Coffee Making AI Video: Put Anyone, Any Pet or Any Character in the Kitchen

Recreate the reference video [Video 1] shot for shot: the same home kitchen with wooden cabinets and a ceiling vent, the same speckled stone counter with the spilled coffee grounds, the red mug, the steel kettle, the jar of instant coffee with the red label and the steel milk jug, the same fixed camera at counter height, the same framing, timing and comedy. One continuous take, no cuts. The ONLY change: [Image 1] replaces the tall knight in black armor who stands behind the counter, and [Image 2] replaces the small kitten in armor who sits on the counter at the left. Each photo can show a person, a pet, a toy, a cartoon or game character, a figure or an object: whoever or whatever it shows takes that place with its WHOLE body, not only the head. Use [Video 1] only for the place, the camera, the timing and the moves: nothing of the knight or the kitten stays in any frame. The one in the knight's place = [Image 1], from head to feet in EVERY frame. If [Image 1] shows a person: copy the exact face - 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 - and the clothes from [Image 1]: a real grown adult at their real size behind the counter, with no armor, no helmet and no metal gloves. If it shows anything else (a pet, a toy, a cartoon or game character, a figure or an object): that exact subject, with its own shape, proportions, colors, surface, material and art style, standing upright behind the counter as tall as the knight; its own whole body, whatever it has (head, torso, arms, paws, legs, feet or a base), replaces ALL of the knight, with no armor, no helmet and no metal gloves unless [Image 1] shows them; it holds the spoon and the mug with its own paws or limbs, or nudges them when it has none; a cat stays a cat, a plush stays soft, a blocky figure stays blocky. Never drift back to the knight of [Video 1]: nothing of the knight stays in any frame. The one in the kitten's place = [Image 2], in EVERY frame, copied from [Image 2] in the same way. A pet, a toy, a character or a small object sits upright on the counter at the left at the kitten's small size, with its own face, fur or surface, colors and style, and no armor and no bow unless [Image 2] shows them. A person stands behind the counter at the left at their real size, chest up in view, leaning on the counter, with the exact face from [Image 2] and the clothes from [Image 2]. Never drift back to the kitten of [Video 1]: not its face, its fur, its bow or its armor unless [Image 2] shows them. When a photo shows only a head or an upper body, add the rest so it matches. Both make the moves of the knight and the kitten in the way their own bodies allow. The same two in every frame, from the first second to the last, so their friends instantly recognize them. Never morph, never blend the two: [Image 1] is only the one in the knight's place, [Image 2] is only the one in the kitten's place. The action, matching [Video 1] second by second: 00:00-00:03: a hand from the left edge of the frame pours hot water from the steel kettle into the red mug, the one in the knight's place stands behind the counter with a spoon, coffee grounds lie spilled on the counter, the one in the kitten's place watches. 00:03-00:05: the one in the knight's place spoons instant coffee from the jar into the red mug and spills more grounds on the counter. 00:05-00:09: it leans over the counter, wipes at the spilled coffee and reaches across for the jar, coming closer to the camera. 00:09-00:10.5: it lifts the red mug. 00:10.5-00:12: the steel jug from the left pours milk, the milk splashes over the counter and spreads in a big white puddle. 00:12-00:15: the one in the knight's place holds the red mug and looks at the mess, the one in the kitten's place sits still and watches. Real live-action footage, natural motion. Anatomy rules: one head each, on its own body, never merged. A pet keeps animal paws, never human hands. The only hand that is not one of the two is the hand at the left edge that pours from the kettle, as in [Video 1]. No extra people or animals. No captions, no watermark, no other text.

Recreate the reference video [Video 1] shot for shot: the same home kitchen with wooden cabinets and a ceiling vent, the same speckled stone counter with the spilled coffee grounds, the red mug, the steel kettle, the jar of instant coffee with the red label and the steel milk jug, the same fixed camera at counter height, the same framing, timing and comedy. One continuous take, no cuts. The ONLY change: [Image 1] replaces the tall knight in black armor who stands behind the counter. The photo can show a person, a pet, a toy, a cartoon or game character, a figure or an object: whoever or whatever it shows takes the knight's place with its WHOLE body, not only the head. The small kitten in armor on the counter at the left stays exactly as in [Video 1] in every frame, and it never takes the look of [Image 1]. The one in the knight's place = [Image 1], from head to feet in EVERY frame. If [Image 1] shows a person: copy the exact face - 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 - and the clothes from [Image 1]: a real grown adult at their real size behind the counter, with no armor, no helmet and no metal gloves. If it shows anything else (a pet, a toy, a cartoon or game character, a figure or an object): that exact subject, with its own shape, proportions, colors, surface, material and art style, standing upright behind the counter as tall as the knight; its own whole body, whatever it has (head, torso, arms, paws, legs, feet or a base), replaces ALL of the knight, with no armor, no helmet and no metal gloves unless [Image 1] shows them; it holds the spoon and the mug with its own paws or limbs, or nudges them when it has none; a cat stays a cat, a plush stays soft, a blocky figure stays blocky. Never drift back to the knight of [Video 1]: nothing of the knight stays in any frame. When the photo shows only a head or an upper body, add the rest so it matches. It makes the knight's moves in the way its own body allows. The same one in every frame, from the first second to the last, so their friends instantly recognize it. Never morph. The action, matching [Video 1] second by second: 00:00-00:03: a hand from the left edge of the frame pours hot water from the steel kettle into the red mug, the one in the knight's place stands behind the counter with a spoon, coffee grounds lie spilled on the counter, the kitten watches. 00:03-00:05: the one in the knight's place spoons instant coffee from the jar into the red mug and spills more grounds on the counter. 00:05-00:09: it leans over the counter, wipes at the spilled coffee and reaches across for the jar, coming closer to the camera. 00:09-00:10.5: it lifts the red mug. 00:10.5-00:12: the steel jug from the left pours milk, the milk splashes over the counter and spreads in a big white puddle. 00:12-00:15: the one in the knight's place holds the red mug and looks at the mess, the kitten sits still and watches. Real live-action footage, natural motion. Anatomy rules: one head each, on its own body, never merged. A pet keeps animal paws, never human hands. The only hand that is not one of the two is the hand at the left edge that pours from the kettle, as in [Video 1]. No extra people or animals. No captions, no watermark, no other text.

Recreate the reference video [Video 1] shot for shot: the same kitchen with sage-green cabinets, a white tiled wall and an open doorway, the same steel counter with scattered coffee grounds, the black kettle, the white mug and the milk bottle, the same fixed camera at counter height, the same framing, timing and comedy. The ONLY change: the dog on the LEFT is now the person in [Image 1], a real grown adult. The dog on the RIGHT stays exactly as in [Video 1]. The person = the person in [Image 1], in EVERY frame: 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), so their friends recognize them at once. A HUMAN head and a human body: never a dog head, no dog ears, no fur, no muzzle, no tail. They wear their own clothes from [Image 1]. The same real person from the first second to the last, also when they hide the face behind their hands at the end: never morph, never drift back to the left dog of [Video 1]. If [Image 1] shows an animal, it stays that animal with its own face, fur and markings, not a person. Size: the person has a grown adult's real size, not the dog's size. They stand behind the counter on the far side, like an adult at a kitchen island, and lean forward with both forearms on the steel counter, seen from the chest up, so the face is where the left dog's head was and the head is never cut off by the top of the frame. Adult shoulders, arms and hands, clearly bigger than the small dog next to them: never shrunk to the dog's size, never a child's body. The dog on the right = the same dog as in [Video 1] in every frame, unchanged, at its own small size. It never takes the face, the hair or the clothes of [Image 1]. The action, matching [Video 1] second by second: 00:00-00:05: the person holds the black kettle in both hands and pours hot coffee into the white mug, the dog on the right watches and lifts a paw toward the mug. 00:05-00:09.5: the dog on the right reaches over the mug and stirs it, the person watches closely. 00:09.5-00:12: the person's hand knocks over the milk bottle at the front left, milk pours out and spreads in a white puddle across the counter, both freeze. 00:12-00:14: the person pulls back a little and stares into the camera with an innocent face, the dog with a paw on the mug. 00:14-00:15: the person covers their face with both hands, the dog keeps the innocent stare. Anatomy rules: exactly one person and one dog side by side, each with one head on its own body, never merged. The person has two human hands with five fingers each; the dog has animal paws, never human hands. No extra people, no extra animals. Real live-action footage, natural motion, real skin. No text, no captions, no logos, no watermark: the milk bottle label is plain, with no letters.

Recreate the reference video [Video 1] shot for shot: the same kitchen with sage-green cabinets, a white tiled wall and an open doorway, the same steel counter with scattered coffee grounds, the black kettle, the white mug and the milk bottle, the same fixed camera at counter height, the same framing, timing and comedy. The ONLY change: the dog on the LEFT is now the person in [Image 1], and the dog on the RIGHT is now the person in [Image 2], two real grown adults. Both change: no dog from the video stays, also when a person turns the head or hides the face. Person 1 = the person in [Image 1], in EVERY frame: on the left, the one who pours the coffee. 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). Person 2 = the person in [Image 2], in EVERY frame: on the right, the one who stirs. Copy the exact face from [Image 2] in the same way. Never blend their faces; each face stays the same from the first frame to the last, so their friends recognize them at once. Both have HUMAN heads and human bodies: never a dog head, no dog ears, no fur, no muzzle, no tail. Each wears their own clothes from their photo. Never drift back to the dogs of the original video. If an image shows an animal, that one is that animal with its own face, fur and markings, not a person. Size: both have a grown adult's real size, not the dogs' size. They stand side by side behind the counter on the far side, like two adults at a kitchen island, and lean forward with their forearms on the steel counter, shoulder to shoulder, seen from the chest up. Both faces stay fully in the frame, never cut off by the top or the sides: the camera may sit a little further back than in [Video 1] to fit two adults. Adult shoulders, arms and hands: never shrunk to the dogs' size, never children's bodies. The action, matching [Video 1] second by second: 00:00-00:05: person 1 holds the black kettle in both hands and pours hot coffee into the white mug, person 2 watches and lifts a hand toward the mug. 00:05-00:09.5: person 2 reaches over the mug and stirs it, person 1 watches closely. 00:09.5-00:12: person 1's hand knocks over the milk bottle at the front left, milk pours out and spreads in a white puddle across the counter, both freeze. 00:12-00:14: both pull back a little and stare into the camera with innocent faces, person 2 with a hand on the mug. 00:14-00:15: person 1 covers the face with both hands, person 2 keeps the innocent stare. Anatomy rules: exactly two people side by side, each with one head on their own body, never merged, two human hands with five fingers each. No animals, no extra people. Real live-action footage, natural motion, real skin. No text, no captions, no logos, no watermark: the milk bottle label is plain, with no letters.

Recreate the reference video [Video 1] shot for shot: the same kitchen with sage-green cabinets, a white tiled wall and an open doorway, the same steel counter with scattered coffee grounds, the black kettle, the white mug and the milk bottle, the same fixed camera at counter height, the same framing, timing and comedy. The ONLY change: the dog on the LEFT is now the pet in [Image 1]. The dog on the RIGHT stays exactly as in [Video 1]. The left pet = the pet in [Image 1], 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. Whether [Image 1] shows a dog, a cat or another animal, it stays that animal, sitting upright at the counter. The same pet in every frame, from the first second to the last, so its owner instantly recognizes it, also when it hides its face behind its paws. Never drift back to the left dog of [Video 1]: not the face, the ears or the coat of the dog on the left in the video unless [Image 1] shows them. The dog on the right = the same dog as in [Video 1] in every frame, unchanged. It never takes the face or the fur of [Image 1]. The white mug keeps its shape, but its printed picture is now a simple cute drawing of the pet from [Image 1], on the side that faces the camera, in every frame. The action, matching [Video 1] second by second: 00:00-00:05: the left pet holds the black kettle in its front paws and pours hot coffee into the white mug, the right dog watches and lifts a paw toward the mug. 00:05-00:09.5: the right dog reaches over the mug and stirs it, the left pet watches closely. 00:09.5-00:12: the milk bottle at the front left tips over under the left pet's paw, milk pours out and spreads in a white puddle across the counter, both freeze. 00:12-00:14: both sit up straight and stare into the camera with innocent faces, the right dog with a paw on the mug. 00:14-00:15: the left pet covers its face with both front paws, the right dog keeps the innocent stare. Real live-action footage, natural animal motion, real fur. Anatomy rules: exactly two animals side by side, each with one head on its own body, never merged. Animal paws, never human hands. No people, no extra animals. No text, no captions, no logos, no watermark: the milk bottle label is plain, with no letters.

Recreate the reference video [Video 1] shot for shot: the same kitchen with sage-green cabinets, a white tiled wall and an open doorway, the same steel counter with scattered coffee grounds, the black kettle, the white mug and the milk bottle, the same fixed camera at counter height, the same framing, timing and comedy. The ONLY change: the dog on the LEFT is now the pet in [Image 1], and the dog on the RIGHT is now the pet in [Image 2]. Both change: no dog from the video stays, also when a pet turns its head or hides its face. The left pet = the pet in [Image 1], in EVERY frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings as in [Image 1]. Never drift back to the left dog of [Video 1]: not the face, the ears or the coat of the dog on the left in the video unless [Image 1] shows them. The right pet = the pet in [Image 2], in EVERY frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings as in [Image 2]. Never drift back to the right dog of [Video 1]: not the face, the ears or the coat of the dog on the right in the video unless [Image 2] shows them. Each pet keeps the natural body volume and proportions of its own animal: never flattened, squashed, stretched or merged with anything. Whether a photo shows a dog, a cat or another animal, it stays that animal, sitting upright at the counter. Never blend the two pets: each keeps its own face and fur, from the first second to the last, so their owner instantly recognizes both. The white mug keeps its shape, but its printed picture is now a simple cute drawing of the pet from [Image 1], on the side that faces the camera, in every frame. The action, matching [Video 1] second by second: 00:00-00:05: the left pet holds the black kettle in its front paws and pours hot coffee into the white mug, the right pet watches and lifts a paw toward the mug. 00:05-00:09.5: the right pet reaches over the mug and stirs it, the left pet watches closely. 00:09.5-00:12: the milk bottle at the front left tips over under the left pet's paw, milk pours out and spreads in a white puddle across the counter, both freeze. 00:12-00:14: both sit up straight and stare into the camera with innocent faces, the right pet with a paw on the mug. 00:14-00:15: the left pet covers its face with both front paws, the right pet keeps the innocent stare. Real live-action footage, natural animal motion, real fur. Anatomy rules: exactly two animals side by side, each with one head on its own body, never merged. Animal paws, never human hands. No people, no extra animals. No text, no captions, no logos, no watermark: the milk bottle label is plain, with no letters.