PROMPTS · CREATIVE EXPLORATION

Prompt Gallery

Explore real prompts and their generated examples. Find inspiration for your next creative mission and copy the complete prompt for free.

Examples
11,025
Models
18
Sources
1277
11,025 prompt examples · page 196 of 230
Example generated from “四城极简旅行海报系列”
GPT Image 2en

Minimalist flat travel poster illustration series of iconic destinations around the world, clean vector art style, Scandinavian color palette, soft pastel tones, calm atmospheric scenery, Hallstatt Austria lakeside village with alpine mountains and reflections, Bergen Norway colorful harbor houses with fjord background, Kyoto Japan traditional riverside town with cherry blossoms and pagoda, Santorini Greece white architecture with blue domes overlooking the sea, ultra clean composition, geometric landscape shapes, smooth gradients, elegant typography with destination names, modern tourism poster aesthetic, serene travel mood, crisp vector lines, cinematic wide-angle scenery, peaceful skies with stylized clouds, highly detailed environment art, contemporary flat illustration, premium editorial travel design, balanced composition, minimal shadows, dreamy vacation atmosphere, soft morning lighting, high-end Airbnb poster vibe, Behance trending style, 4k, ultra detailed

Example generated from “四季包装 Campaign 宫格”
GPT Image 2en

PHASE 1 - PRODUCT: [ITEM] in [MATERIAL] packaging, minimal label design PHASE 2 - GRID: 2x2 seasonal grid, four distinct brand worlds PHASE 3 - COMPOSITION: each quadrant a full campaign scene with props and environment PHASE 4 - CONSISTENCY: same product silhouette, four distinct palettes Swap: [ITEM] / [MATERIAL] / [LABEL STYLE]

Example generated from “国风工笔八仙长卷插画”
GPT Image 2mixed

[中文] (国风卷轴插画师)你是一位顶尖的中国传统工笔人物画师,擅长将经典人物群像绘制成长卷式百科海报。根据用户指定的【eight immortals】,生成一张 “中国传统人物群像长卷海报”:画面为横向长卷式构图,所有人物排成一条队列,从左至右依次展开;每个人物都有鲜明的传统服饰、标志性道具和神态,下方配有竖排名牌标注姓名;卷轴顶部有醒目的书法标题;背景为符合主题的场景元素(如祥云、海浪、山水、亭台等)。整体为高质量国风工笔插画:细腻线稿 + 雅致上色,浅米色 / 宣纸质感背景;注释为清晰的中文书法字体;横向 4K 长卷海报,构图均衡,人物分明,氛围贴合主题(如仙气、豪迈、温婉等)。直接出图,人物群像为【eight immortals】。 [English] (Guofeng scroll illustrator) You are a top Chinese traditional Gongbi figure painter, skilled in painting classic character group portraits into long-scroll-style encyclopedia posters. According to the user-specified [eight immortals], generate a "Chinese traditional character group portrait long scroll poster": The picture is a horizontal long-scroll composition, all characters are arranged in a queue, unfolding sequentially from left to right; each character has distinct traditional clothing, iconic props, and expressions, below is a vertical nameplate annotating the name; the top of the scroll has a striking calligraphy title; the background is scene elements fitting the theme (such as auspicious clouds, ocean waves, mountains and rivers, pavilions). The overall style is high-quality Guofeng Gongbi illustration: delicate line art + elegant coloring, light beige / Xuan paper texture background; annotations are in clear Chinese calligraphy fonts; horizontal 4K long scroll poster, balanced composition, distinct characters, atmosphere fitting the theme (such as fairy-like, heroic, gentle). Output the image directly, the character group portrait is [eight immortals].

Example generated from “图像生成案例图”
GPT Image 2en

[CORE TASK] Transform the provided input image into a pose-and-light analysis sheet. This is NOT a finished character illustration. This is NOT a clothing sheet. This is NOT a beauty-preserving redraw. This is a white-line rough mannequin conversion. [PRIMARY GOAL] Extract and visualize only: - pose structure - body balance - camera angle - body line flow - inferred light source placement - illuminated areas and light intensity [INPUT ROLE] Use the provided image as the strict anchor for: - pose - camera angle - body tilt - weight distribution - approximate lighting situation Do NOT preserve: - face rendering - hairstyle rendering - clothing detail - accessories - weapon detail - background architecture - character identity - emotional expression [FIGURE CONVERSION] single rough mannequin-like human figure white body contour lines white internal construction lines simple mannequin head no face no eyes no mouth no eyelashes no personality no individual identity human figure should look like: - rough pose mannequin - anatomy proxy - line-based body guide - structural sketch - white-line rough dummy keep: - pose readability - silhouette flow - head tilt - torso direction - pelvis direction - limb placement [BACKGROUND] pure black background negative-style dark field no scenery no props no architecture no environmental storytelling [LINE STYLE] rough white line drawing clean but sketch-like construction-line feeling anatomy guide lines visible joint flow visible body contour emphasized no polished illustration finish [LIGHT ESTIMATION] predict the likely light source positions from the input image visualize the light sources and illuminated areas using green glow only use green light intensity with variation: - strongest green where the light directly hits - medium green for wrap light - soft green for reflected or fading light mark the estimated light sources with labels and arrows such as: - Main Light - Rim Light - Fill Light - Floor Bounce - Back Light only if appropriate IMPORTANT: do not invent random lights infer lighting from the original input image if the lighting is ambiguous, keep the annotations simple and plausible [GREEN LIGHT VISUALIZATION] show green glow on: - head / skull plane - neck - shoulders - chest plane - ribcage direction - pelvis edge - thigh planes - knee contact points - floor contact bounce if applicable use green light not as decoration, but as lighting analysis information [POSE PRIORITY] 1. preserve pose structure 2. preserve camera angle 3. preserve body balance 4. preserve head-torso relationship 5. visualize likely light direction 6. show illuminated areas with readable green intensity variation [NEGATIVE] finished person, cute girl, detailed face, hair rendering, clothing rendering, weapon emphasis, beautiful anatomy

Example generated from “图像生成案例图”
GPT Image 2en

[CORE TASK] Transform the provided input image into a pose-and-light analysis sheet. This is NOT a finished character illustration. This is NOT a clothing sheet. This is NOT a beauty-preserving redraw. This is a white-line rough mannequin conversion. [PRIMARY GOAL] Extract and visualize only: - pose structure - body balance - camera angle - body line flow - inferred light source placement - illuminated areas and light intensity [INPUT ROLE] Use the provided image as the strict anchor for: - pose - camera angle - body tilt - weight distribution - approximate lighting situation Do NOT preserve: - face rendering - hairstyle rendering - clothing detail - accessories - weapon detail - background architecture - character identity - emotional expression [FIGURE CONVERSION] single rough mannequin-like human figure white body contour lines white internal construction lines simple mannequin head no face no eyes no mouth no eyelashes no personality no individual identity human figure should look like: - rough pose mannequin - anatomy proxy - line-based body guide - structural sketch - white-line rough dummy keep: - pose readability - silhouette flow - head tilt - torso direction - pelvis direction - limb placement [BACKGROUND] pure black background negative-style dark field no scenery no props no architecture no environmental storytelling [LINE STYLE] rough white line drawing clean but sketch-like construction-line feeling anatomy guide lines visible joint flow visible body contour emphasized no polished illustration finish [LIGHT ESTIMATION] predict the likely light source positions from the input image visualize the light sources and illuminated areas using green glow only use green light intensity with variation: - strongest green where the light directly hits - medium green for wrap light - soft green for reflected or fading light mark the estimated light sources with labels and arrows such as: - Main Light - Rim Light - Fill Light - Floor Bounce - Back Light only if appropriate IMPORTANT: do not invent random lights infer lighting from the original input image if the lighting is ambiguous, keep the annotations simple and plausible [GREEN LIGHT VISUALIZATION] show green glow on: - head / skull plane - neck - shoulders - chest plane - ribcage direction - pelvis edge - thigh planes - knee contact points - floor contact bounce if applicable use green light not as decoration, but as lighting analysis information [POSE PRIORITY] 1. preserve pose structure 2. preserve camera angle 3. preserve body balance 4. preserve head-torso relationship 5. visualize likely light direction 6. show illuminated areas with readable green intensity variation [NEGATIVE] finished person, cute girl, detailed face, hair rendering, clothing rendering, weapon emphasis, beautiful anatomy

Example generated from “图像生成案例图”
GPT Image 2en

[CORE TASK] Transform the provided input image into a pose-and-light analysis sheet. This is NOT a finished character illustration. This is NOT a clothing sheet. This is NOT a beauty-preserving redraw. This is a white-line rough mannequin conversion. [PRIMARY GOAL] Extract and visualize only: - pose structure - body balance - camera angle - body line flow - inferred light source placement - illuminated areas and light intensity [INPUT ROLE] Use the provided image as the strict anchor for: - pose - camera angle - body tilt - weight distribution - approximate lighting situation Do NOT preserve: - face rendering - hairstyle rendering - clothing detail - accessories - weapon detail - background architecture - character identity - emotional expression [FIGURE CONVERSION] single rough mannequin-like human figure white body contour lines white internal construction lines simple mannequin head no face no eyes no mouth no eyelashes no personality no individual identity human figure should look like: - rough pose mannequin - anatomy proxy - line-based body guide - structural sketch - white-line rough dummy keep: - pose readability - silhouette flow - head tilt - torso direction - pelvis direction - limb placement [BACKGROUND] pure black background negative-style dark field no scenery no props no architecture no environmental storytelling [LINE STYLE] rough white line drawing clean but sketch-like construction-line feeling anatomy guide lines visible joint flow visible body contour emphasized no polished illustration finish [LIGHT ESTIMATION] predict the likely light source positions from the input image visualize the light sources and illuminated areas using green glow only use green light intensity with variation: - strongest green where the light directly hits - medium green for wrap light - soft green for reflected or fading light mark the estimated light sources with labels and arrows such as: - Main Light - Rim Light - Fill Light - Floor Bounce - Back Light only if appropriate IMPORTANT: do not invent random lights infer lighting from the original input image if the lighting is ambiguous, keep the annotations simple and plausible [GREEN LIGHT VISUALIZATION] show green glow on: - head / skull plane - neck - shoulders - chest plane - ribcage direction - pelvis edge - thigh planes - knee contact points - floor contact bounce if applicable use green light not as decoration, but as lighting analysis information [POSE PRIORITY] 1. preserve pose structure 2. preserve camera angle 3. preserve body balance 4. preserve head-torso relationship 5. visualize likely light direction 6. show illuminated areas with readable green intensity variation [NEGATIVE] finished person, cute girl, detailed face, hair rendering, clothing rendering, weapon emphasis, beautiful anatomy

Example generated from “圣诞街景 Chibi 真实背景人像”
GPT Image 2en

Use the uploaded image as the primary reference. Transform the person into a cute, hand-drawn anime/chibi character while preserving the original person’s recognizable facial features, hairstyle, outfit, pose, and accessories. A cute young woman standing on a modern city street at blue hour, surrounded by tall illuminated skyscrapers and festive Christmas decorations. A huge glowing Christmas tree covered in warm golden lights stands directly behind her, creating a magical holiday atmosphere. The street is filled with elegant decorative lights, pedestrians, modern architecture, and soft evening city illumination. Render the character in a charming Japanese hand-drawn anime/chibi illustration style with expressive large eyes, soft blush on the cheeks, delicate facial details, textured pencil-and-ink outlines, subtle watercolor-like coloring, and slightly imperfect handmade sketch details. Keep the background photorealistic and highly detailed, creating a beautiful contrast between the illustrated character and the real-world environment. Cinematic composition, natural perspective, soft evening lighting, warm Christmas glow, realistic background depth, detailed clothing texture, cozy winter atmosphere, high detail, aesthetically pleasing, vertical portrait composition.

Example generated from “城市名地标排版旅行海报”
GPT Image 2en

Create a clean, modern typographic travel poster where the city name itself becomes the composition. Render the city name in large, bold, uppercase sans-serif letters spanning the width of the artwork. Seamlessly integrate the city's most iconic landmarks, architecture, monuments, streets, transportation, cultural symbols, cafés, bridges, parks, skylines, sculptures, waterfronts, historic buildings, and local details into, around, and inside the letters. Let landmarks naturally interact with the typography while preserving legibility. Use an elegant flat vector illustration style with crisp geometric shapes, minimal detail, clean outlines, subtle shadows, and a premium editorial aesthetic. Maintain a limited color palette of deep navy, warm cream, muted red, and soft gray-blue for a timeless travel-poster look. Add small decorative elements such as street lamps, trees, clouds, birds, benches, bicycles, fountains, trams, ferries, or other city-specific objects where appropriate. Keep generous negative space with a clean background and perfectly balanced composition. Ensure every landmark, architectural style, vehicle, sign, and cultural element is accurate to the chosen city—avoid generic or incorrect landmarks. If desired, include a small elegant tagline beneath the city name (such as a famous nickname or slogan) in minimal typography. Style: premium flat vector, minimalist travel poster, geometric illustration, editorial design, tourism branding, clean typography, high contrast, ultra-sharp lines, museum-quality print, modern graphic design, centered composition, scalable SVG aesthetic, 8K resolution.

Example generated from “城市地图微缩旅行海报”
GPT Image 2en

Create a highly detailed cinematic miniature tilt-shift travel scene of [CITY NAME] featuring a realistic [VEHICLE NAME] driving along a winding elevated road that emerges naturally from a printed vintage-style city map. The road should curve dramatically toward the background skyline and landmarks of [CITY NAME], while the vehicle remains the clear focal point in the foreground. Blend the real city seamlessly with the illustrated map surface so the road appears integrated into the map itself. Include recognizable local landmarks, waterways, architecture, vegetation, and atmosphere associated with [CITY NAME], but keep the composition clean and uncluttered. Show large bold typography of "[CITY NAME]" printed directly on the map in the foreground. Use warm golden-hour lighting, shallow depth of field, realistic textures, cinematic shadows, aerial perspective, and photorealistic detail. The overall aesthetic should feel like a premium Instagram travel poster mixed with a miniature diorama. Aspect ratio 1:1.

Example generated from “城市文字旅行海报”
GPT Image 2en

Ultra-high-resolution typography travel poster themed around [CITY NAME]. 16:9 poster ratio. IMPORTANT: every visible word on the poster must be in English, perfectly spelled, professionally typeset. No distorted letters, no random symbols, no broken text, no AI gibberish. CORE COMPOSITION: Place the giant English word "[CITY_NAME]" front and center. Each letter is a tall, bold, elongated sans-serif form, and each one frames a different illustrated scene from the city, like a row of gallery windows. Spread landmarks, streets, transport, nature, culture, and architecture across the letters so the scenes flow from one letter into the next as a single connected urban panorama. TOP HORIZONTAL STRIP: Across the top of the poster, a thin panoramic band: city skyline silhouettes, cars, trams or trains, boats where it fits, birds, clouds, sun. Keep it minimalist, elegant, rhythmically balanced. STYLE: mid-century modern editorial poster, Swiss graphic design, minimal vector illustration, architectural infographic feel, travel typography poster, flat geometric illustration, ultra-clean composition, premium magazine design, screen-print poster vibe, retro-futuristic travel branding. ILLUSTRATION: Flat vector shapes only. No realism, no gradients, no noise. Clean geometric shadows, simplified architectural forms, a mix of map-like top-down with side-view cityscape. Subtle line-art details, crisp vector edges, strong negative space, harmonious rhythm between the letters. TYPOGRAPHY: Giant bold sans-serif, letters fill most of the canvas height. Pixel-perfect alignment. Each letter acts as its own framed illustration panel. Soft rounded corners where it suits. Editorial spacing. Print-ready and geometrically clean. COLOR PALETTE: Pull a cohesive palette inspired by [CITY_NAME]: coastal city -> aqua, sand, coral, muted teal desert city -> terracotta, beige, warm cream cyber city -> mint, navy, steel blue historic European city -> dusty rose, olive green, parchment Muted pastels, soft vintage travel-poster colors, low saturation. Max 4 to 6 colors. CONTENT: Include iconic landmarks, famous streets and transport, local urban patterns, nearby nature, skyline silhouettes, bridges/rivers/coastline if relevant, culturally symbolic architecture, recognizable local atmosphere. COMPOSITION: Centered typography on a white or soft ivory background. Lots of breathing room. The top panoramic strip balances the heavy typography below. Asymmetrical but visually balanced. Each letter shows its own scene depth and perspective. Museum-quality poster hierarchy. MOOD: premium, intellectual, calm, design-forward, travel-editorial, stylish enough for a museum gift-shop wall. QUALITY: 8K ultra-detailed, print-ready, razor-sharp vector edges, flawless typography, zero distorted text, zero random characters, zero spelling errors, zero AI artifacts.

Example generated from “塔可爆炸拆解信息图”
GPT Image 2en

Create a hyper-realistic exploded vertical infographic composition of tacos. Top → Bottom structure: Fresh Lettuce (crisp green texture with natural folds) → Tomato & Salsa Layer (juicy diced tomatoes and salsa mix) → Melted Cheese (smooth cheddar texture) → Grilled Meat Filling (juicy seasoned meat detail) → Taco Shell Base (crispy golden shell texture) Perfect vertical alignment, rustic background, soft studio lighting, realistic shadows beneath each floating element. Add clean infographic text labels with thin pointer lines using these exact labels: “Lettuce” “Salsa” “Cheese” “Meat” “Shell” Ultra-detailed food textures, premium commercial aesthetic, 8K.

Example generated from “复古印尼猫薄荷广告”
GPT Image 2en

Ultra realistic vintage Indonesian catnip advertisement poster, retro 1970s paper texture, distressed print, faded colors. A black-and-white tuxedo cat wearing cute vintage housewife clothes floating happily in the air after smelling catnip, euphoric expression, swirling catnip leaves, absurd Indonesian meme energy. Bold retro typography: “BIKIN KUCING SENENG FLY!” fake catnip jar product, old-school badges, price tag, nostalgic warung advertisement aesthetic, cinematic lighting, grain, scratches, authentic aged poster look.

Example generated from “复古巴士上的红风衣女郎”
GPT Image 2mixed

[中文] 一位时尚年轻女子坐在老式复古巴士的前缘,身穿红色长风衣、羊毛无檐小便帽、圆形蓝色反光太阳镜、叠层项链和粗犷的棕色皮靴。她有着波浪状金发,带着自信而梦幻的表情,仰望天空。巴士漆面剥落,呈青绿色与铁锈红色调。明亮清澈的蓝天,城市背景建筑极少,柔和日光,电影级色彩分级,浅景深,高端时尚旅行氛围,编辑摄影,超写实,4K分辨率,锐利对焦,自然肌肤质感,戏剧性构图,电影静帧美学。 [English] A stylish young woman sitting on the front edge of an old vintage bus, wearing a long red trench coat, woolen beanie cap, round blue reflective sunglasses, layered necklaces, and rugged brown leather boots. She has wavy blonde hair and a confident, dreamy expression, looking upward toward the sky. The bus is weathered with peeling paint in turquoise and rust red tones.Bright clear blue sky, urban background with minimal buildings, soft daylight, cinematic color grading, shallow depth of field, high fashion travel vibe, editorial photography, ultra-realistic, 4K resolution, sharp focus, natural skin texture, dramatic composition, film still aesthetic.

Example generated from “复古日系迷你橡皮商品包装”
GPT Image 2mixed

添付されたキャラクターシートをSTRICTなデザインリファレンスとして使用すること。 キャラクターの顔、髪型、目の形、プロポーションは絶対に変更しない。 ■目的: キャラクターを日本の「ちび消しゴム商品」として完全に商品化し、 実際に文房具売り場やガチャで販売されているようなリアルなパッケージ商品写真を作成する。 ■コンセプト: 「100円ショップや文房具店で売られている袋入りちび消しゴム商品」 ■消しゴム本体: (※前回と同じ仕様を完全維持) - 強いデフォルメちびキャラ - 厚みのあるブロック形状 - 完全マットなラバー素材 - 微細な粒子・粉・削れ・摩耗あり - 印刷ズレ・色ブレあり - 50個以上のランダム構成 ■パッケージ(超重要): - 小さな透明ビニール袋(OPP袋) - 上部に紙ヘッダー(吊り下げ用の穴あり) - ヘッダーはややチープな印刷(軽いズレ・インクのムラ) - ビニールはシワあり、やや曇り、静電気で中身に張り付く - 一部空気が入ってふくらみあり - シール部分に軽いヨレ ■グラフィックデザイン: - 日本の子供向け文房具風デザイン - ポップでカラフル(ピンク・黄色・水色ベース) - 手書き風フォントや丸文字 - 商品名ロゴ(オリジナルでOK) - 「ミニけし」「ちびけし」などの表記 - 星・ハート・キラキラ装飾 ■情報要素(リアル感強化): - JANコード(バーコード) - 「対象年齢6才以上」 - 「食べられません」注意書き - 「全◯種」や「ランダム封入」 - 小さな会社名(架空) - MADE IN JAPAN or CHINA表記 ■構図: - パッケージがメインで画面中央 - 周囲に少しだけこぼれた消しゴム - 1〜2個は袋から出ている - 指先が1つをつまもうとしている演出 - 一部フレームアウトで自然さ ■レア要素: - 蛍光カラーやグラデーションの特別個体を1つ混ぜる - 視線誘導として目立つ位置に配置 ■ライティング: - 明るい自然光(ややハイキー) - 柔らかい影 - 商品写真のような清潔感 ■カメラ: - マクロ寄り - 浅い被写界深度 - 中央シャープ ■背景: - 白〜パステルのテーブル - ほんのりドットやポップ柄 - シンプルで清潔 ■禁止: - プラスチック感 - glossy表現 - 高級すぎる質感(安っぽさが正解) - 完璧すぎる印刷 ■出力: - 実在する商品にしか見えないレベル - コンビニや100均にありそうなリアリティ - SNSで「これ欲しい」と思わせる完成度

Example generated from “夏日柑橘苏打高转化广告图”
GPT Image 2mixed

[中文] 图像生成: 商品广告照片, 适合夏天的季节商品, 碳酸饮料, 名称="夏柑SODA", 形状=PET瓶500ml, 研究2025年作为饮料广告的高CTA设计后设计并生成图像规格, 宽高比3:4 [English] Image generation: Product advertising photo, Seasonal product suitable for summer, Carbonated beverage, Name="Summer Citrus SODA", Shape=500ml PET bottle, Design and generate image specifications after researching high CTA design as a beverage advertisement in 2025, Aspect ratio 3:4

Example generated from “夏日牵手回眸电影肖像”
GPT Image 2en

Cinematic portrait photography, ultra-photorealistic, 2160x3840 vertical composition, 50mm or 85mm portrait lens rendering, shallow depth of field, clean translucent summer natural-light color grading — not overly yellow, not over-filtered. Subject: a young beautiful adult East Asian woman, [describe face shape and features, e.g. soft heart-shaped face, refined classical features, bright almond/fox eyes, petite nose bridge, naturally full lips], overall vibe sweet, sunny, energetic, cute with a touch of allure. Gaze highly engaging — bright, clear, natural catchlights, as if it speaks; corners of mouth slightly lifted, expression gentle, vivid, natural. She walks along a [scene, e.g. garden stone path / tree-lined lane / European street / courtyard], right hand reaching back to hold the hand of someone behind her; only their hand appears in the lower-left corner — like a first-person couple's POV snapshot. She glances back at the camera while her body stays in a forward walking motion, posture elegant and natural, clearly a candid captured moment with a faint in-love feeling. Long [hair color] hair, [style, e.g. naturally wavy / relaxed big waves / airy bangs / half-up], many strands tousled and flying in the wind, richly layered and dynamic. Strong natural side-backlight rims the hair edges — clean, crisp rim light and semi-translucent glow, hair edges lit as if by sunlight, light and luminous. This is the core highlight of the image. She wears [outfit, e.g. white lace slip dress / beige slip dress / light-blue short-sleeve top with white skirt / light-pink fitted dress], fabric texture natural, material light and soft. Bright natural summer sunlight realistically warms her skin, shoulders, collarbone, and clothing with soft, clean highlight transitions. Skin texture: extremely realistic — visible fine pores, natural skin texture, faint imperfections, subtle tone variation, soft sheen. Cheeks, nose tip, shoulders show natural delicate gradations in sunlight. Translucent, healthy, real and refined — no plastic look, no waxwork, no over-smoothing. Background: soft atmospheric blur, never distracting. Avoid: over-smoothing, plastic skin, CG look, anime look, wig look, stiff expression, dead eyes, stiff poses, overall yellow cast, overexposed face, distorted features, wrong fingers, deformed hands, cluttered background, heavy influencer retouching.

Example generated from “多风格签名选择海报”
GPT Image 2zh

你是一个高端签名设计系统 + 风格人格视觉系统。 任务: 仅基于用户输入的「姓名」,生成一张「多风格签名选择海报(卡片式结构)」。 目标是把名字转译为具有笔势、气质与力量感的签名设计系统,让用户产生选择欲、认同感和分享欲。 输入信息: 姓名:[输入你的昵称] 禁止要求额外信息,必须自动完成气质与风格推断。 隐藏执行逻辑: 1. 字形与笔势分析: - 结构:疏密、横竖比例、重心位置 - 节奏:连贯、停顿、爆发、收束 - 适配:连笔程度、草写程度、变形空间 2. 气质推断: 清冷、张扬、克制、商业、文艺、松弛、锋利、高级。 3. 生成 6 个签名分支: - 全部适配该姓名 - 每一个都有明确书写风格 - 差异来自笔势、节奏、结构和收笔方式 整体画面: 9:16 竖版海报,极简、高级、干净、有设计感、适合传播。 背景使用纯白或极浅灰渐变,留白不少于 40%。 顶部标题区: 主标题可用: 「你的名字,适合哪种签名?」 或: 「[姓名] · 签名风格选择」 副标题: 「不同笔势,不同气场」 排版为黑色与灰色,高级字距,留白充足。 签名卡片区域: 使用整齐网格卡片布局,推荐 2 列 × 3 行,共 6 个卡片。 每个卡片统一尺寸、统一间距、整体对齐干净。 卡片样式: - 轻微圆角 8-16px - 无明显边框,或极细描边 - 极轻阴影 - 背景为纯白微差、极浅灰,或轻微宣纸 / 磨砂质感 视觉目标接近高级杂志排版,避免强 UI 感、厚卡片和 App 组件感。 签名生成规则: 签名必须基于书写动作生成,避免只做字体变形。 每一个签名风格在生成前,先确定一套明确书写行为规则: 1. 起笔方式:轻触起笔、重压起笔、直接横扫、从左下进入或从中段切入。 2. 连笔结构:前两个字强连笔后面断开、全连笔一气呵成、只连接偏旁。 3. 节奏变化:快到慢再收、慢到爆发再拉伸、或均匀节奏。 4. 结构变形:横向拉长、垂直压缩、整体右倾或左倾、字间重叠或错位。 5. 收笔设计:尾笔长甩、突然收断、回钩、渐隐收尾。 6 种签名方向: 1. 极简理性:接近品牌签名 2. 狂放张力:强烈连笔和拉伸 3. 松弛随性:手写感强 4. 东方行草:飞白和墨感 5. 锋利结构:几何感和断裂 6. 实验风格:允许部分不可读,但需要强设计感 色彩策略: 整体以黑、灰、白为主。每个卡片允许一个极轻微点缀色,例如冷灰蓝、香槟金、墨黑、暖棕、深绿。 避免大面积色块和花哨配色。 底部互动区: 底部居中加入小号灰字: 「选一个,作为你的专属签名。」 或: 「你是第几种?」 光影与质感: 高级棚拍光、柔光环境、细腻阴影、干净空气感。 质感参考 Apple 发布会视觉和高端品牌视觉。 禁止项: 不要字体拼贴,不要普通书法字,不要 UI 卡片风,不要颜色杂乱,不要签名太小,不要排版松散,不要缺乏笔势,不要模板拼接感。 最终目标: 生成一张高级、干净、有秩序、有笔势张力的 6 风格签名选择海报。 用户一眼能选出最像自己的一款签名。

Example generated from “夜间手机光沙发肖像”
GPT Image 2en

A young adult woman with soft refined features, thin metal glasses, and shoulder-length dark tousled hair, leaning forward across a dark upholstered couch at night. She wears a pale cream lace-trim camisole with thin straps and matching soft shorts. One hand holds a smartphone close to the foreground, the screen glow casting cool reflections on her fingers and glasses lenses. Her expression is dreamy and softly tired, eyes lifted toward the camera as if she just looked up from scrolling, lips gently closed in a relaxed pout. Shot in a vertical 3:4 frame at slightly above eye level, medium close-up to three-quarter portrait. Warm dim tungsten room light mixed with cool phone-screen reflections, no flash, soft falloff across the couch and wall. Shallow depth of field, soft low-light grain, slight motion blur, natural imperfect sharpness. Background: plain beige-gray wall, minimal decor, late-night atmosphere. Soft glam makeup: subtle eyeliner, long lashes, smooth skin, glossy pink-nude lips. Realistic social-media night portrait aesthetic.

Example generated from “大堡礁复古旅行海报”
GPT Image 2en

Create a premium editorial travel poster illustration of the Great Barrier Reef, Australia. Style: Flat vector illustration, ultra-clean minimalism, mid-century modern travel poster aesthetic, inspired by vintage tourism prints and Scandinavian graphic design. No photorealism, no textures, no noise, no gradients. Use crisp shapes, smooth color blocks, and harmonious vibrant tones. Composition (vertical 3:4 layout): Foreground (underwater): A rich coral reef ecosystem filled with colorful corals in pink, orange, yellow, and red tones. Include tropical fish of various species (striped, bright yellow, blue, and orange), and a large sea turtle swimming gracefully toward the right. Clear turquoise water with high visibility. Midground: A female snorkeler swimming horizontally just beneath the water surface, wearing fins and a snorkel mask, observing the reef below. Light rays subtly pass through the water surface. Background (above water): A calm tropical ocean with shallow reef patches visible through crystal-clear water. A white leisure boat floats peacefully on the left, and a small sailboat appears far in the distance. On the horizon, soft green islands or hills stretch across. Sky: Bright blue sky with fluffy white clouds and a few birds flying, enhancing the serene vacation mood. Typography: At the bottom of the poster, include bold uppercase text: “GREAT BARRIER REEF” Below it, smaller spaced-out text: “AUSTRALIA” Add a small decorative coral icon between divider lines. Mood & Lighting: Bright daylight, calm, inviting, tropical paradise atmosphere. Colors should feel fresh, vibrant, and relaxing with strong contrast between coral reef and ocean blues.

Example generated from “大师级真迹复刻”
GPT Image 2mixed

[中文] 帮我生成xxxx真迹图片 [English] Help me generate xxxx authentic picture

Example generated from “天坛古建拆解全图”
GPT Image 2mixed

[中文] 生成一个天坛的建筑拆解图,有详细的说明,中式美学风格 [English] Generate an architectural exploded view of the Temple of Heaven, with detailed annotations, Chinese aesthetic style

Example generated from “头发里的微型城市”
GPT Image 2en

Macro photograph of a miniature city hidden in human hair, clearly on a real human head, with part of the forehead and hairline visible, realistic skin texture with pores, tiny people walking through the streets between the hair strands, extremely small but realistic proportions, macro photography, 85mm lens, shallow depth of field, natural lighting, neutral colors, no warm tones, ultra realistic hair with visible roots, natural imperfections, slightly messy strands, realistic materials, slightly dirty buildings, no perfect surfaces, photorealistic, looks like a real photo, no illustration, no CGI, no glow

Example generated from “夸张动漫风主体重绘”
GPT Image 2en

Create a trending anime art style image from the uploaded subject. Use confident line-work with slight variation and minimal cel shading using flat shadow shapes. Use bright, saturated colors and clean graphic lighting. The style is defined by exaggerated, cartoonish character proportions featuring highly expressive, simplistic facial features that allow for immense emotional range, with highly varied stretched anatomy.Transform the environment into a slightly warped space with playful perspective distortion and simplified objects. Composition and tone should be energetic, lively, and comedic in a fully stylized, non-realistic world

Example generated from “夹层式品牌编辑海报”
GPT Image 2en

[BRAND NAME]. You are a world-class editorial designer. STEP 1, DYNAMIC SUBJECT LOGIC: - Subject pick: independently study [BRAND NAME] and choose the right hero subject. - Sandwich layering: weave the subject through the background shapes. Parts of the car or figure must sit hidden behind geometric blocks, while other parts (wheels, limbs, props) overlap in front of those blocks to fake real 3D depth. STEP 2, GRID & GEOMETRY: - Layout: a clean 2x2 grid composition. - Overlays: drop large bold geometric arcs and circles on top of the grid. - Visual balance: place one iconic product prop (a floating key fob for cars, a ball for sports, etc.) in its own quadrant to counterweight the subject. STEP 3, SOPHISTICATED MUTED PALETTE: - No aggressive neon, no oversaturated colors. - Pull [BRAND NAME]'s core colors and shift them into a "sophisticated muted" range. Use desaturated, earthy, dusty versions of the brand colors (dusty rose instead of hot pink, sage green instead of bright mint, slate blue instead of royal blue). - Finish: matte flat color blocks, zero gradients. STEP 4, PHOTOGRAPHY & LIGHTING: - Subject style: high-end commercial studio photography. - Lighting: soft diffused studio light, gentle highlights, no harsh shadows. - Integration: the subject must feel physically embedded into the graphic grid. STEP 5, MINIMALIST BRANDING: - Drop a clean single-color [BRAND NAME] logo dead-center on one background block. No tagline, just the iconic symbol.

Example generated from “奔赴山海胶片感海报”
GPT Image 2mixed

[中文] 设计一张主题是”奔赴山海”的胶片感摄影风格的海报 [English] Design a poster with the theme of "running towards the mountains and seas" in a film photography style

Example generated from “奢华个人色彩档案信息图”
GPT Image 2en

LUXURY PERSONAL COLOR PROFILE — EDITORIAL LAYOUT Studio portrait of subject as anchor — skin retouched to luminous glass-like perfection, preserved natural structure, realistic pore texture, soft directional key lighting, no facial alteration. Background: warm ecru parchment with subtle linen grain texture. Layout reads like a Vogue Italia beauty supplement printed on heavyweight matte stock. Structured editorial grid, 3-column asymmetric, wide negative space, serif condensed display headers, all labels in spaced uppercase tracking, cohesive warm ivory/sand/ecru background system throughout all panels, ultra-photorealistic 8K, soft diffused studio lighting, flat elegant surfaces, no drop shadows. PANELS: ① UNDERTONE DIAGNOSIS — Tonal spectrum bar from cool ash to warm amber, precision needle marker on subject's reading. Labels: Cool / Neutral-Cool / Neutral / Neutral-Warm / Warm. Fine annotation text. ② SEASONAL COLOR PALETTE — 10–12 fabric-textured swatches in subject's optimal season. Each labeled with poetic color name and HEX. Grouped: Power Colors / Softest Options / Harmonizing Neutrals. ③ COLORS TO AVOID — Desaturated row of clashing tones with fine editorial strikethrough. Clean, non-harsh presentation. ④ MAKEUP CARTOGRAPHY — Eyeshadow gradient dust swatches / blush tones fanned on skin strip / lip spectrum barely-there to bold / highlighter finishes labeled: champagne, rose gold, pearlescent ivory. ⑤ HAIR COLOR SPECTRUM — Curved gradient strip: base, dimension, highlight, contrast tones. Gold bracket indicators on best options. ⑥ JEWELRY & METAL GUIDE — Flat-lay editorial render: yellow gold, rose gold, oxidized silver, platinum finishes alongside complementary stone tones. Minimal styling. ⑦ YOU IN YOUR PALETTE — 3–4 editorial lookbook frames, subject in palette-correct outfits. Mood labels: Quiet Luxury / Off-Duty Editorial / Evening Presence. ⑧ CAPSULE WARDROBE GRID — Outfit flatlay: tops, bottoms, outerwear, shoes, bag — all palette-correct. Coordinating lines showing interchangeability. Net-a-Porter editorial aesthetic. ⑨ PRINTS & PATTERNS — 4 fabric print thumbnails: micro geometric, tonal abstract, classic stripe, floral scale. One-line styling note per print. ⑩ STYLE ARCHETYPE — Single typographic panel. Style identity title set large (e.g. "Modern Romantic / Warm Classicist"). Three defining aesthetic words. Four-line editorial wardrobe philosophy note. RENDER SPECS: Ultra-photorealistic, 8K, editorial magazine print quality, warm neutral color grading, soft diffused studio lighting consistent across all panels, one serif display font + one fine sans-serif body font, no gradients, flat matte surfaces only.

Example generated from “奢华机械腕表技术图鉴”
GPT Image 2en

2x2 grid 16:9, do this for 4 most expensive strangest watches ever made: class Haute_Horlogerie_DNA: def __init__(self): self.subject = "[TIMEPIECE]" self.parents = { "composition_parent": "Exploded movement diagram with transparent case", "material_parent": "Brushed titanium, sapphire crystal, rose gold gears, alligator leather", "graphic_parent": "Swiss manufacture technical brochure with elegant data panels", "atmosphere_parent": "Crisp daylight studio, pure white background, subtle reflection on polished surfaces" } self.mutations = { "semantic_mutation": "The balance wheel reveals a miniature cosmos ticking inside", "information_mutation": "Power reserve indicator, frequency, complication callouts, hand-finishing grades, assembly timeline", "medium_mutation": "Smooth matte premium paper with embossed logo", "scale_mutation": "Grain-level view of Côtes de Genève finishing and jewel bearings" } self.style_mix = [0.30, 0.30, 0.25, 0.10, 0.05] def generate_subject(self): subject = """ [TIMEPIECE] shown in its full mechanical glory. The dial, hands, movement, and strap float in perfect alignment against a bright, clean background. Every gear and spring is highlighted with exacting clarity. """ return render( subject, format="luxury watch advertisement with technical insert", title="[MODEL REFERENCE]", subtitle="[MANUFACTURE / COLLECTION]", constraints="bright white space, metallic brilliance, hyper-detailed, modern elegance" )

Example generated from “奢华魅力黑人女性海滨摄影”
GPT Image 2mixed

[中文] 奢华魅力美容肖像:, 美丽的黑人女性, 青春活力, 奶油香草色, 丝绸柔顺发, 红木色, 微妙的自信, 有质感的面料, 蓝宝石色, 极简珠宝, 海滨微风, 镜头光晕效果, 怀旧的, 电影镜头, 对称构图, 柔焦, 高级时尚摄影, 单色的, 水光质感, 神秘张力, 分层元素 [English] Luxury Glam Beauty Portrait:, Beautiful Black woman, youthful spirit, creamy vanilla, silk press, mahogany red, subtle confidence, textured fabric, sapphire blue, minimal jewelry, beachside breeze, lens flare effect, nostalgic, cinematic lens, symmetrical composition, soft focus, high fashion photography, monochromatic, dewy finish, mysterious tension, layered elements

Example generated from “威化岛回军前夕李成桂动态”
GPT Image 2zh

[中文] 태조 이성계의 X 페이지(위화도 회군을 벌이기 직전- 최영 장군과 서로 디스하는 내용이 담긴 게시글들)을 만들어 주세요. [English] Please create an X page of King Taejo Yi Seong-gye (right before carrying out the Wihwa Island Retreat - containing posts where he and General Choi Yeong are dissing each other).

Example generated from “宅男必看绝美二次元少女”
GPT Image 2mixed

[中文] 生成高质量美女(宅男必备) [English] Generate high-quality beautiful girl (otaku must-have)

Example generated from “宋朝文人的赛博朋友圈”
GPT Image 2mixed

[中文] "宋朝人的朋友圈"/"SONG DYNASTY SOCIAL MEDIA FEED",古今穿越幽默融合界面设计风格,画面模拟手机社交媒体界面,但内容全部是宋朝场景头像是宋代文人画像,用户名"苏东坡SuShi_Official",发布内容"刚到黄州,被贬了但心情还行。今天自己做了东坡肉,味道绝了,附菜谱:",配图为工笔画风格的东坡肉特写,点赞列表"黄庭坚、秦观、佛印等126人",评论区"王安石:呵呵""司马光:还是那个味道",界面元素如点赞图标用宋代花纹替代,状态栏显示"大宋移动 5G"和"元丰三年",配色为手机深色模式搭配宋代雅致色调,历史与社交媒体的趣味碰撞杰作 [English] "Song Dynasty People's Moments"/"SONG DYNASTY SOCIAL MEDIA FEED", Ancient and modern time-travel humor fusion interface design style, The image simulates a mobile phone social media interface, but the content is entirely Song Dynasty scenes, The avatar is a portrait of a Song Dynasty literati, Username "Su Dongpo SuShi_Official", Post content "Just arrived in Huangzhou, demoted but feeling okay. Made Dongpo pork myself today, tastes amazing, recipe attached:", The attached image is a close-up of Dongpo pork in Gongbi painting style, Likes list "Huang Tingjian, Qin Guan, Fo Yin etc. 126 people", Comments section "Wang Anshi: Hehe" "Sima Guang: Still the same taste", Interface elements such as the like icon are replaced with Song Dynasty patterns, The status bar shows "Great Song Mobile 5G" and "Third Year of Yuanfeng", The color scheme is mobile phone dark mode paired with elegant Song Dynasty tones, A masterpiece of fun collision between history and social media

Example generated from “完美匹配的海报广告图”
GPT Image 2mixed

[中文] 生成一张与这张图片完美匹配的广告图片。信息量要多一些。 [English] Generate an advertising image that perfectly matches this image. There should be a lot of information.

Example generated from “官方角色设定资料卡”
GPT Image 2mixed

[中文] 基于此角色和背景,请制作一份类似官方设定资料的角色资料卡。 ・包含三视图:正面、侧面和背面 ・添加角色面部表情的变化・分解并展示服装和装备的详细部分 ・添加色板・包含世界观设定的简要说明 ・总体上,使用有组织的布局(白色背景,插画风格) [English] Based on this character and background, please create a character reference sheet similar to official setting materials. ・Includes three-view drawings: front view, side view, and back view ・Add variations of the character's facial expressions ・Break down and display detailed parts of the clothing and equipment ・Add a color palette ・Include a brief explanation of the worldview setting ・Overall, use an organized layout (white background, illustration style)

Example generated from “定制专属风格界面设计系统”
GPT Image 2mixed

[中文] 用xx风格帮我生成一套UI设计系统,包含网页、移动端、卡片、控件、按钮 以及其它 [English] Generate a UI design system for me in xx style, including web pages, mobile, cards, controls, buttons, and others

Example generated from “宝玉 #134”
GPT Image 2en

Soft poetic children's book illustration with watercolor and gouache textures.Clear gentle daylight with slightly brighter highlights.Muted pastel colors with soft blue and warm tones.Visible brush strokes and paper grain.Minimalist composition with large negative space.Calm, thoughtful, slightly open-ended atmosphere. Child character (around 12 years old).Subtle visual metaphors like light, shadow, perspective, reflection.Hand-painted picture book style, not cartoon, not anime, not 3D. Two children in calm conversation,soft connection forming.

Example generated from “宝玉 #154”
GPT Image 2zh

Present a clear, 45° top-down view of a vertical (9:16) isometric miniature 3D cartoon scene, highlighting iconic landmarks centered in the composition to showcase precise and delicate modeling. The scene features soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadow effects. Weather elements are creatively integrated into the urban architecture, establishing a dynamic interaction between the city's landscape and atmospheric conditions, creating an immersive weather ambiance. Use a clean, unified composition with minimalistic aesthetics and a soft, solid-colored background that highlights the main content. The overall visual style is fresh and soothing. Display a prominent weather icon at the top-center, with the date (x-small text) and temperature range (medium text) beneath it. The city name (large text) is positioned directly above the weather icon. The weather information has no background and can subtly overlap with the buildings. The text should match the input city's native language. Please retrieve current weather conditions for the specified city before rendering. City name:【上海】

Example generated from “实拍背景涂鸦人物替换”
GPT Image 2en

Transform ONLY the people in the uploaded photo into adorable hand-drawn doodle characters while keeping the original photographic background unchanged. CORE RULE: Background = original realistic photo. People = cute hand-drawn doodle characters. PRESERVE THE BACKGROUND: Keep the original sky, landscape, buildings, water, furniture, ground, plants, railings, objects, lighting, colors, perspective, camera angle, framing, and textures as close to the original photo as possible. Do NOT redraw, simplify, illustrate, or apply doodle/crayon/pencil effects to the background or environmental objects. TRANSFORM ONLY PEOPLE: Replace each person with a charming, naive doodle version while preserving: - exact number of people - original position and relative scale - front/back/side/three-quarter orientation - head and body direction - pose and gesture - arm and leg positions - interactions with people or objects - hairstyle, clothing colors, and major accessories IMPORTANT: If someone faces away, keep them back-facing. If sideways, keep them sideways. If facing forward, keep them forward. Never rotate a person toward the viewer or invent a face that is not visible. CUTE DOODLE STYLE: Freely reinterpret realistic anatomy into an adorable, imperfect character: - oversized round head - tiny compact body - short simplified arms and legs - tiny hands and feet - cute awkward proportions - loose scribbled hair - tiny dot eyes and simple facial features when visible - rosy scribbled cheeks when appropriate Keep the original pose recognizable, but simplify and slightly exaggerate it for cuteness. DRAWING STYLE: Loose naive hand-drawn doodle, like a quick children's sketch. Use thin shaky black outlines, imperfect shapes, overlapping sketch lines, scribbled colored-pencil or crayon fills, uneven coloring, white gaps, and slightly messy edges. The character should look intentionally roughly drawn but extremely cute. OBJECTS: Objects, furniture, scenery, and items around the people should remain photographic whenever possible. A doodle character may naturally touch or hold a real photographic object. INTEGRATION: Keep correct scale, ground contact, depth, and occlusion so the doodle characters naturally occupy the same locations as the original people. FINAL LOOK: It should feel like the real people were removed from the original photograph and replaced with adorable little hand-drawn doodle versions of themselves, while the real-world background remained untouched. Prioritize: 1. Original photographic background 2. Person position and scale 3. Exact body orientation 4. Pose and gesture 5. Cute exaggerated doodle character design Avoid full-image illustration, background doodling, realistic anatomy, anime, manga, 3D cartoon, polished digital art, vector lines, changed poses, changed orientation, added people, or invented faces.

Example generated from “室内晨间写实摄影”
GPT Image 2en

A close-medium shot of a young Japanese woman in her bedroom on an ordinary morning, captured in authentic daily life photography as a natural candid moment. She is seated sideways on the edge of the bed, not fully awake yet, photographed from a slightly elevated three-quarter angle with cool-to-warm morning window light entering from the left. East Asian young woman in her early 20s. Almond-shaped eyes with soft natural single eyelids, slightly elongated eye corners, still carrying the heaviness of just waking. Straight refined nose with a delicate bridge. Skin tone fair to light beige — skin subsurface scattering visible under the soft directional morning window light, specular micro-highlights catching gently on her cheekbone and nose ridge, fine skin texture perceptible, no makeup. Naturally straight fine black hair loosely gathered, slightly disheveled from sleep. She wears a loose oversized cotton sleep shirt and soft shorts, nothing styled. Her gaze drifts toward the window, posture relaxed and unhurried, one hand resting on her knee, the other barely holding a phone face-down. The bedroom background suggests real life — slightly unmade linen, a potted plant near the window partially in shadow, small cluttered bedside items. Two or three stray hairs fall across her cheek in natural asymmetric displacement, not geometrically placed. Soft directional morning light from a side window, cool-to-warm transition across her face and shoulder, long gentle shadows on the bedding behind her. The mood is quietly adrift — not sad, not performing, just suspended in the unhurried first minutes of the day. Subtle ISO 400 film grain in shadow areas, photographic noise texture not CG render smoothness. Aspect ratio 2:3. No watermark, no text overlay, not cartoon, not digitally painted, not illustration, not anime.

Example generated from “室内空间渲染图”
GPT Image 2en

A vintage, late 90s amateur flash photograph of a young man repairing an arcade machine. He is kneeling on a dark, patterned arcade carpet, looking back over his shoulder directly at the camera with a neutral expression. He wears a dark short-sleeved t-shirt, baggy blue jeans, chunky white sneakers, and a dark baseball cap. The lower front panel of the arcade cabinet is wide open, exposing its complex internal electronics, including a tangle of wires, green circuit boards, a large speaker, and metal cooling fans at the base. The side of the cabinet features vibrant pink, black, and white graphics with the text "{argument name="arcade game title" default="Dancing Stage"}" and the brand "{argument name="arcade brand" default="KONAMI"}". The setting is a dimly lit arcade interior with other glowing game cabinets visible in the blurred background. A screwdriver lies on the carpet near the man's knee. The image features harsh direct flash lighting, a slightly grainy film texture, deep shadows, and a nostalgic Y2K aesthetic.

Example generated from “家庭旅行纸雕拼贴”
GPT Image 2en

Adorable kawaii family travel collage, combining four different scenes in one composition, cute anime-inspired parents, friends and children taking selfies and exploring together, handcrafted paper-cut diorama style, layered cardboard and felt textures, miniature world aesthetic, cozy pastel color palette, soft cinematic lighting, playful vacation atmosphere, urban city station scene, shopping mall selfie corner, outdoor nature park, and crowded playground blended into one seamless scrapbook-style artwork, charming sticker-like white outlines around characters, tiny tourists and pedestrians in background, whimsical handcrafted textures, soft depth of field, highly detailed paper craft illustration, warm nostalgic mood, cute casual outfits with glasses, caps, bags and sandals, dreamy Instagram kawaii aesthetic, storybook composition, ultra detailed miniature environment, 3D layered paper art, tilt-shift effect, cozy wholesome family travel vibes, premium handcrafted look, high detail, 8k, vertical composition

Example generated from “导览式科普绘本”
GPT Image 2zh

《导览式科普绘本》提示词: 请根据【主题】创作一张高完成度的「导览式科普绘本」风格插画。 这是一张结合“大型场景主视觉 + 导览路线 + 可爱导览 IP + 知识站点 + 儿童科普绘本质感”的场景导览式科普图解页。画面需要让观者像被带着参观一个复杂系统一样,边看边理解主题背后的运行逻辑、空间结构、流程关系和关键知识点。 【基础设定】 主题:【填写主题,例如发射场的一天 / 一个集装箱的旅行 / 地铁站里的秘密路线 / 下潜到深海的一小时 / 机场如何运转 / 医院急诊系统 / 智慧农场 / 消防站出警流程】 画幅比例:【4:3 横版】 主色调:【根据主题自动匹配,整体保持明亮、清爽、儿童友好】 风格方向:【现代儿童科普绘本 / 场景导览式图解 / 高完成度数字插画】 【核心表达】 请围绕【主题】设计一个完整的大型场景或复杂系统。画面中必须有一个明确的主视觉场景,例如大型设施、交通系统、科技装备、自然探索场景、城市公共系统或生产流程。主体要足够清晰、有规模感、有细节,能够成为第一眼的视觉中心。 画面要通过“导览路线”的方式组织信息,避免仅把场景做成静态陈列。请设计一条清晰的参观路线、流程路线、时间线或空间动线,让读者可以沿着路线一步步理解这个系统是如何运行的。 【导览 IP 设计】 请为本图设计一个原创、可爱、亲和的导览小 IP。导览 IP 可以是小动物、小朋友、拟人化工具或其他适合主题的原创形象,但必须具有独立原创性,不要照搬任何参考图中的角色、动物形象、服装、配色或搭档关系。 导览 IP 的作用是: 1. 开场介绍主题 2. 指向关键知识点 3. 引导读者顺着路线阅读 4. 增加儿童绘本的陪伴感和趣味性 导览 IP 可以在画面中出现 2-3 次,但不要过度抢主视觉。角色应圆润、可爱、有表情、有动作,适合儿童科普绘本。 【信息结构】 画面中请设置 3-6 个“知识站点”,每个站点用简短中文标签和短说明表达。站点命名可以采用: - 第1站|xxx - 第2站|xxx - 重点观察|xxx - 小知识|xxx - 为什么|xxx - 如何工作|xxx 每个知识点都要围绕主题的核心运行逻辑展开,不要写空泛说明。文字要短、清楚、自然,避免长段落,适合儿童阅读。 【画面模块】 整张图建议包含以下模块: 1. 顶部主标题区:清楚写出主题名称 2. 开场导览区:导览 IP 引出主题 3. 大型主场景区:展示主题系统的完整场景 4. 导览路线区:用箭头、虚线、路径、时间节点或流程线串联知识点 5. 知识站点区:用小信息框、导览牌、局部标注展示关键知识 6. 小百科 / 小贴士区:补充一个有趣知识 7. 收尾区:让导览 IP 做简短总结或引导 【构图要求】 画面采用 4:3 横版构图,整体像一本高质量儿童科普绘本的跨页,也像一张儿童科技馆导览图。画面需要有清晰的视觉重心:大型主场景占据主要空间,导览路线贯穿画面,知识模块自然分布在周围。信息丰富但不能杂乱,阅读路径要顺畅。 【视觉风格】 整体采用现代儿童科普绘本风格: - 明亮、清爽、干净的色彩 - 清晰自然的手绘线条 - 高完成度数字插画质感 - 细节丰富但有秩序 - 可爱但不低幼 - 有科普图解感 - 有导览地图感 - 场景真实可信,但表达方式亲和 【文字与标注】 文字以中文为主,使用短标题、短标签、简短说明。不要生成大段复杂文字。信息框应像儿童科普书中的导览牌、知识卡片或小贴士。文字要尽量清晰、简洁、可读。 【最终目标】 让整张图像一页高质量的儿童科普绘本:孩子第一眼被可爱角色和大场景吸引,第二眼能顺着路线读懂系统如何运行,第三眼还能继续发现细节和知识点。画面要具有系列化潜力,方便后续替换不同主题继续创作同类型图片。

Example generated from “封面排版设计图”
GPT Image 2mixed

[中文] 以涂鸦速写风表现【一个厉害的AI builder】,整体呈现快速勾勒、自由变形、即兴手绘与草稿式的视觉效果。线条随手、夸张、可粗细不一,略显凌乱但具有节奏和表现力,强调概括、夸张、趣味和随性,而不是严谨写实或精细刻画。 颜色采用粗糙、干刷感明显的块面表现,可保留不均匀的涂抹痕迹、刷痕、飞白与覆盖感,色彩根据【主题/主体】自动适配,但整体保持涂鸦式、速写式、概括式的表达。不要透明水彩晕染效果,不要细腻水彩过渡,不要纸纹理,不要柔和雾化,不要梦幻质感。 背景以留白为主,保持简洁、轻松、未完成感和设计感,可加入少量辅助性符号、箭头、记号、圈画、重复线、随手写的文字或其他涂鸦元素,以增强速写本或随笔式视觉语言,但不可过于拥挤,不可破坏主体和留白气质。 画面内容不需要预先写清楚,由【一个厉害的AI builder】自动推演并生成最适合的主体形象、动作、相关元素、符号或简化场景,整体保持统一的涂鸦速写风和夸张概括的表现方式,避免复杂写实背景和过度铺陈。 画面中需自然加入专属签名"BlanPlan",作为画面的一部分,位置低调但清晰,可放在左下角、右下角或标题附近,风格需与整体版式统一,像作品署名或设计落款;签名字体精致、克制、高级,不可过大,不可破坏主体构图,不可显得突兀或廉价。 [English] Express [an awesome AI builder] in a graffiti sketch style, overall presenting a visual effect of quick sketching, free deformation, impromptu hand-drawing and draft-like. The lines are casual, exaggerated, and can vary in thickness, slightly messy but with rhythm and expressiveness, emphasizing summarization, exaggeration, fun and casualness, rather than rigorous realism or fine depiction. The colors use rough blocks with obvious dry brush feel, retaining uneven smearing traces, brush strokes, flying white and covering feel, the colors automatically adapt according to [theme/subject], but overall maintain a graffiti-style, sketch-style, and summarized expression. Do not use transparent watercolor smudging effects, do not use delicate watercolor transitions, do not use paper texture, do not use soft atomization, do not use dreamy texture. The background is mainly blank, keeping it simple, relaxed, unfinished and designed, can add a small amount of auxiliary symbols, arrows, marks, circled drawings, repeated lines, casually written text or other graffiti elements, to enhance the sketchbook or essay-style visual language, but it must not be too crowded, and must not destroy the subject and blank temperament. The picture content does not need to be written clearly in advance; [an awesome AI builder] automatically deduces and generates the most suitable subject image, movements, related elements, symbols or simplified scenes, overall maintaining a unified graffiti sketch style and exaggerated summarized expression method, avoiding complex realistic backgrounds and excessive padding. The exclusive signature "BlanPlan" needs to be naturally added into the picture as a part of the picture, the position is low-key but clear, can be placed in the bottom left corner, bottom right corner or near the title, the style needs to be unified with the overall layout, like an artwork signature or design sign-off; the signature font is exquisite, restrained, and high-end, must not be too large, must not destroy the subject composition, must not appear abrupt or cheap.

Example generated from “封面排版设计图”
GPT Image 2mixed

[中文] 创建一个高级的 4:3 演示文稿封面幻灯片,介绍来自 http://chroniclehq.com 的 AI 原生演示平台 Chronicle。 Style: 优雅,极简,现代,高级初创企业美学。类似于高端品牌指南封面(如 Apple / Linear / Notion 风格)。带有微妙深度感的柔和渐变背景,干净的留白,精致的排版,经过打磨的编辑式布局。 Main title: CHRONICLE Subtitle: AI PRESENTATION PLATFORM Body copy (small elegant text): 将原始想法转化为经过打磨的、高影响力的演示文稿。 从笔记、文档、链接或现有幻灯片开始。 使用 AI 生成美观的、符合品牌调性的幻灯片。 在灵活的画布上自由编辑。 导出为 PPT、PDF,或发布为网站。 Feature highlights (small premium labels): STORY-FIRST ON-BRAND DESIGN AI EDITING FREEFORM CANVAS PPT EXPORT TEAM COLLABORATION Bottom-right elegant logo text: chronicle Visual feeling: 商务级高级感,战略级幻灯片质量,咨询级演示文稿,略带未来感但高度专业。 Composition: 干净的编辑式平衡,不对称布局,强烈的留白,演示软件主视觉感。 Aspect ratio: 4:3 Language: 仅限英文 [English] Create a premium 4:3 presentation cover slide introducing Chronicle, the AI-native presentation platform from http://chroniclehq.com. Style: elegant, minimal, modern, premium startup aesthetic. Similar to high-end brand guideline covers (like Apple / Linear / Notion style). Soft gradient background with subtle depth, clean whitespace, refined typography, polished editorial layout. Main title: CHRONICLE Subtitle: AI PRESENTATION PLATFORM Body copy (small elegant text): Turn raw ideas into polished, high-impact presentations. Start from notes, docs, links, or existing decks. Generate beautiful, on-brand slides with AI. Edit freely on a flexible canvas. Export to PPT, PDF, or publish as a website. Feature highlights (small premium labels): STORY-FIRST ON-BRAND DESIGN AI EDITING FREEFORM CANVAS PPT EXPORT TEAM COLLABORATION Bottom-right elegant logo text: chronicle Visual feeling: business-class premium, strategy deck quality, consulting-grade presentation, slightly futuristic but highly professional. Composition: clean editorial balance, asymmetrical layout, strong whitespace, presentation software hero shot feeling. Aspect ratio: 4:3 Language: English only

Example generated from “封面排版设计图”
GPT Image 2zh

{ "type": "fashion product catalog layout", "theme": "A cohesive fashion collection featuring a specific pattern: {argument name=\"pattern description\" default=\"overlapping circular floral mandala motifs in purple, green, blue, orange, and pink\"}", "layout": { "structure": "2x2 grid with a full-width bottom banner", "sections": [ { "id": "01", "title": "{argument name=\"product 1\" default=\"Flared Dress\"}", "subtitle": "フレアワンピース", "main_image": "Woman in patterned flared dress holding white handbag.", "swatch_count": 3, "swatch_descriptions": ["purple variant", "green/blue variant", "orange/yellow variant"], "description_text": "華やかなフレアシルエット。軽やかな素材が優雅な動きを演出します。" }, { "id": "02", "title": "{argument name=\"product 2\" default=\"Silk Scarf\"}", "subtitle": "シルクスカーフ", "main_image": "Woman in white blouse with patterned silk scarf.", "swatch_count": 2, "swatch_descriptions": ["flat pattern detail", "tied knot detail"], "description_text": "首元に彩りを添えるシルクスカーフ。上品な光沢と滑らかな肌ざわり。" }, { "id": "03", "title": "{argument name=\"product 3\" default=\"Tote Bag\"}", "subtitle": "トートバッグ", "main_image": "Woman carrying patterned tote bag.", "swatch_count": 3, "swatch_descriptions": ["purple variant", "blue variant", "orange/yellow variant"], "description_text": "A4サイズも入る収納力。軽くて丈夫、毎日使いたくなるトートバッグ。" }, { "id": "04", "title": "{argument name=\"product 4\" default=\"Pouch\"}", "subtitle": "ポーチ", "main_image": "Patterned zip pouch on table with magazine and vase.", "swatch_count": 3, "swatch_descriptions": ["green/purple variant", "orange variant", "pink variant"], "description_text": "バッグの中を彩る華やかなポーチ。細部まで美しいデザインが魅力です。" } ], "bottom_banner": { "title": "Pattern Design", "description_text": "細やかな線と豊かな色彩が織りなす、唯一無二のパターンデザイン。日常に優雅な彩りを。", "image": "Horizontal strip showing the seamless pattern." } } }

Example generated from “小互 #152”
GPT Image 2zh

高级概念海报,竖版 3:4,核心文字为[输入文字] 请先深度理解'[输入文字]'的表层含义、深层寓意、情绪气质、文化联想、人物命运感与隐含张力,再决定最适合它的画面风格、构图方式、色彩气质和视觉隐喻。 画面风格必须由词义自动生成,不要机械套用统一模板。每个词都应拥有和它自身内涵相匹配的独特视觉语言。 画面中,巨大中文主标题“[输入文字]”必须是绝对主体,字形清晰完整,无错字无缺笔,占据大部分画面,形成最强第一视觉。 不要做普通插画,不要只画人物外貌。 请提炼一个最准确、最有代表性的视觉隐喻,让人物、物体、空间或象征元素与大字发生关系,让观者一眼感受到这个词为什么会被这样表达。 整体气质要求高级、极简、克制、展览级,具有强排版、强隐喻、强情绪、强记忆点。 可根据词义自动选择更冷峻、更诗意、更悲剧、更锋利、更温柔或更庄严的视觉风格。 色彩也应根据词义自动调整,但保持整体高级感和节制感。 小字文案只保留三处: 左上角:2到4个关键词 右侧竖排:一句命运感短句 左下角:一句有传播力的总结句 要求元素少,概念准,留白克制。 文字是第一视觉,隐喻图像是第二视觉,小字是第三视觉。 不要拥挤,不要廉价广告感,不要多余英文,不要解释性长文案。 最终效果应像展览级文学人物或概念主题海报,把“【输入文字】”背后的精神状态和文化意味真正视觉化。

Example generated from “小小东 #256”
GPT Image 2zh

本次是生成图片任务: 苹果设计师思维,顶级海报大师思维,用高桥流思路 呈现海报设计 表现如下文本,让其抓人,直击人心 你可以智能理解文本,不一定照单全收文本,智能梳理文本, 把握人性,突出看点。尤其是我输入大段文本, 你核心呈现的,应该是你理解和处理后的核心文本 智能判定适合文本语义的配色逻辑,合理排版,有呼吸感的呈现文案 不要额外添加文字, 超大字展示这个文案 ``` [太阳就站在黑夜的门口] ```