GPT Image 2 prompts

Goal: Create a refined minimalist morning greeting poster for {argument name="city name" default="上海"}, blending city travel aesthetics, light editorial typography, and a calm coffee-by-the-window mood.

Canvas: Wide horizontal poster, 16:9 ratio, clean white background with generous negative space and pale blue-gray accents. Overall feeling is airy, quiet, premium, and slightly poetic.

Layout: Left half is a typography and information panel; right half is a large soft-focus lifestyle photo panel. Place a small pale-blue circular badge at the top left reading 「早安」, followed by a thin slash and the small Chinese line 「每一座城市，都有清晨的温度」. Below it, create an oversized black Chinese city title 「上海」, with a very large pale blue-gray serif English title “SHANGHAI” underneath, partially overlapping the Chinese characters. Add subtle thin orbital curve lines and small blue dots across the white background.

Right image panel: A rectangular photo area occupying the middle-right, showing a white ceramic coffee cup on a saucer on a bright windowsill or table, with a hazy Shanghai skyline in the background, including the Oriental Pearl Tower and tall modern skyscrapers. Morning sunlight, slight overexposure, soft blue atmosphere, shallow depth of field. Include a small glass vase with green leafy stems near the far right edge. The lower-right corner of the photo panel should have a rounded or curved cutout edge.

Top-right date card: Add a thin outlined white box in the upper right with the date {argument name="date" default="2026-07-17"} in black serif numerals, and smaller text underneath: 「星期五　农历六月初四」.

Info row: Under the main title on the left, create exactly 5 small vertical information items, evenly spaced, with light blue-gray numbers and delicate divider lines. The five items are: 1) “01 / 天光 / 微蓝”, 2) a rounded vertical pill labeled 「节奏」 with 「明快」 below and a small blue dot, 3) “03 / 灵感 / 向上”, 4) a small blue filled rectangle labeled 「推荐」 with 「先喝 / 咖啡」 below, 5) a thin outlined circle labeled “05 / 心情 / 清醒” with a small blue dot on its rim.

Quote section: Below the info row, place large pale-blue quotation marks around the quote {argument name="quote" default="让清晨先温柔你，再把锋芒交给今天。"}. Use elegant Chinese typography, centered-left under the info row.

Body copy: At the lower left, add a thin vertical blue line and a short paragraph in small Chinese text: 「上海的清晨，从一束光开始。阳光穿过梧桐的缝隙，落在街角的咖啡店与江面的微波上。给自己一段安静的时间，整理思绪，明确方向，让每一个清醒的开始，都通向更好的自己。」

Footer and QR: Along the bottom, add widely spaced pale-blue uppercase footer text: “MORNING GREETING / CITY NOTE”. In the lower right, place a small QR code with two lines of Chinese caption: 「城市早安计划」 and 「扫码开启美好一天」.

Visual style: Editorial magazine layout, luxury city postcard, pale sky-blue accents, black Chinese calligraphy-like serif title, high-end serif English lettering, thin rules, precise alignment, soft gradients, quiet morning atmosphere. Keep the design spacious, balanced, and uncluttered. No extra icons, no watermark, no additional text beyond the specified content.

Create a photorealistic vertical street portrait of {argument name="subject" default="a young East Asian woman"} standing in a narrow old alley on a bright sunny day. She leans lightly against a rough, weathered gray plaster wall on the right side of the frame, shown from mid-thigh upward in a 2:3 vertical composition. She has very long straight {argument name="hair color" default="dark brown-black hair"} falling over her shoulders and down past her waist, fair skin, delicate natural makeup, and a calm contemplative expression as she gazes upward toward the sunlight. Her right hand is raised to her forehead to shade her eyes, while her left arm hangs relaxed by her side. Dress her in a soft casual outfit: a fitted light gray camisole tank top, a sheer cream cardigan with sleeves pushed to the elbows, and a flowing off-white long skirt; include a small woven straw shoulder bag partly visible behind her hip. The setting is an aged pedestrian lane with stone paving, potted green plants along the wall, distant old building facades, a red lantern hanging in the blurred background, and strong midday sunlight casting crisp highlights and shadows. Use natural colors, shallow depth of field, realistic skin texture, soft cinematic bokeh, high detail, 35mm documentary fashion photography style, no text, no watermark, no extra people.

Goal: Create a dark technical blueprint poster of a mechanical exploded assembly labeled {argument name="unit name" default="PGU-05 Planetary Gear Unit"}, with the subtitle “Exploded View & Component Reference,” styled like a precision engineering CAD reference sheet.

Canvas: Square 1:1 format on a black/charcoal background with a faint grid, thin border lines, corner crop marks, small registration crosshairs at the top and bottom center, and a small sheet number “01” in the upper-right corner. Use white and light gray monoline drafting lines, with selective red highlights.

Main subject: Center a detailed isometric exploded view of a planetary gear unit, vertically arranged from top to bottom. Show exactly 10 labeled component groups with leader lines on the right: 01 Cap screw (x6), 02 Top cover, 03 Ring gear internal, 04 Planet gear (x3), 05 Sun gear, 06 Planet carrier, 07 Thrust washer, 08 Output shaft, 09 Bearing (x2), 10 Housing. Render the exploded parts as transparent wireframe/technical linework with hidden construction lines and dotted alignment axes. Make the sun gear the only emphasized component in red, positioned in the middle of the assembly, with a red leader line and red label.

Left information panel: At the upper left, place the title “PGU-05 PLANETARY GEAR UNIT” and subtitle “EXPLODED VIEW & COMPONENT REFERENCE.” Below it, include a specifications block with exactly 5 rows: Gear ratio 27.31:1, Max input RPM 6000, Max output torque 320 N-m, Efficiency 94%, Weight 3.7 kg. Under that, add a function overview paragraph explaining that a planetary gear set uses multiple planet gears rotating around a central sun gear while meshing with an internal ring gear, distributing load and increasing torque capacity in a compact drive train.

Inset diagrams: Add exactly 2 inset boxes on the lower-left side. The upper inset is labeled “SECTION A-A” and shows a white line cross-section of the assembled gear unit. The lower inset is labeled “05 SUN GEAR [DETAIL]” and uses red linework to show the isolated sun gear with dimension arrows and annotations such as Ø18.00, Ø32.00, and Ø12.00 (H7).

Right reference panel: Use compact monospaced technical text for the component list and notes. Include material and tooth-count callouts such as ring gear Z=72 module 1.25, planet gear Z=24 module 1.25, and sun gear Z=18 module 1.25. Add a notes block with exactly 5 numbered notes: all gears 20° pressure angle, gear material 20CrMnTi, heat treatment carburized, all dimensions in millimeters, tolerances ISO 2768-mK. Add a bottom scale bar labeled 1:1 with ticks from 0 to 100 mm.

Visual style: High-detail CAD drafting aesthetic, thin precise strokes, clean monospaced typography, subtle glow on white linework, red accent only for the sun gear detail and corresponding callouts, no photographic shading, no color except white/gray and red. Keep all text legible and aligned like a professional mechanical drawing.

Goal: Create an editorial fashion magazine cover featuring a dreamy close-up portrait of {argument name="character name" default="a young woman"} as a spring muse, surrounded by white flowers, with elegant high-fashion typography and soft cinematic light.

Canvas: Vertical magazine cover, 3:4 aspect ratio, full-bleed portrait photography style, cool pale blue-white palette with deep shadowed background edges.

Subject details: Extreme close-up of a delicate young woman with {argument name="hair color" default="platinum blonde"} tousled wispy hair falling across her forehead and partly over one eye, pale luminous skin, large glassy blue-gray eyes looking directly at the viewer, subtle peach-pink glossy lips slightly parted, minimal natural makeup, ethereal and melancholic expression. Her face fills the upper and center-right area of the cover, partly veiled by strands of hair and flower shadows.

Floral styling: Use exactly 5 visible flower groups in the foreground: 1 large soft white flower at bottom left, 1 large pale flower near the lower center, 1 cluster of tiny baby's-breath blossoms across the middle, 1 cluster of small white blossoms near the left cheek, and 1 pale daisy-like bloom near the lower right cheek. Flowers should overlap the lower half of the face and create translucent petal texture.

Lighting and mood: Soft spring sunlight from the upper left, high-key highlights on hair and flowers, gentle dappled flower shadows across the nose, cheek, and lips, muted contrast, airy haze, romantic quiet mood, refined art-magazine aesthetic.

Layout and typography: Place a huge white Didot/Bodoni-style serif masthead reading {argument name="magazine title" default="BLOOM"} across the very top, oversized and partially cropped by the canvas edges. Keep the masthead behind or visually integrated with the hair, but still readable. Use elegant white serif and small sans-serif text blocks.

Text content: Include exactly 6 discrete text elements: 1) masthead: “BLOOM” at the top; 2) small vertical tagline on upper left: “soft days in bloom — just as you are.”; 3) main feature title on left: {argument name="feature title" default="Spring Muse"}; 4) small Chinese subtitle below it: “花与光的私语”; 5) lower-left caption: {argument name="bottom caption" default="today, i choose softness. and a little bit of magic."}; 6) right-side poetic blurb: “a moment held for you petals, light, and everything I love about this season.” Add a small circular badge near the bottom center-left reading “vol. 07”.

Constraints: Fashion magazine cover only, no barcode, no extra logos, no additional text beyond the specified 6 text elements and the volume badge, no harsh retouching, no cartoon style, no watermark.

Create a full-body kawaii anime VTuber-style illustration of a cheerful cat-eared girl mascot, centered on a clean white background with pastel magical effects. The character is a petite teenage-looking anime girl with {argument name="hair color" default="silvery lavender-blue"} wavy shoulder-length hair, soft bangs, bright cyan-blue eyes, rosy cheeks, and an open happy smile. She has large cat ears with pink inner ears and dark outer tips, decorated with ornate gold-and-white floral hair accessories, small chains, beads, and a pink ribbon bow. Pose her dynamically as if floating or skipping forward: one hand raised close to the viewer in a friendly wave with five fingers visible, the other arm extended outward, one leg straight down and the other bent back playfully. Outfit: pastel blue oversized cropped jacket with puffy sleeves and white drawstring bows, pale blue shirt, white asymmetrical overall-style skirt/shorts dress with visible straps, buttons, seams, a white belt with crossing straps and small gold bow charm, layered light-blue ruffled shorts underneath, one white knee sock, one oversized blue leg warmer with bow details, and light blue-and-white sneakers. Add a tied ribbon accessory and small dangling charm at the hip. The color palette should be soft baby blue, white, pale pink, and gold accents, with delicate cel-shaded anime rendering, clean line art, glossy eyes, soft gradients, and high-detail clothing folds. Surround her with a circular aura of pastel pink and blue sparkles, glowing starbursts, bokeh dots, and floating heart-shaped petals; include exactly 3 large pink heart petals, 5 medium blue heart petals, and many tiny pink petals and miniature flower shapes scattered around the frame. Make the composition vertical, full body visible from head to shoes, airy and bright, with no text, no watermark, no extra characters, and a polished Japanese mobile-game character key visual look.

Create a cute pastel storybook illustration of a chubby golden-brown hamster sitting under a tipped-over wooden crate like a tiny trap on a light wooden floor. The hamster should have fluffy orange and cream fur, oversized glossy teary brown eyes, pink cheeks, tiny paws held nervously to its chest, little pink feet, a small open worried mouth, and an embarrassed expression. The wooden crate is propped up on the left by one rough stick tied with one rope knot and a cord leading down to a bait pile; the crate roof has hand-drawn writing that says {argument name="crate sign text" default="FREE SUNFLOWER SEEDS!"}, a downward arrow, and a small sunflower doodle. In front of the hamster place exactly 34 visible sunflower seeds: 26 clustered in the main bait pile and 8 scattered around the floor, with a few tiny crumbs. Add exactly 2 blue sweat drops near the hamster and one thought bubble in the upper left containing {argument name="thought bubble text" default="... I can't believe I fell for that..."}. Background: warm cream wall, soft depth of field, one blurred potted plant on the left, and one small framed hamster picture with a heart on the right. Visual style: adorable Japanese kawaii children’s-book watercolor mixed with clean digital line art, warm beige and honey tones, soft shading, rounded forms, gentle humor, no harsh outlines, square composition.

Create a dramatic vertical low-angle cinematic image of a colossal humanoid female android robot and her human pilot under a clear blue sky. The giant robot is the dominant subject, filling almost the entire frame from chest to head, viewed from below so she feels monumental. She has an anime-inspired beautiful face with pale porcelain skin, short tousled {argument name="hair color" default="silver-white"} bob hair with long wispy strands, glowing red cybernetic eyes with circular mechanical iris patterns, and a calm slightly distant expression with parted lips. Add detailed facial cybernetics: metallic jaw and cheek plates, small chrome ear components, black mechanical neck structure, and exposed glossy black inner machinery. Her body is a sleek futuristic female-form mech with highly reflective white and chrome armor, large rounded chest plates, segmented shoulder armor, visible black pistons, joints, panels, screws, seams, vents, and mirrored highlights. On the robot’s right shoulder stands exactly 1 human pilot: a young woman wearing glasses, long dark hair, a white long-sleeve blouse, dark blue jeans, and sneakers, standing confidently and looking outward toward the horizon. The composition should emphasize extreme scale contrast between the tiny pilot and the enormous robot. Use bright midday sunlight, crisp reflections, lens-like specular highlights on polished metal, ultra-detailed hard-surface design, realistic 3D rendering mixed with anime aesthetics, sharp focus, high contrast, and a vivid saturated blue sky with a small number of soft white clouds. No text, no watermark, no extra characters, no cockpit, no weapons.

Create a cinematic widescreen anime illustration of a scruffy middle-aged man leaning forward toward a large bowl of rice on a table, as if yawning, shouting, or reacting hungrily. The man has messy spiky {argument name="hair color" default="brown hair with lighter sunlit tips"}, rough stubble and short beard, tired closed eyes, an open mouth, and a wiry expressive body. He wears a loose worn {argument name="shirt color" default="pale gray-blue"} T-shirt with rolled sleeves, blue jeans, and a red belt. Place him in a cluttered old shed or garage interior at golden-hour morning light, with a dusty bicycle silhouette on the left, cardboard boxes and miscellaneous junk in the background, wooden beams, and soft haze through a bright window. In the foreground, show exactly 1 ceramic bowl filled with white rice topped with dark sauce and small green garnish on a worn wooden tabletop. Use dramatic backlighting from the upper left, warm amber highlights, cool teal-blue shadows, detailed hand-drawn linework, rough painterly anime texture, shallow depth of field, film still composition, expressive exaggerated pose, no text, no watermark.

Goal: Create a vertical monochrome Japanese manga page about a true-story style hamster father going overboard with a child’s summer homework poster.

Canvas: Tall portrait manga page, about 9:16, sepia ink on warm off-white paper, hand-drawn crosshatching and pencil-like linework, thin black panel borders, nostalgic Showa-era storybook atmosphere.

Layout: Use exactly 6 stacked horizontal comic panels. Interior setting is a cozy wooden room with floorboards, bookshelf, potted plant, curtains and window, art supplies, a large sheet of drawing paper, paint tray, bucket, brushes, and mugs. Keep all dialogue in Japanese speech bubbles and narration boxes.

Characters: Two fluffy hamsters. The child hamster is small, round, cute, black glossy eyes, no glasses, drawing earnestly with a brush. The father hamster is larger and rounder, wearing small round glasses, holding a mug at first, then a brush, becoming increasingly intense and focused. Both are rendered as realistic-cute hamsters rather than humanoid mascots.

Panel details: Panel 1 shows the child hamster facing a blank poster sheet on the floor, art supplies on the left, curtains and bookshelf behind. Add a vertical narration box on the right reading 「ハムスターの夏休みの宿題は『自由研究』の課題ポスターの提出が必要だった」 and a speech bubble from the child reading 「今年も緑化ポスターを描こう」. Panel 2 shows the child hamster drawing trees on the large paper while the father hamster with round glasses stands nearby holding a mug and watching. Panel 3 shows father and child side by side over the poster; father points or comments with a bubble 「ポスターか」 and the child replies 「うん、夏休みの宿題」. Panel 4 shows the father asking to borrow the brush, facing the child across the paper; include a question mark over the child’s head, father bubble 「ちょっと貸して」 and child bubble 「うん？」. Panel 5 is a close-up of the poster becoming extremely detailed: dense forest scenery with many trees and foliage, father’s paw holding a brush at the upper right, child bubble on the left 「おお……！お父さん上手！」. Panel 6 shows the father hamster completely absorbed, sweating and hunched over the poster, drawing an incredibly elaborate forest with dramatic speed lines; the child hamster behind him looks shocked and panicked. Include scattered art supplies, paint tray and bucket. Add a jagged speech bubble from the child reading 「お父さん……!!そしたらハムスターが描いたポスターじゃなくなっちゃう!!!お父さん!!お父さん!!」 and a bottom caption box reading 「ラストの２日で描き直した」.

Visual style: Vintage Japanese newspaper manga, soft sepia monochrome, detailed fur texture, expressive faces, gentle comedy pacing, realistic room perspective, no modern digital coloring, no watermark.

Customizable elements: The homework theme is {argument name="homework poster theme" default="greenery poster"}; the main characters are {argument name="animal characters" default="father and child hamsters"}; the father accessory is {argument name="father accessory" default="round glasses"}; the final poster subject is {argument name="final poster subject" default="dense forest scenery"}; the bottom punchline caption is {argument name="punchline caption" default="ラストの２日で描き直した"}.

Create a vertical photorealistic fashion portrait of an adult androgynous-styled woman with {argument name="hair color" default="black"} shoulder-length bob hair, pale smooth skin, and a calm confident expression. She is posed from mid-thigh to head against a dark black studio background with subtle film grain and faint dust speckles, body angled slightly left while facing the camera. She wears a sharp black tailored blazer over a crisp white button-down shirt with a deep open neckline, tucked into high-waisted black trousers, giving a stylish executive “big boss” look. Her left hand is raised to the temple of her sunglasses as if adjusting them. The image is mostly high-contrast black and white, but the round wire-frame sunglasses have vivid translucent {argument name="lens color" default="red"} lenses as the only strong color accent. Use dramatic softbox lighting from the upper left, sculpted shadows, glossy highlights on the hair, clean skin detail, cinematic editorial photography, shallow depth of field, realistic fabric folds, elegant monochrome tonality, and a vertical 9:16 composition. No text, no watermark, no extra people, no props beyond the sunglasses and outfit.

Create a retro 2.5D anime thumbnail in a cinematic 16:9 frame, showing a close-up of {argument name="character name" default="a mischievous gothic anime girl"} leaning toward the camera in a cluttered analog electronics room. She has long straight {argument name="hair color" default="black hair"} with blunt bangs, teal-green eyes, pale skin, small blush marks, pointed ears, and a wide unsettling grin with sharp triangular teeth. She wears a black top and a thin black choker, with her face centered and dominating the composition, shoulders cropped at the bottom, direct eye contact, playful but eerie expression. The background is a dim retro tech studio with exactly two visible CRT televisions: one large CRT on the left displaying bright cyan static and one darker CRT on the lower right with a small blue glow; include shelves, cables, ceiling pipes, hanging wires, old equipment, and a high window with washed-out daylight. Use a NORINORI CORE-inspired retro 2.5D aesthetic: cel-shaded anime character over a semi-realistic grungy room, thick ink outlines, muted olive-gray shadows, teal and magenta chromatic aberration along edges, VHS scanline noise, slight fisheye wide-angle distortion, low-light atmosphere, crisp face details, gritty analog texture, 1990s cyberpunk anime mood. Keep the image text-free, no logos, no watermark, no extra characters.

Create a polished sci-fi anime cosplay promotional composite featuring {argument name="character name" default="Alfin from Crusher Joe"} portrayed by the same tall young female cosplayer in exactly 5 separate poses, layered over a deep outer-space background. The character has long straight {argument name="hair color" default="honey-blonde hair"} with bangs, fair skin, soft idol-like makeup, and a serious-to-confident expression style. She wears a glossy retro space-pilot costume: a red leather cropped jacket integrated into a white-and-silver fitted flight suit, high metallic silver collar, silver gloves, white slim pants, red-and-white boots, a wide silver belt with a central buckle marked with a red “J”, and gold rectangular chest plates on the red jacket. Include exactly 5 visible character instances: 1) a large close-up figure in the lower left foreground, hand raised near her ear, looking toward the viewer; 2) an upper center figure with arms crossed, gazing off to the side; 3) an upper right back-turned three-quarter figure holding a futuristic silver pistol upright; 4) a full-body center figure standing with one hand on her hip; 5) a mid-right figure leaning forward and pointing directly toward the viewer. Behind them place a detailed retro rocket spaceship angled diagonally from left to right, with a blue nose cone, weathered metal hull panels, fins, engine glow, and a visible red “J” marking on one wing. Background is a dramatic starfield with blue nebula clouds, scattered bright stars, and cinematic space lighting. Style should look like high-end photorealistic cosplay photography blended with Japanese 1980s space-anime poster composition, sharp faces, glossy costume reflections, realistic fabric and leather texture, crisp cutout layering, dramatic rim light, no text captions, no watermark, no extra characters, and no additional repeated poses.

Goal: Create a cinematic Japanese supercar advertisement and technical blueprint poster for {argument name="car model" default="HAYABUSA 01"}, a fictional next-generation super sport hypercar.

Canvas: Wide 16:9 landscape poster, dark navy/black background with subtle engineering grid lines, high contrast, sharp readable typography, glossy photorealistic render blended with wireframe CAD drawing.

Main subject: A low, aggressive red hypercar in front three-quarter view facing right, occupying the lower center and right side. The front half is fully rendered in deep metallic crimson with black carbon fiber hood, sharp LED headlights, black mesh intakes, large splitter, black multi-spoke wheels, red brake calipers, reflections and rain-slick road highlights. The rear/left half transitions into a translucent white-blue wireframe cutaway showing chassis, wheel wells, cabin outline, engine/mechanical parts, and aerodynamic surfaces. Add blue and orange callout leader lines pointing to technical features.

Layout: Top left contains the English title “HAYABUSA 01” and subtitle “NEXT GENERATION SUPER SPORT.” Beneath it is a specification box. Across the top left/center are two blueprint views: 1 top-down car view and 1 side profile view with measurement lines. The center-left and lower-left contain technical diagram panels. The right half has a large Japanese headline and performance metrics. Bottom right contains a limited-production price block and a faint manufacturer-style logo.

Visible text content: Use crisp, legible text. Include these major Japanese headline lines exactly: “未来を、加速する。” and “頂点を超えるパフォーマンス。” Add smaller Japanese body copy beneath the headline. Include a stylized emblem/kanji mark at top right, “HAYABUSA 01” beneath it, and a red “01.” Include bottom tagline “DESIGNED FOR THOSE WHO DARE.” plus Japanese small copy. Include a large faint brand wordmark near the bottom right reading approximately “UN YAMAKI.”

Technical content and counts: Show exactly 6 technical information areas: 1 specifications table, 1 V6 twin turbo engine diagram section, 1 suspension system section, 1 dimensions section, 1 aerodynamics callout, and 1 wheels & tires / carbon fiber body callout area. The specifications table should list 9 rows: overall size 4,750 × 2,020 × 1,180 mm, wheelbase 2,780 mm, vehicle weight 1,250 kg, engine V6 twin turbo, displacement 3,500 cc, max power 670 ps / 7,000 rpm, max torque 82.6 kgf·m / 4,500 rpm, transmission 8-speed DCT, drive system MR. The performance stack on the right should contain exactly 4 metric cards with icons: MAX POWER 670 ps, 0–100 km/h 2.8 sec, TOP SPEED 340 km/h, LATERAL G 1.85 g. The blueprint measurement drawings should show exactly 4 prominent dimension values: 4,750, 2,020, 2,780, and 1,180. The lower dimensions panel should show exactly 2 car views, front and rear, with width numbers around 1,730 and 1,710.

Style: Premium automotive launch poster, cyberpunk Tokyo night mood, dark glossy street, red light trails on the far right, faint city lights and mist, precise white and cyan blueprint lines, orange accent callouts, subtle scanline/glow effects, luxury magazine advertising quality, ultra-detailed, realistic reflections, dramatic studio lighting.

Constraints: Keep all text clean and readable, do not let Japanese characters deform, no people, no extra vehicles, no watermark, no messy duplicated text, maintain the half-wireframe half-photorealistic car effect.

Goal: Create a cute scrapbook-style photo collage introducing a tiny black toy poodle puppy named {argument name="dog name" default="ぐり"}, with playful handwritten Japanese annotations and heart/paw doodles.

Canvas: Landscape 3:2 image, warm indoor lighting, cozy pet-room setting with beige fleece bedding and black metal crate bars in the background. Use realistic smartphone-style puppy photos combined into a clean collage, with thin white dividers between panels.

Layout: Use exactly 5 photo panels. Panel 1 is a large top-left close-up of the black puppy biting a human finger, showing huge glossy eyes, fluffy curly black fur, long floppy ears, and a tiny muzzle. Panel 2 is a top-right action shot of the puppy jumping or bouncing on a beige pet bed with ears flying outward and mouth open. Panel 3 is a bottom-left full-body shot of the puppy standing on a soft beige blanket, facing forward. Panel 4 is a bottom-center close-up of the puppy gently mouthing a hand, tilted head, fluffy ears framing the face. Panel 5 is a large bottom-right action shot of the puppy running or leaping across the bed with one front paw stretched forward, ears flying, mouth open excitedly.

Central text block: Place a black cloud-shaped label near the upper center overlap area. In small handwritten white text above it write 「なまえは」, then large white text 「ぐり」 with a white paw-print icon beside the name. Below the name area, add exactly 4 white handwritten bullet points with heart bullets: 「足がちょっと短い」, 「すっごい暴れる」, 「コヤの中が大すき♡」, 「とにかく、かわいい。」

Handwritten annotations: Add exactly 10 playful white handwritten Japanese callouts with black shadow/outline and small arrows or doodles: 1) near the top-left puppy ear, 「耳がちょっと上にある」 with an arrow pointing to the ear; 2) near the top center over the fluffy head/ear area, 「耳がでかい!! 毛がすっごく長いの♡」; 3) near the biting finger in the top-left panel, 「指を噛んでくる!!」 with an arrow; 4) near the bottom-left standing puppy, 「あそぼ!!」; 5) near the bottom-center hand-biting puppy, 「がぶっ♡」; 6) near the top-right jumping puppy, a small puff doodle; 7) near the top-right/bottom-right area, a simple motion doodle; 8) near the right side of the collage, 「コヤの中ですっごい暴れる!!」; 9) near the top of the bottom-right action panel, 「うぉぉぉー!!」; 10) near the bottom-right running puppy, a small motion-swoosh doodle.

Subject details: The puppy is a very small black toy poodle with extremely fluffy curly fur, oversized floppy ears, shiny round black eyes, a short muzzle, tiny legs, and an energetic mischievous personality. Keep the dog adorable, lively, and slightly chaotic.

Visual style: Realistic pet photography collage with cute social-media annotation style, white hand-drawn lettering, black drop shadows, little hearts, arrows, paw print, and motion doodles. The overall mood is affectionate, funny, and cozy.

Constraints: Use exactly 5 photo panels and exactly the listed text elements. Do not add extra dogs, extra panels, logos, watermarks, or unrelated text. Keep the Japanese text legible and handwritten.

Using REFERENCE_0 as the portrait photo, create a vertical Japanese appearance-consulting diagnosis sheet. Keep the original portrait recognizable and place it cropped on the upper-left side, while adding a clean editorial report layout around it.

Goal: Turn the single portrait into a polished “face diagnosis report” infographic for men, like a professional styling/appearance consultation output.

Canvas and style: Vertical A4-style report, cream/off-white paper background, thin black and gold decorative rules, navy section headers, small simple icons, neat Japanese typography, dense but readable magazine-consulting layout.

Main headline: Use {argument name="headline text" default="顔面診断レポート"} at the top right, with a smaller subtitle below: {argument name="subtitle text" default="印象・似合う髪型・服装・カラー提案"}. Add a tiny note saying it is an estimated diagnosis from one photo.

Layout: Create exactly 8 numbered diagnostic sections plus 1 final summary bar. Arrange them in bordered cards, with the portrait occupying the upper-left column and the analysis cards filling the right side and lower area.

Sections to include, exactly 8:
1. Overall impression: mature, clean, direct gaze, cool and calm atmosphere, suitable for mode/smart casual styling.
2. Face type estimate: “adult × close to straight-line features,” explaining sharp eyes/contours and a balanced elegant impression.
3. Personal color estimate: {argument name="personal color type" default="ブルベ冬寄り"}; include two color rows: recommended deep/high-contrast colors and colors that may be difficult. Show exactly 12 color swatches total: 6 recommended colors labeled black, charcoal, navy, royal blue, burgundy, silver gray; and 6 difficult colors labeled yellowish beige, orange, mustard, yellow-brown, pastel yellow, and a similar warm pale color.
4. Body frame estimate: {argument name="body type" default="ストレート寄り"}; describe a simple, high-quality, just-size outfit impression.
5. Best hairstyle: suggest not too long bangs, center/side part, clean silhouette, ash/gray/dark ash tones, and avoid overly heavy or voluminous perms.
6. Clothing that suits: list clean tops such as black shirt and navy shirt, tailored jackets and leather jackets, slim to just-size silhouettes, and V-neck/open-collar tops.
7. Colors that suit / colors that do not suit: create two small comparison boxes. Suited colors: black, charcoal, navy, wine, blue-gray. Less-suited colors: yellowish beige, orange, mustard, bright yellow-brown, overly pale colors.
8. Subtle improvement points: suggest small grooming and styling adjustments such as eyebrow design, hair volume control, reducing under-eye shadows with concealer, not overdoing face-line changes, maintaining a clean silhouette, and natural skin tone refinement.

Final summary: Add a full-width dark navy bottom summary bar with gold laurel/crown accents and the label {argument name="summary label" default="総評"}. Summarize that cool, mature charm is strong and black/navy/charcoal styling with sharp hair and high-quality simple clothing maximizes the impression.

Constraints: Keep the reference portrait identity and expression unchanged, do not beautify it unrealistically, do not add extra people, do not use English labels in the report, and keep all Japanese text visually plausible and neatly typeset.

Goal: Create a side-by-side comparison image showing an ancient illuminated manuscript page before and after restoration, inspired by the Book of Kells, with the restored version looking far cleaner, brighter, and more ornate than the damaged original.

Canvas: Wide horizontal black background, approximately 16:9. Place two large vertical manuscript panels side by side with generous margins: the left panel is the damaged original, the right panel is the restored reconstruction. Add a small centered label under each panel: left label “Original”, right label “Restored”.

Layout: Use exactly 2 main panels. The left panel occupies the left half and sits inside a white photo-like border. The right panel occupies the right half and is larger-looking, crisp, and framed by a pale parchment page edge. Both panels show the same general manuscript-page composition: a tall decorative border, a left text column, and a right illustration column.

Left panel, damaged original: Show a faded, weathered manuscript page photographed on a grayish archival background. The parchment is brown, stained, frayed, and translucent in places, with torn edges, missing corners, water damage, darkened seams, and uneven discoloration. The design is barely legible: a vertical text block on the left with dark medieval calligraphy, faded red and gold initials, and a right column with two ghostly miniature illustrations that are almost erased. The ornamental border should be visible but worn, dirty, and incomplete. Include one small dark circular blemish or hole near the center-right of the original page. Keep the whole left image muted, low contrast, and degraded.

Right panel, restored version: Show a vividly restored illuminated manuscript page on warm cream parchment. The page has a highly polished medieval Celtic style with abundant gold leaf, red, green, black, and orange ornament. Use an ornate architectural frame with interlacing knotwork, geometric panels, round medallions, and a domed arch at the top. The restoration should look idealized and too pristine, with sharp lines and saturated colors.

Restored page element count: Include exactly 1 large outer decorated manuscript frame; exactly 1 domed arch at the top filled with Celtic spiral ornament; exactly 4 protruding side ornaments on the frame, one at each side midpoint and corner-like extension; exactly 1 left vertical text column containing 10 lines of pseudo-Latin uncial calligraphy with decorated initials; exactly 2 rectangular narrative miniature illustrations stacked vertically in the right column; exactly 3 circular medallion ornaments overlapping the central divider and side frame; exactly 4 small square gold decorative blocks, placed near the top, center, lower center, and bottom of the frame.

Text and lettering: The manuscript text should resemble medieval Insular script and pseudo-Latin, not modern readable typography. Use decorative initials in green, red, gold, and black. Suggested visible pseudo-text can include “Scooc”, “infiricipio”, “Sicloi”, “thoratio”, “chomias”, “abysus”, “Zorozobat”, “ipsemagenu”, “bubliuns”, “Qauncor”, “habacautum”, “Zacchäus”, and “uenufurcanos”, but it may remain partly nonsensical as long as the style matches.

Visual style: Museum-comparison presentation, archival documentary on the left and idealized digital restoration on the right. High contrast between decay and restoration. The restored page should include obvious metallic gold leaf highlights, clean parchment, Celtic knots, evangelist-manuscript styling, and intricate medieval ornament.

Constraints: Do not add extra panels, people, UI controls, watermarks, or explanatory captions beyond the two small labels. Keep the comparison balanced and centered on a plain black background.

Using the provided reference image as the character base, transform the cosplay photo into a polished 2D anime key visual of {argument name="character name" default="Elfaria Albis Serfort"}. Keep the recognizable pale blue long hair, blue eyes, white-and-gold fantasy dress, off-shoulder sleeves, thigh-high stockings, and blue chest gem consistent with the reference, but redraw everything in clean high-quality anime line art with soft cel shading and luminous highlights.

Change the pose and framing: make her appear in a graceful upright seated pose near the same outdoor tree setting, hands gently clasping the skirt at the knees, looking toward the viewer with a calm soft smile. Let her long hair flow dramatically to the left as if caught by a breeze.

Background additions: create an idealized bright forest clearing with a tree trunk on the right, leafy canopy above, strong diagonal sunbeams from the upper left, soft blue sky glow, white daisies near the lower edge, and a few drifting white flower petals. Use a vertical portrait composition, close-to-medium framing, vibrant fantasy-anime lighting, crisp details, and a romantic ethereal atmosphere. Avoid photorealism; make it look like an official anime illustration.

Create a vertical vintage travel-poster collage about a solo traveler in Russia, using a gritty torn-paper scrapbook aesthetic, muted beige paper texture, halftone dots, rough paint strokes, distressed print grain, and high-contrast editorial photomontage. The main headline should dominate the top half: a black torn strip with white uppercase text “LOST IN” above enormous distressed red block letters “RUSSIA”. Center foreground: a stylish male tourist in his early 30s with short brown hair, trimmed beard, black sunglasses, tan overshirt jacket, gray T-shirt, black backpack straps, wristwatch, and a black camera hanging from his neck; he holds an unfolded paper map at waist level and looks confidently toward the right. Background and collage elements: on the right, large colorful onion domes of St. Basil’s Cathedral; on the left, an urban Moscow street scene with old buildings, pedestrians, and a red vintage car driving forward; include a red Moscow Metro “M” sign and a dark directional signboard with exactly 3 arrows labeled “RED SQUARE”, “GUM DEPARTMENT STORE”, and “ST. BASIL’S CATHEDRAL” with smaller Russian text above each English line. Add a blue brush-stroke caption near the upper left-center reading “WHERE STORIES LIVE FOREVER”. Include exactly 3 travel stamp/sticker elements: a round “ADVENTURE AWAITS” airplane stamp in the upper left, a small tan “RUSSIA” postage sticker in the upper right with Cyrillic text, and a round visa/passport stamp near the lower left. Add exactly 3 cultural/food stickers in the lower right: a bowl of red borscht with sour cream, and 3 nested matryoshka dolls grouped beside it. Add a torn black note panel in the bottom right with exactly 3 bullet lines: red star “ICONIC LANDMARKS”, blue star “RICH CULTURE”, white star “UNFORGETTABLE JOURNEYS”. Add a bottom-left torn label reading “RUSSIA MADE FOR EXPLORERS”. Keep the composition busy but readable, with layered ripped paper edges, blue and red paint accents, realistic photographic subject, poster-like typography, and no extra logos or watermarks.

Create a dramatic cinematic historical collage in a wide 16:9 format about a lost classical music masterpiece. The scene is split diagonally by torn parchment and black-gold paint textures. On the left, show a terrified young mother in an 18th-century cream linen dress fleeing through a dark rain-slick European city street while clutching her small curly-haired son in her arms; behind them, a shadowy armed husband pursues them through blue fog near baroque church silhouettes and old street lanterns. On the right, show an elderly 18th-century composer, about {argument name="composer age" default="84"} years old, with white powdered hair and a black velvet coat, seated at a candlelit wooden desk writing musical notation with a quill on manuscript paper. Behind him, include two sepia portrait busts or painted composer portraits, one with a rough red brushstroke across the eyes to suggest misattribution and historical mystery. Overlay the entire image with exactly three prominent manuscript-music elements: one sweeping golden staff of notes across the upper center, one torn sheet of musical score across the lower center, and one smaller red-and-gold notation fragment in the lower left. Add scattered gold ink splashes, black soot textures, torn paper edges, a red wax seal near the lower right, stacks of old papers, brass candlesticks with lit candles, and deep chiaroscuro lighting. Use a baroque thriller aesthetic, ultra-detailed painterly photorealism, moody blue shadows on the fleeing figures, warm amber candlelight on the composer, high contrast, textured parchment background, no modern objects, no readable text, no watermark.

Using the provided reference image, restore and enhance it into a clean, realistic cinematic portrait while preserving the same subject, pose, composition, wet-hair look, black sleeveless outfit, backlit subway-platform setting, and moody atmosphere. Remove the dirty glass/reflection overlay, stains, haze, and visual noise from the reference. Reconstruct obscured facial and body details naturally, making the face, skin, hair strands, shoulder, back, and clothing clearer and more lifelike without changing the identity or framing. Slightly sharpen the image, improve contrast, and apply natural color correction with warm golden backlight and subdued green-black shadows. Keep the background softly blurred and atmospheric, with the platform lights and distant silhouettes remaining out of focus. The final result should look like a realistically restored, high-quality editorial photo rather than an overprocessed image.

Create a photorealistic full-body portrait of an adult {argument name="subject" default="East Asian woman in her mid 20s"} sitting on the edge of a dark wooden outdoor deck in front of large black-framed glass patio doors. She has long straight {argument name="hair color" default="dark brown"} hair parted slightly to one side, natural makeup, small earrings, and a gentle relaxed smile while looking directly at the camera. She wears a fitted short-sleeve {argument name="dress color" default="pale pink"} high-neck mini dress, a delicate bracelet, and no shoes; her bare feet rest on the deck, her legs are crossed at the knees, and her hands are folded neatly on her lap. The setting is a modern café or cabin terrace with warm wooden benches and tables visible through and beside the glass, a folded cream bag or cloth on a wooden bench to the right, and soft greenery reflected in the windows. Use natural daylight, soft diffused lighting, shallow depth of field, realistic skin texture, accurate anatomy, elegant casual posing, warm wood tones, and a high-resolution DSLR portrait look. Vertical composition, eye-level camera, 3/4 seated pose, subject centered slightly right, calm lifestyle fashion photography mood. Avoid text, watermark, extra limbs, distorted hands or feet, heavy retouching, cartoon style, or overly dramatic lighting.

Create an elegant editorial studio portrait poster for {argument name="brand initials" default="ABKR"}. Use a square canvas with a warm off-white textured paper background. Center a large rounded-rectangle photo panel in very dark forest green, leaving generous cream margins. Inside the panel, show a photorealistic waist-up portrait of a young Black man with deep brown skin, short close-cropped black hair, clean-shaven face, defined jawline, full lips, straight nose, and expressive dark eyes looking off to the viewer’s left. He wears a plain black crewneck T-shirt with a small gold handwritten signature logo reading {argument name="signature text" default="Abkr"} across the chest. Pose him three-quarter view with shoulders angled slightly left and head turned left, calm confident expression, soft studio lighting, crisp skin detail, natural shadows, premium fashion look. At the top, set the large spaced serif letters {argument name="top monogram" default="A B K R"} in dark green, centered, with a thin gold ornamental divider beneath it. At the bottom right, add small gold issue numbering {argument name="issue number" default="01"} with a thin horizontal line below. Minimal luxury branding, refined typography, muted color palette of cream, dark green, black, and gold, high-end magazine cover aesthetic, no extra text, no watermark.

Create a realistic night street fashion portrait in a busy Tokyo-style city intersection, shot at pedestrian height with a shallow depth of field. The subject is {argument name="character description" default="a young East Asian woman with long wavy black hair, fair skin, and a soft confident smile"}, standing on a wide zebra crossing and looking back over her shoulder toward the camera in a three-quarter rear pose. She wears {argument name="top" default="a fitted white spaghetti-strap tank top"} and {argument name="pants" default="high-waisted light blue skinny jeans"}, with a delicate dangling earring visible. In her lowered right hand she holds a small cream-colored structured handbag and a black smartphone. The background shows a crowded urban crosswalk at night, blurred pedestrians, a passing black taxi on the left, bright storefronts, glass buildings, glowing billboards, and recognizable Shibuya/Ginza-like city lighting. Use natural skin texture, soft cinematic bokeh, realistic lens perspective, muted urban colors, and flattering ambient neon illumination. Compose vertically in a 2:3 aspect ratio, full-body to mid-calf framing, with the woman centered slightly right and the crosswalk stripes leading into the luminous city behind her. Avoid text overlays, watermarks, exaggerated anatomy, cartoon styling, or over-smoothed plastic skin.

Create a cinematic 16:9 anime fantasy portrait of a tall, slender mage facing forward in a powerful symmetrical pose. The character wears a white lacquer fox-like half mask with two tall horn-shaped ears, orange-red ritual markings, narrow eye slits, and one glowing circular sigil centered on the forehead. Long wild black hair streams dramatically outward behind the head, with two thin front braids tied with small red tassels. The mage is dressed in pale layered robes and a voluminous cream-white feathered or fur-like mantle with soft textured tufts, arms extending outward beyond the frame. Use a vibrant neon-accented palette: warm ivory robes, deep blue-black hair, orange flame-like glow, and a flat teal-blue sky background. Add a few floating ember sparks and partial orange flame shapes near the upper right edge and mask tips. Style it as high-end painterly anime concept art with rough ink lines, visible grain, expressive brush texture, dramatic backlit rim lighting, calm mysterious expression, centered composition, no text, no watermark.