{ "image": { "main_description": "A chaotic and fun flash-photography snapshot of a holiday house party. A man is kneeling on a marble kitchen island, catching a stream of champagne being poured into his mouth by a friend standing above him.", "characters": { "main_reference_character": { "identity_anchor": "The character based on the provided reference photo, preserving strictly the user's identity source.", "ethnicity_and_phenotype": "Determined by the user provided reference photo.", "face_and_skin": "Skin illuminated by direct camera flash, showing a flush of excitement; facial features strictly derived from the reference.", "expression": "Head tilted back, mouth wide open in a laugh or shout, eyes likely closed or squinting in anticipation of the drink.", "hair": "The specific hairstyle visible in the user's reference photo.", "body_and_pose": "Kneeling on top of a kitchen counter/island, leaning back slightly with hands resting on thighs or the counter surface for balance.", "outfit": "A luxurious emerald green silk pajama set (long-sleeve button-down shirt with white piping details and matching trousers)." }, "supporting_characters": [ { "role": "The Pourer", "description": "A woman with distinctive split-dyed hair (half bright red, half green), wearing a pink silk pajama set with black piping. She is standing and holding a large green champagne bottle upside down.", "interaction": "Pouring a stream of champagne directly into the main character's mouth." }, { "role": "The Observer", "description": "A woman with long red hair, wearing a cream/white silk pajama set with feather cuffs. She holds a smartphone in one hand (filming the action) and a coupe glass in the other.", "interaction": "Standing to the side, laughing and recording the scene." } ] }, "text_elements": { "content": "", "typography": "", "placement": "", "integration": "" }, "environment": { "location": "A modern, upscale home kitchen with white cabinetry and marble countertops.", "elements": "Holiday/Christmas decorations including a pine garland on the island, tall taper candles, scattered red cups, and other party debris.", "atmosphere": "Loud, festive, late-night party vibe, domestic but chaotic." }, "cinematography": { "lighting_setup": "Direct on-camera flash style (harsh, bright front lighting) creating hard shadows behind the subjects.", "color_grading": "High contrast, saturated colors (especially the green and pink pajamas), realistic digital photography look.", "shadows_and_highlights": "Bright highlights on the silk fabrics and skin; sharp, dark shadows cast against the white cabinets.", "reflections": "Glare on the marble countertop and cabinet finishes." }, "camera_and_tech": { "framing": "Medium wide shot, capturing the group interaction and the kitchen setting.", "optics": "Wide angle lens, deep depth of field (everything in focus due to flash).", "visual_fidelity": "Candid aesthetic, 'caught in the moment' realism." }, "style_and_mood": { "aesthetic": "Flash Photography, Candid Party, Gen Z aesthetic, Lifestyle.", "emotional_vibe": "Wild, joyful, intoxicated, celebratory." }, "aspect_ratio": "4:5" } }
I am standing facing the camera in a dark, nightlife-style environment, centered tightly in the frame. My posture is upright but playful, shoulders relaxed, body facing straight forward. The composition feels intimate and energetic, focused on my upper body and face. Both of my arms are raised symmetrically in front of my face. I am holding two elegant cocktail glasses by their stems, lifting them up to eye level. One glass is filled with a deep red drink, the other with a warm golden-yellow cocktail. I position the glasses directly in front of my eyes, aligning them like improvised lenses, partially covering my face. My fingers grip the stems firmly but casually, rings visible on my hands, adding a bold, stylish detail.
My head is held straight, facing forward. My mouth is open slightly, tongue visible, creating a playful, cheeky, and uninhibited expression. My facial expression conveys fun, confidence, and spontaneous party energy rather than a posed smile. I am looking toward the camera through the glasses, fully engaged with the viewer.
I am wearing a modern, fashion-forward outfit consisting of a light-colored, subtly shimmering tailored blazer with a clean, sharp cut. Underneath, I wear a minimalist top with a deep neckline, giving a refined but bold evening look. Around my neck, I wear a sleek metallic choker-style necklace that reflects light and emphasizes the celebratory, nightlife aesthetic. The fabrics appear smooth, elegant, and slightly reflective, enhancing the high-end party vibe.
The background is dark and unobtrusive, allowing full focus on my face, hands, glasses, and styling. The lighting is direct and dramatic, illuminating my face, blazer, jewelry, and the liquids inside the glasses. Highlights sparkle on the glass rims and rings, while shadows remain soft and controlled, adding depth without distraction.
The camera is positioned at eye level, creating a direct and engaging connection. The image is captured as a tight portrait using a portrait lens (approximately 85mm), producing natural facial proportions and a shallow depth of field that keeps my face and hands sharply in focus while the background stays dark and blurred.
The overall image has a high-end editorial nightlife aesthetic — playful, confident, stylish, and celebratory — with crisp detail, cinematic lighting, and strong New Year's Eve or party energy. My face must remain exactly the same as the reference, fully preserved with accurate facial structure, proportions, and expression.
I am sitting inside a classic bathtub filled with white foam, positioned diagonally within the frame. My body is relaxed and spread out casually inside the tub. One of my legs is bent and resting against the inner edge of the bathtub, while the other leg is extended forward, partially submerged in the foam. My posture feels confident, careless, and dominant, as if I am fully owning the moment without concern. My torso leans slightly backward against the tub, allowing my shoulders to rest comfortably. My head is held upright and facing forward.
I am looking directly toward the camera with a calm, serious, and detached expression. My face shows no smile; instead, it conveys control, confidence, and quiet arrogance. My gaze is steady and composed. Both of my arms are raised outward in a strong, symmetrical gesture. In one hand, lifted above my head, I am holding a champagne bottle tilted downward, with liquid visibly pouring from the bottle mid-air. In my other hand, also raised, I am holding a small yellow rubber duck, creating a striking contrast between luxury and irony. My hands are relaxed yet deliberate, reinforcing the playful but dominant attitude.
I am wearing a classic black tuxedo with a sharp, elegant cut. The jacket and trousers are fully soaked, clinging slightly to the fabric due to the water. Underneath, I wear a crisp white dress shirt paired with a black bow tie. The contrast between the formal attire and the bath setting creates a bold, cinematic effect. I am also wearing dark sunglasses, which hide my eyes and add an extra layer of detachment and mystery. The fabrics appear smooth, structured, and high-quality, even when wet.
The bathtub is set inside a luxurious bathroom with beige and cream marble walls and matching marble surfaces. Gold-toned fixtures, including the faucet and handles, add a refined, upscale feel. The foam fills the tub generously, spilling slightly over my legs and jacket, emphasizing excess and indulgence.
The camera is positioned slightly above me, angled downward, creating a subtle top-down perspective that captures my full body inside the tub. The image is shot with a moderately wide lens (approximately 28mm–35mm), allowing the entire bathtub and surrounding details to remain visible while maintaining strong subject focus. The depth of field is moderate, keeping all key elements sharp.
The final image has a cinematic, high-fashion editorial style with crisp detail, controlled lighting, strong contrast, and a bold, decadent, luxurious party-aftermath mood. My face must remain exactly the same as the reference, fully preserved with accurate facial structure, proportions, and expression.
I am lying flat on my back on a dark wooden floor in the middle of a chaotic party aftermath. My body is stretched out and relaxed, slightly diagonal within the frame. One of my arms is bent at the elbow, resting loosely near my torso, while my other arm lies relaxed by my side. My posture feels careless and exhausted, as if I have completely given in to the moment after a long night of celebration. My head is turned slightly to the side, resting directly on the floor.
I am wearing dark sunglasses, completely obscuring my eyes, giving me an indifferent, detached expression. Between my lips, I am holding a party horn angled upward, frozen mid-blow, reinforcing a playful yet worn-out party mood. My facial expression appears calm, detached, and slightly dazed rather than joyful or posed.
I am dressed in a classic black suit with a clean, modern cut. The suit jacket is slightly open, revealing a white dress shirt underneath with the top buttons undone, adding to the relaxed, end-of-the-night feeling. Wrapped loosely around my neck and shoulders is a metallic gold tinsel garland, creating a festive contrast against the dark suit fabric. The textures of the suit are matte and smooth, while the tinsel reflects light in sharp highlights.
The floor around me is covered in colorful party confetti, metallic streamers, and scattered decorative pieces in gold, silver, and bright colors. Surrounding me, only the lower bodies of other party guests are visible: legs in formal trousers, dress shoes, and sheer stockings with high heels. These figures stand around me casually, partially cropped by the frame, emphasizing my position on the ground and the chaotic party environment.
The lighting is low and dramatic, with focused highlights illuminating my face, suit, tinsel, and the confetti immediately around me. Shadows fall naturally across the floor, adding depth and contrast. The scene feels candid, cinematic, and slightly decadent, capturing the raw aftermath of a celebration rather than a polished party moment.
The camera is positioned above me, shooting from a high angle directly downward, creating a strong top-down perspective. The image is captured with a moderately wide lens (approximately 28mm–35mm), allowing the surrounding environment, confetti, and people’s legs to remain visible while keeping me as the central subject. The depth of field is moderate, with clear detail across the scene and slight softening toward the edges.
The final image has a cinematic, editorial photography style with realistic lighting, rich contrast, visible textures, and a gritty, end-of-the-night party atmosphere. My face must remain exactly the same as the reference, fully preserved with accurate facial structure, proportions, and expression.
Prompt: FACE LOCK (MANDATORY): Use the exact same face from the uploaded reference image with absolutely no modification. Facial structure, proportions, bone shape, eyes, nose, mouth, jawline, skin tone, pores, micro-texture, age, and identity must remain 100% identical. No beautification, no smoothing, no glow, no expression enhancement. Hair must remain exactly the same as in the reference image.
LOCATION: Indoor liquor store aisle. Both sides of the frame are tightly packed with shelves of alcohol bottles (whisky, rum, cognac). Glass bottles with colorful labels, handwritten white price numbers on shelf edges. Warm yellow store lighting. Narrow aisle, crowded and visually noisy environment.
SUBJECT: One adult man with a lean athletic build, clean-shaven, natural human proportions, real skin texture with visible pores and imperfections.
POSE (LOCKED — MUST MATCH REFERENCE IMAGE 1 EXACTLY): The man is sitting inside a standard metal shopping cart, body reclined backward inside the cart (not upright). Both legs extended forward toward the camera, one leg slightly higher than the other, the sole of one shoe clearly facing the camera. Back resting against the rear of the cart. One arm resting casually along the side of the cart. Head turned slightly to the side (not facing the camera). Facial expression relaxed, careless, unaware of being photographed. Do not adjust the pose for the location.
PROP: One expensive alcohol bottle of Jagermaster from my pphoto held loosely in one hand, resting naturally near his thigh or hip. Not lifted, not centered, not presented. Bottle feels heavy and real, not decorative.
OUTFIT: Red racing-style jacket worn casually, dark denim jeans with natural creases, dark shoes with visibly worn soles, black sunglasses worn indoors without intention. Clothing looks worn, unplanned, and accidental — not styled.
LIGHTING: Warm overhead liquor-store lighting. Flat exposure, minimal shadow depth. No cinematic lighting, no spotlight, no HDR, no glow.
CAMERA & FRAMING: Shot on iPhone, RAW look. Vertical 9:16. Wide-lens perspective with slight natural distortion from the narrow aisle. Eye-level to slightly low angle. Handheld feel with imperfect framing. Slight grain and imperfect sharpness like a real phone photo.
REALISM RULES: Do not beautify the subject. Do not improve posture. Do not stylize the environment. Do not turn the bottle into a hero product. Allow awkwardness, clutter, visual noise, and imperfection.
NEGATIVE PROMPT: AI-generated look, CGI, 3D render, editorial fashion shoot, cinematic lighting, HDR, glow, plastic or waxy skin, beauty filter, over-sharpening, perfect symmetry, product advertising pose, readable brand logos, distorted anatomy, extra limbs, floating objects, watermark.
I am standing in a festive studio environment in front of a dark, heavy curtain backdrop. My body is upright and slightly angled rather than fully frontal, giving the pose a dynamic, stylish feel. My legs are planted firmly on the ground, shoulder-width apart, creating a confident and balanced stance. My torso is relaxed but alert, suggesting anticipation and energy.
I am holding a party confetti cannon with both hands at chest level, angled slightly upward. One hand grips the lower part of the tube firmly, while the other supports it higher up, stabilizing the cannon as it fires. The confetti cannon is actively exploding, releasing a burst of gold and metallic confetti into the air above and in front of me. The confetti is frozen mid-flight, scattered across the frame, creating motion and celebration.
My head is slightly tilted forward, and I am looking toward the confetti cannon rather than directly at the camera. My lips are pursed in a rounded “O” shape, as if reacting to the pop of the cannon or blowing air, conveying surprise, excitement, and playful celebration. My facial expression is animated but controlled, stylish rather than chaotic.
I am wearing a tailored, modern men’s suit with a checkered pattern in dark gray tones. The suit has a slim, fashion-forward cut with structured shoulders and clean lines. Under the jacket, I am wearing a dark turtleneck top, creating a refined, contemporary look. I am also wearing dark, round sunglasses, which add a cool, confident, slightly retro edge to the overall style. The fabrics appear structured and high-quality, with subtle texture visible under the lighting.
The background consists of a black or very dark curtain, providing strong contrast and allowing the gold confetti to stand out vividly. The environment feels like a controlled studio setup rather than a real party location, emphasizing an editorial, fashion-oriented aesthetic.
The lighting is focused and dramatic, illuminating my face, suit, hands, and the confetti clearly while keeping the background subdued. Highlights catch on the confetti pieces, creating sparkling points of light throughout the scene. Shadows remain soft and intentional, adding depth without obscuring detail.
The camera is positioned at approximately eye level, creating a natural, engaging perspective. The shot is framed as a mid-to-full body portrait. The image is captured with a standard-to-portrait focal length (approximately 50mm–85mm), producing realistic proportions and a clean separation between subject and background. The depth of field is moderate, keeping both me and the confetti sharp.
The final image has a cinematic, editorial fashion-photography style with crisp detail, controlled lighting, frozen motion, and a sophisticated New Year’s Eve or celebration mood. My face must remain exactly the same as the reference, fully preserved with accurate facial structure, proportions, and expression.
{ "image": { "main_description": "A gritty, cinematic medium shot of a battered, shirtless man standing on a balcony, smoking a cigarette and holding a glass of whiskey, exuding a tough, stoic demeanor after a fight.", "characters": { "main_reference_character": { "identity_anchor": "The character based on the provided reference photo, preserving strictly the user's identity source.", "ethnicity_and_phenotype": "Determined by the user provided reference photo.", "face_and_skin": "Skin texture and lighting interaction consistent with the scene, but facial features are strictly derived from the reference. The skin is marked with realistic bruises, cuts, abrasions, and smears of dried blood on the chest, arms, and face. A sheen of sweat is visible. ", "expression": "Stoic, calm, and indifferent. The mouth is slightly open, holding a lit cigarette.", "hair": "Voluminous, textured dark hair, styled in a messy, swept-up fashion. A beard and mustache are present (styled as per the input vibe).", "body_and_pose": "Muscular, shirtless torso showing definition. Standing upright facing the camera. The right hand is raised to the mouth holding a cigarette. The left hand is lowered, gripping a glass of amber liquid. Heavy white gauze bandages wrap both hands and wrists.", "outfit": "White linen drawstring trousers with a relaxed fit. Medical gauze patch taped to the left shoulder." }, "supporting_characters": [] }, "text_elements": { "content": "", "typography": "", "placement": "", "integration": "" }, "environment": { "location": "A wooden balcony or veranda overlooking a city. Snow, winter", "elements": "Wooden railings and pillars. Christmas tree and foliage visible to the left and right. A glass of whiskey/alcohol in hand.", "atmosphere": "Daytime, slightly hazy urban atmosphere. The mood is raw and recuperative. Snow, winter" }, "cinematography": { "lighting_setup": "Natural daylight, slightly diffuse but directional enough to create soft shadows that accentuate muscle definition and the texture of the injuries.", "color_grading": "Naturalistic with a slight grit; balanced skin tones contrasting with the red of the injuries and the green of the background foliage.", "shadows_and_highlights": "Soft contrast, detailed textures in the skin and fabric.", "reflections": "Subtle reflection in the glass of liquid." }, "camera_and_tech": { "framing": "Medium shot (Cowboy shot), capturing from the thighs up. Frontal angle.", "optics": "Medium focal length (approx 50mm-85mm), shallow depth of field blurring the city background.", "visual_fidelity": "High resolution, cinematic texture, realistic skin detailing." }, "style_and_mood": { "aesthetic": "Action movie aftermath, gritty realism, heroic resilience.", "emotional_vibe": "Tough, calm under pressure, battle-hardened." }, "aspect_ratio": "3:4" } }
Prompt: A documentary-style photograph shows a man with short brown hair, wearing a teal terry cloth robe, calmly sitting in a black velvet armchair on a dirt road. He holds a patterned Jagermaster shot, looking at the camera. Behind him, a Red Square and the burning Kremlin is fully engulfed in flames, with smoke billowing into a cloudy, overcast sky. A silver teapot rests on a small side table to his right. The ground is covered in gravel and grass. Winter, snow everywhere
SHOT: Composition: medium_shot, eye_level, [Detailed Focus: sharp focus on the man's face and the pouring liquid, slight motion blur on the liquid stream, bokeh background], [Blocking: man seated on left, anthropomorphic deer seated on right, close proximity at a cluttered table, Z-depth layering with bottle in foreground], [Framing: two-shot, centered composition]
SUBJECT: subject_1: Description: male, young adult, short textured hair with curls on top and faded sides, light beige button-down shirt, high detail, bright skin, natural skin texture and visible real skin pores, realistic gloss, sharp skin detail, natural glow, skin grain, subtle imperfections, soft matte finish, no smoothing Wardrobe: voluminous vibrant orange faux-fur coat, heavy texture, plush appearance Mood: satisfied, charismatic, happy, enjoying the moment, slight smirk, relaxed confidence subject_2: Description: anthropomorphic stag, realistic animal head with large antlers, detailed fur texture, human-like posture, expressive deer eyes reflecting the room lights Wardrobe: tailored emerald green velvet suit jacket, crisp white shirt underneath, elegant and dapper style Mood: stoic companion, surreal presence, calm observer
VISUAL DETAILS: Action: the man is tilting a distinctive rectangular dark green glass bottle, pouring a dark herbal liqueur into a clear heavy-bottomed shot glass, the liquid has a viscous realistic flow, the deer is watching the pour Props: Jägermeister bottle, iconic orange and black label with stag and cross logo, shot glass filled with amber liquid, scattered golden coins, tipped over empty bottles, black smartphone face down, cigarette lighter, messy white tablecloth Location: dimly lit private room, after-party atmosphere, moody bar setting, smoke haze in the air
CINEMATOGRAPHY: Lighting: hard_key, rim_light, volumetric_godrays, moody_club_lighting Contrast: punchy_dynamic, deep_blacks, high_contrast Color Grading: complementary_teal_orange, warm_cinematic, rich_amber_tones Color Saturation: vibrant_saturated Shadows: deep_teal, crushed_black, dramatic_falloff Midtones: warm_amber, golden_hour Highlights: clean_specular, soft_rolloff Skin Tones: warm_caramel, natural_tan, realistic_texture
VISUAL STYLE: style: cinematic_surrealism, commercial_lifestyle, high_end_editorial, magical_realism, hyper_realistic_cgi, gritty_glamour, vivid_colors, highly_detailed_textures, 8k_resolution, advertising_aesthetic
