Find a prompt from the picture and copy it. Every post keeps the author credit and the original link.
通用 / 未注明1:1，冷粉白近轴直闪黑底高反差，韩系女友视角超近距离贴脸大头照，干净数码成像，无颗粒。 成年年轻女性，Y2K 桃粉玻璃唇妆的冷粉变体，冷白通透底妆，细长微上扬眼线，桃粉玻璃唇只集中在唇部，额头与双颊保持自然半哑光，鼻梁与鼻尖仅留窄而克制的小高光，真实毛孔与细小绒毛可见，湿润微乱黑色长发，几缕湿发自然垂落额前和脸侧。 黑色贴身高领，只露肩线和领口，细银项链，银色小耳环。 脸极靠近镜头，近距离平视，大胆裁切，只留下脸、少量头发和肩颈。左手从下方托住脸颊，手指自然弯曲贴近太阳穴，眼神直接看向镜头，表情安静、略带疏离感。 近轴柔闪从镜头方向正面打来，瞳孔内形成清晰圆形高光，鼻尖、下眼睑和唇珠分别留下一个小高光，湿发边缘出现冷白亮线，背景迅速衰减成纯黑。
通用 / 未注明2Use the uploaded reference image as the STRICT PRIMARY visual reference for the woman’s face, facial features, hairstyle, hair color, hair length, body proportions, outfit, pose, camera angle, framing, lighting, and overall composition. Preserve her appearance as closely as possible. Create an ultra-photorealistic lifestyle fashion street snapshot of a clearly ADULT young Japanese woman in her 20s in a beautiful tree-lined urban park on a bright early-autumn day. She has natural realistic skin, dark-brown eyes, and long dark-brown hair tied in a low ponytail with wispy bangs. She gently tilts her head, lightly touches her hair near one ear, smiles softly at the camera, and holds an iced coffee with a black straw in her other hand. Outfit Ivory textured sleeveless halter-neck blouse with pointed collar, button front and subtle keyhole opening, fitted silhouette; high-waisted wide-leg brown trousers; brown leather belt with gold buckle; dark-brown leather shoulder bag; clean white low-top sneakers. She stands in a relaxed S-shaped pose with one leg slightly crossed and one foot playfully lifted behind her. Background Stylish Japanese urban park with mature trees, greenery, stone benches and paved walkway. On the right, include a black café chalkboard reading: “Good Coffee Good Days ♡” Warm natural sunlight filters through the trees, creating realistic dappled shadows and subtle hair highlights. Photography Vertical 2:3 portrait, full-body framing, natural candid street-fashion composition, 35mm-equivalent perspective, iPhone 17 Pro aesthetic, Apple Smart HDR, realistic skin and fabric texture, natural depth of field, high-resolution detail, authentic smartphone photography.
GPT Image 22Create a beautiful, highly detailed, handmade travel sketchbook spread inspired by an artist’s personal travel journal. Show an open sketchbook with warm ivory paper, slightly imperfect edges, and visible paper texture, filled with intricate hand-drawn illustrations of [COUNTRY / CITY]. The two-page spread should feel like a collection of little memories gathered during a journey, with famous landmarks, traditional architecture, charming streets, cultural symbols, local food, nature, and tiny everyday details arranged organically across both pages. Use fine black ink linework, delicate cross-hatching, loose pencil strokes, architectural doodles, handwritten labels, tiny arrows, and small notes pointing toward the illustrated places. Let the drawings feel authentic and handmade, like a real artist sketched them while travelling. 🌈 The Special Touch — Selective Beautiful Colors Keep most of the artwork in elegant black-and-white ink, but bring selected elements to life with beautiful, carefully placed splashes of color. 🗻 Mountains and landscapes with soft watercolor blues, sage greens, and snowy whites. 🏯 Famous landmarks with subtle terracotta, warm beige, and muted golden tones. 🌸 Flowers and leaves with delicate pinks, coral, and fresh greens. 🍜 Local food illustrated in appetizing, vibrant colors. 🏮 Traditional lanterns, cultural objects, or street signs highlighted with rich reds and warm amber. 🌊 Rivers, lakes, or ocean views accented with dreamy turquoise and soft blue. 🚌 Tiny travel details featuring unexpected pops of mustard yellow, dusty orange, and pastel colors. Important: The colors should appear selectively, as if the artist used watercolor and colored pencils to highlight their favorite memories. Some illustrations should remain completely monochrome, while others should be partially or beautifully colored. The contrast between black ink and colorful details should make the artwork visually captivating without overwhelming the page. ✍️ Composition & Atmosphere Include the country name in large, artistic handwritten lettering, accompanied by a tiny national flag. Add a mixture of large landmark sketches and smaller doodles, creating a rich yet balanced composition. Allow some drawings to overlap slightly or extend toward the edges of the pages. Include spontaneous pencil marks, unfinished outlines, tiny stars, handwritten location names, and subtle artistic imperfections. Show the sketchbook as a real physical object, opened in someone's hand against a simple, softly lit background. Use a close-up perspective, natural daylight, realistic paper texture, and gentle shadows. Art style: Travel journal meets architectural ink illustration meets selective watercolor sketching. Sophisticated, cozy, artistic, nostalgic, and irresistibly beautiful. Aspect ratio: 4:5 vertical composition. Final result: A stunning, realistic travel sketchbook that looks handmade rather than digitally designed, with intricate black ink drawings and strategically placed bursts of beautiful color that make every page feel like a treasured travel memory.
通用 / 未注明2Use the uploaded reference image as the STRICT PRIMARY AND HIGHEST-PRIORITY visual reference for the woman’s facial identity, facial proportions, hairstyle, hair color, skin tone, body proportions, and overall appearance. Do not redesign or beautify her identity. Create a highly photorealistic Japanese fashion street snapshot of an adult Japanese woman walking along a sophisticated modern office district in Tokyo. SUBJECT: A beautiful adult Japanese woman with long, soft, wavy medium-brown hair, delicate wispy bangs, natural makeup, large expressive eyes, soft feminine facial features, and realistic natural skin texture. Preserve the exact facial identity and hairstyle from the reference image. OUTFIT: fitted taupe-gray sleeveless ribbed high-neck knit top soft dusty-pink cardigan casually draped over her shoulders and arms layered ivory / pale champagne chiffon ruffle mini skirt with multiple delicate translucent tiers elegant black pointed-toe high heels small black quilted shoulder bag with a gold chain strap delicate gold necklace refined feminine Korean/Japanese street-fashion aesthetic sophisticated neutral color palette POSE: Full-body fashion street snapshot. She is walking naturally toward the camera with one leg crossing slightly in front of the other. One hand lightly holds the shoulder-bag strap near her chest. The other hand rests naturally near the skirt. Relaxed shoulders, natural posture, elegant walking motion. Her head is upright, not tilted. She looks directly toward the camera with a soft, slightly gentle expression. Natural candid fashion-editorial feeling, not a posed studio shot. LOCATION: A clean upscale urban office district with modern glass-and-stone commercial buildings. Large reflective glass windows and dark granite walls. Minimal greenery in large architectural planters. Clean tiled sidewalk. No distracting signs, advertisements, crowds, or unnecessary objects. No other people in the background. LIGHTING: Bright late-morning to early-afternoon natural sunlight. Soft warm sunlight from the side/front. Natural shadows cast across the pavement. Subtle rim light around the hair. Realistic reflections in the glass windows. Balanced exposure with soft highlight roll-off. Natural skin tones. CAMERA: Vertical 4:5 composition. Full-body framing from slightly below eye level. Approximately 50mm equivalent smartphone/portrait perspective. Natural smartphone photography rather than DSLR-style photography. High-detail computational photography similar to an iPhone 17 Pro with Apple Smart HDR. Sharp facial details and realistic skin texture. Natural depth of field with the background gently softened. Authentic photographic perspective and realistic proportions. STYLE: Ultra-photorealistic. High-end Japanese fashion street photography. Natural candid snapshot. Realistic fabric texture, hair strands, skin pores, glass reflections, pavement texture, and sunlight. Subtle cinematic color grading. Premium fashion editorial quality while maintaining an authentic everyday street-photography appearance.
Nano Banana4Minimal hand-drawn illustration, off-white paper background, dark gray sketch lines, muted umbrella yellow as the only accent color, lots of negative space, Notion-like doodle aesthetic, faceless round-headed human figure, clean editorial composition, conceptual rather than literal, simple background, no realism, no 3D, no painterly texture, no high saturation, no complex scene, no photographic detail. Add one short Chinese quote in a natural handwritten style near the bottom. The overall mood is restrained, lucid, slightly ironic, and emotionally calm. Keep the whole series visually consistent. Use Chinese wherever possible for any visible language or textual content, unless a proper noun, technical term, or special usage is better kept in its original form.
通用 / 未注明4一位年轻成年感女性形象站在昏暗的音乐排练室或后台器材空间中，人物位于窄竖幅画面的中下部，上方保留大面积黑色幕布和暗色留白。她的身体大致朝向镜头，头部轻微侧倾，目光看向画面右侧而不是直视镜头，表情平静，像处在演奏间隙或试音停顿中。 她留有暖棕色中长卷发，发丝自然落在肩前，并受到右侧暖光照亮。穿贴身黑色长袖上衣、宽松浅灰色旧化破损牛仔裤、黑色金属装饰腰带，胸前佩戴细长十字吊坠。黑色上衣部分融入暗背景，浅色牛仔裤承担下半身明度。 一把青蓝色电贝司斜跨身体，琴身位于左下方，琴颈向右上方延伸并部分伸出画面。左手自然握住琴颈，右手停在琴弦和琴桥附近，动作像短暂暂停而非夸张演奏。浅色背带从肩部连接到琴身。 背景以黑色幕布为主，右后方保留扩音箱、机架设备和器材箱，但细节对比低于人物。画面最右侧有一道强烈竖向高亮区域，像舞台侧光、门口或大型灯面，具体来源不需明确。它从右前方照亮人物脸部、头发和肩部边缘，并形成“右亮左暗”的方向关系。 采用窄竖幅膝上环境人像，人物位置偏低，头顶留白明显，轻微近距离广角透视。眼睛、发丝、琴弦和牛仔布细节清楚，皮肤柔和但保留自然纹理；暗部允许出现轻微噪点和手机拍摄式压缩感，不使用塑料化磨皮。
GPT Image 24【主题】：{填写一个四字成语或四字词，如：行云流水 / 山明水秀 / 清风明月}
【英文主题】：{填写对应英文标题}
【展览名称】：{可填写，如：东方视觉主题展}
【日期】：{可填写}
【场馆】：{可填写}
【画幅比例】：9:16
请围绕同一个【主题】，设计一组 4 张完整的东方当代文化海报。四张海报的主题、核心文字和基础展览信息保持一致，但必须分别采用 4 套明显不同的平面设计语言。重点不是简单更换配色，而是改变构图、字体尺度、图像组织方式、信息结构、材质和视觉节奏，让人一眼看出这是“同一个主题的四种设计解法”。
整体参考成熟东方文化展览、美术馆视觉、编辑设计与当代平面海报的审美，将传统东方元素与现代设计语言结合。每张海报都必须是一件能够独立成立的完整作品，拥有明确的主题表达、主视觉、辅助图像、文字层级和信息系统，不要做成只有标题和背景的模板示意图。
第一种为【水墨解构风】：使用暖白宣纸、大面积留白、巨幅自由书法、古画碎片、水纹、山形、云气与墨迹进行非对称拼贴。巨大中文书法直接作为构图骨架，与古画、水纹和墨迹形成遮挡、裁切与穿插，同时加入少量现代中英文编辑信息和朱砂印章。整体以黑白灰为主，视觉自由、有张力，具有东方实验艺术和现代编辑设计感。
第二种为【现代展陈风】：采用严格的现代编辑网格、超尺度汉字、横向图像样本带和精细的小型信息系统。将东方自然素材、古画局部、纹样、器物或摄影图像像博物馆研究档案一样重新组织。色彩可使用米白、墨绿、青瓷灰绿、奶油黄等克制组合，让巨大文字首先成为几何构成，再被阅读成主题。整体应具有文化机构、美术馆和设计展览的专业视觉感。
第三种为【彩墨巨字风】：使用石青、青绿、赭金、灰蓝、米色等东方矿物色构成接近满版的山水色场，通过河流、云气、山体等元素形成连续视觉动势，再叠加超尺度象牙白书法。文字必须与山水真正发生遮挡、穿插和前后空间关系，而不是简单贴在背景上。远看首先看到强烈色域和巨大文字，近看再发现自然景观与细节。
第四种为【黑底解构风】：使用深炭黑背景、巨大象牙白现代中文字体、东方器物、山石、流云纹、古画剪影和连续曲线进行拼贴，再加入克制的几何框架、细线、展品注释和博物馆档案式信息系统。整体以黑、象牙白、青瓷灰绿、旧金和极少朱砂为主，让传统文化素材呈现出当代艺术展、设计双年展和高级文化机构的视觉气质。
四张海报必须保持明确系列感：主题完全一致，中文与英文核心标题一致，基础展览信息一致，并统一保留少量东方文化识别元素。但四张在构图方式、视觉重心、字体表现、色彩体系、图像材料和信息组织方式上必须形成明显差异，不能只是同一模板换颜色或更换背景。
每张海报都建立清楚的三级视觉层级：第一层是足够强烈的大型主视觉或巨大主题文字；第二层是东方文化图像、山水、器物、古画或其他主题视觉素材；第三层是中英文展览信息、日期、场馆、说明文字和少量印章。远看要有清楚的大形和视觉焦点，近看再发现丰富的图文关系和设计细节。
请保证作品具有足够的信息密度、版式设计感和完整度。不要偷工减料，不要只生成“背景图 + 居中标题”；需要真实处理文字与图像之间的穿插、遮挡、裁切、比例、留白、层级和阅读路径，使每张都像经过专业平面设计师完整设计的文化海报。
避免廉价国潮、古风游戏 UI、旅游宣传海报、普通山水画直接加字、四张仅更换颜色、过度对称、满屏小元素、随机装饰、无意义英文、乱码文字、编号和四角星芒。
4 张海报必须分别独立生成，不要合并成四宫格或拼图。
GPT Image 23【主题】：{例如：漆器 / 青铜 / 砚台 / 古琴 / 玉器 / 陶瓷}
【中文标题】：{4–6 字主题名称}
【英文标题】：{对应英文展览标题}
【核心器物】：{具体器物}
【辅助档案元素】：{古画 / 拓片 / 琴谱 / 线稿 / 铭文 / 材质研究等}
【主色调】：{例如：朱砂红+墨黑 / 青铜灰绿 / 黑灰 / 深木褐}
【构图机制】：{巨字穿插 / 巨大圆弧 / 黑白块面 / 斜向长轴等}
【画幅比例】：9:16
设计一张高级东方文博编辑海报，将传统东方器物重新组织进当代博物馆展览与艺术出版物的视觉系统中。
整体使用温润干净的暖象牙白艺术纸背景，保留极轻微真实纸纤维，不做旧、不脏、不泛黄。采用低饱和东方材质色系、大面积留白、非对称编辑网格，以及现代宋体 / 明朝体与高对比 Serif 英文字体混排。
核心器物使用真实、具有材质重量的博物馆级摄影表现，不做普通产品展示。根据【构图机制】将器物进行大胆裁切、放大、斜向穿插或局部超出画面，使器物本身成为版式结构的一部分。
中文标题使用大尺度 Typography，形成强视觉锚点；英文标题作为第二层级；边缘与留白区域加入极小字号的展览说明、材质研究、年代、工艺、档案信息，形成“巨大标题 × 微型信息”的强烈尺度反差。
加入与【核心器物】真实相关的【辅助档案元素】，例如古画局部、铭文拓片、器物线稿、琴谱、材料研究图等。所有档案元素应低对比、半透明、局部裁切，只作为第二层信息，不抢主体。
画面必须具有明确的三级阅读层级：
远看：器物大形 + 大标题首先成立；
中距离：看到器物、文字和档案图层之间的穿插关系；
近距离：才能阅读微型说明、材质信息与研究细节。
所有文字都应具有真实文化展览和博物馆出版物语气，不使用 Lorem Ipsum 或随机无意义英文。
信息丰富但不拥挤，主体高密度、背景低密度，保留约 40%–55% 的有效留白。
最终效果像亚洲顶级美术馆、文化研究机构或独立设计工作室制作的东方文博展览主视觉：传统内容，当代排版，安静、克制、高级，同时具有明显的视觉冲击和完整作品感。
GPT Image 24请生成一张竖版 2:3 高清图片，主题为《建筑微缩蓝图》。 建筑名称：[填写具体建筑] 画面是一张现代建筑设计手稿，上面布满中文平面图、剖面图、立面图、结构细节图、尺寸标注和施工说明。一座高度仿真的中国古建筑微缩模型，从图纸中立体“建”出来。 主建筑要占画面 65%–75%，更大、更高、更有视觉冲击力。使用低角度 3/4 俯视视角，突出模型高度、体积感和真实阴影。建筑要符合所选主题的真实特征，并呈现正在施工中的状态，完成度约 70%–85%。 加入微缩施工细节：施工小人、脚手架、木架、坡道、滑轮、木梁、石块、瓦片、材料堆、小推车、马车、半完成台阶、屋顶施工区等。细节要围绕建筑本身展开，形成一个仿真的微缩建造世界。 整体风格是现代建筑事务所概念提案板 + 博物馆级微缩模型。图纸干净高级，颜色以米白、浅灰、淡蓝、灰黑线稿为主。所有文字必须是中文，主标题写“[建筑名称]”，副标题写“建筑营造过程示意图”。 使用柔和中性光线，画面清晰、现代、克制、有高级感。避免复古黄、羊皮纸、古董感、杂乱工作室、书本、蜡烛、卷轴、尺子、指南针、桌面摆件、现代机械、现代车辆和无关背景。 最终效果：让一座中国古建筑像从现代设计图纸里真实建造出来，兼具建筑学专业感、微缩模型趣味和强烈视觉冲击力。
GPT Image 24【主题】：填写主题，例如树纪、雨序、器语、纸间 【中文标题】：填写 2–4 个字 【英文标题】：填写英文标题 【右下主视觉】：填写核心自然或人文材料，例如年轮、陶器、手工纸页、水面器皿 【中部垂直元素】：填写半透明纸、薄纱、雨幕、植物影、手部动作残影等 【右上档案物】：填写植物标本、陶片、石头、纸张碎片等小型真实物件 【主题短句】：填写一句关于时间、材料、记忆或人的短句 【主色调】：填写低饱和自然色，默认暖象牙米白、灰褐、浅赭、灰绿、墨褐 【画幅比例】：9:16 生成一张当代东方人文艺术展览海报，整体融合东方自然美学、材料档案、独立艺术杂志与现代 Editorial Design。画面安静、克制、优雅，有明显纸本感和人文气质，不做传统国潮，也不做商业广告海报。 严格保持固定版式结构：画面右下角放置一个被明显放大的【右下主视觉】，约占画面 50%–60%，主体必须被右侧或底部自然裁切，形成强烈的大尺度视觉锚点；画面中间偏左加入一条从顶部垂下的【中部垂直元素】，约占画面宽度 20%–25%，保持半透明、低对比和材料感，内部可以隐约出现植物、手影、纹理、文字残痕或自然痕迹，但不能抢过主视觉。 画面左侧保留大面积暖米白留白，纵向排列【中文标题】，使用纤细、修长、具有东方骨架的现代宋体或高级中文 Serif，不使用巨大毛笔书法。中文标题下方加入【英文标题】，使用优雅纤细的英文 Serif Typography，并加入少量主题短句和极小型编辑信息。 左上、右上、左下形成固定的小型信息系统：左上放系列身份或展览类别；右上放一个非常小的【右上档案物】以及 2–3 个极小英文关键词；左下放日期、场馆或展览说明。小字只承担编辑纹理，不要塞满画面，不生成大量无意义英文。 背景使用干净温润的象牙米白高级艺术纸，只保留轻微天然纸纤维、细颗粒和 Offset Print 印刷质感。整体配色采用【主色调】，低饱和、柔和、哑光，不使用纯黑纯白、高饱和渐变或商业亮色。 真实材料必须保留清楚的触感，例如木纹、纸纤维、陶土旋纹、水纹、植物叶脉、布料纹理或石头表面，但不要过度锐化、HDR 或 CGI。画面远看依靠“左侧标题 + 中部垂直结构 + 右下巨大主视觉”成立，近看才逐渐发现材料细节、小型档案物和微型文字。 最终效果应像真正存在于当代艺术馆、文化机构或独立艺术出版物中的东方人文展览海报，让每张作品都有明确主题和意义，而不是模板化占位设计。
通用 / 未注明【角色 / 作品】，后互联网手帐拼贴 × 社交媒体原生视觉 × 手机近距离快照 × 日系私人日记感 × 独立小志排版 × 非对称大留白。 如果填写【角色】，围绕该角色制作一张极近距离、私人记录感很强的手机快照海报；如果填写【作品】，从作品中选择 1–3 位最适合近距离表现的核心角色，统一转译进同一套社交媒体日记视觉系统。 高优先级保留角色身份锚点： 发型轮廓、发色、眼睛主色、脸部最明显特征、角色主色、头饰、耳朵、角、尾巴、面部纹样、标志配饰或其他最具辨识度的身份符号。 画面主体采用手机极近距离拍摄： 镜头贴近角色面部， 以眼睛、鼻子、嘴、耳朵或面部局部作为主要视觉中心， 允许前景产生轻微近距离透视变形， 允许鼻子、眼睛、手、耳朵等离镜头更近的部位被自然放大， 但角色身份必须清楚。 构图为下半部或中下部主体 + 上半部大面积留白。 人物 / 角色可以只露出半张脸、眼睛、额头、耳朵或上半张面部， 允许边缘裁切， 允许主体略偏左或偏右， 不要标准证件照式正中构图。 摄影质感： 手机随手快照， intimate mobile close-up， shallow depth of field， near-field perspective， soft ambient light， natural catchlight， slight focal falloff。 眼睛必须保持清楚， 眼球高光明显， 面部其他区域可出现轻微柔焦和浅景深， 形成“眼睛最清楚，鼻口逐渐柔化”的视觉层级。 光线使用柔和环境光： 窗边自然光、 室内散射光、 阴天柔光、 轻微逆光或侧光。 不使用强电影光， 不使用复杂棚拍布光， 不做高对比 HDR。 画面氛围： 私密、 随手、 轻松、 低仪式感、 像社交媒体里偶然记录下来的瞬间， 带一点情绪日记感、轻微孤独感、可爱感或冷淡感， 但不过度煽情。 版式加入少量手写视觉元素： 随手毛笔字、 手写短句、 手写英文、 手绘箭头、 小爱心、 涂鸦线、 圆圈、 划线、 边角批注、 便签式小文本块。 文字不是正式海报标题， 而是像随手写在照片上的私人备注。 排版采用 fragmented typography / 碎片化信息结构， 不同文字大小、位置、字重略有差异， 故意不完全对齐， 但整体保持干净。 可加入少量中英日混排或符号化短句， 文字内容应短、自然、像日记或聊天片段， 不要堆满画面。 整体布局： social-media scrapbook， Japanese diary aesthetic， indie zine layout， asymmetrical negative space， handwritten annotation， casual doodle marks。 背景尽量简单： 浅灰、 米白、 雾蓝、 淡粉、 浅绿、 奶油色等低饱和色场， 或真实但高度虚化的室内环境。 不要复杂场景。 色彩整体低对比、低饱和、轻微偏冷或偏奶油色， 角色眼睛、发色、配饰或某个小元素可以作为局部强调色。 图像表面保持现代、干净、清晰， 不要旧纸泛黄， 不要复古胶片划痕， 不要脏污扫描， 不要 VHS， 不要老照片损坏效果。 最终效果像一张社交平台里非常私人的视觉日记： 一张贴得很近的手机照片， 上面有少量随手文字和涂鸦， 主体被裁切， 留白很大， 看起来随意，但版式和视觉重心被精确控制。 右下角仅保留极小“voxcat”签名。
GPT Image 23Create a premium 4:5 vertical conceptual travel artwork for [COUNTRY / CITY / LOCATION / SUBJECT]. GENERATIVE IMAGE ONLY. Create the complete artwork entirely from the written [COUNTRY / CITY / LOCATION / SUBJECT]. Do not use, request, require, inspect, modify, or reference any existing image. No source image is needed. CORE CONCEPT: Create a highly realistic cinematic travel scene combined with oversized white hand-drawn doodle illustrations. The destination itself forms the complete visual foundation, while imaginative white sketch figures interact with the real architecture, landscape, objects, and atmosphere. DESTINATION: Automatically determine the most recognizable architecture, landscape, streets, structures, transportation, natural features, and cultural details associated with [COUNTRY / CITY / LOCATION / SUBJECT]. Build one coherent scene with accurate perspective, believable materials, natural lighting, and authentic local character. DOODLE INTERACTION: Introduce only one strong visual idea. Create oversized white hand-drawn figures that actively interact with something naturally present in the scene. They may climb, hold, repair, paint, pull, carry, explore, play with, or transform a real environmental element. Their hands, feet, props, and gestures must connect naturally with the surrounding architecture or landscape. DOODLE STYLE: Loose white marker/chalk line drawings, simple expressive figures, minimal facial features, imperfect hand-drawn strokes, varied line thickness, playful proportions, natural gestures, subtle whimsical character. The drawings should feel like elegant hand-drawn lines existing within the scene, never like stickers, clip-art, comic characters, or 3D cartoons. COMPOSITION: Keep the realistic destination as the dominant visual layer. Place the white drawings mainly within natural open areas such as sky, water, roads, walls, or atmospheric space. Allow creative scale differences between the drawings and the environment while maintaining believable perspective and spatial relationships. COLOR: Use the authentic colors and lighting of the chosen destination as the main palette. White linework is the primary graphic accent. Add only a small amount of warm mustard-gold/yellow to selected doodle details such as a prop, light, ribbon, flower, clothing detail, or small object. VISUAL LANGUAGE: Cinematic realism × hand-drawn illustration × surreal scale play × visual metaphor × conceptual travel art × premium editorial advertising. MOOD: Clever, imaginative, minimal, warm, playful, sophisticated, cinematic, and visually memorable. The concept should be immediately understandable but reveal additional details on closer inspection. AVOID: Existing-image editing, image references, source images, copied photographs, image recreation, photo manipulation, collage, altered landmarks, unrelated architecture, excessive characters, full-screen doodles, thick black outlines, sticker effects, 3D cartoon characters, generic cartoon scenery, clutter, excessive effects, text, logos, watermarks, UI elements. OUTPUT: 4:5 vertical composition, ultra-detailed realistic environment, seamless white hand-drawn interaction, premium conceptual travel artwork, polished editorial quality.
GPT Image 24【诗词原句】：填写一句带有明显情绪和画面感的古诗词 【两字主题】：从诗句中提炼 2 个核心字 【核心情绪】：流不尽 / 理不清 / 忘不掉 / 留不住 / 等待 / 思念等 【情绪动作】：流走 / 缠绕 / 残留 / 消失 / 褪色 / 漂离等 【小主体】：水迹 / 丝线 / 旧窗 / 花瓣 / 灯 / 舟 / 信笺等 【主色】：填写 1–3 种主要颜色 【浅压纹】：旧河道 / 线痕 / 人影 / 花影 / 水纹 / 月晕等 【地点与日期】：填写 生成一张 9:16 竖版东方诗意留白艺术海报，将【诗词原句】里的【核心情绪】转化为一种可见的【情绪动作】。 使用纯白或轻微冷调的高级手工艺术纸作为背景，保留真实纸纤维、纸浆颗粒和自然压痕。画面保持约 65%–70% 的有效留白，不使用巨大主体压满画面。 只放置一个占画面约 15%–25% 的【小主体】，再加入极小人物或极少量叙事元素。重点不是直接解释诗句，而是通过【情绪动作】让情绪发生在空间里。 背景加入与主题有关的低对比浅浮雕【浅压纹】，压纹必须有含义，例如曾经流过的路径、已经消失的人影、被拉直又缠绕的线痕、褪色花影或旧物留下的位置。远看保持干净，近看才发现这些“残留”。 颜色使用【主色】，可以漂亮、清透、有情绪，但不要为了悲伤全部做成黑白灰。让颜色随着距离和时间逐渐变淡、褪去或进入纸面。 线条、水边、花落轨迹等必须连续、柔和、自然，避免大量断点、碎线和凌乱的 AI 纹理。 中文主标题使用【两字主题】，采用现代宋体或明朝体，可通过字距、轻微错位、细线或局部延伸增加设计感，但必须保证汉字完整、准确、清晰。 同时加入小字号原诗句、地点、日期和简短英文标题。整体效果像古诗情绪、材料实验、纸张压纹与高级编辑海报的结合。 避免：普通古风插画、传统山水画、旅游海报、巨大主体、人物哭泣、乌云暴雨、情绪表达过度直白、背景米黄发旧、线条断裂、压纹没有含义、颜色灰闷、密集文字和廉价 3D。
GPT Image 23【主题 / 项目名】：{填写，例如植物展、材料研究、器物展、品牌产品}
【主视觉文字】：{填写一个适合放大的中文 / 日文 / 英文关键词}
【核心主体 / 图案】：{填写，例如植物、器物、产品、流线、几何图案}
【图文互动方式】：{穿插 / 遮挡 / 绕行 / 折射 / 嵌入 / 前后叠层}
【主色调】：{填写}
【辅助色】：{填写 1–2 个}
【品牌 / 展览信息】：{品牌名、英文副题、日期、地点、关键词等}
【画幅比例】：9:16
生成一张高级日式文字海报。不要采用“主体放中间、标题放旁边”的普通排版，而是先用超大型 Typography 建立整个画面的视觉骨架，再让【核心主体 / 图案】真正进入文字结构，与字形产生明确的【图文互动方式】。
主视觉文字要足够巨大，允许局部超出版心、被裁切、错位或压边，使文字首先成为画面的几何大形。主体与文字必须存在真实的前后关系：部分主体位于字前，部分进入字后或负空间；如果使用流线、植物、液体、玻璃等元素，应让它们因为文字结构产生绕行、遮挡、折射或形态变化，而不是简单覆盖在文字表面。
采用严谨但不僵硬的不对称编辑网格。画面可以同时使用大字、小字、竖排、边缘信息、细线和少量图像模块，但需要保持清楚的视觉层级。远看首先看到主文字、主体和大色块；中距离看到图文之间的互动；近看才读取完整的品牌、展览或产品信息。
建立真实的信息系统：主视觉文字为一级信息，项目名 / 品牌名 / 英文副题为二级信息，日期、地点、创作者、产品说明、研究关键词等作为三级小型信息分布在版面边缘和留白区域。不要使用 Lorem Ipsum 或大量无意义英文，小字也要像真实文化海报、品牌视觉或设计刊物中的信息。
色彩控制在 3–5 个主要颜色内，以【主色调】为基础，搭配【辅助色】和少量黑白灰。整体使用完整、干净、饱满的印刷色面，结合高质量哑光艺术纸、极轻纸纤维和克制的胶版印刷质感。不要明显做旧、破损、黄斑、强颗粒或廉价复古滤镜。
最终画面要具有日本当代平面设计、文化展览海报、品牌 Editorial Design 与 Typography 实验的融合感。重点不是“字排得好看”，而是让文字、主体、图案和信息真正组成一个统一的视觉系统，使每张海报都像完整作品，而不是套用同一个模板。
GPT Image 2竖版3:4，单张真实家庭手机夜拍，不要拼贴，不要四宫格，不要信息图，不要任何文字。 仅参考上传图片中女性的五官、脸型、眼睛、鼻子、嘴唇、自然笑容和黑色长直发。只参考人物外貌，不继承上传图的甜品店背景、黄色座椅、冰淇淋、服装、动作和构图，完全重建普通家庭客厅。 一位年轻成年亚洲女性，身材苗条自然，穿浅米色无袖针织家居长裙，舒服地侧坐在普通布艺沙发上，腿上随意盖着一条薄毯。她一只手拿着薯片，另一只手放在遥控器旁边，原本正在看电视。朋友从沙发另一端突然叫她，她转头看向镜头，表情先有一点发懵，嘴里还在吃东西，随后露出很轻、很自然的笑容。 客厅普通且略显凌乱，不是豪华样板房。沙发上有抱枕和薄毯，茶几上放着零食袋、水杯、纸巾、充电线和遥控器。电视在背景亮着，但屏幕内容模糊不可辨认。电视冷光照亮人物脸部和肩膀，旁边只有一盏较暗的暖色落地灯，形成真实不均匀的冷暖混合光。房间暗部保留明显手机噪点。 使用普通手机后置镜头，26mm广角，从沙发另一侧较低位置拍摄，中景。构图稍微倾斜，人物姿态松弛自然，没有刻意展示身材。保留真实皮肤纹理、轻微毛孔、少量瑕疵、自然油光和凌乱碎发，未经精修，像朋友深夜随手拍到的生活照。
GPT Image 24【主题】：{青瓷 / 传统服饰 / 宣纸 / 砚石 / 其他东方文化材质}
【中文标题】：{4–6 字主题名称}
【英文标题】：{对应英文展览标题}
【核心主体】：{器物 / 织物 / 纸张 / 材质对象}
【辅助档案】：{线稿 / 古画 / 山水 / 结构图 / 材质研究 / 文献等}
【主色调】：{月白灰青 / 浅玉色 / 暖米灰 / 墨黑等}
【核心构图】：{景深留白 / 对角悬浮 / 纸层拼贴 / 大块材质裁切等}
【画幅比例】：9:16
设计一张高级东方文博编辑海报，将传统东方器物、织物、纸张或自然材质重新组织进当代博物馆展览、艺术出版物与文化研究视觉系统中。
整体视觉强调“克制、留白、材质与信息层级”，不是传统中国风装饰海报，也不是普通产品展示。
背景使用温润干净的暖象牙白、月白或极浅灰白艺术纸 / 展览空间，只保留极轻微真实纸张、织物或自然材质纹理，不做旧、不脏、不泛黄。
采用成熟的非对称编辑网格，让【核心主体】通过放大、裁切、悬浮、透光、虚焦、叠层、斜向进入或局部超出画面的方式参与构图。不要规整居中完整展示，而要让主体本身成为版式结构的一部分。
根据【核心构图】建立明确空间关系：
可使用前景虚化、中景主体、远景轮廓形成景深；
可使用半透明纸层、织物、玻璃或自然投影形成叠层；
可使用大块材质切面、留白和阴影形成抽象几何关系；
可让主体的轮廓、褶皱、边缘、孔洞、纹理或结构线自然参与文字排版。
Typography 使用现代宋体 / 明朝体与高对比 Serif 英文字体混排。
中文标题作为主要或次要视觉锚点，根据画面选择横排、竖排、错位或大尺度局部排列；英文标题承担另一层编辑层级。不要所有文字等大，要形成明显的“大标题 × 中型说明 × 极小档案信息”尺度差异。
在留白区域加入少量真正有意义的展览信息、材料研究、制作方式、文化说明和机构信息，使画面接近真实博物馆图录、艺术出版物或研究型展览视觉，而不是使用随机英文或 Lorem Ipsum。
加入与主题相关的【辅助档案】，例如：
器物轮廓线稿、山水档案、传统服饰结构图、材质截面、纸张纹理、拓片、手稿、器形分类、工艺研究图等。
所有辅助内容必须降低对比度、局部裁切、半透明化，只作为第二层或第三层信息，不与主体竞争。
色彩使用低饱和东方材质色，根据主题控制在 3–5 个主要色阶以内。例如：
暖象牙白 + 月白 + 灰青；暖米白 + 浅玉色 + 墨灰；暖白 + 淡茶褐 + 石灰；暖白 + 墨黑 + 浅石色。
不要为了“东方感”堆叠大量红、金、青绿等传统色。
画面必须建立清楚的三级观看关系：
远看：
主体大形、标题和留白首先成立，缩略图状态下仍然有明确视觉重心。
中距离：
能够发现材质、光影、景深、投影、裁切和主体与 Typography 之间的空间关系。
近距离：
才能阅读档案信息、研究标签、线稿、材质说明和细小文字。
保持约 45%–60% 的有效留白，但留白必须受到主体方向、光线、材质边界和文字网格的控制，不能只是单纯空着。
最终效果像亚洲顶级美术馆、设计博物馆、传统工艺研究机构或高级独立艺术出版物制作的东方文博展览主视觉：
传统对象经过当代编辑设计重新组织，安静、克制、真实、有空气感、有知识性，同时具有完整的作品感和成熟的信息层级。
GPT Image 2【主题】：填写展览主题 【中文主标题】：填写 2–6 个汉字 【英文标题】：填写英文标题 【副标题】：填写展览说明 【核心图像】：异兽 / 傩面 / 甲胄 / 星图 / 其他古代图像 【黑色构图】：斜切 / 圆弧 / 纵向断层 / 夜幕负空间 / 其他 【主题短句】：填写一句简短文案 【时间地点】：填写展览信息 【画面比例】：9:16 设计一张「东方暗黑档案」实验博物馆海报。 使用泛黄旧纸、宣纸纤维、扫描颗粒、墨迹渗透和自然印刷磨损作为背景质感，以大面积墨黑平面结构制造强烈正负形关系。黑色必须参与构图，可使用斜切、巨大圆弧、纵向断层、夜幕负空间等形式，每个主题使用不同结构，避免简单套版。 将【核心图像】处理成残缺古图或文物档案切片，只展示最有辨识度的局部，例如眼睛、面具半脸、甲胄与兵刃、星盘与星图等。保留裂纹、褪色颜料、锈蚀、木纹、拓印或年代磨损，让画面像重新发现的古代视觉档案，而不是普通国风插画。 中文主标题使用巨大粗粝书法、碑刻或拓印感字体；英文标题使用超大高对比衬线字体，可裁切、越界、被黑色结构遮挡。副标题、主题短句、TIME、ADDRESS 集中在安静区域，层级清楚，并加入一枚极小朱砂红印章。 整体低饱和，以墨黑、旧纸米黄、赭石、暗金、灰绿为主。画面保持神秘、古老、克制、具有博物馆实验海报与文化档案感。
GPT Image 2Create a breathtaking artistic composition of [REAL LANDMARK] in [CITY, COUNTRY], where a hand-drawn colored-pencil illustration seamlessly transforms into a beautifully detailed, realistic scene. On one side, the landmark appears as an intricate drawing on textured ivory sketchbook paper, featuring visible pencil strokes, wax-crayon shading, delicate crosshatching, and imperfect hand-drawn lines. Moving across the composition, the colored strokes gradually evolve into the real landmark, surrounded by its authentic streets, architecture, and recognizable local environment. Tiny pencil marks transform into real trees, sketchy rooftops become actual buildings, and loose strokes of color turn into the natural sky. The transition must feel fluid and artistic, as if the entire city is being brought to life by an invisible artist. Preserve the landmark’s exact real-world architecture, proportions, and recognizable details. Use a sophisticated palette of warm terracotta, muted turquoise, golden yellow, deep cobalt blue, and natural earthy tones. Add subtle paper grain, expressive colored-pencil textures, wax-crayon details, imperfect outlines, and beautiful natural lighting. Keep the composition clean, visually striking, and professionally art-directed, with the landmark as the unmistakable focal point. Place the real name of the city in elegant, hand-lettered typography at the top, integrated naturally into the artwork. Style: Contemporary editorial illustration meets realistic colored-pencil and wax-crayon artwork, tactile textures, artistic transformation, premium art-book aesthetic, intricate details, visually captivating composition.
通用 / 未注明Use the uploaded reference image as the STRICT PRIMARY AND HIGHEST-PRIORITY visual reference for the clearly ADULT Japanese woman’s FACE, HAIRSTYLE, HAIR COLOR/LENGTH, BODY PROPORTIONS, OUTFIT, POSE, CAMERA ANGLE, FRAMING, café exterior, lighting and overall composition. If anything below conflicts with the reference image, ALWAYS follow the reference. Create an ultra-photorealistic LIVE-ACTION iPhone 17 Pro vertical 2:3 Japanese street-fashion snapshot of the same clearly ADULT Japanese woman in her 20s standing casually outside a modern glass-front café on a bright early-autumn day. SUBJECT / FACE / HAIR: Preserve her recognizable facial identity exactly from the uploaded reference. Long dark chocolate-brown hair worn completely down in soft loose waves, reaching below the chest. Airy wispy see-through bangs and delicate face-framing strands. Fair realistic skin with fine natural texture, natural brown eyes, very light pink-beige makeup, softly rosy cheeks and muted glossy pink lips. Gentle relaxed expression with a soft closed-mouth smile, direct eye contact and slight head tilt. OUTFIT: Fitted dark taupe / charcoal-brown ribbed long-sleeve turtleneck knit top. High-waisted medium-light blue denim maxi skirt with a long straight silhouette and a prominent center-front slit rising to around the knee / lower thigh. Dark brown or black ankle boots. Small structured brown leather shoulder bag with a narrow strap. Delicate silver necklace with a tiny flower / clover pendant. POSE: Standing casually on the sidewalk. Upper body leaning slightly toward the camera. One hand holds a takeaway coffee cup around chest height. The other arm hangs naturally down beside the body, hand relaxed near the front slit of the skirt. One leg slightly forward so the front slit naturally opens and reveals part of the leg. Relaxed shoulders and natural posture. PROP: Simple white takeaway coffee cup with black lid and kraft paper sleeve. Minimal modern coffee-shop branding, small “%”-style symbol on the sleeve. CAMERA / FRAMING: NOT a selfie. Photographed by another person from directly in front. Camera around chest-to-eye level with a very slight downward angle. 28–35mm equivalent lens. Vertical 2:3 composition. Three-quarter to near-full-body fashion portrait. Subject occupies approximately 85–90% of the frame. Frame from the top of the hair to below the knees / boots, with minimal empty space. Natural realistic perspective with no wide-angle distortion. ENVIRONMENT: Modern Japanese urban café exterior. Large glass windows and black metal frames directly behind her. Warm café interior visible through the windows. A black sidewalk chalkboard / menu sign positioned to one side. Minimal greenery near the entrance. Clean paved sidewalk with a few softly blurred pedestrians in the distance. Subtle window reflections and realistic city atmosphere. LIGHTING: Bright clear early-autumn daylight with warm sunlight coming from camera-left / behind. Soft backlight catching individual hair strands. Natural highlights on the face, knit texture and denim. Realistic directional shadows on the pavement. Apple Smart HDR with balanced highlights and natural skin tones. IMAGE QUALITY: Ultra-photorealistic LIVE-ACTION iPhone 17 Pro photography, realistic skin texture, detailed ribbed knit, authentic denim weave, individual hair strands, subtle depth of field, softly blurred background, accurate anatomy and polished Japanese SNS street-fashion aesthetic.
GPT Image 24Create a premium 3:4 vertical editorial food-art poster for [COUNTRY / CITY / LOCAL DISH / FOOD SUBJECT]. TEXT-TO-IMAGE ONLY. Generate the entire composition from the written dish or food subject alone. Do not request, upload, use, or depend on any reference image or existing photograph. Automatically identify the dish’s authentic appearance, ingredients, textures, and cultural identity. CORE CONCEPT: Create one elegant travel-food editorial poster combining realistic food photography in the upper section with a handmade ingredient-observation sketchbook in the lower section. Feature ONE recognizable plate or bowl containing a single dish, with at least three visually distinct ingredients. UPPER SECTION — REALISTIC FOOD PHOTOGRAPHY: Occupy approximately 48% of the canvas height. Create a beautifully composed, authentic photographic view of the specified local dish, preserving believable ingredient textures, natural lighting, realistic proportions, and culturally accurate presentation. Use subtle food-magazine color grading and extremely light film grain. Keep the entire plate or bowl visible. SECTION DIVIDER: Separate both sections with a straight, clean horizontal boundary. A very thin warm-ivory paper strip is optional. No gradients, blending, or elements crossing the divider. LOWER SECTION — INGREDIENT OBSERVATION SHEET: Use warm ivory drawing paper with visible fibers, fine grain, faint smudges, and subtle handmade irregularities. Create a sparse, asymmetrical food-field-note composition rather than repeating the full photographic dish. Place ONE small, simplified but recognizable illustration of the complete dish near the center. Keep it secondary and compact, occupying approximately one-third of the lower section’s width. Around it, illustrate 3–6 individually selected ingredients inferred from the dish. Use small watercolor specimens, cut-surface studies, herb sketches, grain clusters, sauce swatches, or distinctive ingredient shapes. Arrange them at varied sizes and angles with generous breathing room. DRAWING STYLE: Matte gouache, delicate black-ink outlines, slightly hesitant hand-drawn strokes, dry-brush gaps, uneven pigment coverage, soft watercolor edges, visible paper texture, and restrained natural colors. Keep ingredients recognizable without excessive detail. Add a few fine arrows and small handwritten numbers connecting specimens to the miniature dish. TYPOGRAPHY: Use minimal, understated editorial annotations only when helpful. Short ingredient names or tiny handwritten notes are acceptable. Keep all text small and secondary; avoid unnecessary titles or decorative lettering. COLOR PALETTE: Derive the colors naturally from the dish, balanced by warm cream, muted earth tones, and subtle ink details. FINAL AESTHETIC: Authentic local food photography × handmade ingredient studies × refined travel-food editorial × collectible culinary field notebook. AVOID: Multiple dishes, duplicate plates, mixed meals, inaccurate ingredients, excessive garnish, crowded layouts, gradients, bleeding transitions, glossy digital painting, flat vector infographics, 3D rendering, commercial menu styling, excessive text, logos, watermarks, and interface elements. FORMAT: 3:4 vertical portrait, approximately 48% photographic food scene above and 52% illustrated ingredient-observation sheet below, crisp horizontal separation, generous negative space, premium publication quality, ultra-high definition.
GPT Image 24【海报主题】 【主标题】 【核心大色域】 【大色域结构】 【主色调】 【微型文化场景】 【核心动作】 【文化器物】 【活动信息】 【画幅比例】 9:16 竖版 设计一张现代东方文化活动海报，以「纸纤维 + 大色域结构 + 主动留白 + 微型文化场景」为核心。 背景使用暖象牙白手工纸，保留约 45%–60% 留白。使用【核心大色域】建立第一视觉主体，并根据【大色域结构】形成纤维束、螺旋、薄片、正负形、穿插、嵌套或其他清晰的大形关系。远看先看到构图方法，近看才发现它与【海报主题】中的真实工艺或材料相关。 大色域具有明显天然纸纤维、纸浆颗粒、水彩或矿物颜料沉积、自然毛边和哑光质感。整体使用【主色调】，颜色低饱和但完整、有浓度，不做脏旧、褪色、随机斑驳、强噪点和数字渐变。 在大色域附近加入非常小的【微型文化场景】，人物正在真实完成【核心动作】，人物、工具和【文化器物】整体只占约 3%–5%，不做商品陈列。 人物统一采用二维纸本淡彩插画画法：五官极简、轻体积、完整平面色块、少量连续衣褶线，不出现摄影皮肤、3D 微缩模型感、CGI 光影、强投影或真实景深。 微场景与巨大主视觉之间加入一处真实来源的“尺度连接”，例如纤维、旋转轨迹、薄箔边缘、印迹、定位线或材料本身，让小人物正在处理的材料视觉上延展成巨大色域结构。连接必须有明确起点和终点，不漂浮、不机械重复同一种曲线。 主标题【主标题】使用小尺度现代宋体或明朝体，放在留白区域；英文类别、日期、地点和【活动信息】使用更小字号克制排版。所有文字必须具有真实意义。 整体阅读顺序为： 留白与大色域 → 大形结构 → 材料质感 → 微型文化场景 → 工艺动作 → 标题与活动信息。 最终呈现远看大形清楚、近看纸纤维丰富、有文化叙事和材料细节的现代东方编辑海报。 避免巨大标题、普通国风插画、写实人物、3D 微缩模型、摄影背景、PPT 网格、商业广告感、脏旧纸张、随机噪点、CGI、玻璃或镜面材质、Logo、水印、编号和星芒装饰。
通用 / 未注明2Use the uploaded reference image as the STRICT PRIMARY AND HIGHEST-PRIORITY visual reference for the clearly ADULT Japanese woman’s FACE, HAIRSTYLE, BODY PROPORTIONS, OUTFIT, SEATED POSE, CAMERA ANGLE, FRAMING, café exterior and bright natural lighting. If anything below conflicts with the reference image, ALWAYS follow the reference image. Create an ultra-photorealistic LIVE-ACTION iPhone 17 Pro vertical 2:3 Japanese casual street-fashion snapshot of the same clearly ADULT Japanese woman in her 20s sitting on a low concrete step outside a stylish modern café on a bright early-autumn day. SUBJECT: Preserve her recognizable facial identity. Warm medium-brown hair styled in a VERY HIGH, voluminous wavy ponytail, with long loose curls cascading down her back. Airy wispy see-through bangs and delicate curled face-framing strands. Fair realistic skin, natural brown eyes, very light pink-beige makeup, softly rosy cheeks and muted glossy pink lips. Gentle relaxed expression with direct eye contact. OUTFIT: Oversized light heather-gray crewneck sweatshirt, long loose sleeves extending slightly over the hands, worn casually as an oversized sweatshirt dress with bare legs. White ribbed slouch socks scrunched around the lower calves and chunky white-and-light-gray retro running sneakers. Minimal delicate silver accessories. POSE: Sitting casually on the edge of a low rough concrete café step. Knees naturally bent and slightly apart, both feet firmly on the pavement. One elbow rests lightly on her knee while that hand gently supports the side of her cheek. The other hand holds a clear plastic cup of iced café latte with a black straw near her knee. Relaxed natural posture, NOT leaning excessively forward. COMPOSITION: Front three-quarter view from slightly below eye level, 24–28mm wide-angle perspective, NOT a selfie. Full body visible from head to both shoes, subject fills approximately 85–90% of the vertical frame. Shoes prominent in the lower foreground with subtle realistic perspective. BACKGROUND: Modern minimalist café exterior with raw gray concrete walls, large black-framed glass entrance and softly visible warm interior. A tall matte-black café signboard stands beside her with simple white typography such as “COFFEE & GOOD TIME.” Small structured black leather handbag resting on the step beside her. Bright early-autumn sunlight creates soft directional shadows across the concrete pavement. LIGHTING / QUALITY: Natural sunny daylight, soft highlights on her hair and skin, subtle background blur, Apple Smart HDR, realistic skin pores, individual hair strands, detailed sweatshirt fabric, realistic hands, legs and shoes. Authentic Japanese SNS street-fashion photography, polished but natural.
通用 / 未注明超写实户外秋千人像摄影，横版约 4:3，一名年轻成年东亚女性，明确成年，侧坐在乡村公园里的木板秋千上，身体位于画面左侧，右侧保留大面积树林、步道与阴影环境。整体像 2000s 便携数码相机在晴朗午后随手拍下的旅行生活照，色彩明亮、对比偏强、略带旧 CCD 质感。 摄影者位于人物正前方偏右约 2–3 米，采用 28–35mm 等效广角镜头，机位接近秋千座板高度并轻微向上。人物从头顶完整拍到脚部，一条腿向画面右下方长距离伸出，形成明显斜线；秋千链条从画面顶部垂下，强化纵深。不要长焦虚化，不要商业棚拍。 人物为年轻成年东亚女性，中小骨架，肩膀偏窄，腰部自然纤细，腿部修长匀称，大腿有正常柔软体积，小腿逐渐收细，整体偏自然纤细比例，不要健美、粗壮腿或夸张沙漏身材。 人物侧坐在一块厚实的暖棕色实木秋千板上，上半身轻微转向镜头。双手分别抓住左右两根粗金属链条，一只手位置较高、靠近脸侧，另一只手约在胸肩高度。身体略微后仰，肩膀放松。 腿部姿势是重点：一条腿从秋千上向前完全伸直，脚尖指向画面右下方；另一条腿被座板和前腿部分遮挡。伸出的腿几乎与地面平行，形成非常醒目的横向延伸感。不要双腿并拢下垂，也不要蜷缩。 人物留乌黑色超长直发，长度到腰部附近，中分或轻微偏分，无明显厚刘海。头发自然垂在肩膀和背后，阳光下带柔和黑褐色高光。人物转头看向镜头，脸上带轻松自然的露齿笑容，表情开朗、放松、有真实旅行抓拍感。 上身穿一件非常普通的白色短袖圆领 T 恤，版型略宽松，柔软棉质，衣摆自然堆在腰部，不要紧身、不露脐、不要图案。 下身穿浅米白 / 奶油白色短裤，布料偏轻薄，表面有非常细小的彩色碎花或零散小图案，以淡粉、浅红、灰蓝等低饱和色为主。短裤长度到大腿上部，轮廓自然宽松，不要牛仔短裤或百褶裙。 腿部穿一双非常醒目的灰蓝 / 雾霾蓝色长筒袜或过膝袜，袜身从大腿附近一直覆盖到脚部，整体偏不透明的细针织材质。蓝色袜面上均匀散布极小的粉红、红色花点图案，图案非常细碎，不要变成大花纹或条纹。 脚穿浅粉色平底鞋 / 软底芭蕾鞋，颜色为柔和珊瑚粉、蜜桃粉，鞋型简单圆头、低帮，没有高跟。伸出的脚完整可见，粉色鞋与蓝色长袜形成强烈但可爱的撞色。 秋千由两根粗银灰色金属链条＋长方形木板座椅组成，链条清楚可见，从人物两侧向画面顶部延伸。座板为暖棕色木材，边缘厚实，表面略有使用痕迹。 环境为晴朗乡村公园 / 山脚休闲区。人物左后方是一片明亮绿色草地和低矮植物，更远处有整齐农田、竹木围栏或乡村设施。画面中远处能看到一层淡蓝灰色山脉，轮廓被空气雾化。 右侧占据约一半画面的是密集高大树林，树冠深绿色、阴影浓重，树干从地面一直延伸到画面顶部。林间有一条土质/木质步道，散落少量木制游乐设施、吊绳或秋千架结构，整体自然、朴素，不要现代城市公园。 天气为非常晴朗的夏季午后，天空左上方呈高饱和浅蓝色，阳光从画面左前方照入。人物皮肤、白 T 恤、草地和伸出的腿被强烈阳光照亮；右侧树林进入明显深阴影，形成非常大的明暗反差。 整体影像呈 2000s 便携数码相机 / CCD 旅行快照质感：色彩偏鲜艳，绿色和蓝色略饱和，阳光区域局部轻微过曝，暗部较深，动态范围有限，边缘轻微柔软，少量数码锐化和 JPEG 压缩感。不要现代 HDR，不要电影级调色。 重点锁定：成年东亚女性＋乡村木板秋千＋横版 4:3＋超长黑直发＋自然露齿笑＋白色短袖 T 恤＋浅色小碎花短裤＋灰蓝色带细小粉色花点的长筒袜＋浅粉色平底鞋＋双手抓金属秋千链＋侧坐秋千＋一条腿水平向前完全伸直＋绿色草地＋远山＋右侧大片深色树林＋晴朗强日光＋旧数码相机旅行照质感。
GPT Image 22A photorealistic nighttime street-fashion portrait of a young woman standing on a city sidewalk, holding a compact digital camera in both hands as if taking a photo. She has long dark black-brown hair styled into a neat low bun, with soft face-framing strands falling naturally on both sides of her face. A small elegant silver decorative hair clip is attached to the bun. She has delicate youthful facial features, natural smooth skin, subtle rosy cheeks, soft pink lips, and a bright genuine smile. She is looking slightly downward toward the camera in her hands with a cheerful, candid expression. She is wearing an oversized light-blue denim jacket with a slightly faded wash and subtle sparkling/speckled detailing, layered over a simple light-gray fitted T-shirt. She pairs it with high-waisted light-wash denim jeans for a coordinated denim-on-denim streetwear look. A thin delicate silver necklace with a tiny pendant rests around her neck. A black wrist strap is attached to the compact camera. She holds a small black compact digital camera horizontally at chest level, with her left hand gripping the camera body and her right index finger pointing toward or touching the camera controls. The camera is clearly visible and detailed, with a prominent circular lens. The background is a lively urban street at night, filled with softly glowing storefronts, illuminated signs, streetlights, passing cars, trees, and distant pedestrians. The background lights create beautiful circular bokeh and colorful points of light while keeping the woman sharply in focus. A tall streetlamp glows behind her, illuminating the surrounding tree canopy. Composition: vertical 4:5 portrait, medium-to-full body framing, subject centered slightly to the right, camera positioned around chest height, natural candid perspective, compact camera clearly visible in the foreground. Lighting: nighttime ambient city lighting mixed with warm streetlamp illumination, soft highlights on her face and hair, gentle rim light around her silhouette, realistic shadows, colorful bokeh in the background, cinematic low-light atmosphere. Photography style: ultra-realistic smartphone photography, candid Korean/Asian street-fashion aesthetic, natural skin texture, realistic hair strands, detailed denim fibers, authentic camera details, shallow depth of field, strong subject separation, subtle film grain, realistic nighttime exposure, soft cinematic color grading, high detail, 4K.