Prompty Obraz dla App Web Design

Create a square 1:1 pixel-art logo on a clean white background. At the top, place a large two-line Japanese title in chunky 8-bit block lettering reading {argument name="logo text" default="スタジオ直紬"}; the first line is smaller and reads “スタジオ”, the second line is much larger and reads “直紬”. Use a bright cyan-to-mint gradient fill with a very thick dark navy pixelated outline and squared corners, like retro game title typography. Centered below the title, draw one chibi anime mascot head and shoulders in crisp pixel art: a cute surprised character with {argument name="hair color" default="dark navy black"} messy hair, long side locks, a high side ponytail sweeping to the right, teal hair highlights, big cyan-blue eyes, red rectangular glasses, a small open pink mouth, pale skin, and oversized black headphones with cyan ear pads around the neck. Add mint-green accent shapes in the hair and beside the face, including a ribbon-like teal shape on the right. The character should look upward with an excited, surprised expression. Use a limited palette of dark navy outlines, cyan, turquoise, mint, white, pale peach, and red glasses. Keep the entire image sharp, low-resolution, and intentionally pixelated with no antialiasing, no shadows, and no photorealism. Count and place the decorative background pixels exactly: 2 mint four-point sparkle icons, one on the left side of the character and one on the right side; and 5 small mint square pixels scattered around the character, with one upper-left, one mid-left, one lower-left, one mid-right, and one lower-right. Maintain generous white margins and a centered sticker-like composition.

主题方向：{argument name="主题方向" default="东方禅意极简封面海报"} 风格分支：女性审美高对比型 主体内容：一位女子站在极简花器旁，轻轻整理一枝花 情绪母题：精致、明亮、轻奢东方感 场景与意象：白色空间、{argument name="花朵颜色" default="葡萄紫"}花朵、青柠绿叶片、白瓷花器、女子 构图与空间：9:16 竖版构图，花器与人物位于下半部分偏一侧，上方保留完整白色标题区，花枝形成第一视觉点 色彩控制：纯白或奶油白作为高明度基底，{argument name="花朵颜色" default="葡萄紫"}只用于花朵，青柠绿用于叶片，花器保持白色或浅米色，人物服装用浅暖白；避免紫绿污染整张画面 光线与质感：明亮柔光，轮廓清晰，干净平面海报质感 画幅比例：9:16 补充要求：颜色要鲜明现代，整体高级精致，适合女性审美封面

Using the provided reference image as the base screenshot, update the chat UI to show a later point in the same LINE sticker creation workflow rather than the initial setup. Keep the overall desktop layout, left sidebar, chat app framing, and right-side remote-screen panel consistent, but replace the chat contents with progress/status messages about regenerating stickers and checking transparency. Add exactly 1 failed/unfinished sticker preview near the upper-middle of the chat: a mostly blank white square with only tiny cat facial marks and two orange emphasis strokes, implying the character disappeared. Add exactly 3 completed sticker thumbnails in a row near the bottom of the chat, all based on the same fluffy cat from the reference materials, with transparent/white sticker-style backgrounds and colorful Japanese LINE-sticker lettering: 1) {argument name="first sticker text" default="ありがとう"} with the cat sitting cutely, 2) {argument name="second sticker text" default="こんにちは"} with the cat smiling and waving/posing, 3) {argument name="third sticker text" default="爆笑"} with the cat laughing energetically. Use a playful sticker aesthetic with thick outlined text, small comic accent marks, and clean cutout edges. On the right-side remote panel, replace the file-browser view with a dark reconnection screen showing centered Japanese text {argument name="connection status text" default="再接続しています..."} and a small cancel button beneath it. Preserve the sense that this is a live AI-agent chat screenshot documenting automatic sticker generation, not a standalone sticker sheet.

Goal: Create a photorealistic hero section mockup for a cute Harajuku smoothie brand website, focused on {argument name="flavor" default="Strawberry"}. Canvas: Wide 16:9 web landing page, 1200×750 style composition, full-bleed soft bubblegum-pink background with a fluffy white-pink cloud layer along the bottom third. Use a glossy Japanese pop commercial style mixing realistic photography, oversized typography, and playful fruit graphics. Layout: Top navigation bar with the dark teal “do smoothie” logo at top left, three small Japanese nav links centered across the top, and a dark teal rounded coupon button at top right with a pale yellow square arrow segment. Behind everything, place one huge cream-white uppercase word “STRAWBERRY” spanning almost the full width, cropped slightly by the page edges. Center foreground features a smiling young Japanese woman standing in front of the giant word, with floating strawberries around her and a large strawberry smoothie cup near her feet. Left side contains the product copy block. Bottom left contains exactly 2 circular outline arrow buttons: one pointing left and one pointing right. Bottom center contains exactly 4 flavor tabs labeled Strawberry, Mango, Kiwi, Banana, with Strawberry underlined/active. Bottom right contains small microcopy and a large “ALL FLAVORS” link with an arrow. Main subject: A cheerful young Japanese woman, full body, realistic photo cutout, standing slightly right of center. She has long wavy dark brown hair with bangs and small strawberry hair accessories, a bright friendly smile, and a cute idol-like pose with one palm raised. Outfit: red pinafore mini dress with white strawberry-seed dots, white puff-sleeve blouse, white socks with frills, and shiny red platform Mary Jane shoes. Make her crisp and sharply focused. Objects and counted elements: Include exactly 6 floating strawberries around the main subject: two near her upper body, one by her raised hand, one at mid-right, one lower-left near the smoothie cup, and one lower-right near her skirt. Include exactly 1 large transparent plastic smoothie cup in the foreground, filled with pink strawberry smoothie texture, domed lid, straw, condensation, and the “do smoothie” logo printed in dark teal. Include exactly 2 blurred background character/photo cutouts: one on the left in a pale pink/white outfit with banana graphics and a drink, and one on the right in an orange outfit with mango graphics and a drink; keep both smaller, dreamy, and out of focus to emphasize the central strawberry character. Text content: Use Japanese text in the UI where visible. Logo: “do smoothie”. Top nav links: “フレーバー”, “お店について”, “アクセス”. Top button: “クーポンをゲット” plus arrow. Huge headline: “STRAWBERRY”. Left copy block: “今日は何色の気分？” then “doちゃんと選ぶ4つのスムージー。” then “01 — SWEET & LOVELY” then “Strawberry” then “ストロベリー” then “甘いものがほしい日。” Bottom right microcopy: “HARAJUKU FRUIT CLUB — SCROLL TO TASTE !” Large link: “ALL FLAVORS” with arrow, and small Japanese line “すべての味を見る”. Visual style: High-end photorealistic ad composite, soft studio lighting, pastel pink gradient, creamy white typography, dark teal accents, shallow depth of field for background characters, clean modern web design spacing, playful floating fruit, polished commercial realism. Constraints: Keep all text legible and aligned like a real website hero page. Do not add extra navigation items, extra characters, or extra flavor tabs. Avoid watermarks, browser chrome, mobile UI, or visible generation artifacts. Use {argument name="brand name" default="do smoothie"} branding consistently, a {argument name="primary color" default="bubblegum pink"} background, and a {argument name="model style" default="photorealistic Japanese idol commercial model"} central character.

Goal: Create a clean social-media screenshot of an AI image generation interface showing a completed anime music-video storyboard request and its 3x3 output grid. Canvas: Horizontal screenshot, approximately 1200x884 px, white/light-gray background with lots of empty margin. Use a modern minimal web-app UI style with rounded cards, soft shadows, and gray system text. Top area: Near the upper center, show one rectangular reference image preview with a subtle shadow. The preview contains an anime character: a short-haired androgynous young person with {argument name="hair color" default="dark ash-brown bob haircut with straight bangs"}, pale skin, thin round glasses, one eye closed in a wink, one blue visible eye, wearing a white high-collar ceremonial robe with necklaces and a red tassel. Behind them is a dark fantasy cathedral city with a glowing golden circular arch and a blue vortex moon-like sky. Prompt bubble: Below the preview, place a wide black rounded speech bubble with white Japanese text, reading exactly {argument name="prompt text" default="このキャラクターのボカロmvの様々なカットを3x3で出力して 16:9　トンマナ合わせて"}. The bubble should span most of the center width and have large rounded corners. Status text: Under the bubble, aligned left above the output grid, add gray text reading {argument name="status text" default="Worked for 1m 7s"}. Output grid: Show exactly 9 cinematic panels arranged in a 3 columns by 3 rows grid, inside one large rounded rectangle with clipped rounded corners. Each panel is 16:9, separated by thin white grid lines, all sharing the same tone: dark blue, black, white, and warm gold, glossy anime/Vocaloid MV aesthetic, dramatic lighting, cathedral ruins, floating feathers or sparkles, wet reflective floor, glowing golden ring, blue vortex sky. The 9 panels are: 1. Top-left: frontal bust shot of the character under the glowing golden arch, calm expression, glasses, white robe. 2. Top-center: side-profile close-up with hair blowing, eyes closed, blue lights in the dark cathedral background. 3. Top-right: dynamic three-quarter shot, character extending a white sleeve toward the viewer, golden arch and blue vortex behind. 4. Middle-left: low-angle wide shot, character leaning or reaching forward with billowing white sleeves, cathedral towers around them. 5. Middle-center: full-body centered shot standing on a reflective wet floor, framed by a tall archway and distant glowing ring. 6. Middle-right: close shot of character reaching a hand toward the camera, one eye closed, foreshortened hand in foreground. 7. Bottom-left: rear wide shot of the character walking into the cathedral environment beneath the glowing arch. 8. Bottom-center: emotional close-up, character with eyes closed and hands near mouth or chest, surrounded by blue sparkles. 9. Bottom-right: very wide establishing shot of ruined gothic towers, glowing circular arch, blue vortex sky, tiny figure or distant character. Overlay controls: Add exactly 3 circular interface controls over the lower part of the grid: a dark circular button at bottom-left labeled {argument name="edit button text" default="編集"}, a light gray circular download button with a downward arrow near the lower center-right, and a dark circular share button with an upward arrow at bottom-right. Style constraints: The whole image should look like a real captured web UI, not a poster. Keep the interface text crisp, the grid slightly cropped by the bottom edge of the screenshot, and the anime panels high-detail, cinematic, consistent in character design and color grading.

"{argument name="platform" default="Douyin"} 直播界面，两位中国女性网红正在进行分屏直播。"

Goal: Create a retro 2D vertical arcade game title screen for a rail shooter called {argument name="game title" default="GALAXY RAIL"}, with a space-and-railroad theme and Japanese UI text. Canvas: Portrait mobile game splash screen, 9:16 aspect ratio, pixel-art inspired but clean vector-like illustration, dark navy outer-space background filled with many small white and pale yellow stars. Layout: Center the title in the upper-middle. Place a large partially cropped Earth-like blue planet on the left behind the title, occupying about one third of the image height, with simple green landmasses and translucent cloud streaks. Add exactly 3 vertical railroad tracks running from top to bottom: one left track partly over the planet, one center track, and one right track; each track has gray rails and many brown sleepers. Put exactly 2 small train/player cars on the lower center track, stacked vertically with rounded white bodies, blue windows, yellow outlines, and a yellow headlight on the top car. Text content: Main title text is two lines: “GALAXY” in large white slab-serif letters with a dark navy outline, and “RAIL” below in large golden yellow slab-serif letters with a dark navy outline. Under the title, show the Japanese tagline {argument name="tagline" default="銀河を、レールで切り拓く"} in bright cyan. Beneath it, add small gray feature text: “RAIL SHOOTER / 2D VERTICAL / 3 STAGES”. In the lower third, add a translucent dark blue rectangular instruction panel with a thin blue border. Inside the panel, show three Japanese instruction lines: “←→↑↓ / WASD：移動（レールから自動ジャンプ）”, “Z / SPACE：短押し＝単発 / 長押し＝2連射”, and “時間経過で最寄りのレールへ強制着地”. Below the panel, add a small red warning line: “赤いサークル＝瞬着攻撃の予兆。収束前に発生源を倒せ！” At the very bottom, centered, show pale gray prompt text: {argument name="start prompt" default="PRESS Z SPACE OR CLICK TO START"}. Visual style: Retro arcade title screen, simple 2D game mockup, crisp shapes, slightly pixelated typography, high contrast, deep-space palette of navy, white, cyan, yellow, gray, and red. The composition should feel like a vertical rail shooter prototype splash screen. Constraints: Use exactly 3 full-height vertical tracks, exactly 2 train cars, one planet on the left, one instruction panel, and no characters or extra UI windows. Keep all text legible and centered, with no logos or watermarks.

Goal: Create an ornate luxury travel landing page concept for a hot-air-balloon sunrise journey, with a romantic Chinese tourism-brand aesthetic and a cinematic fantasy landscape. Canvas: Wide desktop website hero mockup, 16:9 ratio, polished high-end UI design. Use a warm dawn palette of lavender, blush pink, amber gold, cream, and deep plum, with delicate gold linework and vintage travel-poster ornamentation. Layout: Full-screen hero page with a huge scenic background and overlaid navigation, headline, CTA, booking panel, and bottom itinerary links. The composition should feel like a premium travel agency website for {argument name="travel brand" default="逐光之旅 / Chasing Dawn"}. Hero background: A vast sunrise landscape over a Cappadocia-like stone valley and distant town, soft fog in the canyons, jagged pale rock formations, small towers and stone houses, the sun low on the right horizon. Include exactly 8 visible hot-air balloons: 1 enormous ornate balloon dominating the left foreground with a basket carrying tiny silhouettes, 1 medium balloon near the upper center-right, 1 smaller balloon near center, 1 medium balloon lower right of center, and 4 tiny distant balloons scattered near the horizon. The largest balloon has cream fabric covered in elaborate gold and violet floral filigree, with readable English text on the fabric: “A BRIGHTER JOURNEY A KINDER YOU”. Decorative frame details: On the far left, show a stone arch or wall covered with climbing vines and purple flowers. On the lower right, show flowering vines and an antique lantern. Add subtle gold flourishes in the corners and thin ornamental divider lines, giving the whole site a handcrafted travel-journal feel. Top navigation: Place a centered logo/title area at the top reading “逐光之旅” with small English subtitle “CHASING DAWN”. Add exactly 4 top navigation links across the header: “自由旅程”, “峡谷漫行”, “旅途手记”, plus the central brand title. Add a circular search icon and a hamburger menu icon at the top right. Main hero text: On the right side, large elegant Chinese headline text reading {argument name="headline text" default="追着日出\n升空"}, in dark plum calligraphy-style serif typography. Under it, place the subtitle “让清晨的第一束光，带你看更远。” Add a rounded dark-plum CTA button with gold border reading {argument name="button text" default="开启逐光旅程 ↗"}. Left side microcopy: Along the left vertical wall, add small poetic text blocks including “更远的世界 / 总有一束光 / 在等你”, “TRAVEL / LIGHTER / LIVE BRIGHTER”, and “PLACES / PEOPLE / BRIGHTER / YOU”, set in tiny refined lettering. Booking search panel: Across the lower third, create a large cream-colored rounded rectangular booking card with gold border and drop shadow. It contains exactly 4 sections from left to right: 1) decorative hot-air-balloon illustration plus large Chinese slogan {argument name="booking slogan" default="留一个清晨给天空"} and smaller line “在云端，遇见更辽阔的自己。”; 2) dropdown field with leaf icon labeled “出发时节”; 3) dropdown field with two-person icon labeled “同行人数”; 4) sepia line-art landscape illustration with tiny English text “GOOD MORNINGS BRIGHTER PLACES”. Use dotted vertical dividers between sections. Bottom navigation band: At the very bottom, add a deep plum footer band with gold ornamental curves. Include exactly 2 featured destination links: left link with leaf icon, Chinese title “峡谷中的一天 →” and English subtitle “A DAY IN THE CANYON”; right link with small town icon, Chinese title “住进石色小镇 →” and English subtitle “STAY IN THE STONE TOWN”. Visual style: Ultra-detailed concept art blended with premium web UI design, elegant Chinese serif typography, warm sunrise lighting, soft atmospheric haze, cinematic depth, precise spacing, realistic fantasy travel illustration, high-resolution polished landing page screenshot. Constraints: Keep the page as a single desktop website hero screen, no phone mockup, no extra panels beyond the specified booking card and bottom band, preserve all Chinese text exactly as written, avoid random gibberish text, avoid watermarks.

Create a cinematic 16:9 Mac desktop wallpaper in a realistic voxel-block style, like a high-end ray-traced Minecraft diorama. The scene is a misty forest pasture at dawn or dusk with moody blue-gray fog, soft volumetric light, wet grass, and a dark green color palette. In the foreground there are exactly 2 main subjects: 1 black voxel horse standing on the left in side view, and 1 low black voxel sports car on the right, rear three-quarter view, modeled like a Porsche 911 with a continuous red rear light bar and the visible rear wordmark {argument name="car badge text" default="PORSCHE"}. The car should look glossy, angular, and handcrafted from small blocks, with black wheels and subtle reflections. The horse should be built from dark blocks with a slightly bowed head, standing calmly near the car. Behind them is a wooden block fence running horizontally across the image, with a large blocky tree trunk on the right and leafy cubic canopy overhead, plus a foggy background forest made of many distant block trees. Add centered white inspirational text near the upper middle in exactly 2 lines: line 1 reads {argument name="quote line one" default="If you can see it in your mind,"} and line 2 reads {argument name="quote line two" default="you can hold it in your hand"}. Use a premium cinematic composition, shallow atmospheric depth, subtle rain-damp surfaces, realistic voxel lighting, no people, no extra vehicles, no logos except the car badge, and leave the image clean enough to function as a desktop wallpaper.

Goal: Create a wide black-background comparison graphic showing two generated YouTube home page screenshots for a tech-bro recommendation feed, comparing {argument name="left model label" default="GPT-Image 2.5"} versus {argument name="right model label" default="GPT Image 2"}. Canvas: Very wide 3:1 landscape image, approximately 1200×640 pixels. Use a pure black outer background with generous margins. Center the composition horizontally. Layout: Place exactly 2 large YouTube dark-mode browser screenshots side by side. The left screenshot sits in the left half and the right screenshot sits in the right half, with a clear gap between them. Above each screenshot, center a white model label in a clean sans-serif font. Under both screenshots, centered near the bottom, place one caption: {argument name="bottom caption" default="A screenshot of Youtube home page for a tech bro."} Left screenshot details: A dark-mode YouTube homepage mockup labeled GPT-Image 2.5. Include the YouTube logo at top left, a search bar along the top, sidebar navigation on the far left, and category chips across the top. Show exactly 12 visible video thumbnail cards arranged in a 4-column by 3-row grid. The thumbnails should look like startup, productivity, investing, AI, and self-improvement content. Include these 12 visible thumbnail themes: 1) “The next 10 years” with a young male tech founder portrait, 2) “How to Build a Startup in 2025,” 3) “A Calmer More Focused You” landscape/meditation thumbnail, 4) “ELON MUSK Full Interview,” 5) “M4 Worth it?” laptop thumbnail, 6) “Build a Second Brain” Notion-style thumbnail, 7) “S&P 500” green stock chart, 8) “Stop Scrolling. Build Something.” creator portrait, 9) “The Future of Work” scenic thumbnail, 10) “a day in my life” desk/window lifestyle thumbnail, 11) “Tech Products That Changed My Life” gadgets on table, 12) one additional tech/productivity card consistent with the grid. Use small channel avatars, view counts, durations, and metadata text, but keep most small text only partially legible like a real screenshot. Right screenshot details: A dark-mode YouTube homepage mockup labeled GPT Image 2. Include the YouTube logo, search bar, sidebar navigation, top category chips, and profile/create icons. Show exactly 8 visible video thumbnail cards arranged in a 4-column by 2-row grid. The thumbnails should be sharper and more spacious than the left panel. Include these 8 visible thumbnail themes: 1) “how I built this.” with a Shopify bag icon and founder portrait, 2) “The Era of AI Employees” with two men and AI icons, 3) “$0 to $1M ARR” black chart thumbnail, 4) “The Truth About Silicon Valley” with a man’s portrait, 5) “Hard Truths” with Elon Musk portrait, 6) “minimal. but effective.” desk setup thumbnail, 7) “$10K/MO SIDE PROJECT” with creator portrait and app icons, 8) “How Bitcoin Works” with Bitcoin icon network graphic. Add small video durations and metadata beneath each card. Visual style: Photorealistic screenshot-comparison aesthetic, crisp UI details, dark YouTube theme with charcoal panels, white and gray text, red YouTube accents, subtle thumbnail colors, realistic browser screenshot proportions. The overall graphic should look like a social media post or review image comparing two AI image models. Constraints: Do not add an AI Search video. Keep exactly 2 screenshots, exactly 2 top labels, exactly 1 bottom caption, exactly 12 video cards in the left screenshot, and exactly 8 video cards in the right screenshot. Avoid watermarks and avoid any extra explanatory text outside the specified labels and caption.

基于我上传的图片，设计一套 3D 表情包 1:1 透明贴纸页，包含 9 个各不相同的贴纸，按 3X3 网格排列每个贴纸呈现不同的表情、姿势或反应。贴纸之间留出较宽且完全透明的间隔。无背景、阴影或重叠元素，融入{argument name="表情符号" default="🚀🎉🥳🤟"}

turn {argument name="target" default="it"} into a {argument name="style" default="future building"}

Generate a image of screenshot of a tiktok livestream hosting by a beautiful woman.

Using the provided reference image, transform the blank open foldable mock device into a realistic open-screen smartphone/tablet running a polished recipe app UI, while preserving the exact tabletop setting, camera angle, lighting, hinge pose, and overall open-book orientation. Goal: Replace the gray blank panels with edge-to-edge glossy screens and a thin black phone bezel, making the device look like a premium dual-screen foldable phone in an open-book pose. Screen content: Show a cooking app recipe page for {argument name="recipe title" default="Dan Dan Noodles"}. The layout should span both halves naturally across the hinge. Left screen: Add a large appetizing food photo at the top showing a bowl of noodles with greens, minced topping, scallions, and chili oil. Under it, create an ingredient checklist section titled {argument name="ingredient section title" default="Sichuan oil & sauce base"} with exactly 5 visible checkbox rows: vegetable oil, gochugaru with optional cayenne, ground Sichuan peppercorns, ground cinnamon, and soy sauce / Chinese black vinegar text partially continuing near the bottom. Add a circular back arrow button over the upper-left of the food image. Right screen: Create the recipe detail and instructions panel. Include the title, a small green dropdown chevron, a short descriptive paragraph, two pill tags labeled “Dinner” and “Kid-Approved,” and exactly 3 stat blocks: “40 min TOTAL,” “20 min PREP,” and “4 SERVES.” Add a segmented control with “Shop” selected and “Cook” unselected. Below, show a section titled “Sauce” with exactly 2 numbered instruction steps visible. Controls: Add exactly 2 small rounded-square action buttons at the upper-right of the right screen: edit pencil and three-dot menu. Add a floating vertical toolbar on the lower-right edge with exactly 5 icons: open book highlighted in green, chat bubble, search, checklist, and user/profile. Style constraints: Keep the generated UI crisp, realistic, and slightly perspective-warped to match the device angle. Stretch the app to the screen edges, make the black rim and hinge believable, preserve the original warm outdoor wooden table background, and avoid changing the physical placement of the foldable device.

将此说明图表转换为图标。完全删除其中的文字和背景。*background="{argument name="background" default="transparent"}"

Goal: Create a clean screenshot-style image of a mobile sketch editor interface showing a rough black doodle on a white canvas, as if drawn with a thick marker in a simple drawing app. Canvas: Square 1:1 image, bright white background, rounded app-window corners, very minimal light-gray UI chrome. Layout: At the top left place one gray X close icon. At the top center place a floating rounded toolbar containing exactly 5 tool icons: cursor arrow, squiggle pen tool highlighted with a pale gray circular background, capital T text tool, overlapping shapes icon, and eraser icon. At the top right place exactly 2 undo/redo curved-arrow icons in light gray. On the left side place one vertical light-gray slider with a round knob near the lower third and a small multicolor sparkle button near the center-left. On the right side of the canvas place one small black circular cursor dot with a thin white ring. Along the bottom place exactly 14 circular color controls: rainbow color wheel, selected black swatch with blue outline and white ring, gray, brown, red, orange, yellow-orange, green, teal, cyan, blue, indigo, purple, and pink. Bottom right has one black circular confirmation button with a white checkmark. Drawing content: Use thick, uneven, hand-drawn black lines with rounded ends, like a finger sketch. The drawing is divided by one long horizontal black line across the lower middle of the canvas. Above the line, draw exactly 2 large stick-figure-like doodles: on the left a tall narrow figure with a triangular/hat-like head and long vertical body; on the right a stick person with an oval head, vertical torso, one bent arm extending left, and two angled legs. Below the line, draw exactly 3 smaller stick figures spaced left, center, and right; each has a simple head shape, vertical body, short horizontal arms, and two angled legs. The left lower figure has a wide angular head, the center lower figure has a small oval head, and the right lower figure has a tilted oval head. Visual style: Minimal iOS-like sketch interface, flat vector UI, no shadows except very subtle toolbar softness, white background, black marker strokes as the dominant element. Keep all doodles intentionally crude and childlike, not polished. Constraints: No readable text in the canvas, no watermark, no photorealism, preserve the exact counts of UI icons, color swatches, and stick figures.

Goal: Create a clean screenshot-style chat interface showing an AI image generation result after a Japanese instruction. Canvas: Wide landscape canvas, about 1200×1000 px, with a very light gray-white background and lots of empty space on the right. The main generated image card sits left of center, with a user message bubble near the upper right. Text content: Include exactly 1 pale blue rounded message bubble in the upper right containing the Japanese text {argument name="instruction text" default="真正面直立にしてください。"}. Keep the text dark navy, simple sans-serif, centered vertically in the bubble. Main image card: Show exactly 1 large rounded white image card on the left, with soft corners and a subtle gray shadow. Inside it is a front-facing, full-body cartoon monster drawn like a cute sticker: a squat upright reptile/kaiju with a big rounded head, angry slanted eyes, thick black outlines, brown spotted skin, a yellow belly, short arms with black claws, chunky legs with black toenails, and a curved tail extending to the left. The creature faces straight forward in a rigid standing pose. It has a red forked tongue hanging from a jagged mouth, small nostril dots, and dark spots scattered over the head, arms, body, legs, and tail. Use a hand-drawn marker or watercolor texture with slightly uneven fills. Character colors: {argument name="body color" default="muddy brown"}, {argument name="belly color" default="warm yellow"}, {argument name="tongue color" default="red"}, with thick black outlines. Overlay controls: On the lower edge of the image card, include exactly 2 semi-transparent circular controls: a gray circle at bottom left labeled 「編集」 in white, and a gray circle at bottom right with a white upload/share arrow icon. A faint gray gradient appears along the bottom of the image card behind these controls. Bottom toolbar: Beneath the card, aligned left, include exactly 5 small gray outline icons in this order: copy/duplicate icon, thumbs-up icon, thumbs-down icon, share/upload icon, and horizontal ellipsis icon. Keep them minimal and unfilled. Style constraints: The whole scene should look like a cropped modern AI chat app screenshot, not a poster. Preserve the Japanese text exactly where specified. Do not add extra messages, captions, watermarks, borders, or additional characters.

Using the provided reference image as a loose layout reference, replace the prompt-library interface with a clean 3-column by 3-row gallery of exactly 9 vertical retro graphic posters. Remove all website UI elements, author names, buttons, borders, Korean interface text, and card metadata. Keep only the idea of a tiled poster grid with narrow gutters on an off-white background. Style: Bold 1960s–1970s modernist poster design, flat vector shapes, cream paper backgrounds, high-contrast black typography, saturated primary colors, simple geometric compositions, minimal texture, crisp print-poster look. Create exactly 9 posters, arranged left to right, top to bottom: 1. Poster text: “Travel Farther” — radiating perspective road/fields leading to a yellow sun. 2. Poster text: “CREATE” — large rounded blue psychedelic type above flowing wavy color bands. 3. Poster text: “GROW TOGETHER” — abstract flower with orange sun/circle and layered leaves. 4. Poster text: “LISTEN MORE” — overlapping side-profile silhouettes in black, blue, orange, and cream. 5. Poster text: “FIND YOUR BALANCE” — stacked semicircles and circles in yellow, pink, blue, black, and orange. 6. Poster text: “DRINK MORE WATER” — oversized white block type on a solid blue field with a small orange circle. 7. Poster text: “LEARN SOMETHING NEW” — geometric staircase entering an archway. 8. Poster text: “SEE THE BEAUTY” — halftone illustrated eye over transparent colored circles. 9. Poster text: “CHOOSE KINDNESS” — abstract geometric collage with a pink heart and colorful blocks. Typography: Use bold condensed sans-serif headline lettering; make the text large, readable, and integrated into each poster. Use the headline set {argument name="poster message theme" default="uplifting lifestyle reminders"} while preserving the exact 9-poster count and grid structure. Use a palette based on {argument name="color palette" default="cream, black, yellow, orange-red, cobalt blue, forest green, and pink"}. Overall composition should feel like {argument name="poster era" default="1970s modernist motivational print posters"}.

Goal: Create a clean screenshot-style mockup of an AI image generation interface showing a generated scenic photo in a chat thread. Canvas: Wide horizontal canvas, approximately 1200 × 789 px, with a plain light gray-white background and lots of empty space on the right and bottom. Layout: Place a single black rounded chat bubble near the upper-right area containing the Chinese text {argument name="request text" default="生成一张你觉得最美的图片"} in white. Directly underneath that bubble, align exactly 3 small gray outline action icons from left to right: copy, share/upload, and edit pencil. Below and to the left, place one large rounded-corner generated image card with a thin blue outline, about 640 × 535 px, positioned in the left-center of the canvas. Under the image card at the lower-left of the overall UI, place exactly 5 small gray outline reaction/action icons from left to right: copy, thumbs up, thumbs down, share/upload, and three-dot more menu. Generated image card content: A breathtaking photorealistic mountain sunrise scene viewed from a high alpine cliff. A fluffy {argument name="cat description" default="gray-and-white long-haired cat"} sits on the rocky ledge at the lower-left of the image, facing away toward the horizon. The landscape shows jagged snow-covered mountain peaks on the left, layers of soft clouds and mist filling the valleys, a glowing sunrise near the right horizon, warm peach and golden sky, distant blue-gray mountains, and a reflective lake or fjord far below on the right. In the foreground near the cat, show small white alpine flowers and patches of snow on rocks. The mood should feel serene, majestic, and emotionally beautiful. Image-card UI details: The card has large rounded corners and a subtle blue border indicating selection. Add exactly 2 overlay controls inside the generated image: a dark translucent rounded rectangle button at the bottom-left labeled {argument name="edit button text" default="编辑"} in white, and a circular dark translucent share/upload button at the bottom-right with a white upload arrow icon. Visual style: Minimal modern AI-chat interface, realistic generated photo inside the card, soft natural lighting, high dynamic range, crisp but slightly screenshot-compressed UI icons, no browser chrome, no watermark. Constraints: Keep all visible text exactly as specified, use only the one main generated image card, one chat bubble, 3 icons under the bubble, 2 overlay controls on the card, and 5 bottom toolbar icons. Do not add extra captions, windows, sidebars, people, or additional images.

Goal: Create a premium accessible gelateria brand identity presentation for {argument name="brand name" default="Farnese"}, inspired by the landscape and culture of Governador Valadares: Ibituruna Peak, free flight/paragliding, warm sun, hills, vegetation, and an old industrial smokestack. The overall feeling is artisanal, contemporary, warm, and refined. Canvas: Wide horizontal brand board, 16:9 ratio, arranged as a clean collage grid on a warm cream background with realistic mockup photography mixed with flat vector assets. Layout: Use exactly 8 visible panels. Panel 1 is a large logo panel on the upper left occupying about two-fifths of the width and half the height. Panel 2 is a small burgundy square logo mark tile near the top center. Panel 3 is a small cream logo mark tile directly beneath it. Panel 4 is a large ice cream pint mockup on the upper right. Panel 5 is a shopping bag mockup on the lower left. Panel 6 is a group of three small gelato cup lids in the lower middle. Panel 7 is a cream icon sheet in the lower right-middle. Panel 8 is a burgundy repeating pattern tile on the far lower right. Logo details: The main wordmark reads {argument name="brand name" default="Farnese"} in an elegant custom serif script with thick and thin strokes, deep burgundy color, and a slightly old-world Italian gelateria feel. Above the wordmark, place a minimalist mountain silhouette line with a round sun dot near the right peak, suggesting Ibituruna Peak. Below the wordmark, write {argument name="descriptor text" default="GELATERIA"} in widely spaced uppercase sans serif letters, flanked by two thin horizontal lines. Color palette: Show exactly 4 circular swatches beneath the main logo: 1 deep burgundy, 2 burnt terracotta orange, 3 warm cream beige, 4 muted olive green. Use {argument name="primary burgundy" default="#5A0D17"}, terracotta, cream, and olive throughout the board. Brand mark tiles: Show exactly 2 simplified monogram logo mark tiles. The mark combines a flowing mountain/paraglider curve and a lowercase-style F. The top tile has a deep burgundy background with a cream monogram and a small terracotta dot. The bottom tile has a cream background with a burgundy monogram and terracotta dot. Product mockups: Include exactly 4 branded physical items: 1 large gelato pint on the upper right with a burgundy lid, 1 paper shopping bag on the lower left, and 2 visible small gelato cups in the lower middle, plus 1 third small cup lid partially overlapping in muted olive. The pint and bag both carry the full {argument name="brand name" default="Farnese"} logo and layered wavy landscape bands in terracotta, olive, and burgundy. Add realistic paper/cardboard texture, speckled print grain, warm sunlight, and soft shadows. On the upper-right product scene, include one scoop of pale green pistachio gelato on a small stone slab and scattered pistachios. Icon sheet: Include exactly 7 simple line icons on a cream panel: 1 radiating sun, 1 mountain outline, 1 paraglider with a tiny pilot, 1 palm-like plant, 1 small leafy branch, 1 industrial smokestack tower, and 1 stack of three wavy landscape lines. Draw them in burgundy, terracotta, and olive with clean vector strokes. Pattern tile: Create a deep burgundy square pattern filled with repeated cream wavy mountain lines and terracotta sun dots. Use exactly 5 horizontal wave-line rows and 3 terracotta sun dots distributed vertically. Visual style: High-end branding case-study aesthetic, warm Mediterranean gelato packaging, natural materials, tactile print textures, cohesive grid composition, soft studio sunlight, refined contrast, no people, no clutter, no extra text beyond the brand name and descriptor.

Goal: Create a polished launch-feature hero graphic for {argument name="product name" default="GPT Image 2.5"}, showing a futuristic image-generation interface with multiple capability panels floating in a soft studio environment. Canvas: Wide 16:9 landscape composition, rounded-corner poster, premium tech-ad style. Use a warm off-white background with subtle glassmorphism, soft reflections, luminous circular rings on the floor, and shallow-depth-of-field greenery and stone foreground blur. Layout: Place the large headline “GPT Image 2.5” centered near the top, with “GPT” in black and “Image 2.5” in a blue-to-purple gradient. In the center, show one large rounded rectangular showcase image with a glowing border: a photorealistic Mediterranean coastal terrace at sunset, overlooking cliffs, villas, mountains, a calm sea, and a small sailboat; include a round wooden table with flowers, a cup, a book, and a cozy chair in the foreground. Feature panels: Include exactly 4 surrounding feature areas, each with a visible label. Top left panel labeled “Precise Edits”: two side-by-side dog photos of a golden retriever indoors, separated by a white arrow; the left image has a dashed selection box around a yellow tennis ball, the right image shows the edited object as a soccer ball with a dashed box. Bottom left panel labeled “GIF Creation”: a sequence of exactly 5 overlapping rounded cards showing a golden retriever running and splashing through water, progressing from faint/transparent frames to a sharp final action frame. Top right panel labeled “Sketch to Image”: a simple pencil sketch of an armchair on the left, a white arrow, and a photorealistic green cushioned wooden armchair with a draped blanket on the right. Bottom right panel labeled “Natural Detail”: a 2 by 3 grid of exactly 6 close-up texture tiles: human eye, glossy dark hair, water droplets on glass, reflective curved metal, wood grain corner, and green woven fabric. Visual style: High-end glossy product marketing render, photorealistic image thumbnails, crisp typography, rounded translucent cards, soft drop shadows, white glow trails connecting the panels, balanced symmetry, warm sunlight mixed with cool blue-purple UI accents. Constraints: Keep all text legible and limited to the headline plus the four labels. Do not add extra logos, watermarks, menus, buttons, or unrelated icons.

Create a clean demonstration image on a black canvas showing a white-framed four-pane window graphic with transparency effects. The main subject is a realistic front-facing window centered slightly left, with a thick glossy white frame, beveled edges, a horizontal and vertical crossbar dividing the glass into exactly 4 rectangular panes, and a small sill at the bottom. Behind and through the window is a gray checkerboard transparency pattern, and the glass panes should show the checkerboard faintly with about 50% alpha, plus subtle bluish tint, soft reflections, and two diagonal light streaks. Around the window, include a larger semi-transparent checkerboard rectangle with alternating dark gray squares on the black background to clearly indicate transparency. At the top right, add one rounded blue speech-bubble label containing the Japanese text {argument name="instruction text" default="窓枠と窓の画像、背景透過、窓の部分は50%のアルファ値とする"} in white sans-serif type. At the bottom left of the checkerboard area, add one small dark rounded button labeled 「編集」, and at the bottom right add one small circular dark button with a white upload/share arrow icon. Keep the composition minimal, with no extra objects, no watermark, and crisp UI-like presentation.

为我生成图中角色的卡通Line风格的半身像GIF表情包每一帧的图片，注意头饰和发型要正确。 使用 4行x4列 布局共生成16个小图片。16个小图片为“飞吻”动画的连贯的拆分动作，使用这16张可以组成一个完整的、循环动画，动作流畅逼真，最后一帧应流畅地循环回到第一帧。16张图片里都使用跟图片搭配的字体写着汉字“爱你哦”。16个小图片之间需要有足够留白方便后续切割，每张图片都不要超出自己的区域。 注意不要原图复制，只是使用图片里的人物。背景为纯白色，不要画分割线。图片比例1：1

Goal: Create a polished anime character redesign presentation sheet for a blue-themed schoolgirl mascot, combining a large central illustration with labeled design-analysis panels around it. Canvas: Square 1:1 white presentation board, clean editorial layout, soft pale-blue accents, thin light-gray divider lines, high-resolution anime art, crisp but hand-drawn feel. Main subject: A cute teenage anime girl named {argument name="character name" default="Blue Ribbon"} sitting in the center foreground in a shy, appealing pose, one hand against her cheek and legs folded forward. She has long vivid {argument name="hair color" default="blue"} twin-tail hair with loose flyaway strands, glossy blue eyes, soft blush, small open smile, and delicate facial features. Outfit is a navy-blue sailor school uniform with white trim, oversized pale-blue bow at the chest, pleated skirt with white frills, thigh-high blue socks with white stripes, and black loafers with small blue ribbon details. Use a monochrome blue palette with subtle skin tones and painterly highlights. Layout: Place the large finished redesign illustration slightly left of center, occupying most of the canvas. Surround it with structured reference panels: top-left original design panel, left-column issue cards, top-right expression set, right-middle turnaround, right-lower detail closeups, and bottom-right color palette. Add small blue heart doodles and handwritten Japanese-style notes as decorative accents. Sections and exact counted elements: - Top-left panel: 1 original chibi-style blue character drawing, labeled in Japanese “元のデザイン” with small English subtitle “Original”. - Left column issues: exactly 3 numbered issue cards labeled 1, 2, and 3. Card 1 shows a tiny face sketch and says the eye expression is weak. Card 2 shows a rear/silhouette sketch and says the silhouette is monotonous. Card 3 shows a clothing/pose sketch and says the pose and outfit lack charm. - Top-right expressions: exactly 3 rounded-rectangle face closeups labeled “表情集 Expressions”: 1 smiling with closed eyes, 1 surprised with wide eyes and small open mouth, 1 sleepy or pouting sideways glance. - Right-middle turnaround: exactly 3 full-body views labeled “三面図 Turnaround”: Front, Side, Back, showing the same outfit and long twin-tail hair from each angle. - Right-lower details: exactly 3 square closeup panels labeled “ディテール Details”: 1 eye detail, 1 chest ribbon detail, 1 skirt frill detail. - Bottom-right color palette: exactly 5 circular color swatches: deep blue, royal blue, light blue, very pale blue, and pale skin-pink. Visible text style: Use neat Japanese headings with small English subtitles, including “Original”, “Issues”, “Expressions”, “Turnaround”, “Details”, and “Color Palette”. Include handwritten Japanese catchphrases around the character, such as {argument name="main handwritten note" default="もっと好きになれるわたしに"}, plus bottom notes meaning “I have loved you since then” and “Unchanged blue, cuter.” Add small English footer text: “CHARACTER REDESIGN / SAME BLUE, A BRIGHTER ME.” Visual style: Modern Japanese anime illustration, bright glossy eyes, soft cel shading blended with watercolor-like gradients, delicate blue linework, subtle paper texture, clean UI-like character sheet design, balanced negative space, no heavy background. Make the final design look more charming, expressive, and polished than the simple original sketch. Constraints: Keep the exact panel counts above, maintain the blue-and-white visual identity, avoid extra characters, avoid clutter, no watermark, no photorealism, no 3D rendering.