Boot Stepping into a City Puddle

QUICK STORY — NO CHARACTER DESCRIPTION: A clear morning after a light rain on a busy Manhattan street. The road is still wet, reflecting tall buildings, signs, and natural skylight. A yellow taxi has just passed through a large puddle beside the curb, producing a small splash and long reflected ripples across the road. The main subject is crossing the sidewalk when she suddenly notices a decorative ribbon from a nearby fashion store being blown into the street. She instinctively steps around the puddle while extending one foot forward to maintain her balance. At that exact moment, a large droplet kicked up by the taxi's tire flies close to the camera, combining with the road's reflections to create a strange visual illusion: her leg and the ribbon seem to pass out through the image plane, as though a layer of the real photograph is being pushed open toward the photographer. She is not deliberately creating this effect; everything happens accidentally in an everyday instant. The photographer stands opposite and captures the entire moment with a phone camera, not a selfie. Golden reflections from the taxi, storefront glass, water droplets, and metal accessories create small, natural sparkles. A few minimalist 2D icons appear precisely where movement occurs: speed lines, water droplets, sparkle, ripple, and a tiny taxi symbol, suggesting an unconventional street-fashion campaign while retaining the complete realism of everyday photography. MAIN SUBJECT — 80% OF THE FRAME'S FOCUS: An adult woman with a high-fashion yet natural appearance, without generic AI beauty. Her face must be entirely new, never reusing the facial structure of any previous subject. Do not copy a reference face, perform face averaging or face cloning, or turn the subject into the same person simply by changing hair or clothes. Design a distinctive face for this story: a slightly elongated oval-diamond face, a proportionate forehead, soft temples, subtly prominent cheekbones, a delicate jawline that is not artificially sharp, and a moderately small chin rounded slightly at the tip. Very slight asymmetry between the two sides, like a real person. Overall, a modern Asian–European appearance, elegant and fashionable without CGI-like perfection. The face must have its own recognizable character from the first glance. FACE: The eyes are the main attraction. Slightly elongated almond-shaped eyes of natural size, without exaggeration. Amber-brown irises mixed with gray, containing many tiny textured rings and realistic reflections of the Manhattan sky. Pupil size appropriate to morning light. Her gaze looks directly into the camera, as though she has just noticed the unexpected moment while retaining a model's poise. No looking away, no closed eyes, no lifeless gaze. Clearly resolved individual eyelashes with natural density. Dark-brown eyebrows, fairly straight at the inner ends and gently curved toward the tails, with fine hairs growing in realistic directions. Do not make the eyebrows look drawn on. A moderately high, delicate nose bridge, with a natural transition from forehead to nose. A small, neat tip without unnatural sharpness. Proportionate nostrils. Highlights on the bridge come only from real light. No artificial highlight stripe. Softly shaped lips, the upper lip slightly thinner than the lower. Naturally defined edges, not excessively sharp. Nude pink with a touch of peach. The corners lift into a small fashion-model smile, confident yet natural. No overly broad smile or excessively seductive expression. Do not copy the reference image's expression. Extremely detailed facial skin texture. Cool, fair skin, almost bright ivory, visually resembling an albino-like skin tone without being a medical condition or showing any signs of illness. This is only the subject's skin-color characteristic. Do not make the skin glow or turn it paper-white. Retain a very subtle natural undertone and minute color variations in the cheeks, nose, and ears. Preserve small pores, micro-texture, reflective areas, and shadows. Real texture should remain visible when the camera is close. No airbrush, no skin smoothing, no porcelain skin, no plastic skin, no beauty filter. The cheekbones receive soft skylight. A very subtle highlight appears on the cheekbone nearer the camera. Natural shadow beneath the chin. Do not flatten the face. Retain minute texture around the eyes. Skin must not be absolutely flawless; these small details create the feeling of a real person. HAIR: Very long dark-brown hair, completely different from previous subjects' hairstyles. Naturally layered, with a little volume on top and soft waves at the ends. A section is clipped to one side with a minimalist silver metal hair clip. A few fine strands blow across the forehead and cheeks. Different groups of hair respond to the wind in different directions. Include tiny flyaway hairs. Do not make the hair one glossy black mass. No plastic hair or perfect 3D-rendered hair. A few strands close to the camera catch very small highlights. FIGURE: The subject has average height and balanced, healthy, natural proportions. Do not lengthen the legs with AI or distort the waist. Do not make limbs too long. Shoulders proportionate to the torso. Her weight shifts onto the rear leg because she has just avoided the puddle. Body curves appear as a natural part of the fashion silhouette, without erotic emphasis. The pose has an editorial-fashion quality but still resembles an accidental real-life movement. OUTFIT: A high-end street-fashion ensemble inspired by New York after rain. A slightly oversized ivory blazer in a light wool blend with clearly visible fabric texture. A simple navy square-neck top underneath. Below, a silver-gray A-line skirt reaching close to the knees, with soft folds that move as she steps. A thin black leather belt creates a balanced horizontal line. Slightly glossy black ankle boots with low, practical soles. A small silver-gray shoulder bag worn to one side. Small geometric silver earrings. A champagne-yellow silk scarf lightly attached to the bag strap; this scarf is caught by the wind and becomes part of the frame-breaking effect. The clothing must have real material qualities: individual fibers, stitching, folds, blazer edges, reflections on leather shoes, and metal accessories are all clearly visible. Do not turn the outfit into CGI. No fake brand logos or random brand lettering. POSE: The subject is stepping across the sidewalk and suddenly avoiding a puddle. Her front leg extends strongly toward the camera in forced perspective while maintaining anatomically correct proportions. The foreground foot and shoe appear naturally larger because of their distance from the camera. The rear leg bears her weight. One knee is slightly bent. Her torso rotates gently with the motion. One hand holds the bag strap; the other extends sideways for balance. The champagne scarf is pulled toward the camera by the wind. The special feature is that one foot becomes the main frame-breaking element. The camera is very close in front, so the approaching foot seems to “escape” the edge of the photograph. It is not an unnaturally gigantic foot; the effect comes from forced perspective and camera distance. The shoe retains its correct shape, sole, laces, and structure. No extra toes or distorted foot. No selfie. No phone in her hand. Another person holds the camera at torso height, pointing toward the subject. EXPRESSION: Her face looks directly into the camera. Her eyes show slight surprise at the puddle and flying scarf while retaining a natural fashion-model smile. A small smile, subtly curved lips, bright eyes. No excessively sexy expression, grimacing, or fake smile. Do not copy the reference expression. It should feel as though the photographer has casually caught a beautiful moment. ACCIDENTAL “FRAME-TEARING” EFFECT: No magical doorway or spatial portal. The effect comes entirely from a combination of real movement, reflections, and foreground objects. As the taxi tire passes through the puddle, a small sheet of water curves near the camera. At the same time, the champagne scarf is pulled strongly by the wind. The subject's approaching foot is very close to the camera. These three overlapping elements make the viewer feel that the image plane is being pulled open. A reflection on the roadway stretches from the taxi toward the subject. As she steps across it, the reflection breaks into ripple rings. These rings form curves resembling the edges of paper opening up. This is an optical illusion, not a supernatural object. The champagne scarf crosses the foreground, partly cropped at the left edge and partly passing close to the right edge. Forced perspective makes it seem to pass out through the frame. Do not create a physical tear in the photograph. SPARKLE EFFECTS: Yellow light reflected from the taxi onto the puddle creates tiny bright points. Metal on the bag and earrings catches the light. A few water droplets near the camera create sparkle-shaped highlights. These bright points do not glow artificially. Every sparkle must have a plausible reflective source. Some tiny sparkles have four-pointed star shapes. Some are diamond-shaped. Others are simply natural bright points. Concentrate the effect around the scarf, shoes, droplets, and roadway. Do not cover the skin in sparkles, make the hair glow, or turn the photograph into fantasy CGI. 2D ICONS: Add very small, subtle 2D icons: a tiny yellow taxi symbol near the street corner, two motion lines beside the scarf, three stylized droplets beside the tire, a few ✦ sparkles, a small ripple line on the road, and a curved arrow indicating the scarf's direction. The icons should resemble graphic overlays in a modern street-fashion campaign. Do not use oversized icons or cover the eyes, nose, lips, or body. Do not turn the photograph into a comic. SETTING: Manhattan, New York, on a street combining modern and classical architecture. High-rise glass buildings in the distance, fashion-store façades, storefront windows reflecting the street, a yellow taxi, traffic lights, stone-paved sidewalks, and urban signage. Do not turn it into Times Square unnecessarily. The setting must resemble a real New York street on a morning after rain. A few pedestrians are very far away, slightly out of focus but naturally shaped. None looks directly into the camera. No artificial crowd. The taxi is a background element, not the main subject. The road is wet but not flooded. Small puddles reflect the sky. A few wet leaves lie on the sidewalk. Storefront glass accurately reflects the subject and taxi. WEATHER: The sky has cleared after light rain. Pale blue sky with thin white clouds. Clean, neutral morning light, without yellow coloration. No sunset. No golden hour. No fog. No falling rain. No cinematic haze. CAMERA: Documentary Lifestyle Photography with a high-end smartphone camera held by another person. No selfie, mirror selfie, tripod, or studio. Extremely close to the subject. The camera is slightly below her face to create forced perspective for the approaching foot. Frame from the thighs upward while allowing the front foot to appear very close to the lower edge because of its movement. The subject occupies about 80% of the visual area. A standard smartphone lens, without excessively strong ultra-wide distortion. Do not distort the face, elongate the nose, or make the head unnaturally large. Forced perspective affects only objects near the camera. The face stays proportionate. Focus is locked on the face and main body. Extremely sharp eyes. Clear details in hair, skin, outfit, and scarf. The foreground foot remains sharp, not blurred. The background loses a little detail but remains recognizably Manhattan. COMPOSITION: Dynamic fashion composition. The face sits in the upper central region. The body forms a slight diagonal from the rear toward the foreground foot. The scarf curves from the outfit toward the camera's edge. The yellow taxi supplies a contrasting color point in the background. Reflections on the road form a leading line directly toward the subject. The subject occupies about 80% of the frame. Do not let the background take up too much space. Do not crop out the face or crop the hair illogically. Do not let the foot obscure the face. Every element guides the eye toward the face. LIGHTING: Natural post-rain morning light. Natural smartphone HDR. Neutral white balance. Fair, bright skin that retains texture. Slight blue skylight softens the shadows. Yellow from the taxi appears only in reflections. Real highlights on storefront glass. No studio lighting, artificial rim light, cinematic orange-teal, or yellow tint across the entire image. REFLECTIONS: Puddles reflect the subject, taxi, and sky. Reflections must distort naturally with water ripples. Do not create perfect mirror reflections. When the foot steps across, the reflection breaks into ripples. A few bright points from the taxi stretch into small streaks on the water. This is the main source of the sparkling effect. REALISM: Real person, real face, real skin, real hair, real fabric, real water, real glass, real street, real taxi. Realistic skin texture. Individual pores. Individual hair strands. Natural facial asymmetry. Accurate hands. Accurate feet. Correct anatomy. Realistic clothing physics. Realistic shadows. Realistic reflections. Natural smartphone HDR. Subtle handheld framing. No CGI. No 3D. No 2D character. No anime. No cartoon. No plastic skin. No porcelain skin. No airbrush. No AI beauty filter. No overly smooth face. SHARPNESS: Ultra sharp smartphone photograph. Face extremely detailed. Eyes crisp. Eyelashes visible. Eyebrows individually detailed. Hair strands visible. Fabric fibers visible. Shoe texture visible. Water droplets crisp. Taxi reflection detailed. No motion blur on the face. No soft focus. No dreamy filter. No full-image blur. No excessive depth of field. COLORS: Neutral New York morning palette: ivory, charcoal, navy, silver-gray, wet asphalt gray, natural blue sky and yellow taxi. Skin retains a naturally cool, fair tone. Do not yellow the skin, oversaturate the colors, or apply cinematic color grading. FASHION DIRECTION: Modern New York street fashion, elegant urban editorial, spontaneous luxury lifestyle, practical high-fashion styling. The outfit must look wearable in real life. No costume, fantasy armor, erotic clothing, or pornographic emphasis on the body. TEXT: No headline, slogan, CTA, or watermark. Place TUONG only once, on a small metal sign at the fashion store behind her or on a paper tag attached to the bag. Small lettering, correct perspective, naturally within the scene. Do not float TUONG in the middle of the image. Add no other text. NEGATIVE PROMPT: No minors, no childlike appearance, no nudity, no sexual content, no transparent clothing, no selfie, no mirror selfie, no phone in hand, no duplicate character, no duplicate face, no clone face, no copy reference expression, no repeated face, no AI beauty face, no plastic skin, no porcelain skin, no excessive retouching, no CGI, no 3D, no anime, no cartoon, no illustration, no distorted anatomy, no extra fingers, no fused fingers, no malformed feet, no extra toes, no giant foot, no elongated leg, no warped hands, no deformed face, no giant eyes, no asymmetrical pupils, no blurry face, no blurry image, no artificial bokeh, no excessive sparkle, no excessive icons, no fantasy portal, no magical explosion, no studio background, no fake Manhattan, no fake taxi, no excessive yellow cast, no orange skin, no cinematic teal-orange, no watermark, no text other than TUONG. FINAL DIRECTIVE: Create a vertical 9:16 image in documentary lifestyle photography style, featuring a beautiful adult woman with an entirely new Asian–European face, matching none of the previous faces. Extremely fair, cool-toned skin with an albino-like visual tone, without a medical condition, retaining real human texture and natural light reflections. She wears ivory, navy, and silver-gray street fashion, with long, wavy dark-brown hair, and is accidentally stepping around a puddle on a Manhattan street after rain. One foot comes extremely close to the camera, creating strong forced perspective with entirely correct anatomy, making it seem to pass beyond the photograph's edge. A champagne scarf is pulled toward the camera by the wind. A yellow taxi has just passed, creating a splash and reflections. Water, glass, metal, and fabric together form small sparkles with plausible light sources. Minimalist 2D icons appear around the movement. Her face looks directly at the camera with a natural fashion-model smile; no selfie and no copied reference expression. She occupies about 80% of the frame, with an extremely close camera and fashion framing from the thighs upward, while the foreground leg creates an illusion of breaking the frame's boundaries. The face, eyes, hair, skin, outfit, foot, and water droplets must all be exceptionally sharp. Natural smartphone HDR, clear morning light, neutral colors, no yellow cast, no blur, no CGI, no anime, no 3D, and no AI Face. Overall, it must resemble a completely real street-fashion moment that accidentally creates a strange visual illusion of the subject stepping out of the photograph itself. @Generate image