GPT Image 2 prompts

Create a realistic vertical portrait photograph of {argument name="subject" default="a young East Asian woman"} standing centered in a small warm-toned home kitchen, framed from mid-torso upward and facing the camera directly. She has shoulder-length slightly wavy {argument name="hair color" default="dark black-brown hair"} with a natural side part and soft flyaway strands, clear skin, minimal makeup, dark eyes, and a calm subtle closed-mouth smile. She wears a plain {argument name="sweater color" default="beige"} crew-neck knit sweater with soft texture and relaxed fit. The background is softly out of focus: wooden upper cabinets, a narrow shelf with white cups and bowls, hanging kitchen utensils, light tiled walls, a countertop, a metal pot on the right, and a window on the right edge casting warm natural light. Use intimate documentary photography style, 35mm lens look, shallow depth of field, natural indoor lighting, gentle shadows, warm yellow-brown color grading, realistic skin texture, no text, no watermark, no exaggerated beauty retouching.

Create a dreamy vertical storybook illustration in the style of reverse-painted stained glass, with translucent layered color, fine gold filigree outlines, soft watercolor texture, and luminous reflections. The scene shows {argument name="character" default="a sleepy round hamster"} waking up in a deep quilted cream bed beside a tall old window on a rainy morning; the hamster has tan-and-white fur, tiny paws on the blanket, rosy nose, glossy black eyes, and is winking sleepily. Outside the rain-streaked window is a misty blue-gray European gothic city with steep rooftops, towers, warm yellow lit windows, fog, and storm clouds. Inside the room, use a cozy celestial theme: a puffy cream comforter embroidered with gold stars and crescent moons, blue patchwork accents, a small plush sheep tucked beside the hamster, and warm lamplike highlights contrasting with the cold rainy exterior. Include exactly 3 translucent glass fish floating in the air near the window: 1 large fish to the right of center, 1 small fish lower left, and 1 tiny fish beneath the large fish. Include exactly 5 small floating glass bubbles and exactly 1 glowing glass star between the fish. Add exactly 2 crystal globes: 1 large hanging bauble on the left containing delicate golden branches, and 1 tabletop globe on the right containing a crescent moon and stars. Add exactly 1 dangling crescent-moon crystal ornament chain on the upper right. Add delicate white flowers in a vase on the right windowsill and dark leafy plants blurred in the lower-left foreground. The palette should be {argument name="color palette" default="misty powder blue, pearl cream, muted gold, and soft warm amber"}; lighting should feel like {argument name="mood" default="quiet rainy dawn, cozy and magical"}. Use a vertical {argument name="aspect ratio" default="2:3"} composition, highly detailed, sparkling glass highlights, soft depth of field, no text, no watermark.

Create a polished vertical anime illustration of {argument name="character name" default="a Japanese high school girl"} standing inside a bright convenience store beside a refrigerated drink shelf. She is the single main subject, shown from mid-thigh up, facing slightly left while looking off to the left with a soft curious expression and parted lips. She has {argument name="hair color" default="glossy black"} hair with wispy bangs and exactly 2 long braids falling over her chest, warm brown eyes, fair skin with gentle blush, and thin round wire-frame glasses. Her school uniform has exactly 5 visible clothing components: a short-sleeved white sailor blouse, a navy sailor collar, white striped trim, a large deep red ribbon bow at the chest, and a dark navy pleated skirt. Add exactly 3 main accessories/held objects: round glasses on her face, a large navy shoulder school bag hanging from her left shoulder, and a clear plastic bottled tea drink with a pale yellow-green label held in both hands. Place her next to a right-side refrigerated shelf filled with neatly arranged bottled drinks and small Japanese-style price tags, with the labels softly detailed but not meant to be readable. The background should show a convenience-store entrance or window with bright daylight, blurred greenery and street shapes outside, and cool reflective interior surfaces. Use {argument name="visual style" default="high-quality modern anime, semi-realistic lighting, delicate linework, soft painterly shading"}, shallow depth of field, luminous backlighting, subtle rim light on the hair, natural skin tones, crisp focus on the girl, and a calm summer-after-school atmosphere. Use a vertical 2:3 composition, no text overlay, no watermark, no extra characters.

Goal: Create a realistic social-media-style photo collage of {argument name="character name" default="LINH NHI"}, a young East Asian cafe lifestyle influencer, shown in five candid portrait photos with soft warm lighting, natural skin texture, long brown hair with wispy bangs, a cozy cream cardigan/hoodie, delicate necklace, and feminine casual tank tops. The mood is cute, playful, slightly dreamy, and intimate, like a personal Instagram photo dump.

Canvas: Vertical 4:5 collage, approximately 1000 x 1250 pixels, with thin white dividers between panels. Use a realistic smartphone photography look, shallow depth of field, warm indoor cafe and bedroom lighting, subtle film grain, and soft color grading.

Layout: Use exactly 5 photo panels. Top row has 2 large panels of equal width. Bottom row has 3 smaller vertical panels of equal width. Add a small watermark in the lower-left corner of several panels: a blue dot followed by handwritten white text reading "LINHNHI".

Panel count and contents:
1. Top-left panel: Bedroom selfie angle. The woman wears a cream knit cardigan over a light floral camisole, sits near a bed and wall photos, looks off to the side with a coy expression, one finger touching her lips. Background includes a lamp, flowers, bedding, small wall prints, and a note that reads "Good Things Take Time" with a heart.
2. Top-right panel: Cafe table portrait by a window. She wears a white ribbed tank top with a tiny "alo" logo and a pale gray zip hoodie slipped off one shoulder. She winks, sticks her tongue out slightly, and holds up a large peace sign close to the camera. In front of her is an iced coffee cup with printed text "Good Coffee Better Days" and a small heart. Window text in the background reads "Coffee Brunch Lifestyle" with a heart.
3. Bottom-left panel: Cafe portrait at a table. She wears a gray cardigan, rests her cheek on one hand, looks sideways with a bored or thoughtful expression. A laptop edge is visible in the foreground, background is softly blurred.
4. Bottom-middle panel: Restaurant/cafe dinner setting. She wears a cream cardigan and covers her mouth and cheeks with both sweater-covered hands, eyes looking sideways, shy expression. A bowl of food, chopsticks, and a drink are visible at the bottom edge; warm bokeh lights behind her.
5. Bottom-right panel: Car or window-seat portrait. She wears a cream hoodie over a pink camisole, eyes closed or looking down, one hand on her forehead as if tired or pensive. Soft daylight through the window, black seat and city blur in background.

Visual style: Hyper-realistic Asian influencer photography, soft beauty-retouched but believable, natural facial expressions, warm beige and cream palette, cozy cafe aesthetic, glossy hair, gentle blush, no harsh shadows, no dramatic studio lighting.

Constraints: Keep the same woman consistent across all 5 panels. Use exactly the 5 poses listed, exactly the 2-over-3 collage structure, thin white borders, and the recurring small blue-dot "LINHNHI" watermark. Avoid extra panels, extra people, distorted hands, unreadable main text, or cartoon/anime styling.

Create a charming full-body fantasy character illustration in a hand-painted watercolor storybook style on a warm off-white paper background. Center a stocky, muscular, friendly male hobbit-like adventurer named {argument name="character name" default="Milo"}, standing barefoot and facing forward with a slight turn, smiling warmly and holding up a peace sign with his left hand. He has {argument name="hair color" default="curly chestnut brown"} messy hair, thick eyebrows, large expressive brown eyes, rounded ears, mutton-chop sideburns, light stubble, hairy arms and feet, and a cheerful approachable expression. Dress him in a sleeveless deep {argument name="tunic color" default="cobalt blue"} tunic with rough scalloped hem, a golden patterned sash belt, brown cropped trousers, leather wrist bracers, and colorful beaded bracelets on one wrist. Add one large visible travel backpack with exactly 4 distinct attached items: a rolled bedroll on top, a metal mug hanging on the side, a coiled rope, and leather straps with buckles. Across his chest place a brown leather shoulder strap with a square metal buckle and a small red accent strap. Behind him, include a simple wooden window frame like a rustic picture frame showing a bright blue sky with fluffy white clouds and a faint green horizon; the character overlaps the window, standing in front of it. Use soft pencil outlines, textured watercolor washes, gentle shading, warm earth tones, whimsical children’s book proportions, and a clean centered composition with no text, no logo, no watermark, and no extra characters.

Create a vertical 9:16 photorealistic social-media video still inside a bright fast-food burger restaurant. Show exactly 2 people at a wooden counter: a cute toddler boy on the left, standing and facing slightly toward the camera, wearing a white paper fast-food hat with red stripes, a light blue T-shirt, and a white apron with small red restaurant lettering; and a smiling adult woman on the right, leaning forward with both hands on the counter, wearing a blue denim jacket over a gray shirt, shoulder-length wavy blonde hair, and a wedding ring. The woman looks warmly at the child with an amused, encouraging expression, while the child has a calm, slightly mischievous face. Add a bold centered subtitle over the lower middle of the image reading {argument name="caption text" default="Please"} in large white rounded letters with a black drop shadow. Background: softly blurred fast-food interior with exactly 2 red pendant lamps hanging from the ceiling, 1 large digital menu board in the upper left, 1 glowing circular neon sign behind them, tiled wall, red seating, and daylight through windows. Use shallow depth of field, realistic skin texture, natural indoor lighting, warm colors, candid viral comedy-video framing, no extra characters, no watermark.

Goal: Create a polished 3D animated character design sheet for a cheerful young girl, suitable for animation reference.

Canvas: Wide horizontal 16:9 composition on a clean white studio background with soft even lighting, no visible floor line, no text, no logos, no watermark.

Layout: Show exactly 4 character depictions across the canvas: 1 large close-up portrait on the left occupying about 40% of the width, cropped from chest upward and facing slightly toward the viewer; 3 smaller full-body turnarounds on the right arranged left to right with even spacing: front view, three-quarter side view facing right, and back view.

Character details: The character is {argument name="character age and vibe" default="a cheerful preteen girl with a bright playful personality"}. She has {argument name="hair color and style" default="warm brown hair in a high messy ponytail with loose flyaway strands and side-swept bangs"}, large expressive brown eyes, soft rounded facial features, rosy cheeks, light freckles across the nose and cheeks, small purple hoop earrings, and an open happy smile in the close-up and front view. Add a colorful geometric triangular hair clip and a rainbow-striped ponytail tie.

Outfit: Dress her in {argument name="main outfit" default="an oversized color-block hoodie with a yellow hood and upper chest, cyan left sleeve and lower diagonal panel, purple right sleeve and diagonal panel, and a pink kangaroo pocket with pink drawstrings and dark cord tips"}. Pair it with navy athletic shorts with a vertical purple stripe, white crew socks with pastel colored stripes, and chunky colorful sneakers in pink, teal, yellow, purple, and white. Include a small purple wristband or watch on one wrist.

Visible counted elements: Exactly 4 character depictions total: large close-up portrait, full-body front view, full-body right-facing three-quarter view, full-body back view. Exactly 1 prominent triangular hair clip on each visible head where the front or side is visible. Exactly 1 ponytail tie. Exactly 2 hoodie drawstrings with dark tips. Exactly 2 earrings visible in the close-up if both ears are shown, otherwise at least 1 visible purple hoop earring. Exactly 2 socks and 2 sneakers on each full-body view.

Visual style: High-quality stylized 3D animation look, similar to a modern family-friendly animated film; soft subsurface skin shading, glossy lively eyes, detailed hair clumps, clean shapes, saturated candy colors, crisp character-sheet presentation, gentle shadows, professional model-turnaround lighting.

Constraints: Keep proportions consistent between all 4 depictions, preserve the same outfit colors and hairstyle in every view, use a white background only, do not add labels, props, scenery, extra characters, or text.

Create a cinematic vertical sci‑fi fashion illustration of {argument name="character name" default="JFC-01, the woman of the Gravity Lane"} walking through a futuristic megacity where architecture and gravity seem to bend to open a path for her. The main subject is a tall, elegant young woman in the lower-left foreground, full body, striding confidently toward the viewer while looking slightly up and to her left with a calm, distant expression. She has very long wind-swept {argument name="hair color" default="silver-white"} hair flowing dramatically behind her, pale skin, refined facial features, subtle makeup, and small dangling earrings. Her outfit is high-fashion gothic cyberpunk: a long black layered coat with wide sleeves, structured shoulders, black high-collar inner dress, flowing asymmetrical skirt panels, pale patterned lining visible inside the coat, slim belts and hanging metallic charms, a small glowing cyan pendant-like accessory, and polished black heeled boots. The setting is a vast vertical futuristic city of steel, glass, and concrete, with towering cylindrical skyscrapers, skybridges, floating circular platforms, and suspended transit structures disappearing into misty depth. A massive segmented metallic pedestrian lane rises and curves upward on the right side of the composition, as if gravity has shifted; it has articulated panels, railings, mechanical joints, glowing cyan details, and warm vertical light bars. The ground is a wet reflective metal walkway with panel seams, grates, rails, and embedded cyan light strips, creating strong perspective lines toward the background. Include exactly 5 small distant pedestrians: 3 silhouettes on the elevated curved bridge and 2 silhouettes on the lower walkway in the distance. Use bright overcast daylight with soft clouds, atmospheric haze, rim lighting on the hair, glossy reflections on metal, and a premium concept-art/anime-realism hybrid style with ultra-detailed materials. Color palette: black, graphite, silver, pale concrete, cyan accent lights, and warm white lamps. Camera: low-angle full-body fashion shot, 3/4 view, wide architectural depth, dynamic leading lines, sharp foreground detail and slightly hazy background. No visible title text, no logo, no watermark, no extra characters in the foreground.

Goal: Create a premium cinematic illustrated buddy-cop character bible sheet for two original characters, {argument name="left character name" default="Ryder"} and {argument name="right character name" default="Deshawn"}, with a chaotic action-comedy Miami police tone.

Canvas: Wide 16:9 horizontal poster/character sheet on a mostly white background, high-energy comic-book concept art with ink splatters, brush lettering, dramatic lighting, saturated accent colors, and gritty cinematic polish.

Layout: Split-screen partner format with exactly 2 full-body/three-quarter characters: 1 character on the left and 1 character on the right. Use a bold vertical red paint-streak dividing element in the center. Place a huge central brush slogan reading {argument name="central slogan" default="WHATCHU GONNA DO"} in red, stacked in three lines, with the smaller caption “PARTNERS. BARELY.” underneath. Add a Miami skyline silhouette with palm trees running along the bottom behind both characters, plus paint splatter textures throughout.

Left character details: Show Ryder as a tall, confident, cool Black male Miami PD detective wearing an all-black tailored suit, black open-collar shirt, gold chain, gold watch, black belt, visible police badge clipped at the waist, and a holstered sidearm. He stands relaxed with one hand in his pocket, chin lifted, smirking, looking self-assured. Behind him use gold and black splashes, a black sports car at the lower left, palm trees, and city buildings. Large gold brush-script name at the top left: “RYDER”. Small text under it: “MIAMI PD / WHATCHU GONNA DO.” Add exactly 2 handwritten note blocks on the left side: “DISCIPLINE DRIVES RESULTS.” and “SAME CITY. DIFFERENT APPROACH.”

Right character details: Show Deshawn as an energetic, expressive Black male Miami PD detective with short curly hair, startled wide eyes, open mouth, and raised palms as if panicking or overreacting. He wears a teal Hawaiian shirt with white hibiscus flowers over a white T-shirt, tan cargo pants, bracelet, watch, gold chain, visible police badge at the waist, and a casual slightly messy stance. Behind him use teal splashes, palm trees, and city skyline. Large teal brush-script name at the top right: “DESHAWN”. Small text under it: “MIAMI PD / WHATCHU GONNA DO.” Add exactly 3 handwritten note blocks on the right side: “GOOD PEOPLE. BAD SITUATIONS.”, “OVERTHINKS. OVERREACTS. STILL SHOWS UP.”, and “TEAMWORK (SOMEHOW) WORKS.”

Bottom center details: Include exactly 4 small square color swatches in a row: black, gold, teal, and light gray/white. Beneath them add the tagline in stacked text: “ONE COOL. ONE SCREAMING. BOTH GET IT DONE.” with “BOTH GET IT DONE.” emphasized in red.

Visual style: High-end digital illustration, dynamic action-comedy poster art, crisp anatomy, expressive faces, cinematic shadows, rim lighting, sharp ink outlines, paint splashes, distressed brush typography, urban Miami atmosphere, premium character bible sheet presentation.

Constraints: Use only the 2 named characters, exactly 5 handwritten note blocks total, exactly 4 color swatches, no franchise references, no extra logos, no watermark, keep all text legible and spelled exactly as specified.

A breathtaking vertical view of a futuristic metropolis floating gracefully above an endless sea of dense, rolling dark grey clouds at twilight. The sprawling city skyline features numerous towering skyscrapers with glowing windows that cast warm amber and orange lights onto the urban landscape below. Dominating the upper portion of the frame is a magnificent cosmic ring, a glowing circular nebula composed of {argument name="nebula colors" default="vibrant purples, deep blues, and brilliant warm golden hues"}, sprinkled with countless twinkling stars and distant galaxies across the pitch-black night sky. The composition is balanced and majestic, with the dark cloud layer grounding the lower foreground, contrasting sharply with the radiant cosmic phenomenon above. The lighting is surreal and ethereal, blending the warm artificial glow of the city lights with the cosmic luminescence of the nebula. The atmosphere is quiet, awe-inspiring, and mystical, evoking a sense of interstellar wonder and urban isolation. The detailed textures of the soft, voluminous clouds, the sleek glass and steel architecture of the skyscrapers, and the starry cosmic dust create a high-contrast, visually striking scene.

{argument name="subject" default="AI Gateway"} vintage sign

turn {argument name="target" default="it"} into a {argument name="style" default="future building"}

Please capture a realistic screenshot from a fictional next-generation 3D open-world {argument name="game genre" default="romance RPG"}, presented from the male protagonist’s first-person perspective.  On the {argument name="location" default="beach"}, {argument name="character" default="Morrigan Aensland from Darkstalkers"} invites the protagonist to help her apply sunscreen.  The overall visual style must feature high-quality cartoon-rendered 3D characters combined with Unreal Engine 5-level graphics, achieving AAA-quality visual fidelity. It should include ultra-detailed character modeling, realistic skin shading, cinematic lighting, PBR materials, high-precision clothing textures, and finely rendered classroom environments. The final image must look like an actual playable game screenshot, including a complete game user interface: minimap, quest display, character status bars, interaction prompts, dialogue subtitles, HUD elements, and more.

9:16, wearing a {argument name="clothing" default="qipao"}, {argument name="lighting" default="soft light bloom"}, dreamy blur, high-angle shot looking down, {argument name="model type" default="tall slender model figure"}, refined makeup, fox-like beauty face

Create an ultra-realistic close-up studio portrait of an {argument name="subject" default="adult man"} with a confident, thoughtful expression, photographed from the chest upward in a premium modern editorial style. Give him {argument name="hair style" default="thick, neatly styled short black hair"} with natural volume on top and clean tapered sides. Add a well-groomed full beard and mustache with sharp but natural edges. He is wearing transparent rectangular eyeglasses with subtle reflections from the studio lights. Dress him in a fitted black turtleneck sweater layered underneath a sophisticated black tailored blazer with structured lapels. Keep the outfit completely minimal and monochrome with no visible jewelry or unnecessary accessories. Pose him facing slightly away from the camera, with his head gently tilted upward and his eyes looking toward the upper-right side of the frame, creating a calm, intelligent, aspirational mood. Use dramatic dual-tone studio lighting: {argument name="rim light color" default="vivid magenta/purple"} rim light illuminating the left side of his hair and face, and vibrant electric-blue/cyan light illuminating the right side. Keep soft neutral frontal lighting on the face so the skin remains realistic, detailed, and properly exposed. Create a blurred futuristic studio background with a rich gradient transitioning from deep purple and magenta on the left to electric blue on the right. Add a glowing diagonal neon-magenta light bar in the lower-left background for extra visual depth. Emphasize realistic skin texture, detailed beard hairs, sharp eyes, natural eyeglass reflections, crisp fabric texture, cinematic contrast, shallow depth of field, smooth colorful bokeh, premium personal-branding photography, high-end corporate editorial aesthetic, ultra-photorealistic, 85mm portrait lens look, f/1.8, 8K detail, vertical 4:5 composition.

A photorealistic candid travel portrait of a {argument name="subject" default="young East Asian woman"} standing on a {argument name="location" default="quiet sandy shoreline beside large moss-covered rocks"}, with a magnificent {argument name="landmark" default="historic stone abbey and medieval castle-like architecture"} rising dramatically on a rocky island behind her. She has long straight dark brown hair falling naturally over one shoulder, soft youthful facial features, and a gentle warm smile while looking directly at the camera. She is wearing a long oversized black coat with her hands casually tucked inside the pockets, layered over a light-colored outfit. A large soft cream-white scarf is wrapped warmly around her neck, hanging down the front with a small black designer-style emblem near the end. A delicate chain shoulder bag is partially visible. The composition captures her in the foreground while the vast historic abbey dominates the background, surrounded by ancient stone walls, rocky cliffs, sandy tidal flats, and a calm coastal atmosphere. A few small distant vehicles and people add realistic scale to the scene. Soft natural evening light and a clear pale blue sky create a peaceful European travel mood. Ultra-realistic photography, authentic candid travel photo, natural skin texture, realistic fabric details, soft cinematic lighting, subtle smartphone camera aesthetic, slightly dreamy color grading, natural proportions, detailed architecture, peaceful coastal atmosphere, vertical composition, 3:4 aspect ratio.

Ultra-realistic {argument name="ethnicity" default="Asian"} woman in her early 20s wearing a stunning, elegant {argument name="dress color" default="red"} one-piece dress with a fitted silhouette, delicate fabric details, and a graceful neckline. Natural makeup, long silky dark hair, soft confident expression, feminine and sophisticated look, standing naturally in a {argument name="setting" default="luxurious modern setting"}. Cinematic soft lighting, realistic skin texture, natural body proportions, high-fashion editorial photography, subtle depth of field, premium magazine aesthetic, photorealistic, 4K, vertical 9:16.

“using this json as reference, generate a person holding my product [attach product image]”

> GPT-Image 2.5 generates the photo with that person holding your product

compare it with a version generated without the reference and look at the difference in the lighting and color grading

> save the generated character photo you’re happy with as your reference

> for future generations, attach the character photo each time and ask it to preserve the same facial features

now you have a reference character you can use across multiple product photos

you can also iterate the base json prompt and chat back and forth with GPT-6 Astra based on what you want, then repeat the same process..

i like this because it gives you much more direction over the color grading instead of leaving everything up to the model

the basic colours and grainy look are some of the things that can make an image feel AI-generated, so pay attention to those when comparing your results

this is how you can start building a library of high quality ugc images around your own products

the json gives GPT-Image 2.5 the lighting and color direction, your character reference helps with consistency, and you control the product placement

once you have that starting point, you can keep creating variations without writing everything from scratch

GPT-Image 2.5 Sunburst & Flare are available on Higgsfield. try this with your own product and reference images there

Photorealistic cinematic portrait of a {argument name="subject" default="handsome adult man with tousled medium-length brown hair and a neatly trimmed beard"}, wearing a {argument name="outfit" default="sophisticated black tailored suit with a crisp white open-collar shirt"}, elegant and modern with no tie. He is standing at a slight angle to the camera, one hand casually resting in his trouser pocket while the other hangs naturally by his side, with relaxed shoulders and a confident, composed posture. His head is slightly turned toward the camera, maintaining a calm, intense, subtly contemplative expression. Set in a {argument name="setting" default="luxurious modern rooftop at twilight"}, with softly illuminated city buildings and distant skyline lights creating an elegant urban atmosphere in the background. Subtle warm architectural lights contrast with the cool blue tones of the evening sky. Cinematic depth, gentle atmospheric haze, realistic environmental reflections, and softly blurred city lights. Soft directional key light illuminates his face naturally, with a subtle warm rim light separating his hair and shoulders from the background. Natural skin texture, sharp expressive eyes, realistic facial details, authentic hair strands, realistic fabric texture, shallow depth of field, professional fashion photography, 85mm portrait lens, f/1.8, creamy bokeh, cinematic contrast, sophisticated color grading, luxury fashion editorial aesthetic, ultra-detailed, photorealistic, 8K.

Use the uploaded image as the main composition, styling, pose, lighting, and environment reference. Create a photorealistic 1980s-inspired Miami lifestyle fashion portrait of an {argument name="subject" default="adult man"} standing beside a {argument name="car" default="glossy black vintage convertible"} during golden hour.

Frame him from approximately mid-thigh upward, leaning casually against the open driver-side door with a relaxed, confident expression while looking toward the camera. One hand rests naturally near the car while holding a pair of classic aviator sunglasses, and the other hand is casually tucked into his trouser pocket.

Dress him in an elegant {argument name="outfit" default="cream/off-white linen suit"} with a relaxed tailored blazer and high-waisted pleated trousers. Underneath, add a black open-collar shirt with the top buttons undone for a sophisticated retro look. Add a slim black leather belt with a polished gold buckle and a classic gold-tone wristwatch. Keep the styling refined, masculine, minimal, and authentic to the 1980s.

Place the scene on a glamorous Miami Beach–inspired boulevard, surrounded by tall palm trees, pastel Art Deco architecture, outdoor cafés, vintage cars, and softly blurred pedestrians in the distance. Position a pastel pink-and-white Art Deco hotel building in the background to enhance the vintage South Beach atmosphere.

Use warm late-afternoon sunlight, golden rim lighting around the subject, soft shadows, subtle lens flare, cinematic highlights reflecting across the black car, and a warm nostalgic film color grade. Add realistic skin texture, natural facial details, crisp linen fabric texture, shallow depth of field, soft atmospheric bokeh, subtle film grain, and premium editorial photography.

Add handwritten cream-colored text “{argument name="text" default="1980’s"}” in the upper-right corner with a loose underline stroke.

Style: vintage luxury fashion campaign, 1980s Miami aesthetic, cinematic editorial photography, warm analog film look, realistic DSLR quality, 50mm lens, shallow depth of field, ultra-detailed, natural proportions, photorealistic.

Aspect ratio: 4:5 vertical.

Use the uploaded image as the main restoration and identity reference. Convert this severely damaged old portrait into a clean, fully restored modern-looking photo while preserving the original appearance, pose, and composition.

Restore all missing and damaged areas of the photograph, including torn sections, faded parts, scratches, stains, cracks, peeling emulsion, discoloration, and burned or washed-out regions. Reconstruct the man and woman completely so both subjects appear whole, natural, and clearly visible.

Keep the same arrangement: the woman standing in front holding a large bouquet of flowers, and the man standing slightly behind her. Preserve their facial features, expressions, body proportions, posture, and elegant formal clothing, but refine everything to look polished, realistic, and complete.

Transform the image from an antique sepia damaged print into a high-quality modern portrait with:

clean natural skin tones

realistic facial details

sharp focus

balanced lighting

soft studio background

improved clarity and texture

realistic modern photo finishing

The final image should feel like a professionally restored contemporary portrait, as if the same couple was photographed clearly with a modern camera, while still keeping the classic formal elegance of the original scene.

Style: photorealistic, high detail, restored portrait, modern studio photography, clean, elegant, natural colors, sharp and realistic.

Ultra-realistic casual portrait of {argument name="subject description" default="a young woman"} sitting comfortably in a dark folding lounge chair, photographed indoors with a smartphone. She has long, straight dark-brown hair falling naturally over her shoulders, soft facial features, smooth natural skin, dark expressive eyes, and a warm playful smile with her eyes gently squinting. She wears small silver hoop earrings and {argument name="headwear" default="a pale yellow baseball cap with a playful vintage graphic and lettering on the front"}.
She is dressed in {argument name="clothing" default="a simple fitted white long-sleeve V-neck top and light blue relaxed-fit jeans"}. Her arms are comfortably crossed over her torso, creating a relaxed and confident pose. She is seated with her knees slightly raised toward the camera.
The setting is a cozy indoor balcony or casual room, with a beige wall, a large window covered by sheer patterned curtains, tiled floor, and dark folding chairs in the background. Soft natural daylight enters through the window, producing even illumination and gentle shadows.
Authentic smartphone photography, candid lifestyle aesthetic, natural skin texture, realistic hair strands, detailed clothing fabric, subtle imperfections, soft neutral color palette, relaxed youthful mood, shallow depth of field, realistic proportions, photorealistic, high resolution, vertical 4:5 composition.
Negative prompt: cartoon, anime, CGI, plastic skin, excessive makeup, distorted face, asymmetrical eyes, malformed hands, extra fingers, unnatural pose, unrealistic hair, blurry subject, oversaturated colors, warped background, excessive retouching, text artifacts, watermark.

A {argument name="nationality" default="Taiwanese"} {argument name="portrait style" default="Instagram-style"} adult female influencer, clearly an adult, with fair cool-toned porcelain skin and a few natural faint freckles on the nose bridge and cheeks. She has a {argument name="facial features" default="refined, cool fox-like small face"}: narrow and flowing in shape, with a defined jawline and a small, slightly pointed chin that is not overly sharp. Slender natural eyebrows with a soft arch. Slightly elongated eyes with narrow double eyelids, clear inner corners, and gently upturned outer corners; her gaze is quiet, cool, and slightly distant. Slim straight nose with a small rounded tip. Refined lips, the upper lip slightly thinner and the lower lip a little fuller, with naturally relaxed corners. Not a glamorous or heavily made-up influencer face, but a natural, lightly mature, cool Japanese-beauty look that is distinctive and holds up well. Slender, long-limbed figure with natural proportions. 9:16

Transform this photo into an elevated fashion studio portrait. Choose a {argument name="background color" default="complementing-color"} background that enhances the subject's skin tone. Keep a tight head-and-shoulder composition with the subject centered and facing the camera straight with an optimistic expression. Apply directional lighting with subtle shadows. Preserve natural skin tones while making the image polished, minimal, and editorial—like a magazine photoshoot.