Generate an ultra-photorealistic vertical selfie, 9:16. Use the TWO uploaded face references (a girl and a guy) and preserve identity strictly 1:1: 100% likeness, don't change features, proportions, age, eye/nose/lips/eyebrow shape, skin tone. Faces fully recognizable, no "beautifying."

Scene and pose: the girl and guy are sitting side by side on the edge of a metal grating platform at the very top of the Empire State Building in New York City, at an extreme height above Manhattan. Both looking at the camera, a light confident smile. Required: relaxed posture, weight shift, asymmetrical pose (asymmetry: shoulders at different heights, natural spine curve, torso slightly turned). Hands and fingers anatomically correct.

Camera/perspective: iPhone selfie aesthetic, wide angle ~24mm, slight perspective distortion like a front camera, camera slightly above eye level. Faces large in frame (head+shoulders), but the edge of the platform and the grating beneath them must be visible, and through the mesh — depth/emptiness and the Manhattan skyline far below, so the height reads immediately. No background blur — background should be

 legible.

Location (describe as precisely as possible):

— The uppermost service platform of the Empire State Building's spire/mast structure, a narrow area of galvanized steel open grating with square cells, visible metal ribs, edge profile trim, bolts/nuts/washers, mounting plates — consistent with the building's iconic Art Deco steel framework and antenna mast.

— Right next to the couple — a technical unit: a metal box with a control panel, several round buttons (red/black/metallic), switches/terminals, cables in conduit. No readable text/labels.

— Nearby, mounted aviation warning lights: two red dome lamps in metal housings (as used on the building's actual broadcast tower).

— Behind them — the building's lattice antenna/mast structure with steel diagonal braces, joint connections and cables, rising upward beyond the frame.

— Background: the recognizable Manhattan skyline far below — a dense grid of skyscrapers, the Hudson and East Rivers, Central Park in the distance, light atmospheric haze, clear sky and daylight (or soft golden hour), overwhelming sense of extreme height.

Outfits and accessories (strictly as in the references):

Girl:

— Clothing: a black T-shirt; Bottom — fully black, total-black aesthetic (black pants as in reference: heavy fabric/leather, high waist).

— Headwear: a black ribbed knit beanie with large "cat ear" details, as in reference 2. The beanie sits normally ON the head, NOT pulled down over the face; the face is fully open and clearly visible.

— Jewelry: large silver hoop earrings (several rings/cuffs in the ear as in reference 2) + a black choker snug around the neck.

— No masks/coverings on the face — face fully open.

Guy:

— Clothing: a black ribbed tank top ("wife-beater" style), fitted, as in reference 1 (texture/ribbing visible, natural folds). Bottom — black (pants/trousers in a dark tone), overall strict total-black look.

— Accessories: no cap, no bandana/headband, no face mask — face and head fully open.

Quality/photorealism: photo raw style, Sony A7R look, ultra photorealistic, high detail, sharp focus on faces, natural colors, realistic shadows and contact shadow under the body/legs on the grating, no CGI.

Negative prompt (updated):

face change, identity drift, different makeup, different hair, any face covering on either person, balaclava/mask/bandana, cap/hat on the man, hat covering the woman's face/eyes, outfit change, wrong accessories, extra fingers/limbs, warped hands, floating, mismatched shadows, blur, plastic skin, CGI look, text, watermark, UI, logos.

Vertical 9:16 ultra-realistic portrait of a young adult female inside a luxury car with cream leather seats and panoramic roof, wearing a distressed vintage baseball cap, dark oversized leather jacket, soft natural daylight, relaxed direct gaze, one hand gently touching the cap brim, polished casual streetwear mood, built 100% from the unaltered facial features of the reference image, preserve the original face 100% exactly, hair unchanged, high-end cinematic photography, professional depth of field, natural/cinematic color grading. STRICT FEMININE LOCK: elegant feminine styling only, graceful female outfit, soft feminine proportions, refined pose, tasteful feminine accessory, no masculine tailoring, no boxy menswear, no masculine body language, no facial or hair alteration. single person only, one subject, no extra people, no duplicate face, no cloned body, natural anatomy, realistic hands, realistic eyes, no distorted face, no extra fingers, no warped body, keep the subject as a young adult, not teenage, not older adult, no facial modification, no hair modification, no over-beautification, no plastic skin, gender expression must come only from outfit, styling, pose, and body presentation; do not alter facial identity or hair, completely clean and soft background, smooth uniform gradient, no noise, no grain, no film grain, no sensor noise, no compression artifacts, no banding, perfectly smooth color transitions, extremely high and sharp image quality, soft clean bokeh, no noisy texture in the background

Vertical 9:16 ultra-realistic portrait of a young adult male inside a luxury car with cream leather seats and panoramic roof, wearing a distressed vintage baseball cap, structured dark leather jacket, clean masculine streetwear styling, soft natural daylight, relaxed direct gaze, one hand adjusting the cap brim, polished confident mood, built 100% from the unaltered facial features of the reference image, preserve the original face 100% exactly, hair unchanged, high-end cinematic photography, professional depth of field, natural/cinematic color grading. STRICT MASCULINE LOCK: strictly masculine styling only, menswear tailoring, structured shoulders, straighter silhouette, boxier fit, men’s fit, masculine proportions, sharp lines, minimal masculine accessory: metal watch OR signet ring OR thick chain, no feminine elements, no makeup. grooming consistent with the reference image; keep facial hair if present; if not, clean-shaven. single person only, one subject, no extra people, no duplicate face, no cloned body, natural anatomy, realistic hands, realistic eyes, no distorted face, no extra fingers, no warped body, keep the subject as a young adult, not teenage, not older adult, no lipstick, no eyeliner, no nail polish, no long manicured nails, no dress, no skirt, no handbag/purse, no feminine pose or feminine body language, gender expression must come only from outfit, styling, pose, and body presentation; do not alter facial identity or hair, completely clean and soft background, smooth uniform gradient, no noise, no grain, no film grain, no sensor noise, no compression artifacts, no banding, perfectly smooth color transitions, extremely high and sharp image quality, soft clean bokeh, no noisy texture in the background

Keeptheface 100% identical to the reference. No changes to identity, facial shape, eyes, nose, lips, or hairstyle. Only change lighting and pose. With zero percent change in the faces of the references: photorealistic portrait of a young person (gender neutral) sitting on the ground hugging a large, damaged, bloodstained wooden or sculpted map of Iran, as if it a monument. Expression slightly sad, calm, and emotional. Outfit simple, long-sleeve black, no logos or patterns. Hair natural and neat. Skin with realistic texture, pores, and subtle imperfections. Background plain white to emphasize person and sculpture. Lighting soft and natural, highlighting emotional and sorrowful atmosphere. Hair color, eye color, and main facial features must remain 100% unchanged.

Use the person from the reference image and keep the same facial identity consistent with the reference.
Ultra-realistic nighttime street photography, vertical 4:5 portrait, close-up side-angle of a young woman sitting on a motorcycle, upper body visible, looking back over her shoulder directly into the camera. She wears a matte black full-face motorcycle helmet with the visor raised, revealing only her eyes, eyebrows, and upper cheeks. A few strands of hair visible beneath the helmet (hair color unspecified). Light-colored eyes with long eyelashes, subtle natural makeup, soft eyebrows, calm and confident expression. Black oversized leather jacket with realistic texture and folds. One hand resting on the motorcycle handlebar, motorcycle only partially visible in the lower right corner. Background features a wide empty city street at night with zebra crossing lines, wet asphalt reflecting light, modern streetlights creating soft bokeh, deep black sky, cinematic urban atmosphere. Shot using direct smartphone flash, bright frontal lighting on the face and helmet, high contrast, sharp details, realistic skin texture, matte helmet finish with subtle reflections and tiny imperfections, shallow depth of field, centered composition, eye-level angle, ultra-detailed, photorealistic, HDR, 8K, natural colors, crisp focus, premium smartphone photography, no smile, minimalistic aesthetic.
Negative Prompt:
blurry, low quality, low resolution, cartoon, anime, CGI, painting, illustration, overprocessed skin, excessive beauty filter, exaggerated makeup, extra people, open visor reflections covering eyes, distorted helmet, extra fingers, deformed hands, bad anatomy, cropped face, motion blur, lens flare, watermark, logo, text, oversaturated colors, noisy image, unrealistic lighting.

Use the person from the reference image and keep the same facial identity consistent with the reference.
Ultra-realistic nighttime street photography, vertical 4:5 portrait, close-up side-angle of a young man sitting on a motorcycle, upper body visible, looking back over his shoulder directly into the camera. He wears a matte black full-face motorcycle helmet with the visor raised, revealing only his eyes, eyebrows, and upper cheeks. A few strands of hair visible beneath the helmet (hair color unspecified). Light-colored eyes, thick natural eyebrows, subtle masculine facial features, calm and confident expression. Black oversized leather jacket with realistic texture and folds. One hand resting on the motorcycle handlebar, motorcycle only partially visible in the lower right corner. Background features a wide empty city street at night with zebra crossing lines, wet asphalt reflecting light, modern streetlights creating soft bokeh, deep black sky, cinematic urban atmosphere. Shot using direct smartphone flash, bright frontal lighting on the face and helmet, high contrast, sharp details, realistic skin texture, matte helmet finish with subtle reflections and tiny imperfections, shallow depth of field, centered composition, eye-level angle, ultra-detailed, photorealistic, HDR, 8K, natural colors, crisp focus, premium smartphone photography, no smile, minimalistic aesthetic.

Style: High-resolution, hyper-photorealistic candid couple's portrait.

Core Instruction: Analyze the reference image. Determine the gender of the primary subject in this reference image. 
- If the subject is female: Pair her with a universally recognized, A-list, charming male celebrity (e.g., a popular Hollywood actor).
- If the subject is male: Pair him with a universally recognized, A-list, charming female celebrity.
The AI must perfectly replicate the specific facial features, expressions, and likeness of the original subject and blend them naturally next to the chosen celebrity.

Composition and Pose: A tight, intimate, close-up couple's portrait. Both individuals are in a close embrace with their cheeks gently touching or heads leaning in, smiling warmly and genuinely directly at the camera. The framing should focus on their faces, necks, and shoulders. The perspective is from an external photographer, NOT a selfie.

CRITICAL DETAIL (Exclusions): There must be absolutely NO smartphones, cameras, or handheld electronic devices visible anywhere in the frame. Neither subject is holding a phone. Their hands and arms are positioned naturally (e.g., resting on shoulders or out of frame) to ensure no device is in the shot.

Setting and Lighting: A natural, casual location such as a cozy, sunlit outdoor cafe patio during the daytime. Use warm, golden-hour natural lighting that highlights their faces and creates soft shadows. The background should be slightly blurred (shallow depth of field) with soft bokeh, keeping the absolute sharp focus on both faces.

Technical Details: Emphasize extremely sharp details on skin texture, realistic eyes, individual hair strands, and subtle smile lines. The final result should look like an authentic, professional portrait photograph.