This AI cartoon looks like Pixar tried to sell a $1,999 gaming chair with a toilet built in.
Seedance 2.5 on @makeugc
Prompt
15-second horizontal 16:9 cinematic 3D animated comedy. Two adult characters, an extravagant gaming toilet-chair, a brief domestic conversation and a final price-tag reveal.
Natural movement, conversational English dialogue and tight comedic timing. No rushed speech, prolonged pauses, slow motion or speed ramps.
REFERENCES AND PRIORITY
Image 1 - MAN:
Use the supplied male character reference for his exact identity, face, heavyset body shape, balding crown, messy brown side hair, black rectangular glasses, facial stubble, blue polo shirt, brown trousers and dark sneakers.
Image 2 - WOMAN:
Use the supplied female character reference for her exact identity, face, curvy body shape, freckles, copper-red hair in a loose half-up bun, black glasses, hoop earrings, necklace, fitted red button-front top, ripped blue jeans with rolled cuffs and pale sneakers.
Image 3 - ROOM AND INITIAL CHAIR ORIENTATION:
Use the newest stylized 3D gaming-room image, where the chair is already shown FROM BEHIND and faces the television.
This reference defines the room layout, opening composition, lighting, furniture positions and the chair's orientation relative to the television.
Image 4 - CHAIR DESIGN:
Use the isolated chair on a neutral gray background with the raised overhead lamp.
This reference defines the chair's construction, leather panels, integrated toilet opening, footrest, base, controls, trays, water tank and tall lamp support.
Its frontal product-view camera angle does NOT define the video camera angle or the chair's orientation inside the room.
Do not copy its neutral background into the video.
Apply Image 4's chair design in Image 3's room and orientation. Image 3 determines where the chair faces. Image 4 supplies object details, not scene blocking.
The controller shown on the reference tray is already in the man's hands at the beginning of the video. Leave that tray empty. Add the physical price tag described below.
VISUAL STYLE
Match the polished cinematic 3D animation look of Image 3. Appealing rounded silhouettes, expressive eyes, sculpted faces and nuanced facial acting. Preserve the recognizable identities and body proportions of Images 1 and 2 while harmonizing them with the room's animation style.
Soft skin shading, subtle subsurface scattering, delicate freckles, carefully groomed hair, tactile leather, detailed fabric and convincing glass and metal.
Rich controlled colors, warm golden practical lights, cool blue gaming-room accents, soft global illumination and gentle depth of field.
Believable weight and restrained expressive exaggeration. No live-action characters mixed into an animated room. No studio names or studio logos.
INITIAL POSITION
From the FIRST FRAME, the man is already seated in the chair facing the television, exactly following the orientation shown in Image 3.
His chest, knees and the extended footrest point toward the television. The exterior rear surface of the backrest faces the opening camera.
The opening camera sees the back of the chair and the back of his head, with the television beyond him.
Do not animate a turn. Do not begin with the chair facing the camera. The chair remains stationary throughout the video.
CHARACTERS
MAN:
A heavyset middle-aged man with a round belly, broad cheeks, balding crown, messy brown side hair, black rectangular glasses and short facial stubble.
Preserve his blue polo, brown trousers and dark athletic shoes. His clothing folds naturally over his seated body, and the cushions compress under his weight.
He holds one white-and-black controller with both hands above his lap. His feet rest on the footrest. He is fully dressed and preparing to start the game.
Initially comfortable and pleased with the setup, he becomes sheepish when the woman mentions his paycheck. His smile fades, his eyebrows rise and he tries an unconvincing reassuring smile.
WOMAN:
Preserve the adult woman from Image 2, including her red hair, glasses, freckles, jewelry, red ribbed button-front top, ripped jeans and pale sneakers.
She enters with a practical question about their household money. Her tone is composed and expectant. His hesitation makes her mildly suspicious.
Natural gestures, no shouting or exaggerated anger.
ENVIRONMENT
Reproduce Image 3's stylized room: dark television wall, large screen, low black media cabinet, upright white console, soundbar, warmly illuminated collectible shelves, trailing plants, blue LED strips, wood flooring, plush gray rug, pale curtains and charcoal sofa.
Preserve the black door on the left wall. It opens into a softly lit hallway and stays clear of the woman's route.
The sofa's cushions are slightly compressed and worn, without changing its design or position.
The television retains the colorful GTA VI start-screen artwork visible in Image 3. The man is ready to start the game, not already playing active gameplay. The screen stays unchanged during the conversation.
CHAIR DETAILS
Use Image 4's black stitched leather chair, padded armrests, integrated toilet seat, extended footrest, circular blue-lit base, attached trays and transparent blue-lit water tank.
Preserve the tall curved support and raised warm circular lamp. Maintain generous clearance above the man's head. Do not lower the lamp or shorten its support.
All directions below refer to the seated man's perspective as he faces the television:
HIS LEFT:
Pizza tray with an open pizza box, soda holder, blue-lit water tank and toilet-paper roll.
HIS RIGHT:
The controller tray, empty because the controller is already in his hands.
In the opening rear view, his left-side accessories appear on the left side of the image, matching Image 3.
All accessories remain fixed to the chair. No eating, flushing, operating controls or moving trays.
BLOCKING
The woman enters through the left-wall door and follows the clear aisle outside the chair's left-side accessories.
She stops beside and slightly ahead of his left shoulder, approximately one meter away. She does not block the television, collide with the pizza tray or reach across the tank.
He looks at her with a natural leftward head turn and a small shoulder adjustment. His hips, legs and chair stay directed toward the television.
She remains there after stopping. The door stays ajar.
PRICE TAG
A cream-colored rectangular retail tag is physically attached by a short black cord to the outer front corner of his RIGHT armrest, below the empty controller tray.
The tag hangs against the dark leather, with its printed face pointing outward toward the chair's right side.
Print exactly:
1,999$
Large bold black text. Preserve the comma and trailing dollar sign. No additional digits, logos or fine print.
The tag exists from the beginning. Early framing keeps its printed face outside the crop, turned away or too small to read.
The final camera angle reveals the tag. Nobody picks it up or turns it toward the camera. It never appears spontaneously.
TIMELINE
00:00-00:02.00 | ESTABLISH THE SCENE
Begin with Image 3's rear room composition, now with the man seated in the chair.
Show the exterior backrest, the back of his head and the television directly in front of him. His seated body and footrest point toward the screen. The chair is stationary.
Use a slight rear three-quarter offset if needed to show a glimpse of his hands holding the controller while preserving the room layout.
The black door begins opening immediately. The woman appears and starts crossing the threshold before the shot ends.
Do not reveal the readable price tag.
00:02.00-00:07.00 | HER QUESTION
Cut to a medium front-left three-quarter view filmed from near the television, looking back toward the seated man.
The television is behind this camera and outside its frame. The camera position changes through a cut; the chair does not move.
Continue the woman's entrance without repeating it. She walks toward his left side while saying:
"Where's your paycheck? We need to buy a new sofa."
Clear, natural English delivery and accurate lip sync. She briefly gestures toward the sofa on "a new sofa."
She passes outside the pizza tray and tank, then stops beside and slightly ahead of his left shoulder.
Keep both characters readable. During her sentence, he turns his head toward her. His pleased expression fades at the mention of his paycheck.
His hands continue holding the controller. Let his reaction develop during her speech rather than adding a silent pause afterward.
00:07.00-00:10.00 | HIS ANSWER
Cut to a medium close-up of the man, matching his eyeline toward the woman at his left.
He gives a sheepish half-smile and says:
"Well... there's a tiny problem."
Use a brief hesitation after "Well," then natural conversational pacing. Emphasize "tiny" with a small apologetic shoulder lift.
Both hands remain on the controller. His body stays seated toward the television.
As the line ends, his eyes briefly dip toward the right armrest. Cut directly to the reveal, without an additional reaction shot.
00:10.00-00:12.00 | FIND THE PRICE
Cut to a medium detail view from the man's RIGHT side.
Establish the right armrest, empty controller tray, part of his blue sleeve and the controller still held above his lap.
The camera makes a short downward move and smooth push-in toward the tag below the tray. Shift focus onto its printed face.
The camera angle reveals the existing tag; the tag does not turn itself.
By 00:12.00, the complete price is large and sharp:
1,999$
00:12.00-00:15.00 | THE PUNCHLINE
Hold a clean close-up of the physical price tag.
The entire price remains sharp, stable and inside the frame. Show the black cord and part of the stitched leather armrest so the price clearly belongs to the chair.
Use a very subtle continuing camera push and quiet room ambience.
No further dialogue, reaction cut, animated text or added joke. End on the price.
CAMERA AND EDITING
Image 3 establishes the opening view and correct chair orientation.
After the opening, frontal shots are filmed from the television side, looking back toward the man. The television is behind the camera, never incorrectly behind his head in these shots.
Maintain consistent room geography and matching eyelines. The man looks at the woman, and she looks at him.
The final right-side angle is introduced by a clean cut. No camera passing through furniture or characters.
Keep the price unreadable until the reveal. No early close-up or accidental readable view.
Natural motion, controlled framing and expressive facial acting. No unnecessary orbiting, repeated reactions or artificial acceleration.
AUDIO
All dialogue is in English, spoken once with accurate lip sync.
Woman:
"Where's your paycheck? We need to buy a new sofa."
Man:
"Well... there's a tiny problem."
Her voice is practical and expectant. His voice is warm, embarrassed and hesitant.
Natural door latch, hinge movement, footsteps, clothing movement, soft leather creaks and quiet room ambience.
No active gameplay sounds over the static start screen. No toilet flush.
No background music, narrator, canned laughter, subtitles or extra lines.
CONTINUITY AND CONSTRAINTS
Exactly 15 seconds.
Image 1 controls the man's identity and clothes.
Image 2 controls the woman's identity and clothes.
Image 3 controls the room, opening composition, animation style and chair orientation.
Image 4 controls the chair's detailed construction and raised lamp.
The isolated chair's frontal product view must never override its television-facing position in the room.
The man is already seated facing the television from the first frame. No chair rotation or moving television.
The woman enters once, walks to his left side and stops. The door remains ajar.
One controller only, held in both hands throughout. Its tray stays empty despite the controller appearing there in the object references.
All accessories remain attached. Keep adequate clearance between the man's head and the raised lamp.
One price tag and one cord, fixed to the right armrest. Exact text: "1,999$". No floating price graphic or changing digits.
No extra fingers, intersecting limbs, floating props, disappearing accessories or inconsistent character designs.
Sequence: man already facing the television, her entrance and question, his guilty answer, camera reveal of the attached price tag.
🤝 Paid partnership · 🤖 Made with AI
This chair should come free with GTA 6. No reason to ever pause.
Seedance 2.5 on @makeugc
Prompt
FORMAT
20-second horizontal 16:9 photorealistic cinematic comedy. A confident adult woman demonstrates an extravagant gaming toilet-chair. Real live-action appearance, natural movement, convincing mechanical weight, accurate English lip sync and clear comedic timing.
REFERENCES
Image 1: gaming-room and chair reference. Use it for the exact opening composition, room layout, television artwork, lighting, furniture and chair design. Preserve the black leather toilet-chair, footrest, blue-lit circular base, pizza tray, controller tray, drink holder, toilet-paper roll, transparent blue-lit water tank and overhead circular light.
Image 2: woman's appearance reference. Preserve her face, blue eyes, freckles, long wavy blonde hair with darker roots, natural skin texture, fitted white short-sleeved top with a low rounded neckline, and delicate silver necklace with a small pendant.
Image 2 is a portrait. Complete her outfit with light-blue jeans and white sneakers. Do not copy the portrait background, portrait lighting or the white number "2" into the video.
She is an adult woman, approximately 25 years old. Maintain her appearance, clothing and jewelry throughout.
ENVIRONMENT
Reproduce the room from Image 1: dark charcoal television wall, large central television, low black media cabinet, upright white game console, soundbar, warmly illuminated display shelves with figures and trailing plants, blue LED accents, dark wood flooring, textured gray rug, left-side black door, partial charcoal sofa and pale curtains on the right.
The television retains the same GTA VI start-screen artwork from Image 1 throughout. No unrelated gameplay, changing artwork or morphing lettering.
The black door is initially closed. The woman begins in the hallway behind it.
Realistic leather, fabric, skin, metal, glass and water. Accurate shadows and reflections. Warm practical lights balance the blue accents and preserve natural skin tones.
CHAIR ORIENTATION
Initially, the empty chair faces the opening camera. The television is behind the chair's backrest.
The woman sits facing the same direction as the chair, initially toward the opening camera. The television is behind her.
After she presses the swivel button, the occupied chair rotates through exactly 180 degrees. The woman rotates with it, keeping her hips, torso and legs aligned with the seat.
At the end of the turn:
- Her face, knees and the footrest point toward the television.
- The backrest and back of her head point toward the original camera.
- She is correctly positioned to watch the television.
The chair stops in this orientation and remains stationary for the rest of the video. She never turns the chair back toward the original camera.
ATTACHMENTS AND CONTROLS
All left and right directions below refer to the seated woman's perspective.
HER LEFT:
The attached pizza tray holds an open pizza box.
The soda can rests securely in its holder.
The transparent blue-lit water tank sits beside and slightly behind the left armrest.
The flush button is directly above the tank cap, reachable beside her left shoulder without reaching through the backrest.
The toilet-paper roll remains mounted below this side.
HER RIGHT:
The white-and-black game controller rests on its attached tray.
A separate swivel button is on the right armrest.
In the opening frontal composition, the pizza and tank appear on screen right, while the controller appears on screen left.
The seat, backrest, armrests, footrest, trays, tank, controls and overhead light rotate together as one connected assembly. The circular floor base remains stationary.
Allow sufficient clearance around the chair for all attachments to rotate. Smooth acceleration and deceleration keep the pizza box, controller and drink stable. Plumbing remains concealed inside the assembly.
The toilet opening is visible while the chair is empty. The woman sits naturally on the surrounding supportive seat and remains fully dressed.
CAMERA GEOGRAPHY: IMPORTANT
CAMERA POSITION A:
The opening camera faces the front of the chair, with the television visible behind it. From this position, the completed chair rotation reveals the backrest and the back of the woman's head as she faces the television.
CAMERA POSITION B:
After the rotation finishes, CUT to a camera positioned in the space directly in front of the television, slightly offset toward the woman's left side. This camera points away from the television and back toward the seated woman.
The television is BEHIND CAMERA B and outside its frame. The woman faces the television and therefore also faces approximately toward Camera B. The slight lateral offset creates a front-left three-quarter view that shows her face, pizza tray and flush control.
This is a change of camera position through an editing cut. The chair does not turn again.
The camera occupies real open space between the television and the chair. It is not inside the screen, wall or cabinet.
All shots after the rotation use this television-side viewing direction. Wider framing may reveal both trays without changing the chair's orientation.
When she addresses Camera B, she makes only a small natural head turn toward the lens. Her body remains seated toward the television.
TIMELINE
00:00-00:05.50 | ENTER AND SPEAK
Begin at Camera Position A with the exact composition from Image 1. The empty gaming toilet-chair dominates the foreground. The television is behind it, and the black door is visible on the left.
The door begins opening immediately. The woman steps into the room and says while walking toward the chair:
"If your gaming setup doesn't look like this, you don't love yourself."
Deliver the complete sentence briskly but clearly, with confident, teasing emphasis on the final words. Accurate lip sync.
She briefly presents the setup with an open-hand gesture. She walks outside the controller tray, around its front corner and into the clear space beside the footrest. She never walks through an attachment or steps over the footrest.
By the end of the line, she turns into position to sit, with the seat directly behind her. The door remains ajar.
Use a subtle camera push-in while preserving the room's geography.
00:05.50-00:07.50 | SIT AND PRESS
Cut to a medium three-quarter view from the controller side, showing her knees, the seat and right armrest.
She bends her knees and lowers herself onto the padded seat, using an armrest lightly for balance. Show actual contact and subtle cushion compression.
In one continuous settling movement, she brings her feet onto the footrest. Her feet clear the floor before the rotation begins.
She presses the swivel button on her right armrest with her right index finger. Show the fingertip depressing the control. The motor begins only after contact.
00:07.50-00:10.00 | ROTATE TOWARD THE TELEVISION
Cut back to a wide view from near Camera Position A. Keep the television and entire chair assembly visible.
Show one complete 180-degree clockwise rotation, as viewed from above, in an uninterrupted shot. Keep the camera nearly stationary so the orientation change is unmistakable.
The woman rotates with the chair. Her face is initially visible, then passes through profile. At the end, the camera sees the backrest and the back of her head while she faces the television.
Her torso remains aligned with the seat. She does not twist to keep facing the original camera.
The footrest, pizza tray, controller tray, tank and overhead light all rotate with her. The room and television remain stationary.
The motor slows smoothly and stops with the chair fully facing the television at 00:10.00.
00:10.00-00:14.50 | PIZZA
CUT to Camera Position B: film FROM THE TELEVISION TOWARD THE WOMAN, slightly diagonally from her left.
The television is behind the camera and outside the frame. The woman continues facing the television. The chair has not moved since completing its turn.
Use a medium front-left three-quarter composition showing her face, pizza tray and water tank.
With her left hand, she grasps one pizza slice by its crust, lifts it and takes one small bite from its tip. Show the bite separating naturally and leave a visible missing section.
She lowers that same slice and returns it to the space it came from inside the box. She releases it completely.
She chews the small mouthful while returning the slice and finishes swallowing before speaking again. Natural compact movement, without exaggerated chewing or a long cheese pull.
00:14.50-00:16.00 | THE ANNOUNCEMENT
Continue from Camera Position B with slightly tighter framing.
Keeping her body oriented toward the television, she makes a small head turn toward the nearby lens and says:
"And most importantly..."
Her expression becomes knowingly playful. Emphasize the phrase without a prolonged pause.
As she finishes speaking, she lifts her empty left hand toward the flush button directly above the tank. Use a natural bent-elbow reach beside her left shoulder. Her hand remains outside the backrest and clear of her hair.
She finishes the line before pressing.
00:16.00-00:17.50 | FLUSH AND SMILE
Keep her face, left hand and flush control visible together from the same viewing direction.
She presses the button above the water tank once with her left index finger. Show physical contact and button depression.
Immediately afterward, a loud, unmistakable household toilet-flush sound comes from the chair: rushing water followed by a swirling hollow gurgle.
The transparent tank shows believable turbulence and a modest water-level drop. No leaks or water spraying into the room.
She releases the button and gives the camera a pleased, mischievous smile. No additional dialogue or exaggerated laughter.
The chair stays stationary, facing the television.
00:17.50-00:20.00 | TAKE THE CONTROLLER
The flush continues across a clean cut to a wider composition from the same television-side viewing direction. Include the controller tray on her right.
She lowers her left hand toward her lap. With her right hand, she grips and lifts the white-and-black controller from its tray.
She brings it in front of her waist and places her left hand on the other grip. Both hands hold it naturally, with her thumbs resting over the controls.
Her gaze shifts slightly away from the nearby lens and back to the television behind the camera. End with her comfortably facing the screen, smiling and ready to play.
The flush fades into a brief refill hiss. The television remains on the established start screen, even when outside the frame.
VISUAL STYLE AND EDITING
Cinematic live-action photography with natural skin pores, fine hair strands, realistic fabric weave, leather stitching, water refraction and soft contact shadows.
Use wide framing for the room and rotation, medium framing for facial reactions and prop interactions. Moderate depth of field keeps relevant controls and objects readable.
The rotation shot must show that she finishes facing the television. Do not cut away before the turn completes.
Use a clean cut to Camera Position B afterward. Do not simulate this viewpoint change by rotating the chair back or moving the television.
Preserve appropriate backgrounds:
Camera A sees the television wall beyond the chair.
Camera B sees the opposite side of the room beyond the woman, consistent with the established room layout.
Keep decisive interactions visible: sitting contact, swivel-button press, full rotation and stop, pizza bite, slice replacement, flush-button press and controller pickup.
No camera passing through furniture, walls or attachments. No visible camera or crew reflections.
AUDIO
One consistent natural female voice. English dialogue only, with accurate lip sync.
Exact spoken lines:
1. "If your gaming setup doesn't look like this, you don't love yourself."
2. "And most importantly..."
No additional words, paraphrasing or repeated dialogue.
Natural door movement, footsteps, clothing movement, leather compression, distinct button clicks, quiet electric swivel motor, subtle pizza-box rustle, prominent household toilet flush, brief refill hiss and controller handling.
The flush starts only after the visible flush-button press and continues during the controller pickup.
No background music, voice-over, subtitles, canned laughter or end titles.
CONTINUITY AND CONSTRAINTS
Preserve the reference room and the woman's reference appearance.
The woman remains fully dressed and stays seated after sitting down.
Exactly one 180-degree chair rotation. She finishes facing the television and remains in that orientation. Later small head turns toward the camera do not rotate her torso or chair.
All attached accessories follow the chair. No stationary trays left behind during rotation.
Pizza remains on her left. The controller remains on her right until pickup. Screen positions change naturally with the camera angle.
Her left hand handles the pizza and presses the flush button. Her right hand activates rotation and picks up the controller. She finishes holding the controller with both hands.
The bitten slice retains its missing bite after being returned. The controller stays on the tray until the final pickup.
The swivel button and flush button remain separate controls with separate functions.
No disappearing objects, duplicated props, extra fingers, impossible reaches, floating food, intersecting limbs, changing chair geometry, moving television or rotating room.
No slow motion, speed ramps, idle pauses or repeated completed actions. Exactly 20 seconds.
Trixi retweeted
This chair should come free with GTA 6. No reason to ever pause.
Seedance 2.5 on @makeugc
Prompt
FORMAT
20-second horizontal 16:9 photorealistic cinematic comedy. A confident adult woman demonstrates an extravagant gaming toilet-chair. Real live-action appearance, natural movement, convincing mechanical weight, accurate English lip sync and clear comedic timing.
REFERENCES
Image 1: gaming-room and chair reference. Use it for the exact opening composition, room layout, television artwork, lighting, furniture and chair design. Preserve the black leather toilet-chair, footrest, blue-lit circular base, pizza tray, controller tray, drink holder, toilet-paper roll, transparent blue-lit water tank and overhead circular light.
Image 2: woman's appearance reference. Preserve her face, blue eyes, freckles, long wavy blonde hair with darker roots, natural skin texture, fitted white short-sleeved top with a low rounded neckline, and delicate silver necklace with a small pendant.
Image 2 is a portrait. Complete her outfit with light-blue jeans and white sneakers. Do not copy the portrait background, portrait lighting or the white number "2" into the video.
She is an adult woman, approximately 25 years old. Maintain her appearance, clothing and jewelry throughout.
ENVIRONMENT
Reproduce the room from Image 1: dark charcoal television wall, large central television, low black media cabinet, upright white game console, soundbar, warmly illuminated display shelves with figures and trailing plants, blue LED accents, dark wood flooring, textured gray rug, left-side black door, partial charcoal sofa and pale curtains on the right.
The television retains the same GTA VI start-screen artwork from Image 1 throughout. No unrelated gameplay, changing artwork or morphing lettering.
The black door is initially closed. The woman begins in the hallway behind it.
Realistic leather, fabric, skin, metal, glass and water. Accurate shadows and reflections. Warm practical lights balance the blue accents and preserve natural skin tones.
CHAIR ORIENTATION
Initially, the empty chair faces the opening camera. The television is behind the chair's backrest.
The woman sits facing the same direction as the chair, initially toward the opening camera. The television is behind her.
After she presses the swivel button, the occupied chair rotates through exactly 180 degrees. The woman rotates with it, keeping her hips, torso and legs aligned with the seat.
At the end of the turn:
- Her face, knees and the footrest point toward the television.
- The backrest and back of her head point toward the original camera.
- She is correctly positioned to watch the television.
The chair stops in this orientation and remains stationary for the rest of the video. She never turns the chair back toward the original camera.
ATTACHMENTS AND CONTROLS
All left and right directions below refer to the seated woman's perspective.
HER LEFT:
The attached pizza tray holds an open pizza box.
The soda can rests securely in its holder.
The transparent blue-lit water tank sits beside and slightly behind the left armrest.
The flush button is directly above the tank cap, reachable beside her left shoulder without reaching through the backrest.
The toilet-paper roll remains mounted below this side.
HER RIGHT:
The white-and-black game controller rests on its attached tray.
A separate swivel button is on the right armrest.
In the opening frontal composition, the pizza and tank appear on screen right, while the controller appears on screen left.
The seat, backrest, armrests, footrest, trays, tank, controls and overhead light rotate together as one connected assembly. The circular floor base remains stationary.
Allow sufficient clearance around the chair for all attachments to rotate. Smooth acceleration and deceleration keep the pizza box, controller and drink stable. Plumbing remains concealed inside the assembly.
The toilet opening is visible while the chair is empty. The woman sits naturally on the surrounding supportive seat and remains fully dressed.
CAMERA GEOGRAPHY: IMPORTANT
CAMERA POSITION A:
The opening camera faces the front of the chair, with the television visible behind it. From this position, the completed chair rotation reveals the backrest and the back of the woman's head as she faces the television.
CAMERA POSITION B:
After the rotation finishes, CUT to a camera positioned in the space directly in front of the television, slightly offset toward the woman's left side. This camera points away from the television and back toward the seated woman.
The television is BEHIND CAMERA B and outside its frame. The woman faces the television and therefore also faces approximately toward Camera B. The slight lateral offset creates a front-left three-quarter view that shows her face, pizza tray and flush control.
This is a change of camera position through an editing cut. The chair does not turn again.
The camera occupies real open space between the television and the chair. It is not inside the screen, wall or cabinet.
All shots after the rotation use this television-side viewing direction. Wider framing may reveal both trays without changing the chair's orientation.
When she addresses Camera B, she makes only a small natural head turn toward the lens. Her body remains seated toward the television.
TIMELINE
00:00-00:05.50 | ENTER AND SPEAK
Begin at Camera Position A with the exact composition from Image 1. The empty gaming toilet-chair dominates the foreground. The television is behind it, and the black door is visible on the left.
The door begins opening immediately. The woman steps into the room and says while walking toward the chair:
"If your gaming setup doesn't look like this, you don't love yourself."
Deliver the complete sentence briskly but clearly, with confident, teasing emphasis on the final words. Accurate lip sync.
She briefly presents the setup with an open-hand gesture. She walks outside the controller tray, around its front corner and into the clear space beside the footrest. She never walks through an attachment or steps over the footrest.
By the end of the line, she turns into position to sit, with the seat directly behind her. The door remains ajar.
Use a subtle camera push-in while preserving the room's geography.
00:05.50-00:07.50 | SIT AND PRESS
Cut to a medium three-quarter view from the controller side, showing her knees, the seat and right armrest.
She bends her knees and lowers herself onto the padded seat, using an armrest lightly for balance. Show actual contact and subtle cushion compression.
In one continuous settling movement, she brings her feet onto the footrest. Her feet clear the floor before the rotation begins.
She presses the swivel button on her right armrest with her right index finger. Show the fingertip depressing the control. The motor begins only after contact.
00:07.50-00:10.00 | ROTATE TOWARD THE TELEVISION
Cut back to a wide view from near Camera Position A. Keep the television and entire chair assembly visible.
Show one complete 180-degree clockwise rotation, as viewed from above, in an uninterrupted shot. Keep the camera nearly stationary so the orientation change is unmistakable.
The woman rotates with the chair. Her face is initially visible, then passes through profile. At the end, the camera sees the backrest and the back of her head while she faces the television.
Her torso remains aligned with the seat. She does not twist to keep facing the original camera.
The footrest, pizza tray, controller tray, tank and overhead light all rotate with her. The room and television remain stationary.
The motor slows smoothly and stops with the chair fully facing the television at 00:10.00.
00:10.00-00:14.50 | PIZZA
CUT to Camera Position B: film FROM THE TELEVISION TOWARD THE WOMAN, slightly diagonally from her left.
The television is behind the camera and outside the frame. The woman continues facing the television. The chair has not moved since completing its turn.
Use a medium front-left three-quarter composition showing her face, pizza tray and water tank.
With her left hand, she grasps one pizza slice by its crust, lifts it and takes one small bite from its tip. Show the bite separating naturally and leave a visible missing section.
She lowers that same slice and returns it to the space it came from inside the box. She releases it completely.
She chews the small mouthful while returning the slice and finishes swallowing before speaking again. Natural compact movement, without exaggerated chewing or a long cheese pull.
00:14.50-00:16.00 | THE ANNOUNCEMENT
Continue from Camera Position B with slightly tighter framing.
Keeping her body oriented toward the television, she makes a small head turn toward the nearby lens and says:
"And most importantly..."
Her expression becomes knowingly playful. Emphasize the phrase without a prolonged pause.
As she finishes speaking, she lifts her empty left hand toward the flush button directly above the tank. Use a natural bent-elbow reach beside her left shoulder. Her hand remains outside the backrest and clear of her hair.
She finishes the line before pressing.
00:16.00-00:17.50 | FLUSH AND SMILE
Keep her face, left hand and flush control visible together from the same viewing direction.
She presses the button above the water tank once with her left index finger. Show physical contact and button depression.
Immediately afterward, a loud, unmistakable household toilet-flush sound comes from the chair: rushing water followed by a swirling hollow gurgle.
The transparent tank shows believable turbulence and a modest water-level drop. No leaks or water spraying into the room.
She releases the button and gives the camera a pleased, mischievous smile. No additional dialogue or exaggerated laughter.
The chair stays stationary, facing the television.
00:17.50-00:20.00 | TAKE THE CONTROLLER
The flush continues across a clean cut to a wider composition from the same television-side viewing direction. Include the controller tray on her right.
She lowers her left hand toward her lap. With her right hand, she grips and lifts the white-and-black controller from its tray.
She brings it in front of her waist and places her left hand on the other grip. Both hands hold it naturally, with her thumbs resting over the controls.
Her gaze shifts slightly away from the nearby lens and back to the television behind the camera. End with her comfortably facing the screen, smiling and ready to play.
The flush fades into a brief refill hiss. The television remains on the established start screen, even when outside the frame.
VISUAL STYLE AND EDITING
Cinematic live-action photography with natural skin pores, fine hair strands, realistic fabric weave, leather stitching, water refraction and soft contact shadows.
Use wide framing for the room and rotation, medium framing for facial reactions and prop interactions. Moderate depth of field keeps relevant controls and objects readable.
The rotation shot must show that she finishes facing the television. Do not cut away before the turn completes.
Use a clean cut to Camera Position B afterward. Do not simulate this viewpoint change by rotating the chair back or moving the television.
Preserve appropriate backgrounds:
Camera A sees the television wall beyond the chair.
Camera B sees the opposite side of the room beyond the woman, consistent with the established room layout.
Keep decisive interactions visible: sitting contact, swivel-button press, full rotation and stop, pizza bite, slice replacement, flush-button press and controller pickup.
No camera passing through furniture, walls or attachments. No visible camera or crew reflections.
AUDIO
One consistent natural female voice. English dialogue only, with accurate lip sync.
Exact spoken lines:
1. "If your gaming setup doesn't look like this, you don't love yourself."
2. "And most importantly..."
No additional words, paraphrasing or repeated dialogue.
Natural door movement, footsteps, clothing movement, leather compression, distinct button clicks, quiet electric swivel motor, subtle pizza-box rustle, prominent household toilet flush, brief refill hiss and controller handling.
The flush starts only after the visible flush-button press and continues during the controller pickup.
No background music, voice-over, subtitles, canned laughter or end titles.
CONTINUITY AND CONSTRAINTS
Preserve the reference room and the woman's reference appearance.
The woman remains fully dressed and stays seated after sitting down.
Exactly one 180-degree chair rotation. She finishes facing the television and remains in that orientation. Later small head turns toward the camera do not rotate her torso or chair.
All attached accessories follow the chair. No stationary trays left behind during rotation.
Pizza remains on her left. The controller remains on her right until pickup. Screen positions change naturally with the camera angle.
Her left hand handles the pizza and presses the flush button. Her right hand activates rotation and picks up the controller. She finishes holding the controller with both hands.
The bitten slice retains its missing bite after being returned. The controller stays on the tray until the final pickup.
The swivel button and flush button remain separate controls with separate functions.
No disappearing objects, duplicated props, extra fingers, impossible reaches, floating food, intersecting limbs, changing chair geometry, moving television or rotating room.
No slow motion, speed ramps, idle pauses or repeated completed actions. Exactly 20 seconds.
🤝 Paid partnership · 🤖 Made with AI
This AI video is every GTA 6 fan's bedroom on release day.
Pizza boxes everywhere, a toilet for a gaming chair, and Rockstar still said one more year.
Made with Seedance 2.5 on @makeugc (native 15-second video)
Prompt
FORMAT
15-second vertical 9:16 photorealistic live-action comedy. One continuous first-person POV shot with no cuts. Natural real-time movement.
An impatient gamer sits fully clothed on a toilet placed in his bedroom, waiting for a game-release countdown. The countdown ends with a delay announcement. He throws his controller at the television. The woman watching from the doorway retreats and quietly closes the door.
REFERENCE
Image 1 is the only reference. Use it exclusively as the artwork displayed INSIDE the television during the countdown.
Preserve its sunset, palm trees, cars, illustrated characters, logo, colors, and composition. Replace its existing timer digits with the changing digits specified below. Display only one timer.
Do not use Image 1 as the full video frame or as a reference for the real man's appearance. Its illustrated characters remain flat artwork on the screen.
REALISM
Everything outside the television must look like actual live-action footage: a real adult actor, a real bedroom, natural skin pores and stubble, realistic eyes, cotton fabric, ceramic reflections, cardboard packaging, and rumpled bedding.
Use physically believable weight, inertia, hand grips, joint movement, and object contact. The comedy comes from the situation and performance, not exaggerated cartoon physics.
An eye-level first-person camera with the casual visual character of phone footage: mild wide-angle perspective, subtle body-driven movement, natural motion blur, restrained low-light noise, and gentle exposure adjustment.
The viewpoint is a small head-mounted camera, leaving the woman's hands free. The camera itself is never visible. There is no third person filming.
Keep sufficient depth of field to recognize the toilet and read the television. Only the television artwork is illustrated.
CHARACTERS
MAN
An adult man around 30 with an average build, light skin, short slightly untidy dark-brown hair, and light stubble.
He wears a white sleeveless cotton undershirt, dark-green athletic shorts, and white crew socks. His shorts stay in their normal position throughout.
He sits on a white ceramic toilet facing the television, with the tank behind him and both feet resting on the floor. He initially holds one black wireless game controller in both hands near his lap.
His emotional progression is anticipation, confusion, disbelief, frustrated protest, and an impulsive outburst. He remains seated throughout.
WOMAN
An adult woman observing from the bedroom doorway. Her face and body remain outside the frame. Her voice is close to the viewpoint.
Her left hand operates the door. Her right hand holds a separate phone below the frame; its upper edge becomes briefly visible only at the end. This phone is not the POV recording device.
SETTING
A small messy bedroom at night.
A large landscape television is mounted on the far wall, centered approximately 1.5 meters above the floor. A small game console rests on a low shelf beneath it.
The toilet stands approximately 1.8 meters in front of the television, slightly right of the screen's centerline. The man faces the screen.
An unmade bed with a crumpled gray duvet and pillows stands along the right wall. Open pizza boxes, leftover slices, takeaway containers, snack wrappers, and drink cans clutter the floor.
Leave a clear walking route through the doorway and keep clutter outside the door's swing.
The doorway is behind and slightly to the man's left. From this position, the camera sees his back and partial left profile, the toilet bowl and tank, the bed on the right, and the television ahead.
The television occupies the upper-left to upper-center part of the frame. The man and toilet occupy the lower-right middle ground. Both remain clearly visible.
The white paneled bedroom door has a dark round handle. Viewed from the hallway looking into the bedroom, its hinges are on the right. It opens inward.
The door begins approximately 65 degrees open. The woman stands near its free edge at the threshold, with its handle within natural reach. The door does not obstruct the initial view of the man or television.
Warm hallway light spills faintly through the doorway. The television provides the strongest illumination inside the bedroom.
TIMELINE
00:00-00:04 | THE SETUP
Begin at the doorway with a clear view of the man seated on the toilet and watching the television. Establish the absurd toilet placement immediately.
The television displays Image 1, fitted within its physical screen with correct perspective.
Show this countdown:
00:00-00:01: "00:06"
00:01-00:02: "00:05"
00:02-00:03: "00:04"
00:03-00:04: "00:03"
At approximately 00:00, the woman asks with amused disbelief:
"Are you seriously sitting on a toilet?"
Finish the question naturally within the first three seconds.
The man does not turn around. He leans forward slightly, keeps his eyes on the television, and holds the controller with both hands near his lap.
Show natural breathing, small finger movements, and slight shoulder tension. No repetitive bouncing.
Pink-purple television light illuminates his shoulders, the toilet, and nearby bedding. The camera remains nearly still, with subtle natural sway.
00:04-00:07 | ANTICIPATION
Continue the countdown:
00:04-00:05: "00:02"
00:05-00:06: "00:01"
00:06-00:07: "00:00"
Starting around 00:04, the man says:
"Stay. Stay. Come on. Come on!"
He murmurs the first two words to himself as if willing the countdown to finish without interruption. The final "Come on!" is more urgent. Finish the line before the announcement appears.
He grips the controller more tightly and leans forward a little farther. Both feet stay planted.
Each countdown value appears once in the correct order. The surrounding artwork remains static. Hold zero from 00:06 until 00:07.
00:07-00:10.5 | THE ANNOUNCEMENT
At 00:07, replace the entire countdown artwork with a black television display showing exactly two centered lines of bold white text:
RELEASE DELAYED
365 DAYS
Make the lettering large, stable, correctly spelled, and readable from the doorway. This is a fictional announcement within the comedy.
The colorful television illumination disappears. The bedroom becomes darker but remains visible through the white lettering and faint hallway light. Allow subtle camera exposure adjustment.
The man stiffens and raises his head slightly. His shoulders tense as he processes the message. Keep small breathing motions visible.
At approximately 00:09, he says:
"What?"
His delivery is quiet and disbelieving. The controller remains in both hands near his lap.
He continues staring at the message. Confusion develops into frustrated disbelief through his tightened shoulders, clenched jaw, and short exhale. Do not freeze the image.
00:10.5-00:12 | THE OUTBURST
From approximately 00:10.5 to 00:11.35, the man exclaims:
"Are you serious?!"
The delivery is sharp and incredulous, directed toward the announcement on the television.
As he speaks, he transfers the controller fully into his right hand. His left hand visibly releases it and moves aside for balance.
Still seated, he braces his feet, twists his torso slightly, and draws his right arm back above shoulder height.
Immediately after finishing the question, he snaps his arm forward and releases the controller toward the television.
Show the entire action without a cut: controller in hand, backswing, forward acceleration, finger release, short flight, and one impact near the center of the television at approximately 00:11.6.
Keep the flight and impact unobstructed. The controller must leave his hand before any screen damage appears.
On contact, a localized impact mark forms with radial cracks, a small damaged-pixel patch, and a few thin display artifacts. Keep most of the delay announcement recognizable.
The television remains attached to the wall. Only a few tiny fragments fall near the impact area. No explosion or window-like collapse.
The controller rebounds slightly and falls beneath the television. It lands and remains on the floor. His right hand stays empty afterward.
The camera makes a small startled jolt after contact while preserving a clear view of the impact.
00:12-00:13.5 | THE RETREAT
At approximately 00:12, after the impact, the man exclaims:
"Not again!"
His voice conveys exasperation about another delay. He gestures toward the damaged screen with empty hands while remaining seated. He does not approach the doorway.
The woman reaches for the accessible door handle with her left hand while still at the threshold. She takes a short backward step into the hallway, keeping hold of the handle.
Once her body and viewpoint clear the threshold, she pulls the door closed in one continuous movement.
The panel rotates around its fixed hinges and progressively hides the man, toilet, and cracked television. The camera stays on the hallway side.
Her hand follows the handle with a plausible bent-elbow movement. No stretched arm or hand passing through the panel.
00:13.5-00:15 | THE ENDING
The door finishes closing at approximately 00:13.5 with a small latch click. Her left hand releases the handle and lowers out of view.
Hold on the closed white door from the warmer-lit hallway. The camera settles with faint natural sway.
The upper edge of the phone already held low in her right hand briefly enters the bottom of the frame. Show no readable message and no additional phone action.
The woman remains silent. Any residual movement sounds from the bedroom are muffled by the closed door.
End on this quiet, awkward composition.
CAMERA
One uninterrupted first-person shot at natural adult eye height, approximately 24 mm full-frame-equivalent field of view.
Maintain the doorway position during the countdown and reaction. Keep the man, toilet, and television in the frame throughout the throw.
The only substantial movement is a brief reaction after impact and a short backward retreat into the hallway. Do not turn away before the controller hits.
No cuts, close-up inserts, reverse angles, orbiting, abrupt zooms, slow motion, speed ramps, or viewpoint jumps.
AUDIO
All dialogue is English. Speak each line once, at its assigned time, with no overlapping speakers.
The woman's question sounds close to the viewpoint. The man's voice comes from his physical position inside the bedroom.
His delivery progresses naturally from concentrated anticipation to confusion, protest, and exasperation. Synchronize mouth movement whenever his mouth is visible.
Use only the dialogue specified in the timeline. No improvised words, profanity, or additional shouting.
Natural sounds: faint electronic hum, clothing rustle, controller handling, one sharp plastic-and-screen impact, a few tiny fragments falling, the controller landing, soft footsteps, door movement, and the latch click.
The screen-impact sound occurs exactly at contact. The controller's floor impact follows separately. Bedroom sounds become progressively muffled as the door closes.
No music, narration, subtitles, or laughter track.
CONTINUITY
One man, one toilet, one black controller, one television, and one doorway.
The controller begins in both hands, transfers to the right hand, is released once, strikes once, and stays on the floor afterward.
The screen is intact until impact and remains damaged afterward. The announcement never resets to the countdown.
The man remains seated and his clothes stay unchanged. Furniture and clutter remain stationary unless visibly contacted.
The countdown and announcement stay attached to the television's display plane. The illustrated figures never become real people in the room.
The door starts partially open, follows one physical hinge arc, and ends closed. The woman takes its handle before retreating beyond reach.
Her left hand operates the door. Her right hand holds the separate phone. The head-mounted viewpoint leaves both hands free. No additional hands, arms, or camera operator appear.
NEGATIVE CONSTRAINTS
No cartoon rendering of the room or man, plastic skin, malformed anatomy, duplicated props, floating objects, disappearing controller, damage before contact, hidden release, repeated throw, excessive glass, exploding television, repaired screen, teleportation, changing room geometry, extra people, nudity, depicted toilet use, extra dialogue, captions, watermarks, or end cards.
This AI video is every "I'm not hungry" date in 20 seconds.
He ordered the burger. He's eating the salad.
Created by Kling 4.0 on @makeugc
Prompt
20-second horizontal 16:9 Pixar-style 3D animated comedy short. Expressive character acting, appealing rounded forms, detailed food and fabrics, warm restaurant lighting, and precise visual comedy.
Twenty seconds is edited screen time. Two clear time-ellipsis cuts omit food preparation and part of the meal. All visible movements play at natural speed.
REFERENCES
Image 1 defines the adult woman: recognizable face, curvy build, fair freckled skin, red hair in a loose half-up bun, black rectangular glasses, small earrings, red button-front top, ripped blue jeans, and white sneakers. Translate her into the same stylized animated aesthetic as the man.
Image 2 defines the adult man: rounded face, heavy build, balding crown, messy brown hair at the sides, thick eyebrows, black rectangular glasses, short facial stubble, blue polo, brown trousers, and dark sneakers.
Preserve both identities, body proportions, outfits, and glasses throughout. The man wears his blue polo without a jacket.
SETTING AND GEOGRAPHY
A cozy casual restaurant booth. The woman sits on screen left and the man on screen right, facing each other across a small wooden table.
Film from the open side of the booth in clear three-quarter views. Keep the camera on the same side of the action axis.
Her small white salad bowl belongs on screen left, near her. His large white burger-and-fries plate belongs on screen right, near him. Neither dish changes position.
The table is narrow enough for comfortable reaches across it. Keep the space between the dishes clear.
One compact burger with a sesame bun, patty, cheese, and lettuce. A modest side portion of thin fries. The burger fits securely in her hands and holds together during bites.
TIMELINE
00:00-00:04 | THE ORDER
Medium two-shot of the couple with open menus. No food is present yet.
The woman looks toward an off-screen server at the open end of the booth and says casually:
“I’m not hungry. Just a salad.”
The man then looks toward the same server and says:
“Burger and fries, please.”
Deliver the lines naturally within four seconds, without overlap. He smiles in anticipation.
00:04-00:06 | FOOD ARRIVES
Use a clear time-ellipsis cut to the prepared meal. Menus are now gone.
Her salad bowl is already in front of her, containing lettuce, cucumber slices, and cherry tomatoes.
A server’s hands enter from the open end of the booth and lower the burger-and-fries plate in front of the man. Show the plate contacting the table before the hands release it and withdraw.
The man looks eagerly at his food. The woman’s eyes shift toward the fries.
00:06-00:11 | JUST A TASTE
Cut slightly closer while retaining both faces, her reaching hand, and his plate.
She reaches across with her right hand, pinches one small fry, brings it to her mouth, and eats it. Her hand withdraws as she chews.
After swallowing the first small fry, she reaches again and takes a second. Show the second fry reaching her mouth. She withdraws her hand and finishes chewing by the end of this shot.
The man’s eyes follow the two separate reaches. His eager smile becomes a restrained, suspicious sideways look.
Keep this as two distinct actions at a relaxed but purposeful pace. No handfuls, repeated reaching loops, or simultaneous fries appearing in her hand.
His hands remain beside his plate, leaving her reach unobstructed.
00:11-00:14 | THE BURGER
With her mouth now empty, she glances at the burger and leans forward slightly.
She reaches with both hands, grips the burger on his plate, lifts it securely, and draws it toward herself. Show the complete pickup.
She takes one clear bite. Show mouth contact, slight bun compression, and a visible missing section when she pulls the burger away.
Her expression brightens with pleasure. The man watches with raised eyebrows and quiet disbelief.
Keep the pickup and bite visible in the same shot. Do not repeat either action from another angle.
00:14-00:17 | SOME TIME LATER
Use a brief dissolve into a wider view of the SAME table, clearly indicating that more eating has happened.
After this time jump:
His plate is empty except for a few crumbs.
She has eaten the remaining fries and most of the burger during the omitted interval.
She now holds only a small, coherent final portion of that same burger.
Her salad is still untouched in its original bowl.
Do not show food magically shrinking during continuous action. Establish the later food state only after the dissolve.
The man looks from his empty plate to her untouched salad. With a resigned expression, he reaches across using his right hand, pinches one lettuce leaf by its stem, and lifts it from her bowl.
He brings the leaf toward his mouth. The woman keeps holding her remaining burger portion near her chest, clear of his reaching arm.
00:17-00:20 | THE FINAL CONTRAST
Continue in the same balanced two-shot without another time jump.
The man takes one small bite from the lettuce leaf, leaving a visible missing piece. He chews sadly, shoulders slightly lowered, still holding the rest of the leaf.
Beside him, the woman takes a satisfied bite from the final small portion of his burger and chews with a contented smile. A small remainder stays visibly in her hands.
He gives her one weary sideways glance while she enjoys the food.
End on both expressions together: her satisfaction and his quiet disappointment. His empty plate and her nearly untouched salad remain visible beneath them.
PERFORMANCE
The comedy comes from the contradiction between her opening statement and her actions.
She behaves casually and enjoys the food, without exaggerated villainous expressions.
He progresses from anticipation to suspicion, disbelief, and mild resignation.
Keep reactions alive during the food actions rather than inserting long pauses.
Natural chewing with closed lips. No dialogue while eating.
CAMERA
Clear medium two-shots and one closer food-action shot.
Keep the woman on screen left and the man on screen right.
Keep both dishes and reaching hands readable.
Do not obscure the burger pickup, first burger bite, or lettuce bite.
No slow motion, speed ramps, frantic movement, or excessive cuts.
AUDIO
Exactly two spoken lines, in natural English:
Woman:
“I’m not hungry. Just a salad.”
Man:
“Burger and fries, please.”
Accurate lip synchronization. No overlapping dialogue or additional intelligible speech.
Soft restaurant ambience, subtle menu rustling, plate contact, food handling, restrained bite sounds, and a small crisp lettuce crunch.
No exaggerated wet chewing.
No background music, narration, captions, logos, or end titles.
CONTINUITY
Exactly one burger and one serving of fries.
Before the meal time jump, only the two visibly eaten fries are removed from the serving.
The woman takes the burger from his plate and retains possession throughout.
The first visible bite remains missing until the time jump.
The later nearly finished burger and empty plate are justified by the explicit meal time jump.
After that jump, neither the burger nor the fries regenerate.
The salad bowl stays in front of the woman.
The man removes exactly one lettuce leaf; all remaining salad stays in the bowl.
Her hands remain clear of his arm when he reaches for the salad.
Food is supported by hands or dishes, with visible contact before every pickup.
Preserve consistent glasses, faces, hairstyles, clothing, body proportions, table layout, and lighting.
NEGATIVE CONSTRAINTS
No duplicate burgers, regenerating food, floating ingredients, fused fingers, unexplained dish swaps, instantaneous food disappearance within a continuous shot, or repeated completed actions.
No makeover, clothing changes, sudden body-size changes, or additional foreground diners.
Render both characters and the restaurant in one cohesive Pixar-style animated world.
🤝 Paid partnership · 🤖 Made with AI
This AI cartoon looks like a Pixar short that cost 99% less and took 1% of the time.
Give the girl a snack, and 99% of the drama disappears.
📢 Add this video as a reference and insert my prompt.
Prompt:
FORMAT
Approximately 17 seconds, VERTICAL 9:16. Match the duration and pacing of Video 1.
Polished cinematic 3D animated romantic comedy, matching the supplied character images: expressive stylized faces, detailed hair and clothing, soft cinematic shading, and appealing feature-animation proportions.
TASK AND REFERENCE PRIORITY
Recreate Video 1 using two completely replacement characters.
Video 1 controls the original performance: body movements, gestures, facial expressions, emotional progression, gaze directions, interactions, food handling, camera angles, framing, shot order, cuts, and timing.
Image 1 controls the replacement woman's identity, hairstyle, body proportions, and complete outfit.
Image 2 controls the replacement man's identity, hairstyle, body proportions, and complete outfit.
Make only these intended changes:
1. Completely replace the original woman with the woman from Image 1.
2. Completely replace the original man with the man from Image 2.
3. Slightly refresh the car's interior finishes.
4. Change the exterior atmosphere and cabin illumination to daytime.
The approved character replacements and daylight setting override conflicting visual details in Video 1. Preserve the source performance and story.
CHARACTER 1: WOMAN FROM IMAGE 1
Preserve her recognizable face, green eyes, freckles, lavender-purple hair, high voluminous wavy ponytail, and loose face-framing strands.
Keep her complete reference outfit:
- Open olive-green jacket.
- Cream hoodie beneath the jacket.
- Dark charcoal cargo joggers.
- Lavender-and-white chunky sneakers.
She replaces the original woman in every shot.
Her reference-image smile is not a fixed expression. At the beginning, reproduce the original woman's annoyed expression, tightly crossed arms, tense eyebrows, pursed lips, and dismissive gaze.
Animate her through the source's exact progression from irritation to reluctant eating, puffed-cheek chewing, relaxation, affection, and the final embrace.
CHARACTER 2: MAN FROM IMAGE 2
Preserve his recognizable face, tousled curly dark-brown hair, hazel eyes, thick eyebrows, light stubble, and reference body proportions.
Keep his complete reference outfit:
- Open black jacket.
- Light-gray hoodie beneath the jacket.
- Dark cargo trousers.
- Black-and-white sneakers with orange accents.
He replaces the original man in every shot.
Transfer the original man's cautious glances, concerned reactions, hopeful food presentation, expectant observation, relieved smile, bouquet presentation, and affectionate embrace onto this new character.
Do not retain the original man's muscular build, bare forearms, navy T-shirt, face, or hairstyle. Both replacement characters keep their jacket sleeves and hoodie layers during all gestures.
The image references define appearance, not standing poses, permanent smiles, or studio backgrounds. Both characters are seated and animated according to Video 1. Do not add full-body shots to display their outfits.
CAR INTERIOR AND DAYLIGHT
Preserve the original cabin geometry, seat positions, character spacing, windows, and room for movement.
Slightly refresh the finishes with warm light-gray upholstery, charcoal door trim, and subtle brushed-metal accents. Do not introduce new furniture, large accessories, or a different seating arrangement.
Maintain a consistent daytime exterior throughout. Keep the same general street setting, now naturally lit by daylight.
Soft window daylight illuminates both faces, with balanced exposure, gentle shadows, subtle warm interior bounce, and believable glass reflections.
Keep exterior details softly defocused and secondary to the characters.
No nighttime windows or dominant amber ceiling lighting.
Preserve each character's seat and physical position throughout. Match their screen positions separately for every source shot. Do not mirror the reference, swap seats, or force identical left-right framing across different camera angles.
FOOD, DRINK, AND FLOWERS
Keep the original food and drink:
- Large sesame-seed burger with the reference's visible fillings.
- French fries in a red carton.
- Partially unwrapped chocolate bar in purple packaging.
- Metallic travel mug with a dark lid.
Follow Video 1 for their scale, arrangement, grip, presentation height, and visibility in each shot.
Keep objects distinct, physically supported, and stable during movement.
Preserve the same large bouquet of pink, orange, and purple flowers, including its wrapping, scale, presentation, and position in the final embrace.
PERFORMANCE SEQUENCE
Follow the source video's actual timing and cuts. The following beats explain the action without introducing a separate timing schedule.
1. ANNOYED OPENING
Reproduce the original opening composition and gestures.
The woman crosses or holds her arms exactly as in the source, with tense eyebrows, pursed lips, and an annoyed gaze.
The man notices her mood and gives the same cautious, concerned reaction.
Do not soften her expression early.
2. FOOD PRESENTATION
The man makes the same downward lean and retrieval movement as the original, then brings the food and drink toward her.
Preserve his hand paths, torso movement, hopeful expression, and presentation timing.
Keep the food at the same practical distance from her face as in the reference.
She retains her stubborn posture.
3. RELUCTANT EATING
Match the original close-up, food arrangement, head movements, mouth movements, and comic timing.
During the hands-free fries beat, her arms remain crossed as in Video 1. She moves her mouth toward the exposed fries while the man holds the carton steady.
Show clear mouth-to-food contact before she withdraws and chews. Fries must not teleport into her mouth or pass through her face.
Preserve the contrast between eating willingly and continuing to look annoyed.
Reproduce the original puffed cheeks, eyebrow tension, and eye movements without losing her reference identity.
Do not add a burger bite, drinking action, or other eating action absent from Video 1.
4. EXPECTANT REACTION
Match the original shared framing.
The woman continues the source's chewing performance with puffed cheeks and lingering irritation.
The man watches her with the same tentative expression while maintaining the original food presentation.
Keep the original short reaction pauses. Do not extend them or add repeated chewing loops.
5. EMOTIONAL SOFTENING
Reproduce the source's gradual relaxation: the woman's eyelids, eyebrows, cheeks, and mouth settle into the original affectionate expression.
Preserve the order and timing of her glances and smile.
The man responds with the same relief and warm smile.
No abrupt switch from anger to happiness.
6. BOUQUET TRANSITION
Keep the original edit into the bouquet presentation.
Food and drink are set aside offscreen across this transition. Do not add a separate shot or extend the sequence to show this.
The bouquet is a separate physical object, never a transformation of the food.
Match the original presentation gesture and the woman's movement toward the flowers.
7. FINAL EMBRACE
Reproduce the original closing interaction.
The woman rests her head against the man, and he places his arm around her shoulders.
Match their smiles, closing eyes, body contact, bouquet placement, and final framing.
His embracing hand is free of food and drink.
Finish at the same emotional moment as Video 1, without an additional scene or end card.
CAMERA AND EDITING
Use Video 1 as the direct guide for shot order, shot size, lens perspective, camera height, movement, and cut timing.
Preserve the emphasis on facial reactions.
Keep any framing adjustment minimal and only accommodate the new character proportions and lavender ponytail.
Do not add establishing shots, character introductions, camera orbits, slow motion, speed ramps, or extra reaction shots.
AUDIO
Use the supplied video as the audio reference for its music, sound effects, and nonverbal vocal reactions, preserving their synchronization with the action.
Do not introduce new dialogue, narration, or additional music.
If intelligible source dialogue is present, render its meaning in English with matching delivery and timing.
CONTINUITY
Maintain the same faces, hairstyles, eye colors, clothing layers, and body proportions across every cut.
The woman's ponytail follows her head movement naturally. It remains attached at the same position and does not intersect the roof, seat, clothing, or the man's face.
Preserve both characters' jacket sleeves through crossed-arm poses, food handling, and the embrace.
Keep hands anatomically clear, with consistent grips and visible support for props. No merged fingers, floating packaging, or objects passing through hands.
Food only changes through visible eating, handling, or the original shot occlusion. An item outside the crop is not erased.
Do not restore consumed fries, multiply food, or change the burger's condition without a visible action.
Preserve the source's uninterrupted emotional progression.
NEGATIVE CONSTRAINTS
No original character identities or outfits.
No additional people or duplicated characters.
No seat swapping or mirrored shots.
No permanent reference-photo smiles.
No altered food menu or invented actions.
No food-to-flower morphing.
No hair-color changes, disappearing sleeves, extra limbs, or missing hands.
No nighttime atmosphere.
No live-action conversion.
No captions, subtitles, watermarks, or final text.
Trixi retweeted
Real GTA 6 fans go for a walk exactly like this.
Made with Seedance 2.5 on @makeugc (native 15-second video)
Prompt
FORMAT
15-second horizontal 16:9 photorealistic live-action comedy in Times Square, New York. Real cinema-camera footage, natural movement speed, precise deadpan comic timing.
The first frame immediately shows the absurd situation: a man walking through a real pedestrian plaza while playing GTA VI on a large monitor mounted in front of his face on a backpack-supported metal frame.
REFERENCE
Use the supplied image as the visual reference for the main man, clothing, controller, backpack, monitor, mounting structure, and city atmosphere. The image defines their appearance, not the opening camera position.
Preserve his black baseball cap, dark curly hair, glasses, short facial hair, visible neck and arm tattoos, light gray sleeveless shirt, black backpack, blue illuminated accents, and PlayStation emblem.
Preserve the large black landscape monitor, its substantial bezel, and the black metal support rising from the backpack and extending above his head toward the monitor. Preserve the white-and-black controller held in both hands.
The reference shows an on-foot game scene. For this video, intentionally replace that screen content with continuous GTA VI-style driving gameplay while preserving the reference's game branding and general visual identity.
CHARACTER AND PHYSICAL SETUP
The gamer treats his absurd equipment as completely normal. He concentrates on the game, walks casually, and never performs for the camera.
Both shoulder straps secure the backpack. The monitor is physically supported by the same rigid frame throughout. The support joints remain locked, with a fixed distance between the man's face and screen.
The display surface faces the man. The back of the monitor points forward along his walking direction. Never rotate the screen independently to make it visible to the camera.
The backpack, support, and monitor move together with his torso. Footsteps create only slight vibration. Show believable weight through his posture and taut straps, without exaggerated bouncing or flexing.
His hands hold the controller below the monitor. His eyes can briefly check the ground beneath its lower edge, allowing him to follow a clear walking route.
ENVIRONMENT AND REALISM
Times Square pedestrian plaza after rain, matching the reference: bright advertising displays, reflective damp pavement, metal barriers, moving pedestrians, and traffic beyond the pedestrian area.
Real skin texture, natural hair, fabric weave, worn hardware, plausible reflections, and realistic light from the monitor. The real city must look like live-action footage. Only the image on the monitor looks like a video game.
He stays within the pedestrian plaza. Leave a clear corridor wide enough for the projecting monitor. Pedestrians notice the equipment and make room naturally.
GAMEPLAY
A sports car drives along a palm-lined city boulevard, viewed from a third-person chase camera. Retain the recognizable GTA VI branding from the reference and a simple, stable game HUD.
The same car continues through the same driving sequence across shots. It makes one clear turn during 00:04-00:08, then continues forward.
The car's steering corresponds to a small thumb movement on the controller. Gameplay remains animated whenever the screen is visible, including during the conversation.
Keep all game imagery inside the monitor. Perspective, reflections, and screen brightness must match the physical display. No game graphics appear over the real city.
TIMELINE
00:00-00:04 | ABSURD FROM FRAME ONE
Begin with an eye-level medium-wide tracking shot from the man's side, slightly behind his shoulder.
The opening composition clearly shows the backpack, the entire overhead support, the large monitor projecting in front of him, and both hands holding the controller. Include his walking legs and enough Times Square background to establish that he is outdoors.
Do not begin with a close-up of gameplay. The absurd portable setup must be understandable immediately.
The man walks at an ordinary relaxed pace, looking at the monitor and actively playing.
Beside his route, a stationary adult pedestrian holding a hot dog is about to take a bite. He notices the enormous gaming rig and freezes with the hot dog just short of his open mouth. His eyes follow the gamer.
The gamer continues past without noticing. Keep the reaction brief, believable, and visible within the main shot.
00:04-00:08 | GAMING WHILE WALKING
Cut on a matching footstep to a closer rear three-quarter tracking shot. Clearly show the screen, the man's hands, and the frame's attachment to his backpack.
On the screen, the car enters one sharp turn. His thumb moves the stick, and he makes a small involuntary lean of his shoulders in the same direction, only a few degrees.
His feet keep a normal walking rhythm and remain on the same route. He does not stagger, stop, or swing the monitor sideways. The rigid setup follows his slight torso movement as one assembly.
He straightens as the on-screen car completes the turn.
Two pedestrians ahead notice the equipment and step to the sides with sufficient clearance. Their reactions remain subtle and spontaneous.
An engine rev and one short tire squeal synchronize with the turn on the screen.
00:08-00:12 | THE QUESTION
Cut to an eye-level side two-shot from the gamer's unobstructed side. Frame his face in profile behind the monitor's near edge, with the approaching passerby beside his route.
The monitor remains physically in front of the gamer, facing him. Do not move or shrink it to reveal his face. Choose the camera angle to see his profile naturally.
A young adult male passerby, already approaching from ahead, slows and stops beside the route, outside the monitor's footprint.
From approximately 00:08.2 to 00:10.8, the passerby looks at the rig and asks:
“Bro, why not just play at home?”
While hearing the question, the gamer takes one final short step and stops beside him by approximately 00:09.5. Show a natural transfer of weight as the equipment settles.
The gamer keeps both hands on the controller, continues playing, and does not turn his head toward the passerby.
Allow a brief deadpan reaction beat after the question. The screen remains active.
00:12-00:15 | THE PUNCHLINE
Continue the same side two-shot without a cut.
From approximately 00:12.0 to 00:14.2, the gamer answers casually while watching the game:
“My doctor said I need more walks.”
The delivery is sincere, clear, and conversational, without a smile or exaggerated emphasis.
As he finishes the sentence, he begins walking again, taking one or two natural steps before the video ends. The entire rig travels with him.
The passerby stays where he stopped and silently follows the gamer with a bewildered look. Keep both men visible during this final reaction.
End while the gamer is still walking and playing. No additional event or dialogue.
CAMERA AND EDITING
Use three camera setups:
1. Medium-wide side tracking shot establishing the complete rig.
2. Rear three-quarter tracking shot revealing gameplay.
3. Side two-shot for the full conversation and final reaction.
Use two clean cuts, at approximately 00:04 and 00:08. Match walking direction, body position, controller grip, and equipment orientation across cuts.
Keep support connections readable. Use moderate depth of field so the equipment and relevant reactions remain understandable.
Natural handheld or stabilized camera movement with realistic motion blur. No slow motion, speed ramps, crash zooms, or repeated actions.
AUDIO
Exactly two intelligible spoken lines, both in English.
Passerby, curious and puzzled:
“Bro, why not just play at home?”
Gamer, completely matter-of-fact:
“My doctor said I need more walks.”
Accurate lip synchronization. No voice-over and no extra dialogue.
Natural city ambience, subdued crowd murmur, footsteps on wet pavement, quiet controller clicks, game engine sounds, and one tire squeal. Game audio comes from the monitor speakers.
Keep game and street sounds below the dialogue. No music, laugh track, comedic sting, or subtitles.
CONTINUITY
Maintain the same appearance, clothing, tattoos, backpack, blue accents, controller, screen dimensions, and mounting geometry throughout.
Both hands stay on the controller. The monitor never floats, detaches, changes size, bends, or intersects his head.
The gamer walks during 00:00-00:08, stops while the passerby asks the question, remains stopped for his reply, and resumes walking only as he finishes it.
The hot-dog pedestrian and speaking passerby are two different people with different clothing and positions.
Background pedestrians maintain continuous paths. The passerby remains stationary when the gamer leaves.
No collisions, disappearing objects, duplicated limbs, frozen crowds, cartoon rendering, plastic skin, floating HUD elements, end cards, or added text outside the monitor.
🤝 Paid partnership · 🤖 Made with AI
This AI video is the most accurate GTA 6 release day simulation on the internet.
He brought pizza to the toilet. Rockstar brought another year.
Made with Seedance 2.5 on @makeugc (native 15-second video)
Prompt:
FORMAT
15-second vertical 9:16 photorealistic live-action comedy. One continuous first-person POV shot without cuts. Natural real-time movement.
An impatient gamer has installed a television in his toilet room and surrounded himself with pizza and snacks. He sits on the toilet in an undershirt and opaque boxer briefs, with his athletic shorts gathered around his ankles, waiting for a game-release countdown.
The countdown ends with a delay announcement. He throws his controller at the television. The woman watching from the doorway retreats and quietly closes the door.
REFERENCE
Image 1 is the only reference. Use it exclusively as the artwork displayed INSIDE the television during the opening countdown.
Preserve its sunset, palm trees, cars, illustrated characters, logo, colors, and composition. Replace its existing timer digits with the changing digits specified below. Display only one timer.
Image 1 does not define the full-frame composition, room, or real man's appearance. Its illustrated characters remain flat artwork within the television.
REALISM
Everything outside the television looks like actual live-action footage: a real adult actor, natural skin pores and stubble, believable eyes, cotton fabric, glazed ceramic, tile grout, cardboard pizza boxes, food texture, and physical television materials.
Natural body weight, seated balance, hand grips, joint movement, object inertia, and contact. The comedy comes from the setup and performance, not cartoon physics.
Eye-level first-person footage with mild wide-angle perspective, small body-driven movements, natural motion blur, and subtle exposure adjustment.
The viewpoint is a small head-mounted camera worn by the woman, leaving both hands free. The camera itself is never visible. There is no third person filming.
CHARACTERS
MAN
An adult man around 30 with an average build, light skin, short slightly untidy dark-brown hair, and light stubble.
He wears a white sleeveless cotton undershirt, opaque charcoal boxer briefs, and white crew socks. His dark-green athletic shorts are lowered and gathered loosely around both ankles.
The boxer briefs remain properly worn at his waist and fully cover his groin and buttocks throughout.
He sits naturally on the toilet seat ring, hips supported, knees comfortably apart, feet planted, and torso initially leaning slightly forward. The gathered shorts allow modest foot spacing without unnatural stretching.
The solid toilet lid is raised against the cistern. The separate seat ring is lowered onto the bowl. He sits on the ring, not on the closed lid, bare porcelain rim, or cistern.
No bodily functions are depicted.
He holds one black wireless game controller in both hands near his lap. His emotions progress from anticipation to confusion, disbelief, protest, and an impulsive outburst.
He remains seated throughout. His feet do not step or separate beyond the slack allowed by his shorts.
WOMAN
An adult woman watching from the doorway. Her face and body remain outside the frame. Her voice is close to the viewpoint.
Her left hand operates the door. Her right hand holds a separate phone low, outside the frame until its upper edge briefly appears during the final hallway shot. This phone is not the POV recording device.
LOCATION AND BLOCKING
A believable residential toilet room, approximately 2.2 meters wide and 2.8 meters deep. Warm off-white upper walls, pale gray wall tiles, a slightly worn tiled floor, and a small wall-mounted sink.
The toilet is installed against the right wall, beyond the entrance door's swing. Its cistern is behind the man. The bowl points across the room toward the television on the opposite left wall.
A 50-inch landscape flat-screen television is securely mounted on the left wall. Its screen center is approximately 1.35 meters above the floor, within a short throwing distance of the seated man.
TELEVISION FRAME
Give the television a slightly wider, clearly visible matte-black bezel, approximately 3 centimeters thick around the display, with a subtly thicker lower edge.
It should look like a believable conventional flat-screen television, not a borderless panel, a decorative picture frame, or an old bulky CRT.
The black bezel is a solid physical object with subtle edge highlights. Its dimensions remain identical throughout.
Image 1 fills only the active display area inside the bezel. The artwork never covers the frame. The delay announcement also stays entirely inside this display area.
Mount the television on a short fixed swivel bracket, angled slightly toward the doorway so the screen is readable from the initial camera position while remaining comfortably visible to the man.
The camera sees the screen at a moderate three-quarter angle, not edge-on. The television and bracket do not swivel during the scene.
A narrow shelf beneath the television holds a game console. Cables follow the wall and stay clear of the floor.
An open pizza box with several slices sits on a small side table near the man, below elbow height and outside his throwing path. A second open pizza box, takeaway containers, snack packets, and drink cans sit on a low shelf along the far wall.
Keep the sink, doorway, backward walking route, door swing, and floor beneath the television clear.
There is no bed or bedroom furniture. This is unmistakably a toilet room repurposed as a gaming setup.
From the doorway, the camera sees the television on the left and the man on the toilet on the right. His partial profile, torso, controller, knees, and shorts around his ankles are visible.
The raised lid is visible behind his lower back. Portions of the lowered seat ring remain visible beneath his hips. Maintain a normal eye-level composition without intimate close-ups.
A white paneled door has a dark round handle. Viewed from the hallway looking into the room, its hinges are on the right and it opens inward. It starts approximately 65 degrees open.
The woman stands near the door's free edge at the threshold, with its handle within reach. The open panel does not hide the man or television.
A dim warm ceiling light provides steady base illumination. The television adds stronger pink-purple light during the countdown. Warm hallway light spills faintly through the entrance.
TIMELINE
00:00-00:04 | THE SETUP
Begin at the doorway. Show the man seated on the toilet, the raised lid, lowered seat ring, shorts around his ankles, pizza beside him, and television opposite him.
His opaque boxer briefs remain in place. Establish the situation through the wide composition without moving toward his lap.
The television displays Image 1 inside its active screen. Its wider matte-black bezel remains clearly visible on all four sides.
Show this countdown:
00:00-00:01: "00:06"
00:01-00:02: "00:05"
00:02-00:03: "00:04"
00:03-00:04: "00:03"
At approximately 00:00, the woman asks with amused disbelief:
"Are you seriously sitting on a toilet?"
Finish the question naturally within the first three seconds.
The man does not turn toward her. He watches the television, leans forward slightly, and holds the controller in both hands near his lap.
Show small finger movements, natural breathing, and tense shoulders. His feet remain planted beside the gathered shorts.
Colored television light reflects softly from the tiles, ceramic, and white undershirt.
00:04-00:07 | ANTICIPATION
Continue the countdown:
00:04-00:05: "00:02"
00:05-00:06: "00:01"
00:06-00:07: "00:00"
Starting around 00:04, the man says:
"Stay. Stay. Come on. Come on!"
The first two words are nervous self-directed murmurs, as if willing the countdown to finish without interruption. The last "Come on!" is more urgent. Finish the line before the screen changes.
He tightens his grip and leans slightly farther forward, remaining seated without bouncing.
Each timer value appears once in the correct order. Keep the surrounding artwork static. Hold zero from 00:06 until 00:07.
00:07-00:10.5 | THE ANNOUNCEMENT
At 00:07, replace the countdown artwork with a black display containing exactly two centered lines of bold white text:
RELEASE DELAYED
365 DAYS
The lettering is stable, correctly spelled, and large enough to read from the doorway. This is a fictional announcement within the comedy.
The physical matte-black television bezel remains unchanged and distinguishable from the black display through soft reflections on its edges.
The pink-purple screen illumination disappears. The warm ceiling light stays on, keeping the room visible. Allow a small natural exposure adjustment.
The man stiffens and raises his head. He stares at the announcement with tense shoulders and a slightly open mouth.
At approximately 00:09, he says:
"What?"
His delivery is quiet and disbelieving. The controller remains in both hands.
Confusion develops into frustration through a clenched jaw, tightened grip, and short exhale. Keep breathing visible during the pause.
00:10.5-00:12 | THE OUTBURST
From approximately 00:10.5 to 00:11.35, the man exclaims:
"Are you serious?!"
He directs the line toward the television with sharp disbelief.
While speaking, he transfers the controller entirely into his right hand. His left hand releases it and moves aside for balance.
Still seated with his feet in their established positions, he rotates his torso slightly and raises his right hand beside and just behind his head for a compact overhand throw. His elbow clears the raised lid, cistern, and wall.
Immediately after the question, he accelerates his arm forward and releases the controller toward the active screen.
Show the complete sequence: controller in hand, compact backswing, forward acceleration, release, brief flight, and one impact near the screen's center at approximately 00:11.6.
The controller leaves his fingers before the television reacts. Keep the release and impact unobstructed.
The controller strikes the display, not the black bezel. A localized impact mark forms, followed by radial cracks, a small damaged-pixel patch, and thin display artifacts. Most of the announcement remains recognizable.
The wider bezel remains intact, rigid, and unchanged. The television stays mounted and keeps its original angle.
Only a few tiny fragments fall near the impact. No explosion or window-like collapse.
The controller rebounds slightly, drops onto the clear tiled floor beneath the television, bounces once, and settles. Both hands are now empty.
The camera makes a small startled jolt after contact while keeping the impact visible.
00:12-00:13.5 | THE RETREAT
At approximately 00:12, the man exclaims:
"Not again!"
He gestures toward the damaged television with empty hands while remaining seated.
His boxer briefs stay in place. His shorts remain around his ankles. He does not stand, step, or follow the woman.
The woman takes the accessible door handle with her left hand while still at the threshold. She takes a short backward step into the hallway, maintaining her grip.
Once her body and viewpoint clear the threshold, she pulls the door closed. The panel rotates around its fixed hinges and progressively conceals the man, toilet, pizza, and damaged television.
Her arm follows the handle with a natural bent-elbow movement. No stretched arm or hand passing through the panel.
00:13.5-00:15 | THE ENDING
The door finishes closing at approximately 00:13.5 with a small latch click.
Her left hand releases the handle and lowers out of view. Hold on the closed white door from the hallway.
The camera settles with slight natural sway. The upper edge of the phone already held low in her right hand briefly enters the bottom of the frame. No readable message or extra phone action.
The woman remains silent. Any residual sounds inside are muffled by the closed door.
End on this quiet, awkward beat.
CAMERA
One continuous first-person shot at normal adult eye height, approximately 24 mm full-frame-equivalent field of view.
Maintain the doorway composition during the countdown and reaction: television on the left, man and toilet on the right.
Keep the display readable and its matte-black bezel visible. Show enough of the man's profile to read his reaction.
Show the controller release, flight, and contact within the same shot. Retreat only after impact.
No cuts, inserts, reverse shots, orbiting, abrupt zooms, slow motion, speed ramps, or viewpoint jumps.
AUDIO
All dialogue is English. Each line is spoken once at its assigned time, without overlapping speakers.
The woman's question sounds close to the viewpoint. The man's voice comes from his visible position inside the room, with mild natural tile reverberation.
His delivery progresses from anticipation to confusion, protest, and exasperation. Synchronize visible mouth movements.
Use only the specified lines. No improvised words, profanity, or additional shouting.
Natural sounds: faint ventilation hum, fabric movement, controller handling, one sharp screen impact, tiny fragments falling, the controller hitting and bouncing on tile, soft backward footsteps, door movement, and the latch click.
Match each sound to its visible cause. Muffle room sounds progressively as the door closes. No toilet-use sounds.
No music, narration, subtitles, or laughter track.
CONTINUITY
One adult man, one toilet, one black controller, one television, and one doorway.
The solid lid stays raised. The seat ring stays lowered. The man remains seated on the ring.
His opaque boxer briefs remain properly worn. His shorts remain around his ankles. No unexplained clothing changes.
The controller starts in both hands, transfers to the right hand, is thrown once, strikes once, falls, and stays beneath the television.
The screen is intact before contact and damaged afterward. The announcement never returns to the countdown.
The television's matte-black bezel remains approximately 3 centimeters wide, solid, and unchanged throughout. Its mounting angle stays fixed.
Food, cans, sink, shelves, toilet, and hinges remain in their established locations.
The woman's left hand closes the door; her right hand holds the separate phone. She takes the handle before retreating beyond reach.
NEGATIVE CONSTRAINTS
No cartoon appearance outside the television, plastic skin, distorted anatomy, extra limbs, duplicated props, floating food, disappearing controller, premature damage, hidden release, repeated throw, excessive glass, exploding television, repaired screen, changing bezel thickness, borderless television, teleportation, shifting room geometry, extra people, nudity, depicted bodily functions, extra dialogue, captions, watermarks, or end cards.
Trixi retweeted
This AI video is the most accurate GTA 6 release day simulation on the internet.
He brought pizza to the toilet. Rockstar brought another year.
Made with Seedance 2.5 on @makeugc (native 15-second video)
Prompt:
FORMAT
15-second vertical 9:16 photorealistic live-action comedy. One continuous first-person POV shot without cuts. Natural real-time movement.
An impatient gamer has installed a television in his toilet room and surrounded himself with pizza and snacks. He sits on the toilet in an undershirt and opaque boxer briefs, with his athletic shorts gathered around his ankles, waiting for a game-release countdown.
The countdown ends with a delay announcement. He throws his controller at the television. The woman watching from the doorway retreats and quietly closes the door.
REFERENCE
Image 1 is the only reference. Use it exclusively as the artwork displayed INSIDE the television during the opening countdown.
Preserve its sunset, palm trees, cars, illustrated characters, logo, colors, and composition. Replace its existing timer digits with the changing digits specified below. Display only one timer.
Image 1 does not define the full-frame composition, room, or real man's appearance. Its illustrated characters remain flat artwork within the television.
REALISM
Everything outside the television looks like actual live-action footage: a real adult actor, natural skin pores and stubble, believable eyes, cotton fabric, glazed ceramic, tile grout, cardboard pizza boxes, food texture, and physical television materials.
Natural body weight, seated balance, hand grips, joint movement, object inertia, and contact. The comedy comes from the setup and performance, not cartoon physics.
Eye-level first-person footage with mild wide-angle perspective, small body-driven movements, natural motion blur, and subtle exposure adjustment.
The viewpoint is a small head-mounted camera worn by the woman, leaving both hands free. The camera itself is never visible. There is no third person filming.
CHARACTERS
MAN
An adult man around 30 with an average build, light skin, short slightly untidy dark-brown hair, and light stubble.
He wears a white sleeveless cotton undershirt, opaque charcoal boxer briefs, and white crew socks. His dark-green athletic shorts are lowered and gathered loosely around both ankles.
The boxer briefs remain properly worn at his waist and fully cover his groin and buttocks throughout.
He sits naturally on the toilet seat ring, hips supported, knees comfortably apart, feet planted, and torso initially leaning slightly forward. The gathered shorts allow modest foot spacing without unnatural stretching.
The solid toilet lid is raised against the cistern. The separate seat ring is lowered onto the bowl. He sits on the ring, not on the closed lid, bare porcelain rim, or cistern.
No bodily functions are depicted.
He holds one black wireless game controller in both hands near his lap. His emotions progress from anticipation to confusion, disbelief, protest, and an impulsive outburst.
He remains seated throughout. His feet do not step or separate beyond the slack allowed by his shorts.
WOMAN
An adult woman watching from the doorway. Her face and body remain outside the frame. Her voice is close to the viewpoint.
Her left hand operates the door. Her right hand holds a separate phone low, outside the frame until its upper edge briefly appears during the final hallway shot. This phone is not the POV recording device.
LOCATION AND BLOCKING
A believable residential toilet room, approximately 2.2 meters wide and 2.8 meters deep. Warm off-white upper walls, pale gray wall tiles, a slightly worn tiled floor, and a small wall-mounted sink.
The toilet is installed against the right wall, beyond the entrance door's swing. Its cistern is behind the man. The bowl points across the room toward the television on the opposite left wall.
A 50-inch landscape flat-screen television is securely mounted on the left wall. Its screen center is approximately 1.35 meters above the floor, within a short throwing distance of the seated man.
TELEVISION FRAME
Give the television a slightly wider, clearly visible matte-black bezel, approximately 3 centimeters thick around the display, with a subtly thicker lower edge.
It should look like a believable conventional flat-screen television, not a borderless panel, a decorative picture frame, or an old bulky CRT.
The black bezel is a solid physical object with subtle edge highlights. Its dimensions remain identical throughout.
Image 1 fills only the active display area inside the bezel. The artwork never covers the frame. The delay announcement also stays entirely inside this display area.
Mount the television on a short fixed swivel bracket, angled slightly toward the doorway so the screen is readable from the initial camera position while remaining comfortably visible to the man.
The camera sees the screen at a moderate three-quarter angle, not edge-on. The television and bracket do not swivel during the scene.
A narrow shelf beneath the television holds a game console. Cables follow the wall and stay clear of the floor.
An open pizza box with several slices sits on a small side table near the man, below elbow height and outside his throwing path. A second open pizza box, takeaway containers, snack packets, and drink cans sit on a low shelf along the far wall.
Keep the sink, doorway, backward walking route, door swing, and floor beneath the television clear.
There is no bed or bedroom furniture. This is unmistakably a toilet room repurposed as a gaming setup.
From the doorway, the camera sees the television on the left and the man on the toilet on the right. His partial profile, torso, controller, knees, and shorts around his ankles are visible.
The raised lid is visible behind his lower back. Portions of the lowered seat ring remain visible beneath his hips. Maintain a normal eye-level composition without intimate close-ups.
A white paneled door has a dark round handle. Viewed from the hallway looking into the room, its hinges are on the right and it opens inward. It starts approximately 65 degrees open.
The woman stands near the door's free edge at the threshold, with its handle within reach. The open panel does not hide the man or television.
A dim warm ceiling light provides steady base illumination. The television adds stronger pink-purple light during the countdown. Warm hallway light spills faintly through the entrance.
TIMELINE
00:00-00:04 | THE SETUP
Begin at the doorway. Show the man seated on the toilet, the raised lid, lowered seat ring, shorts around his ankles, pizza beside him, and television opposite him.
His opaque boxer briefs remain in place. Establish the situation through the wide composition without moving toward his lap.
The television displays Image 1 inside its active screen. Its wider matte-black bezel remains clearly visible on all four sides.
Show this countdown:
00:00-00:01: "00:06"
00:01-00:02: "00:05"
00:02-00:03: "00:04"
00:03-00:04: "00:03"
At approximately 00:00, the woman asks with amused disbelief:
"Are you seriously sitting on a toilet?"
Finish the question naturally within the first three seconds.
The man does not turn toward her. He watches the television, leans forward slightly, and holds the controller in both hands near his lap.
Show small finger movements, natural breathing, and tense shoulders. His feet remain planted beside the gathered shorts.
Colored television light reflects softly from the tiles, ceramic, and white undershirt.
00:04-00:07 | ANTICIPATION
Continue the countdown:
00:04-00:05: "00:02"
00:05-00:06: "00:01"
00:06-00:07: "00:00"
Starting around 00:04, the man says:
"Stay. Stay. Come on. Come on!"
The first two words are nervous self-directed murmurs, as if willing the countdown to finish without interruption. The last "Come on!" is more urgent. Finish the line before the screen changes.
He tightens his grip and leans slightly farther forward, remaining seated without bouncing.
Each timer value appears once in the correct order. Keep the surrounding artwork static. Hold zero from 00:06 until 00:07.
00:07-00:10.5 | THE ANNOUNCEMENT
At 00:07, replace the countdown artwork with a black display containing exactly two centered lines of bold white text:
RELEASE DELAYED
365 DAYS
The lettering is stable, correctly spelled, and large enough to read from the doorway. This is a fictional announcement within the comedy.
The physical matte-black television bezel remains unchanged and distinguishable from the black display through soft reflections on its edges.
The pink-purple screen illumination disappears. The warm ceiling light stays on, keeping the room visible. Allow a small natural exposure adjustment.
The man stiffens and raises his head. He stares at the announcement with tense shoulders and a slightly open mouth.
At approximately 00:09, he says:
"What?"
His delivery is quiet and disbelieving. The controller remains in both hands.
Confusion develops into frustration through a clenched jaw, tightened grip, and short exhale. Keep breathing visible during the pause.
00:10.5-00:12 | THE OUTBURST
From approximately 00:10.5 to 00:11.35, the man exclaims:
"Are you serious?!"
He directs the line toward the television with sharp disbelief.
While speaking, he transfers the controller entirely into his right hand. His left hand releases it and moves aside for balance.
Still seated with his feet in their established positions, he rotates his torso slightly and raises his right hand beside and just behind his head for a compact overhand throw. His elbow clears the raised lid, cistern, and wall.
Immediately after the question, he accelerates his arm forward and releases the controller toward the active screen.
Show the complete sequence: controller in hand, compact backswing, forward acceleration, release, brief flight, and one impact near the screen's center at approximately 00:11.6.
The controller leaves his fingers before the television reacts. Keep the release and impact unobstructed.
The controller strikes the display, not the black bezel. A localized impact mark forms, followed by radial cracks, a small damaged-pixel patch, and thin display artifacts. Most of the announcement remains recognizable.
The wider bezel remains intact, rigid, and unchanged. The television stays mounted and keeps its original angle.
Only a few tiny fragments fall near the impact. No explosion or window-like collapse.
The controller rebounds slightly, drops onto the clear tiled floor beneath the television, bounces once, and settles. Both hands are now empty.
The camera makes a small startled jolt after contact while keeping the impact visible.
00:12-00:13.5 | THE RETREAT
At approximately 00:12, the man exclaims:
"Not again!"
He gestures toward the damaged television with empty hands while remaining seated.
His boxer briefs stay in place. His shorts remain around his ankles. He does not stand, step, or follow the woman.
The woman takes the accessible door handle with her left hand while still at the threshold. She takes a short backward step into the hallway, maintaining her grip.
Once her body and viewpoint clear the threshold, she pulls the door closed. The panel rotates around its fixed hinges and progressively conceals the man, toilet, pizza, and damaged television.
Her arm follows the handle with a natural bent-elbow movement. No stretched arm or hand passing through the panel.
00:13.5-00:15 | THE ENDING
The door finishes closing at approximately 00:13.5 with a small latch click.
Her left hand releases the handle and lowers out of view. Hold on the closed white door from the hallway.
The camera settles with slight natural sway. The upper edge of the phone already held low in her right hand briefly enters the bottom of the frame. No readable message or extra phone action.
The woman remains silent. Any residual sounds inside are muffled by the closed door.
End on this quiet, awkward beat.
CAMERA
One continuous first-person shot at normal adult eye height, approximately 24 mm full-frame-equivalent field of view.
Maintain the doorway composition during the countdown and reaction: television on the left, man and toilet on the right.
Keep the display readable and its matte-black bezel visible. Show enough of the man's profile to read his reaction.
Show the controller release, flight, and contact within the same shot. Retreat only after impact.
No cuts, inserts, reverse shots, orbiting, abrupt zooms, slow motion, speed ramps, or viewpoint jumps.
AUDIO
All dialogue is English. Each line is spoken once at its assigned time, without overlapping speakers.
The woman's question sounds close to the viewpoint. The man's voice comes from his visible position inside the room, with mild natural tile reverberation.
His delivery progresses from anticipation to confusion, protest, and exasperation. Synchronize visible mouth movements.
Use only the specified lines. No improvised words, profanity, or additional shouting.
Natural sounds: faint ventilation hum, fabric movement, controller handling, one sharp screen impact, tiny fragments falling, the controller hitting and bouncing on tile, soft backward footsteps, door movement, and the latch click.
Match each sound to its visible cause. Muffle room sounds progressively as the door closes. No toilet-use sounds.
No music, narration, subtitles, or laughter track.
CONTINUITY
One adult man, one toilet, one black controller, one television, and one doorway.
The solid lid stays raised. The seat ring stays lowered. The man remains seated on the ring.
His opaque boxer briefs remain properly worn. His shorts remain around his ankles. No unexplained clothing changes.
The controller starts in both hands, transfers to the right hand, is thrown once, strikes once, falls, and stays beneath the television.
The screen is intact before contact and damaged afterward. The announcement never returns to the countdown.
The television's matte-black bezel remains approximately 3 centimeters wide, solid, and unchanged throughout. Its mounting angle stays fixed.
Food, cans, sink, shelves, toilet, and hinges remain in their established locations.
The woman's left hand closes the door; her right hand holds the separate phone. She takes the handle before retreating beyond reach.
NEGATIVE CONSTRAINTS
No cartoon appearance outside the television, plastic skin, distorted anatomy, extra limbs, duplicated props, floating food, disappearing controller, premature damage, hidden release, repeated throw, excessive glass, exploding television, repaired screen, changing bezel thickness, borderless television, teleportation, shifting room geometry, extra people, nudity, depicted bodily functions, extra dialogue, captions, watermarks, or end cards.
🤝 Paid partnership · 🤖 Made with AI
🎮 GTA 6 and a PS5 vs love, commitment and married life
Only one of them is coming out on Thursday, and it's not the marriage.
Made with Kling 4.0 on @makeugc
He waited 12 years for GTA 6 and put on a diaper so he wouldn’t miss a second
@Zyvex_0x Here's my reply to you, Pixar style, bro
Created by Seedance 2.5 on @makeugc
Save and use this PROMPT:
23-second vertical 9:16 animated comedy.
Premium theatrical 3D animation with appealing sculpted faces, expressive eyebrows and eyes, slightly exaggerated adult proportions, detailed groomed hair, tactile fabrics, soft skin shading, cinematic global illumination and convincing physical weight.
Match the character reference's visual style across the character, room, props and lighting. This is a fully animated scene, not live-action footage or a live-action background with an animated person.
REFERENCES
VIDEO REFERENCE:
Use the supplied video as the primary guide for the opening composition, physical performance, movement sequence, emotional progression, camera behavior and original audio timing.
Preserve its recognizable choreography and comedy. Replace the original man with the character from Image 1 and translate the setting into the same animated visual style.
IMAGE 1:
The identity, costume and rendering reference for the ONLY physical on-screen character.
Preserve his adult face, stocky build, tousled auburn hair, beard, expressive eyebrows, charcoal T-shirt, opaque white adult diaper with side fastening tabs, bare legs, bare feet, dark gaming headset and white-and-black controller.
The diaper is an essential nonsexual comedy prop. Do not replace it with shorts or ordinary underwear.
Image 1 does not define the opening pose or background. Begin with the gamer kneeling as in the video, not standing against the reference's neutral backdrop.
IMAGE 2:
The television screen artwork only.
Preserve its illustrated protagonists, existing logo, tropical sunset palette, composition and countdown-panel design. Keep this artwork confined to the television display.
The two illustrated people are part of a static screen image. They never become physical characters in the room.
PRIORITIES
The video controls performance, camera movement and audio timing.
Image 1 controls the gamer's appearance, clothing and animated visual style.
Image 2 controls the television artwork.
Follow the exact English dialogue provided below. Internal action timings are approximate guides; align gestures and facial reactions to the original audio without stretching, accelerating or cutting speech.
SETTING AND OPENING
A modest living room rendered in polished cinematic 3D animation. A large widescreen television stands on a low dark media console. Gray carpet, dim warm room illumination and pink-purple television light.
Begin immediately in the video's rear three-quarter handheld composition. The gamer is already kneeling close to the television, facing its screen.
His knees and shins rest on the carpet. His diaper is visible below the T-shirt. He holds the controller naturally.
An open pizza box is on his left. A blue snack bag and a beverage can are nearer the camera. A plain white game console stands beside the media unit.
Keep the prop arrangement consistent with the video and leave clear carpet beside the gamer for his final collapse.
The friend speaks from behind the camera and remains unseen throughout. Do not show the friend, their hands, their reflection or a recording device.
PERFORMANCE
The gamer is clearly an adult man in his mid-thirties.
His emotional progression:
confident anticipation,
rising excitement,
premature celebration,
disbelief,
desperate outrage,
exhausted resignation.
Use precise eye direction, expressive brows, readable mouth shapes and coordinated head, shoulder and hand movements. Exaggerate emotion without losing physical coherence.
TIMELINE
The following intervals cover the entire video. Within them, prioritize the reference audio's exact cadence and the event order described below.
00:00-00:04 | THE SETUP
The friend asks from behind the camera:
“Bro, are you wearing a diaper?”
The gamer remains focused on the television and confidently replies:
“I'm not missing a second.”
He makes small eager shifts on his knees, holding the controller and leaning toward the screen. Preserve the source video's gestures and rhythm.
The television displays Image 2. Its countdown panel shows “00:06” until the spoken countdown begins.
00:04-00:10.50 | ANTICIPATION
The gamer counts:
“Six, five, four, three, two, one, zero!”
Match the original vocal cadence. Change the existing television digits in synchronization with the spoken numbers:
Six: 00:06
Five: 00:05
Four: 00:04
Three: 00:03
Two: 00:02
One: 00:01
Zero: 00:00
Keep the surrounding artwork unchanged.
As excitement builds, he releases one hand from the controller and raises both arms, retaining the controller securely in the other hand. His free hand forms a celebratory fist.
Match the video's raised-arm performance. He stays kneeling, with grounded knees and natural torso movement.
00:10.50-00:11.10 | THE REVEAL
Immediately after the spoken “zero,” the countdown reaches 00:00 and its timer panel disappears.
A centered dark translucent download dialog appears over the unchanged television artwork.
Exact dialog text:
“Downloading”
“0%”
“14 hours remaining”
Below the text, show an empty progress-bar outline consistent with 0%.
The dialog is a flat interface element attached to the television screen, correctly following its perspective. It is not a floating object in the room.
The camera moves closer to the television as in the video. Keep “14 hours remaining” readable and unobstructed.
The gamer notices the message before reacting. His celebration stops and his arms begin to lower.
00:11.10-00:14.30 | DISBELIEF
The gamer reacts:
“Fourteen hours? Fourteen hours, bro! Don't laugh.”
The camera returns to a wider framing as he twists toward the unseen friend.
His eyes widen and his mouth opens in shock. He points toward the camera with his free hand while holding the controller in the other.
“Don't laugh” is directed at the friend behind the camera. Do not add a new reply or an invented laugh.
Keep the download dialog visible on the television behind him.
00:14.30-00:18.00 | THE BREAKDOWN
He cries:
“I waited twelve years, Sony! Twelve years!”
Match the reference's emphatic gestures and distressed facial performance. Direct his complaint toward the television, with the same brief looks toward the friend as in the source.
His frustration becomes a physical collapse. He leans forward, braces his free palm on the carpet and lowers his hip and shoulder into the clear space beside him.
Keep the controller in his other hand throughout. He holds it close to his upper chest during the descent so that it cannot pass through his body or become trapped beneath him.
Show a coherent transition from kneeling to lying on his side. No instant pose change or teleportation.
He draws his knees toward his chest. His free hand moves toward his face. The headset remains securely on his head.
The camera tilts down to follow the collapse while retaining the pizza box and part of the television.
By the friend's next question, he is curled on the carpet. He does not land on any food, packaging or the beverage can.
00:18.00-00:22.14 | THE CALLBACK
The unseen friend asks:
“Bro, you good?”
Still curled on his side, the gamer answers:
“Fourteen hours, that's why I wore it.”
Deliver the final line with tired resignation, following the source audio. His face remains sufficiently visible for readable lip synchronization. His eyes briefly turn toward the friend.
The controller remains in one hand near his chest. His free hand rests near his face. His diaper stays visible enough to connect the final line with the opening question.
He remains lying down through the end.
The television still shows the same download dialog:
“Downloading”
“0%”
“14 hours remaining”
Finish naturally after the complete final line, including the word “it.” Do not add another joke, a standing action, a fade-out or an end card.
CAMERA
Follow the source video's informal handheld camera behavior, translated into a virtual animated camera.
Use restrained handheld drift, a slightly tilted horizon, the motivated move toward the television message, the return to the facial reaction and the downward follow during the collapse.
Maintain the reference's apparent continuous handheld flow. Do not introduce new reverse angles, aerial views, spinning moves or unrelated inserts.
The television remains ahead of the gamer. The friend and camera remain behind and slightly to his side.
The audience must understand the screen message before the camera prioritizes the emotional reaction.
AUDIO
Use the supplied video soundtrack as the audio reference. Preserve its dialogue timing, vocal intensity, pauses, existing ambience, and any music or sound effects actually present.
Do not invent an additional soundtrack, narrator, laughter or new lines.
Two distinct English-speaking voices:
OFF-SCREEN FRIEND: casual and conversational.
GAMER: confident at first, then excited, shocked, distressed and finally resigned.
EXACT DIALOGUE, IN ORDER
OFF-SCREEN FRIEND:
“Bro, are you wearing a diaper?”
GAMER:
“I'm not missing a second.”
GAMER:
“Six, five, four, three, two, one, zero!”
GAMER:
“Fourteen hours? Fourteen hours, bro! Don't laugh. I waited twelve years, Sony! Twelve years!”
OFF-SCREEN FRIEND:
“Bro, you good?”
GAMER:
“Fourteen hours, that's why I wore it.”
Do not paraphrase, omit or reorder these lines.
Do not overlap speakers unless they overlap in the supplied audio.
Synchronize visible mouth movements with the gamer's speech.
The gamer's mouth does not speak the off-screen friend's lines.
No subtitles.
CONTINUITY
Only one physical character appears in the room.
The television's illustrated protagonists stay inside its static artwork.
Maintain the exact same gamer identity, body proportions, hairstyle, beard, costume and headset throughout.
The controller stays in his hands from the beginning to the end. During the raised-arm section and the collapse, it stays in the same chosen hand.
The headset and microphone remain attached and correctly positioned.
The diaper stays opaque, fastened and unchanged.
The countdown decreases only during the spoken count. After reaching zero, its panel disappears and never returns.
The download dialog appears only after zero. Progress stays at 0% for the rest of the scene.
Maintain the television artwork, furniture layout and floor-prop positions.
After the collapse, the gamer remains on the floor.
AVOID
Live-action imagery, plastic toy surfaces, changing character identity, childlike age, additional people, extra limbs, merged fingers, duplicated controllers, disappearing props, floating knees, sliding across the carpet, teleporting poses, a headset passing through the floor, costume changes, illegible interface text, a progress bar contradicting 0%, premature reactions, slow motion, accelerated speech, prolonged new pauses, added music, subtitles and end titles.
🤝 Paid partnership · 🤖 Made with AI
He waited 12 years for GTA 6 and still wasn't ready for what happened at 0
Created by Seedance 2.5 on @makeugc
Watch his face the second the screen changes. And stay for his last line, it explains everything.
Be honest, how long would you have lasted?
Prompt:👇
FORMAT: 22 seconds, vertical 9:16, one continuous handheld take, real time, no cuts. Authentic found footage shot on an early-2000s Sony DV tape camcorder: standard definition, soft optics, video noise, interlacing on motion, warm tungsten white balance, limited dynamic range, fine grain. It must feel like a real home clip that leaked online, never like a smartphone video and never like a movie. Where any line below mentions cinema cameras or lenses, this camcorder look overrides it: keep only the realism, physics, skin, texture and consistency requirements. The operator and the camcorder never appear: no hands, no body, no reflections.
CINEMATIC QUALITY (mandatory, applies to every shot of this video):
Generate this video as real live-action footage from a top-budget feature film. It must be indistinguishable from a real camera shoot and never look AI-generated, CGI-plastic or animated. Shot on ARRI Alexa 65 with sharp high-end prime lenses, cinematography in the style of Greig Fraser: motivated natural light, soft realistic shadows, true-to-life exposure, deep but detailed blacks, no blown highlights. 24 fps with natural 180-degree shutter motion blur on all movement. Native high resolution with razor-sharp focus on the subject, crisp micro-contrast and high-frequency detail on every edge, skin pore and surface texture. Subtle organic film-like grain over the whole image, stable across frames. Natural, slightly muted real-world color grade with accurate skin tones. Keep this quality consistent from the first frame to the last, with no flicker, morphing, warping or texture shimmer.
REFERENCES:
- IMAGE 1 (attached PS5 game page screenshot) is the TV screen only. It never affects the people, the room or the camera.
TV SCREEN: A real 55-inch LCD running a real PlayStation 5 shows IMAGE 1 full screen and static, with its exact left-aligned layout, artwork, colors and fonts: GTA VI icon top-left; "PS5" badge and the title "Grand Theft Auto VI: Ultimate Edition" along the top; the "VI grand theft auto" logo on the left; the description text; the white rounded timer button with a clock icon; the round "..." button; the "Friends Who Play" panel; "Official news"; the illustrated woman and man on the right half against a pink-orange sunset; the "R3 Health / Ratings / Privacy / Terms" bar bottom right. Only the timer button ever changes, in exactly two ways:
1. 0.0-3.0s it shows "00:00:06". From 3.0s the digits count down one per second: "00:00:05" at 4.0s, "00:00:04" at 5.0s, "00:00:03" at 6.0s, "00:00:02" at 7.0s, "00:00:01" at 8.0s, "00:00:00" at 9.0s.
2. At 10.0s the timer button disappears instantly and in its exact place appears a real PS5 download block: a large white "0%", under it a thin long almost empty progress bar with a tiny white sliver at the left and a dark grey track, and under the bar a small white line "14 hours remaining". Clean PlayStation-style sans-serif, perfectly spelled. It stays static until the end.
Filmed off the screen: slight LCD moire and a soft lamp reflection on the glass, but the timer and the download block stay sharp and readable.
CAMERA: His best friend films one-handed, about two and a half meters behind the gamer and to his right, camcorder held high at head height, angled slightly down. The whole TV is always visible, filling about two thirds of the frame width in the upper half; the gamer kneels low and to the left of the TV center, so his head never covers the timer or the download block. Two clumsy, overshooting zoom-ins: at 8.5s on the timer, and at 10.0s on the download block so "0%" and "14 hours remaining" fill the frame for about one second, then a jerky zoom back out. Amateur camerawork: hand shake, breathing sway, a slightly tilted horizon, late autofocus, auto-exposure pumping when the screen changes. The image shakes harder whenever the operator laughs.
REALISM: Ordinary people, no model looks. Real skin with pores, oily shine, stubble, sweat. Real physical emotion: a red face, bulging neck veins and spit on screams, wet eyes, a voice that cracks and goes hoarse. Objects have weight: the rug thuds under his fist. Light only from a warm floor lamp and the TV.
CHARACTERS:
- GAMER: about 28, average build, messy dark curly hair, light stubble. A plain black short T-shirt ending at the top of the diaper, NO pants: a bulky white adult diaper of matte cotton-like fabric with side tapes and a printed waistband, worn on bare skin. The diaper is never glowing, shiny, reflective or lit by the screen, only the same soft warm lamp light and shadow as his legs. Bare legs, bare feet. A black over-ear gaming headset. A WHITE PS5 DualSense controller. Obsessed, unhinged, loud, completely serious. A comedic, non-sexual look.
- OPERATOR: his best friend, heard only, laughing.
- No other people on screen.
SET (fixed): A small apartment at night. A 55-inch TV on a low dark wooden media stand against a beige wall, a white PS5 standing upright to its right. A warm floor lamp on the left. A grey shaggy rug. At the lower edge of the frame: an open pizza box with one slice of pizza, two unbranded energy drink cans and a bag of chips.
TIMELINE:
0.0-3.0s, THE SETUP: Timer "00:00:06". He kneels on the rug, back to the camera, the white controller gripped in both hands, rocking. The camera dips clumsily to the diaper, then back up to the TV. Operator, laughing: "Bro, are you wearing a diaper?" He, without turning: "I'm not missing a second."
3.0-9.0s, THE COUNTDOWN: He screams every number at the TV as it appears, louder each time, shoulders shaking: "SIX!" at 3.0s, "FIVE!" at 4.0s, "FOUR!" at 5.0s, "THREE!" at 6.0s, "TWO!" at 7.0s, "ONE!" at 8.0s. At 9.0s "00:00:00": "ZEROOO!", both arms raised, the controller high above his head.
9.0-10.0s, THE BEAT: Arms still raised, he freezes, breathing hard. Silence.
10.0-13.5s, THE DOWNLOAD: The download block appears. Zoom-in, then out. His arms sink slowly. Quiet, shaking: "Fourteen... hours?" He turns over his shoulder toward the camera, eyes wide and wet: "FOURTEEN HOURS, BRO!" The operator snorts. He points at the camera: "DON'T laugh."
13.5-16.5s, THE EXPLOSION: He turns back to the TV, face red, neck veins out, spit flying, pounding the rug with his free fist: "I WAITED TWELVE YEARS, SONY! TWELVE YEARS!" His voice breaks. The operator cries with laughter, the camera shakes.
16.5-22.0s, THE REASON: He goes quiet, slowly lowers himself sideways onto the rug and curls into a fetal position facing the TV, controller hugged to his chest, breathing hard. The download block stays visible above him. Operator, choking: "Bro... you good?" He does not turn his head, hoarse and dead serious: "Fourteen hours. That's why I wore it." The operator bursts out laughing, the camera dips. The picture stays lit to the last frame. End.
AUDIO & DIALOGUE: All dialogue in casual American English. The whole soundtrack must sound like an unedited real home recording made by the camcorder's built-in mic, never like AI voices, dubbing, ADR, voice-over or text-to-speech. Real people talking over each other in a small room.
VOICES:
- GAMER: a normal young man's mid-low voice, slightly nasal, raspy from shouting, casual American, a bit of mumble in quiet lines. Not a trained actor: uneven rhythm, words running together, real breath noise. His voice reaches the mic from about two and a half meters away and from his back, so it is softer, duller and full of room echo, with the high frequencies rolled off; it gets closer and clearer only when he turns toward the camera at 10.0-13.5s.
- OPERATOR: a slightly higher young man's voice, casual, about twenty centimeters from the mic, so it is loud, close, breathy and harsh, with mouth noise. He can barely talk through his own laughter: his words are squeezed out between laughs.
LINE DELIVERY:
- "Bro, are you wearing a diaper?": operator, mid-laugh, the word "diaper" breaking into a snort.
- "I'm not missing a second.": gamer, flat, fast, annoyed, not turning his head, almost mumbled.
- "SIX!" to "ONE!": each number a real scream, short and sharp, a fast inhale between them, getting louder and more strained each time; from "THREE!" on his voice cracks and distorts the mic.
- "ZEROOO!": a long full-chest scream, cracking at the end, heavily clipped.
- 9.0-10.0s: no words, only his hard, fast breathing and the PS5 fan.
- "Fourteen... hours?": barely above a whisper, shaky, a dry swallow before "hours".
- "FOURTEEN HOURS, BRO!": turned toward the camera, closer and clearer, a high desperate yell with a wet, tearful edge.
- "DON'T laugh.": gamer, sharp on "DON'T", then low and threatening on "laugh".
- "I WAITED TWELVE YEARS, SONY! TWELVE YEARS!": a full rage scream, hoarse, spit in the voice, the second "TWELVE YEARS" cracking and breaking into a sob, heavily clipped, overlapped by the fist thuds.
- "Bro... you good?": operator, choking, half a laugh, half concern, wheezing between the words.
- "Fourteen hours. That's why I wore it.": gamer, lying on the rug, quiet, hoarse, totally calm and dead serious, slightly muffled by the rug, a small sniff before "That's".
- The operator's laughter under everything: real and ugly, snorts, high wheezes, silent shaking laughter with only air, a cough from laughing; at the end an explosive laugh right into the mic that clips.
ROOM & MIC: Constant faint tape hiss and low room tone. A small carpeted room: short, soft reflections, no big echo. Handling rumble and plastic creaks whenever the camera moves or zooms; a faint zoom motor whine on each zoom. Loud screams clip and crackle. The PS5 fan whirs quietly the whole time, the TV buzzes faintly. The diaper crinkles softly whenever he moves; his knees scrape on the rug; dull heavy thuds of his fist on the rug at 13.5-16.5s; the rustle of his body settling onto the rug. No music, no sound effects that do not come from the room.
CONTINUITY: The timer reaches "00:00:00" only at 9.0s. The download block appears once at 10.0s and never changes or goes back to the timer. The TV and lamp stay on; the image never goes black. The TV is never fully hidden by his body. He faces the TV except for the turn at 10.0-13.5s. The controller stays in his hands. The headset stays on. The pizza, cans and chips stay in place. T-shirt and diaper the whole time, no pants. He ends lying on the rug.
NEGATIVE CONSTRAINTS: no cuts, no visible operator, hands, camcorder or phone, no gimbal or smooth movement, no slow motion, no music, no subtitles. No smartphone look, no HDR. TV: no redrawn interface, no centered layout, no different art, no timer jumps, no other numbers, no changing download numbers, no pop-ups, no misspelled or warped text, no screen hidden behind his head, no black screen. No glowing, shiny or lit-up diaper, no colored light on the diaper. No black controller, no pants or shorts, no nudity beyond bare legs. No theatrical acting, no model faces. Audio: no robotic, synthetic or studio-clean voices, no AI narrator tone, no perfect diction, no even volume, no dry close-miked studio voices on the gamer, no lip-sync delay. No other people on screen. No objects appearing or vanishing. No cartoonish, plastic or CGI look, no distorted hands or faces.
He waited 12 years for GTA 6 and put on a diaper so he wouldn’t miss a second
@Zyvex_0x Here's my reply to you, Pixar style, bro
Created by Seedance 2.5 on @makeugc
Save and use this PROMPT:
23-second vertical 9:16 animated comedy.
Premium theatrical 3D animation with appealing sculpted faces, expressive eyebrows and eyes, slightly exaggerated adult proportions, detailed groomed hair, tactile fabrics, soft skin shading, cinematic global illumination and convincing physical weight.
Match the character reference's visual style across the character, room, props and lighting. This is a fully animated scene, not live-action footage or a live-action background with an animated person.
REFERENCES
VIDEO REFERENCE:
Use the supplied video as the primary guide for the opening composition, physical performance, movement sequence, emotional progression, camera behavior and original audio timing.
Preserve its recognizable choreography and comedy. Replace the original man with the character from Image 1 and translate the setting into the same animated visual style.
IMAGE 1:
The identity, costume and rendering reference for the ONLY physical on-screen character.
Preserve his adult face, stocky build, tousled auburn hair, beard, expressive eyebrows, charcoal T-shirt, opaque white adult diaper with side fastening tabs, bare legs, bare feet, dark gaming headset and white-and-black controller.
The diaper is an essential nonsexual comedy prop. Do not replace it with shorts or ordinary underwear.
Image 1 does not define the opening pose or background. Begin with the gamer kneeling as in the video, not standing against the reference's neutral backdrop.
IMAGE 2:
The television screen artwork only.
Preserve its illustrated protagonists, existing logo, tropical sunset palette, composition and countdown-panel design. Keep this artwork confined to the television display.
The two illustrated people are part of a static screen image. They never become physical characters in the room.
PRIORITIES
The video controls performance, camera movement and audio timing.
Image 1 controls the gamer's appearance, clothing and animated visual style.
Image 2 controls the television artwork.
Follow the exact English dialogue provided below. Internal action timings are approximate guides; align gestures and facial reactions to the original audio without stretching, accelerating or cutting speech.
SETTING AND OPENING
A modest living room rendered in polished cinematic 3D animation. A large widescreen television stands on a low dark media console. Gray carpet, dim warm room illumination and pink-purple television light.
Begin immediately in the video's rear three-quarter handheld composition. The gamer is already kneeling close to the television, facing its screen.
His knees and shins rest on the carpet. His diaper is visible below the T-shirt. He holds the controller naturally.
An open pizza box is on his left. A blue snack bag and a beverage can are nearer the camera. A plain white game console stands beside the media unit.
Keep the prop arrangement consistent with the video and leave clear carpet beside the gamer for his final collapse.
The friend speaks from behind the camera and remains unseen throughout. Do not show the friend, their hands, their reflection or a recording device.
PERFORMANCE
The gamer is clearly an adult man in his mid-thirties.
His emotional progression:
confident anticipation,
rising excitement,
premature celebration,
disbelief,
desperate outrage,
exhausted resignation.
Use precise eye direction, expressive brows, readable mouth shapes and coordinated head, shoulder and hand movements. Exaggerate emotion without losing physical coherence.
TIMELINE
The following intervals cover the entire video. Within them, prioritize the reference audio's exact cadence and the event order described below.
00:00-00:04 | THE SETUP
The friend asks from behind the camera:
“Bro, are you wearing a diaper?”
The gamer remains focused on the television and confidently replies:
“I'm not missing a second.”
He makes small eager shifts on his knees, holding the controller and leaning toward the screen. Preserve the source video's gestures and rhythm.
The television displays Image 2. Its countdown panel shows “00:06” until the spoken countdown begins.
00:04-00:10.50 | ANTICIPATION
The gamer counts:
“Six, five, four, three, two, one, zero!”
Match the original vocal cadence. Change the existing television digits in synchronization with the spoken numbers:
Six: 00:06
Five: 00:05
Four: 00:04
Three: 00:03
Two: 00:02
One: 00:01
Zero: 00:00
Keep the surrounding artwork unchanged.
As excitement builds, he releases one hand from the controller and raises both arms, retaining the controller securely in the other hand. His free hand forms a celebratory fist.
Match the video's raised-arm performance. He stays kneeling, with grounded knees and natural torso movement.
00:10.50-00:11.10 | THE REVEAL
Immediately after the spoken “zero,” the countdown reaches 00:00 and its timer panel disappears.
A centered dark translucent download dialog appears over the unchanged television artwork.
Exact dialog text:
“Downloading”
“0%”
“14 hours remaining”
Below the text, show an empty progress-bar outline consistent with 0%.
The dialog is a flat interface element attached to the television screen, correctly following its perspective. It is not a floating object in the room.
The camera moves closer to the television as in the video. Keep “14 hours remaining” readable and unobstructed.
The gamer notices the message before reacting. His celebration stops and his arms begin to lower.
00:11.10-00:14.30 | DISBELIEF
The gamer reacts:
“Fourteen hours? Fourteen hours, bro! Don't laugh.”
The camera returns to a wider framing as he twists toward the unseen friend.
His eyes widen and his mouth opens in shock. He points toward the camera with his free hand while holding the controller in the other.
“Don't laugh” is directed at the friend behind the camera. Do not add a new reply or an invented laugh.
Keep the download dialog visible on the television behind him.
00:14.30-00:18.00 | THE BREAKDOWN
He cries:
“I waited twelve years, Sony! Twelve years!”
Match the reference's emphatic gestures and distressed facial performance. Direct his complaint toward the television, with the same brief looks toward the friend as in the source.
His frustration becomes a physical collapse. He leans forward, braces his free palm on the carpet and lowers his hip and shoulder into the clear space beside him.
Keep the controller in his other hand throughout. He holds it close to his upper chest during the descent so that it cannot pass through his body or become trapped beneath him.
Show a coherent transition from kneeling to lying on his side. No instant pose change or teleportation.
He draws his knees toward his chest. His free hand moves toward his face. The headset remains securely on his head.
The camera tilts down to follow the collapse while retaining the pizza box and part of the television.
By the friend's next question, he is curled on the carpet. He does not land on any food, packaging or the beverage can.
00:18.00-00:22.14 | THE CALLBACK
The unseen friend asks:
“Bro, you good?”
Still curled on his side, the gamer answers:
“Fourteen hours, that's why I wore it.”
Deliver the final line with tired resignation, following the source audio. His face remains sufficiently visible for readable lip synchronization. His eyes briefly turn toward the friend.
The controller remains in one hand near his chest. His free hand rests near his face. His diaper stays visible enough to connect the final line with the opening question.
He remains lying down through the end.
The television still shows the same download dialog:
“Downloading”
“0%”
“14 hours remaining”
Finish naturally after the complete final line, including the word “it.” Do not add another joke, a standing action, a fade-out or an end card.
CAMERA
Follow the source video's informal handheld camera behavior, translated into a virtual animated camera.
Use restrained handheld drift, a slightly tilted horizon, the motivated move toward the television message, the return to the facial reaction and the downward follow during the collapse.
Maintain the reference's apparent continuous handheld flow. Do not introduce new reverse angles, aerial views, spinning moves or unrelated inserts.
The television remains ahead of the gamer. The friend and camera remain behind and slightly to his side.
The audience must understand the screen message before the camera prioritizes the emotional reaction.
AUDIO
Use the supplied video soundtrack as the audio reference. Preserve its dialogue timing, vocal intensity, pauses, existing ambience, and any music or sound effects actually present.
Do not invent an additional soundtrack, narrator, laughter or new lines.
Two distinct English-speaking voices:
OFF-SCREEN FRIEND: casual and conversational.
GAMER: confident at first, then excited, shocked, distressed and finally resigned.
EXACT DIALOGUE, IN ORDER
OFF-SCREEN FRIEND:
“Bro, are you wearing a diaper?”
GAMER:
“I'm not missing a second.”
GAMER:
“Six, five, four, three, two, one, zero!”
GAMER:
“Fourteen hours? Fourteen hours, bro! Don't laugh. I waited twelve years, Sony! Twelve years!”
OFF-SCREEN FRIEND:
“Bro, you good?”
GAMER:
“Fourteen hours, that's why I wore it.”
Do not paraphrase, omit or reorder these lines.
Do not overlap speakers unless they overlap in the supplied audio.
Synchronize visible mouth movements with the gamer's speech.
The gamer's mouth does not speak the off-screen friend's lines.
No subtitles.
CONTINUITY
Only one physical character appears in the room.
The television's illustrated protagonists stay inside its static artwork.
Maintain the exact same gamer identity, body proportions, hairstyle, beard, costume and headset throughout.
The controller stays in his hands from the beginning to the end. During the raised-arm section and the collapse, it stays in the same chosen hand.
The headset and microphone remain attached and correctly positioned.
The diaper stays opaque, fastened and unchanged.
The countdown decreases only during the spoken count. After reaching zero, its panel disappears and never returns.
The download dialog appears only after zero. Progress stays at 0% for the rest of the scene.
Maintain the television artwork, furniture layout and floor-prop positions.
After the collapse, the gamer remains on the floor.
AVOID
Live-action imagery, plastic toy surfaces, changing character identity, childlike age, additional people, extra limbs, merged fingers, duplicated controllers, disappearing props, floating knees, sliding across the carpet, teleporting poses, a headset passing through the floor, costume changes, illegible interface text, a progress bar contradicting 0%, premature reactions, slow motion, accelerated speech, prolonged new pauses, added music, subtitles and end titles.
🤝 Paid partnership · 🤖 Made with AI
He waited 12 years for GTA 6 and still wasn't ready for what happened at 0
Created by Seedance 2.5 on @makeugc
Watch his face the second the screen changes. And stay for his last line, it explains everything.
Be honest, how long would you have lasted?
Prompt:👇
FORMAT: 22 seconds, vertical 9:16, one continuous handheld take, real time, no cuts. Authentic found footage shot on an early-2000s Sony DV tape camcorder: standard definition, soft optics, video noise, interlacing on motion, warm tungsten white balance, limited dynamic range, fine grain. It must feel like a real home clip that leaked online, never like a smartphone video and never like a movie. Where any line below mentions cinema cameras or lenses, this camcorder look overrides it: keep only the realism, physics, skin, texture and consistency requirements. The operator and the camcorder never appear: no hands, no body, no reflections.
CINEMATIC QUALITY (mandatory, applies to every shot of this video):
Generate this video as real live-action footage from a top-budget feature film. It must be indistinguishable from a real camera shoot and never look AI-generated, CGI-plastic or animated. Shot on ARRI Alexa 65 with sharp high-end prime lenses, cinematography in the style of Greig Fraser: motivated natural light, soft realistic shadows, true-to-life exposure, deep but detailed blacks, no blown highlights. 24 fps with natural 180-degree shutter motion blur on all movement. Native high resolution with razor-sharp focus on the subject, crisp micro-contrast and high-frequency detail on every edge, skin pore and surface texture. Subtle organic film-like grain over the whole image, stable across frames. Natural, slightly muted real-world color grade with accurate skin tones. Keep this quality consistent from the first frame to the last, with no flicker, morphing, warping or texture shimmer.
REFERENCES:
- IMAGE 1 (attached PS5 game page screenshot) is the TV screen only. It never affects the people, the room or the camera.
TV SCREEN: A real 55-inch LCD running a real PlayStation 5 shows IMAGE 1 full screen and static, with its exact left-aligned layout, artwork, colors and fonts: GTA VI icon top-left; "PS5" badge and the title "Grand Theft Auto VI: Ultimate Edition" along the top; the "VI grand theft auto" logo on the left; the description text; the white rounded timer button with a clock icon; the round "..." button; the "Friends Who Play" panel; "Official news"; the illustrated woman and man on the right half against a pink-orange sunset; the "R3 Health / Ratings / Privacy / Terms" bar bottom right. Only the timer button ever changes, in exactly two ways:
1. 0.0-3.0s it shows "00:00:06". From 3.0s the digits count down one per second: "00:00:05" at 4.0s, "00:00:04" at 5.0s, "00:00:03" at 6.0s, "00:00:02" at 7.0s, "00:00:01" at 8.0s, "00:00:00" at 9.0s.
2. At 10.0s the timer button disappears instantly and in its exact place appears a real PS5 download block: a large white "0%", under it a thin long almost empty progress bar with a tiny white sliver at the left and a dark grey track, and under the bar a small white line "14 hours remaining". Clean PlayStation-style sans-serif, perfectly spelled. It stays static until the end.
Filmed off the screen: slight LCD moire and a soft lamp reflection on the glass, but the timer and the download block stay sharp and readable.
CAMERA: His best friend films one-handed, about two and a half meters behind the gamer and to his right, camcorder held high at head height, angled slightly down. The whole TV is always visible, filling about two thirds of the frame width in the upper half; the gamer kneels low and to the left of the TV center, so his head never covers the timer or the download block. Two clumsy, overshooting zoom-ins: at 8.5s on the timer, and at 10.0s on the download block so "0%" and "14 hours remaining" fill the frame for about one second, then a jerky zoom back out. Amateur camerawork: hand shake, breathing sway, a slightly tilted horizon, late autofocus, auto-exposure pumping when the screen changes. The image shakes harder whenever the operator laughs.
REALISM: Ordinary people, no model looks. Real skin with pores, oily shine, stubble, sweat. Real physical emotion: a red face, bulging neck veins and spit on screams, wet eyes, a voice that cracks and goes hoarse. Objects have weight: the rug thuds under his fist. Light only from a warm floor lamp and the TV.
CHARACTERS:
- GAMER: about 28, average build, messy dark curly hair, light stubble. A plain black short T-shirt ending at the top of the diaper, NO pants: a bulky white adult diaper of matte cotton-like fabric with side tapes and a printed waistband, worn on bare skin. The diaper is never glowing, shiny, reflective or lit by the screen, only the same soft warm lamp light and shadow as his legs. Bare legs, bare feet. A black over-ear gaming headset. A WHITE PS5 DualSense controller. Obsessed, unhinged, loud, completely serious. A comedic, non-sexual look.
- OPERATOR: his best friend, heard only, laughing.
- No other people on screen.
SET (fixed): A small apartment at night. A 55-inch TV on a low dark wooden media stand against a beige wall, a white PS5 standing upright to its right. A warm floor lamp on the left. A grey shaggy rug. At the lower edge of the frame: an open pizza box with one slice of pizza, two unbranded energy drink cans and a bag of chips.
TIMELINE:
0.0-3.0s, THE SETUP: Timer "00:00:06". He kneels on the rug, back to the camera, the white controller gripped in both hands, rocking. The camera dips clumsily to the diaper, then back up to the TV. Operator, laughing: "Bro, are you wearing a diaper?" He, without turning: "I'm not missing a second."
3.0-9.0s, THE COUNTDOWN: He screams every number at the TV as it appears, louder each time, shoulders shaking: "SIX!" at 3.0s, "FIVE!" at 4.0s, "FOUR!" at 5.0s, "THREE!" at 6.0s, "TWO!" at 7.0s, "ONE!" at 8.0s. At 9.0s "00:00:00": "ZEROOO!", both arms raised, the controller high above his head.
9.0-10.0s, THE BEAT: Arms still raised, he freezes, breathing hard. Silence.
10.0-13.5s, THE DOWNLOAD: The download block appears. Zoom-in, then out. His arms sink slowly. Quiet, shaking: "Fourteen... hours?" He turns over his shoulder toward the camera, eyes wide and wet: "FOURTEEN HOURS, BRO!" The operator snorts. He points at the camera: "DON'T laugh."
13.5-16.5s, THE EXPLOSION: He turns back to the TV, face red, neck veins out, spit flying, pounding the rug with his free fist: "I WAITED TWELVE YEARS, SONY! TWELVE YEARS!" His voice breaks. The operator cries with laughter, the camera shakes.
16.5-22.0s, THE REASON: He goes quiet, slowly lowers himself sideways onto the rug and curls into a fetal position facing the TV, controller hugged to his chest, breathing hard. The download block stays visible above him. Operator, choking: "Bro... you good?" He does not turn his head, hoarse and dead serious: "Fourteen hours. That's why I wore it." The operator bursts out laughing, the camera dips. The picture stays lit to the last frame. End.
AUDIO & DIALOGUE: All dialogue in casual American English. The whole soundtrack must sound like an unedited real home recording made by the camcorder's built-in mic, never like AI voices, dubbing, ADR, voice-over or text-to-speech. Real people talking over each other in a small room.
VOICES:
- GAMER: a normal young man's mid-low voice, slightly nasal, raspy from shouting, casual American, a bit of mumble in quiet lines. Not a trained actor: uneven rhythm, words running together, real breath noise. His voice reaches the mic from about two and a half meters away and from his back, so it is softer, duller and full of room echo, with the high frequencies rolled off; it gets closer and clearer only when he turns toward the camera at 10.0-13.5s.
- OPERATOR: a slightly higher young man's voice, casual, about twenty centimeters from the mic, so it is loud, close, breathy and harsh, with mouth noise. He can barely talk through his own laughter: his words are squeezed out between laughs.
LINE DELIVERY:
- "Bro, are you wearing a diaper?": operator, mid-laugh, the word "diaper" breaking into a snort.
- "I'm not missing a second.": gamer, flat, fast, annoyed, not turning his head, almost mumbled.
- "SIX!" to "ONE!": each number a real scream, short and sharp, a fast inhale between them, getting louder and more strained each time; from "THREE!" on his voice cracks and distorts the mic.
- "ZEROOO!": a long full-chest scream, cracking at the end, heavily clipped.
- 9.0-10.0s: no words, only his hard, fast breathing and the PS5 fan.
- "Fourteen... hours?": barely above a whisper, shaky, a dry swallow before "hours".
- "FOURTEEN HOURS, BRO!": turned toward the camera, closer and clearer, a high desperate yell with a wet, tearful edge.
- "DON'T laugh.": gamer, sharp on "DON'T", then low and threatening on "laugh".
- "I WAITED TWELVE YEARS, SONY! TWELVE YEARS!": a full rage scream, hoarse, spit in the voice, the second "TWELVE YEARS" cracking and breaking into a sob, heavily clipped, overlapped by the fist thuds.
- "Bro... you good?": operator, choking, half a laugh, half concern, wheezing between the words.
- "Fourteen hours. That's why I wore it.": gamer, lying on the rug, quiet, hoarse, totally calm and dead serious, slightly muffled by the rug, a small sniff before "That's".
- The operator's laughter under everything: real and ugly, snorts, high wheezes, silent shaking laughter with only air, a cough from laughing; at the end an explosive laugh right into the mic that clips.
ROOM & MIC: Constant faint tape hiss and low room tone. A small carpeted room: short, soft reflections, no big echo. Handling rumble and plastic creaks whenever the camera moves or zooms; a faint zoom motor whine on each zoom. Loud screams clip and crackle. The PS5 fan whirs quietly the whole time, the TV buzzes faintly. The diaper crinkles softly whenever he moves; his knees scrape on the rug; dull heavy thuds of his fist on the rug at 13.5-16.5s; the rustle of his body settling onto the rug. No music, no sound effects that do not come from the room.
CONTINUITY: The timer reaches "00:00:00" only at 9.0s. The download block appears once at 10.0s and never changes or goes back to the timer. The TV and lamp stay on; the image never goes black. The TV is never fully hidden by his body. He faces the TV except for the turn at 10.0-13.5s. The controller stays in his hands. The headset stays on. The pizza, cans and chips stay in place. T-shirt and diaper the whole time, no pants. He ends lying on the rug.
NEGATIVE CONSTRAINTS: no cuts, no visible operator, hands, camcorder or phone, no gimbal or smooth movement, no slow motion, no music, no subtitles. No smartphone look, no HDR. TV: no redrawn interface, no centered layout, no different art, no timer jumps, no other numbers, no changing download numbers, no pop-ups, no misspelled or warped text, no screen hidden behind his head, no black screen. No glowing, shiny or lit-up diaper, no colored light on the diaper. No black controller, no pants or shorts, no nudity beyond bare legs. No theatrical acting, no model faces. Audio: no robotic, synthetic or studio-clean voices, no AI narrator tone, no perfect diction, no even volume, no dry close-miked studio voices on the gamer, no lip-sync delay. No other people on screen. No objects appearing or vanishing. No cartoonish, plastic or CGI look, no distorted hands or faces.
Trixi retweeted
This AI video looks like John Wick fought a shadow and the shadow won.
It seems to me that there is some connection between them.
Made with Seedance 2.5 on @makeugc (native 30-second video)
Prompt:
30-second horizontal 16:9 photorealistic cinematic supernatural action film.
One adult superpowered woman fights one armored human hunter aboard a moving fictional near-future service train at night.
Fast, committed stunt choreography. Realistic acceleration, weight, traction, recoil, and recovery. Multiple cinematic shots with motivated cuts. No idle posing or accelerated limb animation.
Exactly ONE cinematic slow-motion passage at 00:23.5-00:25, during a punch narrowly missing her face. All other character action plays at normal speed. Her earlier localized time power slows glass only.
Timestamps describe edited screen time. Matching cuts may compress running between established positions. Essential contact, catches, power transitions, and landings remain visible.
REFERENCES
IMAGE 1: HEROINE.
Preserve the exact adult woman shown: face, physique, hairstyle, hair colors, clips, clothing, socks, and sneakers. Multiple views depict one character.
IMAGE 2: HUNTER.
Preserve the exact man's face, hair or shaved head, facial hair, physique, armor silhouette, chest plates, forearm braces, mechanical joints, undersuit, and boots.
He is a HUMAN wearing the reference exoskeleton. His reference face stays uncovered. No helmet, robot head, visor, added weapons, or oversized replacement armor.
Images define appearance, not location or pose. No studio backgrounds, reference panels, or duplicate characters.
STYLE
Photographic skin texture, sweat, fabric weave, scratched metal, realistic reflections, and natural motion blur. Cinematic practical lighting with readable faces.
The hunter's movements show armor weight and mechanical assistance. His shoulders and elbows remain anatomically plausible.
The heroine acts while moving. Her hair and clothing respond to wind and inertia. Neutral action framing throughout.
TRAIN AND SPATIAL LAYOUT
The train travels through an OPEN industrial rail corridor at night. Passing rails, lights, and distant structures establish speed. No tunnel or passengers.
Two relevant cars:
REAR CAR: the initial fight location.
FORWARD CAR: the car directly ahead and final location.
Inside the rear car, arrange the following from rear to front:
1. The broken side window.
2. A short fighting area.
3. A glass equipment partition with an open central passage.
4. A cargo rack and cabinet near the forward exit.
The partition has a narrow metal frame and a large glass panel beside its central passage. The hunter can fall through this glass panel without blocking the entire aisle.
Shadow A lies beside the near end of the cargo rack.
Shadow B lies behind the cabinet farther forward.
Both shadows can be seen in one three-quarter wide aisle shot.
Each car has an exterior end deck. A short retractable bridge initially connects the two decks.
The FORWARD car's REAR deck is the final fighting location:
- Approximately two meters wide and two meters deep.
- Central sliding windowed door into the forward car.
- Waist-high steel railings on both sides.
- Open rear-facing transfer edge after separation.
- Fixed corner handhold and small foothold below its rear-left corner.
- Separation control beside the sliding door.
The deck remains visibly OUTDOORS, with open night sky and passing scenery at its sides.
The fictional separation system retracts the empty bridge and releases the connection. The detached rear car brakes and falls behind.
Keep the door, deck, corner supports, and railings in fixed positions.
POWER RULES
METAL MANIPULATION:
Specific gestures move or deform established metal objects. Show the material bending from its original position. Deformation remains afterward. No newly materialized bars.
KINETIC ABSORPTION:
Exactly two blocked punches charge faint branching golden light beneath the heroine's forearm skin. She still recoils.
One palm strike releases the full charge with a compact contact flash. Gold fades immediately afterward. No floating arm outlines or later recharge.
LOCAL TIME:
Only airborne glass across her route slows within a small refractive zone. Characters, camera, and train continue at normal speed.
Fragments resume their trajectories and fall when the field ends.
SHADOW TRANSIT:
One complete disappearance into shadow A followed by one emergence from shadow B. Show both locations in the same wide shot. No duplicates or transition hidden behind the hunter.
PERSONAL GRAVITY:
She reduces her weight during one exterior recovery. A strong visible foot push produces an unusually high, fast upward arc. She retains forward momentum with the train.
Normal weight returns at landing. No prolonged levitation, unsupported direction change, or ladder climbing.
TIMELINE
00:00-00:03 | WINDOW ENTRY
Begin with the heroine already starting her entry through the broken side window.
Exterior three-quarter tracking view: one hand grips the upper frame and one shoe pushes against a narrow exterior ledge. Passing rails are visible below.
Her free hand pulls inward. The obstructing SIDE section of the metal frame bends outward while the upper support remains intact.
She swings both legs through the opening and strikes the hunter's chest armor once with both shoes.
Match cut inside during the same movement. He staggers back from the window. She releases her grip, draws her knees beneath her, and lands on both feet.
Keep the contact and landing visible. No sitting on the sill, prolonged climbing, or repeated kick.
00:03-00:08 | ABSORB AND RELEASE
The hunter initially stands between the heroine and the front of the car.
He drives forward with two distinct punches. She blocks each while taking short diagonal backward steps. The first produces faint golden lines; the second intensifies them.
During the second block, she pivots around his attacking side. Both fighters turn naturally, leaving the hunter's back directed toward the nearby glass partition.
She plants her feet and delivers one open-palm strike into his chest armor.
One compact golden flash at contact. The stored glow leaves her arms completely.
He is propelled backward through the glass panel beside the central passage and lands on one knee and one hand on the forward side of the partition.
Use a shared medium-wide angle so their pivot, his alignment with the partition, the strike, and his landing are clear.
00:08-00:11 | GLASS PASSAGE
Glass scatters across the central passage ahead of the heroine.
She opens her hand, slowing the obstructing fragments inside a compact refractive zone.
She advances through a clear gap at normal speed. A side tracking view shows slowly rotating glass beside her while her feet and the background retain normal movement.
Once she clears the zone, the fragments fall behind her.
Farther ahead, the hunter visibly pushes from his hand and knee and rises with servo assistance. He remains ahead of her, near the cargo rack, between her and the exit.
00:11-00:14 | SHADOW COUNTER
One wide three-quarter shot shows:
The heroine beside shadow A.
The hunter a short distance ahead.
Shadow B beyond him, nearer the exit.
He lunges back toward her with a right punch.
She steps into shadow A and vanishes completely in a compact dark wisp.
His fist continues into the rack beside her former position. Metal dents and catches his forearm briefly.
She emerges from shadow B behind him, closer to the exit, and immediately runs forward.
Show the actual disappearance and emergence. The hunter never conceals both shadow locations.
00:14-00:18 | SEPARATION AND PURSUIT
The heroine crosses the short bridge onto the forward car's rear deck. A matching cut compresses only her approach to the bridge.
The hunter pulls his forearm free and runs after her.
She lands clear of the bridge beside the separation control. A short gesture moves its metal lever.
Cut to one exterior side wide shot showing BOTH car ends:
The empty bridge retracts.
The connection releases.
The rear car begins braking.
A small gap opens with passing rails visible beneath.
The heroine moves toward the LEFT side of the forward deck, keeping the central doorway behind her.
Before the gap becomes too wide, the hunter plants a boot on the rear car's front deck and jumps across with powered leg assistance.
Show the launch and trajectory without replay. Continue directly into his landing.
00:18-00:23 | KNOCKED OVERBOARD, GRAVITY RETURN
The hunter lands on the forward deck near its center.
Without stopping, he turns toward the heroine on his left and drives his shoulder diagonally into her upper torso. The direction of this second movement sends her toward the open rear-left corner.
She slides over the corner and catches its fixed handhold. Her shoe finds the small foothold immediately beneath it.
The hunter follows toward the rear-left edge, reaching to grab her. He does not stand waiting.
She reduces her weight, compresses her supporting leg, and pushes strongly from the foothold as she releases the handhold.
Exterior side view:
Her body rises above the left railing in one fast, unnaturally high arc, clearing the hunter's reaching arm.
She travels inward toward the door-side half of the deck.
Both shoes land behind him, between him and the doorway.
Her knees absorb the return of normal weight.
Show the complete push, rail clearance, and landing. No intermediate climbing, repeated kicking, extra flip, or hovering.
The hunter turns in reaction to her passing above his reach.
00:23-00:27 | NEAR MISS AND METAL RESTRAINT
00:23-00:23.5, normal speed:
The hunter completes his pivot toward her and throws one sweeping right punch.
She is between him and the doorway.
00:23.5-00:25, cinematic slow motion:
She bends her knees and leans her head and upper torso backward, keeping her feet planted.
His fist passes a few centimeters in front of her cheek without touching her.
Slightly oblique side close-medium shot: show the separation between fist and face, her controlled expression, his uncovered reference face, and the moving forearm.
Her spine remains natural. Hair responds to wind and movement.
This is cinematic slow motion across the whole image. It is NOT her localized time power. No refractive field, freeze, orbit, or replay.
00:25-00:27, normal speed:
The same punch completes its follow-through.
She straightens and spreads her hands.
The existing upper sections of the two side railings bend inward toward his armored forearms. His arms move outward only within comfortable human reach, with elbows slightly bent.
The metal travels the remaining distance, curls around each forearm brace, and locks mechanically.
Show rails bending from their established positions into closed restraints. No new bars appear, and no limbs stretch.
He remains standing near the rear half of the deck. His servos strain. She stays on the doorway side, with her exit clear.
00:27-00:30 | END OF THE LINE
The heroine takes one backward step into the forward car while looking at him.
She says:
“End of the line.”
She manually slides the windowed door shut.
Final view from inside through the glass:
The reference hunter stands restrained on the same OPEN EXTERIOR DECK.
His face remains uncovered.
Both bent railings are attached to the deck.
Night scenery is visible beside him.
The detached rear car recedes behind him.
End at thirty seconds. No further attack or prolonged exit.
CAMERA
Controlled energetic coverage, natural motion blur, restrained shake.
Shared medium-wide frames for the blocks, pivot, and palm strike.
Side tracking for slowed glass.
One wide frame for the shadow transition.
Exterior wide for the car separation.
Exterior side coverage for the gravity return.
Close-medium side framing for the near miss.
Wider shared framing for the rail deformation.
Maintain consistent front-to-rear train geography. Cuts continue action rather than repeat it.
No camera paths through intact walls, bodies, or metal. No cuts concealing essential impacts, catches, or landings.
AUDIO
Continuous wheel rhythm, train vibration, passing wind, footsteps, breathing, clothing movement, and armor servos.
Frame bending: stressed steel.
Two blocks: two distinct heavy impacts.
Palm discharge: one sharp low impact.
Partition: glass break.
Time field: only glass sounds stretch locally; train sound stays normal.
Shadow transit: brief low suction.
Separation: mechanical release and receding brake hiss.
Deck landing and collision: heavy boots, armor contact, shoe scrape.
Gravity return: foot push, rushing air, firm landing.
Restraint: bending steel and struggling servomotors.
Stretch the whole soundtrack only during 00:23.5-00:25. Restore normal sound with the continuing punch.
Only one spoken line, in English:
Heroine: “End of the line.”
Natural delivery and lip synchronization. No added music, narration, or subtitles.
CONTINUITY
Exactly two characters matching Images 1 and 2.
No robot replacement, helmet, extra weapons, or costume transformation.
The frame, glass partition, cargo rack, and final railings retain their damage.
The hunter visibly rises before attacking again.
Two charging blocks, one kinetic discharge.
One localized glass field.
One shadow transit.
One gravity-assisted return.
One cinematic slow-motion passage.
The rear car remains behind the forward car and stays detached.
The hunter jumps while the gap is short.
The final deck remains outdoors.
The heroine lands between the hunter and the doorway.
The restraints remain mechanically closed after she lowers her hands.
No graphic injuries, blood, merged bodies, extra limbs, floating feet, repeated impacts, text overlays, logos, split screens, or end card.
🤝 Paid partnership · 🤖 Made with AI
AI video now handles one-on-one fights better than half of Hollywood.
Honestly, I've paid to watch worse fights in theaters.
Made with Seedance 2.5 on @makeugc (native 30-second video)
Here's the prompt I used for this scene. Try it, improve it, and share your result.
PROMPT
30-second horizontal 16:9 photorealistic supernatural fight scene. Live-action feature-film quality, realistic stunt choreography, physically integrated violet VFX.
An underestimated adult woman studies a much larger underground champion, reveals supernatural power, and wins by submission.
One fight presented through multiple cinematic shots, NOT a single continuous take. Fast, committed movement with believable weight, footwork, impact, and recovery.
Exactly ONE slow-motion passage lasting 1.5 seconds of screen time during her first powered punch. All other action plays at normal speed. Timestamps describe edited screen time.
REFERENCE IMAGE 1
The supplied multi-view sheet depicts ONE adult woman from several angles. It defines her face, athletic physique, skin texture, hair, clips, clothing, socks, and sneakers.
Preserve her short tousled bob, vivid pink upper sections and cobalt-blue lower sections. Match the reference color distribution and the placement of the pale lavender hair clips. Never mirror the clips between shots.
Copy her pink and pale-lavender athletic crop top with contrasting trim and chevron detailing, pink pleated athletic skirt with pale inset panels and striped hem, white ribbed crew socks, and chunky white, pink, and lavender sneakers.
Use the reference for appearance only. No studio background, character-sheet panels, split screens, duplicated women, or static reference poses.
CHARACTERS
HEROINE:
The adult woman from Image 1. Bare hands, no added weapons or accessories. Observant and controlled. Hair and skirt respond naturally to movement; clips remain attached. Neutral action framing throughout, including grappling. Never aim beneath the skirt.
CHAMPION:
Adult man in his late thirties, exceptionally tall and muscular, approximately twice her body mass, not twice her height. Close-cropped hair, dark sleeveless shirt, gray fight trousers, athletic shoes, wrapped fists.
He attacks with aggressive forward pressure. Wide right swings expose his torso. After powered hits, he remains visibly winded and unstable. He stays conscious.
ANNOUNCER:
Lean adult man in a worn leather jacket. Microphone in his right hand, open cash envelope in his left. Inside are exactly two equal, separately banded cash bundles. He stands beside the exit gap.
ENVIRONMENT
Underground parking garage at night. Stationary cars with headlights on form an incomplete circle around an eight-meter-wide fighting area. Spectators stand at the perimeter and between cars, leaving the center clear.
The announcer stands beside an exit gap between two cars. At the opposite edge, a thin sheet-metal utility cabinet stands against a pillar, accessible through another gap. Nobody stands directly in front of it.
The fight begins beside the cabinet and moves into the open center before the takedown.
Dry, gritty concrete beneath the fighters. Damp patches only near cars. Stained pillars, exposed pipes, worn paint, dusty glass, faint haze. Cold overhead fluorescents mix with warm-white headlights. Faces remain readable.
REALISM
Real skin pores, sweat, fabric texture, muscle tension, traction, and impact recoil. Cinematic lighting with retained shadow detail.
Each strike has preparation, travel, one contact, and a consequence. Show decisive contacts and landings. Never replay a completed impact from another angle.
Her power adds controlled force to deliberate hand strikes, not accelerated limb animation. He staggers but never flies across the garage. His mass still matters during the takedown; she remains physically movable.
Sneakers plant and flex naturally. Hair, clothing, dust, and smoke obey inertia and gravity. No plastic skin, cartoon motion, game rendering, sliding feet, or weightless bodies.
VIOLET ENERGY
Luminous violet-purple with deep purple edges and near-white violet hot spots. Never blue, red, or green. Her blue hair retains its reference color and is not an energy effect.
No energy before 00:07.
Awakening starts with fingertip sparks, followed by thick purple smoke curling around hands and forearms, stopping at the elbows. Thin arcs flicker between fingers and along wrists. Tiny violet particles drift upward.
Smoke sources track the hands precisely. Smoke curls slowly relative to each hand; released wisps trail naturally. Short motion trails fade within half a second of screen time.
Energy stays dim between strikes. Each powered punch produces exactly ONE brief contact-point flash, a small particle spray, and a compact ring of air distortion. A flat violet ripple crosses the champion's shirt and dissipates without altering the fabric.
The glow lights nearby skin, clothing, metal, and glass. Original hair and clothing colors remain beneath temporary violet illumination. Her eyes only reflect light.
Energy is limited to hands and forearms. No magical knee impact. Gripping, floor contact, and money handling never trigger flashes. Effects must not hide faces, contact points, or anatomy.
No sphere, ground shockwave, glowing cracks, fire, lasers, full-body aura, sky lightning, or decorative flare overlays.
TIMELINE
00:00-00:03 | OPENING IMPACT
Start mid-attack in a three-quarter medium shot beside the cabinet, both fighters visible.
He throws a right punch toward her face. She drops her level and slips sideways. His fist passes her and strikes the thin cabinet door once, leaving a dent with a metallic crash.
Show her evasion, the missed punch, and metal contact in one connected action. The door remains attached and dented.
He withdraws his fist. She moves diagonally toward the center; he turns to pursue. The camera tracks backward, revealing headlights and laughing spectators.
The announcer calls:
“Welcome the rookie!”
Her hands are normal.
00:03-00:07 | READING HIS PATTERN
Lateral medium-wide tracking shot with both fighters and their feet visible.
He advances with a left straight followed by a wide right. She slips the straight and steps outside the right, noticing his exposed torso.
He recovers and throws another distinct wide right while pursuing her. She evades and recognizes the repeated opening.
Keep the exchange flowing with visible recovery. No posing or waiting. Her focused expression remains readable without cutting away from the action.
A spectator shouts:
“Run, rookie!”
She has not landed a strike.
00:07-00:09 | AWAKENING IN MOTION
She steps laterally while he turns toward her.
Sparks appear on her fingers. Purple smoke curls around her hands and forearms. She closes her right fist as thin arcs flicker between her fingers.
Violet light touches her jaw and nearby car paint. A low rumble builds.
He continues approaching. She watches him without stopping for a power-display pose.
00:09-00:13 | FIRST POWERED COUNTER
Three-quarter medium-wide angle showing his attacking arm, her fist, both torsos, and their feet.
00:09-00:09.7, normal speed:
He commits to another wide right. She slips inside its arc, plants her lead foot, and drives her right fist toward his exposed torso.
00:09.7-00:11.2, the ONLY slow motion:
Continue the same punch through approach, contact, and initial recoil.
Her fist visibly compresses his shirt. Exactly one violet-white flash appears at contact, edged in purple. A flat ripple crosses the fabric, with a small particle spray and compact air distortion.
His torso folds while his feet initially remain grounded. Her smoke trail follows her arm. Her short bob moves naturally. The flash stays brief and never fills the frame.
No freeze-frame, replay, or orbit.
00:11.2-00:13, normal speed:
Continue without resetting. She retracts her fist. He stumbles backward two heavy steps and catches his balance, visibly winded.
Laughter stops. Spectators recoil slightly while staying outside the fighting area.
00:13-00:17 | FOLLOW-THROUGH
She closes the short distance as he struggles to restore his guard.
One compact left-hand body punch: visible preparation, contact, and retraction. Exactly one smaller violet flash marks this second powered hit.
She grips his shoulders, bends her supporting leg, jumps, and drives one knee into his chest. Her hands remain dim while gripping. No magical flash on the knee.
Show the knee contact and her landing from a neutral side angle. She releases his shoulders and lands balanced directly in front of him.
He folds and staggers. Still winded, he reaches forward in a desperate attempt to grab her. No complete recovery or idle pause.
00:17-00:20 | TAKEDOWN
He lowers his body, catches her around the waist, and drives forward with his remaining momentum.
She recognizes the rush and stays engaged with his upper body as they descend. She remains active and prepares to continue fighting on the ground.
Use a side medium-wide shot. Show their connected descent and full landing. Her back reaches the concrete, his knees land between her legs, and his upper body remains above her.
A small puff of floor dust rises. No head impact, airborne somersault, or unexplained reversal.
As they settle, his waist grip visibly loosens and his hands move forward. Her hand energy dims to a faint flicker.
00:20-00:24 | SUBMISSION AND RELEASE
Continue directly from the established ground position.
Show a brief, coherent grappling transition: she engages one of his arms as her legs rise into a recognizable triangle submission around his neck and one shoulder. His other arm remains outside and visibly free.
Do not jump directly from both arms around her waist to a completed hold. Keep limb positions consistent and bodies anatomically separate.
Use a slightly elevated side view showing their faces and the grappling silhouette while maintaining natural clothing coverage.
He briefly tries to withdraw, then concedes. A short insert shows his free palm tapping the concrete three times.
She releases immediately. Return wider as her legs disengage and he shifts backward onto his hip, conscious and breathing heavily. She begins sitting up.
The crowd becomes silent. No extra struggle or additional attacks.
00:24-00:30 | PAYMENT
A clear editorial time cut omits her standing and walking to the announcer.
She now stands beside him at the exit-side perimeter. The champion remains seated in the background. Dust from the landing remains on her clothing and skin.
00:24-00:26:
He lowers the microphone in his right hand and offers the open envelope with his left. She takes it in her left hand.
00:26-00:29:
With her right hand, she removes one banded bundle and tosses it a short distance into his now-free left hand. The second bundle stays inside the envelope.
Looking directly at him, she says:
“For his hospital bill.”
Dry, composed delivery. He catches the money, speechless.
00:29-00:30:
Her last violet sparks fade. She turns toward the exit gap and takes one step. The closest spectators begin moving aside. End before a prolonged walk.
CAMERA AND EDITING
Controlled handheld precision, motivated tracking, natural motion blur, and restrained shake.
Favor shared medium-wide frames for attacks, a side view for the takedown, and a slightly elevated side view for grappling. Inserts communicate surrender or payment without hiding essential movements.
Maintain screen direction and established geography. Never move the camera through bodies or vehicles. Cuts must continue the action rather than repeat it.
The payment cut deliberately skips elapsed time. The fight itself retains a continuous causal sequence.
AUDIO
Natural garage reverberation, laughter, shoe traction, clothing movement, heavy breathing, metal impact, body impacts, and floor contact.
Awakening: restrained low rumble.
Active hands: subtle electric crackle.
Powered punches: one electric snap layered with each physical impact.
During the single slow-motion passage, briefly stretch and lower ambient sound. Restore normal sound when he staggers.
Crowd progression: mocking laughter, uncertainty after the first powered punch, subdued reactions during grappling, silence at surrender. No cheering afterward.
No added music. Build rhythm through movement, breathing, impacts, and reactions.
Only three spoken lines, all in English:
Announcer: “Welcome the rookie!”
Spectator: “Run, rookie!”
Heroine: “For his hospital bill.”
Natural delivery, correct speakers, accurate lip synchronization when visible.
CONTINUITY
Exactly two fighters and one heroine. Reference views never become duplicates.
Preserve her reference face, physique, short pink-and-blue bob, clips, top, pleated skirt, socks, and sneakers.
No ponytail, long hair, replacement outfit, trousers, boots, or costume transformation.
Clips never switch sides. Acquired dust remains.
The cabinet stays dented. Vehicles and lights remain fixed.
The champion stays winded after powered hits and seated after surrender.
Exactly two powered punch flashes. No magical flashes during the knee, grappling, tapping, or payment.
The envelope starts with two equal bundles; she returns one and keeps one.
No blood, graphic injuries, broken limbs, extra limbs, merged anatomy, or attacks after surrender.
No titles, subtitles, logos, split screens, or reference-sheet layouts.
This AI cartoon looks like a Pixar short that cost 99% less and took 1% of the time.
Give the girl a snack, and 99% of the drama disappears.
📢 Add this video as a reference and insert my prompt.
Prompt:
FORMAT
Approximately 17 seconds, VERTICAL 9:16. Match the duration and pacing of Video 1.
Polished cinematic 3D animated romantic comedy, matching the supplied character images: expressive stylized faces, detailed hair and clothing, soft cinematic shading, and appealing feature-animation proportions.
TASK AND REFERENCE PRIORITY
Recreate Video 1 using two completely replacement characters.
Video 1 controls the original performance: body movements, gestures, facial expressions, emotional progression, gaze directions, interactions, food handling, camera angles, framing, shot order, cuts, and timing.
Image 1 controls the replacement woman's identity, hairstyle, body proportions, and complete outfit.
Image 2 controls the replacement man's identity, hairstyle, body proportions, and complete outfit.
Make only these intended changes:
1. Completely replace the original woman with the woman from Image 1.
2. Completely replace the original man with the man from Image 2.
3. Slightly refresh the car's interior finishes.
4. Change the exterior atmosphere and cabin illumination to daytime.
The approved character replacements and daylight setting override conflicting visual details in Video 1. Preserve the source performance and story.
CHARACTER 1: WOMAN FROM IMAGE 1
Preserve her recognizable face, green eyes, freckles, lavender-purple hair, high voluminous wavy ponytail, and loose face-framing strands.
Keep her complete reference outfit:
- Open olive-green jacket.
- Cream hoodie beneath the jacket.
- Dark charcoal cargo joggers.
- Lavender-and-white chunky sneakers.
She replaces the original woman in every shot.
Her reference-image smile is not a fixed expression. At the beginning, reproduce the original woman's annoyed expression, tightly crossed arms, tense eyebrows, pursed lips, and dismissive gaze.
Animate her through the source's exact progression from irritation to reluctant eating, puffed-cheek chewing, relaxation, affection, and the final embrace.
CHARACTER 2: MAN FROM IMAGE 2
Preserve his recognizable face, tousled curly dark-brown hair, hazel eyes, thick eyebrows, light stubble, and reference body proportions.
Keep his complete reference outfit:
- Open black jacket.
- Light-gray hoodie beneath the jacket.
- Dark cargo trousers.
- Black-and-white sneakers with orange accents.
He replaces the original man in every shot.
Transfer the original man's cautious glances, concerned reactions, hopeful food presentation, expectant observation, relieved smile, bouquet presentation, and affectionate embrace onto this new character.
Do not retain the original man's muscular build, bare forearms, navy T-shirt, face, or hairstyle. Both replacement characters keep their jacket sleeves and hoodie layers during all gestures.
The image references define appearance, not standing poses, permanent smiles, or studio backgrounds. Both characters are seated and animated according to Video 1. Do not add full-body shots to display their outfits.
CAR INTERIOR AND DAYLIGHT
Preserve the original cabin geometry, seat positions, character spacing, windows, and room for movement.
Slightly refresh the finishes with warm light-gray upholstery, charcoal door trim, and subtle brushed-metal accents. Do not introduce new furniture, large accessories, or a different seating arrangement.
Maintain a consistent daytime exterior throughout. Keep the same general street setting, now naturally lit by daylight.
Soft window daylight illuminates both faces, with balanced exposure, gentle shadows, subtle warm interior bounce, and believable glass reflections.
Keep exterior details softly defocused and secondary to the characters.
No nighttime windows or dominant amber ceiling lighting.
Preserve each character's seat and physical position throughout. Match their screen positions separately for every source shot. Do not mirror the reference, swap seats, or force identical left-right framing across different camera angles.
FOOD, DRINK, AND FLOWERS
Keep the original food and drink:
- Large sesame-seed burger with the reference's visible fillings.
- French fries in a red carton.
- Partially unwrapped chocolate bar in purple packaging.
- Metallic travel mug with a dark lid.
Follow Video 1 for their scale, arrangement, grip, presentation height, and visibility in each shot.
Keep objects distinct, physically supported, and stable during movement.
Preserve the same large bouquet of pink, orange, and purple flowers, including its wrapping, scale, presentation, and position in the final embrace.
PERFORMANCE SEQUENCE
Follow the source video's actual timing and cuts. The following beats explain the action without introducing a separate timing schedule.
1. ANNOYED OPENING
Reproduce the original opening composition and gestures.
The woman crosses or holds her arms exactly as in the source, with tense eyebrows, pursed lips, and an annoyed gaze.
The man notices her mood and gives the same cautious, concerned reaction.
Do not soften her expression early.
2. FOOD PRESENTATION
The man makes the same downward lean and retrieval movement as the original, then brings the food and drink toward her.
Preserve his hand paths, torso movement, hopeful expression, and presentation timing.
Keep the food at the same practical distance from her face as in the reference.
She retains her stubborn posture.
3. RELUCTANT EATING
Match the original close-up, food arrangement, head movements, mouth movements, and comic timing.
During the hands-free fries beat, her arms remain crossed as in Video 1. She moves her mouth toward the exposed fries while the man holds the carton steady.
Show clear mouth-to-food contact before she withdraws and chews. Fries must not teleport into her mouth or pass through her face.
Preserve the contrast between eating willingly and continuing to look annoyed.
Reproduce the original puffed cheeks, eyebrow tension, and eye movements without losing her reference identity.
Do not add a burger bite, drinking action, or other eating action absent from Video 1.
4. EXPECTANT REACTION
Match the original shared framing.
The woman continues the source's chewing performance with puffed cheeks and lingering irritation.
The man watches her with the same tentative expression while maintaining the original food presentation.
Keep the original short reaction pauses. Do not extend them or add repeated chewing loops.
5. EMOTIONAL SOFTENING
Reproduce the source's gradual relaxation: the woman's eyelids, eyebrows, cheeks, and mouth settle into the original affectionate expression.
Preserve the order and timing of her glances and smile.
The man responds with the same relief and warm smile.
No abrupt switch from anger to happiness.
6. BOUQUET TRANSITION
Keep the original edit into the bouquet presentation.
Food and drink are set aside offscreen across this transition. Do not add a separate shot or extend the sequence to show this.
The bouquet is a separate physical object, never a transformation of the food.
Match the original presentation gesture and the woman's movement toward the flowers.
7. FINAL EMBRACE
Reproduce the original closing interaction.
The woman rests her head against the man, and he places his arm around her shoulders.
Match their smiles, closing eyes, body contact, bouquet placement, and final framing.
His embracing hand is free of food and drink.
Finish at the same emotional moment as Video 1, without an additional scene or end card.
CAMERA AND EDITING
Use Video 1 as the direct guide for shot order, shot size, lens perspective, camera height, movement, and cut timing.
Preserve the emphasis on facial reactions.
Keep any framing adjustment minimal and only accommodate the new character proportions and lavender ponytail.
Do not add establishing shots, character introductions, camera orbits, slow motion, speed ramps, or extra reaction shots.
AUDIO
Use the supplied video as the audio reference for its music, sound effects, and nonverbal vocal reactions, preserving their synchronization with the action.
Do not introduce new dialogue, narration, or additional music.
If intelligible source dialogue is present, render its meaning in English with matching delivery and timing.
CONTINUITY
Maintain the same faces, hairstyles, eye colors, clothing layers, and body proportions across every cut.
The woman's ponytail follows her head movement naturally. It remains attached at the same position and does not intersect the roof, seat, clothing, or the man's face.
Preserve both characters' jacket sleeves through crossed-arm poses, food handling, and the embrace.
Keep hands anatomically clear, with consistent grips and visible support for props. No merged fingers, floating packaging, or objects passing through hands.
Food only changes through visible eating, handling, or the original shot occlusion. An item outside the crop is not erased.
Do not restore consumed fries, multiply food, or change the burger's condition without a visible action.
Preserve the source's uninterrupted emotional progression.
NEGATIVE CONSTRAINTS
No original character identities or outfits.
No additional people or duplicated characters.
No seat swapping or mirrored shots.
No permanent reference-photo smiles.
No altered food menu or invented actions.
No food-to-flower morphing.
No hair-color changes, disappearing sleeves, extra limbs, or missing hands.
No nighttime atmosphere.
No live-action conversion.
No captions, subtitles, watermarks, or final text.
🤝 Paid partnership · 🤖 Made with AI
All men do this at first, and then they run away from their responsibilities.
I created this AI cartoon using Kling 4.0 on @makeugc
Prompt:
A 15-second vertical 9:16 premium stylized 3D animated comedy, matching the supplied video reference's performance, pacing, framing, and continuous-shot presentation.
Replace only the two characters and slightly redesign the kitchen. Preserve the original actions, emotions, comedy, camera behavior, and audio timing.
REFERENCE PRIORITY
The video reference controls the complete sequence of actions, exact movement timing, gestures, facial expressions, eye lines, reaction pauses, prop interactions, camera behavior, and exit choreography.
Image 1 controls the replacement woman's identity and outfit.
Image 2 controls the replacement man's identity and outfit.
The action descriptions below explain the sequence. They must not override the video's actual movements or microtiming. Do not add actions to illustrate descriptive wording.
CHARACTERS
Image 1: one adult woman in her twenties. Preserve her exact stylized face, green eyes, freckles, long wavy lavender high ponytail, loose face-framing strands, lavender ribbed camisole crop top, lavender shorts with white piping and a white drawstring, and cream fluffy slippers.
Image 2: one adult man in his twenties. Preserve his exact stylized face, brown eyes, thick eyebrows, wavy dark brown hair, light stubble, white ribbed tank top, navy shorts with white piping and a white drawstring, and gray slippers.
Use the supplied images for character design, not for frozen poses or permanent smiles. Animate both faces through the full range of expressions in the video.
Do not copy the original video's character faces, hairstyles, or clothing. Keep the replacement designs consistent throughout.
VISUAL STYLE
Use the polished stylized 3D animated-feature appearance of the supplied character images. Expressive faces, detailed hair, soft skin shading, convincing fabric textures, warm lighting, and coherent contact shadows.
Render the kitchen and props in a compatible high-quality 3D style. Preserve the video's overall lighting mood and exposure.
LOCATION CHANGE
Slightly redesign the original contemporary kitchen using muted sage-green lower cabinets, pale oak upper cabinets, a warm ivory backsplash, cream stone countertops, and brass pendant fixtures.
Keep the original functional layout, counter heights, distances, background depth, refrigerator position, and open escape route. Change finishes and small decorative details without moving obstacles into the characters' paths.
The foreground counter and wooden cutting board must retain their original placement and visual prominence. Keep the background readable and uncluttered.
CAMERA
Match the video reference's vertical composition, camera height, perspective, framing, and any subtle camera movement.
Maintain the same continuous-shot appearance. Do not introduce new cuts, close-ups, camera angles, zooms, slow motion, or speed ramps.
Do not widen the shot merely to show the characters' slippers. Their footwear remains consistent whenever their feet become visible naturally.
ACTION SEQUENCE: 00:00-00:15
Follow the source video's exact timing throughout the full 15-second sequence. Preserve the relative duration of every action, reaction, and pause.
1. OPENING
The woman starts on screen left and the man on screen right, matching the original positions and body orientations.
One whole red tomato rests on the wooden cutting board in the foreground. The woman holds the original katana and its white sheath in the same position, with the same hand assignment and grip as the source. The man starts with crossed arms and the original confident expression.
Reproduce their opening glances, smiles, head movements, and posture.
2. KATANA TRICK
Transfer the woman's exact sword-and-sheath choreography from the video, including the small blade movement, its speed, and its return to the starting state.
Preserve the original visual joke: an almost imperceptible action followed by the tomato separating. Do not embellish the movement with an additional swing, repeated strike, magical flash, or new flourish.
The tomato remains whole until the source's split cue. It then separates into exactly two halves, matching the source's direction, spacing, rotation, and settling motion.
Copy the man's reaction and the woman's satisfied expression at the same moments.
3. HANDOVER
Reproduce the original katana handover precisely. The woman presents it, the man uncrosses his arms and accepts it, then places the sheathed katana on the counter to the right of the cutting board.
Match the original grips, hand trajectories, release order, and placement timing. Maintain continuous physical contact and ownership during the transfer.
Once placed, the katana stays there for the remainder of the video.
4. WAISTBAND GESTURE
Copy the man's original self-satisfied expression and brief two-handed movement at the front of his waistband.
His replacement outfit has drawstring shorts rather than jeans. Preserve the original hand positions, trajectory, speed, and timing, adapting contact to the existing waistband area.
Do not add a separate knot-untying action, prolonged drawstring pull, zipper, belt, or clothing removal. The shorts remain securely in place.
5. SUDDEN BELLY TRANSFORMATION
At the exact transformation moment in the source video, the woman's initially flat abdomen rapidly expands into the same large rounded pregnant-belly silhouette.
Match the original onset, speed, and final size. This is the same instantaneous cartoon gag, not a new transformation sequence. Do not add particles, glowing effects, a time jump, or an explanatory action.
Only her abdomen and the necessary fabric fit change. Preserve her face, limbs, hair, and overall identity.
Her lavender camisole remains the same garment. Its hem moves naturally as needed above the expanding belly. Her shorts remain the same shorts, with the elastic waistband fitting beneath the belly. Preserve all colors, fabric details, white piping, and the drawstring. No tearing, disappearing fabric, or costume replacement.
Copy her exact downward glance, widened eyes, open mouth, head movement, and startled posture. Match the man's changing expression to the source.
6. REALIZATION AND ANGER
Reproduce the woman's original hand placements on her belly and the sequence of looks between her abdomen and the man.
Match the progression from surprise to disbelief and anger through the original eyebrow positions, eye movements, mouth shapes, head angles, and posture.
Reproduce the man's reactions at the same moments. Preserve the source's brief reaction pauses without extending or removing them.
7. RETREAT
The man raises his open palms and backs away exactly as in the source, with matching hand gestures, worried expression, body lean, and steps.
The woman tracks him with the same eyes, head movements, and angry expression.
Her belly keeps its established size and shape. It must not shrink, pulse, or grow again.
8. ESCAPE AND PURSUIT
Reproduce the man's turn and escape into the background, followed by the woman's turn and pursuit.
Match their original movement paths, order, spacing, speed, arm movements, and exit timing. Follow the original route around the kitchen rather than crossing through counters or furniture.
Preserve the replacement outfits and footwear. Adapt secondary motion naturally: the woman's long lavender ponytail follows her movements with believable inertia without changing her primary choreography or obscuring key facial reactions.
9. FINAL HOLD
Both characters leave the frame at the same moments as in the reference.
Preserve the original final hold on the empty kitchen. The two tomato halves remain on the cutting board. The sheathed katana remains on the counter where the man placed it.
End at 15 seconds without an added action, title, or end card.
AUDIO
Preserve the supplied video's original soundtrack and its synchronization with the action. Keep the existing music, vocal sounds, speech if present, sound effects, ambience, pauses, and relative levels.
Do not invent or transcribe unheard dialogue. Do not add new lines, narration, music, or sound effects. Match mouth animation to the actual source vocal track.
Keep every visual cue aligned with its corresponding sound in the original video. Do not change playback speed or introduce timing drift.
CONTINUITY
Exactly two adult characters, one katana, one matching sheath, one cutting board, and one tomato that becomes exactly two halves.
The katana's blade and sheath remain separate, coherent components with stable dimensions. Preserve their actual relationship and visibility from the video.
The tomato stays split after the trick. The katana stays on the counter after placement. The woman's belly appears only at the original cue and persists until she exits.
Maintain original handedness and screen direction. Do not mirror the choreography.
Keep faces, hairstyles, clothing, colors, body proportions, and accessories consistent. Expressions must change according to the performance.
No duplicated objects, extra limbs, detached hands, intersecting bodies, teleporting props, sliding feet, disappearing footwear, added people, subtitles, logos, or watermarks.
❗️Use this video as a reference.
This AI cartoon looks like a Pixar short that cost 99% less and took 1% of the time.
Give the girl a snack, and 99% of the drama disappears.
📢 Add this video as a reference and insert my prompt.
Prompt:
FORMAT
Approximately 17 seconds, VERTICAL 9:16. Match the duration and pacing of Video 1.
Polished cinematic 3D animated romantic comedy, matching the supplied character images: expressive stylized faces, detailed hair and clothing, soft cinematic shading, and appealing feature-animation proportions.
TASK AND REFERENCE PRIORITY
Recreate Video 1 using two completely replacement characters.
Video 1 controls the original performance: body movements, gestures, facial expressions, emotional progression, gaze directions, interactions, food handling, camera angles, framing, shot order, cuts, and timing.
Image 1 controls the replacement woman's identity, hairstyle, body proportions, and complete outfit.
Image 2 controls the replacement man's identity, hairstyle, body proportions, and complete outfit.
Make only these intended changes:
1. Completely replace the original woman with the woman from Image 1.
2. Completely replace the original man with the man from Image 2.
3. Slightly refresh the car's interior finishes.
4. Change the exterior atmosphere and cabin illumination to daytime.
The approved character replacements and daylight setting override conflicting visual details in Video 1. Preserve the source performance and story.
CHARACTER 1: WOMAN FROM IMAGE 1
Preserve her recognizable face, green eyes, freckles, lavender-purple hair, high voluminous wavy ponytail, and loose face-framing strands.
Keep her complete reference outfit:
- Open olive-green jacket.
- Cream hoodie beneath the jacket.
- Dark charcoal cargo joggers.
- Lavender-and-white chunky sneakers.
She replaces the original woman in every shot.
Her reference-image smile is not a fixed expression. At the beginning, reproduce the original woman's annoyed expression, tightly crossed arms, tense eyebrows, pursed lips, and dismissive gaze.
Animate her through the source's exact progression from irritation to reluctant eating, puffed-cheek chewing, relaxation, affection, and the final embrace.
CHARACTER 2: MAN FROM IMAGE 2
Preserve his recognizable face, tousled curly dark-brown hair, hazel eyes, thick eyebrows, light stubble, and reference body proportions.
Keep his complete reference outfit:
- Open black jacket.
- Light-gray hoodie beneath the jacket.
- Dark cargo trousers.
- Black-and-white sneakers with orange accents.
He replaces the original man in every shot.
Transfer the original man's cautious glances, concerned reactions, hopeful food presentation, expectant observation, relieved smile, bouquet presentation, and affectionate embrace onto this new character.
Do not retain the original man's muscular build, bare forearms, navy T-shirt, face, or hairstyle. Both replacement characters keep their jacket sleeves and hoodie layers during all gestures.
The image references define appearance, not standing poses, permanent smiles, or studio backgrounds. Both characters are seated and animated according to Video 1. Do not add full-body shots to display their outfits.
CAR INTERIOR AND DAYLIGHT
Preserve the original cabin geometry, seat positions, character spacing, windows, and room for movement.
Slightly refresh the finishes with warm light-gray upholstery, charcoal door trim, and subtle brushed-metal accents. Do not introduce new furniture, large accessories, or a different seating arrangement.
Maintain a consistent daytime exterior throughout. Keep the same general street setting, now naturally lit by daylight.
Soft window daylight illuminates both faces, with balanced exposure, gentle shadows, subtle warm interior bounce, and believable glass reflections.
Keep exterior details softly defocused and secondary to the characters.
No nighttime windows or dominant amber ceiling lighting.
Preserve each character's seat and physical position throughout. Match their screen positions separately for every source shot. Do not mirror the reference, swap seats, or force identical left-right framing across different camera angles.
FOOD, DRINK, AND FLOWERS
Keep the original food and drink:
- Large sesame-seed burger with the reference's visible fillings.
- French fries in a red carton.
- Partially unwrapped chocolate bar in purple packaging.
- Metallic travel mug with a dark lid.
Follow Video 1 for their scale, arrangement, grip, presentation height, and visibility in each shot.
Keep objects distinct, physically supported, and stable during movement.
Preserve the same large bouquet of pink, orange, and purple flowers, including its wrapping, scale, presentation, and position in the final embrace.
PERFORMANCE SEQUENCE
Follow the source video's actual timing and cuts. The following beats explain the action without introducing a separate timing schedule.
1. ANNOYED OPENING
Reproduce the original opening composition and gestures.
The woman crosses or holds her arms exactly as in the source, with tense eyebrows, pursed lips, and an annoyed gaze.
The man notices her mood and gives the same cautious, concerned reaction.
Do not soften her expression early.
2. FOOD PRESENTATION
The man makes the same downward lean and retrieval movement as the original, then brings the food and drink toward her.
Preserve his hand paths, torso movement, hopeful expression, and presentation timing.
Keep the food at the same practical distance from her face as in the reference.
She retains her stubborn posture.
3. RELUCTANT EATING
Match the original close-up, food arrangement, head movements, mouth movements, and comic timing.
During the hands-free fries beat, her arms remain crossed as in Video 1. She moves her mouth toward the exposed fries while the man holds the carton steady.
Show clear mouth-to-food contact before she withdraws and chews. Fries must not teleport into her mouth or pass through her face.
Preserve the contrast between eating willingly and continuing to look annoyed.
Reproduce the original puffed cheeks, eyebrow tension, and eye movements without losing her reference identity.
Do not add a burger bite, drinking action, or other eating action absent from Video 1.
4. EXPECTANT REACTION
Match the original shared framing.
The woman continues the source's chewing performance with puffed cheeks and lingering irritation.
The man watches her with the same tentative expression while maintaining the original food presentation.
Keep the original short reaction pauses. Do not extend them or add repeated chewing loops.
5. EMOTIONAL SOFTENING
Reproduce the source's gradual relaxation: the woman's eyelids, eyebrows, cheeks, and mouth settle into the original affectionate expression.
Preserve the order and timing of her glances and smile.
The man responds with the same relief and warm smile.
No abrupt switch from anger to happiness.
6. BOUQUET TRANSITION
Keep the original edit into the bouquet presentation.
Food and drink are set aside offscreen across this transition. Do not add a separate shot or extend the sequence to show this.
The bouquet is a separate physical object, never a transformation of the food.
Match the original presentation gesture and the woman's movement toward the flowers.
7. FINAL EMBRACE
Reproduce the original closing interaction.
The woman rests her head against the man, and he places his arm around her shoulders.
Match their smiles, closing eyes, body contact, bouquet placement, and final framing.
His embracing hand is free of food and drink.
Finish at the same emotional moment as Video 1, without an additional scene or end card.
CAMERA AND EDITING
Use Video 1 as the direct guide for shot order, shot size, lens perspective, camera height, movement, and cut timing.
Preserve the emphasis on facial reactions.
Keep any framing adjustment minimal and only accommodate the new character proportions and lavender ponytail.
Do not add establishing shots, character introductions, camera orbits, slow motion, speed ramps, or extra reaction shots.
AUDIO
Use the supplied video as the audio reference for its music, sound effects, and nonverbal vocal reactions, preserving their synchronization with the action.
Do not introduce new dialogue, narration, or additional music.
If intelligible source dialogue is present, render its meaning in English with matching delivery and timing.
CONTINUITY
Maintain the same faces, hairstyles, eye colors, clothing layers, and body proportions across every cut.
The woman's ponytail follows her head movement naturally. It remains attached at the same position and does not intersect the roof, seat, clothing, or the man's face.
Preserve both characters' jacket sleeves through crossed-arm poses, food handling, and the embrace.
Keep hands anatomically clear, with consistent grips and visible support for props. No merged fingers, floating packaging, or objects passing through hands.
Food only changes through visible eating, handling, or the original shot occlusion. An item outside the crop is not erased.
Do not restore consumed fries, multiply food, or change the burger's condition without a visible action.
Preserve the source's uninterrupted emotional progression.
NEGATIVE CONSTRAINTS
No original character identities or outfits.
No additional people or duplicated characters.
No seat swapping or mirrored shots.
No permanent reference-photo smiles.
No altered food menu or invented actions.
No food-to-flower morphing.
No hair-color changes, disappearing sleeves, extra limbs, or missing hands.
No nighttime atmosphere.
No live-action conversion.
No captions, subtitles, watermarks, or final text.
🤝 Paid partnership · 🤖 Made with AI
All men do this at first, and then they run away from their responsibilities.
I created this AI cartoon using Kling 4.0 on @makeugc
Prompt:
A 15-second vertical 9:16 premium stylized 3D animated comedy, matching the supplied video reference's performance, pacing, framing, and continuous-shot presentation.
Replace only the two characters and slightly redesign the kitchen. Preserve the original actions, emotions, comedy, camera behavior, and audio timing.
REFERENCE PRIORITY
The video reference controls the complete sequence of actions, exact movement timing, gestures, facial expressions, eye lines, reaction pauses, prop interactions, camera behavior, and exit choreography.
Image 1 controls the replacement woman's identity and outfit.
Image 2 controls the replacement man's identity and outfit.
The action descriptions below explain the sequence. They must not override the video's actual movements or microtiming. Do not add actions to illustrate descriptive wording.
CHARACTERS
Image 1: one adult woman in her twenties. Preserve her exact stylized face, green eyes, freckles, long wavy lavender high ponytail, loose face-framing strands, lavender ribbed camisole crop top, lavender shorts with white piping and a white drawstring, and cream fluffy slippers.
Image 2: one adult man in his twenties. Preserve his exact stylized face, brown eyes, thick eyebrows, wavy dark brown hair, light stubble, white ribbed tank top, navy shorts with white piping and a white drawstring, and gray slippers.
Use the supplied images for character design, not for frozen poses or permanent smiles. Animate both faces through the full range of expressions in the video.
Do not copy the original video's character faces, hairstyles, or clothing. Keep the replacement designs consistent throughout.
VISUAL STYLE
Use the polished stylized 3D animated-feature appearance of the supplied character images. Expressive faces, detailed hair, soft skin shading, convincing fabric textures, warm lighting, and coherent contact shadows.
Render the kitchen and props in a compatible high-quality 3D style. Preserve the video's overall lighting mood and exposure.
LOCATION CHANGE
Slightly redesign the original contemporary kitchen using muted sage-green lower cabinets, pale oak upper cabinets, a warm ivory backsplash, cream stone countertops, and brass pendant fixtures.
Keep the original functional layout, counter heights, distances, background depth, refrigerator position, and open escape route. Change finishes and small decorative details without moving obstacles into the characters' paths.
The foreground counter and wooden cutting board must retain their original placement and visual prominence. Keep the background readable and uncluttered.
CAMERA
Match the video reference's vertical composition, camera height, perspective, framing, and any subtle camera movement.
Maintain the same continuous-shot appearance. Do not introduce new cuts, close-ups, camera angles, zooms, slow motion, or speed ramps.
Do not widen the shot merely to show the characters' slippers. Their footwear remains consistent whenever their feet become visible naturally.
ACTION SEQUENCE: 00:00-00:15
Follow the source video's exact timing throughout the full 15-second sequence. Preserve the relative duration of every action, reaction, and pause.
1. OPENING
The woman starts on screen left and the man on screen right, matching the original positions and body orientations.
One whole red tomato rests on the wooden cutting board in the foreground. The woman holds the original katana and its white sheath in the same position, with the same hand assignment and grip as the source. The man starts with crossed arms and the original confident expression.
Reproduce their opening glances, smiles, head movements, and posture.
2. KATANA TRICK
Transfer the woman's exact sword-and-sheath choreography from the video, including the small blade movement, its speed, and its return to the starting state.
Preserve the original visual joke: an almost imperceptible action followed by the tomato separating. Do not embellish the movement with an additional swing, repeated strike, magical flash, or new flourish.
The tomato remains whole until the source's split cue. It then separates into exactly two halves, matching the source's direction, spacing, rotation, and settling motion.
Copy the man's reaction and the woman's satisfied expression at the same moments.
3. HANDOVER
Reproduce the original katana handover precisely. The woman presents it, the man uncrosses his arms and accepts it, then places the sheathed katana on the counter to the right of the cutting board.
Match the original grips, hand trajectories, release order, and placement timing. Maintain continuous physical contact and ownership during the transfer.
Once placed, the katana stays there for the remainder of the video.
4. WAISTBAND GESTURE
Copy the man's original self-satisfied expression and brief two-handed movement at the front of his waistband.
His replacement outfit has drawstring shorts rather than jeans. Preserve the original hand positions, trajectory, speed, and timing, adapting contact to the existing waistband area.
Do not add a separate knot-untying action, prolonged drawstring pull, zipper, belt, or clothing removal. The shorts remain securely in place.
5. SUDDEN BELLY TRANSFORMATION
At the exact transformation moment in the source video, the woman's initially flat abdomen rapidly expands into the same large rounded pregnant-belly silhouette.
Match the original onset, speed, and final size. This is the same instantaneous cartoon gag, not a new transformation sequence. Do not add particles, glowing effects, a time jump, or an explanatory action.
Only her abdomen and the necessary fabric fit change. Preserve her face, limbs, hair, and overall identity.
Her lavender camisole remains the same garment. Its hem moves naturally as needed above the expanding belly. Her shorts remain the same shorts, with the elastic waistband fitting beneath the belly. Preserve all colors, fabric details, white piping, and the drawstring. No tearing, disappearing fabric, or costume replacement.
Copy her exact downward glance, widened eyes, open mouth, head movement, and startled posture. Match the man's changing expression to the source.
6. REALIZATION AND ANGER
Reproduce the woman's original hand placements on her belly and the sequence of looks between her abdomen and the man.
Match the progression from surprise to disbelief and anger through the original eyebrow positions, eye movements, mouth shapes, head angles, and posture.
Reproduce the man's reactions at the same moments. Preserve the source's brief reaction pauses without extending or removing them.
7. RETREAT
The man raises his open palms and backs away exactly as in the source, with matching hand gestures, worried expression, body lean, and steps.
The woman tracks him with the same eyes, head movements, and angry expression.
Her belly keeps its established size and shape. It must not shrink, pulse, or grow again.
8. ESCAPE AND PURSUIT
Reproduce the man's turn and escape into the background, followed by the woman's turn and pursuit.
Match their original movement paths, order, spacing, speed, arm movements, and exit timing. Follow the original route around the kitchen rather than crossing through counters or furniture.
Preserve the replacement outfits and footwear. Adapt secondary motion naturally: the woman's long lavender ponytail follows her movements with believable inertia without changing her primary choreography or obscuring key facial reactions.
9. FINAL HOLD
Both characters leave the frame at the same moments as in the reference.
Preserve the original final hold on the empty kitchen. The two tomato halves remain on the cutting board. The sheathed katana remains on the counter where the man placed it.
End at 15 seconds without an added action, title, or end card.
AUDIO
Preserve the supplied video's original soundtrack and its synchronization with the action. Keep the existing music, vocal sounds, speech if present, sound effects, ambience, pauses, and relative levels.
Do not invent or transcribe unheard dialogue. Do not add new lines, narration, music, or sound effects. Match mouth animation to the actual source vocal track.
Keep every visual cue aligned with its corresponding sound in the original video. Do not change playback speed or introduce timing drift.
CONTINUITY
Exactly two adult characters, one katana, one matching sheath, one cutting board, and one tomato that becomes exactly two halves.
The katana's blade and sheath remain separate, coherent components with stable dimensions. Preserve their actual relationship and visibility from the video.
The tomato stays split after the trick. The katana stays on the counter after placement. The woman's belly appears only at the original cue and persists until she exits.
Maintain original handedness and screen direction. Do not mirror the choreography.
Keep faces, hairstyles, clothing, colors, body proportions, and accessories consistent. Expressions must change according to the performance.
No duplicated objects, extra limbs, detached hands, intersecting bodies, teleporting props, sliding feet, disappearing footwear, added people, subtitles, logos, or watermarks.
❗️Use this video as a reference.
This AI video proves "I'm almost ready" is the longest unit of time on Earth.
Created by Kling 4.0 on @makeugc (native 20-second video)
Prompt
FORMAT
20-second horizontal 16:9 animated comedy short in Pixar-style feature-film 3D animation. Appealing character designs, expressive faces, detailed hair and fabric, warm cinematic lighting, and precise visual comedy.
Several seasons passing during a “five-minute” wait is deliberate comedic exaggeration.
REFERENCES AND CHARACTERS
Image 1 defines the adult woman’s identity: recognizable face, curvy build, fair freckled skin, red hair, black rectangular glasses, and small earrings. Translate her into the same stylized 3D animation aesthetic as the man.
INITIAL APPEARANCE, 00:00-00:05:
Match Image 1: red hair in a loose half-up bun with loose strands, fitted red button-front top, ripped blue jeans, and white sneakers. Natural everyday makeup.
FINAL APPEARANCE, 00:12-00:20:
The SAME woman returns fully dressed for an evening out. She wears an elegant burgundy satin midi dress with a fitted waist, a tasteful V-neckline, and short sleeves, paired with black low-heeled pumps. Her red hair is now completely released from the bun and styled into polished, loose shoulder-length waves. Refined evening makeup: defined eyeliner, softly shaded eyelids, subtle blush, and deep rose lipstick. Her original black rectangular glasses and small earrings remain.
Preserve her exact facial identity, freckles, red hair color, body size, and proportions. Her makeover changes only clothing, hair styling, and makeup. She looks pleased and confident. No literal glow or magical transformation.
The makeover happens entirely off-screen inside the bedroom. Show only the two clearly defined appearances, with no intermediate costume morphing.
Image 2 defines the adult man: rounded face, heavy build, balding crown, messy brown hair at the sides, thick eyebrows, black rectangular glasses, initial short facial stubble, blue polo, brown trousers, and dark sneakers. Add an open charcoal casual jacket over his polo because he is dressed to go out.
Exactly two adult human characters and one small spider.
ENVIRONMENT AND GEOGRAPHY
A cozy apartment living room. A sofa stands beneath a broad window, with one deciduous tree clearly visible outside. The bedroom doorway is on screen right.
The sofa, window, tree, and doorway remain in fixed positions. The sofa back is low enough that the man’s shoulders and head remain clearly visible.
Start in spring daylight. Seasonal changes happen only outside. Interior furniture stays unchanged.
TIMELINE
00:00-00:03 | THE PROMISE
Medium-wide establishing shot. The woman, wearing her initial reference outfit and hairstyle, stands beside the bedroom doorway on screen right. The man stands immediately in front of the sofa, already wearing his jacket and shoes.
Looking at him, she raises one hand with five fingers spread and says with cheerful confidence:
“I’ll be ready in five minutes!”
He gives a small trusting nod. End the shot as she starts turning toward the bedroom.
00:03-00:05 | THE WAIT BEGINS
Cut to a frontal wide shot that includes the sofa, window, and bedroom doorway at the right edge.
Continue her turn without repeating it. Still wearing her red top, jeans, and white sneakers, she steps through the doorway and disappears behind its frame.
At the same time, the man bends his knees and lowers himself onto the sofa. Show his body contacting and compressing the cushion. He settles fully, shoes planted on the floor and hands resting on his thighs.
He looks toward screen right with a patient smile. Establish his seated position before the time-lapse begins.
00:05-00:12 | FIVE MINUTES LATER
Maintain the exact same locked camera position for this entire time-lapse. No cuts, zooms, or camera drift.
00:05-00:07:
Spring blossoms on the tree give way to dense green summer foliage. Warm summer light fills the window. The man’s patient smile slowly fades.
00:07-00:09:
The foliage turns orange and the leaves fall, revealing the same branches. Interior light gradually becomes softer and cooler. His initial stubble progressively thickens into a short scruffy beard. His shoulders sink slightly.
00:09-00:10:
The bare branches accumulate snow. The view settles into winter daylight. His beard reaches its final short, scruffy length and stops growing. His face, hairline, body, and apparent age remain unchanged.
00:10-00:12:
Winter stays stable outside. One small warm-brown spider descends from above the frame on a visible silk thread and lands on the man’s anatomical left shoulder, appearing on screen right in this frontal view.
Show its legs contacting the charcoal jacket before it settles. Give it enough contrast against the fabric to remain readable. It is a harmless stylized spider, not a giant creature.
The man’s head slowly tilts toward his anatomical right, screen left, away from the spider. His eyelids become heavy, but his eyes remain narrowly open at the cut. No snoring yet.
His hands stay on his thighs and his feet stay on the floor. His body moves only through gradual tired settling.
Use smooth seasonal lighting transitions without flashing or strobing day-night cycles.
00:12-00:16 | FINALLY READY
Cut to a full-length shot of the same bedroom doorway so her finished outfit and shoes are visible.
The woman steps into the living room in her FINAL APPEARANCE: burgundy satin midi dress, black low-heeled pumps, polished loose red waves, and refined evening makeup. Her black glasses and small earrings remain. She is unmistakably the same woman, with the same face and curvy build.
Her makeover is already complete when she first appears in the doorway. No clothing or hair transformation occurs on camera.
She takes one confident step into the room and settles into a small, pleased pose. Her dress and loose hair respond naturally to the movement.
Looking toward the sofa, off-screen left, she smiles and says:
“Well, shall we go?”
Leave one brief natural beat after the question. The man remains off-screen and does not answer. He falls fully asleep during this interval.
00:16-00:20 | THE PUNCHLINE
Cut to a medium close-up of the man, including his face, beard, and both shoulders.
His head remains tilted toward screen left, matching the previous sofa shot. His eyes are now fully closed. His glasses stay correctly positioned. The spider remains on his anatomical left shoulder, screen right.
He releases one soft but unmistakable snore instead of answering. His chest rises gently with breathing, and the spider makes a tiny balancing adjustment on the moving jacket.
Use a subtle camera push-in to emphasize his peacefully sleeping expression. Hold the final image long enough for the joke to register. He stays asleep until the end.
CAMERA AND PERFORMANCE
Clear framing, consistent screen direction, and restrained editing.
Normal-speed acting outside the designated time-lapse.
Keep seasonal transformations inside the continuous locked sofa shot.
Favor readable eyebrows, eye movements, posture, and small expressions.
Make the contrast between her casual initial appearance and elegant final appearance immediately visible.
Avoid frantic gestures or prolonged pauses.
AUDIO AND DIALOGUE
Exactly two spoken lines, both delivered by the woman in natural English:
“I’ll be ready in five minutes!”
“Well, shall we go?”
Accurate lip synchronization. No male dialogue or additional speech.
Quiet apartment ambience, natural footsteps, jacket rustling, and sofa compression.
Accelerated clock ticking and subtle seasonal outdoor sounds during the time-lapse.
Return to normal room ambience when the woman reappears. Her final footsteps have the light sound of low heels.
Reserve the first audible snore for the final shot.
No background music, narration, captions, logos, or end titles.
CONTINUITY
The woman stays inside the bedroom between her exit and return.
Before entering the bedroom, she wears her reference outfit and half-up bun.
After returning, she wears the burgundy dress, black pumps, loose waves, and evening makeup consistently.
Her face, body proportions, freckles, hair color, glasses, and earrings remain recognizable and unchanged.
Her original top, jeans, and sneakers remain off-screen in the bedroom after the makeover.
The man remains in the same sofa seat after sitting down.
His jacket stays open over the blue polo, and his shoes remain on.
His beard grows progressively and retains its final length.
He becomes drowsy during the time-lapse and is fully asleep in the final shot.
The spider visibly arrives and stays on the same shoulder.
His head tilts away from the spider and retains that tilt across the final cut.
Winter persists after the time-lapse.
The same tree changes season without changing its location or main branch structure.
Both humans retain the same stylized 3D visual treatment throughout.
NEGATIVE CONSTRAINTS
No replacement woman, changed facial identity, slimmer body after the makeover, missing glasses, on-camera costume morphing, or return to the initial outfit after her reveal.
No sudden elderly transformation, long white beard, skeleton transformation, duplicated people, extra limbs, disappearing spider, indoor snowfall, rearranged furniture, flickering lighting, or repeated sitting action.
🤝 Paid partnership · 🤖 Made with AI
All men do this at first, and then they run away from their responsibilities.
I created this AI cartoon using Kling 4.0 on @makeugc
Prompt:
A 15-second vertical 9:16 premium stylized 3D animated comedy, matching the supplied video reference's performance, pacing, framing, and continuous-shot presentation.
Replace only the two characters and slightly redesign the kitchen. Preserve the original actions, emotions, comedy, camera behavior, and audio timing.
REFERENCE PRIORITY
The video reference controls the complete sequence of actions, exact movement timing, gestures, facial expressions, eye lines, reaction pauses, prop interactions, camera behavior, and exit choreography.
Image 1 controls the replacement woman's identity and outfit.
Image 2 controls the replacement man's identity and outfit.
The action descriptions below explain the sequence. They must not override the video's actual movements or microtiming. Do not add actions to illustrate descriptive wording.
CHARACTERS
Image 1: one adult woman in her twenties. Preserve her exact stylized face, green eyes, freckles, long wavy lavender high ponytail, loose face-framing strands, lavender ribbed camisole crop top, lavender shorts with white piping and a white drawstring, and cream fluffy slippers.
Image 2: one adult man in his twenties. Preserve his exact stylized face, brown eyes, thick eyebrows, wavy dark brown hair, light stubble, white ribbed tank top, navy shorts with white piping and a white drawstring, and gray slippers.
Use the supplied images for character design, not for frozen poses or permanent smiles. Animate both faces through the full range of expressions in the video.
Do not copy the original video's character faces, hairstyles, or clothing. Keep the replacement designs consistent throughout.
VISUAL STYLE
Use the polished stylized 3D animated-feature appearance of the supplied character images. Expressive faces, detailed hair, soft skin shading, convincing fabric textures, warm lighting, and coherent contact shadows.
Render the kitchen and props in a compatible high-quality 3D style. Preserve the video's overall lighting mood and exposure.
LOCATION CHANGE
Slightly redesign the original contemporary kitchen using muted sage-green lower cabinets, pale oak upper cabinets, a warm ivory backsplash, cream stone countertops, and brass pendant fixtures.
Keep the original functional layout, counter heights, distances, background depth, refrigerator position, and open escape route. Change finishes and small decorative details without moving obstacles into the characters' paths.
The foreground counter and wooden cutting board must retain their original placement and visual prominence. Keep the background readable and uncluttered.
CAMERA
Match the video reference's vertical composition, camera height, perspective, framing, and any subtle camera movement.
Maintain the same continuous-shot appearance. Do not introduce new cuts, close-ups, camera angles, zooms, slow motion, or speed ramps.
Do not widen the shot merely to show the characters' slippers. Their footwear remains consistent whenever their feet become visible naturally.
ACTION SEQUENCE: 00:00-00:15
Follow the source video's exact timing throughout the full 15-second sequence. Preserve the relative duration of every action, reaction, and pause.
1. OPENING
The woman starts on screen left and the man on screen right, matching the original positions and body orientations.
One whole red tomato rests on the wooden cutting board in the foreground. The woman holds the original katana and its white sheath in the same position, with the same hand assignment and grip as the source. The man starts with crossed arms and the original confident expression.
Reproduce their opening glances, smiles, head movements, and posture.
2. KATANA TRICK
Transfer the woman's exact sword-and-sheath choreography from the video, including the small blade movement, its speed, and its return to the starting state.
Preserve the original visual joke: an almost imperceptible action followed by the tomato separating. Do not embellish the movement with an additional swing, repeated strike, magical flash, or new flourish.
The tomato remains whole until the source's split cue. It then separates into exactly two halves, matching the source's direction, spacing, rotation, and settling motion.
Copy the man's reaction and the woman's satisfied expression at the same moments.
3. HANDOVER
Reproduce the original katana handover precisely. The woman presents it, the man uncrosses his arms and accepts it, then places the sheathed katana on the counter to the right of the cutting board.
Match the original grips, hand trajectories, release order, and placement timing. Maintain continuous physical contact and ownership during the transfer.
Once placed, the katana stays there for the remainder of the video.
4. WAISTBAND GESTURE
Copy the man's original self-satisfied expression and brief two-handed movement at the front of his waistband.
His replacement outfit has drawstring shorts rather than jeans. Preserve the original hand positions, trajectory, speed, and timing, adapting contact to the existing waistband area.
Do not add a separate knot-untying action, prolonged drawstring pull, zipper, belt, or clothing removal. The shorts remain securely in place.
5. SUDDEN BELLY TRANSFORMATION
At the exact transformation moment in the source video, the woman's initially flat abdomen rapidly expands into the same large rounded pregnant-belly silhouette.
Match the original onset, speed, and final size. This is the same instantaneous cartoon gag, not a new transformation sequence. Do not add particles, glowing effects, a time jump, or an explanatory action.
Only her abdomen and the necessary fabric fit change. Preserve her face, limbs, hair, and overall identity.
Her lavender camisole remains the same garment. Its hem moves naturally as needed above the expanding belly. Her shorts remain the same shorts, with the elastic waistband fitting beneath the belly. Preserve all colors, fabric details, white piping, and the drawstring. No tearing, disappearing fabric, or costume replacement.
Copy her exact downward glance, widened eyes, open mouth, head movement, and startled posture. Match the man's changing expression to the source.
6. REALIZATION AND ANGER
Reproduce the woman's original hand placements on her belly and the sequence of looks between her abdomen and the man.
Match the progression from surprise to disbelief and anger through the original eyebrow positions, eye movements, mouth shapes, head angles, and posture.
Reproduce the man's reactions at the same moments. Preserve the source's brief reaction pauses without extending or removing them.
7. RETREAT
The man raises his open palms and backs away exactly as in the source, with matching hand gestures, worried expression, body lean, and steps.
The woman tracks him with the same eyes, head movements, and angry expression.
Her belly keeps its established size and shape. It must not shrink, pulse, or grow again.
8. ESCAPE AND PURSUIT
Reproduce the man's turn and escape into the background, followed by the woman's turn and pursuit.
Match their original movement paths, order, spacing, speed, arm movements, and exit timing. Follow the original route around the kitchen rather than crossing through counters or furniture.
Preserve the replacement outfits and footwear. Adapt secondary motion naturally: the woman's long lavender ponytail follows her movements with believable inertia without changing her primary choreography or obscuring key facial reactions.
9. FINAL HOLD
Both characters leave the frame at the same moments as in the reference.
Preserve the original final hold on the empty kitchen. The two tomato halves remain on the cutting board. The sheathed katana remains on the counter where the man placed it.
End at 15 seconds without an added action, title, or end card.
AUDIO
Preserve the supplied video's original soundtrack and its synchronization with the action. Keep the existing music, vocal sounds, speech if present, sound effects, ambience, pauses, and relative levels.
Do not invent or transcribe unheard dialogue. Do not add new lines, narration, music, or sound effects. Match mouth animation to the actual source vocal track.
Keep every visual cue aligned with its corresponding sound in the original video. Do not change playback speed or introduce timing drift.
CONTINUITY
Exactly two adult characters, one katana, one matching sheath, one cutting board, and one tomato that becomes exactly two halves.
The katana's blade and sheath remain separate, coherent components with stable dimensions. Preserve their actual relationship and visibility from the video.
The tomato stays split after the trick. The katana stays on the counter after placement. The woman's belly appears only at the original cue and persists until she exits.
Maintain original handedness and screen direction. Do not mirror the choreography.
Keep faces, hairstyles, clothing, colors, body proportions, and accessories consistent. Expressions must change according to the performance.
No duplicated objects, extra limbs, detached hands, intersecting bodies, teleporting props, sliding feet, disappearing footwear, added people, subtitles, logos, or watermarks.
❗️Use this video as a reference.
All men do this at first, and then they run away from their responsibilities.
I created this AI cartoon using Kling 4.0 on @makeugc
Prompt:
A 15-second vertical 9:16 premium stylized 3D animated comedy, matching the supplied video reference's performance, pacing, framing, and continuous-shot presentation.
Replace only the two characters and slightly redesign the kitchen. Preserve the original actions, emotions, comedy, camera behavior, and audio timing.
REFERENCE PRIORITY
The video reference controls the complete sequence of actions, exact movement timing, gestures, facial expressions, eye lines, reaction pauses, prop interactions, camera behavior, and exit choreography.
Image 1 controls the replacement woman's identity and outfit.
Image 2 controls the replacement man's identity and outfit.
The action descriptions below explain the sequence. They must not override the video's actual movements or microtiming. Do not add actions to illustrate descriptive wording.
CHARACTERS
Image 1: one adult woman in her twenties. Preserve her exact stylized face, green eyes, freckles, long wavy lavender high ponytail, loose face-framing strands, lavender ribbed camisole crop top, lavender shorts with white piping and a white drawstring, and cream fluffy slippers.
Image 2: one adult man in his twenties. Preserve his exact stylized face, brown eyes, thick eyebrows, wavy dark brown hair, light stubble, white ribbed tank top, navy shorts with white piping and a white drawstring, and gray slippers.
Use the supplied images for character design, not for frozen poses or permanent smiles. Animate both faces through the full range of expressions in the video.
Do not copy the original video's character faces, hairstyles, or clothing. Keep the replacement designs consistent throughout.
VISUAL STYLE
Use the polished stylized 3D animated-feature appearance of the supplied character images. Expressive faces, detailed hair, soft skin shading, convincing fabric textures, warm lighting, and coherent contact shadows.
Render the kitchen and props in a compatible high-quality 3D style. Preserve the video's overall lighting mood and exposure.
LOCATION CHANGE
Slightly redesign the original contemporary kitchen using muted sage-green lower cabinets, pale oak upper cabinets, a warm ivory backsplash, cream stone countertops, and brass pendant fixtures.
Keep the original functional layout, counter heights, distances, background depth, refrigerator position, and open escape route. Change finishes and small decorative details without moving obstacles into the characters' paths.
The foreground counter and wooden cutting board must retain their original placement and visual prominence. Keep the background readable and uncluttered.
CAMERA
Match the video reference's vertical composition, camera height, perspective, framing, and any subtle camera movement.
Maintain the same continuous-shot appearance. Do not introduce new cuts, close-ups, camera angles, zooms, slow motion, or speed ramps.
Do not widen the shot merely to show the characters' slippers. Their footwear remains consistent whenever their feet become visible naturally.
ACTION SEQUENCE: 00:00-00:15
Follow the source video's exact timing throughout the full 15-second sequence. Preserve the relative duration of every action, reaction, and pause.
1. OPENING
The woman starts on screen left and the man on screen right, matching the original positions and body orientations.
One whole red tomato rests on the wooden cutting board in the foreground. The woman holds the original katana and its white sheath in the same position, with the same hand assignment and grip as the source. The man starts with crossed arms and the original confident expression.
Reproduce their opening glances, smiles, head movements, and posture.
2. KATANA TRICK
Transfer the woman's exact sword-and-sheath choreography from the video, including the small blade movement, its speed, and its return to the starting state.
Preserve the original visual joke: an almost imperceptible action followed by the tomato separating. Do not embellish the movement with an additional swing, repeated strike, magical flash, or new flourish.
The tomato remains whole until the source's split cue. It then separates into exactly two halves, matching the source's direction, spacing, rotation, and settling motion.
Copy the man's reaction and the woman's satisfied expression at the same moments.
3. HANDOVER
Reproduce the original katana handover precisely. The woman presents it, the man uncrosses his arms and accepts it, then places the sheathed katana on the counter to the right of the cutting board.
Match the original grips, hand trajectories, release order, and placement timing. Maintain continuous physical contact and ownership during the transfer.
Once placed, the katana stays there for the remainder of the video.
4. WAISTBAND GESTURE
Copy the man's original self-satisfied expression and brief two-handed movement at the front of his waistband.
His replacement outfit has drawstring shorts rather than jeans. Preserve the original hand positions, trajectory, speed, and timing, adapting contact to the existing waistband area.
Do not add a separate knot-untying action, prolonged drawstring pull, zipper, belt, or clothing removal. The shorts remain securely in place.
5. SUDDEN BELLY TRANSFORMATION
At the exact transformation moment in the source video, the woman's initially flat abdomen rapidly expands into the same large rounded pregnant-belly silhouette.
Match the original onset, speed, and final size. This is the same instantaneous cartoon gag, not a new transformation sequence. Do not add particles, glowing effects, a time jump, or an explanatory action.
Only her abdomen and the necessary fabric fit change. Preserve her face, limbs, hair, and overall identity.
Her lavender camisole remains the same garment. Its hem moves naturally as needed above the expanding belly. Her shorts remain the same shorts, with the elastic waistband fitting beneath the belly. Preserve all colors, fabric details, white piping, and the drawstring. No tearing, disappearing fabric, or costume replacement.
Copy her exact downward glance, widened eyes, open mouth, head movement, and startled posture. Match the man's changing expression to the source.
6. REALIZATION AND ANGER
Reproduce the woman's original hand placements on her belly and the sequence of looks between her abdomen and the man.
Match the progression from surprise to disbelief and anger through the original eyebrow positions, eye movements, mouth shapes, head angles, and posture.
Reproduce the man's reactions at the same moments. Preserve the source's brief reaction pauses without extending or removing them.
7. RETREAT
The man raises his open palms and backs away exactly as in the source, with matching hand gestures, worried expression, body lean, and steps.
The woman tracks him with the same eyes, head movements, and angry expression.
Her belly keeps its established size and shape. It must not shrink, pulse, or grow again.
8. ESCAPE AND PURSUIT
Reproduce the man's turn and escape into the background, followed by the woman's turn and pursuit.
Match their original movement paths, order, spacing, speed, arm movements, and exit timing. Follow the original route around the kitchen rather than crossing through counters or furniture.
Preserve the replacement outfits and footwear. Adapt secondary motion naturally: the woman's long lavender ponytail follows her movements with believable inertia without changing her primary choreography or obscuring key facial reactions.
9. FINAL HOLD
Both characters leave the frame at the same moments as in the reference.
Preserve the original final hold on the empty kitchen. The two tomato halves remain on the cutting board. The sheathed katana remains on the counter where the man placed it.
End at 15 seconds without an added action, title, or end card.
AUDIO
Preserve the supplied video's original soundtrack and its synchronization with the action. Keep the existing music, vocal sounds, speech if present, sound effects, ambience, pauses, and relative levels.
Do not invent or transcribe unheard dialogue. Do not add new lines, narration, music, or sound effects. Match mouth animation to the actual source vocal track.
Keep every visual cue aligned with its corresponding sound in the original video. Do not change playback speed or introduce timing drift.
CONTINUITY
Exactly two adult characters, one katana, one matching sheath, one cutting board, and one tomato that becomes exactly two halves.
The katana's blade and sheath remain separate, coherent components with stable dimensions. Preserve their actual relationship and visibility from the video.
The tomato stays split after the trick. The katana stays on the counter after placement. The woman's belly appears only at the original cue and persists until she exits.
Maintain original handedness and screen direction. Do not mirror the choreography.
Keep faces, hairstyles, clothing, colors, body proportions, and accessories consistent. Expressions must change according to the performance.
No duplicated objects, extra limbs, detached hands, intersecting bodies, teleporting props, sliding feet, disappearing footwear, added people, subtitles, logos, or watermarks.
❗️Use this video as a reference.
🤝 Paid partnership · 🤖 Made with AI
This AI cartoon just showed what a healthy relationship between a man and a woman should look like.
Created by Kling 4.0 on @makeugc
Workflow + prompt:
- Download a video reference
- Create 2 photo references
- Add the PROMPT:
FORMAT
Create a premium Pixar-style 3D animated bathroom comedy using the supplied video as the direct performance reference.
Match Video 1's full duration, approximately 14.5 seconds, vertical 9:16 composition, playback speed and original action sequence. Replace only the two characters and make the minor bathroom decor changes specified below.
REFERENCE ROLES
Video 1: master reference for the complete performance, action timing, facial expressions, body movements, prop handling, spatial composition, camera behavior and audio.
Image 1: appearance reference for the replacement woman.
Image 2: appearance reference for the replacement man.
Transfer the original woman's performance to the woman from Image 1.
Transfer the original man's performance to the man from Image 2.
The photos control character appearance and clothing only. Do not copy their neutral standing poses, studio backgrounds or full-body framing into the video.
PRIORITY
Use Image 1 and Image 2 for character identity, hairstyle, colors and clothing.
Use Video 1 for all actions, expressions, timing, framing and interaction.
Only the bathroom finishes may change as described below.
Do not reinterpret the scene or invent additional actions.
WOMAN
The same beautiful 25-year-old adult woman from Image 1.
Preserve her exact face, green eyes, freckles, skin tone and adult proportions.
Preserve her pastel-lavender high wavy ponytail, including its volume, length and loose face-framing strands.
Preserve her ivory long-sleeve henley, sage-green lounge trousers and cream slippers wherever visible.
Do not replace her ponytail with the original woman's dark bun.
Her facial expression must follow the video performance, not remain fixed in the reference photo's smile.
MAN
The same 25-year-old adult man from Image 2.
Preserve his exact face, hazel eyes, tousled dark-brown wavy hair, eyebrows, light stubble and adult proportions.
Preserve his navy short-sleeve T-shirt, taupe lounge trousers and dark-gray slippers wherever visible.
His expression must follow the video performance, not remain fixed in the reference photo's smile.
EXACT PERFORMANCE MATCH
Use Video 1 as the continuous motion and expression guide from its first frame to its last.
Match each character's:
- Head position, tilt, turn and forward lean.
- Gaze direction, blinks, eyelid movement and eye widening.
- Eyebrow movement, mouth opening, lip pursing, smiles and annoyed reactions.
- Shoulder movement, arm trajectory, wrist rotation and finger gesture.
- Hand-to-face contact and interaction with grooming tools.
- Start and end timing of every gesture.
- Original brief pauses and reaction delays.
Preserve the original timing difference between the woman's actions and the man's imitations. Do not make them move in perfect synchronization unless they do so in the source.
The man imitates only at the moments shown in Video 1. At other moments, reproduce his watching behavior and facial reactions. Do not invent continuous mirroring.
Preserve the full movement paths, not merely a few key poses. Keep the action flowing naturally between them.
Do not add pauses, accelerate gestures, prolong reactions or repeat completed movements.
ACTION ANCHORS
These anchors identify the source actions, not a replacement timeline. Their timing, order, duration and detailed execution must come directly from Video 1.
Opening:
The woman applies mascara near her eye with the original wide-eyed, open-mouth expression.
The man stands behind her toward screen-right and imitates her using his empty hand.
Reproduce the exact moment when she lowers the wand and reacts.
Middle:
Match her downward glance and displeased expression, his amused reaction and the original transition from mascara to the blue razor.
Reproduce her grooming movements around the chin, cheek and upper-lip area.
Match how her free hand stretches her cheek and how her mouth changes shape.
Preserve the man's original watching expressions throughout.
Ending:
Reproduce his finger gesture near his own upper lip, her reaction, their final gaze shifts and her reach toward screen-right.
End on the same phase of her movement toward the counter as the source.
Do not add a new ending, punchline, embrace or final pose.
CAMERA AND SPATIAL COMPOSITION
Match Video 1's camera position, perspective, framing and near-static composition.
Keep the woman in the foreground and the man behind her, offset toward screen-right, with the same relative screen positions and apparent sizes as the source.
Preserve visibility of their faces and hands at the same moments as in Video 1.
Do not widen to a full-body view because the character photos show full bodies.
Preserve the original screen orientation and hand assignments. Do not horizontally flip the scene.
Reproduce only the mirror presentation already visible in Video 1.
Do not add a new mirror, a reverse angle, an over-the-shoulder view or a second reflected copy of either character.
No visible camera or camera operator.
Follow the source camera behavior and any source edits. Do not introduce additional cuts, zooms, pans or camera shake.
BATHROOM
Keep the original room layout and functional geometry:
- Vanity counter in the foreground.
- Wooden storage toward screen-left.
- Window toward screen-right.
- The same available space for grooming gestures.
- Essential props in positions consistent with the original hand movements.
Make only these subtle decorative changes:
Muted sage-green wall tiles, pale oak cabinetry and a warm ivory stone countertop.
Keep the original arrangement of grooming bottles, dispensers and the toothbrush cup sufficiently similar that every reach and prop interaction remains logical.
Do not add objects that obscure faces or interfere with hand movements.
Preserve the original lighting direction and overall brightness, with soft daylight from screen-right and gentle warm interior fill.
VISUAL QUALITY
Premium Pixar-style feature animation matching the two character images.
Detailed hair strands, expressive facial animation, soft skin shading, fabric texture and stable contact shadows.
Adapt the original performance to the new facial proportions while preserving expression, intensity and timing.
Maintain stable facial identity during extreme mouth and eye expressions.
The ponytail responds naturally to the woman's movements with restrained secondary motion. It must not obscure important facial expressions or interfere with her grooming tools.
PROP AND ANATOMY CONTINUITY
Exactly two characters.
The woman uses the mascara wand and then the blue razor according to Video 1.
The man performs his imitation with an empty hand. Do not give him grooming tools.
Match the source hand used for each action.
Keep tools consistently attached to the correct grip.
Preserve each object's size, shape and color.
The mascara wand must not transform into the razor. Follow the source's lowering and pickup transition.
Objects leaving the frame must remain spatially consistent when they reappear.
Maintain coherent wrists, elbows and fingers.
No floating tools, duplicated props, bending razor handles, merged hands or tools passing through skin.
Transfer intentional gestures without reproducing accidental source deformations.
AUDIO
Use Video 1's original audio as the audio reference.
Preserve its timing and synchronization with the performance.
Do not add new dialogue, narration, music or sound effects.
NEGATIVE CONSTRAINTS
No new actions or rewritten comedy.
No additional characters.
No character identity changes.
No hairstyle, hair-color, eye-color or outfit changes.
No forced permanent smiles.
No additional pauses or repeated gestures.
No slow motion, speed ramps or fast-forward.
No new camera angles or transitions.
No subtitles, captions, logos or end cards.
This AI cartoon just showed what a healthy relationship between a man and a woman should look like.
Created by Kling 4.0 on @makeugc
Workflow + prompt:
- Download a video reference
- Create 2 photo references
- Add the PROMPT:
FORMAT
Create a premium Pixar-style 3D animated bathroom comedy using the supplied video as the direct performance reference.
Match Video 1's full duration, approximately 14.5 seconds, vertical 9:16 composition, playback speed and original action sequence. Replace only the two characters and make the minor bathroom decor changes specified below.
REFERENCE ROLES
Video 1: master reference for the complete performance, action timing, facial expressions, body movements, prop handling, spatial composition, camera behavior and audio.
Image 1: appearance reference for the replacement woman.
Image 2: appearance reference for the replacement man.
Transfer the original woman's performance to the woman from Image 1.
Transfer the original man's performance to the man from Image 2.
The photos control character appearance and clothing only. Do not copy their neutral standing poses, studio backgrounds or full-body framing into the video.
PRIORITY
Use Image 1 and Image 2 for character identity, hairstyle, colors and clothing.
Use Video 1 for all actions, expressions, timing, framing and interaction.
Only the bathroom finishes may change as described below.
Do not reinterpret the scene or invent additional actions.
WOMAN
The same beautiful 25-year-old adult woman from Image 1.
Preserve her exact face, green eyes, freckles, skin tone and adult proportions.
Preserve her pastel-lavender high wavy ponytail, including its volume, length and loose face-framing strands.
Preserve her ivory long-sleeve henley, sage-green lounge trousers and cream slippers wherever visible.
Do not replace her ponytail with the original woman's dark bun.
Her facial expression must follow the video performance, not remain fixed in the reference photo's smile.
MAN
The same 25-year-old adult man from Image 2.
Preserve his exact face, hazel eyes, tousled dark-brown wavy hair, eyebrows, light stubble and adult proportions.
Preserve his navy short-sleeve T-shirt, taupe lounge trousers and dark-gray slippers wherever visible.
His expression must follow the video performance, not remain fixed in the reference photo's smile.
EXACT PERFORMANCE MATCH
Use Video 1 as the continuous motion and expression guide from its first frame to its last.
Match each character's:
- Head position, tilt, turn and forward lean.
- Gaze direction, blinks, eyelid movement and eye widening.
- Eyebrow movement, mouth opening, lip pursing, smiles and annoyed reactions.
- Shoulder movement, arm trajectory, wrist rotation and finger gesture.
- Hand-to-face contact and interaction with grooming tools.
- Start and end timing of every gesture.
- Original brief pauses and reaction delays.
Preserve the original timing difference between the woman's actions and the man's imitations. Do not make them move in perfect synchronization unless they do so in the source.
The man imitates only at the moments shown in Video 1. At other moments, reproduce his watching behavior and facial reactions. Do not invent continuous mirroring.
Preserve the full movement paths, not merely a few key poses. Keep the action flowing naturally between them.
Do not add pauses, accelerate gestures, prolong reactions or repeat completed movements.
ACTION ANCHORS
These anchors identify the source actions, not a replacement timeline. Their timing, order, duration and detailed execution must come directly from Video 1.
Opening:
The woman applies mascara near her eye with the original wide-eyed, open-mouth expression.
The man stands behind her toward screen-right and imitates her using his empty hand.
Reproduce the exact moment when she lowers the wand and reacts.
Middle:
Match her downward glance and displeased expression, his amused reaction and the original transition from mascara to the blue razor.
Reproduce her grooming movements around the chin, cheek and upper-lip area.
Match how her free hand stretches her cheek and how her mouth changes shape.
Preserve the man's original watching expressions throughout.
Ending:
Reproduce his finger gesture near his own upper lip, her reaction, their final gaze shifts and her reach toward screen-right.
End on the same phase of her movement toward the counter as the source.
Do not add a new ending, punchline, embrace or final pose.
CAMERA AND SPATIAL COMPOSITION
Match Video 1's camera position, perspective, framing and near-static composition.
Keep the woman in the foreground and the man behind her, offset toward screen-right, with the same relative screen positions and apparent sizes as the source.
Preserve visibility of their faces and hands at the same moments as in Video 1.
Do not widen to a full-body view because the character photos show full bodies.
Preserve the original screen orientation and hand assignments. Do not horizontally flip the scene.
Reproduce only the mirror presentation already visible in Video 1.
Do not add a new mirror, a reverse angle, an over-the-shoulder view or a second reflected copy of either character.
No visible camera or camera operator.
Follow the source camera behavior and any source edits. Do not introduce additional cuts, zooms, pans or camera shake.
BATHROOM
Keep the original room layout and functional geometry:
- Vanity counter in the foreground.
- Wooden storage toward screen-left.
- Window toward screen-right.
- The same available space for grooming gestures.
- Essential props in positions consistent with the original hand movements.
Make only these subtle decorative changes:
Muted sage-green wall tiles, pale oak cabinetry and a warm ivory stone countertop.
Keep the original arrangement of grooming bottles, dispensers and the toothbrush cup sufficiently similar that every reach and prop interaction remains logical.
Do not add objects that obscure faces or interfere with hand movements.
Preserve the original lighting direction and overall brightness, with soft daylight from screen-right and gentle warm interior fill.
VISUAL QUALITY
Premium Pixar-style feature animation matching the two character images.
Detailed hair strands, expressive facial animation, soft skin shading, fabric texture and stable contact shadows.
Adapt the original performance to the new facial proportions while preserving expression, intensity and timing.
Maintain stable facial identity during extreme mouth and eye expressions.
The ponytail responds naturally to the woman's movements with restrained secondary motion. It must not obscure important facial expressions or interfere with her grooming tools.
PROP AND ANATOMY CONTINUITY
Exactly two characters.
The woman uses the mascara wand and then the blue razor according to Video 1.
The man performs his imitation with an empty hand. Do not give him grooming tools.
Match the source hand used for each action.
Keep tools consistently attached to the correct grip.
Preserve each object's size, shape and color.
The mascara wand must not transform into the razor. Follow the source's lowering and pickup transition.
Objects leaving the frame must remain spatially consistent when they reappear.
Maintain coherent wrists, elbows and fingers.
No floating tools, duplicated props, bending razor handles, merged hands or tools passing through skin.
Transfer intentional gestures without reproducing accidental source deformations.
AUDIO
Use Video 1's original audio as the audio reference.
Preserve its timing and synchronization with the performance.
Do not add new dialogue, narration, music or sound effects.
NEGATIVE CONSTRAINTS
No new actions or rewritten comedy.
No additional characters.
No character identity changes.
No hairstyle, hair-color, eye-color or outfit changes.
No forced permanent smiles.
No additional pauses or repeated gestures.
No slow motion, speed ramps or fast-forward.
No new camera angles or transitions.
No subtitles, captions, logos or end cards.
🤝 Paid partnership · 🤖 Made with AI
This AI video is an absolute masterpiece.
GTA 6 vs love - the answer is obvious🎮🩷
Created by Seedance 2.5 on @makeugc
Workflow + prompt:
- Download a video reference
- Create 3 photo references
- Add the PROMPT:
FORMAT
25-second VERTICAL 9:16 cinematic 3D animated comedy in Pixar style.
Adapt the supplied reference video's narrative, movements, emotions, reactions, camera work and music using exactly THREE principal characters.
Render the entire video in a cohesive Pixar-style animated aesthetic, including characters, escalators, shopping mall, props and living-room fantasy.
REFERENCES
video1 = source choreography, expressions, emotional progression, camera work, editing rhythm and original music, subject to the three-character adaptation below.
image1 = the heavy, balding PS5 shopper on the LEFT escalator.
image2 = the woman in the couple on the adjacent escalator.
image3 = her male companion.
These are the only three character image references.
Preserve each image's exact animated face, hairstyle, physique, clothing, footwear, accessories and colors.
Use the images for identity and wardrobe, not frozen poses.
Transfer the corresponding source performances onto these characters.
THREE-CHARACTER ADAPTATION
The heavy shopper from image1 is the ONLY featured shopper on the left descending escalator.
Remove the source video's second, slim shopper, positioned higher up and behind the heavy shopper on the same left escalator. Remove his PS5 box, shopping bag and separate passage completely.
Do not replace him with another person.
Remove shots and reactions that depend exclusively on his presence.
All of the couple's man's purchase-related attention is directed toward the heavy shopper and HIS PS5 box and shopping bag.
Preserve the remaining source story, including the living-room fantasy, appliance-box handover, crossing attempt, interruption, seated landing and final comic payoff.
CHARACTERS
image1:
The heavy, balding shopper. Preserve his exact reference design and body proportions. He carries one PS5 Pro / GTA VI box and one doll-window shopping bag.
image2:
The woman accompanying image3. Preserve her exact reference appearance and outfit throughout. Transfer the source woman's gestures, attention shifts, reactions and final interaction to her.
image3:
The woman's male companion. Preserve his exact reference appearance and outfit throughout.
He performs the source man's curious looks, temptation, gaming fantasy, distracted reactions, attempted crossing and embarrassed final response.
The man in the fantasy is also image3, wearing the SAME outfit.
No identity swaps, costume changes or additional principal characters.
VISUAL STYLE
High-quality Pixar-style 3D animation with expressive eyes, appealing facial shapes, carefully groomed hair, detailed fabrics and cinematic lighting.
Match the supplied character images consistently in close-ups, profiles and wide shots.
All environments and objects share the same stylized rendering.
Use clear facial acting while preserving the source emotions and comic timing.
Maintain convincing body weight, natural gestures, balance shifts, grounded feet and subtle secondary motion.
The heavy shopper retains his reference physique. Do not slim him down during movement.
No rubbery limbs, floating bodies or excessive squash-and-stretch.
Normal movement speed. No slow motion, fast-forward or speed ramps.
PS5 BOX AND SHOPPING BAG
In the real mall scene, the heavy shopper carries exactly:
- ONE rigid PS5 Pro retail box.
- ONE black “Be happy” shopping bag.
The front of the console box clearly displays:
- “PS5 Pro” branding.
- A white PS5 Pro console product image.
- Grand Theft Auto VI cover artwork.
- Recognizable “grand theft auto” lettering and the Roman numeral “VI”.
The game is GTA VI, meaning GTA 6. Never GTA V.
The artwork is physically printed on the packaging.
Preserve the prop designs from image1, subject to this explicit branding requirement.
The bag has a real oval window cut through its front panel.
Inside is the three-dimensional manufactured doll head from image1.
The doll's face is recessed behind the panel, visible through the opening.
Show cut edges, interior depth, occlusion and shadows.
The doll face is NOT printed on the bag.
It remains an inanimate object with a fixed expression.
No blinking, talking or independent movement.
Follow the source heavy shopper's hand assignments and carrying choreography.
Hands grip the box and bag handles securely.
The box stays rigid. The bag swings subtly with his movement.
Do not create a second PS5 box or second shopping bag in the real mall scene.
APPLIANCE BOX
Preserve the couple's tall green-and-white household-appliance box from video1, rendered in the same animated style.
Keep its source carrying positions and visible handover before the man's crossing attempt.
This is a household-appliance box, not a PS5 box.
During the handover, the woman's receiving grip becomes secure before the man releases it.
She continues supporting the box through the final interaction.
No floating box, unsupported weight or disappearing prop.
ENVIRONMENT
A contemporary shopping mall with adjacent escalators moving in opposite directions.
In the opening composition:
- The heavy shopper occupies the LEFT descending escalator.
- The couple rides the adjacent escalator in the opposite direction.
Preserve the source escalator slope, central divider, rail positions and spacing required for the action.
Maintain coherent screen geography across camera angles.
Do not mirror the layout or reverse the escalators.
Slightly refresh decorative details:
Pale stone finishes, revised ceiling fixtures, different plant pots and subtle changes to distant storefronts.
Do not alter structural elements needed for the blocking.
Keep the architecture and decorations consistent between shots.
Render glass, polished metal, rubber handrails and moving steps in the same Pixar-style aesthetic.
Use warm indoor lighting, soft bounce light, contact shadows and restrained reflections.
Keep the action area clear.
Do not place another featured shopper where the removed source character stood.
The fantasy takes place in a cozy animated living room.
Preserve the source sofa, practical lamp, plants and gaming setup sufficiently to reproduce the original composition and performance.
STORY AND PERFORMANCE
Follow the remaining source beats in this order:
1. ESTABLISH THE THREE CHARACTERS
Show the heavy shopper on the left escalator carrying his PS5 Pro / GTA VI box and doll-window bag.
Show the woman and her companion on the adjacent escalator.
Adapt the source opening composition to these three characters.
2. THE PURCHASES ATTRACT ATTENTION
Reproduce the heavy shopper's satisfied glances and source performance with his purchases.
The couple's man notices the PS5 box and bag.
Match his attention shift, temptation and expression changes.
Preserve the woman's corresponding reactions.
Every purchase-related eyeline points toward the heavy shopper or his props.
No reactions toward an absent second shopper.
3. LIVING-ROOM FANTASY
Retain the imagined gaming sequence.
The image3 man sits on the sofa holding the controller.
Reproduce the source posture, hand movements and pleased expressions.
Keep his exact reference appearance and clothing.
Preserve the relevant fantasy shopping props, using PS5 Pro / GTA VI branding and the same physical doll-window construction.
This is an imagined scene, not a physical transfer of the shopper's possessions.
No additional person appears in the fantasy.
Match the source transition into and out of this sequence.
The fantasy is a brief subjective moment and does not require the same amount of real-world time to pass on the escalators.
4. RETURN TO THE COUPLE
Return to the mall at a spatially coherent point after the initial encounter.
The heavy shopper continues descending naturally.
The woman tries to regain her companion's attention, following the source performance.
He responds with the source distracted reaction.
Omit the second shopper's passage completely.
Continue toward the appliance-box handover without a replacement encounter or prolonged empty staring.
5. HANDOVER AND CROSSING ATTEMPT
Reproduce the appliance-box handover.
Once the woman securely supports it, the man attempts to cross the central divider toward the shopper's escalator.
Match the source preparation, hand placement, weight shift and leg lift.
Maintain visible support and coherent relationships between his body, the divider and moving steps.
His motivation is the heavy shopper's purchases.
Do not make the shopper stop, reverse or reappear at an earlier position.
Do not invent another close pass.
6. INTERRUPTION AND SEATED LANDING
Reproduce the source woman's interruption and the man's resulting return onto the steps.
Use video1 to determine the precise contact and choreography.
Keep the decisive contact, loss of balance and seated landing visible and readable.
Show convincing animated weight and inertia.
Do not substitute a different shove, strike, jump or fall.
Do not replay the contact after a cut.
7. FINAL COMIC PAYOFF
The man remains seated on the moving steps.
The woman stands holding the appliance box.
Preserve her final box gesture and his defeated reaction.
End on the source's final emotional beat.
Do not make him stand again or add a different ending.
The heavy shopper may naturally travel out of frame.
DURATION, CAMERA AND EDITING
Exactly 30 seconds.
Preserve the original order and natural speed of the retained actions.
Adapt the source edit to remove the second shopper while keeping the complete fantasy and final physical sequence.
Use natural-length retained performances and reactions to sustain the duration.
No frozen poses, stretched movement, duplicate actions or artificial pauses.
Match the source camera angles, shot sizes, movement and transitions wherever compatible with the three-character adaptation.
Adjust framing only to maintain clear composition, correct eyelines and visible props.
Keep the handover, crossing preparation, decisive contact and seated landing readable.
Maintain screen direction across cuts.
AUDIO
Use the original music from video1.
Preserve its recognizable rhythm, mood, playback speed and pitch.
Fit it to the 25-second edit with clean, beat-aligned trims.
Retain synchronized sounds and vocal reactions belonging to the three remaining characters.
Remove sounds tied exclusively to the deleted shopper's actions.
Align action sounds with their corresponding contacts.
No added dialogue, narration, lyrics or replacement music.
CONTINUITY
Exactly three principal characters: image1, image2 and image3.
In the real mall scene:
- image1 owns one PS5 Pro / GTA VI box and one doll-window bag.
- The couple carries one separate household-appliance box.
- Ownership changes only through the visible appliance-box handover.
The fantasy does not alter possession of objects in the mall.
Keep identities, proportions, outfits and packaging consistent.
The doll head stays inside its bag and remains inanimate.
Escalator steps, handrails and riders move coherently.
Feet remain supported until a deliberate step or lift.
Bodies and props do not pass through rails, glass or each other.
After the man lands seated, he remains seated through the ending.
NEGATIVE CONSTRAINTS
No second PS5 shopper.
No fourth principal character.
No duplicate heavy shopper or duplicated purchases.
No original live-action faces or costumes.
No mixed animation styles.
No GTA V branding.
No printed doll-face substitute for the physical bag window.
No animated doll head.
No disappearing props, extra limbs, fused fingers or deforming boxes.
No reactions toward absent characters.
No repeated falls, invented collisions or new ending.
No slow motion, speed ramps, freezes or unnatural pauses.
No subtitles, captions, watermarks or end cards.
Trixi retweeted
This AI video shows what father-daughter love really looks like, and it hits harder than most real movies.
Made with WAN 3.0 on @makeugc
Workflow:
- Download this video as a reference
- Create 2 photos of the father and daughter in ChatGPT
- Add my prompt
PROMPT
Approximately 16 seconds, vertical 9:16, polished cinematic 3D animation. Match the reference video's complete duration and original pacing. Preserve its beginning and ending without adding an introduction or extending the final pose.
REFERENCE ROLES
Video reference: the source for the complete performance, action sequence, timing, emotional progression, camera behavior, framing and audio.
Image 1: the new father. Preserve his exact face, green-hazel eyes, wavy auburn hair, fuller reddish-brown beard, body design, sage green knitted sweater, navy trousers and cream sneakers.
Image 2: the new toddler daughter. Preserve her exact face, green-hazel eyes, curly auburn pigtails, mustard bows, toddler proportions, mustard corduroy pinafore, ivory blouse, cream tights and brown ankle boots.
The images define character appearance, clothing and 3D rendering style only. Do not copy their standing poses, studio backgrounds, portrait composition or studio lighting into the scene.
Replace both original characters and their entire outfits with these two referenced characters from the first frame onward. No gradual transformation, blended identities or remnants of the original outfits.
ACTION AND PERFORMANCE
Follow the video reference throughout, preserving every action in its original order and at its original time. Do not create a new choreography or rearrange the emotional beats.
Begin with the new father already holding the new daughter in the equivalent position shown at the start of the video. Keep the father on screen left and the daughter on screen right, matching the reference's orientation and framing.
Preserve the original head movements, hand movements, touches, kisses, eye contact, facial reactions, smiles, laughter and final embrace. Preserve the natural pauses and transitions between these actions. Add no extra gestures or repeated kisses.
Transfer the reference performance onto the new character designs. Preserve the direction, rhythm, intention and timing of each movement while making only the small spatial adjustments needed for their different facial shapes, hair and beard.
For every touch or kiss, preserve the intended contact target from the video. Hands must reach the new character's actual cheek or beard surface. Faces approach, make gentle contact and separate naturally. Do not copy coordinates that cause hands or faces to intersect.
The father's fuller beard remains consistent with Image 1. It compresses slightly under the daughter's fingers or against her face and returns naturally after contact.
Preserve the daughter's small toddler scale relative to her father. Her individual reference image fills its frame for presentation only; it does not mean she is adult-sized.
The father supports the daughter's weight continuously. Keep his supporting arms and hands anatomically connected and consistent with the reference action, including when they are partially outside the frame.
EMOTIONS
Match the original emotional progression rather than displaying one fixed expression.
Reproduce the father's affectionate gaze, smiles, eye closures, emotional reactions and visible tears at the corresponding moments in the reference. Do not introduce tears earlier or exaggerate them into sobbing.
Reproduce the daughter's changing expressions, playful attention, affectionate reactions and laughter at their original moments. Preserve who looks at whom and when.
Match the final cuddle and the characters' closing expressions to the video reference. Do not replace the ending with a pose toward the camera.
LOCATION AND LIGHTING
Change the background subtly to a slightly different cozy family living room: warm beige walls, a softly blurred pale oak shelf and a small muted green houseplant.
Keep these elements in the background and outside the characters' movement paths. No additional people or background activity.
Preserve the video's warm light direction, soft shadows, intimate atmosphere and shallow depth of field. Adapt that lighting to the new characters and clothing. The background remains visually secondary to their faces and interaction.
CAMERA AND TIMING
Follow the reference video's shot structure, camera height, perspective, framing and camera movements. Preserve any cuts only where they exist in the reference.
Keep the intimate framing. Do not widen the shot to display the complete outfits or shoes. Clothing appears only where naturally visible within the original composition.
Do not add camera angles, cutaways, transitions, dramatic zooms, slow motion, speed ramps or extra pauses. Preserve the original action rhythm and all contact moments.
AUDIO AND LIP SYNC
Use the video reference's audio as the exact target for music, words, vocal delivery, pronunciation, pauses and all audible nonverbal sounds.
Preserve the original language and exact wording. Do not translate, paraphrase, add dialogue or infer lines from the filename.
Preserve the original speaker assignments. Synchronize the new characters' mouth movements and expressions to the corresponding speech, laughter and other vocal sounds at their original timestamps.
Preserve the reference music, timing and balance with the voices. Retain sounds only where they are present in the source. Add no new music, narration or sound effects.
VISUAL QUALITY AND CONTINUITY
Maintain the polished stylized 3D animated-feature appearance of the character images, with expressive eyes, soft skin shading, detailed hair, knitted fabric and corduroy.
Keep both identities and outfits stable throughout. Preserve the father's beard shape and the daughter's hairstyle, bows and toddler proportions across all movement.
Hair and clothing respond naturally to motion and contact. Keep the daughter's pinafore straps and skirt consistent as she is held. Fabric must not fuse with the father's sweater or hands.
Maintain believable anatomy and continuous physical contact. Tears, where present, follow the original timing and remain coherent between frames.
PRIORITY
Character images control appearance and wardrobe.
The location description controls the modest background change.
The video reference controls performance, emotional progression, action timing, camera behavior and audio.
Adapt contact geometry only as necessary to preserve believable interaction between the new character designs.
CONSTRAINTS
No original character faces or clothing, identity blending, copied studio poses, studio backdrop, additional characters, added actions, repeated completed gestures, extra limbs, fused fingers, penetrating hands, intersecting faces, floating child, disappearing support, changing outfits, subtitles, logos or end cards.
🤝 Paid partnership · 🤖 Made with AI
🎮 GTA 6 and a PS5 vs love, commitment and married life
Only one of them is coming out on Thursday, and it's not the marriage.
Made with Kling 4.0 on @makeugc
Trixi retweeted
Worst Gift Ever! 😱✈️
Created by Seedance 2.5 on
@makeugc
🤝 Paid partnership · 🤖 Made with AI
Trixi retweeted
You can now create AI creators that promote your products for just $1.20 a video.
Kling 4.0 for $0.08/s + 2 reference images.
Brands are still paying $500 per creator video.
For that same $500, I can make 416 videos.
RT & drop “Want” below and i’ll send the workflow.
🤖 Made with AI










