT pool edge is now the person in [Image 1], and the man standing waist-deep in the pool on the RIGHT, the singer, is now the person in [Image 2]. STRICT TWO-PERSON IDENTITY REPLACEMENT: replace both original men. [Image 1] is only the one on the edge, [Image 2] is only the singer. Never swap identities, blend faces or retain original faces. The one on the edge = 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 from [Image 1]. NO long wavy dark hair, no full dark beard, no grey t-shirt and no brown trousers unless [Image 1] shows them. The singer = 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 from [Image 2]. NO black leather jacket, no black shirt, no grey goatee and no slicked-back grey hair unless [Image 2] shows them. STRICT IDENTITY CONSISTENCY: the same real people in every frame, first to last, also in head turns and gestures. Never morph, never drift back to the original men's faces. Both change: no one from the video stays. EXACT 14-SECOND MOTION REPLICATION: [Video 1] is the ONLY source of motion, timing, expressions, gestures and camera movement. 0-2 s: the one on the edge sits on the LEFT edge, leaning slightly forward, looking toward the singer. The singer bends forward in the water, looking down. 2-3.5 s: the singer straightens up and turns toward the one on the edge. 3.5-6 s: the singer sings with natural mouth movements and small hand gestures. The one on the edge watches and listens. 6-8 s: the singer brings both hands together near the chest, the same clasping and emphasizing gestures as the reference. 8-10 s: the singer smiles, more expressive, and opens the arms outward. 10-14 s: expressive hand gestures and subtle body moves, the gaze alternating between the one on the edge and the camera, until the end. The one on the edge stays seated. NATURAL WATER INTERACTION: preserve the original water level, reflections, ripples, splashes and water occlusion. The singer stands waist-deep, fully dressed. Anatomy rules: one head per character, on its own body. Exactly two characters, no extra people. Do not import the photos' backgrounds. No dialogue throughout the entire video. No background music. No subtitles, captions, text, logos or watermarks.

Recreate the reference video [Video 1] shot for shot: the same small tropical garden pool with the light stone edge, the banana plants and palms behind it, the clear blue water, the daylight, the same handheld phone camera with its subtle horizontal pan, framing, timing and gestures. The ONLY change: the man standing waist-deep in the pool on the RIGHT, the singer, is now the person in [Image 1], and the man sitting on the LEFT pool edge is now a new, made-up adult man. The singer = 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 from [Image 1]. NO black leather jacket, no black shirt, no grey goatee and no slicked-back grey hair unless [Image 1] shows them. The one on the edge = a completely original, fictional adult man with a natural, realistic appearance: short light-brown hair, clean-shaven, a plain white t-shirt and blue jeans. Not the original man's face or likeness: NO long wavy dark hair, no full dark beard, no grey t-shirt. STRICT IDENTITY CONSISTENCY: the singer is the same real person in every frame, first to last, also in head turns, expressions and gestures. Never morph, never drift back to the original man's face. Never blend the two identities or duplicate the singer. EXACT 14-SECOND MOTION REPLICATION: [Video 1] is the ONLY source of motion, timing, expressions, gestures and camera movement. 0-2 s: the one on the edge sits on the LEFT edge, leaning slightly forward, looking toward the singer. The singer bends forward in the water, looking down. 2-3.5 s: the singer straightens up and turns toward the one on the edge. 3.5-6 s: the singer sings with natural mouth movements and small hand gestures. The one on the edge watches and listens. 6-8 s: the singer brings both hands together near the chest, the same clasping and emphasizing gestures as the reference. 8-10 s: the singer smiles, more expressive, and opens the arms outward. 10-14 s: expressive hand gestures and subtle body moves, the gaze alternating between the one on the edge and the camera, until the end. The one on the edge stays seated. NATURAL WATER INTERACTION: preserve the original water level, reflections, ripples, splashes and water occlusion. The singer stands waist-deep, fully dressed. Anatomy rules: one head per character, on its own body. Exactly two characters, no extra people. Do not import the photos' backgrounds. No dialogue throughout the entire video. No background music. No subtitles, captions, text, logos or watermarks.

Recreate the reference video [Video 1] shot for shot: the same small tropical garden pool with the light stone edge, the banana plants and palms behind it, the clear blue water, the daylight, the same handheld phone camera with its subtle horizontal pan, framing, timing and gestures. The ONLY change: the man sitting on the LEFT pool edge is now the pet in [Image 1], and the man standing waist-deep in the pool on the RIGHT, the singer, is now the person in [Image 2]. The one on the edge = the pet in [Image 1], whole body, in EVERY frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings 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 recognizes it at once. It sits on the stone edge like a real animal, front paws near the water, and turns its head to the singer and to the camera on the man's beats. No clothes, no human hands, never upright, no long dark hair, no beard. The singer = 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 from [Image 2]. NO black leather jacket, no black shirt, no grey goatee and no slicked-back grey hair unless [Image 2] shows them. STRICT IDENTITY CONSISTENCY: the same pet and the same real person in every frame, from the first second to the last. Never morph, never drift back to the original men. Both change: no one from the video stays. EXACT 14-SECOND MOTION REPLICATION: [Video 1] is the ONLY source of motion, timing, expressions, gestures and camera movement. 0-2 s: the one on the edge sits on the LEFT edge, leaning slightly forward, looking toward the singer. The singer bends forward in the water, looking down. 2-3.5 s: the singer straightens up and turns toward the one on the edge. 3.5-6 s: the singer sings with natural mouth movements and small hand gestures. The one on the edge watches and listens. 6-8 s: the singer brings both hands together near the chest, the same clasping and emphasizing gestures as the reference. 8-10 s: the singer smiles, more expressive, and opens the arms outward. 10-14 s: expressive hand gestures and subtle body moves, the gaze alternating between the one on the edge and the camera, until the end. The one on the edge stays seated. NATURAL WATER INTERACTION: preserve the original water level, reflections, ripples, splashes and water occlusion. The singer stands waist-deep, fully dressed. Anatomy rules: one head per character, on its own body. Exactly two characters, no extra people. Do not import the photos' backgrounds. No dialogue throughout the entire video. No background music. No subtitles, captions, text, logos or watermarks.

Recreate the reference video [Video 1] shot for shot: the same small tropical garden pool with the light stone edge, the banana plants and palms behind it, the clear blue water, the daylight, the same handheld phone camera with its subtle horizontal pan, framing, timing and gestures. The ONLY change: the man sitting on the LEFT pool edge is now the pet in [Image 1], and the man standing waist-deep in the pool on the RIGHT, the singer, is now a new, made-up adult man. The one on the edge = the pet in [Image 1], whole body, in EVERY frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings 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 recognizes it at once. It sits on the stone edge like a real animal, front paws near the water, and turns its head to the singer and to the camera on the man's beats. No clothes, no human hands, never upright, no long dark hair, no beard. The singer = a completely original, fictional adult man with a natural, realistic appearance: short dark-brown hair, clean-shaven, a light blue button-up shirt and dark trousers. Not the original man's face or likeness: NO black leather jacket, no grey goatee, no slicked-back grey hair. STRICT IDENTITY CONSISTENCY: the same pet in every frame, from the first second to the last. Never drift back to the original men. No one from the video stays. EXACT 14-SECOND MOTION REPLICATION: [Video 1] is the ONLY source of motion, timing, expressions, gestures and camera movement. 0-2 s: the one on the edge sits on the LEFT edge, leaning slightly forward, looking toward the singer. The singer bends forward in the water, looking down. 2-3.5 s: the singer straightens up and turns toward the one on the edge. 3.5-6 s: the singer sings with natural mouth movements and small hand gestures. The one on the edge watches and listens. 6-8 s: the singer brings both hands together near the chest, the same clasping and emphasizing gestures as the reference. 8-10 s: the singer smiles, more expressive, and opens the arms outward. 10-14 s: expressive hand gestures and subtle body moves, the gaze alternating between the one on the edge and the camera, until the end. The one on the edge stays seated. NATURAL WATER INTERACTION: preserve the original water level, reflections, ripples, splashes and water occlusion. The singer stands waist-deep, fully dressed. Anatomy rules: one head per character, on its own body. Exactly two characters, no extra people. Do not import the photos' backgrounds. No dialogue throughout the entire video. No background music. No subtitles, captions, text, logos or watermarks.