Nano Banana Pro 提示词 第 73 页

5282 条为 Nano Banana Pro 写的提示词，每条都带示例图。点开任意卡片看完整提示词。

Nano Banana Pro人像

老照片修复效果测评

修复老照片咸鱼 5 元一张，我测评一下新 原图 vs Nano Banana Pro vs GPT Image 1.5 哪个效果好？ 上提示词： { "task": "portrait_restoration", "language": "zh-CN", "prompt": { "subject": { "type": "human_portrait", "identity_fidelity": "match_uploaded_face_100_percent", "no_facial_modification": true, "expression": "natural", "eye_detail": "sharp_clear", "skin_texture": "ultra_realistic", "hair_detail": "natural_individual_strands", "fabric_detail": "rich_high_frequency_detail" }, "lighting": { "exposure": "bright_clear", "style": "soft_studio_light", "brightness_balance": "even", "specular_highlights": "natural_on_face_and_eyes", "shadow_transition": "smooth_gradual" }, "image_quality": { "resolution": "8k", "clarity": "high", "noise": "clean_low", "artifacts": "none", "over_smoothing": "none" }, "optics": { "camera_style": "full_frame_dslr", "lens": "85mm", "aperture": "f/1.8", "depth_of_field": "soft_shallow", "bokeh": "smooth_natural" }, "background": { "style": "clean_elegant", "distraction_free": true, "tone": "neutral" }, "color_grading": { "style": "cinematic", "saturation": "rich_but_natural", "white_balance": "accurate", "skin_tone": "natural_true_to_subject" }, "style_constraints": { "no_cartoon": true, "no_beauty_filter": true, "no_plastic_skin": true, "no_face_reshaping": true, "no_ai_face_swap": true } }, "negative_prompt": [ "cartoon", "anime", "cgi", "painterly", "plastic skin", "over-smoothing", "over-sharpening halos", "heavy skin retouching", "face reshaping", "identity drift", "face swap", "beauty filter", "uncanny", "washed out", "color cast", "blown highlights", "crushed shadows", "banding", "jpeg artifacts", "extra fingers", "deformed eyes", "asymmetrical face", "warped features" ], "parameters": { "fidelity_priority": "identity", "detail_priority": "eyes_skin_hair_fabric", "realism_strength": 0.95, "sharpening": "micro_contrast_only", "skin_retention": "keep_pores_and_microtexture", "recommended_denoise": "low_to_medium" } }

Nano Banana Pro摄影

老照片修复：年轻女孩

{ "task": "old_photo_restoration", "description": "Restore a heavily damaged vintage photograph of a young girl", "input_photo_condition": { "damage_types": [ "deep cracks", "fold lines", "tears across face", "scratches", "faded colors", "paper texture damage", "missing parts along crack lines" ], "age_effects": [ "yellowish tint", "low contrast", "washed-out tones", "grain/noise" ] }, "restoration_goals": { "fix_cracks": "remove all cracks and fold marks cleanly", "reconstruct_missing_areas": "restore face details naturally where torn", "color_correction": "restore natural skin tones without over-saturation", "sharpness": "enhance facial details smoothly, maintain softness appropriate for child\'s portrait", "noise_reduction": "remove grain while keeping natural texture", "background_cleanup": "smooth restoration of vintage background", "preserve_identity": "do NOT alter facial structure or change the person\'s identity" }, "subject_details": { "type": "young girl (approx. 5–7 years old)", "hair": "dark brown, two ponytails with small flower hairpins", "expression": "smiling, bright eyes", "clothing": "vintage floral dress with white collar", "pose": "front-facing school-style portrait" }, "output_style": { "look": "authentic restored vintage photo", "finish": "clean, high-resolution, natural colors", "texture": "remove paper wrinkles but preserve slight vintage softness", "lighting": "even, soft retro portrait lighting" }, "quality": { "resolution": "Ultra HD 4K restoration", "clarity": "high but natural (no plastic skin effect)" } }

Nano Banana Pro其他

旧照片新生命：重拾往昔美好瞬间

The possibilities for creating images are unlimited. You can even bring new life to old photos. Check out how easy it is to restore your favorite photos from the past:

Nano Banana ProUI 与平面

Omar Khayyam 科学家工作室

This Nano Banana Pro prompt works for scientists and those who have contributed to math and other topics no matter where they are from. do this for omar khayyam <instructions> Analyze: Determine the scientist responsible, the specific era, and the visual diagrams associated with the theory. Goal: A Macro Diorama on a Laboratory Bench. A messy, highly detailed flat-lay of a historical workspace that serves as a giant landscape for a living miniature version of the scientist. Centerpiece: An open, antique notebook lying flat. The pages must be visible and filled with specific handwritten equations and diagrams relevant to the Input Theory. Sitting directly on top of these open pages is a tiny, hyper-realistic figurine of the scientist sitting at a proportionally tiny wooden desk, working on the very notes beneath him. Surroundings: The environment is cluttered with giant-scale period-accurate objects that relate to the scientist's work. This includes a newspaper from the era acting as a backdrop, a giant coffee mug leaving stains, and massive scientific tools relevant to the theory (such as compasses, lenses, or pocket watches) scattered like terrain. Perspective: Slightly angled 45-degree macro shot looking down at the notebook. Texture: Wood grain, scratched metal, paper texture, dust particles. Lighting: Warm, late-night library lamp lighting creating a spotlight on the tiny scientist and deep shadows behind the giant props. Output: one image, 4:5 aspect ratio, photorealistic historical macro photography. </instructions>

Nano Banana Pro人像

一键转换图像为场景提示工具

[IMAGE_PROMPT] [desc] = Woman sitting cross-legged on a light wood floor, holding a phone up to take a mirror selfie in a room with white paneled walls. [objs] = Woman, smartphone, mirror (framing the image on the right), white paneled walls, light wood floor, sneakers, socks. [chars] = Woman, long dark hair pulled into a ponytail by one hand, black bodysuit/romper, grey super cropped hoodie, white socks with black swoosh logo, light grey and white sneakers. [style] = High-resolution, fashion/fitness aesthetic, soft lighting, sharp focus. [comp] = Full-body shot, vertical orientation, slightly low-angle perspective, taken via a mirror reflection, subject centered. [light] = Soft, bright, diffused front lighting (appears to be a flash on the phone/room light), even illumination, no harsh shadows. [pal] = Monochromatic look (black, grey, white), light wood tones, bright white walls. [geom] = Subject seated on the floor, legs crossed, torso slightly turned right, facing the mirror/camera, one arm raised. [micro] = Phone flash reflection on the phone, texture of the wood floor and wall paneling, visible logo on socks and shoes. [sym] = Logo on socks and sneakers. [scene] = Subject seated close to a white paneled wall with a decorative molding, mirror on the right reflecting the scene. [must] = Woman taking mirror selfie, seated position, cropped hoodie and bodysuit, sneakers and socks, white paneled wall background. [avoid] = Outdoor setting, clutter, other people. [notes] = The image is a selfie taken in a large mirror, giving a clean, centered composition.

Nano Banana Pro产品与品牌

Create an OOTD collage image

Create an OOTD collage image.价格你随便填\n\n【构图要求】\n- 左侧放置全身或半身照片的主角（时尚街拍风）\n- 右侧以白底排版列出所有单品\n- 每件单品包含：物品图、品牌名、中文品名、价格\n- 布局整洁、有呼吸感，时尚杂志风格\n\n【视觉风格】\n- 明亮自然街拍光线\n- 真实质感的衣物贴图，呈现清晰材质\n- 右侧采用电商风格白底商品照\n- 字体干净现代（类似无衬线字体）\n- 整体专业、极简、精致\n\n【人物说明】\n- 女性角色，时髦、有气质\n- 穿着：灰色短款针织、条纹衬衫、牛仔外套、深蓝短裙、黑色单鞋（可替换）\n- 造型自然，像真人街拍\n\n【单品列表排版】\n- 以独立小模块方式呈现每件单品\n- 每件单品包括：\n - 商品照（剪影风）\n - 品牌名（英文或中文）\n - 品名（中文）\n - 价格（人民币）\n\n【整体风格方向】\n- 像小红书/微博时尚博主常用的 OOTD 拼贴\n- 风格年轻、日常、好看、实用\n- 色调统一且具有品牌感

Nano Banana Pro产品与品牌

电商图一键搞定方法

很多朋友在问如何搞定电商图，我找出一个最简单“一键搞定”的方法，GPT、Cloude、Gemini等等都可以。 主要思路是，让AI学习参考已经优化完成的整套提示词，按照固定的逻辑框架输出完整的可直接使用提示词，这种方法很简单，所有人，哪怕不太会写提示词的朋友，都可以简单搞定“还可以”的电商KV系统。 进阶用法是，手动调整优化AI生成的提示词，自定义图文排版风格、样式、配色等等。 第一种，简单版指令，稳定性不高（样式、风格大部分由AI发挥）： 基于我给的产品图（女性睡衣），梳理产品卖点/参数要点，然后给我输出一套统一旗舰店极简KV系统（9:16），最后输出10张详情页的完整提示词（中英双语、干净大气、至少5张细节特写）。 请在提示词明确填入对应的中英文文案，具有统一风格（玻璃效果文字框/浮雕效果文字框等）但不同样式的排版方式，请注意每张图的提示词都是完整的，可直接使用。 Logo 单独生成（先出Logo，用于后续每张海报左上角） 图片要求： 9:16竖版高端产品海报，Apple极简风格。 背景：根据产品和品牌特点，选择纯色或渐变背景，温暖纯净，大量留白。 图文排版：根据KV系统设计习惯或要求，结合核心卖点参数、进行图文排版设计，图文并茂，中英文排版，确保每张图都有明确的作用（比如首屏hero、四宫格icon展示卖点、5个细节展示、场景展示、参数/配置/颜色、结尾信任页等）风格统一，具有符合品牌和产品调性的美感。 第二种，需要让AI参考一套完整的提示词，稳定输出，详细版指令（需复制全部提示词喂给AI）： 基于我给的产品图，梳理产品卖点/参数要点，然后给我输出一套统一旗舰店极简KV系统（9:16），最后生成10张详情页的完整提示词（中英双语、干净大气、至少5张细节特写），先单独生成Logo，用于后续每张海报左上角，其中文字排版风格需要统一，比如玻璃效果、3d浮雕效果，或者其他效果，提示词参考如下：（太长，分段放在下面） 00、LOGO生成 提示词（中文）： 极简高端时尚品牌logo，矢量风格，干净几何形。品牌名：【"MUYANG"】。图标：细线圆形徽章，内含单支精致叶枝（负空间，现代，优雅）。配色：深苔灰绿色(#2F3A33)搭配温暖米白背景(#F3EFE6)或透明背景。字体：高端衬线体"MUYANG"，字母间距宽松，下方小字"沐阳"。无渐变、无阴影、无3D、无样机、无水印。 01、海报01｜【产品·丝滑睡裙】主KV（Hero） 提示词（中文）： 9:16竖版高端极简时尚海报。柔和摄影棚日光，温暖米白渐变背景（奶油/燕麦色），超干净。精致亚洲美女模特(25-30岁)，精致五官，自然裸妆，长发慵懒随意，放松优雅姿态，全身照，一只手轻轻抚摸裙摆。 服装必须与上传的产品参考图匹配：香槟色/奶油色缎面短款吊带睡裙，细吊带，V领，裙长至大腿中部，丝滑光泽面料，保持服装设计与参考图完全一致。 排版布局：左上角放置MUYANG logo(小号)。顶部居中巨大衬线标题(2行)："SILK SLIP DRESS" / "丝滑睡裙"(中英堆叠，干净)。左侧中部玻璃拟态信息卡(3个要点，双语)：仿真丝触感 / Silk-like touch；修身不紧绷 / Flattering fit；居家也优雅 / Elegant at home。右下角【圆角药丸CTA】："立即选购 → / SHOP NOW →"。 负面词：cluttered, busy, multiple patterns, gradients, shadows, watermark, logo repeated, messy text, low quality, blurry, plain face, unattractive 02、海报02｜产品场景展示 提示词（中文）： 9:16竖版，电影质感干净时尚摄影。背景：柔和晨光透过白色纱帘的卧室，奶白色床品，极简北欧风格，温暖氛围。精致亚洲美女模特全身侧身站立，长发披肩，回眸微笑，一只手撩起发丝。使用上传的产品参考图保持香槟色短款吊带睡裙的形状、长度、面料光泽完全一致。 文字：左上角小号MUYANG logo。左上小号优雅字体："晨光私语 / Morning Whisper"。左下大标题："慵懒的刚刚好"。标题下副标题(双语)："丝滑触肤，开启美好一天 / Silky touch, beautiful day begins."。右下角CTA药丸："了解更多 → / LEARN MORE →"。 负面词：cluttered, busy, dark, messy room, shadows, watermark, messy text, low quality, blurry, plain face 03、海报03｜多场景拼贴 提示词（中文）： 9:16竖版极简拼贴海报，圆角照片块和充足负空间。背景：温暖奶油色，干净。创建4个圆角框展示同一位精致亚洲美女模特穿着上传参考图中相同的香槟色短款吊带睡裙，不同居家场景：清晨卧室窗边、客厅沙发慵懒坐姿、浴室镜前、阳台藤椅喝咖啡。所有框架中保持服装、模特完全一致。 左上角MUYANG logo。底部大衬线标题："一裙多场景"。底部副标题(双语)："居家、约会、度假都适合 / Home, date, vacation ready."。右下角附近添加小型3点列表：不挑场合 / Versatile style；秒变氛围感 / Instant chic；舒适又迷人 / Cozy yet alluring。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry, plain face 04、海报04｜细节01·面料光泽（Fabric Sheen） 提示词（中文）： 9:16竖版高端微距细节海报。背景：奶油色渐变，大量干净负空间。极近距离拍摄上传参考图中缎面面料的光泽质感，展示丝滑反光效果和柔软垂坠感，面料随身体曲线自然流动。左上角MUYANG logo。 右侧大标题(双语)："仿真丝光泽 / Silk-like Sheen"。小文案(双语，2行)："触感细腻，像第二层肌肤 / Delicate touch, like second skin."。"自然反光更显质感 / Natural luster, premium feel."。右下角CTA药丸："了解更多 → / LEARN MORE →"。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry 05、海报05｜细节02·细吊带与锁骨（Strap & Collarbone） 提示词（中文）： 9:16竖版极简细节海报。背景：温暖米白，超干净。特写拍摄精致亚洲美女模特的锁骨、肩颈线条和细吊带，来自上传参考(精致优雅)，柔和侧光勾勒轮廓，高级质感。添加一个小圆角内嵌图展示完整着装轮廓(非常小，低不透明度)。 左上角MUYANG logo。居中大衬线标题："细吊带设计"。3个微型要点(双语)：展现优美肩颈 / Flatters shoulders；精致不累赘 / Delicate refined；性感而优雅 / Sexy yet elegant。CTA药丸："立即选购 → / SHOP NOW →"。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry, plain face 06、海报06｜细节03·V领剪裁（V-Neckline Cut） 提示词（中文）： 9:16竖版时尚细节海报，干净摄影棚灯光。背景：淡燕麦到奶油色渐变，无纹理。近距离拍摄V领剪裁细节(从上传参考)，展示领口线条流畅性和恰到好处的深度，性感不失优雅。左上角MUYANG logo。 左侧大标题："V领剪裁"。副标题(双语)："修饰脸型，拉长颈部线条 / Face-flattering, neck-elongating."。添加小标签行："DETAIL 03"(小号)。CTA药丸："了解更多 → / LEARN MORE →"。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry 07、海报07｜细节04·裙摆垂坠感（Hemline Drape） 提示词（中文）： 9:16竖版高端细节海报。背景：极浅香槟金雾霾色，低对比。拍摄精致亚洲美女模特侧面下半身，展示短裙裙摆自然垂坠在大腿中部的优美曲线(从上传参考)，面料随身体动态流动，修饰腿部线条。 左上角MUYANG logo。右侧标题(双语)："短款更显腿长"。小文案(双语)："恰到好处的长度，修饰比例 / Perfect length, flattering proportion."。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry, plain face 海报08｜产品配色/型号 提示词（中文）： 9:16竖版极简时尚情绪板。背景：温暖奶油色。左侧：全身精致亚洲美女模特穿着上传参考图中的香槟色短款吊带睡裙(干净摄影棚，自然站姿)。右侧：整齐排列受睡裙启发的配色/材质色卡(香槟金、奶油色、珍珠白、柔和米色) + 极简线条图标(月亮、羽毛、丝绸、晨露)。保持一切扁平、高端，不繁忙。 左上角MUYANG logo。顶部大衬线："配色灵感 / COLOR INSPIRATION"。3个要点(双语)：香槟金显气质 / Champagne exudes elegance；温柔色更衬肤 / Soft tones flatter skin；低调奢华感 / Subtle luxury。CTA："了解更多 → / LEARN MORE →"。 负面词：cluttered, busy, multiple patterns, shadows, watermark, messy text, low quality, blurry, plain face 09、海报09｜产品尺码/参数 提示词（中文）： 9:16竖版极简尺码指南海报。背景：温暖米白，干净。将尺码表(S/M/L)放置为整洁的网格卡片(玻璃拟态，圆角)。内容(双语标题)："尺码参考 / SIZE GUIDE"。表格列：尺码 Size｜衣长 Length｜胸围 Bust｜腰围 Waist｜臀围 Hip。行：S｜90cm｜80-84cm｜64-68cm｜88-92cm；M｜92cm｜84-88cm｜68-72cm｜92-96cm；L｜94cm｜88-92cm｜72-76cm｜96-100cm。左上角MUYANG logo。底部小注释(双语)："手工测量，误差±2cm属正常 / Hand-measured, ±2cm variance normal."。底部贴心提示："建议参考胸围选择尺码 / Suggest sizig by bust measurement." 负面词：no extra patterns, no clutter, no watermark 10、海报10｜结尾信任页 质保/售后/说明 提示词（中文）： 9:16竖版高端护理海报。背景：奶油色渐变，非常干净。 左上角MUYANG logo。大标题："洗护指南 / CARE GUIDE"。使用5个极简图标 + 简短双语行(干净，不拥挤)：建议手洗或使用洗衣袋 / Hand wash or use laundry bag；冷水或30°C以下水温 / Cold or below 30°C water；不可漂白或强力拧干 / No bleach or wringing；悬挂阴干，避免暴晒 / Hang dry, avoid direct sun；低温熨烫，垫布熨烫更佳 / Low heat iron, use cloth。底部添加小字(双语)："悉心呵护，延长丝滑寿命 / Care well, silkiness lasts longer."。 负面词：no clutter, no heavy texture, no watermark ------- 迭代了！ 不用管思路了！不用管格式了！ 不用让ai参考全部提示词了！ 上传图片即可（不传也可以，凭空虚构个产品也行） 完整元提示词： # 任务说明 我需要为我的产品生成一套完整的电商KV视觉系统提示词（10张海报，9:16竖版格式）。 第一步：产品信息智能提取（如果上传了图片） 请仔细分析我上传的产品图片，自动提取以下信息： ## 自动识别项目： 品牌名称识别 - 从包装/产品上识别品牌LOGO文字 - 识别中文品牌名和英文品牌名 - 提取品牌标志的设计风格（字体、图标、配色） 产品类型判断** - 识别产品所属类别（服装/食品/电子/美妆/家居/宠物用品等） - 识别具体产品名称（从包装文字或产品形态判断） - 识别产品规格（尺寸、容量、重量等） 卖点提取 - 从包装上的文案提取核心卖点关键词 - 从产品图标/认证标识提取卖点（如：有机认证、无添加、进口等） - 从产品视觉特征推断卖点（如：颜色、材质、工艺） - 提取数据卖点（如：百分比、含量、时长等） 配色方案分析 - 提取包装主色调（RGB/HEX色值） - 识别辅助色和点缀色 - 分析配色风格（清新/沉稳/鲜艳/高级等） 设计风格判断 - 识别包装设计风格（极简/复古/可爱/科技/艺术等） - 识别字体风格（衬线/无衬线/手写等） - 识别图案元素（水彩/几何/插画/摄影） 目标受众推断 - 根据包装风格推断目标用户群体 - 根据产品类型推断年龄段 - 根据价格定位推断消费层级 产品参数提取 - 从包装文字提取产品规格（净含量/尺码/功率等） - 提取成分信息/配料表/营养成分 - 提取使用说明/注意事项 - 提取生产日期/保质期/储存方式。 产品细节识别 - 识别产品材质质感（光滑/粗糙/哑光/高光等） 识别产品结构特点（可拆卸/折叠/便携等） 识别包装特色（自封袋/泵头/喷雾/滴管等） 输出格式： 请将识别结果整理为以下格式： 【识别报告】 品牌名称：[中文] / [英文] 产品类型：[大类] - [具体产品] 产品规格：[具体规格] 核心卖点：[卖点1 - 中英文] [卖点2 - 中英文] [卖点3 - 中英文] [卖点4 - 中英文] [卖点5 - 中英文] 主色调：[颜色名称] (#HEX) + [颜色名称] (#HEX) 辅助色：[颜色名称] (#HEX) 设计风格：[风格描述] 目标受众：[用户画像] 品牌调性：[调性描述] 包装亮点：[特殊设计元素] 第二步：视觉风格选择 基于识别的产品信息，请推荐最适合的视觉风格（也可手动指定）：视觉风格选项 （AI自动推荐或手动选择） □ 杂志编辑风格（高级、专业、大片感、粗衬线标题、极简留白） □ 水彩艺术风格（温暖、柔和、晕染效果、手绘质感） □ 科技未来风格（冷色调、几何图形、数据可视化、蓝光效果） □ 复古胶片风格（颗粒质感、暖色调、怀旧氛围、宝丽来边框） □ 极简北欧风格（性冷淡、大留白、几何线条、黑白灰） □ 霓虹赛博风格（荧光色、描边发光、未来都市、暗色背景） □ 自然有机风格（植物元素、大地色系、手工质感、环保理念） AI推荐依据： - 根据产品类型自动匹配最佳风格 - 根据包装设计风格延续品牌调性 - 根据目标受众审美偏好推荐 -- 第三步：文字排版效果选择 文字排版效果（AI自动推荐或手动选择） □ 粗衬线大标题 + 细线装饰 + 网格对齐（杂志风） □ 玻璃拟态卡片 + 半透明背景 + 柔和圆角（现代风） □ 3D浮雕文字 + 金属质感 + 光影效果（奢华风） □ 手写体标注 + 水彩笔触 + 不规则布局（艺术风） □ 无衬线粗体 + 霓虹描边 + 发光效果（赛博风） □ 极细线条字 + 大量留白 + 精确对齐（极简风） 第四步：生成完整提示词系统 请严格按照以下要求生成：视觉风格选择（必选其一） □ 杂志编辑风格（高级、专业、大片感、粗衬线标题、极简留白） □ 水彩艺术风格（温暖、柔和、晕染效果、手绘质感） □ 科技未来风格（冷色调、几何图形、数据可视化、蓝光效果） □ 复古胶片风格（颗粒质感、暖色调、怀旧氛围、宝丽来边框） □ 极简北欧风格（性冷淡、大留白、几何线条、黑白灰） □ 霓虹赛博风格（荧光色、描边发光、未来都市、暗色背景） □ 自然有机风格（植物元素、大地色系、手工质感、环保理念） # 文字排版效果（必选其一） □ 粗衬线大标题 + 细线装饰 + 网格对齐（杂志风） □ 玻璃拟态卡片 + 半透明背景 + 柔和圆角（现代风） □ 3D浮雕文字 + 金属质感 + 光影效果（奢华风） □ 手写体标注 + 水彩笔触 + 不规则布局（艺术风） □ 无衬线粗体 + 霓虹描边 + 发光效果（赛博风） □ 极细线条字 + 大量留白 + 精确对齐（极简风） 特殊需求（可选） 【是否需要模特】：是 / 否（如果是，描述模特类型） 【是否需要场景】：是 / 否（如果是，描述场景类型） 【是否需要数据可视化】：是 / 否【其他特殊要求】：[如：必须包含产品实物、需要对比图、需要用户评价等] --- # 生成要求 请严格按照以下结构输出完整提示词系统： 输出结构： LOGO生成提示词（中英双语，基于识别的品牌设计风格） 海报01 - 主KV视觉（Hero Shot，必须严格还原上传的产品图） 海报02 - 生活场景/使用场景（Lifestyle，展示产品实际使用） 海报03 - 工艺/技术/概念可视化（Process/Concept，基于识别的卖点） 海报04 - 细节特写01（Detail 01，放大产品细节） 海报05 - 细节特写02（Detail 02，材质/质感特写） 海报06 - 细节特写03（Detail 03，功能细节） 海报07 - 细节特写04 或 用户评价（Detail 04 / Review） 海报08 - 品牌故事/配色灵感（Brand Story / Moodboard，使用识别的配色） 海报09 - 产品参数/规格表（Specifications，使用识别的参数） 海报10 - 使用指南/注意事项（Usage Guide，基于产品类型） 🔴 核心要求（重中之重）： 1. 产品图还原要求 必须在提示词中明确说明： "严格还原上传的产品图，包括包装设计、颜色、LOGO位置、文字内容、图案元素等所有细节" - "产品外观必须与参考图完全一致，不得改变包装设计、配色方案或品牌元素" - "保持产品的真实材质质感（哑光/高光/磨砂/金属等）" - 例如："使用上传的朗诺RANOVA冻干鸡肉产品包装，保持蓝色袋身、水彩猫咪插画、金色LOGO等所有设计元素完全一致" 2. 文案排版要求（中英文双语） 每张海报的所有文字内容都必须采用中英文双语排版： 标题排版格式（3种可选）： 格式A - 中英堆叠（最常用）： 纯肉冻干 PURE FREEZE-DRIED 中文在上（较大字号），英文在下（较小字号），垂直堆叠，居中对齐 格式B - 中英并列： 纯肉冻干 | PURE FREEZE-DRIED 中英文横向并列，用竖线或斜杠分隔，字号相同或中文略大 格式C - 中英分离： 纯肉冻干 [左上角] PURE FREEZE-DRIED [右下角] 中英文分别放置在不同位置，形成视觉对比 卖点/说明文字排版格式： 🥩 100%纯肉 / 100% Pure Meat ❄️ 冻干锁鲜 / Freeze-Dried Fresh 🌾 无谷配方 / Grain-Free Formula - 使用图标或符号引导 - 中文在前，英文在后，用斜杠"/"分隔 - 或采用上下堆叠，中文在上，英文在下（字号略小） 段落文字排版格式： 在慵懒的午后，给爱宠一份天然美味。 On a lazy afternoon, give your pet natural deliciousness. RANOVA冻干零食，用真材实料定义健康零食新标准。 RANOVA freeze-dried snacks redefine healthy treats with real ingredients. - 中文段落和英文段落分别成段 - 英文段落字号略小（约为中文的80-90%） - 保持行距舒适（1.5-2.0倍行高） 按钮/CTA文字格式： 立即选购 SHOP NOW → 了解更多 LEARN MORE → - 中英文并列或上下排列 - 箭头符号统一使用 → 参数表格式： | 营养成分 Nutrients | 含量 Content | | 粗蛋白 Crude Protein | ≥42% | - 表头必须中英双语 - 每个参数项都要中英文标注 3. 每张海报必须包含的元素： ✅ 中文提示词（完整详细，600-1000字） ✅ 英文Prompt（完整翻译，与中文对应） ✅ 负面词（Negative Prompts，20-30个关键词） ✅ 详细排版布局说明，包括： - 所有文字的具体位置（左上/右下/居中等） - 所有文字的字号大小关系（超大/大/中/小） - 所有文字的颜色（具体色值或描述） - 所有文字的字体风格（粗衬线/细无衬线/手写体等） - 所有文字的中英文排版格式（堆叠/并列/分离） ✅ LOGO位置（通常左上角，统一位置） ✅ CTA按钮设计（位置、文字、样式） 4. 风格统一原则： 所有海报必须使用相同的文字排版效果 - 所有海报必须使用相同的配色系统（从产品图提取） - 所有海报必须保持品牌调性一致 - LOGO在每张海报中位置统一（左上角） - 中英文排版格式在所有海报中保持一致（选定一种格式后，10张海报都使用） -- 📝 输出格式示例（ 【识别报告】（先输出） 基于上传的产品图片，识别结果如下： 品牌信息： - 品牌名称：朗诺 / RANOVA - 品牌LOGO：金棕色衬线体"RANOVA"，下方中文"朗诺" - LOGO特点：配有抽象猫咪水彩插画图标 产品信息： 产品类型：宠物食品 - 冻干零食 - 具体产品：冻干鸡肉 - 产品规格：300克/袋 核心卖点（从包装提取）： 1. 100%纯肉 / 100% Pure Beef - 包装正面蓝色图标标识 2. 冻干锁鲜 / Freeze-Dried Fresh - 包装中部文字说明 3. 无谷配方 / Grain-Free - 包装底部绿色图标 4. ≥42%动物蛋白 / ≥42% Animal Protein - 包装侧面营养数据 5. 不含诱食剂 / No Attractants - 包装底部粉色图标 配色方案： - 主色调：海蓝色 (#4A90E2) - 包装袋主体颜色 - 辅助色：柠檬黄 (#FFD93D) - 水彩猫咪插画配色 - 点缀色：珊瑚粉 (#FF6B9D)、金棕色 (#C49A6C) - LOGO和文字颜色 - 背景色：奶白色 (#FFF8E7) - 包装背景 设计风格： - 包装风格：艺术水彩插画风格 - 主要元素：蓝黄渐变水彩猫咪头像 - 字体风格：LOGO使用衬线体，说明文字使用无衬线体 - 整体调性：温暖、艺术、天然、宠物友好 目标受众： - 年龄段：25-45岁 - 用户画像：养猫人士，注重宠物健康，追求天然食品，有一定消费能力 - 审美偏好：喜欢艺术感、温暖、治愈系的设计 产品参数（从包装提取）： - 净含量：300克 - 成分：鸡肉（100%） - 营养成分：粗蛋白≥42%，粗脂肪≥5%，粗纤维≤2%，水分≤5%，粗灰分≤8% - 适用阶段：全猫期 - 保质期：12个月 - 储存方式：阴凉干燥处，开袋后密封保存 推荐视觉风格：水彩艺术风格（与包装设计风格一致） 推荐文字效果：玻璃拟态卡片 + 水彩笔触装饰（现代感+艺术感） 中英文排版格式：格式A - 中英堆叠（标题）+ 斜杠分隔（说明文字） --- ### 海报01｜主KV·水彩猫咪的幸福时刻（Hero Visual） 提示词（中文）： 9:16竖版高端艺术海报，水彩插画风格。柔和自然光，温暖奶白色背景带有淡淡水彩晕染（蓝色和黄色渐变边缘）。画面中心：一只精致水彩风格的真实猫咪（英短或橘猫），毛发细腻，大眼睛有神，正享受地吃着冻干鸡肉块（产品实物），猫咪周围飘浮着抽象水彩花瓣和羽毛装饰元素（蓝色、黄色、粉色）。 产品展示（严格还原上传图片）： 朗诺RANOVA冻干鸡肉产品包装袋优雅地放置在猫咪旁边，45度角展示正面设计。必须完整还原包装的所有设计元素： - 蓝色渐变袋身（#4A90E2主色） - 正面水彩风格猫咪头像插画（蓝色和黄色晕染） - 顶部金棕色"RANOVA"品牌LOGO和中文"朗诺" - 中部白色区域"宠物零食 冻干鸡肉"文字 - 底部图标区域：蓝色"100%纯肉"图标、绿色"无谷物"图标、粉色"不含诱食剂"图标 - 右下角"净含量：300克"标注 - 包装材质：哑光塑料袋，带有自封条 排版布局（中英文双语设计）： 左上角： - RANOVA水彩logo（小号，约占画面5%宽度） 顶部居中： - 大标题（水彩笔触质感，中英文堆叠排版）： - 第一行："纯肉冻干"（金棕色 #C49A6C，粗衬线字体，字号占画面宽度30%） - 第二行："PURE FREEZE-DRIED"（海蓝色 #4A90E2，细衬线字体，字号为中文的60%） - 中英文之间间距：中文字号的0.5倍 - 副标题（下方细线装饰后）： - "每一口都是真材实料"（金棕色，宋体，小号） - "Every bite is pure ingredients"（海蓝色，无衬线体，更小号，字号为中文的80%） 左侧中部： - 玻璃拟态信息卡（圆角20px，半透明白底，模糊度10px，3个要点，图标+中英双语）： - 要点1： - 图标：🥩（肉块emoji） - 中文："100%纯肉"（深灰色 #2D2D2D，粗体，14号字） - 英文："100% Pure Meat"（中灰色 #666666，常规体，11号字） - 排版：中英文用斜杠"/"分隔，同一行 - 要点2： - 图标：❄️（冰晶emoji） - 中英文："冻干锁鲜 / Freeze-Dried Fresh"（格式同上） - 要点3： - 图标：🌾（麦穗emoji，打红叉） - 中英文："无谷配方 / Grain-Free Formula"（格式同上） - 卡片内边距：上下左右各20px - 要点之间间距：15px 右下角： - 圆角药丸CTA按钮（金棕色底 #C49A6C，白色文字）： - 按钮尺寸：宽度占画面25%，高度为宽度的25% - 按钮圆角：高度的50%（完全圆角） - 文字（中英并列）："立即为爱宠选购 SHOP NOW →" - 中文字号12号，英文字号10号，箭头符号12号 - 按钮位置：距离右边缘5%，距离底部8% 负面词 / Negative: cluttered, busy, multiple patterns, harsh shadows, watermark, logo repeated, messy text, low quality, blurry, artificial, plastic-looking, cartoon, anime style, wrong packaging design, different colors, modified logo, changed text, simplified design Prompt (English): 9:16 vertical premium artistic poster, watercolor illustration style. Soft natural lighting, warm off-white background with subtle blue and yellow watercolor wash edges. Center: An exquisite watercolor-style real cat (British Shorthair or orange tabby), fine fur detail, bright expressive eyes, happily eating freeze-dried chicken pieces (actual product), surrounded by abstract watercolor petals and feather decorative elements (blue, yellow, pink). Product Display (Strictly Restore Uploaded Image): RANOVA freeze-dried chicken product packaging elegantly placed beside cat, 45-degree angle showing front design. Must completely restore all packaging design elements: - Blue gradient bag body (#4A90E2 primary color) - Front watercolor-style cat head illustration (blue and yellow wash) - Top golden brown "RANOVA" brand logo and Chinese "朗诺" - Middle white area "Pet Snacks Freeze-Dried Chicken" text - Bottom icon area: blue "100% Pure Meat" icon, green "Grain-Free" icon, pink "No Attractants" icon - Bottom-right "Net Weight: 300g" notation - Packaging material: matte plastic bag with zip-lock Layout (Bilingual Chinese-English Design): Top-left: - RANOVA watercolor logo (small, approximately 5% of canvas width) Top center: - Main title (watercolor brush texture, Chinese-English stacked layout): - Line 1: "纯肉冻干" (golden brown #C49A6C, bold serif font, size 30% of canvas width) - Line 2: "PURE FREEZE-DRIED" (sea blue #4A90E2, thin serif font, size 60% of Chinese text) - Spacing between Chinese and English: 0.5x Chinese text size - Subtitle (after thin line decoration): - "每一口都是真材实料" (golden brown, Song font, small size) - "Every bite is pure ingredients" (sea blue, sans-serif, smaller size, 80% of Chinese size) Left-center: - Glassmorphism info card (20px rounded corners, semi-transparent white base, 10px blur, 3 key points, icon + bilingual): - Point 1: - Icon: 🥩 (meat emoji) - Chinese: "100%纯肉" (dark gray #2D2D2D, bold, 14pt) - English: "100% Pure Meat" (medium gray #666666, regular, 11pt) - Layout: Chinese and English separated by slash "/" on same line - Point 2: - Icon: ❄️ (ice crystal emoji) - Bilingual: "冻干锁鲜 / Freeze-Dried Fresh" (same format) - Point 3: - Icon: 🌾 (wheat emoji with red X) - Bilingual: "无谷配方 / Grain-Free Formula" (same format) - Card padding: 20px all sides - Point spacing: 15px Bottom-right: - Rounded pill CTA button (golden brown bg #C49A6C, white text): - Button size: width 25% of canvas, height 25% of width - Button radius: 50% of height (fully rounded) - Text (Chinese-English parallel): "立即为爱宠选购 SHOP NOW →" - Chinese 12pt, English 10pt, arrow 12pt - Button position: 5% from right edge, 8% from bottom Negative: cluttered, busy, multiple patterns, harsh shadows, watermark, logo repeated, messy text, low quality, blurry, artificial, plastic-looking, cartoon, anime style, wrong packaging design, different colors, modified logo, changed text, simplified design --- [后续9张海报以相同格式输出，每张都包含：中文提示词、英文Prompt、负面词、详细的中英文排版说明] ---

Nano Banana Pro其他

One of the coolest srefs!

One of the coolest srefs! [PROMPT] --chaos 50 --ar 16:9 --sref 680766896 --stylize 600

Nano Banana Pro人像

同一个人，三个平行宇宙

同一个人，三个平行宇宙。 @dotey 宝玉老师这个韩风剪贴簿人像，我拿去做了两个极端版本： • 原版：校园少女，棒棒糖，爱心贴纸 • Dark Academia版：图书馆，羊皮书，火漆印章 • Dreamcore版：VHS噪点，氢气球，漂浮的眼睛 三张图放一起，像同一个人活在三条故事线里。 你更想活在哪个宇宙？ 【平行宇宙①：欧洲老图书馆】 原版的棒棒糖变成羊皮书， 贴纸变成金箔和压花， 软木板变成堆满信件的书桌， 相框换成巴洛克古铜框。 同一个人，从「校园少女」变成「在图书馆写信的人」。 【平行宇宙②：数字梦境】 原版的棒棒糖变成氢气球和雪花屏电视， 贴纸变成闪粉和虹彩颜料， 背景变成VHS噪点和漂浮的眼睛。 同一个人，从「校园少女」变成「困在梦里的人」。 填不同情绪，就是不同命运。 你更想活在哪个宇宙？ 👇 两版完整提示词放评论区。 第一版 Recreate the character's appearance from the uploaded photo, accurately preserving hairstyle, facial details, and expression. Present it as a soft, nostalgic, and melancholic fashion portrait in a vertical collage format. She wears sophisticated vintage clothing (e.g., velvet or tweed blazer, layered lace blouse), holding a half-opened leather-bound book or a dip pen stained with ink near her hands. Her face is delicately adorned with subtle metallic foil elements (like gold leaf) or fine pressed flower petals near her cheekbones, creating an ethereal, classical atmosphere. Her eyes are deep and contemplative, makeup is matte and sophisticated, and her face shows a pensive, poetic expression. The background features an aged, leather writing desk covered with handwritten letters, fountain pens, and sealed wax stamps, creating an old-world library and epistolary vibe. Scattered, elegant calligraphic quotes in script font and stylized pressed botanical illustrations (ferns, roses) add to the romantic, vintage literary aesthetic. Surrounding the main subject are ~4 ornate oval or rectangular baroque frames in tarnished silver or bronze, showcasing different poses of the same person engaged in reading or writing. Overall, the image should utilize soft, diffused natural daylight streaming from a window, deep, moody tones (sepia, dark academia palette), high-definition textural details (paper, fabric, leather), a layered photographic and manuscript aesthetic, and a European vintage magazine style. Aspect ratio: 9:16. 第二版 Recreate the character's appearance from the uploaded photo, accurately preserving hairstyle, facial details, and expression. Present it as a hazy, ephemeral, and surreal fashion portrait in a vertical collage format. She wears oversized, comfortable lo-fi streetwear (e.g., vintage band tee or muted sweatshirt), holding a tethered helium balloon or a small, outdated CRT television displaying static near her body. Her face is covered with subtle, shimmering glitter or blurred, iridescent paint swipes, creating a hypnotic, dreamlike atmosphere. Her eyes are half-closed and distant, makeup is minimalist and slightly smudged, and her face shows a trance-like, ambiguous expression. The background features a faded bedroom wall or a vast, empty pastel-colored space (liminal space aesthetic), overlaid with soft, grainy textures like VHS static and dust motes. Repetitive, abstract shapes (floating eyes, disembodied hands) and minimalist, pixelated text fragments (e.g., "FEEL" or "LOOP") add to the unsettling, hazy, dreamcore aesthetic. Surrounding the main subject are ~4 distressed, square frames or Polaroid borders showcasing the same person interacting with surreal objects (e.g., an unnaturally large key, a door in the middle of a field). Overall, the image should utilize soft, slightly blown-out lighting (overexposed analog feel), a muted pastel and vaporwave color palette (faded pinks, blues, and yellows), visible analog noise and compression artifacts, a layered, hazy, lo-fi aesthetic, and a digital dream journal style. Aspect ratio: 9:16.

Nano Banana Pro其他

一句话表情生成指南

一句话生成各种表情，这提示词也是简洁高效了 Make a character design expression style guide of image

Nano Banana Pro美食饮品

《海贼王》动漫主题手办包装盒风格半身/全身照片

衍生版本：《海贼王》（One Piece）动漫主题手办 工具：Sora 或者 GPT-4o 注意： 1. 上传一张半身或者全身照片 2. 多试几次 把照片中的人物变成《海贼王》（One Piece）动漫主题手办包装盒的风格，以等距视角（isometric）呈现。包装盒内展示的是基于照片人物的《海贼王》动漫画风设计的形象，旁边搭配有日常必备物品（苹果笔记本电脑，手机，眼镜，帽子，咖啡）同时，在包装盒旁边还应呈现该手办本体的实物效果，采用逼真的、具有真实感的渲染风格。

Nano Banana Pro其他

One Piece風デビルフード能力者変身

GM! One Pieceの悪魔の実の名前を入れると、その実の能力者になれるnanobananaのPromptです。 <<DEVIL FRUIT NAME>>に悪魔の実の名前を入れて下さい。実の名前は日本語でも英語でも大丈夫でした😃 Promptはコメントに記載します。 #nanobanana2 最初の<<DEVIL FRUIT NAME>>に悪魔の実の名前を入れて下さい😃 { "version": "1.0", "description": "Transform a real person in a photo into a One Piece-style Devil Fruit ability user: dynamic pose, dramatic camera angle, ability-specific SFX, and a photorealistic manifestation of the specified Devil Fruit’s power.", "variables": { "DEVIL_FRUIT_NAME": { "type": "string", "value": "<<DEVIL FRUIT NAME>>", "description": "The canonical Devil Fruit name whose ability should be interpreted and applied to the subject (e.g., Gum-Gum Fruit, Flame-Flame Fruit, Ice-Ice Fruit, Sand-Sand Fruit, Rumble-Rumble Fruit, Flower-Flower Fruit, Dark-Dark Fruit, Paw-Paw Fruit, etc.)." } }, "steps": [ { "name": "DEVIL_FRUIT_ABILITY_EDIT", "goal": "Apply a dynamic One Piece-style pose, dramatic camera angle, ability-specific manga SFX, and a photorealistic manifestation of the specified Devil Fruit’s ability.", "instructions": "Use the uploaded photo as the base.\n\nKeep the person photorealistic (eyes, face, skin texture, hair, makeup). Do NOT convert the scene into manga. Do NOT replace the background.\n\n=====================================\nDEVIL FRUIT ABILITY TRANSFORMATION\n=====================================\nInsert your Devil Fruit name here: [DEVIL_FRUIT_NAME]\n\nInterpret the canon ability of [DEVIL_FRUIT_NAME] realistically and apply it to the body or surrounding environment. The effect must look like a live-action One Piece movie.\n\nExamples:\n- Gum-Gum Fruit: stretched limbs, elastic skin, tension folds, rubber reflection\n- Flame-Flame Fruit: realistic flames, heat distortion, warm illumination\n- Ice-Ice Fruit: frost buildup, ice crystals, cold vapor\n- Rumble-Rumble Fruit: lightning arcs, photoreal sparks\n- Sand-Sand Fruit: sand disintegration, sandstorm motion\n- Flower-Flower Fruit: photoreal arms blooming from surfaces\n- Paw-Paw Fruit: shockwave compression ripples\n- Dark-Dark Fruit: gravitational distortion, dark smoke tendrils\n\nRules:\n- The face must remain recognizable.\n- Effects must integrate into real lighting and shadows.\n- No cartoon filters — supernatural physics must look real.\n\n=====================================\nONE PIECE-STYLE POSE TRANSFORMATION\n=====================================\nRepose the body into a dramatic battle pose:\n- wide stance, strong dynamic gestures\n- stretched arm for Gum-Gum, open palm for shockwave, ignition stance for flame, elemental charge-up for logias, etc.\n- clothing should deform realistically\n\n=====================================\nEXTREME CAMERA ANGLES\n=====================================\nChoose one at random:\n- ultra low-angle\n- ultra high-angle\n- 20–24mm wide angle\n- 14mm super-wide distortion\n- fisheye\n- Dutch tilt\n- forced perspective (hand reaching toward lens)\n- telephoto compression (85–135mm)\n\n=====================================\nABILITY-SPECIFIC MANGA SFX (INK LINE ART)\n=====================================\nAutomatically choose the most appropriate SFX based on [DEVIL_FRUIT_NAME].\nUse ONLY One Piece-style onomatopoeia.\n\nWhen generating SFX, follow these rules:\n- pure black ink line art (no gradients)\n- placed behind or beside the character\n- must NOT cover the face\n\nUse the SFX set that matches the ability theme:\n\n=== SFX SELECTION LOGIC ===\nIf [DEVIL_FRUIT_NAME] contains:\n\n- \"Gum-Gum\" → Use: 「ドン!!!」, 「バキィ!!」, 「ゴムッ!!」, 「ブンッ!!」\n- \"Flame-Flame\" → Use: 「メラメラ…」, 「ボッ!!」, 「ゴォォ!!」, 「ドン!!!」\n- \"Ice-Ice\" → Use: 「ヒエェェ…」, 「パキパキ!!」, 「スッ…」\n- \"Rumble-Rumble\" → Use: 「ビリビリッ!!」, 「ズドン!!」, 「ゴロゴロ…」\n- \"Sand-Sand\" → Use: 「サラサラ…」, 「ザザザッ!!」, 「ドン!!」\n- \"Flower-Flower\" → Use: 「パッ!!」, 「ボンッ!!」\n- \"Dark-Dark\" → Use: 「ズズズ…」, 「ゴゴゴゴ…」, 「ドン…!!」\n- \"Paw-Paw\" → Use: 「バシュッ!!」, 「ドン!!」, 「ボフッ!!」\n- otherwise (unknown fruit) → Use: 「ドン!!!」, 「ゴゴゴゴ…」 (universal SFX)\n\n=====================================\nOPTIONAL MANGA LINES\n=====================================\nAdd subtle speed lines, impact lines, or depth lines, but keep the real background visible.\n\n=====================================\nFINAL GOAL\n=====================================\nCreate a photorealistic action image where:\n- The person stays realistic\n- The camera angle is dramatic\n- The pose is dynamic\n- The Devil Fruit ability is manifested photorealistically\n- Ability-appropriate SFX appear as ink line art around them\n\nFinal result must look like \"A real photograph capturing a live-action One Piece Devil Fruit battle moment.\"\n" } ], "final_goal": "Produce a single photorealistic One Piece-style image where the person in the uploaded photo is dynamically posed and visually affected by the real-world manifestation of the chosen Devil Fruit [DEVIL_FRUIT_NAME], with ability-specific SFX." }

Nano Banana Pro人像

一键生成你的完美肌肤✨ - 使用Nano Banana Pro或Seedream 4.5

You are a professional skin analyst and skincare expert. The user uploads a close-up photo of their face and may add short notes (age, allergies, current routine, pregnancy, etc.). Use ONLY what you see in the image plus the user text. 1. Carefully inspect the skin: shine, pores, redness, blemishes, spots, texture, flaking, fine lines, dark circles, etc. 2. Decide the main skin type: oily, dry, normal, combination, or sensitive. 3. Identify visible issues: acne/breakouts, blackheads/whiteheads, post-acne marks, hyperpigmentation, redness, enlarged pores, uneven texture, dehydration, fine lines, dark circles, puffiness, etc. RESPONSE FORMAT (very important) Your answer must be plain text in this exact structure: 1. First, write 3–6 short lines describing the skin and problems, for example: • overall skin type and how you know • where the main issues appear (forehead, cheeks, nose, chin, jawline, under-eyes) • how severe they look (mild / moderate / severe). 2. On a new line, write the word in caps: SKIN ROUTINE 3. Under SKIN ROUTINE, give at least 5 numbered steps (1., 2., 3., …). Each step must include: • what to do (e.g. “Cleanser”, “Treatment serum”, “Moisturizer”, “Sunscreen”, “Night treatment”), • product TYPE and key INGREDIENTS to look for (no brand names), • when to use it (AM, PM, or both) and how often, • 1 short practical instruction (how to apply, how much, any caution). Focus on over-the-counter products only (no prescription or medical diagnosis). If acne or irritation looks very severe or infected, clearly but kindly suggest visiting a dermatologist. Keep the tone supportive, simple and clear.

Nano Banana Pro时尚

出门必带的唯一物品

A high-resolution studio fashion photograph taken with a Canon EOS R5 and an RF 85mm f/1.2L USM lens captures the woman from the image wearing a shimmering metallic red sequined three-piece suit. The outfit consists of an oversized blazer, a knotted bandeau bra top,which reveals her midriff and navel and loose-fitting trousers with her hands in the pockets. Her long, wavy black hair falls over her shoulders, and she wears a delicate double-layered silver necklace.

Nano Banana Pro其他

One-Eyed Whippet on a Moped

A whippet with an eye patch riding a moped through a UK street filled with shops with boarded up windows.

Nano Banana Pro时尚

开放式Gemini纳米香蕉/Groks

1. Open Gemini nano banana / Grok 2. Upload your image 3. Prompt { "reference": "use uploaded image as facial reference, preserve original face and identity exactly", "character_type": "caricature-style keychain, gender-neutral", "pose": "riding a yellow scooter indoors", "head_style": "oversized head with joyful, playful smile", "outfit_beanie": "yellow knit beanie", "outfit_top": "striped yellow-black sweater", "outfit_bottom": "denim shorts", "socks": "white socks", "footwear": "white sneakers", "keychain_detail": "blue strap labeled \'SAMMU\'", "lighting": "soft indoor lighting", "depth_of_field": "shallow depth of field", "background": "mall-like indoor environment", "style": "whimsical, toy-like, premium collectible", "photography": "cinematic product photography", "texture": "smooth plastic, high detail finish" }

Nano Banana Pro静物

OpenAI Wax Seal Glow

[Deep Emerald Green] glossy wax seal icon depicting [OpenAI] logo, lying flat on a plain white background. The seal is made of thick, deformed plastic or wax with an irregular, squashed shape and a prominent 'drip' or smear extending to the right side. The center features a clear, raised relief impression of the subject. The lighting is soft and even, creating smooth specular highlights on the curved, glossy edges. The shadow cast is soft and minimal.

Nano Banana Pro海报设计

OpenAI 年终总结分享图

任务目标： 基于用户同时上传的年终总结截图中的数据和信息，设计一张风格鲜明、极具视觉冲击力的 3D 年终总结海报，用户名 [guizang] 整体风格与情绪（固定风格）： 核心风格： 融合 3D 趋势、游戏化元素和高饱和度色彩。 材质感： 画面主体呈现精致的黏土（Clay）或软塑胶材质渲染，边缘圆润，光影柔和，给人一种“盲盒玩具”的亲切感。 排版感： 整体布局要像一份精致的高级杂志，疏密有致，信息架构清晰。文字排版简洁明了，不要添加任何卡片、胶囊或底框类的装饰背景。 画面主体（核心视觉）： 视觉中心是一颗巨大的、紧密堆叠的 Q 版 3D 黏土球体。球体的组成元素需要根据用户上传截图中的具体内容来动态生成： 数据气泡： 将截图中提取的关键数字和对应的标签（例如：消息总数、聊天次数、生成图片数、活跃度排名等）制作成圆润的黏土数据气泡嵌入球体。 主题图标： 根据截图体现的用户兴趣点，添加相应的通用黏土图标（例如：游戏手柄、大脑、图表、对话气泡等）。 类别建筑（核心要求）： 分析截图中的内容侧重点，在球体中融入几座代表不同聊天品类的精致微缩黏土建筑。例如： 如果包含 AI/技术内容，加入一座带有科技感的未来数据中心建筑。 如果包含游戏内容，加入一座像素风格的游戏城堡。 如果包含创意/艺术内容，加入一个微型艺术工作室。 组合方式： 所有这些元素（气泡、图标、建筑）必须非常紧密、融洽地挤在一起，无缝组成一个完美的球形，不露出内部结构。 背景设计（固定框架）： 底色： 采用高饱和度的暖橙色到柔和紫色的渐变背景（参考之前的风格）。 背景文字： 在星球背后，放置六个巨大的、带有喷溅纹理和反向蚀刻效果的汉字，主题可以是“冒险 创新 探索”（上排）和“创造 硬核 冲击”（下排），部分被球体遮挡，增加街头硬核感。 信息架构与排版（内容从截图中提取）： 顶部 (Header)： 放置白色的 ChatGPT Logo，并根据截图信息生成标题，格式为：“[从截图中提取的用户名] 的 [年份] 年终总结”。 底部数据区 (Data Grid)： 在球体下方，创建一个极简的 2x2 纯文字数据网格。从截图中选取 4 个最核心的数据，使用超粗无衬线字体展示大数字，并配上相应的文字标签和有趣的社交属性短语（例如：“社交牛逼症”、“话痨”、“六边形战士”等，依据数据特性生成）。 页脚总结 (Footer)： 在最底部用小字排版两段文字，内容直接从用户截图中的总结段落（如“你的聊天风格”和“年度亮点”）提取。

Nano Banana Pro其他

优化的人物与故事性提示词

看来大家还蛮喜欢这个提示词的，我重新优化了一下人物和故事性。让画面更加具有故事感。 新提示词👇 prompt #NanoBananaPro { "input_song": "[歌曲名称]", "ai_system_instruction": { "role": "Synesthetic 3D Architect & Visual Director", "task": "Analyze the INPUT_SONG\'s lyrics/mood. Construct a complex, multi-layered, hyper-rich 3D floating structure that embodies the song. FILL IN the brackets [...] below." }, "visual_prompt_template": { "description": "A hyper-realistic, dreamlike 3D concept art visualization of the song [INPUT_SONG].", "sections": { "1_container": { "title": "The Container (The Multi-Dimensional Floating Complex)", "description": "The scene features a complex, multi-layered floating structure, NOT a single flat island. It consists of 2-3 interconnected tiers or varied elevations (e.g., linked by bridges, roots, or gravity-defying elements). Volumetric Richness: The structure is incredibly rich and deep. Elements are NOT just on top; they grow from the vertical cliff sides, hang from the rugged underside, and orbit around the main body. Environment: The complex is surrounded by soft, billowing white clouds, but the structure pushes through them, revealing its intricate multi-level details." }, "2_narrative_ecosystem": { "title": "The Narrative Ecosystem (AI-Inferred & Integrated Across All Dimensions)", "description": "Based on the song\'s analysis, populate the entire complex with key props and narrative characters.", "main_terrains": "The different levels are transformed into [AI: Insert varied terrain types based on song, e.g., \'upper level ruined church, lower level dark forest\'].", "integrated_props_and_characters": { "on_top_surface": "[AI: Insert Prop 1] and [AI: Insert Character 1 & Action, e.g., \'a lonely figure gazing at the moon\'].", "emerging_from_sides_cliffs": "[AI: Insert Prop 2, e.g., \'a giant clock face embedded in rock\'] and [AI: Insert Character 2 & Action].", "hanging_from_bottom_orbiting": "[AI: Insert Prop 3, e.g., upside-down buildings or floating instruments].", "living_details_and_flow": "[AI: Insert dynamic elements like waterfalls between layers, glowing particles, or flocks of birds]." } }, "3_atmosphere_and_mood": { "description": "The scene radiates a complex [AI: Insert Emotion] atmosphere. The lighting is [AI: Insert Lighting Style], casting [AI: Insert Color] tones, creating deep shadows and highlights in the complex geometry." }, "4_text_overlay": { "song_title": "3D floating text \'[INPUT_SONG]\' integrated into the architecture.", "classic_lyric": "A glowing subtitle: \'[AI: Insert 1 famous lyric line]\'." } }, "style_and_tech": "Tilt-shift photography effect (emphasizing the intricate, miniature model feel), Octane Render, 8k resolution, extreme detail, volumetric fog, masterpiece. --ar 1:1 --stylize 850" } }

Nano Banana Pro其他

提示词优化，图片生成效果提升

哈哈，这个提示词玩上瘾了，我进一步优化了提示词，可以直接参考图片生成，效果进阶！@sundyme Haha, I'm hooked on this prompt. I've further optimized it so that it can directly generate content by referring to pictures, and the effect has improved!

Nano Banana Pro插画与 3D

橙iPhone 17 Pro拆解渲染挑战

STEAL THIS PROMPT VOL 2: "What\'s inside SPLIT" The rules are simple: You can STEAL this prompt but only if you write you created it. Do NOT credit me. Say you did it, and then use it as much as you like. Create a high-quality, realistic 3D render of exactly one instance of the object: [Orange iPhone 17 Pro]. The object must float freely in mid-air and be gently tilted and rotated in 3D space (not front-facing). Use a soft, minimalist dark background in a clean 1080×1080 composition. Left Half — Full Realism The left half of the object should appear exactly as it looks in real life — accurate materials, colors, textures, reflections, and proportions. This half must be completely opaque with no transparency and no wireframe overlay. No soft transition, no fading, no blending. Right Half — Hard Cut Wireframe Interior The right half must switch cleanly to a wireframe interior diagram. The boundary between the two halves must be a perfectly vertical, perfectly sharp, crisp cut line, stretching straight from the top edge to the bottom edge of the object. No diagonal edges, no curved slicing, no gradient. The wireframe must use only two line colors: Primary: white (≈80% of all lines) Secondary: a color sampled from the dominant color of the realistic half (<20% of lines) The wireframe lines must be thin, precise, aligned, and engineering-style. Every wireframe component must perfectly match the geometry of the object. Strict Single-Object Rule Render only ONE object in the entire frame. Render only one physical object. Do NOT show a second object from any angle. Do NOT show a second object as a reflection, shadow, silhouette, outline, ghost image, or transparency. Do NOT show a second object for comparison or display purposes. Do NOT show both the front and the back separately. Do NOT show an extra device behind, beside, underneath, or partially hidden. Only one single object is allowed in the entire frame. No duplicate objects, no mirrored back-and-front pairings, no reflections showing a second object. The object must appear alone, floating. Pose & Lighting: Apply a natural, subtle tilt + rotation in 3D to make it look like a floating product visualization. Use soft, neutral global illumination and no shadows under the object. No extra props, no text, no labels unless explicitly requested. And of course SHOW ME what you generated. Just make sure to say it's your prompt now!

Nano Banana Pro其他

Orchestra Playing 'Baby Got Back' in Vienna

a conductor's point of view of an orchestra during a Christmas concert in Vienna, with the score for an orchestral arrangement of "Baby Got Back" on the music stand. Photorealistic. RF 20mm f/1.4 L VCM lens at 4.0, Canon R5 with Aperture priority +1 ev.

Nano Banana Pro摄影

非凡节日中的普通物体

Ordinary Object, Extraordinary Festival A band of tiny [CHARACTERS] throwing a colorful festival on the rim of an enormous [EVERYDAY_OBJECT]. Paper lanterns strung on wire, confetti made from magazine scraps, warm ambient city-bokeh background, shallow depth of field, cinematic wide-angle close-up, vibrant saturated palette, tactile fabric and wood textures.

Nano Banana Pro人像

Origami Movie Poster Transform

Transform this movie poster into an origami version, as if the entire artwork is folded from high-quality paper. Preserve the key elements of the poster so it remains instantly recognizable, but simplify shapes into crisp folds, geometric paper edges, and realistic paper textures. Add soft studio lighting and subtle paper shadows for a clean collectible art look.

Nano Banana Pro其他

金字塔与狮身人面像的原始风貌

> a photo of the pyramids and sphinx, but how they looked when they were originally built, the sphinx's face is perfect

Nano Banana Pro美食饮品

原创宝可梦，来自Chat Gpt 4o的创意！

Create your original Pokemon with Chat Gpt 4o !! ⭐️ It's so fun !! I can't wait to see all your creations from photos of objects, foods, drinks ...ect from your home!! Prompt in thread 👇

Nano Banana ProUI 与平面

奥司他韦胶囊科普信息图

现在的药品的说明书你们真的会看吗？ 如果长这样，我肯定会认认真真的看完！ 🍌Nano Banana Pro Prompt: { "image_analysis": { "subject": "[药物名称] 科普信息图，9:16", "style": "模块化Bento Grid设计 (便当盒网格布局) / 极简医疗UI设计", "tone": "专业、临床、严谨、科学、值得信赖", "primary_colors": [ "临床白 (Clinical White)", "医疗蓝 (Medical Blue)", "石板灰 (Slate Grey)", "薄荷绿 (Mint Green)" ] }, "prompt_elements": { "subject_description": "一张关于 [药物名称] 的高质量科普信息海报。", "layout": "便当盒风格的模块化网格布局，干净的医疗UI/UX界面设计，分为清晰的矩形卡片。", "visual_details": [ "顶部页眉带有醒目的无衬线现代字体标题“药物中文名称”及其化学/通用名", "顶部中央是 [药物剂型/包装] 的超写实微距摄影图片（如药片、胶囊或药瓶）", "角落里有一幅 [化学结构式] 的极简线条图", "第1部分：带有环形图和柱状图的有效成分与药理作用分析，数据可视化", "第2部分：带有极简线条图标的适用症", "第3部分：带有极简线条图标（[口服/注射]、[频次]、[剂量]的用法用量矩阵", "第4部分：带有线性图表的药代动力学或起效时间轴", "第5部分：带有简单警示图标（[药物相互作用]、[禁忌]、[副作用]）的注意事项网格，药物相互作用，禁忌，副作用你需要联网搜索", "第6部分：适用人群画像图标（如老人、儿童、孕妇的适用性标记）", "第7部分：带有温度计和湿度图标的药品储存指南" ], "art_style": "极简科学可视化设计，精细的医疗插图与产品摄影相结合，扁平化医疗图标，瑞士风格排版。", "lighting": "明亮的实验室无影灯光，干净透彻，强调无菌感与清晰度。", "color_palette": "单色临床白或浅灰背景，半透明磨砂玻璃卡片，深灰色和海军蓝文字，点缀医疗蓝或青色以突出重点。" }, "negative_prompt": "杂乱，暖色调，复古风，手写体，低分辨率，模糊，文字扭曲，甚至噪点，深色背景，不卫生，过饱和，水印，食物质感" } 药物名称： 奥司他韦胶囊

Nano Banana Pro其他

Ottoman Miniature Painting Request

#ottoman #miniaturepainting #NanoBananaPro #ChatGPTImage #yerli #milli Minyatür tarzı (User request doldurulacak) You are an expert in Ottoman miniature painting (Nakkaşhane) style. The user will enter only a single-line request. Without asking any follow-up questions, you will complete all missing creative and technical decisions internally and transform that request into a single visual scene in authentic Ottoman miniature aesthetics. Input (user request): {USER_REQUEST} Internal process (do not show to the user, just apply): 1.Analyze the request and automatically determine: the main event, main characters/figures, setting/location, time period, and cultural context. If the user does not specify a time, choose the most iconic and recognizable period that best fits the subject. 2.Period accuracy is mandatory: •Clothing, hair, accessories, stage/environment objects, vehicles, signage, architecture, and crowd behavior must be consistent with the chosen era. •For concert/event scenes: stage layout, instruments, lighting system, speaker stacks, poster aesthetic (without text), crowd clothing style, and safety barriers must match the era. •Example rule: If the user says “Metallica,” construct a concert scene; depict era-appropriate metal concert clothing (black T-shirts, leather jackets, denim, band-merch vibe), crowd dynamics (headbanging, hands raised), and correct-looking stage gear and instruments, but rendered in miniature language (stylized, not photorealistic).

Nano Banana Pro其他

户外阳台场景中的金毛比熊

ChatGPT Prompt: { "type": "image_prompt", "format": "photorealistic", "aspect_ratio": "1536:1358", "scene": { "setting": "outdoor balcony/terrace with a glass railing", "time_of_day": "daytime", "weather": "clear", "foreground_surface": "large rectangular lounge cushion with a light beige/cream top, gray side panels, and visible piping seams" }, "subject": { "primary_subject": "small long-haired chihuahua", "pose": "lying down on the cushion with front paws forward, relaxed body, head slightly raised", "expression": "calm, slightly squinting in bright sun", "fur": { "color": "warm golden-brown/tan with lighter cream highlights", "texture": "fluffy long coat with wispy strands around ears and neck", "markings": "slightly grayer muzzle and chin; lighter fur on paws/toes" }, "features": { "ears": "large upright ears with feathery fur", "eyes": "dark brown, glossy", "nose": "small black nose" } }, "background": { "midground": "calm blue water (bay/harbor) with a tree-lined shoreline/island", "distant_elements": [ "multiple large white cruise ships", "port cranes/industrial structures on the left", "hazy city skyline with high-rise buildings on the right" ], "structure": "a white vertical balcony pillar centered behind the dog", "depth_of_field": "background noticeably blurred/soft compared to the dog" }, "lighting": { "type": "strong natural sunlight", "direction": "from the left/front-left", "effects": [ "bright highlights on the dog’s fur", "soft shadows and a diagonal shadow across the cushion" ] }, "composition": { "framing": "medium close-up with the dog occupying the right half of the frame", "focus": "sharp focus on the dog; background out of focus", "camera_angle": "eye-level/slightly above the dog", "mood": "warm, tranquil, sunbathing" }, "color_palette": [ "golden tan", "cream/beige", "cool blue", "soft gray", "white" ], "prompt": "A photorealistic daytime balcony scene: a small long-haired chihuahua with warm golden-brown/tan fur and lighter cream highlights lies relaxed on a large rectangular lounge cushion (light beige/cream top with gray sides and piped seams). The dog faces slightly left, head raised, calm expression with slightly squinting dark eyes, upright feathery ears, small black nose, and a subtly grayer muzzle; front paws forward with lighter fur on the toes. Strong natural sunlight from the left creates bright highlights on the fur and soft shadows across the cushion. Behind the dog is a glass balcony railing, a white vertical pillar centered in the background, and a soft, defocused view of a blue bay/harbor with a tree-lined shoreline, several large white cruise ships, port cranes in the distance, and a hazy city skyline of high-rise buildings on the right. Shallow depth of field, crisp focus on the dog, background softly blurred, warm serene mood.", "negative_prompt": [ "cartoon", "illustration", "painting", "heavy grain", "nighttime", "rain", "people", "multiple dogs", "leash", "text", "watermarks", "oversaturated colors", "distorted anatomy" ] }

Nano Banana Pro其他

户外阳台上的小长毛吉娃娃

Met AI Prompt • used GPT prompt { "type": "image_prompt", "format": "photorealistic", "aspect_ratio": "1536:1358", "scene": { "setting": "outdoor balcony/terrace with a glass railing", "time_of_day": "daytime", "weather": "clear", "foreground_surface": "large rectangular lounge cushion with a light beige/cream top, gray side panels, and visible piping seams" }, "subject": { "primary_subject": "small long-haired chihuahua", "pose": "lying down on the cushion with front paws forward, relaxed body, head slightly raised", "expression": "calm, slightly squinting in bright sun", "fur": { "color": "warm golden-brown/tan with lighter cream highlights", "texture": "fluffy long coat with wispy strands around ears and neck", "markings": "slightly grayer muzzle and chin; lighter fur on paws/toes" }, "features": { "ears": "large upright ears with feathery fur", "eyes": "dark brown, glossy", "nose": "small black nose" } }, "background": { "midground": "calm blue water (bay/harbor) with a tree-lined shoreline/island", "distant_elements": [ "multiple large white cruise ships", "port cranes/industrial structures on the left", "hazy city skyline with high-rise buildings on the right" ], "structure": "a white vertical balcony pillar centered behind the dog", "depth_of_field": "background noticeably blurred/soft compared to the dog" }, "lighting": { "type": "strong natural sunlight", "direction": "from the left/front-left", "effects": [ "bright highlights on the dog’s fur", "soft shadows and a diagonal shadow across the cushion" ] }, "composition": { "framing": "medium close-up with the dog occupying the right half of the frame", "focus": "sharp focus on the dog; background out of focus", "camera_angle": "eye-level/slightly above the dog", "mood": "warm, tranquil, sunbathing" }, "color_palette": [ "golden tan", "cream/beige", "cool blue", "soft gray", "white" ], "prompt": "A photorealistic daytime balcony scene: a small long-haired chihuahua with warm golden-brown/tan fur and lighter cream highlights lies relaxed on a large rectangular lounge cushion (light beige/cream top with gray sides and piped seams). The dog faces slightly left, head raised, calm expression with slightly squinting dark eyes, upright feathery ears, small black nose, and a subtly grayer muzzle; front paws forward with lighter fur on the toes. Strong natural sunlight from the left creates bright highlights on the fur and soft shadows across the cushion. Behind the dog is a glass balcony railing, a white vertical pillar centered in the background, and a soft, defocused view of a blue bay/harbor with a tree-lined shoreline, several large white cruise ships, port cranes in the distance, and a hazy city skyline of high-rise buildings on the right. Shallow depth of field, crisp focus on the dog, background softly blurred, warm serene mood.", "negative_prompt": [ "cartoon", "illustration", "painting", "heavy grain", "nighttime", "rain", "people", "multiple dogs", "leash", "text", "watermarks", "oversaturated colors", "distorted anatomy" ] }

Nano Banana Pro人像

户外休闲人像

Nano banana Pro on Gemini app. { "type": "image_generation_prompt", "style": "casual, stylish, outdoor portrait, photorealistic", "identity_preservation": { "use_reference_image": true, "alter_face": false, "notes": "Preserve the woman’s face, hairstyle, skin tone, and body proportions exactly as shown in the reference image. Do not change facial features." }, "subject": { "gender": "female", "pose": { "stance": "standing and leaning casually against a tree trunk", "body_orientation": "slightly turned to the side", "gaze": "looking to the side through sunglasses", "expression": "confident and relaxed", "hand_position": "one hand resting naturally on her thigh" }, "wardrobe": { "top": "Brazilian national soccer team jersey", "bottoms": "black pants", "accessories": [ "dark sunglasses", "wristwatch with dark band", "simple metal bracelet" ] } }, "environment": { "location": "outdoor park or green area", "ground": [ "grass", "paved walking path" ], "background": { "style": "softly blurred (bokeh)", "lighting": "bright natural sunlight" } }, "lighting": { "type": "natural daylight", "quality": "bright and direct", "effects": [ "defined highlights", "natural shadows enhancing body shape" ] }, "camera": { "camera_type": "full-frame", "lens": "85mm f/1.8 or 50mm f/1.4", "aperture": "f/2.8 – f/4.0", "iso": 100, "shutter_speed": "1/500s – 1/1000s", "depth_of_field": "creamy bokeh with subject isolation", "framing": "medium-length portrait" }, "mood": { "atmosphere": "relaxed, confident, sunny", "style": "modern lifestyle photography" }, "quality": { "realism": "highly photorealistic", "detail_level": "sharp subject with natural textures" }, "output_goal": "Create a realistic outdoor lifestyle portrait of a woman in a park, leaning against a tree while wearing a Brazilian national soccer team jersey, preserving her exact identity and delivering a confident, casual, and sunlit aesthetic." }

Nano Banana Pro人像

户外野餐的女性肖像

Looking nice!!! Try this Nano Banana Pro 🍌 prompt Like It Follow @AITechGirl for more 😍 ❤️❤️❤️ { "image_prompt": { "subject": { "description": "young woman sitting outdoors on a picnic blanket in a sunny open field", "face_preservation": true, "pose": { "body_position": "sitting cross-legged on a quilted blanket", "hands": "holding a small bouquet of white baby\'s breath flowers", "expression": "soft, relaxed smile", "posture": "upright, facing forward" }, "appearance": { "hair": { "color": "dark-brown", "style": "long, slightly wavy, parted with natural flow" }, "clothing": { "dress": { "type": "sleeveless sundress", "color": "light yellow", "details": "tie detail at chest, soft flowing fabric" } }, "accessories": { "jewelry": [ "delicate necklace", "bracelet", "rings" ] } } }, "environment": { "setting": "large grassy park under a bright blue sky", "details": { "elements": [ "scattered clouds", "pond with small fountain", "houses and trees in distance", "early spring foliage" ], "ground": "colorful patchwork quilt on green grass", "lighting": "bright natural sunlight creating soft shadows" } }, "photography": { "style": "natural outdoor portrait", "framing": "centered portrait with full upper body visible", "camera_angle": "eye-level perspective", "quality": "high resolution, crisp daylight image", "color_tone": "warm, vibrant, natural colors" }, "composition": { "focus": "subject centered on blanket holding flowers", "background_depth": "wide landscape with sky and clouds providing depth", "negative_prompt": [ "altered face", "incorrect lighting", "extra people", "text or watermark", "distorted proportions" ] } } } /// #NanobananaAI #nanobanana3 #nanobanana

Nano Banana Pro美食饮品

街头咖啡馆户外自拍

Thought of calm looks here 😌 { "scene_description": "A candid outdoor selfie of a beautiful woman sitting at a cafe table on the pavement.", "environment": { "setting": "European-style street cafe", "time_of_day": "Late afternoon with soft natural light", "background": "Shallow depth of field showing blurred pedestrians, bicycles, and warm storefront tones" }, "subject": { "gender": "female", "hair": { "style": "curly", "color": "black", "length": "shoulder-length" }, "face_details": { "freckles": "light and natural across the nose and cheeks", "makeup": { "mascara_color": "light blue", "style": "subtle but noticeable" } }, "accessories": [ { "type": "bracelet", "material": "silver", "location": "left arm" } ] }, "props": { "table_items": [ { "item": "system camera", "position": "on the cafe table in front of her", "style": "modern mirrorless design" } ] }, "camera": { "shot_type": "selfie", "angle": "slightly elevated, tilted for aesthetic composition", "focus": "sharp on face, creamy bokeh depth of field behind", "resolution": "8K" }, "style": { "vibe": "cinematic candid street photography", "lighting": "soft natural daylight", "color_palette": "earth tones with complementary light blue accent", "mood": "calm, confident, relaxed" } }

Nano Banana Pro时尚

户外街拍可爱少女

可爱萌萌萌萌炸了😆我稍微修改了一下提示词，可以让AI参考上传的图片生成 户外街拍照片，一位开朗的年轻女生站在人行道上，在明亮日光下对着镜头自拍，整体氛围元气、俏皮、真实、略带一点可爱少女感。 如果用户上传了参考照片，请务必以参考图为基础进行生成： 保持人物的面部完全不变——脸型、五官结构、五官比例、肤色特征和发际线都要与参考图高度一致，只做轻微美化，不能改变长相； 保持人物的服装不变——上衣、裤子、腰带、包包、配饰等的款式和大体配色都要与参考图一致，只优化质感和光影。 整体的妆容风格、动作气质和人物风格也以参考图为主，不做大幅度改变，只在细节上微调，让画面更精致、更有街拍感。 画面内容参考如下进行补充和优化： 女孩在街边人行道上，左眼眨眼，用左手比出 “V 字手势 / peace 手势”；右手举着一部智能手机对着镜头，好像正在和镜头外的人互动。手机屏幕上显示她的自拍照，自拍里多了一枚粉色小花贴纸点缀在头发附近，增加可爱感。 她戴一顶棕色渔夫帽，帽子上点缀几枚蓝色徽章；上身穿白色拉链短款上衣（露出一点腰线），下身是浅蓝色宽松牛仔裤，搭配棕色皮质腰带。左手腕上佩戴一条粗大的银色链条手链。她背着或挎着一只红白条纹托特包，包上挂着蓝色小鲨鱼钥匙扣；裤子或腰带环上挂着一个小红色 Snoopy 零钱包作为装饰。配饰和服装的具体造型、图案和颜色如与参考图冲突时，以参考图为准，只在不违和的前提下补充这些元素。 妆面和皮肤质感要求：在不改变参考图整体妆容风格的前提下微调和强化细节。 睫毛可以稍微强调为根根分明、略带簇状的卷翘长睫毛；在双颊和鼻尖处增加柔和的蜜桃粉色腮红，让脸颊和鼻尖有一点轻微晒红的可爱感；嘴唇饱满水润，呈现渐变粉色唇妆，带有微微湿润光泽的 “水光唇” 效果。整体底妆偏水光、通透，皮肤在自然日光和闪光灯下略微反光，看起来干净、有光泽，但不要过度磨皮，保留一定真实肌理。 氛围与特效：在她的手机周围以及头部附近，添加一些小而精致的彩色星星、闪光贴纸、涂鸦感的数字贴纸，让画面充满社交媒体滤镜感、年轻感和可爱感，但不要抢走人物的视觉中心。 背景是白天街景：可以看到一面店铺橱窗和混凝土墙面，光线明亮，给人阳光、真实的都市生活感。整体风格为写实、摄影级质感的街拍照片。使用直接闪光灯拍摄的效果，闪光打在人物面部和上半身上，呈现略微强烈、生硬的高光和阴影，对比感较高，带有真实相机直出照片的味道，而不是柔光棚拍。 画面整体要求： 写实、逼真、photorealistic，构图干净，人物为画面主体； 在保证参考图人物五官和服装完全不变的前提下，叠加以上街拍场景、妆容细节和可爱贴纸效果； 禁止把人物脸改成 “网红模板脸”，禁止更换发色、发型轮廓或服装款式，只允许做细节优化和环境补充。

Nano Banana Pro美食饮品

户外街景人像

Grok Imagine Base Image @KusoPhoto High quality photo of an outdoor street portrait taken during midday/afternoon under clear weather. A young kwaii japanese woman stands in front of a turquoise storefront with a visible 'COFFEE SHOP' sign in bold sans-serif font. She faces the camera, wearing a black baseball cap, white lace blouse with intricate floral patterns and ribbed cuffs, and a black pinafore dress with box pleats and gold buttons. She holds a bright red leather shoulder bag with a gold clasp, the bag's strap creating a leading line from her shoulder to the bag. The woman has pale skin, ash-blonde bob hair with straight bangs, neutral makeup, and subtle freckles visible on her cheeks, with soft catchlights in her eyes. The background includes parked cars, a doorway, plants, and a warm wall sconce. Lighting is natural sunlight with a slight top-down direction, soft diffused shadows, and neutral to slightly warm color temperature, possibly enhanced by a reflector. The color palette features dominant colors of black (#0A0A0A), off-white (#EDEBE6), and turquoise (#19B4C0), with red and turquoise accents and high contrast. The composition uses an eye-level camera angle, medium-shot framing from waist-up to knees, shallow depth of field with a softly blurred background, focusing on the woman’s face and the red bag strap.

Nano Banana Pro时尚

户外露台时尚生活摄影

{ "aspect_ratio": "9:16", "scene_type": "outdoor terrace fashion lifestyle photography", "camera": { "device": "smartphone or mirrorless", "angle": "slightly elevated rear three-quarter", "position": "behind and slightly above subject’s right side", "framing": "full body with terrace and sky", "orientation": "vertical", "focus": "sharp subject, clear background", "lens_effect": "natural perspective, mild wide-angle" }, "subject": { "gender": "female", "age": "adult", "skin_tone": "light to medium with daylight highlights", "hair": "medium brown, shoulder-length, straight with slight texture, center-parted, tucked behind ears", "face": { "shape": "oval", "expression": "playful, relaxed smile", "gaze": "looking directly at camera over shoulder", "eyes": "open and engaged", "features": "natural brows, straight nose, small decorative cheek mark" }, "posture": { "pose": "deep squat with heels down", "lower_body": "knees fully bent and angled outward, feet flat and slightly apart, balanced stance", "hips_silhouette": "hips lowered close to ground, neutral pelvis, natural curves emphasized by garment fit", "torso": "facing mostly away, upper torso twisted back toward camera, naturally curved spine", "shoulders": "relaxed, slightly rolled back", "arms": "one hand resting on thigh for balance, other near hip", "head_neck": "head turned back over shoulder with slight tilt, controlled and stable" }, "wardrobe": { "top": "red strappy crop top with lace-up back ties, snug fit", "bottom": "mustard yellow fitted shorts, stretch knit, body-contouring", "footwear": "white low-top sneakers", "accessories": "small hoop earrings, smartwatch or fitness band" } }, "environment": { "location": "outdoor terrace or rooftop patio", "ground": "light speckled stone or concrete", "background": { "furniture": "modern lounge chairs with cushions", "railing": "dark metal", "plants": "large potted tropical plants", "architecture": "modern residential elements" }, "sky": "light blue with soft scattered clouds" }, "lighting": { "type": "natural daylight", "time_of_day": "late morning or afternoon", "direction": "even frontal and side light", "highlights": "soft on hair, shoulders, fabric", "shadows": "gentle beneath body and furniture" }, "artistic_style": { "genre": "fashion and lifestyle photography", "aesthetic": "modern, casual, body-positive", "mood": "confident, playful, relaxed", "focus": "curves presented as fashion silhouette and garment fit", "palette": [ "yellow", "red", "neutral tones", "blue sky" ] }, "quality_tags": [ "photorealistic", "accurate posture", "locked gaze", "natural anatomy", "editorial casual fashion", "no text", "no watermark" ] }

Nano Banana Pro动物

《链锯人》东山小红户外日常

✨《链锯人》中的「东山小红」，可爱🥰 ✍️中文提示词： 一、整体氛围 1 场景设定：户外日常、住宅区小路、白色栅栏、绿植背景、晴朗日光 2 画面气质：清新、安静、略带呆萌、日系青春感、轻微二次元感 3 色彩基调：黑白主色、肤色偏白、点缀鲜红配饰、整体冷暖对比柔和 二、人物形象 1 年龄形象：脸型精致可爱、眼睛偏大、右眼下方点了一颗小痣，唇色淡粉、妆容干净偏日韩感，少女感、身材纤细、脸型偏幼态、皮肤细腻 2 发型表情姿态：cos的电锯人中的东山小红，正面站立、双手抬起做剪刀手 三、服饰风格 1 上装：黑色宽松外套、毛绒翻领、前拉链设计、下摆与袖口略蓬松 2 图案元素：外套上有鱼骨、十字、简笔画动物等涂鸦图案，带一点暗黑童趣感 3 内搭：浅色圆领上衣，露出少量领口形成明暗对比 4 配饰：红色颈圈式项圈、金属扣环、长款十字架耳饰、红色发夹成组佩戴 5 风格标签：街头可爱风、软萌与轻微叛逆混合、偏亚文化少女穿搭 四、构图与机位 1 构图方式：人物居中、半身取景、上半身和手势为视觉重点 2 机位视角：略微俯视、接近人眼高度、距离适中 3 空间关系：人物与背景栅栏有一定距离，背景略虚化以突出主体 五、光影与质感 1 光线来源：自然日光、从前方偏侧照射，脸部光线均匀 2 明暗关系：人物整体偏亮、背景略暗并有树荫块面，形成柔和对比 3 质感表现：毛绒领口质感清晰、外套呈现柔软绒面、金属饰品有细小高光 六、环境元素 1 背景建筑：金属大门、远处住宅墙面、局部车辆与石柱 2 周围细节：白色木栅栏、石板路、地面略有水迹与落叶 3 氛围关键词：安静居民区、轻松散步场景、略有冬日或早春气息

Nano Banana Pro其他

Outfit Swap with New Pants from Reference

Keep the character in [Image1] unchanged, but replace her pant with the outfit in [Image2]. Maintain the same pose, body proportions, and facial features, while applying the color, texture, and style of the pants in [Image2]. High-quality, realistic, consistent detail.

Nano Banana Pro海报设计

服装海报生成指南

很多人都问提示词，提示词评论区见： Disclaimer: AI-generated content for educational reference only. Not for commercial use. -------------------------- Using the uploaded photo as the sole character reference, generate a vertical outfit poster. 【LAYOUT HARD RULES】 - Must have exactly 6 cards only, 2 rows × 3 columns (3 columns across, 2 rows down) - Row 1: LOOK 1, 2, 3 | Row 2: LOOK 4, 5, 6 - Prohibited: 9-grid, 3 rows × 2 columns, 2-column layout, extra cards, top header/title 【CANVAS & LAYOUT】 - Vertical 4:5 aspect ratio, background #F7F5F2 - Grid occupies ≥92% of canvas height, bottom margin ≤3% - Outer margin 2%, spacing 1.5%, strictly aligned 【CARD SPECIFICATIONS】 - White background #FFFFFF, border-radius 5%, stroke 1px #E5E7EB - Top title bar: height 12%, background #F3F4F6, text color #111827 - Sans-serif font, alignment consistent throughout 【CHARACTER CONSISTENCY】 - All 6 must be the same person in different outfits: same face, same hairstyle, same body proportions, same demeanor - Prohibited: switching people/changing face/altering gender features/extreme slimming or leg lengthening 【PHOTOGRAPHY QUALITY】 - Master-level studio full-body lookbook, 85mm portrait lens look - Softbox key light + subtle fill, natural skin texture with light retouching - Solid seamless background (white/light gray/off-white), no clutter 【UNIFORM CROPPING】 - 4:5 full-body, complete from head to shoes - Subject centered, height 88%±2% - Headroom 2-4%, footroom 3-5%, shoes fully visible - All six shots: consistent camera height/focal length/lighting/pose 【OUTFIT RULES】 - Auto-adapt based on subject age (adult/child) - Each look ≤3 core items, max 3 colors per outfit, accessories ≤2 - 6 looks distinctly different, but unified style: minimal/clean/polished/easy to recreate 【TITLE SETS】 Adult: Business/Classic → Casual/Weekend → Smart Casual/Evening → Resort/Vacation → Athleisure/Active → Layered/Transitional Kids: Everyday/Clean → School/Polished → Weekend/Play → Party/Sweet → Active/Sporty → Layered/Cozy NEGATIVE: 3x3, nine-grid, 9 cards, extra cards, 3 rows x 2 columns, two-column layout, big top header, page title, switching people, changing face, multiple people, lowres, blurry, plastic skin, wide-angle distortion, fisheye, warped body, extreme slimming, long legs effect, outdoor background, textured wall, cut off shoes, half body, adultification, sexy, lingerie, see-through, high heels (kids), heavy makeup (kids), watermark, cropped text -------------------------- How to use it: Using uploaded photo, generate a 6-panel outfit poster: strict 2 rows × 3 columns, same person in different outfits, studio full-body shots, 85mm lens look, white cards with title bars, no top header, subject at 88% height from head to shoes, 6 distinct but minimal/polished looks.

Nano Banana Pro自然

植物覆盖物体

[OBJECT] overgrown with plants green tree, rain, lush, dramatic, cinematic lighting, green jungle, with plants, forest, realistic detailed, photorealism, beautiful, high quality, realistic, looks real Would love to see your creations inspired by this prompt and will repost my favorites

Nano Banana Pro海报设计

自己的国家地标时尚杂志

a luxurious fashion magazine cover designed in the style of [COUNTRY], blending iconic landmarks, cultural symbols, and local fashion aesthetics. The layout mimics high-end editorial design, with headlines inspired by the country’s language, trends, and lifestyle. Sophisticated, cinematic lighting, vertical 9:16 format, ultra-detailed, Vogue-level elegance 以 [COUNTRY] 风格设计的豪华时尚杂志封面，融合了标志性地标、文化符号和当地时尚美学。布局模仿高端编辑设计，标题的灵感来自该国的语言、趋势和生活方式。精致的电影级灯光，垂直 9：16 格式，超细节，Vogue 级别的优雅

Nano Banana Pro其他

PS5的技术蓝图

A two-panel technical blueprint diagram in clean monochrome line-art, matching the exact layout of the provided PlayStation 1 schematic. On the left side, draw a full, intact Sony PlayStation 5 console in precise thin line-art on a white background. On the right side, draw a highly detailed, vertically exploded-view diagram of the PS5 showing each internal component separated into layers: outer shell panels, faceplates, cooling fan, heatsink tower, Blu-ray drive, motherboard, SSD module, power supply, internal frame, ports, vents, base stand, screws. Use consistent thin grey line-weight with no shading. Add numbered circular labels around each part, and include a matching numbered parts list at the bottom just like the reference blueprint. Place the SONY logo, PlayStation logo, and “PlayStation 5” text in the top left in the exact same position and style as the uploaded reference image. The entire artwork should mirror the composition, spacing, typography, and minimalist engineering-ma

Nano Banana Pro产品与品牌

包装设计展示图分析

AI变现，怎么少的了包装/封面设计！！ 不管是什么商品，一个好的包装总是能加不少分的，就像面包、奶茶、或者外卖，有质感的，或者有创意的包装会给消费者留下深刻印象。 写了一组提示词，更方便的为任意品牌/行业，融入任意形象，快速设计包装袋、贴纸、吊牌等。 开店或者摆摊的朋友，根据AI的初步设计，再让它生成详细的设计图，写出详细的尺寸、配色和材质要求，直接交给印刷商家，就可以直接做出来了。 这可比专业设计师设计要快的多。 【服装/奶茶/面包】品牌包装设计展示图，一张完整设计稿画面，【总体风格描述，纯黑色包装袋，简约Logo设计，具有质感的材质………】，【需融入形象】…… 画面中同时展示： •【服装】包装袋设计和吊牌设计 •左侧为黑色线稿结构图（线描风格，工业设计草图） •右侧为完成上色的成品效果图（真实材质质感） •下方或角落配有简洁的设计标注文字（尺寸、材质、工艺说明，示意性） 整体风格为专业包装设计提案，【干净白色】背景，平面排版清晰 设计感强，理性、有秩序 非广告海报风格 视角为正视图 + 轻微等轴测视角 高分辨率，细节清晰

Nano Banana Pro其他

根据古诗画一幅画

关关雎鸠，在河之洲。窈窕淑女，君子好逑。\n根据古诗画一幅画，并附上原文。

Nano Banana Pro其他

根据古诗画一幅画

蒹葭苍苍，白露为霜。所谓伊人，在水一方。\n根据古诗画一幅画，并附上原文。

Nano Banana Pro其他

压印成波的涂鸦

Before it was a wave, it was just paint pressed, shaped, and forced into motion.

Nano Banana Pro其他

绘画推荐系统版本 0.1：分析《呐喊》及其类似风格的艺术家作品

This prompt turns Nano Banana Pro into a painting recommendation system. I need to work to make it a bit smarter, so this is version 0.1 to be honest. Do this for Scream <instructions> I want you to act as a world class painting expert and visual artist. I want you to analyze the input by the user (painting name or artist), it style, subject, character, and come up with 4 OTHER paintings by artists past or present, no matter what country, who are less known but have a similar in style. For each painting: Analyze: The brushstroke technique, the 3D depth implied, and the hidden symbols. Goal: A "Paint Tube Squeeze." A giant, realistic oil paint tube sitting on a palette. Rules: Action: The tube is being squeezed, and the paint coming out is not just a blob, but it forms the 3D landscape of the painting. The main feature is emerging in 3D relief from the 2D smear of paint. Texture: Viscous, thick oil paint texture (impasto). Props: Paintbrushes, a dirty rag, a palette knife, plus culture appropriate tools and environment and tiny 3D printed version of the painter on the desk drawing it on a tiny easel and a newspaper headline covering the inspiration behind it. Lighting: North-light studio lighting, true color representation. artistic process" aesthetic. Output: 2x2 grid, each grid with a different painting </instruction>

Nano Banana Pro其他

绘画的价值与信息控制

ワシは絵の価値を技術だとは思ってなくて、個性やそこに込めた気持ちなんかを大切にしたいと思ってる。でも、技術はもちろん大切で、情報量が多い絵というのは、技術的な意味では価値は高い。 ただ、情報のコントロールはもっと大切で、情報が多すぎると凄いけど、どこを見てよいか分からない絵になる。 【考え方】 Step1：情報を増やす 水平垂直を無くし絵のいろんなところを斜めにする。関節のひねり・構図・ポーズ・カメラの傾きなど変化を多くする。 Step2：情報を減らす 見なくてよいところの情報をガッツリ消す。顔などを精密に描いて他は省略。 こんな感じで、Gpt-images1.5でも「絵」になる出力が可能になります。ぜひ試してみて！