GPT Image 2Prompts

Create an image displaying a collection of 'rejected routes' for {argument name="対象キャラクター" default="this character"} in a game UI style. Arrange multiple cards showing 'what-if' scenarios not seen in the main story (e.g., {argument name="シナリオ例" default="breakup, rejection, misunderstanding, going out of control, etc."}), each with a short title and a one-sentence description. Change the character's expression and atmosphere for each route. Make it look like a scenario selection screen from a social game or visual novel.

Please generate a complete single building model image of "[Building Name]". The image should only show the main body of the building and its immediate foundation environment, without showing unrelated buildings, large empty spaces, city backgrounds, or complex surroundings. Please highlight the building's volume, frontal structure, roof form, entrance, facade, stylobate, and steps. The perspective should be an isometric slight top-down view, with a centered, symmetrical, and clear composition, like displaying an independent ancient building model. The main building should occupy more than 70% of the visual area of the image. The image is suitable as a reference for subsequent AI construction animations from "foundation to completion". Do not include people, vehicles, modern machinery, text signs, billboards, or unrelated elements. Based on the previous single building reference image of "[Building Name]", generate a structural exploded view. Please maintain the same isometric slight top-down perspective and composition, separating the building vertically according to the construction levels to clearly show the assembly relationship of each layer's structure. Please divide it into reasonable levels according to the building's own characteristics: foundation or bottom base, stylobate, platform, steps or base layer, column grid, walls, doors and windows and main frame, beam frame, load-bearing structure and porch structure, facade, railings, decorative components and detailed structures, roof skeleton, roof covering and top structure, final exterior decoration and finishing components. The image should look like a high-quality architectural illustration, with each layer staggered vertically but maintaining central axis alignment. Each layer must be clear, clean, and recognizable, suitable as a reference for subsequent AI construction animations. Based on the previous complete model image and structural exploded view of "[Building Name]", generate a building materials and components display image. Like a construction material list, neatly arrange the main materials and key components needed for construction in the image. Each material or component should be displayed as a clear physical sample or independent component model. Please include the following types according to the building's characteristics: foundation, stylobate, platform, step components, wooden columns, walls, main frame components, doors, windows, railings, entrance, porch components, beams, frames, support structures and load-bearing components, roof skeleton, roof tiles, top covering, facade materials, decorative pieces and finishing components, the building's most recognizable roof, porch, and traditional wooden details. The image should be a clean material display board, with an isometric or orthographic perspective, all components clearly grouped, neatly arranged, and with realistic textures. The overall color and material style must match the building itself. Based on the previous complete model image, structural exploded view, and material component image of "[Building Name]", generate an 8-panel construction flowchart. Theme: The construction process of "[Building Name]" from an empty foundation to a complete building. Please use a unified isometric slight top-down perspective, unified composition, and unified lighting, keeping the building always centered. The image should only show the main building and necessary immediate foundation environment, without unrelated buildings, large empty spaces, people, vehicles, or complex backgrounds. The sequence of the 8 panels should be reasonably generated according to the building's own structure: empty foundation or bottom base appears; stylobate, platform, base layer, and steps form; stairs, railings, boundaries, and entrance foundation details are completed; wooden columns, walls, doors, windows, and main frame are erected; beam frame, load-bearing structure, porch, and intermediate structures are installed; roof skeleton, top structure, and main shape are completed; roof tiles, facade, decorative pieces, and key feature components are gradually completed; the complete building is finally presented. Each panel should look like a continuous construction stage under the same camera lens, and there must be a clear progressive relationship between stages. Do not make panel 7 and panel 8 too similar. Panel 7 should be close to completion but not fully finished, and panel 8 is the complete final piece.

{"type":"Japanese YouTube thumbnail collage","style":"bold anime-tech promotional thumbnail with clean digital illustration, high contrast, saturated colors, thick outlined typography, energetic magazine-style composition","canvas":{"aspect_ratio":"16:9","resolution":"1200x630"},"background":{"frame":"mint green outer border with cyan accent strip along the top and bottom edges","main_scene":"warm modern bedroom interior with wooden headboard, beige bedding, cream curtains, bedside shelf, and a small alarm clock"},"layout":{"sections":[{"title":"データセット作り!","position":"top-left","count":8,"labels":["back view","three-quarter back view","front view","full back standing view","side profile","rear side profile","three-quarter front view","standing portrait with crossed arms"]},{"title":"部分修正!","position":"bottom-left","count":1,"labels":["character editing app screenshot with anime woman in white jacket over blue shirt"]},{"title":"素材作り!","position":"lower-mid-left","count":1,"labels":["smartphone asset design image showing a hand holding a purple screen phone with a large eye symbol and a vertical strip of 5 small variant thumbnails"]},{"title":"合成!","position":"upper-center-right","count":2,"labels":["anime woman cutout portrait","bedroom background plate"]}],"connectors":{"count":2,"style":"curved pink arrows with white outline pointing from the cutout portrait and bedroom plate toward the final composite on the right"},"text_overlays":{"count":7,"items":["データセット作り!","部分修正!","素材作り!","合成!","「{argument name=\"headline text\" default=\"GPT Image2\"}」徹底検証!","ノイズ除去法から{argument name=\"feature text\" default=\"LoRA学習\"}まで","©{argument name=\"credit name\" default=\"スタジオ真榊\"}"]}},"subjects":{"main":{"type":"anime woman","count":1,"appearance":{"age":"young adult","build":"slim curvy","hair":{"color":"{argument name=\"hair color\" default=\"long black\"}","style":"very long straight hair with soft shine, center part, strands falling over shoulders"},"face":"intentionally blurred/censored rectangle over the face","outfit":["white fitted long-sleeve scoop-neck top","visible black camisole straps","black pants"]},"pose":"seated on the edge of a bed, torso angled slightly left, hands resting near lap, looking toward camera"},"inset_character":{"type":"same anime woman reference art","count":10,"notes":"all inset figures use the same character design with face blurred in several panels"}},"typography":{"primary":"very large Japanese headline across the bottom in white with black outline and hot pink emphasis around GPT Image2","secondary":"subheadline in orange, white, black, and bright blue mixed emphasis","annotation":"handwritten energetic pink labels with white stroke near each inset section"},"color_palette":{"count":8,"colors":["hot pink","white","black","cyan","mint green","orange","beige","dark brown"]},"composition":"right half dominated by the final anime bedroom illustration, left half packed with inset process examples and screenshots, oversized bottom headline spanning nearly full width, designed to advertise a deep-dive verification article about GPT Image2 workflows for dataset creation, partial edits, asset generation, compositing, noise removal, and LoRA training"}

Using the provided reference image, recreate the same two foreground people in the same selfie composition, preserving their clothing, hairstyle silhouettes, hand gesture, and relative positions, but transform the photo into a crude hand-drawn digital doodle. Make it look like a simple MS Paint cartoon with thick black outlines, flat fills, intentionally rough proportions, minimal detail, and a plain light gray background. Remove the waterfront, sky, and all background people so only the 2 main subjects remain. Keep the face areas anonymized as large blurred rectangular blocks.

A highly detailed Dadaist mixed-media collage portrait of an androgynous anime boy centered in the composition, shown from the chest up with a calm, slightly melancholic expression and direct gaze. He has messy spiky white-gray hair and pale skin, with one visible eye rendered in a realistic anime style and the face fragmented by torn paper strips, geometric shards, and overlapping newsprint pieces. The entire figure is constructed from layered vintage newspaper clippings, technical diagrams, blueprint grids, distressed typography, cut-paper textures, and photocollage fragments, creating a deconstructed cubist look. Use a muted aged-paper palette of beige, off-white, charcoal black, faded navy blue, gray, and small accents of dark red. The background is a dense wall of torn printed pages and graphic scraps on weathered paper, with exact visible text elements including large “DADA” at the upper left, “anti-kunst” near the upper right, “Die Kunst ist tot / Es lebe / die Kunst” on the left-middle, “ZUFALL / ist / notwendig” on the lower left, oversized “6” and “No.” on the left, fragmented “X”, “UT”, and “frag / ment” on the lower right, and partial year numerals “192” at the top right. Include exactly 3 separate realistic eye cutouts in the collage outside or partially outside the main face, 2 small bee illustrations pinned into the body area, 3 target-like circular graphics on the clothing, 1 small astronaut or suited figure photo at the upper right, 1 mechanical rocket or engine collage element at the upper left, 1 ocean-wave photo strip at the lower right, and multiple circular diagram overlays. The character’s outfit should read as a futuristic high-collared jacket assembled from paper scraps and schematic fragments, with small red label details near the collar and a visible “06” marking on the chest. Composition should be vertically poster-like, tightly packed, asymmetrical, and editorial, with gritty tactile paper edges, glue seams, xerox noise, ink smudges, and strong contrast between organic portrait features and abstract graphic construction. Style: avant-garde Dada, Bauhaus-inflected collage, manga portrait fused with archival print ephemera, ultra-detailed, textured, flat frontal view, no clean digital gradients, no modern glossy finish.

A moody cubist geometric portrait of a futuristic humanoid figure, shown from the chest up and filling the frame, with the face intentionally obscured by a large soft-edged rectangular blur centered over the facial area. The composition is built from sharp interlocking triangular and polygonal planes, like fractured glass or faceted metal, forming the hair, head, neck, shoulders, and body armor. Use a dark palette dominated by navy blue, slate, charcoal, black, steel gray, and off-white, with small but striking accents of deep red and muted rust. The figure has angular black hair rendered as jagged crystalline shards, one visible ear on the right side, a pale faceted neck, and broad armored shoulders. The torso resembles a sci-fi mech or android shell in white and blue-gray panels, with the printed number {argument name="chest marking" default="01"} on the upper chest and 2 visible circular mechanical ports or lens-like details: 1 large dark circular component near the lower center chest and 1 smaller dark circular component on the right shoulder plate. In the background, include 2 circular celestial or abstract orb forms: 1 pale moon-like circle in the upper left and 1 dark red orb on the right side, plus 2 sets of vertical architectural bar shapes, one along the left edge and one near the upper right edge, integrated into the same faceted abstract structure. Style it as an oil painting with heavy brush texture on canvas, combining cubism, futurist portraiture, and abstract sci-fi design. The mood is somber, enigmatic, and cinematic, with strong contrast, fragmented lighting, and a symmetrical-but-broken composition. Portrait orientation, tightly cropped, highly detailed, textured, gallery-quality artwork.

A dark, ornate, Pre-Raphaelite-inspired portrait of {argument name="character name" default="a red-haired anime heroine"} standing front-facing in a dense cathedral garden, wearing a glossy red futuristic plug suit with black and dark blue paneling and small green chest accents. She has very long, slightly tousled auburn hair with two subtle red hair clips near the crown, pale skin, and a solemn, devotional pose: one hand resting over her chest and the other loosely holding a small bouquet of white lilies downward. Behind her head is a large circular stained-glass halo with intricate gold tracery, blue and ruby jewel tones, and star motifs, creating the effect of a saint icon. The background is packed with climbing vines, deep crimson roses, blooming white lilies, antique brass candleholders, and a faint statue-like female figure recessed on the right side. The composition is centered, symmetrical, and waist-to-thigh portrait framing, with rich oil-painting texture, moody chiaroscuro lighting, aged varnish tones, high detail, gothic floral decoration, sacred-art atmosphere, and an elegant fusion of anime mecha design and medieval religious iconography.

A monochrome pencil sketch landscape drawn in a loose scribbly hand on white paper, with visible graphite texture, rough hatching, and expressive crosshatched shading. Show a peaceful rural valley scene with 1 large leafy tree dominating the right foreground, its trunk dark and textured and its canopy made of sketchy clustered marks. A narrow dirt road begins near the bottom center and curves gently into the middle distance toward 1 small farmhouse with a pitched roof placed left of center. Add 1 line of fence posts with wire running alongside the road in the left foreground, low grasses and bushes around the roadside, and scattered shrubs and trees near the house. In the background, draw a range of layered mountains with the tallest peak left of center, softly shaded with diagonal pencil strokes. Include a lightly sketched sky with 2 large clouds and 3 tiny birds in flight. Keep the composition airy, pastoral, and hand-drawn, with natural perspective, unfinished sketch energy, and no color, as if from a casual landscape sketchbook study.

{"type":"anime manga comic page","style":"clean modern manga illustration, colorful slice-of-life, soft shading, glossy eyes, bright highlights, polished digital art, black panel borders, white speech bubbles with Japanese text, energetic and heartwarming mood","format":"single page with 5 numbered panels","reading_direction":"right to left manga layout","setting":{"location":"small cozy apartment room on a rainy holiday weekend","weather_start":"steady rain outside the window","weather_change":"sudden bright sunshine and blue sky"},"characters":[{"role":"main girl","appearance":"teen anime girl with very long straight black hair, fair skin, oversized lavender sweatshirt, relaxed indoor look","emotion_arc":["disappointed","surprised","excited","grateful","cheerful"]},{"role":"visitor friend","name":"{argument name=\"character name\" default=\"高坂穂乃果\"}","appearance":"cheerful anime girl with bright orange side ponytail tied with a yellow ribbon, orange zip hoodie over a white T-shirt with a yellow star motif, blue denim shorts","energy":"sunny, lively, encouraging"}],"layout":{"panels":[{"number":1,"position":"top full-width panel split composition","count":2,"elements":["weekly weather forecast board leaning at left side showing 7 days with many gray cloud and blue umbrella rain icons","main girl sitting by the window looking at a pink smartphone with a gloomy expression","rain streaks on the window","mug on the table","round beige cushion or plush in the background"],"text_mood":"she sighs because the long weekend forecast is all rain and she cannot go out to play"},{"number":2,"position":"upper middle right panel","count":2,"elements":["friend suddenly appears energetically at the doorway with sparkling effects","main girl looks up in shock"],"text_mood":"the friend says rainy days do not suit her and greets her energetically"},{"number":3,"position":"upper middle left large panel","count":1,"elements":["friend outdoors under a vivid blue sky with a blazing sun, arm stretched wide, winking, sparkling everywhere, dramatic warm glow"],"text_mood":"the friend declares she will stop the rain"},{"number":4,"position":"middle bottom split panel","count":2,"elements":["main girl indoors with clasped hands and shining eyes, deeply impressed and thankful","adjacent small scene of her kneeling on the floor preparing to go out, holding up a white dress on a hanger beside a pink travel bag, straw hat, folded clothes, and sunny window"],"text_mood":"she praises the friend as truly sunny and starts getting dressed up to go out"},{"number":5,"position":"bottom full-width split panel","count":2,"elements":["friend outside in sunshine turns back with a bright smile and raised finger, light breeze moving her hoodie","main girl at the doorway waves goodbye happily with a small heart symbol"],"text_mood":"they thank each other and promise to have fun"}]},"props":{"count":10,"items":["weekly weather forecast board","pink smartphone","ceramic mug","rainy window","beige round cushion or plush","white dress on hanger","pink bag","straw hat","folded clothes","sparkle effects"]},"text":{"language":"Japanese","visible_labels":["週間天気予報","土","日","月","火","水","木","金","はぁ…","パァァァッ!!","ひょこっ","ほ"]},"color_palette":{"rainy_scene":"muted grays, cool blues, lavender","sunny_scene":"bright sky blue, warm sunlight, orange, yellow sparkles"},"camera":"varied manga framing with close-ups, medium shots, and one dramatic outdoor hero shot","quality":"high-resolution manga page suitable for social media sharing or a short character comic"}

Redraw the attached image in the most clumsy, scribbled, and completely pathetic way possible. Use a white background and make it look like it was drawn in {argument name="software" default="MS Paint"} with a mouse. It should be vaguely similar, but also not really, kind of matching, but also wrong in a confusing and clumsy way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, draw it however you want.

{"type":"anime-style floral personality poster","subject":{"gender_presentation":"young woman","pose":"three-quarter back view, upper body turned slightly left, head angled down gently, holding a large wrapped bouquet in both hands","face":"mostly obscured with a soft rectangular blur over the face area","hair":{"color":"very dark brown to black","length":"very long, reaching past the waist","style":"straight, silky, center part, smooth layers framing the head and back"},"clothing":{"top":"soft knit off-shoulder sweater dress","color":"cool gray","fit":"loose and slightly oversized with long sleeves slipping down the shoulders"}},"bouquet":{"style":"romantic mauve and dusty purple mixed flower bouquet wrapped in translucent paper","count":8,"items":["white pink-tinted lilies","dark purple calla lilies","lavender rose","burgundy roses","pale blush roses","pink astilbe","baby's breath","eucalyptus foliage"]},"layout":{"background":"clean light gray to off-white minimal background","composition":"large illustrated woman on the left, vertical flower meaning list on the right, concluding quote box centered at the bottom","sections":[{"title":"flower list","position":"right side vertical column","count":8,"labels":["01. Lily (Pink)","02. Rose (Lavender)","03. Rose (Burgundy)","04. Calla Lily (Dark Purple)","05. Lisianthus","06. Astilbe (Pink)","07. Baby's Breath","08. Eucalyptus"]},{"title":"summary quote","position":"bottom center boxed text","count":1,"labels":["The structure of the person you are, represented by this bouquet"]}],"right_column_format":"each of the 8 entries has a circular flower thumbnail, a numbered Japanese heading, then 2 short explanatory lines beginning with Flower Language and Reason","bottom_box_format":"one heading line above one quoted Japanese sentence"},"text":{"language":"Japanese","bottom_heading":"The structure of the person you are, represented by this bouquet","bottom_quote":"'A person who combines delicate sensibility with inner strength, staying true to their own aesthetics.'"},"style":{"medium":"delicate watercolor and pencil anime illustration","mood":"elegant, introspective, feminine, poetic","palette":"muted mauve, lavender, burgundy, dusty pink, charcoal gray, soft white, sage green","linework":"fine sketch-like lines with soft shading","finish":"editorial character poster with refined Japanese typography and airy negative space"}}

A dramatic Japanese movie poster collage in a glossy sentimental coming-of-age style, designed like an official theatrical key visual. The composition centers on a large close-up portrait of {argument name="main character" default="a young Japanese woman"} with shoulder-length softly wavy brown hair, natural makeup, and a white blouse, lit by warm golden sunset light and rim light around the hair. Surround the central portrait with a dense montage of 9 supporting visual elements: 1) top left, the heroine as a high school student in a dark school uniform with a ribbon tie, seen in profile against a glowing sunset sky; 2) mid left, a smaller school-uniform portrait of the heroine; 3) left lower-mid, a small fluffy long-haired brown dog looking toward camera; 4) top right, the heroine as an office worker typing on a laptop indoors at night in warm room light; 5) right middle, a romantic silhouette scene of a woman and man standing by a riverside railing at sunset; 6) right lower-middle, a ferret curled in a soft blanket looking outward; 7) lower right, a graduate in cap and gown holding a diploma; 8) lower center-left, the heroine sitting on a shoreline from behind beside the dog and the ferret; 9) a stack of 2 small tilted snapshot photos on the right side, one showing a concert or live-house scene from behind and one showing the heroine riding a bicycle by the water. In the lower left background, include a large red torii gate standing in the sea near a city skyline, reminiscent of Miyajima, under a vivid orange-pink twilight sky with reflective water. Add soft cherry blossoms framing the lower right edge. The overall mood should be emotional, inspirational, bittersweet, and life-affirming, with rich amber, rose, and violet tones, cinematic depth, poster-grade compositing, soft bloom, and polished film-poster typography. Prominently place the large Japanese title {argument name="title text" default="私という奇跡"} across the center-bottom in bold white brush-calligraphy, with the English subtitle {argument name="english subtitle" default="The Miracle of Me"} below it in elegant serif type. Add multiple lines of small white Japanese catchphrase text integrated around the collage, including reflective quotes near the upper left, upper right, left middle, and bottom area. Include a centered Japanese tagline below the title, small production credits near the bottom center, and the year plus {argument name="release label" default="ROADSHOW"} at the bottom right. Make it look like a premium 2024 Japanese drama film poster about one woman's life journey through school, work, love, pets, music, and graduation.

A cute hand-drawn animal illustration in a soft watercolor and colored-pencil storybook style, viewed from directly above. Two ferrets are curled together snugly inside a square pet bed with high padded sides. The left ferret is a pale cream color with fluffy fur, a pink nose, round glossy black eyes, and a gentle sweet expression; its long body curves around the other ferret protectively. The right ferret is a sable ferret with a dark brown body, warm tan underfur, a cream face mask, pink nose, and bright black eyes, smiling slightly with tiny teeth visible and one small paw raised near its chest. Their bodies form a cozy spiral composition, touching cheek to cheek. The bed has a soft light gray inner cushion and dark charcoal-black outer sides, with visible fabric texture and softly shaded folds in each corner. Around them are 4 pink doodle hearts and 4 sparkle or emphasis marks in a playful sticker-like style, adding a kawaii mood. Use a warm off-white paper background with subtle beige wash, delicate textured edges, fine fur detail, soft lighting, charming pastel accents, and an overall adorable affectionate feel.

A warm, cinematic anime-style group illustration set in a cozy creative studio at night, showing 5 young adult characters gathered around a wooden table during an AI brainstorming session. The scene is viewed at table height in a natural candid composition, not everyone looking at the camera. In the foreground center, a short black-haired person in a black hoodie sits with their back partly toward the viewer, working on an open laptop whose screen shows a glowing blue futuristic AI interface with a circular "AI" emblem. On the left foreground, a silver-haired young man in a white high-collar jacket with pale blue trim sits in profile, facing toward the group. Mid-left, another silver-haired young man in a light jacket and white shirt sits thoughtfully with one hand near his chin. At the back center-right, a tall elegant silver-haired figure in flowing white layered robes leans forward over the table, guiding the discussion. On the right, a silver-blue-haired young woman with a side ponytail wears a white and blue hoodie and rests her cheek on one hand while using a tablet. Include exactly 2 visible laptops with glowing blue AI-themed dashboards, exactly 1 tablet in use on the right, exactly 1 white ceramic mug near the center, exactly 1 black takeaway cup with a blue heart icon near the front right, and exactly 1 small bowl of snack cubes on the far right edge of the table. In the background, show a glass board or wall on the left with hand-drawn Japanese brainstorming notes and diagrams, including "AI", "アイデア", "未来", and repeated "画像生成" written in marker. Add a leafy green houseplant behind the group and warm hanging lights or soft bokeh lighting in the studio. Use golden hour indoor lighting, rich amber highlights, soft shadows, highly polished anime illustration rendering, detailed hair strands, reflective screens, and a collaborative, intelligent, relaxed mood. Add an elegant cursive text overlay along the bottom reading "{argument name="character names" default="Mai, Luca, Koyo, Grace & Shun"}".

Deconstruct the outfit of the main character in the image to generate a fashion design layout. Include clothing structure, color scheme, materials, accessories, props, front view, side view, back view, detail close-ups, and real-person wearing effect, 3:2.

remove the hair from the nape of the character in the image 1. Use the back view of the character sheet in image 2 as reference for the correct character look. remove the blue strand of hair from the character of image 1, located just above the hand on her head. Use the back view of the character sheet in image 2 as reference for the correct character look.

{ "prompt": { "overall_concept": "A realistic young western woman in a taekwondo uniform (dobok) standing confidently with arms crossed, surrounded by 5 chibi/anime-style cartoon versions of herself in various taekwondo poses, all on a clean white/light gray studio background", "main_subject": { "type": "realistic photographic style", "person": { "ethnicity": "western ", "age_appearance": "early-to-mid 20s", "gender": "female", "hair": { "color": "blonde, (#1a1008)", "length": "long, past shoulders", "style": "straight with soft layers, side-swept bangs, flowing naturally", "accessory": "large dark navy blue bow/ribbon hair tie on the right side of head, matte fabric texture, double-loop bow shape, color: #1a2a4a" }, "face": { "expression": "calm, confident, neutral with slight seriousness", "eyes": "green, almond-shaped, natural makeup", "skin_tone": "fair porcelain Korean skin, warm undertone, hex approximately #f0d5bc", "features": "soft facial features, natural no-heavy-makeup look" }, "pose": "standing upright, arms crossed over chest, weight balanced evenly, barefoot", "body": "slim athletic build" }, "uniform": { "name": "Taekwondo Dobok (태권도)", "top": { "color": "pure bright white (#ffffff)", "collar_and_trim": "solid black V-neck collar trim, approximately 1.5cm wide, color #0a0a0a", "fabric": "crisp cotton with slight texture, natural light wrinkles", "patch_left_sleeve": { "type": "Korean Taegukgi (태극기) flag patch", "size": "approximately 6x4cm rectangular", "colors": "red (#c8102e), blue (#003478), white (#ffffff), black trigrams (#000000)" }, "text_on_sleeve": "태권도 in black Korean hangul characters" }, "belt": { "color": "solid black (#0a0a0a)", "width": "approximately 4-5cm", "text": "태권도 written vertically in gold/yellow Korean characters (#d4a017), centered on belt front", "knot": "standard martial arts double-knot at center front with two equal-length tails" }, "pants": { "color": "pure white (#ffffff)", "style": "wide-leg, traditional dobok cut", "fabric": "same crisp white cotton as top" }, "feet": "bare, natural skin tone" } }, "chibi_characters": { "style": "Japanese anime chibi style, 2D flat illustration with clean black outlines, cel-shaded coloring, large round heads (approximately 1:1.5 head-to-body ratio), oversized eyes", "shared_design": { "hair": "same dark brown-black (#1a1008) long hair as main subject", "hair_bow": "same dark navy blue bow (#1a2a4a) on right side of head", "uniform": "same white dobok with black collar trim, Korean flag patch, black belt", "skin": "warm anime-style peach skin (#f5c9a0)", "eyes": "large round anime eyes, dark brown with highlight sparkles (#2a1a0a with white #ffffff catchlight", "outline": "clean black #000000 outlines, 2-3px weight", "cheek_blush": "subtle round pink blush marks on cheeks (#f4a0a0, low opacity)" }, "instances": [ { "position": "held in arms of main subject, upper left area", "pose": "sitting/perched, one hand raised in salute gesture near forehead, mouth open in happy expression", "expression": "cheerful, excited" }, { "position": "lower left of composition", "pose": "fighting stance, legs spread wide, one arm raised with fist, one arm lowered in guard", "expression": "determined, shouting battle cry, mouth wide open" } ] } } }

Photorealistic candid image of a {argument name="subject" default="young Japanese female cashier"} (early 20s) working in a {argument name="location" default="convenience store"}, wearing a typical uniform (white shirt with green, red, and orange accents, name tag “{argument name="name" default="Aiko"}”, hair neatly tied back). She stands behind the counter, serving a customer with a natural, friendly expression. Shot from a customer’s smartphone POV—slight foreground blur, imperfect framing, unposed feel. On the counter: POS terminal, barcode scanner, small items like snacks and drinks. Bright, even convenience store lighting; clean interior with neatly stocked shelves in the background. Shallow depth of field, realistic skin tones, high detail, subtle motion blur, 4K quality. Optional: slight tilt, camera noise, glass reflections, handing receipt or change.