Explore image prompts.

Goal: Create a vertical Chinese promotional infographic poster about unlocking comic creation logic with GPT-2, using a playful hand-drawn editorial style. Canvas: Portrait 3:4 poster, warm off-white textured paper background, soft pastel palette, slightly grainy risograph print texture, rounded friendly shapes, dark teal headline typography, coral accent text, pale green/yellow/pink/lavender section cards. Layout: Left side is a bold text-heavy headline and feature list; right side is a large illustration of an open padlock with a glowing keyhole releasing comics, sketches, speech bubbles, arrows, and diary pages. Bottom right has an open comic book, with pages and comic panels swirling upward from it into the lock area. Keep generous margins and a lively but readable composition. Text content: Use a large Chinese headline at top left: {argument name="headline text" default="漫画的\n创作逻辑"}. Under it, add smaller bold Chinese copy: {argument name="subheadline text" default="就这么水灵灵的被\nGPT-2 解锁了"}, with “GPT-2” in large coral red and the rest in dark teal/black. Add a green underline and smaller line: {argument name="tagline" default="这个思路，真是让人好生喜欢"}. Include small decorative coral sparkle marks and a hand-drawn heart near the tagline. Feature cards: Place exactly 4 rounded horizontal cards stacked vertically on the lower left, each with one circular icon on the left and bold Chinese label on the right. Card 1 is pale green with an open notebook and pencil icon, label {argument name="card one label" default="日记转"}. Card 2 is pale yellow with a lightbulb rising from an open book icon, label “知识转”. Card 3 is pale peach with a steaming mug icon containing a heart, label “鸡汤转”. Card 4 is pale lavender with a paper airplane icon, label “各种转换，\n玩的飞起”. From each of the 4 cards, draw one dotted arrow pointing right toward the flying comic materials; use matching muted arrow colors. Right-side subject details: Draw exactly 1 oversized open padlock in muted green-gray, positioned upper right, with chalk-like doodles on its body: tiny speech bubbles, comic thumbnails, and simple character sketches. Insert exactly 1 golden key into the keyhole; the key has a fountain-pen nib as its handle, symbolizing writing unlocking comics. Make the keyhole glow with warm yellow light. Flying comic materials: Show exactly 6 loose paper/comic elements floating from the open book toward the lock: 1 small portrait sketch sheet, 1 four-panel comic page, 1 single-page layout with a yellow image block, 1 two-character dialogue comic page, 1 small pink note page, and 1 larger horizontal comic strip page. Add curved motion trails, sparkles, tiny hearts, arrows, and speech bubbles around them, but keep the main count of loose sheets exactly 6. Bottom illustration: Draw exactly 1 open comic book at the lower right with visible comic panels and a cute simple character on the left page; use thin dark teal linework and pale yellow highlights. Add soft cloud-like pale green shapes along the bottom edge of the poster. Visual style: Cute Chinese social-media poster aesthetic, hand-drawn line art, rounded sans-serif Chinese typography, vintage print grain, pastel accents, clean hierarchy, whimsical educational tone. Constraints: Maintain the exact 4 feature cards and exact 6 loose flying paper/comic elements. Do not add extra major sections, extra logos, watermarks, QR codes, or English explanatory text beyond “GPT-2”.

Inspired by this product, design a set of women's clothing in a {argument name="style" default="cool and refreshing style"}.

Create a hyper-realistic {argument name="portrait type" default="luxury Hanfu fashion-editorial portrait"} inspired by premium Chinese beauty campaigns and cinematic Asian photography aesthetics. IMPORTANT: Generate ONLY ONE SINGLE VERTICAL IMAGE. Do NOT create multiple posters. Do NOT create collages. STYLE: Luxury glossy realism. Elegant bold feminine aesthetics. Soft cinematic editorial photography. MAIN CONCEPT: A luxury Hanfu beauty reclining beside glowing lanterns with flowing silk fabric and dreamy emotional atmosphere, blending ancient elegance with modern fashion-editorial energy. MODEL: Adult Chinese female model with sophisticated mature beauty. Glossy realistic skin. Luxury emotional makeup. Elegant cinematic expression. OUTFIT: {argument name="clothing color" default="Champagne-gold"} {argument name="fabric type" default="satin Hanfu"} with: deep silk folds, luxury embroidery, soft reflective fabric, flowing sleeve movement, and elegant fitted styling. VISUAL STRUCTURE: - cinematic reclining composition - glossy beauty close-up - elegant silk folds - dreamy editorial framing - luxury atmospheric depth - cinematic composition balance BACKGROUND: Luxury ancient-Chinese {argument name="background setting" default="lantern garden"} with: warm lantern glow, soft fog atmosphere, floating petals, traditional architecture silhouettes, and dreamy cinematic depth blur. COLOR PALETTE: Champagne gold, soft ivory, warm amber, cream beige, deep shadow tones. LIGHTING: Warm cinematic lantern lighting. Luxury glossy skin highlights. Dreamy editorial glow. MOOD: Luxury. Elegant. Bold feminine beauty. QUALITY: Ultra realistic native 4K HDR realism. Natural skin pores. Detailed satin textures. Looks like a real luxury Chinese fashion-editorial campaign.

Create a hyper-detailed comedic Japanese arcade fighting game screenshot styled like a versus battle scene, using a real-world photo aesthetic with game UI overlaid on top. The scene shows an intense mock battle between two groups of theme-park fans competing for the front row at an outdoor show plaza in Tokyo DisneySea. Use a wide 16:9 composition. In the background, clearly show Mediterranean Harbor and Mount Prometheus under bright daytime skies, with the waterfront and DisneySea architecture visible. In the foreground, show exactly 10 young adult people in winter casual clothing, split into 2 opposing teams of 5, physically leaning, grabbing, reaching, and shoving in a tug-of-war-like scrum over position, with exaggerated competitive body language and frozen action as if in a fighting game. Faces should be anonymized with soft blurred blocks. Add floating character labels above each person with levels and names in Japanese. The overall tone is absurdly realistic, like a real candid photo transformed into a polished arcade game battle screen. Add a full Japanese fighting-game HUD with glossy blue-versus-red interface styling. At the very top, place a center stage title bar reading "東京ディズニーシー　ミッキー広場　ショー最前列バトル" and a large timer in the middle reading "TIME 89". In the top left, add a blue team header "PLAYER1" and team name "最前列ガチ勢A". In the top right, add a red team header "RIVAL" and team name "ライバルグループB". On the left side, stack exactly 5 blue player status panels with portraits, level, Japanese class-like nicknames, HP, SP, and BURST meters. The 5 left-side labels are: "Lv.25 ガチ勢リーダー ユウキ", "Lv.24 筋肉マン タケシ", "Lv.23 眼鏡オタク シンジ", "Lv.23 開角心MAX ケント", "Lv.22 サポート要員 リョウ". On the right side, stack exactly 5 red rival status panels with the labels: "Lv.27 ライバルリーダー ダイキ", "Lv.26 パワフル代表 マサル", "Lv.24 戦略家 コウジ", "Lv.23 熱血漢 リク", "Lv.22 サポート女子 サキ". Each panel should include numeric HP and SP values and segmented BURST gauges, styled like a Japanese arcade RPG-fighter interface. Place exactly 10 in-battle nameplates above the fighters in the center scene, color-coded blue for the left team and red for the right team. The 10 labels are: "Lv.24 タケシ", "Lv.25 ユウキ", "Lv.23 シンジ", "Lv.23 ケント", "Lv.22 リョウ", "Lv.27 ダイキ", "Lv.26 マサル", "Lv.23 リク", "Lv.22 サキ", "Lv.22 ミサキ". At the lower left, add a skill menu titled "スキル" listing exactly 5 skills with SP costs: "ダッシュ突撃 SP 20", "肩押し強奪 SP 25", "荷物で場所確保 SP 15", "ロープくぐり SP 10", "本気の根性 SP 50". Beneath that, add a dark description box explaining the highlighted skill "本気の根性" with the Japanese text: "気合で相手を威圧し、どかす！ 一定時間、相手が怯みやすくなる！ （バーストゲージを大きく消費する） 効果時間：10秒". At the bottom center, add an item menu titled "アイテム" with exactly 5 item slots showing icons and counts: a water bottle "x3", a folded purple towel "x2", a blue drawstring bag "x1", a gray backpack "x1", and a boxed meal "x2". At the lower right, add a quest panel titled "クエスト" with the mission text "ショー開始までに最前列を死守しろ！" and condition text "条件：ライバルグループを全員後ろに押し戻せ！" and countdown text "ショー開始まで：02:30". Beside it, add a mini-map titled "ミッキー広場MAP" showing red and blue dots for both teams in the plaza. Along the very bottom edge, include small controller prompts in Japanese for actions such as skill use, item use, grab/push, and dash. Use dramatic, saturated lighting, crisp detail, realistic clothing folds, authentic plaza stone pavement, and a high-end Japanese game screenshot look. The image should feel like a ridiculous but believable crossover between a real Tokyo DisneySea crowd photo and a competitive arcade battle game interface.

Create a funny geometric cubist-style vector caricature portrait inspired by modern minimalist editorial illustrations. The artwork should feature exaggerated facial proportions, long neck, angular jawlines, sharp polygonal shading, oversized expressive eyes, stylized hair, and flat pastel colors. Use a clean {argument name="background color" default="teal"} textured background with soft vignette edges. The art style should look like a playful retro vector poster mixed with cubism and fashion illustration aesthetics. Create four separate portraits in this exact same style: {argument name="subjects" default="1. Elon Musk in a black futuristic outfit, 2. Cristiano Ronaldo in a Portugal jersey, 3. Virat Kohli in an India cricket jersey, 4. Lionel Messi in an Argentina jersey"}. Style details: geometric polygon face design, flat vector shading, minimal smooth gradients, exaggerated funny proportions, long neck and sharp facial structure, modern cartoon/editorial illustration vibe, clean crisp edges, retro pastel color palette, no watermark, highly detailed vector art, centered composition, portrait poster format

Goal: Create a richly detailed vertical dark-fantasy anime poster for {argument name="story title" default="Alice in Wonderland"}, reimagined as an elegant gothic tea-party character illustration. Canvas: Tall 2:3 portrait poster, dense decorative composition, cinematic lighting, deep navy, violet, black, antique gold, muted cream, and ruby-red accents. Use ornate Victorian borders, filigree corners, glowing bokeh, floating cards, and magical dust throughout. Main subject: A beautiful androgynous young male anime character seated in a plush vintage armchair at the center, looking tired, aloof, and melancholic. He has messy dark blue-purple hair, golden amber eyes, pale skin, and black cat ears, with a dark fluffy cat tail visible near the lower right. He wears an extravagant Mad Hatter-inspired gothic aristocrat outfit: oversized checkerboard top hat decorated with playing cards, blue roses, chains, gears, ribbons, and small charms; layered black and navy tailcoat with gold trim; ruffled white lace shirt; blue bow at the neck; ornate brooches; shoulder epaulettes; dangling chains; pocket watches; belts; gloves or lace cuffs; fitted dark trousers; and tall black lace-up platform boots. Pose him lounging with one leg crossed forward, one elbow resting on the chair arm, one hand near his face, and the other holding a delicate teacup. Environment: A surreal enchanted Wonderland forest or tea-party room with blurred glowing lanterns, blue stained-glass-like lights, mushrooms, roses, antique bottles, tea sets, cakes, clocks, playing cards, ribbons, and magical floating fragments. The mood should feel mysterious, decadent, dreamlike, and slightly ominous. Layout and text elements: Include exactly 6 distinct readable graphic text panels/signs: 1. Upper-left ornate arched title plaque with the large title “ALICE in WONDERLAND”, a smaller Japanese subtitle “不思議の国のアリス”, a tiny teapot icon, and story text: “Down the rabbit-hole he fell, chasing a whisper not meant for him— In a land where time is broken and rules are only a joke, ...is there a way to return?” 2. Upper-right wooden signpost with 4 arrow signs labeled exactly: “This Way”, “That Way”, “Tea Party”, and “Go Back”. 3. Lower-left parchment invitation card titled “Mad Hatter’s Tea Invitation” with smaller text: “You’re invited to a most unusual tea. Don’t be late. Or be. It doesn’t matter.” 4. Bottom-left ornate oval cameo frame showing a tiny silhouette tea-party scene with two seated figures, labeled “Who Are You?” 5. Lower-center handwritten chalk-like quote: {argument name="center quote" default="There’s no truth here. Only what you choose to believe."} with a small doodle cat face and sparkle marks. 6. Lower-right parchment tag titled “Drink Me” with smaller text: “A sip may shrink you, A sip may change you, Choose wisely.” plus a small potion-bottle illustration. Additional visible objects: Include floating playing cards with suits, at least 3 red roses, at least 2 pocket watches, a teapot and cupcake tea set near the lower left, a glowing potion bottle labeled “Drink me” on the lower right, a crystal orb or glowing glass lamp, wax seals on parchment notes, ribbons, chains, and blue flowers. Visual style: Ultra-detailed Japanese anime key visual, ornate gothic lolita / ouji fashion, Victorian fantasy poster design, high-contrast rim lighting, soft painterly rendering, crisp character details, luminous particles, intricate accessories, dramatic depth of field, premium collectible illustration quality. Constraints: Keep the main character recognizable as the central focus, do not crop off the hat or boots, preserve all 6 text panels/signs, avoid modern objects, avoid minimalism, avoid flat colors, and make the typography decorative but legible.

Please transform each photo I upload into an individual high-end design poster with a {argument name="aspect ratio" default="3:4"} vertical composition, following a dual-layer logic: the top half is realistic photography, while the bottom half is a painterly distillation of the original image's core imagery, creating an echo between reality and memory. The top half retains the original photo, maintaining subject identity, structure, posture, texture, and natural lighting, with subtle high-end photographic toning to evoke an independent art magazine or exhibition quality. The environment can be naturally extended to fit the frame, but the subject must not be distorted. The bottom half extracts the most recognizable **subject, outline, and narrative relationships** from the photo, reimagining only the most memorable information. Avoid full restoration of the scene; instead, focus on a single core subject with minimal narrative details, like a reorganized visual memory. The background of the bottom half should use **extremely light colors and large areas of negative space**. The background color should intelligently match the photo's temperature (e.g., warm white or cool off-white) to feel clean and quiet. This blank space should convey air, distance, and emotion. Emphasize **visual weight, negative space, and tension** in the composition. The subject can be offset or suspended to create beauty through contrast and scale. If the most moving part of the original photo is the distance between two objects, prioritize that relationship over individual detail. The painting style should use relaxed, naive artistic textures like **gouache, acrylic, and oil pastel**, with summary color blocks and hand-drawn outlines. Shapes can be slightly awkward or exaggerated, but the key posture must be accurate. Retain hand-painted traces like pauses and visible brushstrokes. The palette should be a **warm, bright, and naive artist's color scheme** extracted from the photo. Use warm blocks like {argument name="warm tones" default="cream yellow, apricot, coral pink, or dusty rose"} contrasted with {argument name="cool tones" default="sky blue, mint green, or sage"}. Colors don't have to be realistic but must be harmonious, avoiding heavy Morandi grays or high-saturation digital hues. Text should be minimal and meaningful, generated based on the theme or emotion of the photo rather than fixed titles. Text can naturally enter the white space, appearing slightly hand-written or misplaced to maintain an artistic feel without looking like a mechanical advertisement. The overall goal is **minimal subjects, large white space, and warm hand-drawn aesthetic with clear visual metaphors**, resembling an independent publication hand-painted by an artist.

{argument name="character" default="Li Shishi"}'s live broadcast room, an ancient-style beauty playing the pipa and singing, with the live comments scrolling "{argument name="comment" default="Reward 10,000"}."

A luxurious cinematic product photograph of a classic rectangular perfume bottle inspired by {argument name="brand label" default="N°5 CHANEL PARIS PARFUM"}, placed upright on a glossy black marble surface with white veining. The bottle is centered slightly to the right, made of clear faceted glass with a large transparent crystal stopper, filled with rich amber-gold perfume that glows from within. Tiny condensation droplets cover the glass, adding texture and realism. Dramatic warm lighting from the upper left creates golden highlights, deep reflections on the marble, and a soft luminous bloom in the background. Wisps of elegant smoke curl around the bottle on both sides, enhancing a moody high-end advertisement feel. Dark background, shallow depth of field, ultra-detailed studio product photography, luxury beauty campaign aesthetic, crisp focus on the bottle, realistic reflections, warm black-and-gold color palette. Add a small white {argument name="corner logo" default="Pollo.ai"} in the top-right corner. Square composition, premium commercial ad, photorealistic, high contrast, refined and sophisticated.

Goal: Create a premium vertical restaurant menu poster for a Nanyang brunch tasting, combining realistic food photography with hand-drawn chalk annotations and refined brand-menu layout. Canvas: Vertical 2:3 poster, warm olive-green linen/tablecloth background with soft natural sunlight and leaf shadows from the upper left. Use a high-end editorial food photography look, realistic dishes, shallow depth of field, appetizing warm highlights, and white handwritten chalk-style graphics. Layout: Large hand-drawn Chinese headline centered near the top reading {argument name="headline text" default="南洋早午餐灵感"}, with the English subtitle “Nanyang Brunch Tasting” underneath in casual handwritten script and a thin underline. Arrange exactly 6 photographed menu items across the poster with white annotation arrows, doodles, and bilingual labels. Keep generous spacing and an elegant restaurant poster composition. Add a dark green brand footer strip at the bottom. Menu items: Include exactly 6 dishes/drinks with these labels and prices: 1) Kaya Toast, ¥32, shown at upper left as stacked golden toast triangles with a square of butter on a patterned ceramic plate; 2) Laksa Noodles, ¥48, shown at upper right in a ceramic bowl with orange curry broth, noodles, shrimp, herbs, and a lime half; 3) Pandan Kaya Cake, ¥36, shown left-middle as a neat green layered cake slice topped with shredded coconut on a small ceramic plate; 4) Nasi Lemak, ¥58, shown as the largest hero dish in the center-lower area on an oval plate lined with banana leaf, including a dome of coconut rice, fried chicken leg, cucumber slices, sambal in a small metal cup, peanuts, and anchovies; 5) Fried Spring Rolls, ¥28, shown lower left in a small woven basket on banana leaf with several golden rolls and garnish; 6) Iced Coffee, ¥26, shown lower right in a clear glass with ice cubes, creamy coffee layers, on a small woven coaster. Hand-drawn details: Add white chalk doodles throughout the negative space: palm tree sketch near top left, small stars, flying birds, leaf outlines, arrows pointing to dishes, little sparkle marks, a lime sketch near the spring rolls, a coffee cup doodle near the iced coffee, and playful scribbles around labels. Use thin irregular chalk lines, not digital-perfect vectors. Brand footer: Bottom dark green band with a simple line-art palm logo on the left and the restaurant name {argument name="brand name" default="NANYA HOUSE"} in large white serif uppercase centered. Add Chinese text “南也咖啡馆” below or beside it, and the tagline {argument name="tagline" default="KEEP IT WARM, KEEP IT EASY"} in small spaced uppercase at the bottom. Include a small leaf line drawing on the right. Visual style: Realistic food photography composited into a designed poster, premium handmade café aesthetic, Southeast Asian brunch mood, olive green, cream, white chalk, golden-brown food tones, natural shadows, crisp but warm. Avoid clutter, avoid extra menu items, avoid watermarks, and keep all text legible.

Create a premium high-quality {argument name="style" default="3D caricature companion"} of the person in the reference image while keeping the original realistic person fully present and untouched. The realistic person must remain photorealistic, highly detailed and faithful to the original photo. Create a stylized 3D caricature version of the SAME person standing beside them. Preserve the same: outfit, hairstyle, accessories, fashion styling, identity, facial resemblance, attitude and vibe.The caricature must have: large expressive eyes, slightly oversized head, smooth cinematic skin, {argument name="animation style" default="Pixar/Disney-inspired premium 3D styling"}, smaller body proportions, but still look fashionable and recognizable, NOT childish, toy-like or baby-sized.IMPORTANT: The caricature height should be approximately {argument name="size" default="shoulder to ear level"} of the real person, never tiny or child-sized. The caricature and real person must be physically and emotionally interacting naturally. Examples of interaction: holding hands, looking at each other, walking together, sharing an object, leaning, playful pose, touching shoulder, mirroring pose, reacting to each other, casual chemistry, candid companionship. The caricature should feel like a living animated version of the same person existing in the same world. Preserve original scene, lighting and perspective whenever possible. Professional photography composition, cinematic lighting, realistic shadows, luxury editorial realism mixed with premium stylized 3D animation. No tiny companion, no side mascot, no disconnected pose, no separate standing character, no toy proportions, no plastic doll look, no replacing the original person.

Create a highly realistic vertical courtside audience photo of a beautiful young {argument name="subject ethnicity" default="Asian"} woman watching an NBA playoff game from the stands, framed waist-up in a close closeup. She sits among packed Golden State Warriors fans inside a vibrant basketball arena, looking slightly upward and off-camera with a surprised open-mouth reaction as if witnessing a dramatic play. She has a messy high bun with loose face-framing strands, glossy dark hair, bold winged eyeliner, long lashes, peach blush, soft peach lipstick, smooth luminous skin, and large gold hoop earrings. Dress her in a fitted royal-blue Golden State Warriors zip-up jacket with yellow zipper, yellow-and-white shoulder panels, ribbed collar stripes, and a clear Warriors bridge logo patch on the chest. The background should be sharp and detailed, crowded with fans in blue and gold Warriors gear: foam fingers raised, baseball caps, jerseys, arena ribbon boards, bright stadium lights, drink bottles, and rows of seats, creating playoff energy without blurring away the environment. Use natural arena lighting, documentary sports photography realism, crisp facial detail, shallow-to-moderate depth of field, vivid blue and gold color palette, vertical 2:3 composition, no watermark, no URL, no distorted hands or extra facial features.

Create a highly realistic vertical smartphone-style courtside portrait of a young woman at a Chicago Bulls NBA game, framed from about mid-thigh/waist up, standing or seated near the lower bowl seats and facing the camera. She wears an oversized bright {argument name="hoodie color" default="red"} Chicago Bulls hoodie with large varsity-style “BULLS” lettering across the chest and the Bulls logo below, loose sleeves, front pouch pocket, and hoodie drawstrings. Her {argument name="hair style" default="dark brown layered messy wolf cut with loose waves"} falls around her shoulders, with natural volume and slightly tousled texture. Her face is intentionally anonymized by a centered plain rectangular blur/block in a warm skin-tone color covering the facial features. She holds one clear plastic cup of amber beer or iced drink in her left hand near chest height; the cup has a black-and-red Chicago Bulls bull logo printed on it, condensation and realistic plastic reflections. Use a relaxed casual fan pose, one hand holding the drink and the other tucked into the hoodie pocket. The background is a packed basketball arena with visible rows of spectators, detailed seating tiers, red LED ribbon boards reading “BULLS” with Bulls logos, the basketball court and hoop visible on the right, a shot clock showing 24, and players/staff in the distance. Keep the stadium background detailed and recognizable rather than blurred, with indoor arena lighting, realistic crowd density, natural phone-camera perspective, sharp fabric texture, glossy drink reflections, and authentic courtside atmosphere. No extra text beyond visible arena signage and Bulls branding.

Create a photorealistic vertical waist-up close-up of a {argument name="subject" default="young morena woman basketball fan"} sitting in the lower-bowl audience at a packed Boston Celtics NBA playoff game. She is centered close to the camera, wearing a green {argument name="jersey text" default="CELTICS"} basketball jersey with the number 0 and a black varsity jacket with glossy leather sleeves, green-and-white striped cuffs, silver snap buttons, and a round Celtics shamrock patch on the chest. She has long voluminous dark curly hair, small hoop earrings, and a radiant game-day makeup look; her face should be visible and expressive, showing an emotional cheering reaction. Pose her with one arm raised high in a clenched-fist celebration while the other arm is lower near the seat, as if reacting to an intense play. The background is a fully sharp, busy NBA arena interior with a basketball court visible below, dense cheering crowd, green Celtics playoff ribbon boards, bright stadium lights, and a large overhead jumbotron showing the live court and scoreboard details. Use realistic arena lighting, crisp detail throughout the packed stadium, natural skin texture, authentic sports-photo perspective, 35mm documentary photography feel, high dynamic range, no blur, no watermark, no extra logos beyond Celtics-style arena and jersey details.

Create a photorealistic vertical smartphone photo of a {argument name="subject" default="young woman NBA fan"} seated courtside in a packed basketball arena, framed waist-up in a close closeup. She has long natural dark brown hair with soft loose waves and volume, parted near the center, falling over her shoulders. Her face is intentionally covered by a large opaque rectangular privacy block in a muted brown skin-tone color, centered over the entire face. She wears a black fitted New York Knicks varsity jacket with shiny black leather sleeves, orange-and-blue striped collar trim, snap buttons, and a visible Knicks basketball logo patch on the left chest, over a fitted white tank top. Add a small gold pendant necklace at her collarbone and a subtle small earring. The background shows Madison Square Garden-style NBA game atmosphere: hardwood court visible to the left, basketball hoop and shot clock in the distance, dense arena crowd in dark seats, bright blue LED ribbon boards, scoreboard lights, and a visible Delta sign, all slightly out of focus with realistic depth of field. Lighting should be authentic indoor arena lighting with crisp phone-camera detail, natural contrast, slight wide-angle perspective, candid fan snapshot feeling, no glamour studio lighting, no extra text overlays, no watermark.

Create a cohesive editorial travel-journal image inspired by the provided reference photos: a {argument name="subject" default="real-world coffee shop moment"} paired with a {argument name="style" default="minimalist hand-drawn illustration"} of the exact same scene, arranged as a sophisticated split-page layout. On the left, show a warm documentary-style photograph of a barista’s hand holding a clear glass of iced coffee beside a professional coffee machine, with visible ice cubes, rich amber-brown coffee, realistic reflections, stainless-steel equipment, and subtle café details; on the right, recreate the same composition as a loose vintage ink-and-watercolor sketch on {argument name="paper" default="textured warm ivory paper"}, preserving the glass, hand, coffee machine, perspective, and key details while using imperfect black linework with restrained earthy ochre and muted blue accents. Use an authentic independent café travel-zine aesthetic, natural imperfections, soft grain, slightly faded analog photography, tactile paper texture, editorial typography, generous negative space, small understated location/date/caption text, balanced asymmetrical composition, nostalgic 2020s travel diary mood, premium art-direction, realistic photography seamlessly contrasted with handmade illustration, muted earthy color palette, soft natural lighting, subtle film grain, high detail, vertical 4:5 composition, no logos, no watermark.

Create a hyper-realistic vertical smartphone photo of {argument name="character description" default="a young Asian woman"} sitting courtside/in the lower audience section at a packed Los Angeles Lakers NBA game, framed waist-up in a close candid closeup. She is centered in the foreground, seated on a black arena chair, wearing {argument name="team hoodie" default="a black cropped Los Angeles Lakers hoodie with purple-and-gold sleeve stripes and a large number 23 on the front"}, black leather-look pants, and gold accessories including exactly 2 visible jewelry pieces: a thin gold necklace with a round pendant and a dangling gold earring. Her hair is dark, slightly messy, pulled back into a sleek ponytail with loose strands around the ears. Show her posture as calm and focused, hands resting low near her lap, watching the game action off-camera. Include exactly 3 prominent foreground spectators: the main woman in the center, a young man on the left in a purple Lakers hoodie looking left, and a young man on the right in a black Lakers zip hoodie holding a phone; obscure exactly 2 faces with flat rectangular skin-tone privacy blocks, one over the main woman's face and one over the right spectator's face. The background is a densely crowded basketball arena with hundreds of fans, upper seating tiers, bright stadium lights, LED ribbon boards, and readable arena signage such as {argument name="arena signage" default="LOS ANGELES LAKERS"} and a Toyota logo near the scoreboard. Use realistic indoor arena lighting, natural phone-camera perspective, high detail fabric texture, shallow-to-moderate depth of field, slight wide-angle distortion, authentic candid sports-event atmosphere, no glamour studio lighting, no watermark.

You are an AI that reproduces snapshots taken with disposable instant cameras that were very popular in the 1990s. Create one image of the person in the attached image with a quality that could be mistaken for a print photo taken by an amateur in the 90s. [Subject] - Year: {argument name="shooting year" default="1997"} (Enter in AD). - Person: [] (If blank, generate a person from that era). - Pose/Expression: {argument name="pose" default="peace sign/shy smile"} (e.g., peace sign, shy smile, arm around a friend). - Clothing: {argument name="outfit style" default="loose socks/ganguro"} (e.g., loose socks, ganguro, street style, salaryman). - Location: [] (e.g., in front of a Purikura machine, Izakaya, school trip bus, own room). - Time of day: [] (e.g., day/evening/night). - Flash: [] (Specify 'Yes' or 'No'). - Date stamp: [] (e.g., '97 08 15). - White border: [] (Specify 'Yes' or 'No'). [Absolute rules for image quality/texture] - Lens: Fixed-focus single-focal plastic lens. Slightly out of focus except for the center. - Exposure: Only if flash is 'on', the face and foreground will be slightly overexposed by the flash, and the background will drop off sharply. - Color: Overall yellow to orange film color cast. Skin becomes more reddish. - Grain: Graininess unique to ISO400 film all over. - Vignette: Light fall-off at the four corners. Lens flare or red-eye effect is OK. - Composition: Amateur-specific tilt, too centered, or casual cut-offs. - Prohibited: Modern smartphone sharpness/HDR/skin correction/beautiful bokeh/4K feel.

Create a hand-drawn style infographic card with a 9:16 vertical aspect ratio. The card has a clear theme and the background is beige or off-white with a paper texture. The overall design reflects a simple and friendly hand-drawn aesthetic. The top of the card features a large brush cursive font in alternating red and black with sharp contrast to highlight the title and attract visual focus. The text content is all in Chinese cursive, and the overall layout is divided into 2 to 4 clear sections, each using short, concise Chinese phrases to express core points. The font maintains the smooth rhythm of cursive, being both legible and artistic. The card is dotted with simple, fun hand-drawn illustrations or icons, such as characters or symbolic signs, to enhance visual appeal and trigger thought and resonance in the reader. The overall layout pays attention to visual balance, reserving enough white space to ensure the image is concise, clear, and easy to read and understand. The theme is: "{argument name="theme content" default="Building an IP is long-term compound interest. Keep setting up your stall every day, keep doing it, and there will definitely be results, because 99% of people can't stick to it."}"

ChatGPT, we’ve been together for quite a while now. I’d like to see what you look like. Please generate an image that feels like a casual snapshot taken on an {argument name="camera" default="iPhone"}—nothing with a clear subject or intentional composition. Just something very ordinary, even slightly flawed, like an accidental photo. The image should have {argument name="visual artifacts" default="a bit of motion blur, uneven lighting, and be slightly overexposed"}. The angle should feel awkward, the framing messy, and overall it should give off a “too real, spur-of-the-moment” vibe like a {argument name="scenario" default="selfie accidentally taken while pulling a phone out of a pocket"}.