The Gatecrasher

GPT IMAGE 2.5 (FLARE) · 16:9 · CAR REFERENCE SHEET

A single professional vehicle reference sheet (model turnaround chart) of the exact car shown in the reference images, built for use as a consistency reference in AI video production.

Image 1: front three-quarter view, defines the nose, the full-width white light bar and the angular wedge front.

Image 2: pure side profile, defines the silhouette, roofline, window graphic and proportions.

Image 3: rear three-quarter view with both doors raised vertically and the tall rear wing, defines the door mechanism and wing.

Image 4: top-down view, defines the plan shape and the dark bronze-tinted glass roof.

Image 5: detail collage, defines the wheels, tire sidewall, rear wing, rear light bar, rear deck, license plate and exhaust tips.

Reproduce this one car with perfect fidelity in every panel: same faceted angular body, matte off-white paint, gloss-black lower body and sills, dark bronze-tinted glass canopy, six-spoke two-tone black-and-white aero wheels, thin full-width white front light bar, full-width red rear light bar, four round exhaust tips, carbon fiber rear diffuser, rear plate reading "RDSTR". Do not redesign, simplify or reinterpret any part.

Layout: one clean landscape sheet on a seamless dark charcoal studio backdrop, organized in a neat grid with thin grey divider lines.

Top row, five orthographic-style views at identical scale, all doors closed, wing retracted: FRONT, REAR, LEFT SIDE, RIGHT SIDE, TOP.

Middle row, three wide perspective views: front three-quarter low angle, rear three-quarter low angle, rear three-quarter with both doors raised vertically and the rear wing deployed.

Bottom row, six tight close-up detail crops: front wheel and tire sidewall, front light bar and nose edge, side marker light and door seam, deployed rear wing and strut, rear light bar with plate and exhaust tips, carbon fiber diffuser.

Lighting identical across all panels: soft overhead key light with a gentle floor pool, controlled reflections that reveal the faceted surfaces, deep soft shadows, neutral color. Photoreal automotive studio photography, sharp focus on the car in every panel, true-to-reference materials, matte paint texture visible.

Each panel has a small, clean, uppercase sans-serif label in light grey in its lower left corner: "FRONT", "REAR", "LEFT", "RIGHT", "TOP", "FRONT 3/4", "REAR 3/4", "DOORS OPEN", "WHEEL", "FRONT LIGHT", "SIDE DETAIL", "REAR WING", "REAR LIGHTS", "DIFFUSER". No other text, no title, no watermark, no people, no props, no background scenery.

NANO BANANA 2.1 · 4:3 · 2K · THINKING MEDIUM

A wide frame grabbed from an amateur phone video secretly filmed in the Stone Age, about forty meters away, in a rocky valley with a cave entrance and a smoky campfire, on a cool hazy morning. A proud caveman with wild hair and a fur pelt is rolling the very first stone wheel, a crude round stone disc with a hole in the middle, toward his tribe, pushing it upright with both hands and grinning. The tribe, a dozen cavemen and cavewomen in furs, sit around the fire and stand at the cave mouth, staring at the wheel in amazement, one elder holding a spear, a child pointing.

Far away down the valley, small in the frame, the car from Image 1 is flying low toward them, a few meters above the rocky ground, a trail of dust behind it, its wheels not touching anything.

The car is the exact vehicle in Image 1: faceted angular matte off-white electric roadster, dark bronze-tinted glass canopy, gloss-black lower body, six-spoke two-tone aero wheels, thin white front light bar. It flies on four round pressurized air vents under its floor; thrust is clear compressed air with dust, no fire, no flames. Nobody has noticed it yet.

Handheld phone footage look: wide view, subjects small in the middle distance, slight camera shake, mild digital zoom so the image is soft and compressed, a blurry rock edge close to the lens in the foreground, campfire smoke drifting, phone sensor noise, slightly tilted framing, candid and not staged. Photorealistic, like a real phone video of a real prehistoric moment, not a movie set. No text, no watermark, no logos.

SEEDANCE 2.5 · 15 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 15 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the misty rocky valley with the stream, the cave mouth, the small campfire with blue smoke, the long-haired caveman in fur pushing the round stone wheel with a hole in the middle, the tribe in furs around the fire (the old grey-bearded elder, the man with the spear, the women, the small child), the rough rocks framing the view in the foreground, the flat misty light. The video does not open on this image and does not copy its framing; there is NO car anywhere in the valley at the start, and it starts a little earlier, with the caveman still rolling the wheel toward the tribe.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car.

TIMELINE:

0-4s: someone hiding behind the rocks films through the gap between them: the caveman rolls the stone wheel the last few meters, stops it, slaps it proudly with both hands and points at it, grunting to the tribe; they stare at it, the child points too. No car in sight, the valley is empty.

4-8s: the tribe erupts: primal whoops, they rush in, lift the caveman up onto their shoulders and bounce him up and down, spears and fists raised, the child jumping around the wheel, the elder clapping.

8-11s: in the middle of the celebration, the white car comes flying low out of the misty valley on its air jets, dust trailing, sweeps from left to right right in front of the tribe, does one fast sideways roll around its own long axis as it passes, nose always pointing the way it is flying, and shoots off out of frame to the right. A wave of dust and smoke washes over everyone; the tribe freezes mid-cheer, the caveman still up on their shoulders.

11-15s: a sudden jerky digital zoom pushes in very close on the caveman's face: wide eyes, mouth hanging open, staring after the car, then slowly looking down at his stone wheel. The zoom is soft, grainy and slightly pixelated, autofocus hunting on his face, small shakes. Ends on his stunned face.

CAMERA: filmed on an iPhone by someone hidden behind the rocks holding the phone in the gap: the action stays small to medium in the frame until the final beat, which is a very close but soft, grainy digital zoom on the caveman's face; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between the foreground rocks and the tribe, auto-exposure pumping against the bright misty sky, rolling-shutter wobble on fast moves, the out-of-focus rocks framing and partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the stone wheel is heavy, the car has weight, the jets kick up real dust and push the campfire smoke, the roll is one continuous rotation around the car's long axis only. The car is one rigid object: front always at the front, rear always at the rear.

AUDIO: wind through the valley, the stream trickling, the campfire crackling, the heavy stone wheel grinding over gravel, grunts, primal whoops and stomping, a rising electric whine, a loud pressurized air hiss and roar sweeping past from left to right, gravel and dust pattering down, then sudden silence and the wind. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, car visible at the start, sharp clean close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, rocket exhaust, wings, propellers, explosion, crash, the car hitting anyone, injuries, front and rear swapping, the car turning around, end-over-end flip, drone, CGI look, morphing, car shape changing, the caveman's face changing, the stone wheel changing shape, extra limbs, people appearing from nowhere.

NANO BANANA 2.1 · 4:3 · 2K · THINKING MEDIUM

A wide frame grabbed from an amateur phone video secretly filmed from a hill about one hundred meters away, outside the walls of ancient Troy on a windy overcast afternoon. Below, a group of ancient Greek soldiers in bronze helmets and linen armor push the giant wooden Trojan Horse on its wheeled platform across the dusty plain toward the massive closed city gates. On top of the stone walls, Trojan guards with spears lean over curiously watching. A small hatch is visible on the horse's belly.

Far away on the plain to the side, small in the frame, the car from Image 1 is flying low toward the city gates, a few meters above the ground, a long trail of dust behind it.

The car is the exact vehicle in Image 1: faceted angular matte off-white electric roadster, dark bronze-tinted glass canopy, gloss-black lower body, six-spoke two-tone aero wheels, thin white front light bar. It flies on four round pressurized air vents under its floor; thrust is clear compressed air with dust, no fire, no flames. Nobody has noticed it yet.

Handheld phone footage look: wide view, subjects small in the middle distance, slight camera shake, mild digital zoom so the image is soft and compressed, blurry dry grass close to the lens in the foreground, flat grey light, phone sensor noise, slightly tilted framing, candid and not staged. Photorealistic, like a real phone video of a real historical moment, not a movie set. No text, no watermark, no logos.

SEEDANCE 2.5 · 12 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 12 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the stone walls with towers and the closed wooden gate, the guards with spears on the battlements, the giant wooden horse on its wheeled platform, the soldiers in bronze helmets pushing it, the dusty plain, the dry grass and bushes in the foreground, the overcast light. The video does not open on this image and does not copy its framing; it starts a little earlier, with the horse further from the gate and the car not yet in view.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing straight down as dense white vapor columns that lift the car.

TIMELINE:

0-3s: someone hiding in the tall dry grass on a low hill holds the phone up just above the grass blades and zooms jerkily toward the soldiers pushing the wooden horse to the gate; the guards on the wall watch. A dust plume appears far right; the operator swings late and zooms clumsily to 3x on a tiny white car speeding across the plain.

3-6s: the car races past behind the horse; the four air jets fire downward with a sharp hiss, blasting rings of dust off the ground; the car lifts off the dirt, nose up, climbing fast toward the wall. Soldiers whip their heads around.

6-9s: in the air the car does two full barrel rolls, jets puffing short white bursts to correct, then one front flip right above the battlements; the guards duck; it clears the wall top and drops inside the city out of view, leaving a white vapor trail and a dust cloud hanging. The camera tilts up too fast, loses it in the gray sky, exposure blows out, zoom pumps out, autofocus hunts.

9-12s: the camera drops back to the soldiers: frozen, a spear falls, several point at the wall where it vanished, one lets go of the rope and the horse platform rolls a little on its own; the guards lean over the battlements looking inside. Ends on this shaky, frozen moment.

CAMERA: filmed on an iPhone by someone crouched in the grass on the hill holding the phone up: the action stays small to medium in the frame, never a close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between grass blades and the plain, auto-exposure pumping against the bright overcast sky, rolling-shutter wobble on fast moves, out-of-focus grass stems and twigs partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the car has weight, the jets kick up real dust, the rolls are fast and sharp.

AUDIO: wind and grass rustling close to the phone, wooden wheels creaking, soldiers grunting, a rising electric whine, then a loud pressurized air hiss and roar, distant gasps and indistinct shouting, the operator's sharp breath. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, fire, flames, rocket exhaust, wings, propellers, explosion, the car hitting the wall, crash, drone, CGI look, morphing, car shape changing, extra limbs, people appearing from nowhere.

NANO BANANA 2.1 · 4:3 · 2K · THINKING MEDIUM

A wide frame grabbed from an amateur phone video secretly filmed from the reedy bank of the Nile in ancient Egypt, about fifty meters away, in golden late-afternoon light. In the middle of the river floats Cleopatra's ornate royal barge with a gilded canopy and purple sails. Cleopatra, in a white linen gown, gold collar and braided black wig, reclines on cushions looking bored. Two attendants slowly fan her with tall palm-leaf fans. In front of her, the Roman general Mark Antony in red cloak and bronze breastplate kneels on one knee, holding out a small jeweled chest as a gift. Rowers sit along the sides of the barge.

Far down the river behind them, small in the frame, the car from Image 1 is skimming toward the barge just above the water surface, its air blast throwing a low white spray trail across the Nile.

The car is the exact vehicle in Image 1: faceted angular matte off-white electric roadster, dark bronze-tinted glass canopy, gloss-black lower body, six-spoke two-tone aero wheels, thin white front light bar. It flies on four round pressurized air vents under its floor; thrust is clear compressed air with water spray, no fire, no flames. Nobody has noticed it yet.

Handheld phone footage look: wide view, subjects small in the middle distance, slight camera shake, mild digital zoom so the image is soft and compressed, blurry papyrus reeds close to the lens in the foreground, warm sunlight glare on the water, phone sensor noise, slightly tilted framing, candid and not staged. Photorealistic, like a real phone video of a real historical moment, not a movie set. No text, no watermark, no logos.

SEEDANCE 2.5 · 12 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 12 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the Nile river at golden hour, the palm-lined far bank, the papyrus reeds in the foreground, the royal barge with the golden prow, purple sails and golden canopy, Cleopatra in white reclining on her daybed, the Roman man in the red cloak beside her, the fan-bearers, the rowers, costumes and light. The video does not open on this image and does not copy its framing; it starts a little earlier, with the car further back down the river, and reaches the action on its own.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car.

TIMELINE:

0-3s: someone crouched in the papyrus reeds on the riverbank holds the phone up just above the reed tops: the royal barge glides along, oars dipping, fans swaying. Far behind it, a small white car skims low over the water on its air jets, throwing a long trail of spray; the operator notices late and zooms jerkily to 3x on it.

3-6s: the car rushes up behind the barge, the jets roar, it lifts steeply off the water, banks hard, swerves around the tall mast and passes low over the deck; spray rains onto the barge, the purple sails whip, the rowers duck, a fan is blown out of a bearer's hands.

6-9s: the car climbs fast into the bright sky and does two full barrel rolls and one flip, jets puffing short white bursts, leaving a white vapor trail. The camera tilts up too fast, loses it in the sun glare, exposure blows out, lens flare, autofocus hunts.

9-12s: the camera drops back to the barge and zooms jerkily to 3x on Cleopatra: she sits up on her daybed, stares up at the sky in shock, raises her arm and points at the car; the Roman beside her stands frozen. Zoom softness and focus hunting on her. Ends on this moment.

CAMERA: filmed on an iPhone by someone crouched in the reeds on the bank holding the phone up: the action stays small to medium in the frame, at the end only a soft digital zoom to a medium shot of Cleopatra, never a sharp close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between reed tops and the river, auto-exposure pumping against the low sun and water glare, rolling-shutter wobble on fast moves, out-of-focus papyrus heads and reeds partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the car has weight, the jets kick up real water spray and mist, the swerve and rolls are fast and sharp.

AUDIO: reeds rustling and water lapping close to the phone, oars splashing, a distant drum keeping the rowing beat, a rising electric whine, a loud pressurized air hiss and roar passing overhead, spray hitting the water, gasps and indistinct shouting on the barge, the operator's sharp breath. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, sharp close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, fire, flames, rocket exhaust, wings, propellers, explosion, the car hitting the mast or the barge, the barge capsizing, crash, drone, CGI look, morphing, car shape changing, Cleopatra's face or costume changing, extra limbs, people appearing from nowhere.

SEEDANCE 2.5 · 15 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 15 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the dusty ancient Egyptian market street, the mud-brick houses, palm trees, market stalls with baskets of dates and onions, the crowd in linen robes, the man holding a goat, the stray dog, the fan-bearers with white feather fans, the shaven bearers in loincloths carrying the car on two long wooden poles, Cleopatra in her golden headdress at the wheel, costumes and harsh midday sun. The video does not open on this image and does not copy its framing; it starts a little earlier, with the procession further down the street, and reaches that moment on its own.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car.

TIMELINE:

0-3s: someone standing behind the crowd at a market stall holds the phone up over the heads: the bearers march the car along on their poles through the dust, fan-bearers beside it, the crowd watching, the dog trotting alongside.

3-6s: a jerky 3x zoom onto Cleopatra through the open side window: she turns her head toward the crowd, gives a small smug smile and raises one finger in a calm "watch this" gesture, then grips the wheel. Zoom softness, autofocus hunting on her.

6-9s: the zoom pumps back out; the four air jets fire downward with a sharp hiss, blasting sand everywhere; the car lifts off the poles, the poles spring up and the bearers stumble back and sit down hard in the sand, the crowd ducks, the feather fans whip, the dog barks; the car climbs steeply.

9-12s: high in the sky the car does two full barrel rolls and one flip, jets puffing short white bursts. The camera tilts up too fast, loses it in the sun, exposure blows out, lens flare, then finds it again.

12-15s: the car flies a smooth looping path and its jets leave a thick white vapor trail that draws one large, clear heart shape across the blue sky, two curves meeting at a point at the bottom; the trail hangs and slowly spreads. Blurry heads of the crowd look up at the bottom of the frame. Ends on the finished heart.

CAMERA: filmed on an iPhone by someone at the back of the crowd holding the phone up over the heads: the action stays small to medium in the frame, at the Cleopatra beat only a soft digital zoom to a medium shot, never a sharp close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between heads and the street, auto-exposure pumping in the harsh sun, rolling-shutter wobble on fast moves, out-of-focus heads and shoulders partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the car has weight, the jets kick up real sand, the poles spring up when the weight leaves, the rolls are fast and sharp, the vapor trail drifts in the wind.

AUDIO: market chatter close to the phone, the goat bleating, bare feet on sand, bearers grunting, a rising electric whine, a loud pressurized air hiss and roar, sand hissing down, the dog barking, gasps and indistinct shouting, then the jets fading high above. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, sharp close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, fire, flames, rocket exhaust, wings, propellers, explosion, crash, injuries, drone, CGI look, morphing, car shape changing, Cleopatra's face or headdress changing, broken or messy heart shape, extra limbs, people appearing from nowhere.

NANO BANANA 2.1 · 16:9 · 2K · THINKING MEDIUM

A wide frame grabbed from an amateur phone video filmed from across the street, about fifty meters away, in a Brooklyn-style New York neighborhood on an overcast afternoon. A six-story red-brick apartment building has thick grey smoke pouring out of its upper windows. On a small fifth-floor iron balcony, a young mother clutching her baby waves for help. Below, a red fire truck is parked at the curb with its aerial ladder fully extended, but the top of the ladder stops a full floor short of the balcony; firefighters in tan turnout gear look up and point, one shouting into a radio, neighbors gathered behind yellow tape filming with phones.

Far down the street, small in the frame, the car from Image 1 is flying toward the building at second-floor height, kicking up dust and litter from the street below.

The car is the exact vehicle in Image 1: faceted angular matte off-white electric roadster, dark bronze-tinted glass canopy, gloss-black lower body, six-spoke two-tone aero wheels, thin white front light bar. It flies on four round pressurized air vents under its floor; thrust is clear compressed air, no fire or flames from the car. Nobody has noticed it yet.

Handheld amateur phone footage filmed from far away by a bystander: wide view, subjects small in the middle distance, slight camera shake, mild digital zoom so the image is soft and compressed, a blurry parked car mirror close to the lens, flat grey daylight, phone sensor noise, slightly tilted framing, candid and not staged. Real-world imperfect textures, not cinematic, not a movie set. No text, no readable signs, no logos, no watermark.

SEEDANCE 2.5 · 15 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 15 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the overcast brick-apartment street, the building with thick gray smoke pouring from the windows, the woman holding her child on the fire escape, the red fire truck with the extended aerial ladder, the firefighters in tan turnout gear, the police officers, the crowd behind the yellow tape filming with phones, the parked cars, the side mirror in the foreground, the flat gray light. The video does not open on this image and does not copy its framing; it starts earlier, with the ladder still intact and the car not yet in view, and reaches the action on its own.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car.

TIMELINE:

0-3s: someone sitting in a car parked at the curb films out of the open window, the side mirror in the foreground: the aerial ladder slowly extends toward the fire escape where the woman holds her child and waves for help; smoke pours from the windows; the crowd behind the tape films with raised phones.

3-6s: just short of the fire escape, the top section of the ladder cracks at a joint and drops away, swinging down and slamming onto the empty street in a burst of dust; nobody is on it. The firefighters jump back, the crowd gasps, the operator flinches and the camera jolts.

6-10s: the white car shoots in from down the street, flying low on its air jets, climbs steeply alongside the building and hovers level with the fire escape, the jets pushing the smoke aside; the woman steps over the railing onto the car's flat roof, crouches and holds her child tight.

10-15s: the car descends slowly and steadily, jets kicking up dust and paper, and lands softly in the street right in front of the fire truck; the woman slides down holding her child, both safe; firefighters run to them and wrap a blanket around them; the crowd erupts cheering, phones up. Ends on this moment.

CAMERA: filmed on an iPhone by someone in a parked car holding the phone at the open window: the action stays small to medium in the frame, never a close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between the side mirror and the building, auto-exposure pumping against the bright gray sky, rolling-shutter wobble on fast moves, the out-of-focus side mirror partly blocking the lower frame with its reflection a soft blur, heads of the crowd drifting into view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the falling ladder section has weight, the car has weight, the jets kick up real dust and push real smoke, the hover is steady and controlled, the landing is soft.

AUDIO: sirens, the fire truck engine idling, a hydraulic whine, radio chatter, crowd murmuring close to the phone, a sharp metallic crack and a heavy crash on the asphalt, gasps, a rising electric whine, a loud pressurized air hiss, the crowd erupting in cheers. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, phone visible in the mirror, camera interface, text overlays, readable text, logos, visible flames, explosion, anyone falling, anyone hit by the ladder, injuries, the car tilting while carrying them, crash, wings, propellers, rocket exhaust, drone, CGI look, morphing, car shape changing, the woman or child changing appearance, extra limbs, people appearing from nowhere.

NANO BANANA 2.1 · 4:3 · 2K · THINKING MEDIUM

A wide frame grabbed from an amateur phone video filmed at midday from across a narrow back street in an old working-class Istanbul neighborhood, about twenty-five meters away. A traditional neighborhood coffeehouse (kıraathane) with a worn ground floor, a faded awning, plastic stools and small wooden tables out on the cracked sidewalk, an old building above with a concrete overhanging balcony, peeling paint, tangled electric cables, a satellite dish. The car from Image 1 is clamped upside down to the underside of the overhanging concrete balcony, wheels flat against it, casting a cool shadow over the tables below. In that shadow, four old men in flat caps and cardigans sit around a table playing okey with their tiles on wooden racks. A teenage tea boy in a vest stands on tiptoe holding up a small metal tray with a tulip glass of tea toward the car's open driver window, where the upside-down driver's hand reaches down for it. A stray cat sleeps under a stool.

The car is the exact vehicle in Image 1: faceted angular matte off-white electric roadster, dark bronze-tinted glass canopy, gloss-black lower body, six-spoke two-tone aero wheels.

Handheld phone footage look: wide view, subjects small in the middle distance, slight camera shake, mild digital zoom so the image is soft and compressed, a blurry parked scooter mirror close to the lens, harsh midday sun with deep shadows, phone sensor noise, slightly tilted framing, candid and not staged. Gritty, imperfect, real-world textures, not cinematic, not a movie set. No text, no readable signs, no watermark, no logos.

SEEDANCE 2.5 · 12 S · ONE CONTINUOUS HANDHELD SHOT

FORMAT: 16:9, 12 seconds, one continuous handheld shot, no cuts, real-time.

REFERENCES:

@Image 1 = reference only, NOT the first frame: use it for the narrow worn Istanbul street corner, the old stained apartment building with the low concrete balcony overhang above the kahvehane, the faded awning, the four old men in flat caps playing okey at the small table on plastic stools, the waiter boy in a black vest with a small tea tray, the sleeping cat, the parked cars, trash bins, tangled cables, satellite dishes, the motorcycle in the foreground, the harsh midday sun. The video does not open on this image and does not copy its framing; it starts earlier, with no car under the balcony, and reaches that moment on its own.

@Image 2, @Image 3, @Image 4, @Image 5, @Image 6 = the car only (ignore studio backgrounds, night road and desert): a low pearl-white wedge-shaped electric sports car, sharp faceted panels, dark bronze-tinted glass roof, thin full-width light bar at the front, red full-width light bar at the rear, black six-spoke wheels, rear wing.

@Image 7 = flight mechanism only (ignore the night stage and crowd): four pressurized air jets under the car near each wheel, firing as dense white vapor columns that lift the car.

TIMELINE:

0-3s: someone standing behind the parked motorcycle across the street films over its handlebar: the old men slap okey tiles on the table, the boy waits by the door with the tray. The white car comes down the side street on the right, turns at the corner and rolls slowly to the left along the front of the kahvehane, nose pointing left toward the awning, rear light bar and wing on the right, and stops under the balcony overhang.

3-6s: the four air jets fire downward with a sharp hiss, blasting dust and litter across the asphalt, the awning flaps; the car lifts straight up, level, to just below the overhang. There it does one fast sideways roll around its own long axis, like a log turning in place: the roof swings down and the wheels swing up, the nose keeps pointing left and the rear keeps pointing right the whole time. It finishes upside down and the jets push it the last half meter up until all four wheels press flat against the underside of the overhang with a heavy thump, sticking there upside down right above the okey table, nose left, rear right. Plaster dust drifts down onto the men; they glance up for a second and go back to their game. The cat keeps sleeping.

6-9s: the boy walks over with the tray, stands on tiptoe on the curb and raises a tulip glass of tea on its saucer toward the open driver window of the upside-down car.

9-12s: the driver's arm reaches down out of the window and calmly takes the tea glass by its saucer; the tea stays upright and does not spill. The men keep playing. Ends on this moment.

CAMERA: filmed on an iPhone by someone across the street behind the motorcycle: the action stays small to medium in the frame, never a close-up; shaky handheld drift, sudden jerky 2x to 3x digital zooms in and out with zoom softness, autofocus hunting between the motorcycle mirror and the corner, auto-exposure pumping between harsh sun and shade, rolling-shutter wobble on fast moves, the out-of-focus motorcycle mirror and handlebar partly blocking the view, reacting a beat late. No fingers, hands or phone of the operator ever visible.

STYLE: raw everyday iPhone video: over-sharpened, compressed, noisy, Smart HDR, white balance a little off. Not cinematic.

MOTION: true real-time speed, real physics: the car has weight, the jets kick up real dust and litter, the roll is one continuous rotation around the car's long axis only, the landing on the overhang is solid. The car is one rigid object: front always at the front, rear always at the rear, its direction never changes from the moment it turns the corner to the end.

AUDIO: busy street ambience, okey tiles clacking on the table, indistinct old men muttering, a distant scooter, a rising electric whine, a loud pressurized air hiss, a heavy thump of wheels on concrete, falling plaster grit, the clink of the tea glass on its saucer. No music, no clear words.

NEGATIVE PROMPT: slow motion, starting on the reference image, close-up, cinematic camera move, dolly, crane, gimbal, stabilization, cinematic color grade, shallow depth of field, cuts, music, fingers or hands of the operator, camera interface, text overlays, readable text, logos, fire, flames, rocket exhaust, wings, propellers, explosion, the car falling, building damage, tea spilling, the men running away, drone, CGI look, morphing, car shape changing, front and rear swapping, the car turning around or reversing direction, end-over-end flip, the car spinning flat, the car teleporting into position, extra limbs, extra arms, people appearing from nowhere.

ONE CAR. SIX WORLDS. NOBODY SAW IT COMING.

The joke is not the flying car. It is the person who happened to be filming.

Swap the Roadster for any product and the skeleton still carries it: lock the object once in a reference sheet, build each world as a distant phone still where nobody has noticed it yet, then give Seedance one unbroken handheld take that ends on a reaction. The more ordinary the moment, the harder the interruption lands.

Every step of this film was made inside Arcads: the car sheet in GPT Image 2.5, the scene stills in Nano Banana 2.1 and all six clips in Seedance 2.5, in one workspace from first reference to final take. Start building your own:

arcads.ai

WRITTEN, DIRECTED & PROMPTED BY DENIZ AKKABAK · @DENIZ.AKKABAK