Infographic Edu Visual圖片提示詞

Create a vertical before-and-after comparison image showing an ordinary landscape transformed into a minimalist watercolor-and-ink illustration. Canvas: portrait 4:5 aspect ratio. Layout: split horizontally into two equal panels with no border; the top panel is a realistic landscape photo and the bottom panel is the stylized illustration on warm off-white watercolor paper. Top panel: a clear daytime scene with {argument name="mountain name" default="Mount Fuji"} centered in the distance, blue sky with subtle wispy clouds, snow-capped peak, low mountain range, a row of white arched bridges crossing the midground, dry tan riverbank grasses, calm deep-blue river in the foreground with reflections, crisp natural colors and photographic detail. Bottom panel: preserve the exact same composition but simplify it into a delicate minimalist watercolor and thin ink sketch; small centered island-like landscape motif with a blue mountain silhouette and white snowy peak, white arched bridges, tan ochre riverbank, soft blue water reflections below, lots of empty paper around it, light washes, gentle bleeding edges, sparse fine-line details, elegant Japanese travel-sketch feeling. Include exactly one tiny handwritten signature-like mark centered beneath the illustration, very subtle and not readable. Use {argument name="sky color" default="clear vivid blue"}, {argument name="watercolor paper tone" default="warm ivory"}, and {argument name="illustration style" default="delicate minimalist watercolor and ink"}. Avoid extra text, people, vehicles, frames, heavy outlines, or clutter.

Create a clean anime production setting illustration of a {argument name="fish species" default="Japanese sea bass"} in full left-facing side profile, centered horizontally on a deep navy blue background. The fish should be long and realistic but stylized like a hand-painted animation reference sheet, with a dark bluish-gray back, silver-white belly, visible overlapping scales, a pale lateral line, large golden eye, defined gill plates, and crisp ink outlines. Show exactly 7 visible fins: one spiny dorsal fin near the front of the back, one soft dorsal fin behind it, one large forked tail fin, one pectoral fin on the visible side, one pelvic fin underneath near the head, one anal fin underneath near the rear, and a small lower fin edge partially visible behind the body. Add a thin fishing line entering from the left into the fish’s mouth and a small metallic lure or hook rig positioned inside the open mouth so that the hook appears caught in the mouth, not floating outside; keep the lure subtle and partially hidden by the lips. Use detailed fin rays, delicate scale texture, muted natural colors, soft cel-shading, and a polished concept-art look. No labels, no extra objects, no watermark, no border.

Create an ultra-high-resolution 4:5 vertical travel poster themed around {argument name="location" default="TOKYO"}. All visible text must be in English only, perfectly spelled and professionally typeset, with no distorted letters, random symbols, or AI gibberish. CORE DESIGN: Place the giant word “{argument name="location" default="TOKYO"}” prominently in the center. Use tall, bold sans-serif letters, with each letter containing a different illustrated scene from the location. Treat the letters as “gallery windows,” incorporating recognizable landmarks, architecture, streets, transportation, nature, culture, and local atmosphere. Connect the scenes across the letters to create one cohesive visual panorama. TOP STRIP: Add a thin panoramic strip above the typography featuring simplified local elements such as skyline, roads, vehicles, trains, boats, bridges, birds, clouds, sun, or coastline where relevant. STYLE: Mid-century modern editorial poster, Swiss graphic design, premium travel branding, minimal flat-vector illustration, architectural infographic aesthetic, geometric forms, clean edges, subtle line-art details, strong negative space, and refined composition. COLOR: Automatically derive a cohesive palette inspired by {argument name="location" default="TOKYO"}. Use only 4–6 muted pastel colors with elegant, low-saturation travel-poster tones.

Take the person from the reference image and create a single 2x2 grid showing this exact same close-up portrait under four different professional lighting setups. Identity lock: identical face, expression (calm neutral), hairstyle, dark top, head size and camera angle in every panel — only the light changes. Panel 1 REMBRANDT: key at forty-five degrees left and above, small triangle of light on the shadowed cheek, moody falloff. Panel 2 BUTTERFLY: key directly above the camera, soft symmetric shadow under the nose, beauty-portrait glow. Panel 3 SPLIT: key exactly from the side, one half of the face lit, the other in darkness. Panel 4 RIM: key behind the subject edging hair and shoulders in bright outline, face lifted only by faint fill, near-silhouette drama. Same {argument name="background color" default="medium-gray"} background throughout, 85mm look, sharp focus on the eyes. Small white labels beneath each panel: "REMBRANDT", "BUTTERFLY", "SPLIT", "RIM".

请将我上传的每一张照片分别制作成一张独立的“旅行观察档案”设计海报，不进行多图拼贴，每张照片单独输出。 整体采用2:3竖版构图，由上下两个相互呼应的区域组成。上方实景摄影约占画面43%，下方旅行观察档案约占57%。分界清晰、平直，不使用撕纸、渐变融合或装饰性边框。 ## 上方：实景摄影 忠实保留原始照片，准确维持主体身份、数量、外观、结构、姿态、方向、地形、建筑、道路、水域、空间关系、真实材质、自然光影与原有色彩氛围。 只进行克制的展览级摄影调色，适度改善曝光、层次、清晰度和色彩统一性，使其具有旅行杂志、独立出版物与摄影展览的质感。 为适配竖版画幅，可以自然调整裁切，或合理扩展天空、地面、水面及周边环境，但不得拉伸、扭曲、移动、替换或重新设计主体。 如果原图包含雾、云、雪或弱光，应保留真实天气特征，但不要让浓雾、乳白色空气感或低对比度遮蔽主体。主体边缘、关键材质和空间层次必须清楚可辨。 ## 下方：旅行观察档案 在温暖的米白色天然档案纸上，重新绘制照片中的同一场景。 首先识别照片中最具有旅行叙事性的视觉锚点，例如： 船、灯塔、孤屋、房车、桥梁、车站、亭阁、门楼、塔楼、道路、码头或其他能够代表地点与旅程的主体。 将这一主体作为下方观察绘图的核心，并保持其外形、比例、方向、结构特征及其与环境之间的关系，使人能够一眼认出原照片。 使用以下绘画语言： - 铅笔结构素描 - 干墨线条 - 细密但克制的排线 - 少量从照片中提取的低饱和设色 - 局部纸张透底 - 轻微旧档案颗粒 - 精细引线与观察标注 - 尺寸参考、方向线和环境记录 - 松散但准确的旅行手稿质感 不要把下方做成精确的建筑CAD、工程制图或密集科普信息图。它应该像旅行者、建筑观察者或自然研究者留下的一页私人观察档案，具有知识感，但仍然安静、诗意并保留大量留白。 下方主体绘图应占据主要视觉区域。周围可以出现少量细线标注，指出照片中真实存在的重要结构、自然特征和空间关系。 底部设置5个尺寸统一的小型观察图板，根据照片内容自动选择： - 地理位置示意 - 地形或天际线轮廓 - 主体正视图或侧视图 - 局部结构剖面 - 天气、水面、云层、植被或道路观察 所有图板均应来自原照片内容，不得凭空添加无关结构。 ## 中文排版 根据照片中的地点、主体和旅行意象，自动生成： - 一个2至6字的中文主标题 - 编号，例如“编号 01” - 四位数年份 - 一句简短、克制且具有画面感的中文说明 - 3至4项场景信息 - 4至6个结构观察标注 - 5个底部图板标题…

Goal: Create an elegant Chinese literary presentation cover slide about {argument name="topic" default="李清照对当代女性的启示"}, blending Song dynasty poetic atmosphere with modern editorial design. Canvas: 16:9 horizontal slide, clean off-white background with a pale sage-green vertical panel occupying the right third. Use lots of negative space, refined margins, soft paper texture, faint ink-wash stains, and subtle gray botanical shadows across the middle. Layout: Left two-thirds is the text area; right third is a still-life photograph area. Place the large headline in the upper-left, arranged as two lines of dark forest-green Chinese serif type: line 1 “李清照对当代”, line 2 “女性的启示”. Under the headline add a thin muted red horizontal accent line. Below it place the subtitle in smaller black Chinese serif text: {argument name="subtitle text" default="从文学人生，看见女性如何表达自我、选择人生、抵抗困境。"} Middle-left feature row: include exactly 3 small icon cards in a horizontal row, separated by two thin vertical divider lines. Card 1 has a muted rose circular icon with a white leaf symbol and the label “以文学\n确立自我”. Card 2 has a warm beige circular icon with a white balance-scale symbol and the label “在时代与命运之间\n保持判断”. Card 3 has a desaturated teal circular icon with a white user silhouette and the label “不被单一\n身份定义”. Bottom-left keyword row: include exactly 3 keywords separated by vertical bars, with a small dark green leading mark: “表达自我 | 保持独立 | 承受变化”. Right still-life details: show an open antique Chinese letter or manuscript paper lying diagonally on a desk, with visible vertical handwritten Chinese calligraphy in gray ink. A black-and-brown calligraphy brush rests diagonally over the paper, pointing toward the lower-right. Add exactly 2 blooming plum blossom branches: one branch crosses the upper-right corner with several pale white-pink blossoms and buds, and one smaller branch extends from the center-left toward the right, casting soft shadows. The right panel background should be pale sage green; the paper is warm ivory with slightly curled edges and soft folds. Visual style: tasteful, literary, museum-catalog minimalism; calm Song dynasty aesthetics; natural daylight from upper left; soft shadows; muted palette of ivory, forest green, sage, rose, beige, and ink gray; high-resolution editorial composition, realistic still-life photo blended with clean graphic typography. Constraints: Keep all visible text in Chinese exactly as specified, with no extra captions or watermark. Maintain the 3 icon cards and 3 bottom keywords exactly. Avoid clutter, bright colors, cartoon styling, or modern tech UI effects.

A vintage British caricature depicts a woman with an elaborate hairstyle adorned with a sailing ship, flowers, and feathers. She is seated in an ornate chair, wearing a richly decorated dress and holding a fan. The background shows a lavish interior with a fireplace, clock, and a window overlooking a harbor scene. A small dog sits on a cushion to her right. The overall style is that of a 18th-century satirical print.

Goal: Create a 2x2 comparison collage showing four generated anime-style reference images for a short video concept, on a dark charcoal background with large white labels. Canvas: Landscape 3:2 composition, approximately 1200x900 px. Use a matte black/dark gray background. Arrange exactly 4 rectangular image panels in a clean grid with generous margins and gutters. Each panel has a large bold white label above it: exactly 4 labels, “@image1” at top left, “@image2” at top right, “@image3” at bottom left, and “@image4” at bottom right. Overall visual style: Soft hand-drawn anime illustration, warm muted colors, gentle line art, subtle watercolor-like shading, nostalgic Japanese school atmosphere, clean character design, no photorealism. The recurring subject is {argument name="character description" default="a cute middle-school Japanese girl with shoulder-length dark brown wavy hair, simple dot eyes, a small smile, and a sailor-style school uniform"}. Her outfit is consistent across panels: cream short-sleeve sailor blouse with navy trim, orange neckerchief, dark plaid pleated skirt with orange and teal lines, navy knee socks with orange stripes, and beige sneakers. Panel @image1: A single illustration on a warm beige background. Show exactly 1 girl sitting at a classic school desk and chair in side three-quarter view, facing right. She is relaxed with both hands on the desktop as if writing or reading. Include exactly 1 desk and exactly 1 chair, with thin black metal legs and a wooden seat/backrest. Her legs extend forward slightly; sneakers are visible. Keep the background plain and minimal. Panel @image2: A character turnaround sheet on a clean white background. Show exactly 3 full-body views of the same girl, evenly spaced: 1 front view on the left, 1 side profile view in the center facing left, and 1 back view on the right. Keep the proportions chibi-like but not super-deformed, with a large head, small body, and simple facial features. No extra props or text inside this panel. Panel @image3: A bird’s-eye view illustration of {argument name="school setting" default="a small suburban Japanese school"}. Show exactly 1 main school building, rectangular and two stories tall, with a dark teal roof and long rows of windows. Include exactly 1 sandy schoolyard with faint white court markings, exactly 1 perimeter wall, and surrounding residential neighborhood houses, trees, narrow streets, utility poles, and warm afternoon lighting. The perspective should be high aerial/isometric, like a reference image for a 3D scene. Panel @image4: View into a classroom through a large window frame, as if the viewer is outside looking in. In the foreground, show exactly 1 main girl seated at a desk near the window, facing slightly right, with an open book or notebook on her desk. Behind her, show exactly 6 background students seated at separate desks, softly blurred and simplified, facing forward or downward as if studying. Include warm sunlight, window reflections, classroom wall panels, and rows of desks. The window frame should visibly border the panel and create a cinematic shot. Constraints: Keep all 4 panels in the same illustration style and color palette. Do not add extra panels, extra labels, watermarks, captions, or logos beyond the four @image labels. The collage should look like a social media post showing four prompt-generated reference images.

Goal: Create a warm vertical Xiaohongshu-style illustrated poster explaining that letting AI think longer can reduce the bill, using a cozy home DIY scene and clear handwritten Chinese typography. Canvas: Vertical 3:4 social media poster, soft golden afternoon light, high-resolution anime/editorial illustration, inviting and optimistic. Main headline: At the very top, place a large cream brush-stroke banner with bold hand-painted Chinese text: {argument name="headline text" default="让 AI 多想一会儿，账单竟然少了近一半"}. Emphasize the final phrase in orange-red while the rest is dark brown-black. Add small yellow-orange emphasis rays on both sides. Subtitle: Directly below the headline, add a smaller rounded white label with Chinese text: {argument name="subtitle text" default="Astra 的能力曲线为什么开始拐弯"}. Central scene: A cute young man with {argument name="hair color" default="messy dark brown hair"}, wearing a forest-green sweater and dark pants, sits cross-legged on a rug in a sunlit room. He looks upward thoughtfully with a small smile, holding a pencil near his chin and an open instruction booklet in his lap. The booklet shows a simple line drawing of a shelf on the left page and a checklist on the right page. Counted text elements and labels: Include exactly 1 thought bubble above the character with Chinese text: {argument name="thought bubble text" default="先想清楚 再动手..."}. Include exactly 4 checklist rows in the booklet: 3 checked items labeled 「思考」, 「规划」, 「执行」, and 1 unchecked grey item labeled 「返工」. Include exactly 1 whiteboard chart in the background labeled 「效果 vs 成本」 with a vertical axis 「效果 (%)」 and horizontal axis 「成本 ($)」. On the chart, show exactly 2 curves: an orange solid curve with round markers bending upward then flattening, labeled 「Astra 开始拐弯」 with an orange arrow, and a grey dashed curve labeled 「不够思考 成本更高」. Room and objects: The setting is a cozy living room or study with blurred plants, framed pictures, warm window light, and a wooden shelving unit being assembled. Show exactly 1 sleeping orange-and-white cat curled on top of the shelf. Show scattered DIY parts in the foreground: wooden boards, screws, and 1 orange-black screwdriver. Add exactly 1 white mug near the character with English text stacked as “Good Plan Lower Bill” and a small smiley face. Sticky notes and cardboard signs: Include exactly 3 yellow note/sign elements: 1 sticky note on the upper right wall saying 「多一步思考 少很多返工 更聪明 也更省钱」 with a smiley face; 1 sticky note on the wooden shelf saying 「一次做好 省时省钱」 with a bold check mark and small yellow emphasis rays; 1 cardboard box sign in the lower right foreground saying 「更聪明的 AI 更轻松的生活」 with a simple house icon. Visual style: Soft painterly anime illustration mixed with infographic design, rounded shapes, thick friendly hand-lettering, warm beige/orange/green palette, gentle depth of field, clean composition, lively but not cluttered. Constraints: Preserve all Chinese text exactly as specified, keep the poster readable, use no logos or watermarks, and do not add extra charts, extra sticky notes, extra characters, or extra checklist items.

A scientific botanical poster on cream paper. A single oversized {argument name="flower" default="forget-me-not"} painted in watercolor, roots and all, with tiny numbered labels on stem and petal. Title in italic serif at the top: "FORGET-ME-NOT". Subtitle: "A FIELD PLATE". Bottom: "{argument name="plate number" default="PLATE VII · 1887"}". Pencil notes in the margin. Cream, indigo, green, 2:3 aspect ratio.

请将我上传的每一张照片分别制作成一张独立的「橡皮章旅行田野笔记海报」，每张照片单独输出，不要多图拼贴。整体采用4:3横版构图，将画面划分为左右两个区域，但不要绘制明显的分隔线。左侧约占画面58%，忠实保留原始照片。准确保持主体身份、地形、建筑、植物、人物、空间关系、自然光影、真实质感和原有色彩氛围，仅进行克制的艺术出版物级摄影调色，并加入极轻微的细腻胶片颗粒。为适配版式可以自然裁切，但不得拉伸、扭曲、移动、替换或重新绘制主体。右侧约占画面42%，使用温暖的米白色旧纸作为背景。纸张具有细微纤维、天然颗粒、轻微使用痕迹和哑光触感，同时保留大面积未经印刷的纸张留白，让空白成为版式的重要组成部分。分析原始照片，从中提取最具地点辨识度的主体轮廓、建筑结构、地形走势、植物姿态、道路、水岸线或其他关键视觉关系，将其压缩成一枚小型多色橡皮章图像。不要逐项复制照片中的全部内容。只保留能够让人一眼认出原始地点、主体和场景关系所必需的最少信息。删除人群、车辆、密集窗户、重复建筑、细碎植被、装饰构件和无关背景。章印位于右侧纸张区域的中下部，整体只占右侧区域高度的约30%—38%，周围必须保留充足留白。章印不能放大成普通插画、完整风景画或品牌Logo。根据原图构图决定章印的组织方式：- 标志性建筑：保留最有辨识度的外轮廓、屋顶、穹顶、拱门、塔楼或主要结构。- 山地聚落：将建筑压缩成沿地形排列的少量阶梯状色块。- 海岸风景：保留山体走势、聚落层级、岸线 and 少量断续水纹。- 城市远景：保留主要天际线、一个标志性建筑及一两层远山。- 自然景观：保留主要山体、树木、水岸或道路的方向关系。- 近景遮挡物：如果其对原图叙事重要，可作为前景章印轮廓保留。从原始照片中提取2—4种专色油墨。优先使用炭黑、深绿、砖红、赭黄、灰蓝、灰褐等经过降低饱和度的颜色，但不得强行套用固定色盘。保留原照片最有辨识度的色彩性格，仅允许一个小面积颜色作为视觉强调。每一种颜色都要呈现为分别手工盖印的效果：真实橡皮章雕刻纹理、手工刻痕、粗细不均的排线、轮廓缺口、断裂边缘、干燥缺墨、纸张透底、颗粒状油墨、压力不均、局部重影，以及约1—2毫米的轻微套色偏移。不同色层之间允许出现自然错位，边缘不能数字化平滑。印迹应像真正刻制后压在旧纸上的橡皮章，而不是套用滤镜的照片、平滑矢量插画或线稿Logo。根据照片中的地点、主题和视觉意象生成文字：地点英文名称 No. 编号 三个简短英文关键词 西元年份 文字放在章印下方或邻近留白处，使用小型、克制、略带…

Create a sophisticated 4:5 vertical contemporary country art print inspired by Swiss graphic design, topographic maps, modern editorial posters, and premium outdoor cartography. MAIN CONCEPT: Represent {argument name="country" default="[COUNTRY]"} through its topography, coordinates, and geographic identity rather than landmarks or tourist imagery. BACKGROUND: Clean warm-white / very light ivory paper with subtle tactile grain. MAP COMPOSITION: Use 2–3 cropped sections of highly detailed black-and-gray topographic contour maps representing important geographic regions of {argument name="country_name" default="[COUNTRY]"}. Arrange them asymmetrically with generous white space. Place one large translucent circular accent over the most significant geographic location. The circle should feel like a modern cartographic location marker rather than a normal map pin. TYPOGRAPHY: Across the center, place an enormous bold condensed sans-serif title: {argument name="country_title" default="[COUNTRY]"} The typography should partially overlap the contour maps, creating a striking editorial composition. Add small technical geographic information around the poster: [LATITUDE]° [LONGITUDE]° LOCATION: [CITY / REGION] ELEVATION: [ELEVATION] M FIRST EDITION: [YEAR] Include a tiny minimalist globe / compass / geographic coordinate symbol in one corner. Add a very small secondary typographic element: [COUNTRY] / TOPOGRAPHIC STUDY / No. 01 COLOR PALETTE: Mostly black, white, and soft gray with one bold {argument name="accent color" default="muted accent color"} — deep red, burnt orange, forest green, cobalt blue, or ochre. Use the accent only for the circular geographic markers. DESIGN LANGUAGE: Swiss International Typographic Style × contemporary cartography × vintage topographic survey × minimalist editorial design × luxury outdoor magazine. IMPORTANT: The contour lines must be dense, organic, geographically believable, and beautifully detailed. They should become the main visual texture of the artwork. No flags • no tourist landmarks • no illustrations • no photographs • no decorative borders • no excessive text • no gradients • no clutter. MOOD: intelligent • geographic • modern • adventurous • architectural • collectible • premium. FINAL PRESENTATION: Show the print as a clean gallery/product photograph, either pinned or hanging against a simple architectural wall, with soft directional lighting and a subtle natural shadow.

Goal: Create a refined travel-and-architecture poster that combines a realistic coastal harbor photograph with a matching architect-style concept sketch of the same scene. Canvas: Vertical 3:4 poster, elegant editorial layout. Split the composition into exactly 2 stacked sections: the top half is a full-bleed twilight harbor photograph; the bottom half is an off-white paper poster area containing typography and a hand-drawn architectural perspective sketch. Top photographic section: Show a quiet harbor at blue hour in {argument name="place" default="Japan"}. The scene includes calm deep-blue water, mountain silhouettes in the background, a small coastal village on the right hillside, warm yellow streetlights and house lights, and long shimmering reflections on the water. Include exactly 4 visible boats: 1 main white fishing boat near the center foreground, 1 smaller boat near the right foreground, 1 darker boat moored near the right pier, and 1 small boat near the center-right harbor wall. Add a breakwater pier on the left with a single glowing beacon, distant town lights across the bay, layered blue mountains, scattered twilight clouds, and a soft pink-orange horizon fading into blue. Bottom poster section: Use warm ivory paper with subtle grain. In the upper-left, set large elegant serif title text: “{argument name="headline text" default="Harbor at Twilight"}”. Beneath it, add small widely spaced uppercase subtitle text in two lines: “A QUIET EDGE” and “A BRIGHTER TOMORROW”. In the upper-right, add tiny stacked uppercase words: “PLACE”, “PEOPLE”, “LANDSCAPE”, “A BETTER DAILY LIFE”. In the lower-left, add small uppercase text in three lines: “COASTAL VILLAGE”, “STUDY SKETCH”, “{argument name="country label" default="JAPAN"}”. In the lower-right, add loose handwritten signature-style text: “{argument name="handwritten note" default="Same Sea / A Kinder Tomorrow"}”. Architectural sketch: Center the bottom half with a delicate hand-rendered perspective drawing of the same harbor scene from the photo. Use thin graphite construction lines, faint perspective guides, vertical measurement marks, ink outlines, loose watercolor washes, pale blue mountains, soft gray roofs, muted green trees, and warm yellow highlights for lamps and reflections. Include exactly 4 sketched boats matching the top image: the main white fishing boat in the center foreground, one small skiff to its left, one small boat near the center-right, and one larger boat on the far right. Include the pier, village houses, hillside trees, mountains, and beacon, all simplified as an architect’s concept drawing. Visual style: Premium Japanese coastal travel poster, calm and poetic, realistic photography above and airy architectural watercolor sketch below. Use refined typography, generous negative space, thin rules, soft lighting, cinematic twilight blues, warm golden reflections, and no clutter. Constraints: Keep the top and bottom halves visually aligned so the sketch clearly corresponds to the photograph. Do not add extra panels, extra boats, logos, QR codes, borders, or watermarks.

请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用 3:4 竖版构图，上下两个区域高度严格 1:1，各占画面 50%。上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志与展览图像质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。下半部分只提取照片中最具识别性的主体、轮廓、结构、姿态与叙事关系，重构为建筑概念透视草图 / 建筑方案表现手绘。不要完整保留场景，不要逐物复制照片；主动删去大部分背景、配景和无关细节，只留下最能代表原始主题的核心形体、空间关系与视觉记忆点。下半部分重新做美术判断。哪怕原图构图差、背景乱、主体小，也要通过删减、重组、裁切、尺度变化和留白，把它救成一张成立的作品，真正赋予模型重新导演画面的权力。画风采用自由徒手透视线稿 + 少量选择性色块。线条松弛、克制、略带重复与停顿感，可保留少量辅助线、延长线、构造线与建筑手绘的几何参考线，形成明确的设计推敲感。色彩只在少数关键部位轻微铺陈，用于强调主体、结构层次、局部阴影或空间重点，其余区域尽量不画。画面必须以大量有意识的留白为核心。主体应更小、更精炼，其余空间大面积留空。留白不是空背景，而是构图的一部分，要与主体、线稿、参考线、阴影和少量色块共同形成呼吸感、空间感与节奏感。主体可偏心、贴边、局部裁切或缩小尺度；宁可少画，也不要填满。可加入少量几何阴影色块强化体量、进深与空间层次，但避免厚重渲染、复杂环境和写实效果图感。背景保持极简，只保留极少量必要的场地暗示。配色从上方照片中提取 2–4 种最具识别度和生命力的颜色，重新整理为更干净、克制、耐看的草图色系。整体可适度提亮、提纯、去灰，以米白、浅灰、暖灰、柔和绿色、淡木色、浅蓝灰等为主，局部保留少量更鲜明但不刺眼的点睛色。避免脏灰、暗沉、过度复古和廉价高饱和感。文字只作极少量编辑性介入，不限制语种。可根据主体、地点、动作或情绪生成少量字词、短句或注记，安静地落在留白区域，与画面形成克制的图文关系。整体呈现建筑概念手绘、自由线稿、几何参考线、少量色块、几何阴影、超大量留白与编辑式排版共同构成的高级视觉效果。避免完整场景保留、逐物复制、复杂背景、满幅上色、写实效果图、粗重描边、卡通感、3D感和模板化表现。

Goal: Create a polished 2x2 collage of four social media / marketing graphic examples for an AI image generation platform, separated by thin white gutters, showing the variety of visuals that can be made: ecommerce, motivational lifestyle, AI education, and productivity quote content. Canvas: Landscape 3:2 aspect ratio, approximately 1200x800, divided into exactly 4 equal rectangular panels in a clean grid with white borders between panels. Use realistic photography blended with crisp overlaid graphic design text. Panel 1, top left — ecommerce new arrivals: A warm beige desk scene with a laptop and smartphone displaying a fashion shop website. The laptop screen shows a clean online store with exactly 3 product cards: Brown Jacket, White Top, and Beige Jacket, each with a model photo, price, and small “ADD TO CART” button. The phone in front also shows the Brown Jacket product. Add a soft leafy plant shadow in the upper left. Large white serif headline on the left reads “{argument name="fashion headline" default="New Arrivals"}”, smaller line reads “Summer Collection”, body copy reads “Discover our latest collection designed for comfort and style.”, and a rounded outline button reads “SHOP NOW”. Panel 2, top right — motivational lifestyle post: Cozy warm bedroom photo of a smiling young woman sitting on a bed, wearing a cream knit sweater and beige pants, holding a white mug, with plants and a round wall mirror softly blurred in the background. Overlay bold white sans-serif text on the right reading “{argument name="motivational headline" default="Small Steps Every Day"}”, smaller text underneath reading “Be proud of how far you’ve come.”, a white hand-drawn underline flourish, and exactly 3 small white outline heart doodles in the top-right corner. Panel 3, bottom left — AI prompt engineering educational graphic: Dark navy futuristic workspace scene with a focused man wearing glasses using a laptop at night, blue-purple neon UI overlays and subtle grid lines. Left side contains a large educational title: “PROMPT ENGINEERING” above “{argument name="AI education title" default="TIPS TO GET BETTER AI RESPONSES"}”, with “AI” highlighted in cyan. Include exactly 4 checklist tips with small cyan square icons: “Be Clear & Specific”, “Provide Context”, “Use Examples”, and “Iterate & Refine”. On the right of the title area place exactly 2 translucent rounded UI cards: one labeled “INPUT PROMPT” with text “Explain the concept of quantum computing in simple terms.” and one labeled “AI RESPONSE” with text “Quantum computing uses qubits that can exist in multiple states at once...”. Add exactly 2 small decorative interface icons: a circular brain icon near the top right and a small chat bubble icon near the lower right. Panel 4, bottom right — discipline quote card: Sunlit wooden desk scene with blurred green plants outside a window. Place a gray ceramic mug on the left with stacked white text reading “FOCUS PLAN EXECUTE”, next to a closed notebook. On the right place a black rounded rectangle quote card with large typographic quote marks in muted gold. White quote text reads “{argument name="quote text" default="Discipline today leads to freedom tomorrow. Keep showing up."}” with the phrase “showing up” highlighted in muted gold. Visual style: Premium social media marketing mockup, photorealistic base images, soft natural lighting in the lifestyle and product panels, deep cinematic blue lighting in the AI panel, modern clean typography, realistic shadows, high contrast, sharp readable text, professional content-creator aesthetic. Constraints: Use exactly 4 panels and the listed repeated elements: 3 ecommerce product cards, 3 heart doodles, 4 checklist tips, 2 translucent UI cards, and 2 decorative AI interface icons. Keep all visible text legible and spelled correctly. No watermarks, no extra panels, no random logos.

a photorealistic, taken by phone photo of a handwritten essay in pencil, albert einstein handwriting, on an 8.5x11 piece of lined paper, about the {argument name="essay topic" default="history of money in world"}. make sure there is variance in the writing in a very einstein way. give it a slight {argument name="stain type" default="coffee stain"} on the top right corner

Create a clean infographic summarizing {argument name="subject" default="Teva’s revenue report"}, with clear headings and a {argument name="chart type" default="chart showing annual growth"}.

Goal: Create a detailed vintage illustrated visual reference sheet for {argument name="food subject" default="Croissant"} in a warm hand-drawn {argument name="art style" default="Studio Ghibli style"}, like a pastry-making guide from an old cookbook. Canvas: Wide horizontal 16:9 composition on warm cream parchment paper, with thin brown rounded panel borders, muted sepia ink outlines, soft watercolor shading, and cozy bakery lighting. Use an off-white background with subtle paper texture. Header: Large bold hand-lettered title at the top left reading “{argument name="headline text" default="CROISSANT"}”. Beneath it, smaller uppercase subtitle: “VISUAL REFERENCE SHEET – STUDIO GHIBLI STYLE”, flanked by small decorative leaf sprigs. Layout: Divide the sheet into 5 main areas: 1 large ingredients panel on the upper left, 1 tools panel on the lower left, 1 color palette strip along the bottom left, 1 large finished croissant showcase panel on the upper right, and 1 making process panel with 5 numbered steps on the lower right. Ingredients panel: Label the panel “INGREDIENTS”. Show exactly 6 ingredient illustrations arranged left to right, each with a bold uppercase label and a short note: 1) raw dough ball, smooth and pale, dusted with flour; 2) flat beaten butter, pale yellow and cold; 3) rolled out dough, thin and even rectangular sheet; 4) dough triangle, before rolling; 5) raw crescent, unbaked and pale soft; 6) baked croissant, golden and flaky with caramelized surface. Tools panel: Label the panel “TOOLS”. Show exactly 5 tools arranged left to right: 1) wooden rolling pin, captioned for rolling dough evenly; 2) pastry knife with wooden handle, captioned sharp blade for clean cuts; 3) metal baking tray lined with parchment paper; 4) pastry brush with wooden handle, captioned for egg wash application; 5) brick oven with glowing fire, captioned high heat for baking. Finished croissant panel: Label it “FINISHED CROISSANT”. Show one large finished croissant on a white oval plate, angled slightly from lower left to upper right. The croissant is oversized, glossy, golden brown, crescent-shaped, with many visible laminated layers, darker caramelized ridges, flaky cracks, toasted spots, and a soft shadow on the plate. Making process panel: Label it “MAKING PROCESS”. Include exactly 5 vertical numbered cards from left to right, each with a dark circular number badge and a small illustration above text: 1) “BEAT BUTTER FLAT” showing a square block of butter on parchment, note that butter is beaten between sheets until flat and even in a square; 2) “WRAP AND SEAL” showing dough folded around butter, note to place butter in the center of rolled dough and seal edges tightly; 3) “FOLD AND ROLL” showing a folded laminated dough stack, note to fold dough and roll out and repeat several times to build layers; 4) “CUT AND SHAPE” showing long dough triangles and a raw crescent, note to cut into triangles and roll up from base to tip; 5) “EGG WASH AND BAKE” showing several croissants on a baking tray, note to brush with egg wash and bake until golden and flaky. Color palette strip: Label it “COLOR PALETTE”. Show exactly 7 circular color swatches with names and hex codes: 1) Dough Cream #F5ECD7, 2) Butter Yellow #F5C518, 3) Baked Gold #D4A55A, 4) Caramel Crust #8B5E3C, 5) Flaky Interior #FAF3E0, 6) Parchment White #F9F6F0, 7) Char Brown #3D1F0A. Typography and style: Use bold condensed hand-drawn uppercase lettering for labels, smaller neat handwritten captions, dark chocolate-brown ink, rounded cream label tabs, and consistent old-fashioned bakery reference-sheet design. Keep all illustrations charming, clean, and readable, with soft painterly shadows and warm amber highlights. Constraints: Include no people, no photorealism, no modern UI elements, no watermark, and no extra sections beyond the described 5 main areas. Keep all visible English text legible and spelled correctly.

Turn the main subject into a visual story told through {argument name="frame count" default="4–6 small illustrated frames"}. Keep the original object recognizable, but reinterpret it as a charming hand-drawn sequence showing its ingredients, preparation, texture, and final form. Use a {argument name="background style" default="warm cream paper background"}, delicate ink outlines, subtle handwritten annotations, tiny arrows, ingredient sketches, measurement marks, and imperfect print textures. The composition should feel like a page from an {argument name="illustration style" default="old culinary sketchbook"} — artistic, intelligent, nostalgic, and highly curated. Do not simply reproduce the photograph. Transform its subject into an illustrated visual narrative.

主题：{argument name="主题" default="文化评论"} / 英语等级：{argument name="英语等级" default="B2"} / 正文词数：{argument name="词数" default="400"} 生成一张高级黑白报刊社论风英文文章版式，整体视觉像高端文学杂志、文化期刊或报纸专题页。 文章语言必须使用英语，并严格按照第一行指定的 CEFR 英语水平进行写作。英语等级可填写 A1、A2、B1、B2、C1 或 C2；“主题”为文章主题；“正文词数”为目标英文正文词数。 英语内容难度要求： - A1：使用非常基础、高频词汇和简单短句，句式清晰直接，适合英语初学者。 - A2：使用常见生活词汇、简单连接词和基础复合句，表达自然易懂。 - B1：使用较丰富的日常与抽象词汇，加入原因、例子和观点表达，句式有一定变化。 - B2：使用较成熟的议论文表达、较丰富词汇和复杂句式，观点清晰、有逻辑层次。 - C1：使用高级、准确且自然的英语，词汇丰富，句式复杂，具有文学 and 评论文章质感。 - C2：使用接近高水平母语文化评论或文学社论的英语，允许细腻修辞、复杂句法、抽象概念与富有层次的论证，但保持自然、清晰和可读性。 无论选择哪个等级，都必须确保文章真正符合该 CEFR 难度，而不是只更换少量高级或简单词汇。根据语言等级自动调整观点复杂度、句子长度、词汇难度、抽象程度和论证深度。 文章必须围绕第一行指定的主题展开，并尽量将正文控制在指定词数左右，允许约 ±10% 的浮动。 页面顶部设置简洁的英文报刊刊头、栏目名称、日期和细横线分隔，例如： “THE LITERARY REVIEW” “ESSAY / CULTURE” 以及英文日期。 页面中央使用超大号优雅高对比度衬线字体作为英文主标题。主标题应根据主题自动生成自然、简洁、有编辑感的英文标题，不要机械地直接复制主题。 标题下方居中放置英文作者署名，例如： “By Knwoledgefxg” 页面采用严格的编辑设计网格和经典多栏排版。正文为三栏窄幅英文文章，两端对齐，段落紧凑、字距自然，呈现真实英文报刊文章视觉效果。 左侧设置一块醒目的粗体斜体英文引言或金句区域，内容从文章核心观点中提炼，长度约 1–3 句，并搭配粗细适中的横线。该引言的语言难度必须与指定英语等级保持一致。 页面中部放置一张大幅黑白纪实摄影，摄影内容应根据文章主题自动选择与内容相关的现实场景。摄影风格真实、克制、纪实，不使用插画风格。照片下方设置小号英文图片说明文字，语言简洁自然，并符合指定英语等级。 整体视觉克制、理性、文学感强、知识感强，具有传统新闻出版物和高端文化杂志的高级感。字体以高对比度衬线字体为主，视觉气质类似 Didot、Bodoni、Times 或经典报刊字体。标题优雅而庄重，正文紧凑规整，斜体仅用于引言、署名或强调信息。 页面使用暖白色、略带泛黄感的新闻纸材质，加入轻微纸张褶皱、自然折痕、印刷颗粒、轻微油墨晕染、细微套印误差和胶片颗粒感，形成真实传统纸媒印刷效果。 整体仅使用黑色、深灰色和米白色，不使用鲜艳颜色，不使用渐变，不使用现代 UI 元素，不使用插画，不使用未来科技感，不使用霓虹效果。 页面底部设置一个细线边框的信息框或行动号召区域，内部使用居中的大号斜体衬线英文文字。内容应是一句与文章主题相关的简短总结、反思或行动号召，并符合指定英语等级。 竖版构图，完整单页英文杂志专题设计，正面视角，充足留白，严格编辑网格，精致排版，高级、克制、经典、文学、知识型、editorial design aesthetic。 重要要求： 1. 页面中的所有可见文章文字必须为英语。 2. 所有正文、标题、副标题、引言、图片说明和底部文案都必须语义自然，不使用随机乱码或无意义占位文本。 3. 英语内容必须严格符合第一行指定的英语等级。 4. 正文长度尽量接近第一行指定的词数。 5. 正文必须围绕第一行指定的主题展开，并像一篇真实完整的英文文章，而不是文字填充。 6. 保持版面视觉高级感的同时，确保英文正文具有足够可读性。 7. 更换第一行参数后，其余提示词无需修改即可重复使用。

Create a photorealistic 2×2 four-panel recipe collage showing the preparation of a {argument name="smoothie type" default="creamy banana smoothie"} on a {argument name="table style" default="rustic dark wooden kitchen table"}. Top-left: Several ripe yellow bananas, one peeled banana, a clear glass of milk, a small glass bowl of thick white yogurt, and a bowl of ice cubes neatly arranged as ingredients. Top-right: Close-up of hands peeling a ripe banana and placing banana pieces into a transparent glass blender jar. Bottom-left: Milk being poured from a transparent measuring cup into the blender containing banana pieces, yogurt, and ice cubes. Bottom-right: Thick creamy banana smoothie being poured from the blender into a clear drinking glass, with another finished smoothie glass in the background and a few banana slices on the wooden table. Warm natural kitchen lighting, realistic food textures, creamy pale-yellow smoothie, transparent glassware, shallow depth of field, rustic wooden background, clean composition, professional food photography, highly detailed, realistic hands, natural shadows, 4K photorealism, no text, no labels, no watermark.

Goal: Create a vertical social-media field-note poster about {argument name="headline topic" default="真正值得收藏的 12 个提示词网站"}, combining a clean editorial infographic layout with an anime character workspace scene. Canvas: Portrait 2:3 aspect ratio, warm beige paper texture background, soft sunlight and window-shadow patterns from the upper left, minimalist Japanese/Scandinavian studio atmosphere. Use a restrained palette of cream, sand, charcoal black, and golden yellow. Top branding and header: In the top-left corner place small text “起风了 | AI Lab”. In the top-right corner place a tiny yellow dot followed by “FIELD NOTE · 01”. Center near the top add a rounded yellow pill label reading “AI 生图 · 资源清单”. Below it, create a large bold Chinese headline: “真正值得收藏的” on the first line and “12 个提示词网站” on the second line, with the number “12” oversized in golden yellow and the rest in dark charcoal. Under the headline add a small subtitle with thin horizontal divider lines: “按场景选，别再乱收藏”. Main layout: The middle area contains exactly 12 rounded white resource cards arranged in two vertical columns of 6 cards each, floating over the background and partially framing the character. Each card has a golden vertical accent strip on the left, a circular yellow number badge, bold black website name, smaller gray Chinese description, subtle shadow, and a small bracket-like corner mark at the upper right. Keep spacing even and aligned. Left column cards, exactly 6: 01 Midjourney Explore — “MJ 灵感与参数”; 02 PromptHero — “跨模型大库”; 03 Lexica — “视觉搜索”; 04 Civitai — “模型与生成数据”; 05 Krea — “多模型与反推”; 06 OpenArt — “图片转 Prompt”. Right column cards, exactly 6: 07 Public Prompts — “免费 SD 示例”; 08 GPTIMG.app — “GPT Image 2 专库”; 09 2Slides — “226+ 社区 Prompt”; 10 GPTImg.ai — “按任务分类”; 11 CUTY — “配图、变量、作者”; 12 PromptBase — “付费模板市场”. Central subject: At the lower center, place {argument name="character description" default="a stylish young anime male researcher with spiky black-and-yellow hair, sharp focused eyes, and a black headband"}. He is seated at a light wood desk, facing forward slightly, looking down with a serious expression while holding or using a black tablet/laptop. Outfit: bright yellow oversized tech jacket with black collar and white accents, black high-neck shirt, black pants, black-and-yellow high-top sneakers, a small gold pendant necklace, modern streetwear details. The character should be visible from head to shoes, centered between the two card columns. Desk and environment: Use a simple light wood table across the lower third. On the desk include exactly 7 visible objects: a black tablet/laptop in front of the character, three small white paper notes, one beige plant pot on stacked books at the left, one shallow round tray at the right, and one small beige vase with a thin plant stem at the right. Add a larger potted plant on the far left edge, hanging greenery on the right wall, and a few books stacked on the floor at the lower right. Background wall has subtle fabric/paper texture and a horizontal wainscot line. Footer: Bottom-left tiny text “AI 资源盘点系列”. Bottom-right tiny text “PROMPT SITES · 01” in faint golden yellow. Visual style: High-quality GPT Image 2 poster design, clean editorial typography, readable Chinese text, soft natural lighting, warm shadows, balanced negative space, anime illustration blended with realistic interior and infographic UI cards. Avoid logos, watermarks, extra cards, misspelled website names, or adding more than the specified 12 resources.

Create a cinematic astrophotography-style educational space poster of the Horsehead Nebula, {argument name="nebula name" default="Barnard 33"}, in a wide horizontal 4:3 canvas. The background is a deep red emission nebula filled with dense tiny white stars, with a glowing crimson hydrogen cloud band running horizontally through the middle. Center-right, place one large dark black-brown dust cloud silhouette shaped like a horse’s head and neck, rising upward with a curled snout and mane-like wisps, rim-lit by red light from behind. Add subtle blue haze in the lower-left corner and two especially prominent blue-white stars: one bright star near the left edge and one smaller bright star in the right-middle area, plus many smaller stars scattered naturally. In the upper-left corner, overlay exactly 3 text elements in white serif type: a large Japanese headline {argument name="headline text" default="馬頭星雲"}, a smaller English subtitle {argument name="subtitle text" default="Barnard 33"}, and a four-line Japanese description {argument name="description text" default="オリオン座にある暗黒星雲。\n背景の赤く光る散光星雲を、\n手前の冷たいガスと塵が遮って\n「馬の頭」のシルエットに見える。"}. Use elegant museum-planetarium typography, high contrast, realistic nebula detail, no borders, no logos, no extra labels.

Create a wide cropped comparison graphic showing two side-by-side image-generation quality results on a plain white background. The canvas is an ultra-wide horizontal strip, about 5:1 aspect ratio, cropped tightly so only the top portion of each result is visible. At the top left above the first crop place the bold black uppercase label “MEDIUM”; near the upper center above the second crop place the bold black uppercase label “HIGH”. Each of the 2 comparison panels shows the same fitness-class style tiled layout: a photographic band at the top with gym equipment and dark exercise machines, underneath a deep teal rectangular title bar with large bold white Japanese text {argument name="main tile text" default="有酸素"}. Use thick white borders and sharp diagonal white dividers between tiles, giving the layout a dynamic slanted collage look. Count exactly 2 main visible teal title tiles with the full text “有酸素”, one in each panel, plus exactly 2 partially visible neighboring teal tiles at the right edge showing only the first character or fragment {argument name="partial tile text" default="ス"}. A thin lower white divider and the top edge of another teal row are barely visible along the bottom, cropped off. Emphasize the artifact being compared: around the white Japanese letters on the solid teal backgrounds, include subtle uneven brightness and saturation patches, faint haloing, and mottled texture, with the “HIGH” panel slightly cleaner but still showing visible nonuniformity. Keep the composition as a technical screenshot/comparison crop, not a polished poster. Use crisp sans-serif typography, high contrast, no extra captions, no watermark.