Image Prompts for Diagram Chart

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…

Use the uploaded photo as the primary reference. Create a sophisticated 4:3 landscape {argument name="style" default="architectural specimen card inspired by museum archives, architectural surveys, and vintage scientific documentation"}. Keep the {argument name="location" default="original location"} recognizable, but transform the presentation into a curated architectural study rather than a normal travel poster. * Place the main landmark as a large monochrome architectural cutout or finely detailed ink drawing. * Add a smaller original-color photographic fragment showing one distinctive detail of the location. * Include a simplified topographic contour map behind the architecture. * Add tiny numbered reference points, measurement marks, arrows, elevation lines, and architectural annotation symbols. * Use an aged cream paper background with subtle grain and imperfections. * Palette: {argument name="palette" default="black, warm beige, muted olive, and one restrained accent color extracted from the landmark"}. * Typography should be small, elegant, and archival: location name, country, year, No. 019, and 3 descriptive keywords. * Create subtle imperfections resembling screen printing, drafting ink, pencil marks, and old paper. * Keep generous negative space and a sophisticated museum-catalog aesthetic. Important: Avoid postcard layouts, circular stamps, tourist graphics, excessive text, cartoon styling, glossy effects, 3D rendering, and overly detailed illustrations. Overall mood: architectural archive × museum specimen × old survey document × contemporary editorial design.

☺️🥸🤠 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{argument name="比例" default="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 and 原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志、独立出版物与展览图像质感。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。 下半部分提取照片中最具识别性的**主体、轮廓、结构、姿态与叙事关系**，将其转译成一张真实可触摸的 **{argument name="风格" default="Physical String-based Systems Map / Tangible Node-link Visualization"}**。不要直接描绘原物，而是把主体拆解为少量具有意义的节点与关系：关键轮廓、结构转折、动作方向、空间位置或环境线索成为图钉式 Nodes，彼此之间使用真实线绳作为 Edges / Links，使原照片的视觉关系重新以实体网络显形，并仍能隐约辨认出原主体的身份与结构。 构图以一个明确的**核心节点或核心关系**作为视觉枢纽，其余节点围绕主体结构自然展开。线绳不是随机缠绕，而应根据原图的方向、比例、远近、连接与叙事逻辑建立关系；部分节点形成放射、聚合、三角、多边形与跨区域连接，使大量简单关系自然产生 **emergent geometry**。整体既复杂又有秩序，中心关系较密，外围逐渐疏松，保留充足负空间，避免把整个版面铺满。 材质必须具有真实实体装置感：使用细小图钉、针脚、棉线或细绳、纸质标签、手写痕迹 and 真实纸板表面，保留轻微线绳松紧差异、节点高度、交叉遮挡、针脚阴影与手工误差。整体像一件经过艺术指导的研究墙、系统设计实验或信息艺术装置，而不是电脑绘制的网络图，也不要出现赛博UI、数字发光线或廉价侦探板效果。 线绳以**鲜明但克制的{argument name="线条色" default="朱红、珊瑚红或暖红色"}**作为主要关系色，在大量自然白、暖白、浅灰或与上方照片综合色温协调的极浅背景中形成视觉张力；图钉、纸签与少量标记可从上方照片提取局部特征色进行低面积呼应。整体颜色干净、现代、有生命力，避免暗褐、脏旧、血红恐怖感 and 过度复古做旧。 文字作为系统中的**Hand-lettered Annotation** 自由介入，不预设固定标题、地点、年份或菜单式信息。根据照片中的主体、动作、位置、情绪、关系或隐喻，自由生成少量关键词、短句、箭头、圈注或微型说明，并直接写在节点附近、线绳交汇处或留白区域。字体使用**细小、松弛、略带研究笔记感与书写偏差的手写注释字体**，让文字像观察过程中自然留下的思考痕迹，同时保持高级编辑设计的克制与可读性。 整体呈现**实体节点、红色线绳、关系映射、涌现几何、手写注释与大量留白**共同构成的高级实验视觉。无论主体是人物、动物、植物、建筑、器物、交通工具、自然景观或复杂场景，都应把“它是什么”进一步转译为“它的各部分如何发生关系”，形成具有研究感、艺术感、系统性与手工温度的实体信息可视化。避免随机红线、无意义节点、满版混乱、恐怖犯罪板、数字网络UI、卡通图钉、模板化思维导图 and 普通流程图。 😌🥲😘

Goal: Create a clean browser-page screenshot showing a Chinese case-study section that presents a large bilingual infographic poster about an urban systems map. Canvas: Landscape screenshot, about 917×833 px, white webpage background, cropped so the very top shows the tail end of a Chinese paragraph and the bottom cuts off part of the poster. Use crisp UI-like rendering, not a full browser chrome. Webpage layout: At the top-left of the visible section, show a small framed picture emoji/icon followed by the bold Chinese heading “精选案例”, with a thin gray horizontal divider line underneath spanning most of the width. Below it, show a bold subsection title: “案例一：信息图可视化”. Under that title place one large infographic image centered with narrow margins. Main poster: Design an information-dense bilingual atlas poster titled “{argument name="main title" default="城市生命系统图谱"}” with the English subtitle “{argument name="English subtitle" default="Urban Metabolism Atlas"}”. Under the title add the small bilingual tagline “城市是一個有生命的系統 / The City is a Living System”. The poster should look like a professional architectural/urban-planning infographic: off-white background, navy headline text, thin gray panel borders, small bilingual labels, diagrammatic icons, and an isometric cutaway city illustration occupying the central majority. Poster top elements: On the upper left, include a compass rose marked N and a scale bar labeled “Scale” with tick marks 0, 50, 100, 200, 500m. Near the top center, include a boxed “System Legend” with exactly 10 colored line samples labeled: Electricity, Gas, Heating, Communication, Traffic, Logistics, Data Flow, People Flow, Clean Water, Wastewater. On the upper right, include one small inset map card labeled “Location”, showing a simplified city map with green parks, blue waterways, gray streets, and a red boundary. Central city illustration: Show a dense isometric smart city with many high-rise towers, mid-rise blocks, roads with cars and buses, a blue canal or river, bridges, street trees, plazas, underground metro tunnels and utility pipes visible in a cutaway at the bottom. Include small details such as a drone, airplane, rooftop solar panels, transit stations, pedestrians, and service vehicles. Use thin colored network lines running through the city to imply water, energy, data, logistics, and transit flows. Add exactly 5 visible circular numbered callout markers in the central scene: 6 on a building, 3 near a road/transport corridor, 8 near the right street edge, 9 in a green plaza, and 10 near an underground tunnel/canal edge. Side information cards: Place exactly 6 visible rounded rectangular system cards around the city, each with a colored numbered badge, bilingual title, small bullet labels, and mini diagrams. Left column has 3 cards: 1 “能源系统 / Energy Grid” with solar panels, battery storage, EV charging, and a car; 2 “城市水循环 / Water Cycle” with water plant, rainwater collection, sewage treatment, reclaimed water, and groundwater diagrams; 3 “交通网络 / Transportation” with a subway train, bus, roads, bicycle icon, and route lines. Right column has 3 cards: 6 “建筑内部系统 / Building Systems” with a cutaway building showing floors, HVAC, fire safety, BMS control, and pipes; 7 “公共服务 / Public Services” with hospital, school, fire station, police station, and community service icons; 8 “食物与物流 / Food & Logistics” with warehouse, cold chain, last-mile delivery, truck, boxes, and robot delivery. Keep the lower portions of the left and right columns slightly cropped by the screenshot edge, matching a captured page view. Visual style: Highly detailed semi-realistic isometric illustration mixed with technical infographic design, muted grays and whites with navy typography, accent colors yellow, cyan, red, purple, orange, and green. Text should be mostly legible at headline level but many small labels can be tiny. Maintain the feeling of an authentic Chinese web article showcasing an example image. Constraints: Do not add browser address bars, watermarks, floating toolbars, or extra social-media UI. Preserve the Chinese headings on the webpage and the bilingual poster title hierarchy. The image should look like a screenshot of a generated infographic embedded in a documentation page.

A high-quality professional product photograph of three premium loaded beef tacos arranged neatly on a dark ceramic plate, centered against a warm terracotta-orange seamless studio background. Each taco features a crisp golden corn shell filled with juicy seasoned grilled beef, melted cheddar cheese, fresh shredded lettuce, diced tomatoes, purple onions, jalapeño slices, and creamy lime sauce. The beef has realistic grilled texture and subtle char marks, while the vegetables appear fresh and vibrant with natural moisture. Soft cinematic studio lighting creates rich highlights and subtle shadows beneath the plate. Ultra-sharp focus, DSLR macro food photography, premium Mexican fast-food advertisement style, hyper realistic, clean commercial composition, 8K. Aspect Ratio: 1:1 Create a hyper-realistic exploded vertical infographic composition of a premium loaded beef taco. Top → Bottom structure: Fresh Cilantro Garnish → Lime Crema → Jalapeño Slices → Diced Tomato & Onion → Shredded Lettuce → Melted Cheddar Cheese → Seasoned Grilled Beef → Crispy Corn Shell Every element must be perfectly centered, evenly spaced, and aligned vertically. Show realistic grilled beef texture, melted cheese, crisp vegetables, fresh herbs, creamy sauce, and a detailed crunchy corn shell. Use a warm terracotta-orange seamless studio background, soft commercial lighting, subtle realistic shadows beneath every floating element, ultra-sharp DSLR macro food photography, premium fast-food infographic aesthetic, clean professional composition, hyper realistic, 8K. Add clean minimalist infographic text labels with thin pointer lines using these exact labels: "Cilantro" "Lime Crema" "Jalapeños" "Tomato & Onion" "Lettuce" "Cheddar Cheese" "Grilled Beef" "Corn Shell" Aspect Ratio: 1:1 The tacos start to slowly spin while the ingredients separate gently and precisely, maintaining alignment and scale. The motion is smooth, appetizing, and controlled with no extra effects.

Goal: Create a dark premium editorial infographic poster for {argument name="brand name" default="DSIV MUSIC"} explaining an “infographic-to-video” workflow using GPT Image 2 and HyperFrames. Canvas: Vertical 4:5 poster, black matte background with subtle charcoal gradients, thin border line around the entire canvas, high-contrast white typography, warm amber accent lines and labels, sleek futuristic music/tech studio aesthetic. Layout: Split composition with text-heavy information on the left, a large angled computer monitor mockup on the right, and a wide prompt card along the bottom. Add faint geometric overlays: curved arc lines, tiny dot-grid texture, plus-sign crosshair marks, and thin divider strokes. Top branding: In the upper left, place the logo text “DSIV” with spaced letters and “MUSIC” underneath. Beneath it place the small number “03” with a short horizontal line. In the upper right, place the website “DSIVMUSIC.COM”. Main headline block: Add a small rounded amber-outline pill reading “GPT Image 2 + HyperFrames”. Below it, set a very large bold white headline on two lines: “Infographic-” and “to-video”. Under the headline, add the subheading: “Generate dense, text-accurate graphics with GPT Image 2, then animate layers in HyperFrames.” Why it works section: Add the amber spaced title “WHY IT WORKS”. Include exactly 2 benefit rows with circular outline icons: 1) an open book icon labeled “Better reading order”; 2) a play button icon labeled “More retention from motion”. Right monitor content: Show a realistic black desktop monitor angled slightly in perspective. On its screen, create a compact business dashboard titled “REVENUE GROWTH ROADMAP” with subtitle “Q2 PLAN OVERVIEW”. The dashboard must contain exactly 4 key metric cards across the top: 1) upward chart icon, “$2.4M”, “Total Revenue”, “+28% vs Q1”; 2) people icon, “12.5K”, “New Customers”, “+35% vs Q1”; 3) shopping cart icon, “$192”, “Avg. Order Value”, “+12% vs Q1”; 4) donut chart icon, “24.8%”, “Gross Margin”, “+6.3pp vs Q1”. Below, include exactly 1 line chart labeled “GROWTH TREND” with “Revenue (USD)” and month labels JAN, FEB, MAR, APR, MAY, JUN. To the right, include exactly 4 growth driver rows: “Product Innovation”, “Marketing Efficiency”, “Sales Expansion”, and “Customer Retention”, each with a small amber icon. Along the bottom of the dashboard, include exactly 4 process boxes connected by arrows: “AWARENESS / Expand reach”, “CONVERSION / Optimize funnel”, “RETENTION / Drive loyalty”, and “GROWTH / Scale impact”. Desk objects: Under the monitor, show a dark audio interface or rack unit with small knobs and lights, a low-profile keyboard, and a compact control pad at the bottom right, all mostly shadowed. Bottom prompt card: Create a large rounded rectangle outline card spanning the lower width. At the top-left of the card, use amber spaced text “MAX PROMPT”. At the top-right, add a small terminal symbol “>_”. Inside the card, use monospaced white text reading: “Create a clean infographic for [TOPIC] with accurate labels, metrics, icons, arrows, and chart elements. Leave visual breathing room. Then convert it into a HyperFrames plan that animates count-ups, line draws, arrows, highlights, captions, and voiceover timing in a deterministic 9:16 or 16:9 MP4.” Footer: Bottom left text “@DSIVMUSIC”. Bottom right small circular glyph resembling a stylized “5”. Visual style: Cinematic black-on-black product photography mixed with crisp UI design, sharp typography, subtle glow, amber highlights, accurate readable text, realistic monitor lighting, clean information hierarchy. Constraints: Keep all text legible and spelled exactly as specified. Use exactly 2 benefit rows, 4 metric cards, 4 growth driver rows, and 4 process boxes. Do not add extra logos, watermarks, or unrelated text.

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"}.

【主题 / 作品名】：{argument name="主题" default="____"} 【左侧状态】：{argument name="左侧状态" default="____"} 【右侧状态】：{argument name="右侧状态" default="____"} 【关系类型】：正面与背面 / 概念与成品 / 来源与传播 / 实体与转译 / 其他 【中轴变化】：____ → ____ → ____ 【中文标题】：____ 【英文标题】：____ 【主色调】：____ 【辅助色】：____ 【画面比例】：9:16 生成一张具有成熟 Editorial Design 与展览视觉质感的左右构图海报。 不要简单把画面切成左右两栏，而是让左右两个视觉区域表达同一个主题的不同状态，并让“中间边界”成为变化真正发生的位置。 左右区域采用不等比例布局，根据主体重量使用 40:60、45:55、55:45 等关系，不要机械 50:50。左侧负责建立起点或原始状态，右侧负责展示变化后的结果，例如： 正面作品 → 背后的结构与制作路径； 设计草图 → 建成后的真实空间； 声源主体 → 向外扩散的振动与声场； 真实实体 → 纸面上的拓印、痕迹或图像。 最重要的是中轴转译。不要用明显竖线分隔，而要选择一个核心元素穿过左右区域，并在跨越中轴时连续发生变化. 例如：花瓣逐渐化成针脚和丝线；建筑线稿逐渐变成真实墙面；器物震动逐渐扩散成声纹；石刻浮雕逐渐压平成为黑墨拓印。 这种变化必须连续、自然，让观众一眼理解左右两边存在因果、过程或转译关系，而不是两张无关图片拼在一起。 Typography 也参与左右关系，但所有文字必须属于作品本身。使用真正的作品标题、副标题、短句 and 展览信息，不出现“左右构图”“设计案例”“视觉研究”等模板占位文字。 图像较重的一侧减少信息，较空的一侧可以承担更多标题与文字，通过字体大小、密度和位置完成视觉配重。 色彩控制在 2–4 个主要色系。左右可以有明显明暗、冷暖或材质差异，但至少保留一种颜色、纹理或视觉元素跨越中轴，保证整张作品统一。 最终阅读顺序：第一眼看到左右两种明显不同的视觉状态；第二眼发现中轴处正在发生连接 and 变化；第三眼理解“左边为什么会变成右边”；最后再阅读标题与作品信息。 整体要求：两个视觉域各有作用，中间有明确转译过程，左右不平均但视觉平衡，既有内容逻辑，也有成熟作品感。

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、独立出版物与展览图像质感。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。 下半部分提取照片主体最具识别度的**轮廓、结构、姿态与叙事关系**，重构为一组 **3D miniature architectural landscape** 风格的极简艺术画面：以 **isometric view / cut cube composition / perspective of an underwater continental shelf** 的方式呈现，主体像一个被剖开的微缩立体场景，具有正确的等距视图与清晰空间层级。整体以**微缩灯塔景观**为核心语义，可根据原图主体特征灵活转译，但必须保留一眼可辨的识别性与原始叙事关系。 下半部分不是写实插画，而是将主体压缩为**简洁几何形状、扁平色块、细线条与留白**的抽象化表达；在极简基础上保留适度丰富的结构细节，使画面兼具建筑图解感与艺术海报感。主体应像一件置于白色纹理纸上的微型立体模型，带有 **hand-drawn architectural illustration** 气质：线条精细、层次清楚、细节克制而准确，避免厚重真实渲染。 画面中加入明确的**脚手架逻辑**，参考你提供的图像：脚手架不是随意装饰，而应作为包裹、支撑、搭建或介入主体结构的理性系统，与主体共同形成空间秩序。脚手架可由细密的水平、垂直构件与局部连接节点组成，围绕主体外轮廓、关键转折或立体切面展开，呈现一种“正在被建构、修复、测绘或展示”的感觉；视图必须准确，透视关系清晰，不要画成漂浮拼贴。 构图保持**主体居中、画面平衡、秩序克制**，并通过少量水平线、纵向构图线、环形元素或剖面边界增强空间感。背景使用**白色纹理纸或极浅米白纸面**，干净、安静、无阴影或仅有极弱的结构层次，不要厚重投影。保留大面积留白，让主体像悬浮于展览图录或建筑研究海报的版面中。 配色从上方照片中提取灵感，但需重新处理为**更明艳、清透、治愈且有生命力**的高级色系，而不是直接照搬原始色值。保留原图的色相线索后，适度提亮、提纯、去灰，使颜色更鲜活、更轻盈；可形成清澈蓝、湖水青、嫩绿、明黄、珊瑚橙、桃粉、淡紫等柔和而明快的综合色关系，通过冷暖对比与明度节奏建立精致层次。避免灰脏、暗沉、发旧、莫兰迪化、廉价糖果色和塑料感。 文字可少量介入，加入简洁的英文标题、编号或年份，并与主体、脚手架或留白形成自然的排版关系。文字应精致、现代、克制，像国际设计工作室、建筑海报、艺术展览海报和高端品牌视觉系统中的编辑性标注，不喧宾夺主。 整体风格呈现**高级、现代、雅致、克制、艺术化**的视觉效果，融合微缩立体景观、建筑剖面图、等距视图、脚手架系统与极简海报版式。避免过度滤镜、廉价塑料质感、卡通感、强电脑生成感、模板化效果、错误视图和无逻辑的装饰性结构。

A political map of Europe if Eurovision never existed

Goal: Create a clean product reference sheet showing a realistic black tactical carbine-style firearm from multiple angles, like a studio catalog render for a fictional modern weapon. Use {argument name="weapon type" default="black compact tactical carbine"} as the subject, with no hands, no people, and no environment. Canvas: Tall vertical white canvas, approximately 2:3 aspect ratio, divided into exactly 4 horizontal panels by thin light-gray separator lines. Each panel has a small black Japanese label at the upper left. Layout: Show exactly 4 views of the same weapon: 1) top panel labeled {argument name="right side label" default="右側面"}, a perfectly horizontal right-side profile facing right; 2) second panel labeled {argument name="left side label" default="左側面"}, a perfectly horizontal left-side profile facing left; 3) third panel labeled {argument name="top view label" default="上面"}, a narrow top-down view running left to right; 4) bottom panel labeled {argument name="front three quarter label" default="正面3/4"}, a larger front three-quarter view with the muzzle on the left and the stock on the right. Subject details: The weapon is matte black and dark gunmetal with realistic hard-surface modeling, subtle edge highlights, molded polymer body panels, screws, pins, seams, vents, and Picatinny-style rail details. Include exactly 6 major visible components repeated consistently across the views: skeletonized folding-style stock, angled pistol grip, translucent curved magazine, compact optic sight on the top rail, short fore-end with side rails and vent slots, and a cylindrical under-barrel flashlight module. Add small selector markings and tiny red/white decals on the receiver, but keep them mostly illegible. Visual style: High-resolution realistic product photography mixed with technical reference rendering, neutral studio lighting, sharp focus, crisp silhouettes, black and gray tones, minimal shadows, white background, no dramatic effects. Constraints: Keep the firearm unloaded-looking and presented only as a static visual object. Do not show ammunition, firing, disassembly, internal mechanisms, measurements, exploded diagrams, or instructions. Use exactly 4 labeled panels and no extra captions, watermarks, logos, or decorative background elements.

Using the provided reference image, edit the verification-result screen so it shows a positive OpenAI provenance detection result instead of a negative one. Keep the same dark rounded card layout, the embedded keyboard photo, the centered composition, the bottom link, and the white rounded button unchanged. Change exactly 3 verification-status elements: 1) replace the pink circular X icon with a green circular checkmark icon, 2) change the headline to green and set it to 「OpenAI ツールで生成されました」, and 3) replace the explanatory body text with 「このコンテンツは OpenAI のツールを使用して生成されました。以下のシグナルは、この結果を裏付ける証拠です。」 Preserve exactly 2 lower text elements as in the reference: the link 「詳細を表示する」 and the button label 「別のファイルを検証」. Use a clean Japanese UI style, high contrast on black, rounded corners, and make the edit look like an authentic screenshot rather than a redesigned poster.

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.

Create a refined vintage line-art travel poster on warm aged parchment paper, centered on a delicate hand-drawn outline map of {argument name="region" default="Macau, China"}. Use thin sepia ink lines with subtle watercolor washes and lots of empty beige space. Inside the map, place exactly 6 illustrated landmark elements: 1 ornate Baroque church facade near the top with small green and red trees beside it, 1 tall Macau Tower in the middle rising from calm water with low green hills behind it, 1 blue-and-white porcelain teacup in the lower middle-left, 1 flowing black-and-white Portuguese wave mosaic pavement pattern curving across the lower middle-right, 1 pink lotus flower with a green lotus leaf near the bottom, and 1 long narrow bridge extending from the right side of the map. Add a few tiny detached island shapes around the main map outline. Keep the composition elegant, minimal, museum-poster-like, with fine architectural detail, faint speckles, and soft muted colors only inside the illustrations. At the bottom center, add the Chinese title {argument name="main title" default="中国澳门"} in widely spaced black serif-style characters, and beneath it the smaller subtitle {argument name="subtitle" default="内部的小世界"}. No people, no modern graphic effects, no border, no watermark.

2x2 grid, 16:9, do this for 4 tourist cities: input = [{argument name="location" default="city"} + {argument name="infrastructure type" default="infrastructure system"} + environment + {argument name="style" default="optional style"}] run infrastructural_typography_extraction: text_content := parse word_or_place word_identity := infer whether text is a city, brand, concept, landmark, district, event, or fictional place font_personality := infer heavy, elegant, brutalist, futuristic, coastal, industrial, organic, luxury, playful, or monumental letter style infrastructure_dna := infer visual grammar of infrastructure_system network_behavior := infer flow, looping, branching, stacking, crossing, tunneling, ramping, glowing, routing, or circulation logic letter_mapping := map infrastructure onto each glyph’s stems, bowls, counters, diagonals, curves, crossbars, and terminals material_system := infer realistic construction materials light_system := infer city lights, traffic trails, signage glow, window grids, reflections, or ambient illumination environment_logic := infer surrounding urban/landscape context scale_anchors := infer vehicles, people, trees, buildings, waterways, or transit elements camera := infer cinematic aerial, street-level, drone, tilt-shift, or architectural visualization view render: a readable monumental word built from the inferred infrastructure system. constraints: - no fixed city - no fixed road system - no copied composition - no random transport spaghetti - infrastructure must physically construct the typography - word remains readable at thumbnail scale

Goal: Create an ultra-detailed photorealistic isometric miniature scale-model diorama poster of the world from {argument name="anime title" default="Attack on Titan"}, presented like a collectible museum map on a clean off-white studio background. Canvas: Vertical 4:5 poster composition. The upper third is typography, the lower two-thirds is a floating square-cut terrain diorama with rugged rocky sides and a soft realistic shadow beneath. Top typography: Centered at the top, use tall condensed bold distressed sans-serif lettering. Small spaced text above reads "THE WORLD OF". Main title reads "{argument name="main title text" default="ATTACK ON TITAN"}" in very large dark charcoal letters. Small spaced text below reads "{argument name="studio line" default="WIT STUDIO • 2013"}". Diorama layout: Show the walled civilization as a high-angle isometric model with three enormous concentric circular stone walls and fortified gates. The center contains a dense circular royal city with radial streets and a white central monument. Surrounding rings contain miniature villages, farms, roads, rivers, forests, watchtowers, and tiny human figures. Beyond the walls at the back are snow-capped mountains, wilderness, scattered ruins, and open terrain. The outer edge of the model is a thick cliff-like cutaway rock base with grass on top. Labeled signs: Include exactly 14 small dark rectangular map-label plaques with white uppercase text, placed around the diorama: 1) "BEYOND THE WALLS" near the mountains, 2) "ZIGANSHINA DISTRICT" on the upper-left wall area, 3) "KROLVA DISTRICT" on the upper-right wall area, 4) "SHIGANSHINA DISTRICT" on the far right, 5) "LAKE NALLE" by a blue lake on the left, 6) "YARCKEL DISTRICT" on the left outer area, 7) "CHLORBA DISTRICT" on the lower-left area, 8) "HUMANITY'S STRONGEST" beside a small military crest on the lower-left, 9) "TROST DISTRICT" on the right outer area, 10) "TRAINING GROUNDS" on the lower-right, 11) "ROYAL CAPITAL MITRAS" at the central city, 12) "INNER WALL WALL SINA" on the innermost wall, 13) "MIDDLE WALL WALL ROSE" on the middle wall, 14) "OUTER WALL WALL MARIA" on the front outer wall. Subject details: Make the wall rings tall, pale stone, weathered, and segmented with massive gates and red-roofed towers. Populate the landscape with tiny soldiers, civilians, horses, tiled-roof houses, roads, farmland plots, bridges, streams, and forests. Add a few tiny Titan-like humanoid silhouettes outside and near the walls for scale, but keep the scene map-like rather than action-focused. Visual style: Hyper-realistic miniature model photography mixed with anime-world cartography, crisp isometric perspective, warm daylight, realistic shadows, high texture detail, tiny hand-painted model figures, natural greens and browns, pale stone walls, snowy gray mountains, cinematic depth of field but all important labels legible. Constraints: Keep the image as a single poster, no border, no watermark, no extra logos. Preserve the exact 14 map labels listed above and the three wall labels. Use an off-white background and a centered floating diorama with clean studio lighting.

Goal: Create a dark, premium tech carousel slide promoting {argument name="headline text" default="Social media carousels as video"}, branded as DSIV Music, with a cinematic desktop-production setup and instructional marketing copy. Canvas: Vertical 3:4 poster, about 900 × 1200 px, black charcoal background with subtle grain, thin gray border, faint geometric arcs, crosshair marks, dotted grid accents, and warm amber highlight lines. Layout: Use a left-heavy editorial layout with a product mockup on the right. Top left shows the brand text “DSIV” with “MUSIC” beneath it; top right shows “DSIVMUSIC.COM”. Under the brand, place the slide number “04” with a thin horizontal rule. Below that, add a small outlined amber pill label reading {argument name="tool label" default="GPT Image 2 + HyperFrames"}. The main headline occupies the left center in very large bold white sans-serif type across four lines. Beneath it, add the subheading: {argument name="subheading text" default="Turn matching image slides into TikToks, Reels, and Shorts with motion, captions, and timing."} Right visual: Show a realistic dark monitor angled slightly in perspective on a desk, with a keyboard and small audio/control device in shadow. On the monitor, display a carousel-to-video editing interface: exactly 5 vertical slide cards across the top, numbered 01, 02, 03, 04, and 05. Card 01 reads “3 Codex prompts” with smaller text “music producers can actually use”; card 02 reads “Most AI prompts are too broad.”; card 03 reads “Generate better MIDI variations”; card 04 reads “Build a session roadmap”; card 05 is partially cropped and begins with “Turn...” as if continuing offscreen. Below the cards, show exactly 3 labeled timeline rows: “CAPTIONS”, “MUSIC / VO”, and “TRANSITIONS”, with beige caption blocks, an orange audio waveform, and small purple/gray transition blocks. Middle-left section: Add a small amber divider line, then the spaced uppercase label “WHY IT WORKS”. Under it list exactly 2 benefits, each preceded by a circled plus icon: “One idea, many formats” and “Fast repurposing”. Bottom section: Add a large rounded rectangle prompt box outlined in amber. Header text inside the box says “MAX PROMPT”. Body text uses a monospaced typewriter style and reads: “Generate 5–8 matching carousel slides for [TOPIC] with consistent typography, spacing, and visuals. Then create a HyperFrames sequence with slide timing, transition ideas, kinetic captions, music/VO timing, and deterministic render settings for a vertical short-form video.” End with a small terminal-style “>_”. Bottom left footer reads “@DSIVMUSIC”; bottom right has a small abstract circular DSIV-style mark. Visual style: Sleek black-and-white SaaS/creator-economy aesthetic, high contrast typography, warm amber accents, subtle photographic realism on the monitor and desk, clean modern Swiss grid composition, cinematic lighting, crisp legible text, no extra logos beyond DSIV branding.

1. "Anatomy of a {argument name="storm type" default="Thunderstorm"}" — a labeled cross-section of a cumulonimbus with arrows, layers and data callouts, clean flat design. 2. Photorealistic photography of a towering cumulonimbus storm, captured with a 70-200mm lens at f/8. dramatic golden hour light illuminates towering ice crystals and rain shafts, revealing the storm's internal vertical structure. sharp detail highlights the anvil head's fibrous texture and the base's dark, heavy precipitation core featuring in a photorealistic photography style, under neon glow, gritty heavy atmosphere atmosphere, extreme close-up. no AI-style warping natural skin texture with pores and creases deep layered shadows no morphing hands or faces real physics fluid cloth simulation.

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.

Create a vertical 4:5 cooking storyboard with exactly 10 panels in a {argument name="grid" default="2×5 grid"}. {argument name="surface" default="warm wooden tabletop"}, perfect top-down view, thin white borders, dusty-pink rounded headers, cream caption boxes, numbered circles and black handwritten typography.\n\nShow the exact sequence: {argument name="dish" default="mie goreng"} packet → packet opens → noodles enter silver pot → noodles boil → seasoning sachets come out → cooked noodles enter black bowl → seasonings fall in → noodles mix → fried egg placed on top → finished mie goreng with egg and garnishes.\n\nUse clear white curved arrows, motion lines and sparkles to show every movement. Keep identical object continuity, realistic food, warm lighting, clean cute editorial storyboard style, sharp details and balanced spacing. No people, no hands, no extra panels.

Goal: Create a highly detailed cinematic character reference sheet for {argument name="character name" default="CHEN HAO 陈浩"}, a realistic contemporary Asian male delivery worker, designed for film/game character development. Canvas: Wide 16:9 character board on a matte light-gray studio background, approximately 1200 x 675 composition, clean grid layout with thin dividing lines, small black uppercase labels, documentary realism, muted desaturated color palette. Character identity panel: Top-left title reads “CHEN HAO 陈浩”. Include compact profile text: Age 27; Height 5'11” / 181 cm; Build lean-athletic; Occupation delivery worker; Location Chengdu, China. Character has short messy black hair, tired guarded eyes, light stubble, medium-light East Asian skin, slim athletic frame, and a serious worn-down presence. Main turnaround section: Across the upper center-left, show exactly 5 full-body studio views of the same character wearing a dark charcoal open overshirt, faded dark gray T-shirt, loose black jogger pants, and worn black canvas sneakers with white laces and soles. Label the 5 views: “FRONT”, “3/4 ANGLE”, “SIDE PROFILE”, “BACK”, and “FULL BODY”. Keep proportions consistent across all views. Details section: On the left beneath the identity text, show exactly 4 close-up detail reference images: 1 intense face close-up labeled “HAIR CLOTHURE” or similar small label, 1 eye close-up labeled “EYE CLOSE-UP”, 1 skin texture close-up labeled “SKIN TEXTURE”, and 1 small candid side-head detail photo. Expressions section: On the upper right, create exactly 9 head-and-shoulders expression portraits arranged in a clean grid. Labels must be: 1 “NEUTRAL / GUARDED”, 2 “ALERT / FEAR”, 3 “TENSE / DEFENSIVE STARE”, 4 “STUNNED / RECOGNITION”, 5 “SOFT / GENUINE SMILE”, 6 “RELAXED / AFFECTION”, 7 “SHARP / PAIN”, 8 “EXHAUSTED / FRUSTRATION”, 9 “DEADPAN / IRRITATION”. Keep lighting soft gray studio, face realistic and consistent. Pose and movement references: Create exactly 10 mid-to-full-body action reference panels across the middle row, labeled: 1 “DEFENSIVE STANCE / RAISED FOREARMS”, 2 “BACKING AWAY / CAUTIOUS”, 3 “GRIPPING SHOULDERS / URGENT”, 4 “RELAXED STANDING”, 5 “EMBRACING / AFFECTIONATE”, 6 “RECOILING / SHARP PAIN”, 7 “PUSHING FORWARD / DEFENSIVE”, 8 “EXHAUSTED / SLACK”, 9 “RESTRAINED / DEADPAN STANCE”, and 10 a quiet standing reference. Include varied body language: anxious, defensive, injured, gentle, tired. Bottom reference strip: Include exactly 4 sub-sections. “HAND REFERENCES” with 5 close-up hand images: open palm, two-handed gesture, side hand, dirty palm, clenched fist. “FABRIC & MATERIAL REFERENCES” with 5 close-up swatches of black-gray shirt fabric, seams, folds, and worn cotton texture. “FOOTWEAR” with 3 close-up sneaker images: front shoes, side/angle shoes, heel/side detail. “SILHOUETTE & ANATOMY” with 3 figures: front clothed silhouette, back clothed silhouette, and shirtless side torso anatomy. Lighting references: On the far right lower column, show exactly 3 cinematic lighting reference panels labeled: “HARSH MIDDAY DAYLIGHT”, “SOFT OVERCAST DAYLIGHT”, and “LOW-KEY APARTMENT LIGHTING”. The third should have moody blue-orange interior night lighting. Visual style: Photorealistic, sharp professional reference photography, realistic skin pores and fabric, subdued gray background, consistent character likeness, natural imperfections, cinematic Asian social-realist tone, organized like a production design character sheet. Constraints: Use only one recurring character with consistent face, hair, build, outfit, and age. Keep all labels small and legible. No logos, no watermark, no decorative fantasy elements, no extra characters except where an embrace/gripping pose requires partial interaction, and do not add extra panels beyond the specified counts.

Create a vertical 2:3 educational storyboard infographic, 5 horizontal scenes, cinematic realistic 3D science visualization, exactly like a professional educational video storyboard. TOPIC: HOW LIGHTNING HAPPENS Duration: 15 seconds 1 | 0:00–0:03 — STORM CLOUDS Visual: Huge dark storm clouds forming above a landscape. Action: Clouds grow rapidly with electric particles inside. VO: “Lightning begins inside powerful storm clouds.” SFX: Wind and distant thunder. Camera: Slow aerial push in. Transition: Light Flash. 2 | 0:03–0:06 — ELECTRIC CHARGE Visual: Close-up inside cloud showing positive and negative charges separating. Action: Blue and orange particles move to opposite sides. Labels: POSITIVE CHARGE, NEGATIVE CHARGE. VO: “Ice and water particles separate electric charges inside the cloud.” SFX: Electric crackle. Camera: Macro tracking. Transition: Energy Glow. 3 | 0:06–0:09 — CHARGE BUILDS Visual: Dark cloud above the ground, bright electrical energy increasing. Action: Electric particles move downward toward Earth. VO: “As the charge becomes stronger, electricity searches for a path.” SFX: Rising electrical hum. Camera: Tilt from cloud toward ground. Transition: Quick Flash. 4 | 0:09–0:12 — LIGHTNING STRIKE Visual: Bright lightning bolt connects cloud to ground. Action: Lightning travels rapidly downward. Label: LIGHTNING. VO: “A powerful electrical discharge creates a lightning bolt.” SFX: Loud thunder crack. Camera: Fast Pull Back. Transition: White Flash. 5 | 0:12–0:15 — THUNDERSTORM Visual: Wide storm landscape with lightning and rain. Action: Lightning flashes while rain falls below. VO: “The sudden heating of air also creates the sound of thunder.” SFX: Deep thunder rolling. Camera: Wide aerial pull back. Transition: Smooth Fade. Bottom: NARRATOR (VO): Clear, calm, educational male voice.

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，保持主体结构、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有艺术杂志、独立出版物和展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、姿态与叙事关系**，以 **isometric 等距空间逻辑重新构建**。不是把原物简单变成3D模型，而是将主体拆解为清晰的体块、层级、切面与空间关系，在统一等距轴线中重新组合，使其兼具建筑模型般的结构秩序与编辑插画般的视觉概括。可适度调整观察角度、比例和局部结构，以更好地展示主体最有代表性的形态，但必须保持一眼可识别的身份特征。 同时从照片的核心内容、动作、结构或象征关系中提炼一个**主题意象**，将其几何化、符号化并融入isometric构图。主题意象可以成为底座、切面、空间缺口、路径、包围结构或负形，让主体与其发生穿越、嵌合、悬浮、切割、承托或错层关系，使主题不是附加装饰，而是决定主体如何存在于空间中的构图机制。 构图根据主体的视觉重心、轮廓走势 and 空间特性自适应设计，通过等距轴线、体块比例、层级错落、尺度反差、局部裁切和大面积留白建立专业秩序。主体不必机械居中，可偏置、悬浮或延伸，让isometric结构与主题意象共同形成唯一视觉中心。 主体采用**高明度、清透、柔和的日系配色与细腻哑光材质**。颜色从上方照片中提取最有生命力、最能代表主体精气神的色彩重新调制，以柔白、奶油白或极浅暖色作为基础，将核心色转化为干净、明亮、轻柔的色面，通过同色深浅和少量点色区分不同体块。光影柔和而明确，用轻微明暗帮助读取结构，避免厚重3D阴影、塑料材质和灰脏色调。 背景保持大量留白，并加入**达·芬奇手稿式的创作研究痕迹**：与主体相关的轮廓草图、结构拆解、局部放大、比例线、测量线、箭头、几何推演、自然观察线稿和微型注释，以极淡的铅笔、赭色墨线或褪色手稿质感若隐若现地分布在主体周围。手稿应像设计过程留下的思考轨迹，与精确的isometric主体形成“理性成品与感性研究过程”的对照，不形成第二视觉中心。 文字同样围绕主题和空间结构组织。从照片的主体身份、动作、情绪或象征意义中提炼一个简短英文标题，并搭配极少量地点、状态词或微型注释。文字可以沿isometric轴线、主题意象边界、结构切面或手稿辅助线排列，横排、竖排、错位、穿插或隐藏于负形中，使文字像设计图纸和高级艺术出版物中的信息层，而不是后期贴上的标题。 整体呈现**主题隐喻 × Isometric空间秩序 × 达·芬奇式研究手稿 × 日系清透色彩 × 东方留白 × 高级编辑设计**的视觉气质。无论主体是人物、动物、植物、建筑、器物、食物、交通工具或自然景观，都应以其自身结构找到最合适的等距重构方式，避免普通3D模型、游戏场景感、轴测工程图感、卡通低多边形、机械居中、电商展示感和模板感。

生成一张 16:9 横版、纯白背景 的 旗袍结构与工艺细节图鉴，整体风格为 现代简洁图鉴页 + 高端服饰结构研究图 + 新中式极简服装解析页，画面干净、明亮、克制、精致，具有清晰的设计感与传播感。\n\n画面顶部设置完整的标题说明区，排版简洁高级、留白充足：\n\n主标题：“现代改良无袖旗袍”\n副标题：“结构与工艺细节图鉴”\n顶部风格说明行：“新中式极简｜米白提花丝绸｜祥云暗花提纹｜米白底・浅金滚边”\n右上角系列标签：“新中式系列”\n\n背景必须是 纯白色，不要米白、不要宣纸色、不要复古纸张感。\n\n画面中央是一位 22–32 岁的成年东方女性，气质 清雅、现代、克制，五官 清秀知性，轮廓柔和，东方感明确，发型为 简洁低髻。人物姿态自然稳定，正面站姿或轻微 3/4 角度，完整露出全身，双臂不要遮挡服装结构，整体重点是展示旗袍，不是拍人物写真。\n\n她身穿一件 现代改良无袖旗袍，风格方向为 新中式极简，整体廓形为 修身流线型。旗袍具有以下明确设定：\n\n领型：低立领\n襟型：简化斜襟\n盘扣类型：极简一字扣\n袖型：无袖\n长度与开衩：小腿中长款，中开衩\n面料：米白提花丝绸\n纹样与工艺：祥云暗花提纹\n主色与滚边配色：米白底 + 浅金滚边\n\n中央完整旗袍必须清晰展示：\n\n低立领结构\n简化斜襟走向\n极简一字盘扣\n无袖肩部轮廓\n修身腰线与腰省关系\n中开衩位置\n下摆与滚边关系\n\n围绕中央主体，在左右两侧分布 7 个局部拆解模块，所有模块必须严格来自中央同一件旗袍，保证 颜色一致、面料一致、纹样一致、滚边一致、结构一致。拆解重点为：\n\n领口\n襟线\n无袖肩部\n腰省\n开衩\n提花纹理\n滚边工艺\n\n局部模块需混合三类形式：\n\n结构放大图：领口、襟线、无袖肩部、开衩\n工艺微距图：提花纹理、滚边工艺、极简一字盘扣\n结构线稿图：腰省结构线稿\n\n使用 虚线手绘单向箭头 将每个局部模块与中央旗袍的对应位置连接，箭头要求：\n\n极细虚线\n手绘感曲线\n单向箭头\n小圆点定位\n优雅克制，不要科技信息图风\n\n每个局部模块旁边只标注简短中文组件名称，不写长段说明。可使用如下文字：\n\n领口\n襟线\n无袖肩部\n腰省\n开衩\n提花纹理\n滚边工艺\n\n在画面底部加入少量小样陈列，保持简洁，可包含：\n\n米白提花丝绸 面料小样\n浅金滚边 色卡小样\n简约一字盘扣 工艺小样\n\n整体视觉要强调：\n\n纯净感\n现代结构感\n新中式极简气质\n面料提花的细腻层次\n米白与浅金的高级配色\n图鉴感、设计研究页感、可传播性\n\n光线柔和明亮，像高级服装设计展示页，能清晰呈现丝绸提花纹理、滚边厚度、盘扣细节与剪裁结构。\n\n负面约束：\n不要普通写真海报感，不要电商白底商品图感，不要杂乱排版，不要大段说明文字，不要粗箭头，不要科技感直线连接，不要人物遮挡服装结构，不要局部模块与中央旗袍不一致，不要错误开衩位置，不要模糊纹理，不要塑料质感。