Explore image prompts.

Create a newspaper extra for when {argument name="invaders" default="Saiyans"} invade Earth.

Aspect Ratio: 9:16 Subject: A POV shot taken with an iPhone 16 Pro rear camera of {argument name="the scene" default="the scene"}; note, the POV sees the real world, not 2D or 2.5D! Scene: {argument name="character name" default="Nami"} from ONE PIECE performing a skill POV: Random Marine soldier's perspective

A photorealistic corporate photograph of a man resembling {argument name="person name" default="Sam Altman"} wearing a {argument name="clothing" default="black long-sleeve sweater"}, standing in profile and writing on a large whiteboard with a black marker. The whiteboard features clear, handwritten black text reading "{argument name="line 1 text" default="Model: ChatGPT"}" with "{argument name="line 2 text" default="Company: OpenAI"}" written directly below it. In the bottom right corner, smaller text reads "{argument name="signature text" default="- Sam Altman CEO, OpenAI"}". The scene is set in a bright, modern office with soft natural lighting and a softly blurred background.

A well-proportioned hourglass figure, eyes and expression that are {argument name="expression" default="playful and coquettish"}, a mature Japanese female model around 20 years old, in fashionable beachwear.

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

Goal: Create an ultra-wide, extremely information-dense panoramic illustrated timeline of the entire universe, Earth, life, human civilization, technology, and the future, rendered as a single seamless epic cross-section mural for gpt-image-2. Canvas: 16:9 horizontal poster, very high detail, cinematic realism mixed with museum-quality educational illustration, sharp enough to read tiny timeline labels. Use a grand curved horizon of Earth across the center, with outer space above and layered historical scenes below. No blank areas. Overall layout: The composition is divided into 4 main horizontal zones. Top zone: cosmic history in deep space. Upper-middle zone: Earth history and natural evolution across a sweeping landscape. Lower-middle zone: human civilization and technological progress. Bottom zone: a continuous golden timeline strip with exactly 18 labeled milestones in Chinese, each with a small circular marker. Top cosmic zone: Show a fiery Big Bang explosion at far left, colorful nebulae and starfields, a spiral galaxy, forming planets, the solar system, Earth and Moon, asteroids and comets, rockets, satellites, a space station, astronauts on the Moon, lunar rover, Mars rover, futuristic space telescopes, spacecraft, a ring station, distant planets, black hole, and blue laser-like space trails at far right. Add a thin golden orbital timeline line with small circular nodes crossing this upper area. Upper-middle Earth and evolution zone: Blend volcanic early Earth on the left with lightning, lava, meteor impacts, hot oceans, microbial bubbles and sea creatures; transition into lush prehistoric seas with fish, ammonites, trilobites, and marine reptiles; continue into a dinosaur landscape with forests, sauropods, theropods, pterosaurs, and smaller dinosaurs; transition to ice-age mountains and mammoths; then to modern rivers, grasslands, elephants, deer, birds, wind turbines, farmland, and a sleek futuristic city skyline at the right. Keep the transitions seamless like a chronological world map. Lower-middle civilization and technology zone: At far left show human evolution silhouettes walking forward, early campfires, caves, stone tools, primitive huts, pottery, sheep and cattle. Continue through ancient agriculture, pyramids, temples, classical cities, pagodas, medieval castles, churches, marketplaces, sailing ships, caravans, early machines, steam trains, bicycles, automobiles, airplanes, factories with smokestacks, power lines, telephones, radios, televisions, computers, laptops, smartphones, servers, laboratories, control rooms, robots, holographic blue interfaces, high-speed trains, and futuristic glass cities. Include many tiny people in period clothing interacting naturally. Bottom strip: Create a dark blue-black footer band with a thin gold line and exactly 18 milestone nodes, evenly spaced left to right. Use these exact Chinese labels and dates, one per node: 1. 「宇宙诞生\n约138亿年前」, 2. 「太阳系形成\n约46亿年前」, 3. 「地球形成\n约45亿年前」, 4. 「生命起源\n约38亿年前」, 5. 「海洋生命\n约5.4亿年前」, 6. 「恐龙时代\n约2.3亿年前」, 7. 「哺乳动物时代\n约6600万年前」, 8. 「人类出现\n约300万年前」, 9. 「农业革命\n约1.2万年前」, 10. 「文明起源\n约公元前3500年」, 11. 「古典时代\n约公元前800年」, 12. 「中世纪\n约5世纪」, 13. 「大航海时代\n15–17世纪」, 14. 「工业革命\n18–19世纪」, 15. 「电气时代\n19–20世纪」, 16. 「信息时代\n20世纪后半叶」, 17. 「数字时代\n21世纪」, 18. 「未来探索\n未来」. Visual style: Hyper-detailed epic science-history infographic, realistic lighting, vibrant but coherent color grading, gold accent lines, deep blues and oranges, miniature diorama detail, cinematic depth, crisp micro-scenes, no cartoon style, no flat vector look. Constraints: Make the poster astonishingly dense but coherent; keep all 18 bottom labels legible; avoid random unreadable text outside the timeline; avoid duplicated milestone labels; do not add watermarks or logos. The main theme is {argument name="timeline theme" default="the complete history of the universe, Earth, life, civilization, technology, and future exploration"}. Use {argument name="language for milestone labels" default="Chinese"} for the footer labels, a {argument name="visual style" default="hyper-detailed cinematic educational mural"}, a {argument name="accent color" default="gold"}, and a {argument name="future city mood" default="optimistic blue futuristic"}.

A premium e-commerce poster for fresh blueberries in a clean Chinese product-advertising style. Show a clear plastic clamshell box of blueberries as the main subject, placed diagonally from lower center to right side on folded blue fabric, viewed from a slightly elevated angle. The package must remain realistic and consistent: a transparent square container with rounded corners, filled with dark blue blueberries, with a large irregular rounded label on top in white, pale blue, and deep blue, featuring one oversized blueberry illustration in the center and elegant Chinese branding. Make the fruit inside look larger, plumper, fresher, and covered with subtle moisture droplets, while keeping the overall blueberry arrangement believable. The background is an airy icy-blue tabletop with soft cloudy texture, cool daylight, and scattered loose blueberries around the package. Add a few blurred green leaves entering from the top right and bottom right edges for a fresh natural feeling. In the upper-right corner, include 1 small inset image showing the original product package from above on a warm brown surface, like a reference thumbnail. On the left side, create Chinese promotional typography with a large dark blue calligraphy headline {argument name="headline text" default="决茗新"}, followed by 2 smaller lines of copy: {argument name="subheadline text" default="新鲜蓝莓 自然之选"} and {argument name="tagline text" default="每一颗都是自然的礼物"}. Below that, place 3 vertically stacked feature icons with short Chinese captions: a leaf icon for natural ripeness, a fruit icon for juicy fullness, and a heart icon for rich nutrition. Near the bottom left, add large white brush-style Chinese text {argument name="product name" default="蓝莓"}, a secondary line {argument name="benefit text" default="膳食纤维+花青素"}, and a small net weight line reading 125克. Use cool blue color grading, crisp commercial lighting, sparkling highlights on the plastic lid, premium supermarket packaging aesthetics, high detail, realistic product photography blended with polished graphic design.

Goal: Create a vertical modern football superstar collectible poster for {argument name="character name" default="Jude Bellingham"}, styled as a Chinese “new generation star dossier” World Cup poster with hyper-realistic action, light data-file graphics, and a career timeline. Canvas: Tall 9:16 poster, white and deep navy palette with gold accents, high-contrast cinematic sports lighting, premium trading-card / magazine-cover design. Background is a large illuminated football stadium with mist, crowd blur, and a clean futuristic white border frame. Main subject: A hyper-realistic young male footballer in a white kit with dark navy trim, sprinting or striking forward toward the viewer. Use an extreme low-angle perspective: one boot sole is large in the foreground, the torso dominates the center, and a white football with navy/gold markings flies toward the bottom-right foreground. Add shattered glass shards, turf debris, dust, and dynamic impact fragments around the player to create a 3D breakout effect. The player’s face is intentionally covered by a plain soft-edged rectangular blur/solid mask, matching the generated poster. Top typography: Huge bold dark navy Chinese headline reading {argument name="headline text" default="祖德·贝林厄姆"}. Add a tiny gold crown icon centered above the headline. Under it, a smaller spaced subtitle in Chinese: “英格兰新核 · 全能中场 · 领袖锋芒”, with thin gold horizontal divider lines at both sides. Side data panels: Use exactly 8 dark navy information cards with gold outlines and beveled corners, 4 on the left and 4 on the right. Each card contains a simple gold/white tactical diagram, radar chart, silhouette, or stat graphic plus Chinese labels. Left column, top to bottom: 1) “伯明翰起点” with a football pitch diagram and caption “少年崭露头角 / 天赋初现”; 2) “多特蒙德时期” with tactical arrows and caption “迅速成长为中场核心 / 展现全面能力”; 3) “皇马核心” with circular radar/orbit diagram and caption “登陆顶级舞台 / 掌控比赛节奏”; 4) “英格兰主力” with pitch-position graphic and caption “国家队中流砥柱 / 角色中场重任”. Right column, top to bottom: 5) “中场全能属性” with a hexagonal radar chart labeled “传球, 防守, 盘带, 视野, 控球, 射门”; 6) “关键比赛高光” with pitch diagram and stars, caption “大场面先生 / 决定比赛走向”; 7) “进球与助攻能力” with big stats “28+” and “22+”, bar indicators, and captions “进球”, “助攻”, “持续贡献 / 数据见证影响力”; 8) “领袖气质” with a captain silhouette and caption “冷静沉着 | 自信坚定 / 以身作则 | 带动全队”. Bottom timeline: Add one wide dark navy and gold career timeline panel across the bottom with exactly 5 timeline points and one gold trophy icon near the right. The 5 labeled points are: “2003 / 伯明翰 / 足球启蒙”; “2019—2020 / 多特蒙德 / 崭露头角”; “2023—至今 / 皇马核心 / 中场领袖”; “2020—至今 / 英格兰主力 / 大赛担当”; “未来可期 / 足坛新传奇 / 正在书写”. Footer: Large metallic gold Chinese slogan across the very bottom: {argument name="footer slogan" default="新生代巨星破框档案"}. Use embossed block lettering, navy shadow, and angular gold trim. Visual style: Ultra-realistic sports photo composite, dramatic depth of field, sharp player and ball details, navy-and-gold infographic overlays, clean Chinese editorial typography, cinematic stadium haze, collectible poster finish. Keep all visible text in Chinese exactly as specified, avoid logos, avoid club crests, avoid watermarks, and maintain a premium World Cup star-poster feel.

Goal: Create a vertical modern football superstar collectible poster for a Spanish teenage prodigy, with hyper-realistic action photography, explosive 3D depth, light data-profile overlays, and a career timeline. Canvas: Tall portrait poster, 2:3 aspect ratio, high-resolution sports magazine cover style. Background is a packed football stadium under bright daylight, with a slight architectural roof grid and dramatic motion blur. Use red, gold, black, and white as the dominant palette, with glowing gold HUD lines and sparks. Main subject: Center a hyper-realistic young male footballer in a red Spain-inspired kit with yellow stripes, red socks, and football boots, captured from a low-angle wide-lens perspective while lunging forward and striking a ball with his left foot. Make the legs and ball exaggerated by perspective, with the boot and ball close to camera, motion blur on the ball, golden speed trails, grass particles, and cinematic stadium lighting. The player's face is intentionally covered by a flat brown square censor block, while curly brown hair remains visible above it. Top headline text: Huge distressed bold Chinese title across the top: {argument name="headline text" default="西班牙天才新星"}. Under it, add a smaller red subtitle with divider lines: {argument name="subtitle text" default="左脚新核 · 灵动突破 · 少年锋芒"}. Left-side info cards: Add exactly 3 stacked black-and-gold beveled cards on the left, each with an icon and Chinese copy: 1. Building icon, title “拉玛西亚起点”, lines “天赋初现” and “梦想启航”. 2. Stadium icon, title “一线队登场”, lines “少年亮相” and “未来已来”. 3. Star icon, title “西班牙新星”, lines “红色血脉” and “荣耀传承”. Right-side analysis cards: Add exactly 4 stacked black-and-gold beveled cards on the right, each with small sports-data graphics: 1. Running-player icon, title “左脚突破特质”, lines “内切利刃” and “掌控节奏”, with a small golden line chart. 2. Goal/net icon, title “关键进球”, lines “冷静致命” and “一击制胜”, with a small bar chart. 3. Dribbling-player icon, title “关键传球”, lines “洞察空间” and “精准输送”, with a small line graph. 4. Pitch/heatmap icon, title “边路创造力”, lines “撕开防线” and “制造威胁”, with a glowing heat spot. Extra HUD graphics: On the left-middle background place a faint tactical football diagram with circles, arrows, passing routes, and grid lines. Near the lower-left place a black-and-gold hexagonal badge with an upward chart icon and the text “未来可期”, framed by laurel leaves. Bottom timeline: Add a horizontal glowing career timeline with exactly 5 milestones from left to right, each marked by a circular node and Chinese labels: 1. “8岁” / “启蒙” / “足球梦想” / “开启”. 2. “12岁” / “拉玛西亚” / “潜力新星” / “崭露头角”. 3. “16岁” / “一线队登场” / “正式亮相” / “备受瞩目”. 4. “18岁” / “关键时刻” / “决定比赛” / “挺身而出”. 5. “未来” / “无限可能” / “新核崛起” / “闪耀世界”. Footer: Add a dark navy and red angular ribbon footer with gold decorative slashes and the centered Chinese title: {argument name="footer title" default="新生代巨星破框档案"}. Visual style: Hyper-realistic sports action composite, dynamic foreshortening, premium poster design, Chinese typography, distressed headline texture, black translucent data panels with gold outlines, glowing golden motion streaks, subtle red accents, crisp UI elements, cinematic color grading, dramatic depth, energetic collectible-card atmosphere. Constraints: Use exactly 3 left info cards, exactly 4 right analysis cards, exactly 5 timeline milestones, and one lower-left hexagonal badge. Keep all text in Chinese exactly as specified unless customized. Do not add logos, watermarks, or real club badges.

Goal: Create a vertical modern football superstar collectible poster for {argument name="player name" default="埃尔林·哈兰德"}, showing an ultra-realistic striker charging toward the camera in a dramatic stadium action scene, with a futuristic sports-data archive interface around him. Canvas: Tall portrait poster, about 9:16 ratio. Dark blue, icy steel, and gold color palette. High contrast cinematic lighting, rain mist, flying turf, dust, sparks, motion blur, and a packed stadium roof in the background. Main subject: A powerful blond male footballer in a sky-blue jersey, white shorts, and pale blue socks, sprinting and kicking forward from the center of the poster. Use an extreme low-angle perspective: his boot and the football are closest to the viewer, large and motion-blurred in the foreground, while his torso fills the center. The face should be covered by a centered square blurred censor block, while hair, body, uniform, and pose remain visible. Emphasize muscular arms, explosive forward momentum, and a “finishing machine” striker vibe. Top typography: Huge distressed white Chinese headline text reading {argument name="headline text" default="埃尔林·哈兰德"}. Beneath it, a smaller gold subtitle with separators reading {argument name="subtitle text" default="北欧巨炮 · 终结机器 · 禁区统治者"}. Add thin gold horizontal accent lines on both sides. Data interface layout: Place exactly 8 transparent HUD-style stat cards around the player, with thin gold and pale-blue technical borders, tiny charts, icons, microtext, and graphs. Left column has exactly 4 cards from top to bottom: 1) 「青训起点」 with a small player path diagram, 2) 「萨尔茨堡爆发」 with a kicking silhouette and growth chart, 3) 「多特锋芒」 with a running player icon and graph, 4) 「曼城时期」 with a stadium icon and bar chart. Right column has exactly 4 cards from top to bottom: 1) 「进球效率」 with a target icon and bar chart, 2) 「禁区统治力」 with a goal icon and rising line graph, 3) 「冲刺与力量」 with a sprinting icon and bar chart, 4) 「纪录刷新者」 with a trophy icon and data chart. Bottom timeline: Add a thin career timeline stretching across the lower poster with exactly 6 small footballer silhouette milestones and tiny year labels, connected by gold dots and a fine line. Include faint blue equalizer-style bars behind the timeline. Bottom title plate: At the very bottom, add a dark futuristic nameplate with gold trim, chevron arrows on both sides, and large gold Chinese text reading {argument name="bottom slogan" default="新生代巨星破框档案"}. Visual style: Hyper-realistic sports photography mixed with sci-fi infographic design, collectible World Cup poster energy, volumetric stadium light beams, sharp typography, gritty texture, layered depth, premium editorial composition. Constraints: Keep all text legible and in Chinese where specified. Use exactly 8 side stat cards and exactly 6 bottom timeline milestones. Do not add logos, club badges, brand marks, watermarks, or extra people. The central player must dominate the composition, with the ball breaking toward the viewer in the lower right foreground.

Transform each uploaded photo into a standalone high-end design poster. Use a 3:4 vertical composition split 1:1 into two sections. The top half retains the original photo with high-end color grading to give it an art magazine or exhibition feel. The bottom half extracts the most recognizable {argument name="core elements" default="subject, silhouette, structure, pose, and narrative"} and reconstructs them into a {argument name="art style" default="geometric and flat"} artistic expression. Use simple shapes, flat blocks, clean outlines, and white space, compressing complex info into key visual elements that remain recognizable as the subject above. The composition of the lower half should emphasize order, visual weight, and balance. Use off-white or light matching backgrounds with ample white space. Colors should be extracted from the photo and transformed into a {argument name="color mood" default="humanistic and healing"} palette—bright, pure, soft, and warm. Add minimal text for titles or annotations in a refined editorial style. The overall look should be sophisticated, modern, and elegant, avoiding cheap filters or cartoonish effects.

A candid smartphone mirror selfie in a moody upscale restroom with deep {argument name="wall color" default="crimson red"} textured walls and a large round mirror with a thin black frame dominating the composition. A {argument name="subject" default="young woman"} with long {argument name="hair color" default="dark brown"} wavy hair stands slightly off-center, leaning her torso forward and to the side in a relaxed confident pose, one hand holding the phone in front of her face and the other braced on a dark stone or marble countertop. She wears a fitted black off-shoulder long-sleeve top with a sweetheart neckline and high-waisted charcoal or black jeans, with a black shoulder bag tucked under one arm. The phone flash is extremely bright, fully obscuring the face and creating a sharp starburst plus 1 strong horizontal blue-white lens flare streak across the image, with subtle bloom and realistic smartphone exposure clipping. Behind her is a dark wooden paneled door centered in the reflection. The room includes 2 tall cylindrical wall sconces with warm glowing bulbs, one on each side near the mirror edges, 1 small gold-toned light switch plate on the left wall, 1 curved brushed-metal faucet visible at the bottom center, and 2 small candle holders or votive lights at the lower right edge. Style is authentic phone-camera photography, slightly grainy, warm low-light ambience, realistic reflections, minor sensor noise, natural shadows, intimate nightlife restroom aesthetic, vertical portrait framing.

Input an article, go through three rounds of Q&A, and it directly outputs cover prompts that can be used for image generation. No need to understand design, no need to write prompts yourself, the aspect ratio is fixed at 3:4, and facial consistency can be maintained.👇 👹 The entire workflow is as follows: 1. Skill installation and first-time configuration (save a photo of your own face + confirm the image generation model) 2. Give the article content to the agent, which automatically reads and refines it 3. Round 1: Recommend composition styles based on content (10 options to choose from) + automatically come up with candidate titles 4. Round 2: Face reference images + materials such as UI screenshots/product images 5. Round 3: Choose expressions, background tones, fonts, and font colors all at once, or leave it all to the model if you're lazy 6. Output complete prompts: 3:4 composition, safety zone, multi-reference image writing for Image 1 (face) + Image 2 (materials) are all included 7. Take it to Jimeng / Nano Banana / GPT-Image to generate images (if your agent has an image generation API configured, you can have it generate directly in the conversation) 8. Check if the titles have typos, and regenerate any parts you're unhappy with. 🧐 Tips: You must choose an image generation model that supports multiple reference images, otherwise facial consistency cannot be guaranteed. The skill has 8 built-in sets of example prompts reverse-engineered from real trending covers, and the model will automatically use them as references, pushing the image detail to the maximum.

{ "type": "social media short video app interface mockup", "main_image": { "subject": "{argument name=\"subject description\" default=\"young Asian woman with long dark hair wearing a white off-the-shoulder top\"}", "pose": "looking back over her shoulder at the camera, gentle smile, hair blowing slightly in the wind", "setting": "{argument name=\"background location\" default=\"riverside promenade at sunset with a tall modern tower and city skyline\"}", "lighting": "golden hour, warm sunlight reflecting on the river" }, "ui_layout": { "top_bar": { "status_icons": ["time 9:41", "cellular signal", "wifi", "battery 100"], "navigation": { "left": "menu icon", "center_tabs": ["经验", "团购", "关注", "{argument name=\"active top tab\" default=\"推荐\"}"], "right": "search icon" } }, "right_sidebar": { "count": 6, "elements": [ "profile picture with pink plus button", "heart icon with text '23.6万'", "chat bubble icon with text '1.6万'", "star icon with text '2.8万'", "share arrow icon with text '3.7万'", "spinning music record icon" ] }, "bottom_left_overlay": { "username": "{argument name=\"username\" default=\"@小鹿的日常\"}", "caption": "{argument name=\"caption text\" default=\"吹着晚风，看着日落，这一刻好治愈~ 🌅\"}", "audio_track": "🎵 原声 @小鹿的日常创作的原声" }, "bottom_navigation_bar": { "count": 5, "tabs": [ "首页", "朋友 (with red badge '2')", "central plus button in rounded square", "消息 (with red badge '5')", "我" ] } } }

Create a photorealistic vertical portrait of {argument name="subject" default="a young East Asian woman"} sitting beside a bright sunlit window in a soft, airy room. She has {argument name="hair color and style" default="long straight dark brown hair with a center part, falling over one shoulder"}, fair skin, a slim build, and wears {argument name="outfit" default="a simple off-white camisole with thin straps"} plus a small gold hoop earring visible on one ear. Frame her from the upper torso upward in a close, intimate composition, angled slightly from above and to the side, with her shoulder and collarbone catching warm natural light. Her face is intentionally obscured by one large opaque square censor block centered over the face, colored with a soft brown-to-taupe muted gradient, covering the eyes, nose, and mouth while leaving the hair, ear, neck, shoulder, and clothing visible. The background should be softly blurred with white window frames, pale curtains, hints of greenery, and bright morning sunlight, using shallow depth of field, realistic skin texture, glossy hair highlights, natural shadows, and a clean lifestyle photography aesthetic. Use {argument name="lighting" default="warm natural window light with gentle backlighting"} and a high-resolution camera look, vertical 2:3 aspect ratio.

Turn this photo into a funny ugly doodle drawing. Make it look like: a quick sketch using a {argument name="tool" default="cheap marker or crayon"} messy, rough, childlike style bad perspective and awkward proportions slightly exaggerated facial features Add: {argument name="background" default="simple cartoon background (like buildings, trees, street)"} random sketchy lines and details uneven coloring and visible strokes Style: looks like a lazy drawing, not polished humorous and a bit stupid-looking meme-like, casual, internet style Do NOT: make it realistic

Goal: Create a realistic fashion magazine studio shot with an AI toy-catalog feeling: a life-size small figurine-like female model posed on a giant receipt prop, with glitch typography and editorial graphic design. Canvas: Square 1:1 image, clean off-white studio background, high-key soft lighting, subtle shadows, premium magazine cover composition. Subject: A young woman with {argument name="hair color" default="long wavy black hair"}, face deliberately obscured by a soft rectangular blur for anonymity. She is kneeling and leaning forward on both hands, angled three-quarters toward camera, wearing an oversized black leather jacket slipped off one shoulder, a white camisole, layered silver necklaces, black shorts, a white ruffled pleated skirt detail, and black knee-high boots. Add a small black textured handbag with chain hardware near her right side. Her pose should feel like a glossy studio fashion shoot but slightly surreal, as if she is a collectible human figurine. Main props and counted elements: Include exactly 3 main physical props: 1 oversized receipt-shaped floor mat under the model, 1 black-and-white checkerboard pillow behind her left arm, and 1 small black handbag near her right knee. The giant receipt mat must contain barcode graphics, itemized receipt typography, totals, and small editorial notes. Layout: Place the model on the right two-thirds of the frame, crouched over the receipt mat. Reserve the left third for bold editorial text and glitch graphics. Keep the background minimal and creamy white. Add small registration-cross marks in the corners and along the left side for a print-layout feel. Text content: Large headline on the left: {argument name="headline text" default="GLITCH ANGEL"}, in huge black condensed uppercase letters with cyan/red RGB offset, horizontal glitch smears, and distressed pixel edges. Under it, a black strip subtitle: {argument name="subtitle text" default="beauty in static"}. Top-left small copy: "BEAUTY IS NOT PERFECT. IT'S REAL WHEN THE SIGNAL BREAKS." Mid-left italic copy: "signal break / emotion remains". Lower-left stacked copy: "A MOMENT BETWEEN NOISE AND SILENCE." then "//2026" then "EDITORIAL SERIES". Bottom-left tiny copy: "THIS ISN'T A PORTRAIT. IT'S A FREQUENCY." Add two short horizontal glitch bars on the left, exactly 2 bars. Receipt text details: On the oversized receipt mat, include readable typewriter-like receipt lines such as "ITEM RECEIPT", "Family business", "TOTAL", "CASH RECEIVED", "CHANGE", a wide barcode, "THANK YOU FOR YOUR ENERGY", "NOTES: BEAUTY IS DATA. EMOTION IS SIGNAL. YOU ARE THE GLITCH.", "NO RETURNS ON FEELINGS", plus an itemized table with exactly 4 rows: "SUBTOTAL 599.00", "STUDIO FEE 401.00", "CREATIVE DIR. 1,000.00", and "LIGHT SETUP 0.90". Visual style: Photorealistic editorial studio photography mixed with graphic design overlay, soft film grain, muted black/white palette, slight cyan and magenta chromatic glitch accents, crisp textile details, realistic leather shine, realistic receipt print texture. The model should look real, but the composition should feel like a staged toy catalog or magazine spread. Constraints: Use exactly 1 human subject, exactly 3 main physical props, exactly 2 left-side glitch bars, and exactly 4 receipt item rows. No extra people, no watermark, no logo, no raw UI elements. Keep the face blurred and unrecognizable.

A young woman around {argument name="age" default="22 years old"} taking a selfie in a {argument name="setting" default="bright, light-colored bathroom"}. She has {argument name="hair color" default="dark brown"} long wet hair with natural water droplets and a draped feel, wrapped in a clean white towel. Standing in a natural side profile, she holds her phone in front of her with one hand while the other gently touches her hair, looking into the camera with a relaxed expression. The space features off-white and light gray tiled walls, with a glass shower area blurred in the background. Minimalist bathroom fixtures are neatly arranged, with soft side lighting, low contrast, and a realistic home photography texture. No text, no watermark.

{argument name="subject" default="A beautiful internet celebrity"} is live-streaming a {argument name="activity" default="game"}.

Create a dynamic vertical anime action illustration of a {argument name="character type" default="pink-haired gothic lolita maid girl"} performing an acrobatic one-handed breakdance handstand kick inside a grand European palace ballroom. The camera is extremely low near the polished marble floor, looking upward with dramatic foreshortening: one booted leg thrusts close to the viewer and is heavily motion-blurred, the other leg extends backward, while one hand presses on the reflective floor and the character looks toward the viewer with a confident fierce expression. She has long flowing {argument name="hair color" default="rose pink"} twin-tail hair whipping through the air, green eyes, frilly white maid headband, and an ornate {argument name="outfit color" default="deep emerald green"} gothic lolita maid dress with puff sleeves, ruffled white lace trim, corset-like bodice, bows, layered skirt, stockings, and lace-up heeled boots. Add bright white circular speed trails and arcing wind ribbons around her spinning body to emphasize high-speed action. The environment is a luxurious sunlit ballroom with tall arched windows on both sides, gilded wall details, high ceiling, chandeliers, dust motes, shafts of light, and glossy patterned marble reflections. Use cinematic lighting, extreme perspective, intense motion blur, sharp focus on the face and supporting hand, detailed fabric folds and lace, elegant fantasy anime rendering, high detail, vertical composition, dramatic action energy, no text, no watermark.

The background has a {argument name="background color" default="light pure beige"} frosted glass texture, in a minimalist style.

A realistic corporate office photo of a young man seated indoors, holding up a printed research paper toward the camera with both hands. His face is fully obscured by a solid rectangular censor block in a medium tan color. He has short dark brown hair and wears a plain dark charcoal crewneck sweater. The paper is a white letter-size document in portrait orientation, clearly visible and centered in front of his torso. The document title reads “DFlash: A High-Speed, Low-Latency, and High-Endurance Flash Memory Technology for Next-Generation Storage Systems”. Below it are the author lines “DFlash Research Team” and “DFlash Inc.” The page shows 4 visible text sections: “Abstract”, “1. Introduction”, “2. DFlash Technology Overview”, and “2.1 Dual Charge-Trapping Architecture”, set in a formal academic paper layout with dense black serif text. In the background, place a softly blurred modern office lobby with warm ambient lighting, beige walls, glass partitions, a sofa, indoor plants, and the black OpenAI logo and wordmark mounted on the wall at upper left. The composition is a medium shot, straight-on, with the subject slightly right of center so the OpenAI logo remains visible. Shallow depth of field, soft natural office lighting, polished photorealistic style, subtle warm color grading, high detail in the hands, paper, sweater texture, and interior environment. Keep the overall image clean, believable, and like a candid press or announcement photo. Use {argument name="document title" default="DFlash: A High-Speed, Low-Latency, and High-Endurance Flash Memory Technology for Next-Generation Storage Systems"} for the paper title, {argument name="company logo text" default="OpenAI"} for the wall branding, {argument name="sweater color" default="dark charcoal"} for the subject’s clothing, and {argument name="censor block color" default="medium tan"} for the face covering.

Goal: Create a vertical 2:3 commemorative fantasy character visual packed with cute character motifs, like an ornate anime merchandise celebration illustration. Canvas: Portrait 2:3 composition, bright pastel blue sky with soft white clouds, sparkling light effects, glassy reflections, and a delicate lace-and-crystal border around all four edges. Main subject: Center a petite anime girl sitting on top of a huge transparent faceted glass jar. Her face is intentionally covered by a centered pale lavender square censor block. She has very long flowing {argument name="hair color" default="silvery white with pale blue tint"} hair styled into twin tails or long side sections, decorated with blue gingham ribbons, small blue flowers, pearls, and strawberry ornaments. Her pose is front-facing, legs dangling down, hands resting lightly to each side, graceful and doll-like. Outfit: A lavish sweet-lolita dress in {argument name="image color palette" default="sky blue, white, blush pink, crystal clear, and strawberry red"}. Include puff sleeves, layered ruffles, lace trim, blue gingham panels, tiny bows, pearl chains, berry and flower embroidery, a corset-like bodice, and a short tiered skirt. Add white thigh-high stockings with blue bows, platform Mary Jane shoes decorated with strawberries, flowers, pearls, and blue ribbon ties. Central prop: The girl sits on a large transparent glass candy jar with a thick lid rim under her skirt and a faceted base. Inside the jar, show many miniature concept items: blue and white flowers, strawberries, pearls, tiny ribbons, crystal pieces, a small teacup or cake-like ornament, heart charms, and pastel sweets. On the jar front, place an ornate gold-and-blue heart jewel brooch. Balloons: Include exactly 12 visible balloons behind and around the character: 2 pink heart balloons, 2 blue heart balloons, 4 round blue balloons, and 4 transparent iridescent round balloons filled with tiny strawberries, flowers, and confetti. Tie them with fine strings and blue bows so they frame the girl like a celebration bouquet. Surrounding objects: Add exactly 8 major decorative gift/display objects around the base: 1 blue-and-white wrapped gift box on the lower left, 1 crystal perfume-bottle-like ornament on the lower left, 1 faceted blue heart crystal ornament on the far lower left, 1 hanging gift tag on the jar reading {argument name="gift tag text" default="Present for you"}, 1 ornate framed strawberry illustration on the lower right, 1 blue glass bottle or vial on the far lower right, 1 small envelope/card with strawberry art on the lower right, and 1 loose strawberry near the bottom edge. Add scattered pearls, small flowers, lace paper, and tiny gems on the reflective floor. Style: Extremely detailed Japanese anime illustration, dreamy shoujo aesthetic, watercolor-like pastel rendering, transparent glass effects, iridescent highlights, fine line art, luminous sparkles, ornate lace, ribbons, pearls, and crystalline decorations. The mood should be {argument name="mood" default="sweet, celebratory, ethereal, and precious"}. Text: Keep the visible English tag text “Present for you” in elegant cursive. Optional faint decorative script on the left may read {argument name="small signature text" default="Dream Garden"}. Avoid adding any other readable text. Constraints: Vertical 2:3 ratio, centered symmetrical composition, no dark colors, no modern UI elements, no photorealism, no extra characters, keep the face covered by the simple square block, and make every accessory feel tied to strawberries, blue flowers, glass crystals, gifts, and ribbons.

Top-down aesthetic food photography of a cozy meal setup on a beige table, featuring a plate of beef teriyaki with glossy sauce, scrambled eggs, and a perfectly shaped mound of white rice with herbs on top. A tall glass of iced lemon tea with lemon slices sits beside it. Soft warm lighting, minimal shadows, pastel tones. Cute hand-drawn doodles, white handwritten text annotations, and kawaii-style food characters scattered around. Lifestyle composition with a phone and keys subtly placed. Instagram-style, cozy ‘comfort food happy mood’ vibe, high detail, soft focus, clean composition. Top-down cafe table scene with multiple comfort foods: crispy fried chicken cutlet with fries and dipping sauce, omelette with fries, and a slice of cheesecake on a white plate. Two green takeaway cups with straws on the side. Casual dining setup with visible legs under the table. Neutral color palette with warm tones. Decorated with cute white doodles, playful handwritten text, and small cartoon food characters. Soft natural lighting, cozy and cheerful ‘good food good mood’ aesthetic, social media friendly composition, high resolution, minimal shadows.

{"type":"infographic","style":"clean, corporate, flat design, pastel accents, dark blue primary color","header":{"logo":"swirl icon","academy_name":"{argument name=\"academy name\" default=\"OpenAI Academy\"}","main_title":"{argument name=\"main title\" default=\"ChatGPTで画像を作る・直すための実践ガイド\"}","metadata":"date and page info","summary_box":{"title":"要点","content":"paragraph about key points"}},"layout":{"sections":[{"number":1,"title":"{argument name=\"section 1 title\" default=\"よい画像プロンプトの書き方\"}","layout":"two columns","left_column":{"count":6,"items":[{"icon":"target","label":"目的を明確に"},{"icon":"landscape","label":"主題・状況・場所を指定"},{"icon":"brush","label":"スタイル・雰囲気を指定"},{"icon":"sun","label":"光・質感・構図を指定"},{"icon":"prohibition","label":"制約・除外事項を明記"},{"icon":"pencil","label":"編集時は変更点と維持点を明確に"}]},"right_column":{"box_title":"良いプロンプト例","image":"{argument name=\"example image subject\" default=\"white mug on a wooden desk\"}"}},{"number":2,"title":"結果をよくするための段階的な修正","cards":{"count":4,"items":[{"icon":"sun","label":"明るさを調整"},{"icon":"palette","label":"色味を調整"},{"icon":"landscape","label":"背景を調整"},{"icon":"crop","label":"構図を維持"}]},"bottom_banner":"lightbulb icon with text"},{"number":3,"title":"少し踏み込んだ使い方","list":{"count":3,"items":[{"icon":"multiple images","label":"複数画像の活用"},{"icon":"text 'Te'","label":"画像内テキスト"},{"icon":"pie chart","label":"インフォグラフィック・図解"}]},"example_box":{"title":"テキスト指定の例","graphic":"green box with 'SPRING SALE'"}},{"number":4,"title":"追加の注意点","items":{"count":4,"items":[{"icon":"person","label":"実在人物の生成"},{"icon":"shield","label":"ブランド・作品名の使用"},{"icon":"id card","label":"クレジット表記"},{"icon":"checklist","label":"ポリシー遵守"}]}}],"footer":{"style":"dark blue banner","text":"{argument name=\"footer summary\" default=\"まとめ: 目的と制約を具体的に伝え、段階的に修正を重ねることで、より良い画像を生成できます。\"}"}}}

{ "type": "infographic", "style": "clean, corporate, flat design, soft pastel colors, rounded corners, white background", "header": { "main_title": "{argument name=\"main title\" default=\"ChatGPTで画像を作るコツ\"}", "subtitle": "{argument name=\"subtitle\" default=\"良いプロンプトの書き方と、効果的な修正方法（2026年4月10日公開の要点）\"}", "top_right_badge": "OpenAI Academy / Creating images with ChatGPT" }, "layout": { "columns": [ { "color_theme": "blue", "header": "{argument name=\"column 1 title\" default=\"1 良いプロンプトの書き方 (1〜3文で簡潔に)\"}", "item_count": 5, "icons": ["target", "landscape picture", "map pin", "paintbrush", "sliders"] }, { "color_theme": "green", "header": "{argument name=\"column 2 title\" default=\"2 結果をよくする修正のコツ\"}", "item_count": 4, "icons": ["checkmark", "checkmark", "checkmark", "A/B comparison"] }, { "color_theme": "orange", "header": "3 少し高度な使い方", "item_count": 4, "icons": ["multiple images", "letter T", "bar chart", "magic wand"] }, { "color_theme": "purple", "header": "4 注意点", "item_count": 4, "icons": ["shield with check", "star", "document with check", "gavel"] } ], "footer": { "left_section": { "title": "{argument name=\"bottom left title\" default=\"プロンプト例 (1〜3文)\"}", "item_count": 3, "thumbnails": ["orange tabby cat", "coffee cup on white background", "blue bar chart"] }, "right_section": { "title": "ワークフロー", "step_count": 4, "icons": ["upload arrow", "sparkles", "A/B boxes", "checkmark"], "flow_style": "horizontal with dashed arrows" } } } }

Generate a {argument name="newspaper name" default="certain newspaper"} front page. Based on this photo, create a front-page headline; should look like real photography with a vintage texture.

Goal: Create a highly polished pastel product advertisement photo for a fictional gashapon toy line featuring {argument name="character name" default="NOZOMU"}, designed like a collectible capsule figure display. Canvas: Square 1:1 image, high-resolution commercial product photography with soft studio lighting, shallow depth of field, glossy reflections, and a cute teal, white, lavender, and pale pink palette. Main subject: Center foreground shows one chibi anime capsule figure standing on a transparent round display base labeled “NOZOMU.” The figure is a small girl with long dark teal hair, large teal eyes, a cheerful open-mouth smile, and a white bear-ear hoodie with teal bear ears. She wears a teal oversized jacket over a white frilly dress, teal ribbons, tiny bear charms, white socks, and white sneakers. Her right hand lifts the edge of the hood, and her left arm is slightly out to the side. The base is clear acrylic with teal trim, decorative white scrollwork, a small bow motif, and the character name on the front. Background and props: Place the figure in front of a transparent capsule vending machine filled with pastel capsules. Include exactly 9 visible capsule balls: 3 teal capsules, 2 lavender capsules, 2 white capsules, 1 pale blue capsule, and 1 pale pink capsule. The machine has a teal coin panel and a white dial, with small Japanese-style coin-insertion signage. On the right foreground, place exactly 2 large empty transparent capsule halves, slightly open and reflective. On the lower left, place exactly 1 mini brochure/card showing the same character artwork and the text “NOZOMU Mini Collection.” On the lower right, place exactly 1 clear plastic accessory bag containing small teal-and-white toy parts: a tiny bear-face charm, teal ribbon-like pieces, and small white accessories. Left vending-machine sign: Add a rounded white sign with teal text at upper left. It must read “NOZOMU” in large letters, then “Capsule Figure” and “Mini Collection.” Include two teal rounded labels: one says “全5種” and one says “1回 400円.” Decorate the sign with small pale stars and soft pastel shapes. Right collection board: Add a large rectangular collection lineup board on the right side with teal border and rounded corners. Header reads “NOZOMU Mini Collection” with a small teal badge reading “全5種.” The board displays exactly 5 variants in a 2-row grid: 1) “Standard” standing pose, 2) “Smile” winking/smiling pose, 3) “Sitting Pose” standing or seated variant image, 4) “Special Color” gray-toned seated version with a pink “New” sticker, and 5) “Secret” as a dark bear-eared silhouette with a white question mark and a small “Premium Rare” badge. Make the labels small but legible, matching the product mockup style. Visual style: Cute Japanese collectible toy aesthetic, realistic miniature figure material, glossy plastic capsules, pastel teal branding, clean merchandising layout, bokeh highlights, soft shadows, premium catalog photography, detailed anime face and hair sculpt, realistic acrylic reflections. Constraints: Use exactly one main figure on the central base, exactly one lineup board with five variant entries, exactly one left price/collection sign, exactly one brochure, exactly one accessory bag, exactly two open capsule halves, and exactly nine filled capsules in the machine. Keep all text crisp and integrated into the product design. Do not add extra characters, logos, watermarks, or unrelated objects.