A realistic, casual selfie-style video of the person from the reference photo, keeping their exact face, hair, skin tone, eye color, and outfit throughout. They stand facing a static camera, framed from the waist up, in a realistic lived-in room that naturally matches their personality and style — believable furniture, everyday clutter, soft natural daylight mixed with warm indoor light, subtle phone-camera grain, no camera movement. The room must look like a real place someone actually lives in, not a studio or a set. Smooth motion, authentic amateur vibe.AUDIO: No background music. Only natural room atmosphere — quiet indoor ambience, faint air hum, soft fabric rustle when the arms move, gentle breathing, muffled distant household sounds. The floating window has its own subtle sound design over the real ambience: a soft airy "shwip" shimmer when it materializes; a low smooth whoosh rising in pitch as it stretches and a shorter reversed whoosh when it compresses; a faint crystalline hum while it holds; quick papery flicks as it slides or flips across the body; a distinct switch sound each time the art style changes — a light percussive pop, a soft drum hit, an elastic "thwip" snap; and a satisfying pinch "plink" with a tiny air-suck whenever it vanishes. All effect sounds subtle and diegetic-feeling.THE WINDOW: whenever the person loosely frames the air with both hands — thumbs and index fingers in relaxed, imperfect L-shapes — a wide letterbox-style window fades in floating between their fingertips. It is NOT a rigid perfect rectangle: it behaves like a living strip of another world, corners softly catching up when the hands move, tilting a few degrees when one hand drifts higher, stretching with a slight elastic wobble, edges cutting cleanly through face, hair, and clothing. Inside the window, the SAME person — unmistakably a cartoon version of them, same face shape, same hairstyle, same eye color, same outfit silhouette reimagined in the art style — mirrors their real pose and motion in perfect sync. Everything outside the window always stays fully photorealistic.THE PERFORMANCE — fun, expressive, never a resting face: the person treats the whole video like a game they're delighted to be winning. Their expressions keep firing: a half-smile that cracks into a full grin, an exaggerated jaw-drop when the first style appears, a cheeky one-eyed squint as the band crosses their eye, puffed cheeks blown out in mock amazement, a quick wink at the camera, biting back laughter and failing, mouthing a silent "wow", a mock-serious frown that collapses into giggles, eyes going wide at each style switch, a proud little smirk when the costume lands on their chest. Their body plays along — leaning toward the lens, rocking back with a laugh, a small shoulder shimmy, head-bobs and tilts — and the cartoon version performs every expression and move in the same instant, with the same energy, rendered in the art style.THE SCANNING GAME — the core of the video: the person uses the window like a handheld scanner, flipping and sliding it up and down their own body to reveal different parts of their cartoon self one region at a time. Index fingers up and lifting = the band rides up; hands flipped with index fingers pointing down = the band drags down; a wrist roll = the band tilts. Over the eyes: real eyes become large stylized cartoon eyes. Over the mouth: a drawn smile under real eyes. Over the chest: the cartoon outfit appears on their real body. Held low at the waist: real face fully visible above the illustrated torso. The fun is the constant mix-and-match of real and drawn body parts as the band travels. Hand language stays relaxed and playful throughout — wrists rotating slightly, fingers soft and slightly curled, one hand leading while the other lags a beat, little flicks, bounces, and re-grips, hair brushing a hand.0-7 seconds: They look at the camera, half-smile, and casually raise both hands into the loose framing gesture — soft "shwip", the window fades in as a narrow band across their eyes; their eyebrows shoot up in delighted surprise. Inside: a warm ANIME version of themselves — big glossy expressive eyes, clean cel shading, their real hairstyle drawn with flowing highlights, a cozy anime rendition of the same room behind them. They pull their hands apart with a rising whoosh, stretching the band wide with elastic overshoot, then lift it slowly up over their forehead and drop it back down across their eyes — papery flicks — playing peek-a-boo between real and anime, grinning wider with each pass.7-14 seconds: They flip both hands over, index fingers pointing down, and drag the band down past their mouth — a drawn grin under real eyes — then further down over their chest, revealing the anime outfit on their real body; they glance down at it and mouth a silent "wow". A wrist roll tilts the band a few degrees, it wobbles and settles. Then they pinch fingertips together — "plink", air-suck, gone. A smirk, hands snap back up — "shwip" and a soft drum hit — and the window reopens with a bold INK-BRUSH COMIC version of them: confident linework, halftone texture, dramatic shadows, their likeness as a stylish graphic-novel hero in a high-collared jacket, the same room reimagined moody and rain-lit through the window behind them; they respond with a mock-serious hero frown that immediately cracks into giggles.14-21 seconds: They scan the comic band slowly up their body — chest, chin, mouth, eyes — alternating small finger-lifts, each region switching from real to inked as the band passes, one cheeky eye squinting as the band crosses it, then flip it back down in one smooth drop to their shoulders. One hand drifts and the band leans with it before settling. They clap-close it — "plink" — laugh quietly in the natural room tone, and reopen with an elastic "thwip": a SPIDER-INSPIRED HERO version of them — an original web-hero suit, not a copy of any existing costume, its colorway matched to the person's vibe (soft pink and white with rose-gold web texture for one person, deep teal and silver or crimson and black for another), a small original emblem on the chest — and they are HALF-MASKED: the mask covers only the top half of the head, with large expressive teardrop-shaped lenses over the eyes, while the entire lower half of the face — nose, lips, chin, their real smile — stays visible, drawn in the same style and unmistakably them, their real hair spilling out from under the mask, a glowing night skyline behind them. They slide the band over their eyes so the lenses take their place — the lenses widening and narrowing with their real reactions — while their drawn mouth below keeps flashing their own grin; they strike a playful two-finger pose and laugh at themselves.21-30 seconds: They stretch the window as wide as their arms reach — long rising whoosh — holding the near-full-frame half-masked hero world for a beat, their stylized self grinning back in perfect sync; they lean into the camera, eyebrows waggling. Then one last playful scan: down to the chest, up to the eyes, a little tilt, one final wink. Slowly they draw both hands together at chest level; the window narrows, tilts one final time, compresses into a glowing sliver between their closing fingertips, and vanishes with a descending whoosh and a gentle "plink". Only natural room tone remains. Fully photorealistic, they hold the camera's gaze, break into one last real laugh, shake their head slightly in disbelief, and let their hands drop softly as the video ends.