GPT Image 2 prompts

Goal: Create a black-and-white manga page with exactly 2 stacked panels showing a cute small dog discovering a computer keyboard and reacting with excitement.

Canvas: Vertical manga page, portrait orientation, two equal horizontal panels separated by a thick black gutter, clean black border around each panel, grayscale screentone shading, hand-inked line art, polished modern manga style.

Main character: A small, adorable puppy with floppy ears, large sparkling eyes, a white stripe down the face, darker patches on the head and body, a fluffy raised tail, and a collar with a round ring tag. The dog is seated at a desk in an office chair, facing a desktop computer. Use {argument name="dog breed style" default="cute mixed-breed puppy resembling a Jack Russell terrier"}.

Panel 1: The dog sits behind a wooden desk, looking surprised and curious at a large desktop monitor on the left. A keyboard lies in front of the dog. The dog’s mouth is slightly open, eyes wide, with exactly 3 surprise marks above its head. Background: a cozy home office with a window and curtains on the far left, a framed landscape picture on the wall, a small potted plant on a cabinet, and bookshelves on the right. Include one vertical oval speech bubble on the right side containing the Japanese text {argument name="first speech bubble" default="これは何?"}. Mood: confused curiosity.

Panel 2: Same dog, same desk and computer setup, now leaning forward happily and pressing the keyboard with one front paw. The dog smiles broadly with tongue visible, eyes shining, tail lifted. Add dynamic radial speed lines in the background and sparkling effects around the keyboard. Include exactly 8 sparkle effects around the dog and keyboard area. Include one vertical oval speech bubble on the left side containing the Japanese text {argument name="second speech bubble" default="ピカピカだ!"}. Mood: delighted discovery.

Objects and counts: Exactly 2 manga panels; exactly 1 dog appearing in both panels; exactly 1 desktop monitor; exactly 1 keyboard; exactly 1 office chair; exactly 2 speech bubbles total; exactly 3 surprise marks in panel 1; exactly 8 sparkle effects in panel 2; visible background items include 1 window, 1 framed picture, 1 potted plant, and 2 bookshelves or bookcase areas.

Visual style: Monochrome Japanese manga, expressive cute animal character, detailed fur texture, screentone gradients, crisp ink outlines, dramatic but family-friendly expressions, clean readable composition. Keep the speech bubbles vertical and the Japanese text hand-lettered in black. No color, no watermark, no extra panels, no extra characters.

Create a realistic documentary-style outdoor photograph of a partially open {argument name="device" default="silver laptop"} resting on a rough concrete curb beside dense wild grass. The laptop is open only a few inches like a shelter, with a dark shadowed gap between the lid and base, and a small cute {argument name="sticker design" default="smiling flower sticker"} centered on the top lid. Show exactly 6 small green tree frogs: 4 frogs perched on the upper lid, including one near the left edge facing left, one near the back center facing left, one near the right-center facing left, and one on the far right edge facing left; 2 frogs on or under the lower half, including one crouched in the dark gap near the left side and one sitting on the front lower edge near the center facing right. Surround the scene with tall tangled green weeds, thin stems, and small white daisy-like wildflowers, with a dry brown leaf on the right and a dark vertical object barely visible at the far left edge. Use muted natural colors, overcast soft light, shallow depth of field, realistic textures on the mossy stained curb, and a slightly eerie “many tiny animals gathered around an abandoned object” mood. Horizontal 16:9 composition, low eye-level angle, no people, no added text, no watermark.

Goal: Create a clean anime-style male character design sheet for a modern Japanese office worker, with the character's face intentionally obscured by a soft square blur in every portrait.

Canvas: Wide horizontal character-reference sheet on a white background, approximately 16:9. Use thin black divider lines, neat Japanese editorial layout, and muted professional colors.

Layout: Place a left information column, three full-body character views across the center, and a right detail column. The overall look should resemble a polished commercial character settings document.

Left information column: At the top, draw a bordered profile card with exactly 4 labeled rows: name, occupation, height, and weight. Use Japanese text for the visible labels and values: 「名前: {argument name="character name" default="高橋深月"}」 with small furigana above the name and “(Takahashi Mizuki)” underneath, 「職業: サラリーマン」, 「身長: 182cm」, 「体重: 68kg」. Below it, add a section titled 「キャラクター設定」 with exactly 4 bullet points describing him as a salaryman in his late twenties, calm and intellectual with a strong sense of responsibility, serious and trusted at work, and clean-looking with a trustworthy impression. At the bottom, add a section titled 「カラー設定」 with exactly 5 color swatches: hair light brown #8B6F5E, eyes brown #5A3E2B, suit gray #646A70, shirt white #FFFFFF, tie/shoes/belt black #111111.

Center character views: Show exactly 3 full-body views of the same man wearing a fitted gray business suit: left side view labeled 「側面図」, center front view labeled 「正面図」, and right back view labeled 「背面図」. The man is tall and slim, with light-brown center-parted hair, a white dress shirt, black slim tie with a tie pin, gray notch-lapel jacket, matching slim straight trousers with center crease, black belt, black dress shoes, and a simple analog wristwatch. In the side view, show one hand in pocket and a relaxed upright posture. In the front view, show one hand in pocket and the other relaxed at his side. In the back view, show the suit jacket seams and clean tapered silhouette.

Center annotation callouts: Add thin leader lines and Japanese labels pointing to the outfit and traits. Include callouts for hairstyle, expression, suit, necktie, pants, and shoes. The hairstyle note should describe a center part with naturally flowing hair; the expression note should describe a calm and slightly smiling trustworthy impression; the suit note should describe a crisp fitted silhouette; the necktie note should describe a black solid tie with tie pin; the pants note should describe slim straight slacks with a center crease; the shoes note should describe black straight-tip dress shoes.

Right detail column: Title the column 「ディテール」. Include exactly 4 rectangular detail panels stacked vertically: 1) close-up head and hair with blurred face, 2) close-up chest showing lapels, shirt, tie, tie pin, and pocket square, 3) close-up sleeve cuff and simple analog watch, 4) close-up fabric texture swatch. Add Japanese bullet notes beside these panels: bangs are center-parted and flow naturally, hair has neat straight texture, eyes are calm and composed, jacket has notch lapels and a pocket square, sleeves show four real buttons, watch is a simple analog type, fabric is a high-quality wool-blend suit material suitable for spring, autumn, and winter.

Bottom-right notes: Add a small bordered box titled 「備考」 with exactly 3 bullet points emphasizing cleanliness and trustworthiness, a basic refined business-suit style, and a simple but polished design.

Visual style: Semi-realistic anime illustration, clean line art, soft cel shading, realistic suit folds, elegant muted palette, magazine-like Japanese character sheet design, crisp legible typography, no decorative background, no watermark.

Create a highly realistic documentary-style photograph of a clear plastic water bottle lying horizontally on its side in a dry desert, pouring water from its open mouth onto cracked sandy ground. The bottle should be on the right side of the frame, transparent with blue-tinted threads at the neck, ridged sides, visible highlights and refractions, and partially filled with water. A continuous stream of water spills onto the foreground, forming a shallow muddy puddle with ripples, wet sand, small stones, and bright sparkling sunlight reflections. The camera is very low to the ground with a wide-angle close-up perspective and shallow depth of field: sharp focus on the bottle opening, water stream, puddle ripples, pebbles, and gritty desert texture, while the distant background is softly blurred. The environment is an arid desert plain under intense midday sun, with sparse dry shrubs, distant reddish-brown mountains along the horizon, and a clear saturated blue sky. Place the bright sun high in the upper left corner with starburst lens flare and harsh natural shadows. Use photorealistic lighting, crisp detail, realistic water physics, heat-dry atmosphere, no people, no labels or text on the bottle, no watermark.

Create a realistic wide-angle documentary photo inside a clean Korean subway station corridor with tiled walls, ceiling panels, polished gray floor, and platform signage in the background. On the left foreground stands a young woman with long dark hair, wearing an oversized blue denim jacket, white graphic T-shirt, black mini skirt, and casual shoes, smiling but with her face anonymized by a soft rectangular blur; she poses with both hands pointing toward a giant illuminated wall billboard. The billboard fills the right two-thirds of the image, framed in black, and shows a pastel idol birthday advertisement with a large portrait of the same young woman also anonymized by a rectangular blur over the face, long dark hair, denim jacket, and white shirt. The billboard design has a dreamy pink-to-turquoise blue gradient background with sparkles, bokeh, floating petals, small wing and heart decorations, and a small crown above a pink ribbon banner. Include Korean fan-ad typography: the ribbon reads “여신 탄신일”, the huge central name reads “윤슬”, smaller Korean congratulatory lines sit beneath it, and the large date reads “1996.02.15”; along the bottom edge include tiny English text like “YOONSEUL DAY • ALWAYS BE WITH YOU • FROM YOUR STARLIGHT”. Make the scene feel like a celebratory K-pop fan subway birthday ad photo, with natural station lighting, slight lens distortion, realistic reflections, sharp billboard text, and no extra people in the foreground. Customizable details: use the featured name {argument name="character name" default="윤슬"}, birthday date {argument name="birthday date" default="1996.02.15"}, ribbon text {argument name="ribbon text" default="여신 탄신일"}, billboard color palette {argument name="billboard color palette" default="pastel pink and turquoise blue"}, and outfit {argument name="outfit" default="oversized blue denim jacket, white graphic T-shirt, and black mini skirt"}.

Goal: Create a realistic candid photo in a subway or underground station hallway showing a young woman posing beside a large digital birthday advertisement billboard for herself.

Canvas: Horizontal 16:9 photo, eye-level perspective, wide framing. Beige tiled station wall with grout lines and a polished gray floor. Fluorescent ceiling reflections and clean public-transit interior lighting.

Main subject: One young Korean woman stands on the left side of the frame, full body visible from head to upper thighs. She has long dark hair and wears a fitted black long-sleeve top, light blue high-waisted denim shorts with frayed hems, and a small black shoulder bag. Her face is covered by a rectangular soft blur privacy block. She smiles/poses toward the camera and points with both hands toward the billboard.

Billboard: One large horizontal digital screen mounted on the wall to the right, with a thick black frame. The billboard shows a pastel birthday fan-ad design for {argument name="character name" default="윤슬"}. The design is pink on the left blending into blue on the right, with dreamy clouds, sparkles, hearts, bubbles, and a large portrait of the same woman on the right side of the billboard. The portrait face is also covered by a large rectangular soft blur privacy block.

Text content on billboard: Include exactly 6 visible text groups: 1) small English text “HAPPY BIRTHDAY” near the upper left, 2) very large Korean name “윤슬” centered-left in pink and blue bubble lettering, 3) date “1996.02.15” below the name, 4) pink ribbon label “여신 탄신일”, 5) small handwritten Korean line near the lower left, “세상에서 가장 빛나는 순간, 언제나 윤슬과 함께할게 ♡”, 6) handwritten Korean message on the right, “윤슬아, 생일 축하해! 너의 모든 순간을 응원해. 사랑해 ♡”.

Visual style: Photorealistic smartphone travel snapshot, natural station lighting, slight wide-angle lens, realistic reflections on the billboard glass, subtle depth of field but most elements readable. The birthday billboard should look professionally designed and luminous, while the surrounding subway wall remains neutral and realistic.

Constraints: Use exactly 1 posing woman, exactly 1 wall-mounted digital billboard, exactly 2 blurred face privacy rectangles, and exactly 6 billboard text groups. Do not add extra people, extra signs, watermarks, logos, or unrelated text.

Goal: Create a realistic smartphone-style photo taken in a subway station, showing a young woman posing beside a large wall-mounted digital birthday advertisement for a K-pop idol.

Canvas: Horizontal 3:2 photo, eye-level perspective, natural indoor station lighting, slight wide-angle lens look.

Setting: Clean subway corridor with glossy off-white square tiled walls and dark grout, gray stone floor, black base trim, ceiling panels visible at the top, and a small green rectangular sign on the left wall. A large black-framed digital billboard is mounted on the tiled wall, occupying most of the right side of the image.

Main subject: One young woman stands on the left side of the frame in front of the billboard. She has long dark wavy hair and wears a sleeveless short white summer dress with thin straps and a small bow at the chest. She smiles toward the camera, but her face is covered by a soft-edged opaque taupe privacy rectangle. Her pose uses exactly two pointing gestures: her left hand points across her body toward the billboard, and her right hand points upward toward the billboard.

Billboard design: The digital screen shows a pastel pink-and-sky-blue birthday fan ad with sparkles, stars, soft clouds, translucent heart shapes, and a magical swoosh arc in the top-right. On the left half of the billboard is a large glamour portrait of a young woman with long dark hair and bare shoulders; her face is also covered by a large opaque taupe privacy rectangle. The billboard has exactly six visible text elements: 1) small English greeting at the top, 2) large Korean name in teal, 3) date line, 4) large Korean birthday phrase, 5) smaller Korean congratulatory message, 6) teal rounded footer label.

Text content: Use the top greeting {argument name="top greeting" default="Happy Seul Day"}. Use the large central Korean name {argument name="idol name text" default="윤슬"}. Use the date {argument name="birthday date" default="1996.02.15"}. Use the birthday phrase {argument name="birthday phrase" default="여신 탄신일"}. Use the small message and footer text {argument name="fan message" default="사랑스러운 윤슬아, 생일 축하해! 언제나 빛나는 너를 응원해 ♥ / from. 슬의 모든 순간을 사랑하는 팬들"}. Typography should be elegant teal serif-like Korean lettering, with the name largest, the birthday phrase second largest, and the footer in white text inside a teal rounded rectangle.

Visual style: Photorealistic candid fan photo, realistic shadows and reflections on the digital screen, crisp billboard details, slightly muted station colors contrasted with the bright pastel ad. Do not add extra people, extra posters, watermarks, or additional text beyond the six specified text elements.

Create a warm cinematic vertical selfie portrait of a young woman in ornate Chinese hanfu, shot from a high close-up angle with her left arm extended toward the camera. Her face is completely covered by a centered opaque square privacy block in medium warm brown, hiding all facial features. She has dark brown to black hair styled in an elaborate half-up traditional updo with long loose strands falling over both shoulders. Add exactly two large pale aqua-and-white floral hair ornaments, one on each side of the updo, with gold filigree branches, pearl beads, and exactly two long dangling tassel accessories visible, one on the left side and one on the right side. She wears a delicate pale mint blue embroidered hanfu with sheer flowing sleeves, peach-gold floral embroidery, translucent layers, a high collar, and a decorative chest panel with gold trim, pearl-like beads, and a central dangling pale blue pendant. The setting is an intimate traditional East Asian room with warm amber candlelight, wooden window lattice panels in the background, a calligraphy scroll on the left wall with black brush characters, and a glowing paper lantern plus two small candles on a low table. Use shallow depth of field, soft bokeh, warm highlights on hair jewelry, realistic fabric texture, romantic historical-drama styling, and a cozy golden-hour interior atmosphere. Make the composition feel like an accidental elegant selfie, with the sleeve and arm slightly blurred in the foreground and the ornate costume details sharply visible. Use {argument name="outfit color" default="pale mint blue"}, {argument name="hair color" default="dark brown to black"}, {argument name="privacy block color" default="warm medium brown"}, {argument name="room lighting" default="warm amber candlelight"}, and {argument name="background decor" default="calligraphy scroll, wooden lattice windows, paper lantern, and two candles"}.

Create a vertical photorealistic portrait of an elegant adult woman seated on the floor in a traditional Chinese-style wooden room, wearing a glossy white silk qipao-inspired bridal outfit with delicate frog closures, pearl accents, tassels, and a high side slit. Her face is intentionally covered by a centered opaque square censor block in a muted brown skin-tone color. She has long wavy {argument name="hair color" default="dark brown"} hair flowing over her shoulders, decorated with exactly two white floral pearl hair ornaments and exactly two translucent white ribbon bows. She wears exactly two sheer white opera gloves, exactly two white high-heeled Mary Jane shoes with ankle straps, and a sheer white stocking detail with pearl-and-flower trim on one thigh. Pose her sitting low with both knees raised close to the camera, one gloved hand near her face, creating a soft fashion editorial composition. The setting includes exactly one warm glowing paper lantern on a wooden table to the left, exactly one small white teapot on a low table in the background, dark wooden furniture, shoji-style window grids, hanging calligraphy scrolls, and white blossom branches on the right. Use warm natural window light, shallow depth of field, creamy bokeh, realistic skin and fabric texture, high-end cosplay photography aesthetics, muted beige and ivory tones, and a 9:16 vertical crop. Keep the mood graceful, serene, and luxurious; no extra text, no watermark.

Goal: Create a luxury square advertising collage for a futuristic wristwatch brand, showing one premium chronograph watch across four elemental dimensions. Use the brand name {argument name="brand name" default="NOXEN"} and the monogram {argument name="brand monogram" default="N"}.

Canvas: Square 1:1 image divided into exactly 4 equal panels in a clean 2x2 grid, separated by thin white divider lines. Each panel is a cinematic product poster with dramatic lighting, high contrast, sharp watch detail, and premium commercial photography realism.

Overall subject: A masculine luxury stainless-steel chronograph wristwatch with integrated metal bracelet, octagonal/rounded bezel with small screws, black dial, three subdials, baton hour markers, central hands, crown and pushers on the right side, and subtle brand text on the dial. The watch should remain recognizable as the same model in all 4 panels while material color and environment change.

Panel count and details: Exactly 4 distinct watch posters:
1. Top-left panel: matte black watch in a dark smoky void, surrounded by black dust, volcanic ash, floating debris, and mist. Monochrome black-and-charcoal palette with silver highlights. Place the monogram above the brand name near the top center. Add the small tagline {argument name="darkness tagline" default="ENGINEERED IN DARKNESS"} near the bottom center.
2. Top-right panel: polished gold watch surrounded by a dramatic splash of liquid gold, bubbles, and warm amber reflections. Black background with intense golden highlights. Place the monogram above the brand name near the top center. Add the small tagline {argument name="gold tagline" default="CRAFTED IN GOLD"} near the bottom center.
3. Bottom-left panel: silver steel watch frozen inside a translucent block of cracked blue ice, with frosty mist, icy rock texture, and cold blue lighting. Place a large monogram above the brand name near the bottom center, with the small tagline {argument name="time tagline" default="BUILT BEYOND TIME"} beneath it.
4. Bottom-right panel: black and dark steel watch with neon green accents in a cyberpunk futuristic city at night, glowing skyscrapers, circuit-like lines, holographic HUD rings, and emerald light beams. Place a large glowing monogram above the brand name near the top center. Add the small tagline {argument name="future tagline" default="FUTURE. ENGINEERED."} near the bottom center.

Typography: Elegant luxury serif or widely spaced uppercase lettering for the brand name, thin uppercase tracking for taglines, centered and minimal. Text must be crisp and legible: brand name appears in all 4 panels, the monogram appears in all 4 panels, and each panel has exactly one tagline as listed.

Visual style: Ultra-realistic high-end watch advertising, macro product photography, cinematic lighting, glossy reflections, deep blacks, premium contrast, sharp metal textures, atmospheric particles, no people, no extra logos, no watermark, no additional text beyond the specified brand, monogram, and four taglines.

Goal: Create a detailed military-industrial specification sheet for a fictional autonomous scorpion-shaped combat robot named {argument name="platform name" default="Дигваранз-1.6"}, with the subtitle “Autonomous Combat Platform.”

Canvas: Landscape 4:3 technical presentation board on a warm light beige background, thin gray panel borders, clean infographic layout, realistic hard-surface concept art mixed with labeled engineering diagram. Use tan, dark bronze, black, gunmetal, and muted military colors. The overall look should feel like a defense robotics brochure or field manual page.

Main subject: Center a large scorpion-inspired autonomous combat platform in three-quarter view, facing left. It has a low armored body, segmented tan modular armor panels with rivets and dark mechanical joints, six numbered legs, hybrid wheel-and-leg mobility, and a high curved scorpion tail ending in a stabilized turret weapon. The weapon is a compact 30 mm autocannon with a red sensor or muzzle detail. The robot should look rugged, heavy, realistic, and operational, with subtle floor shadows. Add circular callout markers for exactly 6 leg positions: 1, 2, 3, 4, 5, and 6. Include a ground-clearance measurement arrow beneath the center body reading “GROUND CLEARANCE 0.50 m (19.7 in).”

Top-left title block: Add a small black scorpion icon, then the large Cyrillic title “{argument name="platform name" default="Дигваранз-1.6"}” and the English subtitle “Autonomous Combat Platform.” Under it, show exactly 6 feature bullets: “Scorpion-Inspired Mobility,” “Hybrid Wheel-Leg System,” “Stabilized Weapon System,” “Modular Armor,” “All-Terrain Operations,” and “Autonomous Targeting & Navigation.”

Left specifications panel: A bordered box titled “SPECIFICATIONS” with exactly 9 rows: “HEIGHT (TO TOP OF TURRET) 1.0 m (3.28 ft),” “LENGTH 2.0 m (6.56 ft),” “WIDTH 1.6 m (5.25 ft),” “WEIGHT ~350 kg (771 lb),” “GROUND CLEARANCE 0.50 m (19.7 in),” “MAX SPEED 20 km/h (12.4 mph),” “ENDURANCE 6–8 hours,” “PRIMARY ARMAMENT 30mm Autocannon / Energy Weapon (Optional),” and “POWER SOURCE Hybrid (Battery + Generator).”

Top-right comparison panel: A bordered inset titled “DIMENSIONS & COMPARISON.” Show exactly 2 figures inside: the scorpion combat robot beside a standing armored soldier holding a rifle. Add height guides labeled “1.0 m (3.28 ft)” for the robot and “Average Human Height 1.75 m (5.74 ft)” for the soldier.

Right-middle leg configuration panel: A small bordered box titled “LEG CONFIGURATION” with exactly 2 numbered lines: “1, 3, 4, 6 – Wheel Legs” and “2, 5 – Articulated Legs (Middle Legs).”

Bottom row: Add exactly 5 bordered feature cards spanning the width. Each card contains a small realistic render and a caption. Card 1 title “HYBRID MOBILITY,” image of the robot driving across rough ground, caption “Wheel legs for speed and efficiency on flat terrain.” Card 2 title “ARTICULATED MIDDLE LEGS,” image focused on the middle walking legs, caption “Enhanced stability and obstacle climbing capability.” Card 3 title “STABILIZED WEAPON SYSTEM,” image close-up of the tail turret, caption “Low-profile turret with stabilized autocannon for high accuracy.” Card 4 title “ADVANCED SENSORS,” image close-up of the front sensor array with cameras, caption “360° awareness with multi-spectral cameras, LIDAR, and threat detection.” Card 5 title “MODULAR ARMOR,” image close-up of armor plates, caption “Modular armor panels for mission adaptability and protection.”

Style constraints: Use crisp sans-serif typography, black and dark gray text, precise labels, thin leader lines, and realistic lighting. Keep all text legible and aligned. Do not add extra logos, watermarks, explosions, battlefield smoke, or human gore. Maintain a clean concept-sheet presentation for {argument name="robot role" default="autonomous combat platform"}.

Goal: Create a clean studio product render of a custom DIY smart doorbell / intercom enclosure, shown as an exploded multi-view product lineup.

Canvas: Wide horizontal 16:9 composition on a light gray seamless studio background, soft floor shadow, orthographic product-render look, no people, no branding watermark.

Subject: A compact rectangular electronics enclosure with rounded corners, matte {argument name="enclosure color" default="light gray"} plastic, slightly beveled edges, realistic 3D CAD rendering, subtle rough texture.

Layout: Show exactly 5 discrete enclosure views arranged left to right with even spacing: 1) a very thin left side profile standing upright with two stacked circular speaker or sensor grilles; 2) the main front face standing upright, slightly angled, with visible functional details; 3) a narrow side profile with a recessed USB-C port; 4) the rear cover plate standing upright with four corner screw holes and a side cutout; 5) the open back housing/case interior showing electronics installed in the top compartment and an empty lower compartment.

Front face details: On the main front view, include exactly 4 visible feature groups: a small round camera lens near the top center; a square black display/window below it showing two cute cartoon eyes; a large circular illuminated doorbell button below the display with a white glowing ring; and a horizontal speaker grille near the bottom made of short black slits in multiple rows. Add two small round side holes on the left edge of the main body.

Interior electronics: In the open back housing, include exactly 2 circuit boards and visible wiring: the top board is labeled {argument name="camera module label" default="ESP32-CAM"} with a small camera module, and the lower board is labeled {argument name="controller board label" default="DFPlayer Mini"}. Add neatly routed black, white, gray, and red wires around the boards. The interior should have a horizontal divider shelf separating the electronics bay from a larger empty lower cavity. Add four corner screw posts/holes inside the open case.

Style: Photorealistic 3D product visualization, high-detail industrial design concept, soft studio lighting from upper left, gentle ambient occlusion, crisp edges, realistic plastic material, neutral gray palette, shallow but clear shadows, centered composition.

Constraints: Use exactly 5 product views, keep all objects upright, no hands, no extra text beyond the two board labels, no logos, no decorative background objects.

Create a hyperreal cinematic close-up portrait of {argument name="character" default="a rain-soaked cyberpunk female assassin"} holding {argument name="object" default="a translucent neon glass dagger"} with intense, deliberate intent. The composition is very tight and vertical, focused on the left side of the character’s wet face, ear, neck, shoulder, and hand gripping the weapon; most of the face is obscured by a large centered square censor-like overlay, about two thirds of the image width, filled with a dark navy-to-muted-blue gradient. Show slick black wet hair clinging to skin, a visible ear with two small metallic piercings, glossy black leather or tactical collar around the neck, bare wet shoulder, subtle tattoos on the upper chest, and water droplets across skin and clothing. The dagger is held upright along the right side of the frame, close to the face, made of clear glass or crystal with glowing cyan and magenta circuitry-like reflections inside it. Use {argument name="lighting" default="electric blue and hot magenta neon rim lighting"}, with strong reflections on wet skin, hair, leather, and the blade. Add {argument name="atmospheric elements" default="mist, rain droplets, tiny floating particles, and blue haze"} drifting through the frame to create a moody futuristic noir tone. The visible eye area is hidden by the square overlay, but the body language should imply {argument name="emotion" default="cold determination"}. Shallow depth of field, dramatic high contrast, ultra-detailed skin texture, glossy specular highlights, bokeh neon background, hyperreal photography style, no text, no watermark.

Create a hyperreal cinematic close-up portrait of an elderly mystical figure, mostly obscured by a large solid matte brown square censor block centered over the face and upper torso. The visible parts show long wild gray-white hair framing both sides, a dirt- and ash-smeared forehead at the top edge, and weathered grimy hands at the bottom holding an ornate engraved brass or gold spherical artifact with intent. Use {argument name="character" default="an elderly mystical figure"}, {argument name="object" default="an ornate engraved brass sphere"}, and {argument name="lighting" default="warm firelight mixed with dim smoky shadows"}. Subtle metallic reflections catch on the artifact, dirty fingernails, skin texture, and stray hair. Orange sparks and faint smoke drift through a dark background, with shallow depth of field and blurred golden foreground bokeh. The mood is tense, ancient, ritualistic, and mysterious; the hidden eyes should be implied to convey {argument name="emotion" default="intense determination"}. Vertical 3:4 composition, macro lens realism, gritty skin detail, high contrast, cinematic color grading, no text, no watermark.

Cinematic hyperreal close-up portrait of {argument name="character" default="an antique deep-sea diver in a weathered brass diving helmet"} holding {argument name="object" default="a dark mysterious square artifact"} directly in front of the face with intent. The object is centered and blocks most of the visor, appearing as a flat near-black charcoal square with a subtle vertical gradient, sharp clean edges, and no markings. Show the diver’s wet gloved hands at the bottom foreground, fingers curled around the artifact, with realistic skin/leather texture, droplets, grime, and specular highlights. The helmet fills the frame: aged bronze and blackened metal, round rivets, ornate circular side fittings, corroded seams, scratches, algae-like residue, and a glass porthole rim barely visible around the square. Illuminate the scene with {argument name="lighting" default="cold blue underwater light from the left with warm amber reflections along the brass rim"}. Add {argument name="atmospheric elements" default="suspended bubbles, drifting particles, and murky underwater haze"} throughout the frame. The mood is tense and enigmatic; any visible eyes behind the glass should convey {argument name="emotion" default="focused obsession and dread"}. Use shallow depth of field, macro-level detail, cinematic contrast, teal-blue color grading, glossy wet surfaces, volumetric underwater ambience, no text, no watermark, vertical 4:5 composition.

Cinematic hyperreal close-up portrait of a fragile porcelain gothic doll-like woman, {argument name="character" default="a pale cracked porcelain android girl"} holding {argument name="object" default="a cracked white ceramic anatomical heart"} with intense, careful intent. She has a short black bob haircut with blunt bangs, translucent pale skin with fine fracture lines across her cheeks and nose, glossy parted lips, one dark human eye and one clouded broken glass eye surrounded by branching cracks and dark tear-like stains. Her black lace-gloved hands cradle the heart in the foreground; the ceramic heart is fractured, chipped, and glowing faintly red from within through one crack. She wears dark Victorian lace, metal chain earrings, dangling beads, and tarnished ornamental accessories, with subtle wet reflections on the porcelain face, eye, lips, gloves, chains, and cracked heart. Illuminate the scene with {argument name="lighting" default="cold blue-gray side lighting with a faint internal red glow"}, creating deep shadows, soft rim light, and a moody chiaroscuro effect. Add {argument name="atmospheric elements" default="tiny drifting red embers, dust motes, and floating glass-like droplets"} throughout the frame. Her eyes convey {argument name="emotion" default="melancholy obsession and quiet longing"}. Macro lens feel, shallow depth of field, highly detailed skin cracks, ceramic texture, lace fibers, reflective highlights, dark desaturated palette with small red accents, 4:5 vertical composition, no text, no watermark.

Goal: Create a polished vertical social media advertisement for {argument name="brand name" default="PhonePe"}, promoting instant group bill splitting for UPI payments with a bold party/nightlife energy.

Canvas: Square 1:1 digital ad, high-resolution, deep purple and neon violet color palette, glossy fintech campaign style, dramatic depth of field. Background is a rooftop restaurant or lounge at night with city lights, purple bokeh, and a group of friends at a dinner table.

Layout: Top left show the PhonePe logo mark and wordmark in white. Top right show a small shield icon with the text "Trusted UPI". Behind the subject, place huge oversized semi-transparent purple typography reading "NO DRAMA" tilted slightly and filling the upper-left background. On the upper-right, place the main headline in bold white uppercase: "PAY YOUR PART. KEEP THE VIBE." with the subheading below: "One tap and everyone’s sorted." Add a short decorative underline under the subheading.

Main subject: A young woman in the foreground stands confidently at a party table, wearing a purple varsity jacket over a white crop top and light denim jeans, with black nail polish. She holds a large smartphone close to the camera in her left hand, making it the dominant foreground object, while pointing playfully with her other hand. Her face should be covered by a flat rectangular anonymization block in a natural skin-tone brown, and the visible faces of three seated friends in the background should also be covered by similar rectangular skin-tone blocks. Keep the pose, outfit, and lighting stylish and youthful.

Phone screen: Show a purple PhonePe-style bill split interface titled "Dinner Split". At the top display the time "9:41". Large amount: "₹3240". Under it: "8 friends • ₹405 each". A green success card reads "Paid by everyone" and "Completed instantly". Below it, show exactly 8 itemized friend rows, each with a tiny circular avatar, name, amount "₹405", and a green checkmark: 1) Ananya, 2) Rohan, 3) Karan, 4) Meera, 5) Arjun, 6) Simran, 7) Vikram, 8) Neha. At the bottom of the screen, add a purple rounded button labeled "Split Again" with a white shield/check icon.

Floating UI elements: Add exactly 3 glowing purple transaction cards connected by dotted curved lines and small circular avatar bubbles: 1) "Payment Sent ₹405" with a lightning icon, 2) "Paid ₹405" with a green check icon, 3) "All Settled! Everyone Paid" with a green check icon. Make them hover around the subject’s pointing hand on the right side.

Call to action: Near the lower-right center, place a large white pill-shaped button with purple text "Split in Seconds" and a right arrow icon.

Bottom information bar: Add one translucent rounded purple strip containing exactly 4 feature capsules/icons from left to right: 1) lightning icon with "Instant settlements", 2) group icon with "Group friendly", 3) shield icon with "Safe UPI payments", 4) phone icon with "Everywhere accepted". Beneath or beside it show a small group icon with "500M+ Indians use PhonePe". At the bottom right, include exactly 2 app store badges: "GET IT ON Google Play" and "Download on the App Store".

Side text: Along the left edge, add small vertical white text reading "PHONEPE • SPLIT BILLING • SOCIAL PAY • 2026".

Visual style: Premium hyper-realistic advertising composite, cinematic purple rim lighting, glossy UI overlays, neon glow, energetic nightlife mood, sharp foreground phone, blurred background friends and city lights, crisp readable typography.

Constraints: Use the exact visible counts: 8 friend rows on the phone, 3 floating payment cards, 4 bottom feature items, 2 store badges, and 4 anonymized face blocks total. Avoid extra logos, extra payment cards, or extra feature pills.

Create a square cinematic macro photograph of a surreal miniature food-landscape titled {argument name="title text" default="MINI LONDON"}, showing London rising from a vast desert of fine sparkling golden cane sugar. The scene contains exactly 7 recognizable landmark miniatures: 1) Tower Bridge in the front-left made from orange-red candy sticks with pale sugar-cable suspension lines, 2) Big Ben / Elizabeth Tower as the central centerpiece made from stacked glossy red candy wafers with cream icing trim and a readable clock face, 3) The Shard behind it on the right as a tall translucent faceted sugar-glass shard glowing warm white, 4) 30 St Mary Axe / the Gherkin on the far right made from dark green and pale green checker-patterned candy scales, 5) a small red British telephone booth beside a turquoise pond in the foreground, 6) a red rounded modern tower in the mid-background, and 7) a cluster of smaller colorful London skyscrapers and cathedral-like towers made from edible sweets. Surround the buildings with exactly 3 main natural miniature areas: a turquoise sugar-water pond in the foreground center, dense broccoli-like green shrubs and trees around it and between buildings, and scattered palm-like sugar plants sprouting from the sand. Use {argument name="main edible material" default="fine golden cane sugar"} for the desert base, with visible sugar crystals and shallow dunes. Add theatrical colored mist and bokeh lights in the background, with deep black, purple, blue, and magenta haze, plus warm golden highlights on the sugar and landmarks. Place the title text in the upper-left in large elegant white serif capitals, two lines, reading MINI above LONDON. Use a shallow depth of field, tilt-shift miniature scale, ultra-detailed edible textures, glossy candy surfaces, dramatic studio lighting, photoreal macro realism, no people, no watermark, no extra text.

Create a square cinematic macro photograph of a surreal miniature New York City food-landscape rising from a vast desert of fine golden cane sugar. The scene is a detailed diorama viewed from a slightly elevated three-quarter angle with shallow depth of field, atmospheric haze, and warm glowing city lights. Add large elegant white serif text in the upper left reading {argument name="title text" default="MINI NYC"}. Build a miniature Manhattan skyline from edible materials: a central Empire State Building made from stacked glossy purple onion layers with a sparkling sugar-dusted spire; a cream-white Chrysler Building made from carved layered onion or pastry scales with a pointed spire; surrounding towers made from cucumber slices, corn cobs, stacked zucchini rounds, carrots, sugar cubes, wafers, translucent candy blocks, and vegetable cylinders. Include exactly one Statue of Liberty in the foreground, carved from bright orange carrot, standing on a tiny sugar island in a turquoise-blue lagoon. Surround the city with rolling dunes of cane sugar like sand, broccoli florets as clusters of trees, rosemary sprigs as miniature palms and street plantings, cherry tomatoes stacked vertically as a red skyscraper, and glowing miniature Times Square-style billboards along a waterfront street. The composition should feature a turquoise lagoon across the bottom third, dense edible greenery at the lower edges, the tallest purple onion tower near center-left, the white Chrysler-style tower to its right, and warm golden lights at street level. Use hyperreal macro food photography, tilt-shift miniature effect, crisp edible textures, sparkling sugar granules, soft dramatic backlighting, teal shadows, warm amber highlights, whimsical but photorealistic detail, no people, no watermark.

Create a surreal macro food-art miniature cityscape titled {argument name="headline text" default="MINI BEIJING"}, showing Beijing rising from a vast desert of fine golden cane sugar. The centerpiece is a detailed edible Temple of Heaven in the middle: round tiered white sugar-stone terraces, carved staircases, a circular white balustrade, and a dark indigo-purple ridged roof with a golden finial. Surround it with exactly 12 distinct miniature edible Beijing-inspired structures and landmarks: 1 white pagoda tower on the left, 1 small red-and-gold palace pavilion in the front-left, 1 larger red-and-gold palace hall on the right, 2 small red temple buildings flanking the central temple, 1 orange-red ceremonial gate in the foreground over a turquoise pond, 1 green lattice-pattern modern arch resembling the CCTV Headquarters on the right, 1 tall golden needle-like skyscraper in the rear-left center, 1 glowing red tiered tower in the rear center, 1 tall amber-lit skyscraper in the rear-right, 1 purple-lit vertical tower in the far background, and 1 rounded glass dome building behind the temple. Make all architecture appear crafted from edible materials such as sugar crystals, candy, wafer, icing, jelly, fondant, sesame, and translucent hard candy, with warm glowing windows and candy-like details. The ground is a textured golden sugar desert with scattered white sugar pearls around the central plaza, orange candy-brick paths, tiny green broccoli-like trees and shrubs, edible grass reeds, small rocks, and a shallow bright turquoise candy-water pond at the bottom. Use cinematic shallow depth of field: sharp focus on the Temple of Heaven and foreground gate, softly blurred skyscraper skyline in the back, atmospheric pink-purple mist and warm orange light, high contrast, glossy macro photography look, square composition. Place the headline text in the upper-left corner in elegant spaced white serif capitals, two lines, reading exactly {argument name="headline text" default="MINI BEIJING"}. No people, no vehicles, no extra labels, no watermark.

Using the provided reference image, transform the entire photo into a whimsical handmade needle-felt / wool-felt miniature diorama. Preserve the original composition, selfie camera angle, perspective, pose, subject placement, outfit, facial expression, hairstyle, lighting direction, and recognizable setting, but reinterpret every surface as soft felted wool with visible fibers, plush seams, rounded handmade edges, and miniature craft textures. Keep the foreground arm, bracelet, main person, background companion, long arched-column interior, warm amber lighting, and distant visitors in the same relative positions. Convert the architecture into felt columns and arches with stitched stone-block details and colorful felt trim; convert the floor, railings, plants, lights, and background figures into tiny handcrafted diorama pieces. Maintain the same shallow depth of field and tilted wide-angle selfie feel, with soft bokeh and cozy toy-like realism. Do not add text, logos, or extra characters beyond the people already present in the reference.

Create a surreal macro miniature food landscape titled {argument name="title text" default="MINI TOKYO"}, showing Tokyo rising from a vast ground of fine golden-white cane sugar crystals like a desert at night. The composition is a square cinematic diorama with shallow depth of field, dramatic blue-purple smoky background, soft mist between buildings, and warm pink-red edible lighting. In the center stands 1 dominant Tokyo Tower, meticulously built from stacked glossy red pepper strips and pale candy rings, glowing orange at its base. To the right stands 1 tall Tokyo Skytree made from pale sugar sticks and white confectionery rods. Surround them with exactly 16 miniature edible skyscrapers and towers in the hazy background, including 1 black-and-white crisscross oval tower, 1 red-and-white striped cylindrical tower, 1 small clock-tower-like building, 2 pagoda-style towers, 1 green glass luxury storefront labeled {argument name="storefront label" default="PRADA"}, and additional candy-block high-rises made of wafers, gummies, marshmallows, biscuits, and pepper slices. In the foreground, create a tiny Japanese garden made from broccoli, herbs, leafy greens, cauliflower florets, pink pickled ginger, and candy-like shrubs. Add exactly 1 red torii gate at the edge of a glossy dark teal pond, with exactly 2 glowing red lanterns beside it and exactly 3 floating sushi-shaped boats in the water. Use {argument name="main color palette" default="deep navy, magenta, candy red, sugar white, moss green, and warm orange"}. Place the title text in the upper left in elegant white serif typography, with small uppercase “MINI” above large spaced-out “TOKYO.” Ultra-detailed food styling, macro photography realism, whimsical edible architecture, magical miniature scale, crisp foreground textures, bokeh city depth, no people, no watermark.

Goal: Create an ultra-detailed handcrafted edible art world celebrating {argument name="celebration" default="Mother's Day"} in a kawaii Japanese spring bento style, transforming a full meal into a cute character centerpiece made entirely from real foods.

Canvas: Square 1:1 overhead food photography composition, bright pastel color palette, soft natural light, shallow depth but all main foods readable, festive blue tablecloth background covered with cherry blossoms, pink carnations, doodled hearts, clouds, sparkles, and tiny celebration decorations.

Main centerpiece: In the center of a large round pink bento plate, make one large edible girl character: rice face with shiny black eyes, lashes, rosy cheeks, smiling mouth, long blonde hair made from thin omelet/noodle strands, pink flower hair decoration, pink heart earrings, kimono-like outfit made from pink ham and blue rice/crepe layers, holding a bouquet of pink carnation flowers tied with a bow. The character should feel like a lovingly made Mother’s Day food-art doll.

Food elements to include, exactly 15 visible edible feature groups: 1) central girl character, 2) two smiling rice-ball onigiri behind her with nori rectangles and green shiso leaves, 3) small basket of strawberries with one halved strawberry, 4) heart-topped custard pudding on a pink saucer, 5) red sausage octopus with a face and bow tie, 6) cluster of cherry tomatoes and vegetable flowers, 7) pink carnation bouquet in the character’s hands, 8) rolled omelet/noodle roses near the top center, 9) pink bowl of fruit containing green grape, orange segments, and a pink heart sweet, 10) heart-shaped tamagoyaki block with two small red hearts, 11) two breaded fried shrimp with orange tails, 12) broccoli and lemon wedge garnish, 13) pink fluted cup of spaghetti napolitan with peas and flower-shaped toppings, 14) small rice or dumpling hand beside the pasta, 15) separate small plate at bottom right with sakura mochi wrapped in a leaf and topped with a pink flower.

Non-food props and decorations to include, exactly 8 visible groups: 1) teacup at upper right with warm tea and a cute anime girl illustration plus floral print, 2) woven coaster under the cup, 3) triangular pink bunting flags across the upper background, 4) two small fluffy white cloud cutouts near the Japanese writing, 5) floral greeting card sign in the strawberry basket, 6) floral apology/thanks card at bottom left tied with a pink ribbon, 7) two carp-streamer decorations at bottom center, 8) pink-handled small brush on floral paper at bottom right.

Text content: Add handwritten Japanese text in the sky area reading {argument name="background Japanese message" default="おかあさんへ いつもありがとう！！"}. Add a pink heart speech bubble near the top right reading {argument name="heart speech bubble" default="だいすき だよ〜♡"}. Add a small floral card in the strawberry basket reading {argument name="card text" default="Happy Mother's Day"}. Add a bottom-left floral card reading {argument name="bottom card Japanese text" default="感謝をこめて…"}. Keep text hand-drawn, cute, slightly imperfect, and integrated naturally into the scene.

Visual style: Hyper-detailed kawaii edible miniature art, Japanese bento craftsmanship, pastel pink and sky blue, glossy rice grains, crisp fried textures, soft omelet strands, realistic fruit and tea, abundant sakura and carnation motifs, whimsical hearts and sparkles. Make everything look handmade from food, cheerful, warm, and celebratory.

Constraints: Use an overhead flat-lay angle, no humans, no utensils except the small decorative brush, no watermark, no extra text beyond the specified messages, keep all counted food and prop groups clearly visible.

Create a modern isometric illustration sheet on a clean light gray background, showing a seamless grid of cybersecurity, privacy, and compliance icons with soft shadows, glossy 3D materials, rounded edges, and a blue, white, gray, red, and orange accent palette. Use a wide horizontal canvas, evenly spaced rows and columns, with no border or watermark. Include exactly 15 discrete icons arranged in a 3-row by 5-column grid: top row: 1) a blue padlock with silver shackle and black keyhole, 2) a blue shield badge with a white check mark and metallic rim, 3) a silver key angled diagonally, 4) a dark smartphone-like biometric panel showing a glowing blue fingerprint scan line, 5) a desktop monitor login screen with a lock icon, password dots, and a blue button labeled “LOGIN”; middle row: 6) a white document page with folded corner, blue lock icon, and label “ENCRYPTED”, 7) a red brick firewall with an orange flame in front, 8) a white surveillance camera with blue lens mounted on a small wall bracket, 9) an ID badge with clip, portrait thumbnail, text lines, and barcode, 10) a red triangular warning sign with black exclamation mark; bottom row: 11) a dark server stack with colored status lights and a blue shield check badge in front, 12) a clipboard checklist labeled “COMPLIANCE” with green checkboxes, 13) a dark smartphone facial-recognition screen showing a wireframe face, scan brackets, and “VERIFYING...” text, 14) an alert dashboard card labeled “ALERT” with a magnifying glass inspecting the list, 15) a gray safe/vault box with round combination dial beside a white policy document labeled “POLICY” with gray lines and green check mark. Keep all icons consistent in isometric perspective, miniature object scale, polished SaaS/security branding style, crisp edges, ambient occlusion, and subtle contact shadows. Text should be minimal and legible only where specified. Theme customization: {argument name="theme" default="security and compliance"}; primary color customization: {argument name="primary color" default="deep blue"}; background customization: {argument name="background color" default="light gray"}.