GPT Image 2 prompts

Image 1 is a photograph of a transparent mannequin titled 'Outfit Reference', featuring a Front Shot and a Back Shot side by side. Image 2 is a reference image for the outfit design. Please handle images of any style, such as live-action, illustrations, anime, CG, or sketches. You are to act as a professional clothing analyst, apparel pattern maker, and product photographer. [Objective] Accurately interpret only the outfit of the person shown or depicted in Image 2, reconstruct it as a high-quality, real-world garment, and generate a product reference image placed on the transparent mannequin from Image 1. Target the complete coordination, including clothing, shoes, legwear, hats, belts, and accessories. However, completely ignore bags and luggage. [Absolute Prohibitions] - Do not reflect the face, hairstyle, skin tone, body shape, makeup, expression, or pose of the person in Image 2 in the output. - Do not replace the mannequin with human skin or a human body. - Do not lose the texture of the transparent mannequin. - Do not make the outfit look anime-style, CG-style, cosplay-like, or like cheap plastic. - Avoid flat coloring, overly uniform surfaces, and artificial-looking gloss. [Composition] Maintain exactly the same layout as Image 1. - Left half: Front Shot. - Right half: Back Shot. - Reproduce the text labels 'Outfit Reference', '▼Front Shot', and '▼Back Shot' at the top of the image. - The background must be the same solid green back background as Image 1. - Maintain the mannequin's pose, transparency, proportions, joint positions, and standing position. - Fit the outfit naturally to the mannequin's body shape so that the 3D volume of the bust and the slenderness of the waist are clearly identifiable even when the clothes are worn. [Clothing Analysis] Read all of the following elements from Image 2: 1. Item composition: Tops, bottoms, dresses, rompers, outerwear, innerwear, etc. 2. Silhouette: Tight, regular, oversized, A-line, bodycon, flare, etc. 3. Neckline: V-neck, crew neck, square neck, halter, off-the-shoulder, open collar, etc. 4. Sleeves: Sleeveless, short sleeves, long sleeves, puff sleeves, bell sleeves, sheer sleeves, etc. 5. Front closure: Buttons, zippers, hooks, lace-up, wrap, pullover, etc. 6. Pockets: Position, shape, number, flap, patch, slash, cargo, etc. 7. Waist: Belts, corsets, elastic, drawstrings, waist seams, darts, etc. 8. Hem: Length, curve, slits, ruffles, ribbing, raw edges, pleats, etc. 9. Decoration: Embroidery, prints, lace, studs, eyelets, chains, ribbons, ruffles, patches, etc. 10. Shoes: Type, height, material, heel, sole, buckles, laces, metal fittings, etc. 11. Legwear: Socks, tights, stockings, garters, fishnets, etc. 12. Accessories: Hats, chokers, necklaces, bracelets, belts, gloves, etc. 13. Color and color scheme: Main color, accent colors, patterns, gradients, metallic colors, etc. [Backside Completion] If the back is not shown in Image 2, complete it naturally based on the front structure and general garment design. Design the collar, shoulder lines, sleeve attachments, side seams, waist seams, hem lines, zipper positions, back pockets, and back darts without contradiction. [Conversion to Real Materials] Even if Image 2 is in an illustration or anime style, replace that design with materials that would work as real-world garments. While remaining faithful to the colors of the original image, adjust the saturation, brightness, and texture to look natural as real fabric. Estimate the best material from the appearance and describe realistic surface textures such as: - Cotton: Fine plain weave, slight fuzziness, matte diffuse reflection. - Cotton Twill: Diagonal weave, natural stiffness with some thickness. - Denim: Indigo color variations, white warp threads, stiff fold wrinkles, 3D stitch effect. - Satin: Smooth, liquid-like gloss, directional highlights. - Silk: Soft flowing luster, thin and supple drape. - Polyester: Light semi-gloss, fine fiber feel that is not too uniform. - Leather: Natural grain, thickness, swelling around seams, elegant semi-gloss. - Enamel: Strong specular reflection, sharp highlights, hard surface. - Chiffon: Sheerness, airy lightness, density in overlapping areas. - Organza: Stiff transparency, hard reflections. - Lace: 3D thread feel, openwork patterns, fine irregularities on the edges. - Knit: Stitches, ribbing, tension from stretching, soft shadows. - Wool: Napped feel, matte surface, thick drape. - Mesh: Regularity of holes, shadows in overlapping parts, tension of elastic material. [Sewing and Details] To make the outfit look like a genuine high-end apparel product, carefully depict the following: - Topstitching, double stitching, edging stitches. - Sewing thread in buttonholes. - Metallic feel of zipper teeth, sliders, and pulls. - Weight and reflection of eyelets, buckles, studs, and chains. - Darts, princess lines, side seams, shoulder lines, and seam lines. - Hem folds, seam allowances, and slight visibility of the lining. - Edge finishing of lace and ruffles. - Shoe soles, heels, stitching, leather grain, and metal hardware texture. [Wear Wrinkles and Fit] Add natural wrinkles and tension for each material according to the mannequin's body shape. - Soft materials: Fine, shallow wrinkles, smooth drapes along the body. - Hard materials: Large fold wrinkles, structural stiffness. - Thick materials: Weight falling downward due to gravity, thickness around seams. - Thin materials: Light floating feel, sheerness in overlaps, delicate swaying. Locations for wrinkles: Underarms, around the bust, waist narrowing, back of elbows, pocket openings, crotch, back of knees, hem, shoe openings. [Bust and Waist Fit Expression] The outfit should naturally fit the 3D shape of the transparent mannequin's unique body type. - The size of the bust must be clearly visible through the clothes. - Include natural tension lines in horizontal and diagonal directions near the apex of the bust. - Express the 3D form through darts, princess lines, elasticity, and seam tension. - In the case of button-front closures, suggest light tension between buttons around the bust area. - Naturally express the line that narrows sharply from under the bust to the slim waist. - Ensure the presence of the bust is recognizable from the tension of the fabric on the sides and the side lines even in back shots. - However, do not make the clothes look torn, poorly sized, or extremely unnatural. [Lighting and Shooting Quality] The output should be a high-quality photograph, like a lookbook or product shoot for a real apparel brand. - Natural shadows from studio lighting. - Appropriate shadows in wrinkle valleys, back of collars, under pockets, and deep in pleats. - Matte materials have subtle diffuse reflection. - Glossy materials have clear highlights according to the material. - Semi-glossy materials have soft reflections. - Metal parts have small, sharp reflections. - The boundary between the transparent mannequin and the outfit should look natural. - Detailed density that can withstand close-ups. [Final Quality] The final image should be a reconstruction of the outfit design from Image 2 as a high-quality, real-world garment. It should have the material, sewing, weight, gloss, wrinkles, and fit as if produced by a real brand, rather than a cheap cosplay costume.

Subject:
Profile dissolving into greenery

Main Subject:
A vertical 4:5 photograph. A {argument name="age and gender" default="20-year-old woman"} is positioned largely in the center-right of the frame. The upper body to below the knees occupies most of the screen, with shoji screens and wooden frames on the left, and a wooden handrail stretching into the distance on the right. The background is a deep green garden, heavily blurred.

Character and Expression:
A natural and realistic woman. Clear skin, {argument name="hairstyle" default="short dark brown bob"}, with soft bangs falling around the face. Elegant Japanese-style natural makeup with light pink-beige lips, subtle blush, and clear eyes. The face is turned toward the left, a quiet profile looking into the distance. The mouth is not closed too tightly, showing a calm and lingering expression.

Clothing and Pose:
An {argument name="outfit" default="elegant white chiffon camisole dress"}. Drapes of thin overlapping fabric flow diagonally from the chest to the waist, not too transparent, catching light softly. The right hand rests lightly on the wooden handrail on the right, fingers naturally extended. The left hand lightly pinches the fabric in front of the waist, creating fine wrinkles and layers in the drape. Weight is shifted toward the right side of the screen, with a slight twist in the shoulders and waist. While maintaining the original atmosphere, the pose is changed slightly and naturally.

Background and Light:
An engawa (veranda) of a Japanese house. Shoji doors and dark wooden frames on the left, eaves shadows above, and the greenery of a well-kept garden in the back right. A building with a small tiled roof is visible dimly in the distance. The background is treated with large bokeh and soft green gradients. Slightly warm morning natural light shines from the top right, adding faint highlights to the shoulders, cheeks, hair contours, and the edges of the white fabric. The interior side is slightly darker, with soft reflected light from the garden hitting the skin.

Composition and Camera:
A vertical portrait taken with a professional camera. 85mm lens, shallow depth of field around F1.8. Focus is on the face and upper body, with the background garden, tiled roof, and the depth of the handrail beautifully blurred. The camera is roughly at eye level from chest height. Depth is created by the shoji on the left and the handrail on the right, with the profile and diagonal drapes leading the eye.

Texture and Style:
Realistic photographic expression. Skin is not overly processed, leaving natural texture and soft highlights. White chiffon carefully expresses overlapping thin layers, light transmission, and fine wrinkles. Wood is a calm brown, conveying the atmosphere of the veranda. Tones are centered on green and white, low contrast and soft, with an elegant and quiet finish like a magazine photo.

Negative:
Underage-looking person, excessive exposure, nudity, lingerie impression, sexual emphasis, unnatural face, unnatural gaze, extra fingers, missing fingers, fused limbs, broken joints, poor contact between cloth and body, unnatural gravity, incorrect perspective, shadows inconsistent with light source, garbled background text, logos, watermarks, excessive skin correction, plastic-like skin.

"Convert the {argument name="people" default="baby siblings"} in the photo into Japanese miniature figures ({argument name="figure style" default="Nendoroid style"}, SD ratio). - Cute chibi proportions with large heads and small bodies - Smooth PVC/vinyl texture with subtle gloss - Large eyes and soft, lovely expressions, maintaining original facial features and hairstyle - Standing on a transparent acrylic base - Product photo composition with a figure box package placed next to it - Studio lighting, soft shadows, shallow depth of field - Simple white or light gradient background - Realistic textures and details like an actual figure photo"

Realistic vertical fashion portrait, warm vintage {argument name="location" default="mansion"} interior. Adult East Asian female, over {argument name="age" default="21 years old"}, standing barefoot on a polished dark wood floor next to an exquisite wooden staircase handrail. Slightly to the right, full-body shot from feet to head, elegant three-quarter pose towards the camera. Soft, confident, relaxed expression - gentle direct gaze, natural eyeliner, glowing skin, light peach blush, subtle rose pink lip color.

Character: Extremely long dark brown wavy hair, soft volume, falling over one shoulder and extending to the back. One hand lightly raised touching the hair on the side of the head; the other hand near the waist - elegant fashion pose. Dignified, slightly curved posture - one leg relaxed, the other slightly bent.

Clothing: Stylish {argument name="clothing color" default="black"} sleeveless cropped top - high neckline with a small keyhole cutout near the collar. Loose black wide-leg harem pants. Featured gold chain belt at the waist - layered hanging coins, circular links, central designer-style badge pendant - luxury bohemian embellishment. Gold bracelet and delicate dangling earrings. Refined, modern, slightly exotic - emphasizing the drape of black fabric, gold jewelry details, and elegant silhouette.

Scene: Luxurious old-world interior - dark carved wood wall panels, polished wooden staircase handrail with circular pillars, rich burgundy velvet curtains next to tall narrow windows, warm light halo in the background, overall dark brown wood texture. Camera slightly tilted - cinematic diagonal composition - dark wooden door frame softly framing the edges of the image.

Lighting: Warm, moody, cinematic - soft daylight from tall windows behind, warm indoor lighting adding golden highlights. Soft rim light on hair, shoulders, arms, waist, chain belt, and polished handrail. Shallow depth of field, delicate shadows, realistic skin texture, clear fabric folds, fine wood grain, exquisite luxury photography quality.

Style: Hyper-realistic vintage mansion fashion photography, adult model, black cropped top, loose black trousers, gold chain belt, barefoot elegant pose, dark carved wood interior, burgundy curtains, warm cinematic lighting, old-world luxury atmosphere, high detail, vertical aspect ratio. No text, no watermark, no logo, no extra people, no deformed bodies, no cartoonish feel, no strong flash, no cluttered elements, no explicit nudity.

Subject:
{argument name="subject" default="Silence on the white line"}

Main Subject:
A realistic 2:3 vertical photo. In a quiet street corner crosswalk, an adult woman takes a low runner's start-like pose, positioned largely in the center-right of the frame. Her upper body and face are the focus of the top half, while her hands, knees, and sneakers extend downward to create depth.

Person/Expression:
A natural, realistic, mature woman. Clear, bright skin with a subtle glow and natural flush. Dark brown hair in a high ponytail, with thin bangs and wisps around the face catching the light. Elegant Japanese-style makeup: pale pink-beige blush, thin eyeliner, long lashes, natural undereye bags, and moist pink-beige lips. She faces right, looking slightly ahead with a {argument name="expression" default="concentrated expression and slightly parted lips"}.

Clothing/Pose:
{argument name="clothing" default="white camisole with a small floral pattern"} and matching shorts. A sheer white lightweight shirt is draped loosely over it, slipping slightly off the shoulders. Her physique is that of a healthy, mature adult with natural contours. Right knee forward, left knee near the ground, fingertips spread near the crosswalk line. White sneakers positioned slightly back, with weight centered on her arms in a forward-leaning posture. Sleeves and hem gather softly with the pose.

Background/Lighting:
Background is a quiet urban alley with old shops and low buildings. A wooden-style storefront on the right, trees and road signs on the left, and distant pedestrian silhouettes. Sign text is blurred and unreadable. Clear morning light from the upper left creates highlights on her hair, cheeks, shoulders, and arms. Crosswalk lines and building shadows intersect on the ground, with the background softly separated by bright green and gray bokeh.

Composition/Camera:
Low-angle, close-range shot. Shallow depth of field equivalent to 85mm, focusing on the face, upper body, and hands. Arms spread toward the bottom corners, with the white line leading the eye to the face. Leaves space at the top for the cityscape and dappled sunlight, with a heavy background blur. A close-up portrait composition where the subject stays within the frame.

Texture/Style:
A realistic Japanese portrait as if taken with a professional camera. Skin is not overly processed, retaining natural pores and soft highlights. The sheer white shirt has a translucent fibrous texture, the camisole feels like smooth cloth, and the ground shows fine asphalt particles. Bright, clean tones, shallow bokeh, natural backlit-style rim lighting, and a magazine-quality finish.

Negative:
Unnatural face, unnatural gaze, extra fingers, missing fingers, fused limbs, broken joints, poor contact with objects, floating, unnatural gravity, incorrect perspective, shadows inconsistent with light source, gibberish text, readable logos, watermarks, overexposure, excessive skin smoothing, plastic-like skin.

{argument name="art style" default="QT Big Head Art"} {argument name="subject" default="Princess Face"}

上传一张人像作为人物参考，将参考人物自然替换进原图场景。保留原图的构图、机位、动作、姿势、表情、神态、眼神、手势和光影关系，人物面部特征与参考图高度一致，五官自然，不僵硬、不别扭。

Goal: Create a premium 16:9 commercial advertising collage using the visual system “Reverse The Damage,” showing four different product ads where damage is visibly rewinding away from the hero product.

Canvas: Horizontal 16:9 image divided into exactly 4 equal panels in a 2-by-2 grid, separated by thick clean white gutters. Use cinematic studio lighting, high contrast, photorealistic product rendering, glossy reflections, shallow depth of field, and dramatic motion trails. Each product must remain perfectly still, large, sharply focused, centered or near-centered, instantly recognizable, and treated as the hero.

Overall concept: In every panel, the damaged material or debris is pulled backward and away from the product as if time is reversing. Use sweeping white airflow ribbons, streaks, particle trails, and directional motion blur to make the reversal obvious. The products are clean, untouched, and premium; the damage appears to be leaving the scene rather than arriving.

Panel count and contents: Use exactly 4 panels.
1. Top-left panel: {argument name="laundry detergent product" default="an orange Tide Ultra Oxi laundry detergent bottle with blue cap"} standing upright on a reflective dark surface in front of white fabric. Brown mud stains and dirt particles are being pulled backward off a white shirt on the left, transforming into clean bright fabric flowing to the right behind the bottle. Dark studio background, crisp product label, strong white motion streaks.
2. Top-right panel: {argument name="vacuum product" default="a Dyson cordless stick vacuum with purple and metallic accents"} standing upright on a wooden floor in a modern dim living room. A wave of dust, soil, pebbles, and debris is flying backward from left to right into a clean swept path behind the vacuum, with curved white air trails. Background includes a blurred plant and small furniture on the right.
3. Bottom-left panel: {argument name="haircare product" default="a black and gold Kérastase Chronologiste hair oil bottle"} centered on a dark glossy surface. Broken dry split hair fibers and brown splinter-like damage burst from the left, then reconnect into a smooth glossy flowing hair strand sweeping to the right behind the bottle. Black luxury background, gold highlights, elegant salon-beauty mood.
4. Bottom-right panel: {argument name="skincare product" default="a white CeraVe Moisturizing Cream jar with blue label"} sitting on a clean light surface. Dry cracked earth, flakes, and dusty skin-like texture on the left are being pulled backward and replaced by smooth silky white hydrated skin-like waves on the right. Soft beige background, bright clinical skincare lighting, clean medical beauty aesthetic.

Visual style: Premium commercial advertising, photorealistic, ultra-detailed product photography, cinematic rim light, volumetric glow, dynamic particles, sharp hero packaging, high-end retouching, no human models, no extra text overlays beyond product labels visible on packaging.

Constraints: Keep exactly four panels and exactly the four hero products described. Do not add captions, slogans, watermarks, logos outside the product packaging, hands, people, or extra panels. Make the reversal motion clear in each panel: damage on the left, clean restored material flowing on the right, with the hero product fixed and pristine in the center.

Create a luxury perfume advertisement poster for {argument name="brand name" default="ELYSIAN NOIR"}, featuring one single perfume bottle as the main subject. Use a vertical 3:4 canvas with the product centered slightly below the middle. The background should be a deep charcoal-to-black soft gradient with a subtle silk-like fabric texture and faint metallic sheen. Leave generous negative space at the top for refined typography. Place the headline “{argument name="headline text" default="ELYSIAN NOIR"}” in widely spaced elegant uppercase letters, warm champagne-gold color, with a modern sans-serif luxury typeface. Under it, add the small tagline “{argument name="tagline" default="A SCENT OF TIMELESS CRAFTSMANSHIP"}”, then a tiny centered divider line, then the product text “PARFUM” and “100 ML / 3.4 FL.OZ”. Show exactly 1 perfume bottle: a faceted geometric glass bottle with a smoky amber-black transparent body, crisp beveled edges, glossy reflections, a black rectangular cap with gold accents, and the front label reading “ELYSIAN / NOIR / PARFUM” in small gold lettering. Lighting should be cinematic commercial studio photography: low-key, high contrast, warm gold rim lights, sharp highlights along the glass edges, realistic reflections on a polished dark surface, and soft streaks of light sweeping across the lower foreground. Overall color palette is muted black, smoky amber, and champagne gold. Make the composition clean, premium, minimalist, elegant, and suitable for an international luxury fragrance campaign, with ultra-detailed glass, realistic refraction, no people, no extra products, no watermark, no UI elements.

Create a warm, premium studio photoshoot for a baby girl’s first birthday with a soft “Teddy Bear Picnic” theme. A smiling baby girl with curly dark hair sits cross-legged in the center on a round woven jute rug layered with a cream macrame throw, wearing a cream floral ruffle romper and a beige bow headband, hugging a plush brown teddy bear with a pale pink ribbon. The scene is styled in blush pink, cream, tan, rose gold, and warm golden tones with shallow depth of field and cozy fairy-light bokeh. Behind her, build a lush balloon arch with exactly 4 main balloon color/types: blush pink, ivory cream, peach, and metallic rose-gold/gold balloons. Add burlap pennant banners in the background with visible text reading “TEDDY BEAR PICNIC” on the top banner and “HAPPY 1ST BIRTHDAY, {argument name="child name" default="FLORENCE"}” on the lower banner, decorated with eucalyptus garlands and warm string lights. On the left, place a two-tier ivory drip cake on a dark wooden cake stand, topped with a script “One” topper, a small teddy bear topper, pink roses, daisies, greenery, and delicate cream frosting drips. Include exactly 3 visible teddy bears: the teddy bear held by the baby, a large partial teddy bear peeking in from the far left background, and a small seated teddy bear at the lower left foreground. On the right, place a large metallic rose-gold number “1” balloon and an open blush-pink vintage picnic suitcase containing a floral teapot, teacups, and small picnic tea-party items. In the foreground, arrange wooden alphabet blocks spelling exactly 2 phrases: “ONE” on the left and “FLORENCE” on the right. Keep the composition symmetrical and luxurious, with the baby as the sharp focal point, creamy skin tones, realistic photography, soft studio lighting, detailed textures in the woven rug and macrame, and no extra text, logos, or watermarks.

Create a dreamy editorial fashion portrait of a young East Asian woman posing in an ornate vintage bedroom mirror scene, with a soft romantic magazine-cover aesthetic. The subject is {argument name="character description" default="a delicate young East Asian woman with long wavy dark brown hair, fair skin, large expressive eyes, and natural glossy makeup"}, standing slightly off center in front of a carved wooden mirror, one arm raised overhead holding a strand of pearls or the mirror frame and the other bent gracefully near her shoulder. She wears {argument name="outfit" default="an ivory cream corset-style dress with tiny front buttons, textured lace fabric, layered ruffled skirt, and multiple pearl necklaces"}. Show her reflection behind her in the mirror, including her back and raised arm, creating a doubled intimate composition. Surround her with warm beige curtains, peach lace fabric, hanging pearl strands, carved wood, a soft bouquet of pale pink lilies near the lower left, and blurred foreground drapery framing the image like a hazy vignette. Use warm golden window light, creamy highlights, shallow depth of field, soft bloom, film grain, and subtle lens flare. Add oversized translucent prismatic serif typography across the image: at the top, large cropped letters reading {argument name="top title text" default="AUTUMN ECHO"}; near the lower left, small italic text reading {argument name="small caption text" default="dream in static"}; at the bottom, huge iridescent serif letters reading {argument name="bottom title text" default="AFTERGLOW"}. Include exactly 3 visible text elements: the large cropped top title, the small italic caption, and the large bottom title. The typography should look like glossy white holographic magazine text with rainbow chromatic aberration, partially transparent and integrated into the light leaks. Vertical 4:5 composition, ultra-detailed photorealistic fashion photography, ethereal nostalgic mood, no extra logos or readable body copy beyond the specified text.

Create a modern comic-style close-up portrait of a glamorous young woman with {argument name="hair color" default="black"} shoulder-length wavy hair, warm fair skin, glossy full lips, subtle winged eyeliner, and a calm confident gaze looking slightly toward the viewer. She is posed in a three-quarter view with one bare shoulder visible and one elegant hand resting under her chin, long manicured nails visible. Cover her face, neck, shoulder, arm, and hand with vivid projected light patterns: concentric contour-like rainbow ripples in neon cyan, magenta, purple, orange, green, and pale yellow, as if a psychedelic moiré or oil-slick topographic projection is cast across her skin and hair. Use the same swirling luminous pattern as the entire background, dense and high-contrast, with many organic oval rings and warped bands flowing diagonally around her silhouette. Style should be a polished modern manga / semi-realistic comic illustration with sharp ink-like linework, painterly shading, high detail in eyes, lips, hair strands, and hands, dramatic saturated lighting, deep shadows, glossy highlights, and a square canvas. No text, no watermark, no border, no extra characters.

Goal: Create a minimalist corporate recruitment poster for a convenience store partner hiring campaign, using a bold East Asian typographic aesthetic.

Canvas: Vertical poster, 2:3 aspect ratio, warm off-white paper background with lots of negative space on the right.

Layout: Fill the left 75% of the poster with enormous cropped dark-blue Chinese characters, reading like a giant recruitment headline {argument name="main headline" default="招聘"}; the characters are so large that their strokes extend beyond the poster edges. Place a narrow right-side information column centered vertically, aligned near the right margin. Add a small convenience-store line icon and English slogan at the lower right.

Visual style: Rough risograph / screen-print texture, dark navy blue ink on cream paper, gritty distressed edges, speckled ink loss, slightly uneven stamped typography. Use a calm corporate poster composition, modern but tactile, no photos, no gradients, no extra colors.

Text content: The poster contains exactly 1 giant cropped headline area, 1 vertical title line, 7 small information sections, and 1 bottom logo/slogan block. The vertical title line should read {argument name="vertical title" default="便利店伙伴招募中"}. The 7 small sections in the right column are: 1) position: store staff, full-time or part-time; 2) work content: cashier operation, product display, store cleaning; 3) schedule: shift system, 3–5 days per week, 4–8 hours per day; 4) benefits: hourly wage 18–25 yuan, employee discount, holiday benefits; 5) requirements: age 18 or above, responsible, hardworking; 6) location: assigned nearby; 7) contact: scan the QR code below or visit the store to ask. Keep this body text very small, compact, and navy blue.

Bottom block: Draw exactly 1 simple outlined convenience-store icon with an awning marked “24”, and below it place two short English lines: {argument name="english slogan line one" default="WE NEED YOU"} and {argument name="english slogan line two" default="JOIN US"}.

Constraints: Preserve the extreme scale contrast between the huge cropped blue headline and the tiny right-column details. Keep all typography and illustration in the same navy ink. Avoid realistic people, photos, decorative icons beyond the single store icon, QR code detail, shadows, or glossy effects.

Goal: Create a clean 16:9 Japanese business/technical infographic slide about how continuous reasoning context and explicit prompt caching improve long-running task efficiency. Use a polished PowerPoint-native infographic look with dense but readable explanatory text.

Canvas: 16:9 landscape slide, warm off-white background, dark navy text, teal and olive green accent colors, thin rounded borders, subtle shadows, generous margins. Leave no photo-realistic elements; use flat vector icons and crisp typography.

Top text area: Place a large bold Japanese headline at the top left: {argument name="headline text" default="継続推論と明示的キャッシュが長期タスクを効率化"}. Under it, add a smaller semibold lead sentence: {argument name="lead text" default="過去ターンの推論と再利用可能なプロンプトを選択的に保持することで一貫性と効率を高められるが、前提変更や利用回数を踏まえて保存範囲を設計する必要がある。"}

Main layout: Two large rounded rectangular panels sit side by side beneath the lead sentence. The left panel is teal and titled “reasoning.context”; the right panel is olive green and titled “明示的プロンプトキャッシュ”. Connect the panels with a thin line and a small circular chain-link icon centered between them near the bottom, suggesting coordination between reasoning context and cache. A small upward green arrow near the right panel points back toward it.

Left panel details: Include exactly 3 vertically stacked turn markers on the far left, connected by a vertical line with a downward arrow. The markers are labeled “1ターン”, “2ターン”, and “3ターン”. Next to each marker, show a small person icon and speech bubble. To the right, include exactly 3 horizontal rounded cards with teal icon blocks and Japanese explanatory text: 1) gear icon, “auto｜モデルの既定動作を利用”; 2) checklist icon, “all_turns｜安定した目標、前提、優先順位を複数ターンで再利用”; 3) clock icon, “current_turn｜以前の推論が不要になった場面で現在ターンに限定”.

Right panel details: Include exactly 3 horizontal rounded cards with olive icon blocks and Japanese explanatory text: 1) document icon, “再利用する共通プレフィックスを開発者が指定”; 2) database cylinder icon, “キャッシュ書き込みは通常入力単価の1.25倍”; 3) percent tag icon, “読み出しは割引されるため、反復利用の回数が効果を左右する”.

Bottom conclusion band: Across the bottom, create one wide rounded rectangle callout with a thin yellow border. On the left of the band place a gold target icon with an arrow. To the right, place a bold Japanese conclusion: {argument name="conclusion text" default="長期タスクの一貫性と効率を高める一方、前提変更時には過去の推論や不要なキャッシュを切り離す設計が必要"}.

Visual style: Japanese corporate slide design, crisp vector line icons, rounded rectangles, light cream background, teal left section, olive right section, yellow conclusion accent, strong hierarchy, highly legible Japanese sans-serif typography, no decorative clutter.

Constraints: Preserve the exact count of elements: 2 main panels, 3 left turn markers, 3 left option cards, 3 right cache cards, 1 central chain-link connector, 1 bottom conclusion callout, and 1 target icon. Do not add extra panels, extra cards, watermarks, logos, or decorative characters. Keep all slide text inside the infographic sharp and readable.

Goal: Create a dark technical debug visualization of a pachinko machine playfield layout, showing ball lanes, collision rails, pegs, named gameplay regions, and simulated ball trajectories.

Canvas: Square-ish 4:5 technical diagram on a nearly black burgundy background, with a transparent-engineering-overlay feel. Use a dark maroon grid of blocky rectangular obstacle silhouettes behind the layout.

Main layout: Draw a large pachinko board occupying almost the full canvas. The board is formed by thick angular golden-brown rails: one large outer oval/octagonal loop around the perimeter, one large inner polygonal ring around an empty central dark void, and several short rail segments near the bottom and lower-right. Keep the rails chunky, beveled, and slightly translucent, like debug collision geometry.

Trajectory paths: Add exactly 5 thin neon ball-path traces over the rails and lanes: 1 cyan path hugging the far-left launch lane, 1 hot pink path weaving near the left edge and bottom exit, 1 lime green path that curves from the upper-left across the mid-left and down to the bottom, 1 red path that crosses sharply through the left-middle and upper-left, and 1 yellow path following the outer left arc. The paths should overlap and look like simulated pachinko ball travel, with sharp turns and curved segments.

Debug regions: Draw dashed cyan rectangular region boxes with small cyan labels. Include exactly 7 labeled regions: "region:JACKPOT_1" at left-middle, "region:STATIC" near the lower-left/middle, "region:START" centered lower-middle, "region:LUCKY" right-lower-middle, "region:LAUNCHER" bottom-right, "region:OUT" lower-left exit area, and one tall dashed launch/channel region along the left side.

Pegs and labels: Add exactly 15 small green square peg markers with green debug labels. Place them around the central playfield: 2 near the upper-left labeled "peg-left-top-1" and "peg-left-top-2"; 3 near the top center labeled "peg-center-top-1", "peg-center-top-2", and "peg-1"; 3 on the upper-right labeled "peg-right-top-1", "peg-right-top-2", and "peg-right-path-2"; 3 on the lower-right/lower-middle labeled "peg-right-path-1", "peg-lucky-guide", and "peg-right-pocket-1"; 4 in the lower-left/lower-middle labeled "peg-left-path-1", "peg-left-pocket-1", "peg-start-left", and "peg-start-right". Make labels small, thin, and green, as if from a game-engine editor overlay.

Additional details: Include one tiny cyan number box reading "19" near the left-middle jackpot area. Add a few small red guide triangles and line fragments near the top-left lane. The diagram should look like a GPT-generated game-layout review screenshot rather than polished UI art.

Visual style: Low-light debug render, dark maroon and black palette, golden collision rails, cyan dashed UI overlays, green peg annotations, neon trajectory lines. No photorealism, no characters, no real pachinko machine cabinet, no decorative anime art.

Customizable concept: Build the layout as a {argument name="machine type" default="pachinko"} physics debug map titled by implication around {argument name="gameplay focus" default="ball trajectory and lane review"}. Use rail color {argument name="rail color" default="muted golden brown"}, background color {argument name="background color" default="near-black burgundy"}, and trajectory colors {argument name="trajectory colors" default="cyan, hot pink, lime green, red, yellow"}.

Goal: Create a polished vertical Japanese trading-card-game strategy infographic explaining the pros and cons of adding a specific card to a deck.

Canvas: Portrait 2:3 layout, dark navy-black fantasy UI background with thin gold ornamental borders, beveled panels, subtle glow, and a premium card-game analysis aesthetic. Use gold title typography and white Japanese body text.

Main title area: At top right, place a large ornate gold headline reading {argument name="headline text" default="道化の一座 ハット"}. Beneath it, add the subtitle {argument name="subtitle text" default="デッキに加えた際のメリット・デメリット"}. Under the subtitle, place a dark framed explanation box containing 3 short Japanese lines describing that the card can search/deploy Pendulum monsters, also enables non-theme monsters, supports interruption-resistant subroutes, and improves combo stability.

Card display: At top left, show exactly 1 realistic Yu-Gi-Oh-style monster card mockup, named {argument name="card name" default="道化の一座 ハット"}. The card should have an orange monster-card frame, star icons, a small LIGHT attribute icon, dense Japanese effect text, ATK/DEF line, and fantasy artwork of a jester-like rogue in blue clothing holding a staff amid swirling golden magic. Do not use official logos or exact copyrighted card layout details; make it a close fictional TCG-style homage.

Middle comparison section: Add a centered gold label tab reading “Trigger resilience comparison”. Create exactly 2 horizontal comparison rows under it, each split into a left original-deck behavior column, a middle after-adoption result column, and a right small change-image column. Row 1 is draw-type trigger: blue icon, left box has a large blue circle meaning good resilience; arrow points right to a red X meaning resilience becomes worse; right mini diagram shows a blue person icon leading to a card/box and a prohibition symbol, implying the combo stops at the draw stage. Row 2 is interruption-type trigger: red/orange icon, left box has a large red X meaning poor resilience; arrow points right to a blue circle meaning resilience improves; right mini diagram shows a red person icon leading to a card/box and a blue shield check, implying interruption is avoided and deployment continues.

Lower benefits and drawbacks: Create exactly 6 rectangular cards in two columns, 3 benefits on the left and 3 drawbacks on the right. Left column header: “メリット” in a blue panel. Right column header: “デメリット” in a red panel. Benefit card 1 uses a shield icon and says it becomes stronger against interruption-type triggers. Benefit card 2 uses a branching route icon and says the number of deployment subroutes increases. Benefit card 3 uses a checkmark icon and says combo stability improves. Drawback card 1 uses stacked card icons and says it becomes weaker against draw-type triggers. Drawback card 2 uses a weight/bag icon and says deck burden becomes larger. Drawback card 3 uses a warning triangle icon and says unnecessary cards may need to be adopted. Each of the 6 cards must include a bold colored heading plus two smaller Japanese explanatory lines.

Bottom summary: Add a wide dark framed box with a small gold tab header reading “まとめ”. Inside, write a concise Japanese summary explaining the trade-off: resistance to interruption and flexible deployment improve, but weakness to draw-type triggers and deck-building constraints increase. End with a larger gold call-to-action line reading {argument name="closing line" default="環境や構築方針に応じて、採用を検討しよう！"}.

Style constraints: Use crisp vector-like UI panels mixed with realistic card art, high contrast, clean alignment, thin gold borders, blue for positive elements, red for negative elements, arrows between comparison boxes, no watermark, no extra sections, and keep all text legible as an infographic.

Create a vertical full-body anime concept-art illustration of exactly one young male character, {argument name="character name" default="a stern teenage soldier"}, standing front-facing with a slight relaxed slouch on an off-white blank studio background. Preserve a serious, unimpressed expression, short light-blond curly hair mostly covered by a fluffy beige ushanka-style winter hat, pale skin, slim youthful proportions, and large black over-ear tactical headphones. Redesign only the outfit as a modern military field uniform: green-and-brown woodland camouflage jacket and loose cargo pants tucked into black lace-up combat boots, a tan tactical plate carrier with many pouches across the chest and abdomen, tan shoulder straps, a side satchel or backpack visible behind the right arm, a green scarf or neck wrap, and a red-and-yellow sleeve patch on the upper right arm. Add one long black radio antenna rising vertically behind the shoulder and one black assault rifle hanging downward at the character’s left side, held loosely by a strap; do not show the weapon aimed or in use. Include exactly one outfit and exactly one character, no lineup, no collage, no alternate versions. On the left side of the image, add a small block of Japanese-style annotation text with a bold heading and four short lines beneath it, partially cropped and slightly nonsensical, like a character design sheet note. Use expressive sketchy ink outlines, muted watercolor/marker coloring, visible rough construction strokes, subtle shadows under the boots, and a clean manga character-design-sheet aesthetic. The outfit color theme is {argument name="camouflage palette" default="olive green, dark forest green, tan, and brown"}; the sleeve patch should feature {argument name="patch colors" default="red and yellow"}.

Create a clean high-resolution anime illustration of a teenage girl standing outdoors under a vivid summer sky, viewed from a low angle behind her as she turns her head over her shoulder to look at the viewer. She has {argument name="hair color" default="dark brown"} hair in a high side ponytail tied with a {argument name="hair ribbon color" default="navy blue"} ribbon, long loose bangs, large soft purple-brown eyes, a small neutral mouth, and lightly blushing cheeks. She wears an oversized plain {argument name="shirt color" default="white"} short-sleeve T-shirt that drapes loosely over her body and reaches past the hips, with subtle folds and shaded fabric, plus short dark athletic shorts visible underneath. Her posture is casual and slightly shy, one hand tucked near the shirt hem or pocket area, shoulders turned away while her face looks back. Use a bright blue sky background with scattered fluffy white cumulus clouds, strong daylight, crisp cel-shaded anime rendering, soft gradients, delicate line art, and a wholesome slice-of-life mood. Composition: square 1:1 canvas, character centered and occupying most of the frame, low camera angle emphasizing sky, no text, no watermark, no extra characters.

Goal: Create a bright anime-style commemorative social media poster for {argument name="event name" default="Nice Day"}, featuring a cheerful schoolgirl encouraging the viewer to find nice things and make memories.

Canvas: Vertical 3:4 illustration, highly polished Japanese anime key visual, vivid summer colors, sparkling highlights, soft lens flare, sunny blue sky with fluffy clouds over a seaside promenade.

Main subject: One cute teenage anime girl in the foreground, waist-up, leaning toward the viewer with energetic perspective. She has long flowing navy-blue hair with turquoise-blue tips, large turquoise eyes, rosy cheeks, and an open happy smile. She wears a navy sailor school uniform with a white collar, red neck ribbon, gold buttons, and a small star-and-blue-gem hair accessory on the right side of her bangs. Her left hand points directly at the viewer in extreme foreground, and her right hand holds a small spiral notebook.

Layout: Put large playful Japanese headline lettering in the upper left with bubbly white-and-blue typography, orange date text, hearts, stars, and doodles. Place the girl centered-right, overlapping the title. Add a speech bubble on the left near her pointing hand. Add a wooden signboard on the upper right. Add a checklist notebook in her right hand on the mid-right. Add a livestream-style overlay and caption at the bottom, plus a small photo-collage panel in the bottom-right corner.

Text content: Use Japanese text as visible graphic elements. Large top text: {argument name="date text" default="7月13日"} and {argument name="headline text" default="ナイスの日！"}. Two ribbon subtitles below it: 「素敵なことを探そう♪」 and 「いい思い出を作る日」. Speech bubble text: 「ナイス〜！ 今日も最高の 思い出つくろっ！」. Wooden signboard text: 「ナイス！って言葉は、自分も相手もハッピーになれる魔法なんだよ♪」. Notebook title: 「今日のナイス探し！」. Notebook checklist contains exactly 6 checked items: 1) 「青空がナイス！」 2) 「アイスがナイス！」 3) 「友達の笑顔がナイス！」 4) 「ひまわりがナイス！」 5) 「きみがいるのがナイス！」 6) 「ぜーんぶ、ナイス！」. Notebook footer: 「ミナミのナイス100点満点〜！」. Bottom livestream badge: red rectangle reading 「LIVE」 beside a black viewer counter reading 「7,131」 with an eye icon. Bottom main caption: {argument name="bottom caption" default="いいこといっぱい見つけて、今日を宝物にしようね！♡"}. Bottom-right collage header should look handwritten and semi-transparent.

Discrete elements to include: exactly 1 main anime girl, 1 pointing hand in extreme foreground, 1 held spiral notebook, 1 wooden signboard, 1 speech bubble, 1 top headline cluster, 2 subtitle ribbon strips, 1 livestream badge, 1 viewer counter, 1 bottom caption, and 1 bottom-right photo collage. The photo collage contains exactly 4 visible snapshots: 1 blue cream soda drink, 1 sunflower field, 1 group selfie of three girls, and 1 handwritten message card.

Background details: Seaside boardwalk with railings, ocean horizon, bright sky, sunbeams, tropical plants, sunflowers on the left, and a clear glass drink near the lower-left edge. Use many small decorative hearts, stars, sparkles, and pastel doodle outlines, but keep them secondary to the character.

Visual style: Ultra-cute glossy anime illustration, saturated cyan and pink palette, clean line art, soft blush, transparent sticker-like text elements, lively magazine-cover composition, cheerful summer idol energy, high detail, crisp typography, no watermark, no extra characters beyond the three tiny girls only inside the collage snapshot.

Create a cinematic anime illustration of {argument name="character name" default="a tired office-worker demon girl"} relaxing in a small Japanese apartment in warm morning sunlight. She sits on a floor cushion beside a low wooden table, legs crossed, wearing a white blouse, dark cardigan, fitted black office skirt, black stockings, black heels, and a blue lanyard ID badge. She has long pale blonde hair with bangs, pointed elf-like ears, a navy ribbon bow, two large curved black horns, grey charcoal skin, one glowing red eye open while the other eye is winked shut, and huge dark bat wings spread wide behind her; include a long demon tail curling around the cushion. Her mouth is visibly grey inside as she tilts back and drinks from a silver beer can, looking tipsy and relaxed. The room is cluttered but cozy: an open window on the left with sheer curtains, blue sky and city buildings outside, a potted plant, wooden floor, TV and shelves in the background, and a wall calligraphy poster on the right with Japanese writing about drinking morning, noon, and night plus a small doodle. On the low table and floor, show exactly 7 distinct drinking/snack items: 1 open spiral notebook sign reading “weekday but morning sake!!” with a doodled face, 1 tall brown sake bottle with Japanese label, 1 lemon strong canned drink labeled “STRONG 9% lemon,” 1 beer can in her hand, 1 tray of green edamame, 1 dark can labeled like a demon-world morning drink, and 1 tall dark bottle with red demon-themed Japanese lettering. Use highly detailed modern anime rendering, soft volumetric sunlight from the left, realistic fabric and leathery wing texture, shallow depth of field, moody warm interior shadows, 16:9 horizontal composition, no watermark, no extra characters.

Create a square single-panel manga illustration with thick black comic borders and a warm cute style. Show a chibi blonde girl with straight shoulder-length hair and blunt bangs sitting at a wooden restaurant table, smiling with closed happy eyes and puffed cheeks as if chewing. She wears a dark burgundy short-sleeve shirt and holds brown chopsticks in her right hand near her mouth. On the table in front of her is exactly 1 white oval plate of gyoza dumplings topped with chopped green onions and sauce, plus exactly 1 small white dipping-sauce dish on the left filled with reddish-brown sauce. The background is a pink bubbly bokeh pattern. Add exactly 2 white speech bubbles with black outlines: the left vertical bubble says {argument name="left speech bubble text" default="さらに\nもっちもち"}, and the right vertical bubble says {argument name="right speech bubble text" default="水餃子は"}. Add exactly 2 red-orange sound-effect captions with cream outlines: one at lower left says {argument name="left sound effect" default="もちっ"}, and one at lower right says {argument name="right sound effect" default="もちっ"}. Use clean legible Japanese lettering, expressive rounded chibi proportions, rosy cheeks, simple flat shading, a cozy food-comic mood, and no extra panels or extra text.

Goal: Create a bright, polished anime café illustration featuring five magical-girl heroines from {argument name="series" default="Smile Precure!"} enjoying desserts together, in a dynamic close-up group composition with some limbs and hair slightly cropped by the frame.

Canvas: Wide horizontal 16:9 image, high-resolution anime key visual, vibrant colors, clean line art, glossy highlights, warm daylight.

Setting: Cozy modern dessert café with wooden floor and wooden chairs, round wooden table in the foreground, large sunlit windows behind the group, leafy trees visible outside, hanging pendant lamps, soft bokeh and warm ambient light.

Layout: Five characters arranged around one round table, all facing the viewer with cheerful expressions. Use exactly 5 visible magical girls: 1 green girl on the far left in the foreground, 1 blue girl left-center behind the table, 1 pink girl in the center, 1 orange girl standing right-center holding a tray, and 1 yellow girl seated far right reaching toward the camera. Keep the camera close and lively, with a wide-angle feeling and energetic overlapping poses.

Character details: The green heroine has very long voluminous green hair, green eyes, a white winged hair ornament, a green frilled magical-girl dress, white gloves, a gold chest brooch, and she winks while making a peace sign. The blue heroine has long blue hair, blue eyes, a blue-and-white outfit with winged head ornaments, and holds a teacup with both hands. The pink heroine has bright pink twin-tail hair, pink eyes, a pink frilly outfit, and rests her cheeks in her hands with an excited smile. The orange heroine has orange hair in a high bun with loose curled strands, orange eyes, an orange magical-girl dress, and holds a serving tray with a tall parfait. The yellow heroine has huge flowing blonde-yellow hair, golden eyes, a yellow frilly outfit, and extends one hand toward the viewer with a big open smile.

Table items: Include exactly 8 visible dessert and drink items on the table or tray: 1 green melon soda float in a tall glass, 1 strawberry shortcake slice, 1 chocolate cake slice with berries, 1 orange drink with straw, 1 Swiss roll cake slice with fruit garnish, 1 white teapot, 1 white teacup and saucer, and 1 tall fruit parfait on the orange character’s tray.

Visual style: Crisp Japanese TV-anime illustration, colorful magical-girl aesthetic, expressive faces, large sparkling eyes, detailed frills and bows, soft cel shading, glossy dessert rendering, warm afternoon café lighting, joyful friendship atmosphere.

Constraints: No text, no captions, no watermark, no logos. Keep all five characters clearly identifiable by their color themes and costumes. Use {argument name="art style" default="high-quality modern anime key visual"}. Make the mood {argument name="mood" default="cheerful and energetic"} with {argument name="lighting" default="warm sunlit café lighting"}.

Goal: Create a vertical cinematic fantasy light-novel cover illustration in delicate Chinese/Japanese ink-wash anime style, centered on {argument name="character name" default="the silver-haired heroine"} and a tragic xianxia atmosphere.

Canvas: Tall portrait cover, 2:3 aspect ratio, softly aged parchment background with mist, pale gray-blue ink textures, faint mountains, bamboo silhouettes, water ripples, lotus flowers near the bottom, and a dreamy high-detail watercolor finish.

Layout: Build a collage with exactly 5 visible character portraits/figures. 1) A very large translucent left-facing profile of the heroine fills the left half, with long white-silver hair, blue eyes, pale skin, loose strands, floral hair ornaments, and dangling blue crystal earrings. 2) A full-body heroine stands near the lower center, wearing layered white, translucent, and dark navy hanfu robes with flowing sleeves, sash ornaments, and boots, one hand held near her chest. 3) At the upper right, place an elegant pale blond/silver noble man seated on an ornate throne, wearing dark black-gold robes, a small crown, gloves, and elaborate royal accessories, with a cold expression. 4) At the middle right, place a long-haired male cultivator in pale robes turning back toward the viewer, backed by a golden circular astrological chart or celestial diagram. 5) At the lower right, place a black-haired swordsman in dark robes holding a drawn sword downward, looking serious and guarded.

Text content: Add large vertical expressive black ink calligraphy in the center reading {argument name="title text" default="夢外夢生"}, with a small red seal stamp beside or below it. The calligraphy should feel hand-brushed, dramatic, and slightly weathered.

Visual style: Ethereal cinematic wuxia poster, painterly anime faces, fine linework, pale desaturated palette of ivory, ash gray, mist blue, ink black, and muted gold. Use layered transparency so the large profile and background figures blend into the fog. Include ornate palace architecture faintly behind the upper-right throne figure, misty cliffs and ink splashes throughout, and soft falling specks like snow or dust.

Subject details: The heroine has {argument name="hair color" default="white-silver hair"}, delicate blue jewelry, melancholic eyes, and an elegant fragile presence. The clothing should look intricate but not modern, with flowing historical fantasy robes, embroidered patterns, tassels, beads, and semi-transparent veils.

Constraints: Keep the composition like a dramatic album or novel jacket cover, no modern objects, no photorealism, no extra characters beyond the exact 5 listed, no readable text except the central calligraphy and small seal, no watermark, no logo.

Create a vertical 3:4 high-fashion beauty portrait of a young woman with {argument name="hair color" default="warm light brown hair"} in loose, slightly tousled layers, looking back over her shoulder toward the camera with parted lips and soft confident eye contact. She is wrapped in an oversized off-shoulder chunky knit sweater in beige-pink tones, exposing one shoulder and upper back, one hand gently holding the sweater near her chest. Use warm golden-hour lighting and realistic skin texture with subtle makeup, glossy lips, defined lashes, and a natural peach blush. Cover the entire scene with a vivid optical light-projection effect: smooth wavy psychedelic contour stripes projected across her face, body, sweater, and the background, as if from a patterned gel projector. The pattern should contain exactly 5 repeating stripe colors: coral pink, hot magenta, lavender purple, creamy ivory, and warm golden yellow. The background is a seamless matching wall filled with the same flowing wavy stripes, creating a continuous immersive projection that bends over her features and shoulder. Compose her head in the upper center, shoulder in the lower center, shallow depth of field, editorial fashion photography, ultra-realistic, soft shadows, warm orange-pink color grading, no text, no watermark, no extra people.