
nano banana pro 原型人物与手机界面截图
🍌 nano banana pro 1. 准备人物原型 2. 准备手机界面截图 3. 和提示词一起发送
179 条UI 与平面提示词,每条都带示例图。点开任意卡片看完整提示词,可以复制,也可以免费生成。

🍌 nano banana pro 1. 准备人物原型 2. 准备手机界面截图 3. 和提示词一起发送

▷ ポップなデザイン ▷ 解説アイキャッチ画像 などの“にぎやか系”を一発で出したい方に。 コピペOKのプロンプトをこのあと貼っておくので、「使いたい〜」という方は保存してご利用ください☺️ 👇 👇プロンプト # Role: Expert Editorial Illustrator for contemporary Japanese urban lifestyle magazines # Task: Create a "Vertical Magazine Infographic Illustration" comparing Mac and Windows for designers. The style must mimic **sophisticated and playful line art illustrations** found in modern Tokyo culture & lifestyle publications: **Black Line Art + Pop Color Accents.** # INPUT SETTINGS Theme: "Mac vs. Windows for Designers" # VISUAL STYLE GUIDELINES (Strict Adherence) 1. **Style:** **"Monoline Vector Illustration" (Clean Comic Style).** * MUST use clear, consistent **BLACK OUTLINES** for everything. * Not a rough sketch, but a clean, stylish, and friendly doodle style typical of high-end editorial design. * **FLAT 2D View only.** Do NOT generate a photo of a book. Generate the *digital artwork* itself. 2. **Color Palette (Red & Blue Accents):** * **Background:** Pure White. * **Lines:** Ink Black. * **Mac Zone:** Highlighted with **Vibrant Red** (representing passion, innovation, and creative energy). * **Windows Zone:** Highlighted with **Electric Blue/Royal Blue** (representing technical versatility, solid foundation, and corporate identity). * *Note:* Do not color everything. Keep 80% white/line-art to maintain the "clean & airy" look. 3. **Composition & Density (High Information):** * **Layout:** Vertical (Portrait) Aspect Ratio (3:4). * **Structure:** Split the page diagrammatically (e.g., top vs. bottom, or a branching flowchart). * **Micro-Content (Essential):** The page must be bustling with **many tiny, cute characters** acting out scenarios. * Example: A tiny person hugging a large stylish monitor. * Example: Tiny people building a custom PC tower with tools. * Example: Characters exchanging files across a dividing line. 4. **Characters:** * Simple, trendy, anonymous "city dweller" characters (simple dots for eyes, gentle smiles). * They act as guides and workers within the infographic's world. # OUTPUT GENERATION Target Aspect Ratio: --ar 3:4 Quality Tags: vector line art, Japanese editorial design, infographic illustration, kawaii, stylish, clean, trending on design blogs. Target Image Description: A vertical full-page infographic illustration comparing Mac and Windows. The visual style is clean black line art on a pure white background. Specific details: - Top half represents Mac users: Stylized sleek all-in-one computers and laptops, tiny creative people wearing trendy glasses, highlighted with spots of **Vibrant Red**. - Bottom half represents Windows users: Stylized modular PC towers, multi-screen setups, and tablets, tiny people holding wrenches and gears, highlighted with spots of **Electric Blue**. - The layout is packed with connecting lines, arrows, speech bubbles, and small icon elements (cursors, folders, creative tools). - The overall vibe is intellectual, charming, and bustling with activity, like a page from a sophisticated culture magazine. - No photorealism. No shading. Pure flat line art with bold red and blue accents.

diagram of the body of which muscles are affected by bench press

It's finally here! Nano Banana Pro 🎉 It will blow your mind: → Advanced text rendering & infographics → World knowledge with Google Search → Integrated upscale up to 4k (soon) → Enhanced compositing with up to 6 input images Thanks to Google DeepMind for the #EarlyAccess!

Where to use Nano Banana Pro: Google AI Studio: gemini-3-pro-image-preview Google Gemini: Gemini 3 Pro Image Preview Prompt for the image: "Make a realistic infographic of the human skeletal system with labels

A 9:16 vertical, photorealistic cyber-aesthetic futuristic social-app interface. A hand is holding a vertical, iPhone-sized, borderless acrylic card, taking up most of the frame. The card displays a social media profile interface with no banners or background images. Its smooth, rounded edges emit a soft neon glow in blue, pink, and purple gradients. The background is dark and blurred, emphasizing the glowing edges; the light reflections on the fingers feel cinematic and atmospheric, creating a high-tech holographic mood. The card surface is crystal-clear, and the profile details appear almost engraved, showing only the information from the reference image. Displayed in this exact order: - Profile avatar (centered) - Name + blue verification badge (centered) - Username with “@”, e.g., @dotey (centered) - Bio (left-aligned) - Location, website (left-aligned) - Join date (left-aligned) - Following count & followers count (left-aligned) - Follow button (full-width, transparent background, rounded-full, border with soft neon glow)

一个提示词修复Notebooklm幻灯片中文字体崩坏。 Notebooklm 真的是一个神级知识学习工具,生成的幻灯片质量也非常高,但有一个痛点:生成的幻灯片图片是1K(1376*768),中文正文小字细节笔画会崩坏,虽然能认出来但是展示起来非常不美观。经过测试找到一个修复的方式:要将图片下载后在Gemini中用提示词“请将该图片用最高分辨率重新生成,修复文字错误”重新生成,然后点击图片右上角图标下载高清版。这样可以得到2K版,画面几乎看不出差别,中文字体清晰度得到极大改善,崩坏的情况几乎没有了,大家可以放大两张图片看对比。

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>

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
Create a high-resolution illustration of a [skull] icon in the style of a glossy, translucent sculpture. The icon should appear as if made of curved, flowing glass with reflective surfaces. Infuse the form with vivid, refracted rainbow gradients that shift smoothly across its contours. The shape should be abstract yet recognizable, with a sleek, high-gloss finish and soft reflections that mimic light bending through clear material. Center the icon on a solid black background. No shadows, textures, or extra elements. Square aspect ratio. 以光泽、半透明雕塑的风格创建 [骷髅头] 图标的高分辨率插图。图标应看起来像是由具有反射表面的弯曲、流动的玻璃制成的。为形式注入生动的折射彩虹渐变,在其轮廓上平滑移动。形状应该是抽象的但可识别的,具有时尚、高光泽的饰面和柔和的反射,模仿光线穿过透明材料的弯曲。将图标置于纯黑色背景上居中。没有阴影、纹理或额外元素。方形纵横比。

Pues le acabo de pedir a Nano Banana Pro 🍌 una infografía con la evolución de los lenguajes de programación. Sin más.

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 绘制一张双面板的技术蓝图,采用简洁的单色线条,布局与提供的 PlayStation 1 原理图完全一致。左侧面板,以精细的细线在白色背景上绘制完整的索尼 PlayStation 5 主机。右侧面板,绘制一张高度详细的 PS5 垂直分解图,将每个内部组件分层展示:外壳面板、面板、散热风扇、散热塔、蓝光光驱、主板、固态硬盘模块、电源、内部框架、接口、通风口、底座支架和螺丝。使用粗细一致的灰色细线,不要添加阴影。在每个部件周围添加编号的圆形标签,并在底部添加与参考蓝图相同的编号部件清单。将 SONY 标志、PlayStation 标志和“PlayStation 5”字样放置在左上角,位置和样式与上传的参考图像完全相同。整幅图应在构图、间距、字体和极简工程风格等方面保持一致。

🌐 URLを貼るだけでニュースページを“図解画像”にできるって、知ってましたか? Felo LiveDocにWebページのリンクを入れると、 AIが内容を読み取り、要点を整理し、 Nano Banana Proの画像生成でそのまま見やすい図解に変換してくれます🤯✨ 長い記事でも、複雑な説明でも、 一枚でスッと理解できるカードになるの最高👏 使い方もいろいろ⚡ ・最新ニュースのざっくり把握に ・リサーチの下調べに ・授業・講義ノートの時短まとめに などなど! 気になる記事URLで、ぜひ試してみてください📚✨ 「こんな使い方あるよ〜」の共有も大歓迎です! #FeloAI #NanoBananaPro

引用元の有料note、 nano banana Proの力で、 さっそく図解の追加を進めてます。 第1条をまとめさせたら既にエグすぎた... テキストメインにしてる人は、 今すぐ図解化していったほうが良いです。 読者の満足度が鰻登りになる。 プロンプトはリプに掲載しときます。

Create step-by-step recipe infographic for creamy garlic mushroom pasta, top-down view, minimal style on white background, ingredient photos labeled: "200g spaghetti", "150g mushrooms", "3 garlic cloves", "200ml cream", "1 tbsp olive oil", "parmesan", "parsley", dotted lines showing process steps with icons (boiling pot, sauté pan, mixing), final plated pasta shot at the bottom 奶油大蒜蘑菇意面分步食谱信息图制作要求\n呈现视角:俯视角度\n设计风格:简约风格,白色背景\n食材配图及标注:需包含“200克意大利面”“150克蘑菇”“3瓣大蒜”“200毫升淡奶油”“1汤匙橄榄油”“帕玛森奶酪”“欧芹”的图片,并分别标注对应文字\n制作步骤展示:用虚线标注制作流程,搭配图标(煮锅、煎锅、搅拌)说明各步骤\n成品呈现:在底部展示最终装盘的意面图片

X友们,你们有没有发现—— 每一代中国年轻人,都觉得上一代“老”,下一代“怪”。 但当我把 1978–2025 的潮流都放在一张图里时,我突然意识到: 我们其实都是时代的孩子,只是潮流变得太快了。 我做了一张《改革开放以来中国年轻人潮流演化超级信息图》。 灵感来自@berryxia_ai老师的爆火图 从工厂蓝制服 → 港风 → 非主流 → QQ 秀 → 街潮 → 小红书文青 → 二次元 → AI 原生青年 全部排成一条时间线,一次性看透 45 年👇 建议收藏。 📌 想自己生成这种博物馆级的演化信息图?我把全套提示词放在评论区了 👦👧大家属于哪一代? 评论区扣一个你的“青春物件”: 随身听 / QQ 秀 / 山寨机 / iPhone4 / B站 / 球鞋 / AI 头像 我看一下哪个年代的人最多😄 👇元提示词如下,复制粘贴到gemini拿到提示词,再用nanobanana生图即可 ----Prompt---- 请根据我提供的主题,自动生成一条“超高清 3D 信息图提示词”,风格需达到博物馆级呈现、具有工程蓝图美学、信息密度极高、适合 Midjourney / Flux / Stable Diffusion / Gemini 等模型生成。 生成的提示词必须包含以下结构: 【1. 标题】 为主题生成一个专业、宏大、具有档案感的主标题,例如: 《XXXX 演化图》《XXXX 发展史》《XXXX 趋势年表》。 【2. 整体风格要求】 说明信息图的全局视觉风格,包括: —— 16:9 横幅布局 —— 超真实写实 3D 渲染 —— 工程蓝图 / 档案馆质感 —— 多层纹理背景(专利图纸、水印、旧报纸、文件) —— 高对比度标题区 —— 信息密集但有秩序的布局 【3. 主时间轴设计】 要求生成一条从起点到终点的时间轴,并按主题自动拆分为 8–14 个关键节点。 每个节点必须包含: —— 写实 3D 物件 / 图标 / 人物 —— 材质随年代变化 —— 清晰年份标记 【4. 注释网络】 要求模型自动生成: —— 大量白色极细注释线 —— 浮动信息卡片 —— 解释每个节点的核心变化(政策、技术、趋势、文化、产品等) 【5. 时代模块(Era Modules)】 要求将主题的不同阶段自动分区,例如: “早期阶段 / 高速发展 / 爆发期 / 转型期 / 未来趋势”。 以悬浮标签形式呈现。 【6. 放大镜细节】 要求加入圆形放大镜窗口,用于展示: —— 材质纹理 —— 局部设计细节 —— 关键符号或设备 —— 技术结构或界面截图 【7. 底部结构化信息条】 要求自动生成数据区,包括: —— 年份 —— 关键指标 —— 代表物件 —— 时代特征 —— 关键词总结 【8. 技术渲染要求】 需包含: —— Unreal Engine 5 级别写实光影 —— 体积光 —— 信息设计风格 —— 清晰锐利对焦 —— 高级色彩分级 并在结尾加入: --ar 16:9 --v 6 --stylize 300 请严格按照以上框架,根据我接下来输入的主题,自动生成完整提示词。 -------- 改革开放以来,中国的商业机会演化图👇🏻 改革开放以来,中国的消费趋势演化图👇🏻
retexture the image attached in the following json aesthetic style:\n{\n "style": "Retro Pixel UI Icons",\n "resolution": "low (32x32 or 48x48)",\n "color_palette": [\n "#F2F2F2", \n "#C0C0C0", \n "#000000", \n "#FFFFFF", \n "#0000FF", \n "#00FF00", \n "#FFFF99", \n "#008080" \n ],\n "outline": {\n "enabled": true,\n "color": "#000000",\n "thickness": "1px"\n },\n "shading": {\n "method": "dithering",\n "colors_used": ["base color", "highlight", "shadow"],\n "pattern": "checkerboard or diagonal lines"\n },\n "lighting": {\n "type": "flat",\n "source": "top-left",\n "highlight_color": "#FFFFFF",\n "shadow_color": "#808080"\n },\n "background": {\n "color": "#F2F2F2",\n "type": "plain",\n "transparency": false\n },\n "object_properties": {\n "style": "pixel art",\n "perspective": "isometric or front-facing",\n "animation": {\n "enabled": false,\n "frame_style": "static pixel art"\n }\n }\n}
Create an illustration of a [OBJECT] in a retro cartoon style. Use only flat, solid colors with no gradients, smudging, airbrushing, or blur. All shading and highlights should be made from clean, separate color blocks. Outline all shapes with thick, bold black lines. Use a simplified color palette (such as teal, coral, mustard, and white) for a vintage feel. Add small sparkle accents or motion lines for charm, but keep the icon the clear focus. Set the illustration on a plain white background. The final result must be crisp, clean, and vector friendly with sharp edges and no texture or raster effects. Square aspect ratio. 创建复古卡通风格的 [OBJECT] 插图。仅使用单色,不要使用渐变、涂抹、喷枪或模糊。所有阴影和高光都应由干净、独立的色块制成。用粗大的黑色线条勾勒出所有形状的轮廓。使用简化的调色板(如蓝绿色、珊瑚色、芥末色和白色)以获得复古感。添加小的闪光点缀或动感线条以增加魅力,但保持图标的明确焦点。将插图设置在纯白色背景上。最终结果必须清晰、干净且矢量友好,具有锐利的边缘,并且没有纹理或栅格效果。方形纵横比。

do this for Nikola Tesla <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>

生成特色城市天气预报图片 注: - 请修改提示词底部的城市、天气、温度 - “城市特色建筑”可以具体写上名称 - 本图用 sora 生成 以清晰的45°俯视角度,展示一个等距微缩模型场景,内容为城市特色建筑,天气效果巧妙融入场景中,柔和的天气效果与城市轻柔互动。使用基于物理的真实渲染(PBR)和逼真的光照效果,纯色背景,清晰简洁。画面采用居中构图,凸显出三维模型精准而细腻的美感。在图片上方展示城市名称和当前天气状况,并附有相应的天气图标。 城市:上海 天气:多云 温度:20摄氏度

让你的形象和社交媒体相框巧妙融合 注: - 需要上传一张图片作为参考 - 请替换引号内文字 - 本图使用 sora 生成 根据所附照片创建一个风格化的3D Q版人物角色,准确保留人物的面部特征和服装细节。角色的左手比心(手指上方有红色爱心元素),姿势俏皮地坐在一个巨大的Instagram相框边缘,双腿悬挂在框外。相框顶部显示用户名『Jimmy』,四周漂浮着社交媒体图标(点赞、评论、转发)。

Nano Banana Pro prompt share: "A detailed whiteboard illustration and instructions on how to properly use the Squatty Potty

If you're a teacher or a schoolbook author, meet your new best friend, Gemini 3.0. "Make me a detailed diagram showing how mitosis works,, with annotations and visual explanations, organized at a primary school level." + same prompt "at a high school senior level.

i need a flowchart for how to toast bread, make it as wacky and over the top and complicated as possible. 我需要一个烤面包的流程图,越古怪、越夸张、越复杂越好。

创作一张 9:16 竖版 的 《番茄炒蛋》手绘风格教学食谱信息图。\\n\\n整体风格要求:\\n\\t•\\t由专业厨师写给普通人的教学食谱\\n\\t•\\t使用 Z 字形动线排版(左上 → 右上 → 左下),阅读顺畅\\n\\t•\\t彩色水彩笔速写风格,搭配 细腻墨线轮廓\\n\\t•\\t采用 2025 主流插画配色与笔触\\n\\t•\\t米色纸张纹理背景,温暖、质朴、亲切\\n\\t•\\t插图必须让人“看了就想做”\\n\\n⸻\\n\\n内容结构(通用)\\n\\n1. 顶部标题(醒目)\\n\\n《{菜名}》\\n\\n⸻\\n\\n2. 步骤区块(Z 动线排版,3–5 步)\\n\\n每个步骤包含:\\n\\t•\\t手绘步骤插图(彩色水彩+墨线)\\n\\t•\\t简短图文说明\\n\\t•\\t厨师秘技\\n\\t•\\t小心得或提示\\n\\n⸻\\n\\n步骤模板(通用,可被模型自动填充)\\n\\n步骤 1:准备食材\\n(自动根据菜名生成相关食材)\\n插图:整齐摆放的主要食材和调味料。\\n说明:列出并处理该菜的基本材料。\\n秘技:告诉用户如何提升风味或口感。\\n心得:提供简单经验或提醒。\\n\\n⸻\\n\\n步骤 2:调味 / 腌制 / 前置处理\\n插图:调制酱汁、腌肉、处理主料的小碗或砧板画面。\\n说明:展示关键基础步骤。\\n秘技:比例、小技巧、避免失败要点。\\n心得:轻松风格的小提示。\\n\\n⸻\\n\\n步骤 3:炒制 / 烹调关键步骤\\n插图:锅中食材的烹调场景,水彩烟气柔和。\\n说明:大火、小火、顺序、重要动作。\\n秘技:保持火候、控制时间、提升香气的办法。\\n心得:强调料理灵魂所在。\\n\\n⸻\\n\\n步骤 4:合味 / 出锅前步骤\\n插图:加入酱汁、调味、配料混合的场景。\\n说明:整体收汁、调味到位。\\n秘技:亮油、保持口感或香味的小技巧。\\n心得:此步决定成败。\\n\\n⸻\\n\\n步骤 5:点缀 / 完成步骤\\n插图:撒香料、加入坚果、盛盘等动作。\\n说明:最后调整味道或摆盘。\\n秘技:保持脆感、避免过熟等技巧。\\n心得:成品风味描述。\\n\\n⸻\\n\\n底部成品插图\\n\\t•\\t一份精致、色香俱全的 《{菜名}》\\n\\t•\\t水彩质感强烈、油亮、鲜嫩、诱人\\n\\t•\\t让读者看了就想做\\n\\n⸻\\n\\n底部中央署名\\n\\n@木马人 AI

2/ "Look up the 5 best vacuum cleaners under $300 and create an infographic with pros and cons for each

一个Prompt可以让Nano Banana Pro将论文转换成详细的白板照片,提示词: Take this paper and transform in the image of a professor whiteboard image: diagrams, arrows, boxes, and captions explaining the core idea visually. Use colors as well [论文内容整体复制到这] 我用Gemini 3的博客文章试了下,有点意思。

Turn anything into an info graphic with Nano Banana Pro 🍌

【NotebookLM】インフォグラフィック✖葛飾北斎プロンプトがエグイ 葛飾北斎が描いた浮世絵スタイルで資料作らせたら侍と波が爆誕 墨+朱+藍のカラーマップめちゃ良い 学会でもポスターでも絶対目立つ!!!!!! ーーー📒プロンプトーーー 浮世絵師・葛飾北斎が描いたような和風インフォグラフィックにして。波や雲の装飾を入れ、文字は江戸文字(勘亭流)で。カラーパレットは墨・藍・朱・淡黄のみ。現代のデータを侍や町娘が解説している構図で。

🤯 这太疯狂了!一个提示词就能“解剖”任何生物的身体构造?! 这个 万能提示词 能生成: ✨ 超精细的 3D 解剖图 ✨ 自动适配的骨骼/内脏系统 ✨ 带编号的专业医学标注 💡灵感来源:@s_tiva的作品 无论是 皮卡丘的内部结构还是哥斯拉核心,全都能透视!👀 完整提示词放在评论区啦👇 #nanobanana #Gemini #Aiart️ #NanoBananaPro 完整提示词如下👇 ----Prompt---- { "variables": { "ORGANISM_NAME": "<<<user enters only the organism name>>>" }, "promptDetails": { "description": "Ultra-detailed anatomical exploded view (exploded-view) and layered biological infographic of {ORGANISM_NAME}, presented as an educational, clinical-clear scientific visual.\n\nSpecies-accuracy rule (mandatory): Automatically infer the correct anatomy for {ORGANISM_NAME}. If it is a vertebrate, show an internal skeleton (skull, spine, ribs, limb bones as applicable). If it is an invertebrate, show the appropriate exoskeleton/segments and primary support structures. Automatically choose the correct respiratory organs for {ORGANISM_NAME} (lungs, gills, tracheal system, etc.). Depict the reproductive system in a measured, educational manner (no explicit nudity).\n\nCamera and composition:\n- 3/4 front isometric angle, scientific product/anatomy render perspective.\n- Main body centered; outer body partially transparent and opened.\n- Anatomical layers and major systems are separated and floating around the main body in a clean, symmetric, hierarchical exploded layout.\n- Even spacing between layers; no clutter.\n- Callout leader lines never cross; labels stay inside the frame and remain highly legible.\n\nLayers and systems (outer to inner, species-appropriate):\n1) Outer surface: skin or exoskeleton/outer tissue.\n2) Support system: skeleton or exoskeleton/segments.\n3) Muscular system: major muscle groups and tendon attachments.\n4) Circulatory system: heart and major vessels (avoid messy capillary over-detail).\n5) Respiratory system: species-appropriate organs.\n6) Digestive system: stomach/gizzard (if applicable), intestines, liver and associated organs.\n7) Nervous system: brain or ganglia structures, primary nerve pathways.\n8) Reproductive system: species-appropriate core structures.\n9) Signature anatomy: highlight {ORGANISM_NAME}-specific distinctive structures (wings, fins, tail, horns, pouches, antennae, etc.) as separate emphasized layers.\n\nLabeling (mandatory):\n- Thin white leader lines + numbered labels.\n- Typeface: minimalist sans-serif, high legibility.\n- Label format: \"## Part Name (System)\". Example: \"03 Sternum (Skeletal)\".\n- Use 12–24 labels total; no duplicate numbers.\n\nVisual style and quality:\n- Photorealistic 3D medical/anatomy render + textbook infographic aesthetic.\n- Clinical clarity, high contrast, razor-sharp detail, 8K.\n- Clean composition, strong negative space management, educational focus.\n\nLighting and background:\n- Soft, even studio lighting; controlled reflections.\n- Background: seamless smooth dark gray or dark navy scientific studio backdrop.", "styleTags": [ "Anatomical Exploded View", "Medical/Biological Infographic", "Layered Anatomy", "Photorealistic 3D Anatomy Render", "Educational Scientific Style", "Minimalist Labels", "Dark Studio Background", "Clinical clarity", "Exploded view hierarchy" ] }, "negativePrompt": "blood, gore, horror, surgery scene, open wounds, excessive graphic content, real-person portrait, human-identity face, celebrity likeness, messy exploded layout, unnecessary extra organs/limbs, incorrect anatomy, blurry labels, unreadable text, crossed/overlapping leader lines, cartoon style, low-poly, watermark, logo, broken perspective, excessive noise, heavy motion blur", "generationTips": { "aspectRatio": "2:3", "detailLevel": "ultra", "stylization": "low-medium", "camera": { "angle": "3/4 front isometric", "lens": "scientific product/anatomy render perspective" }, "lighting": "soft, even, medical-illustration clarity", "background": "seamless smooth dark gray or dark navy", "compositionLocks": [ "no crossing leader lines", "labels legible and inside frame", "even spacing and clear hierarchy between layers" ] } } --------
interpret the video thumbnail that is @ img1 print your detailed story derived your interpretation of @ img1 as the text only image output. expected output format: small easy to read white sans serif block format text on a blue background

Leonardo Da vinci stili not Object kısmını siz dolduruyorsunuz. Vintage notebook page in the style of Leonardo da Vinci’s sketchbook, carefully studying {OBJECT}. Draw {OBJECT} as hand-sketched technical diagrams, keeping realistic proportions and recognizable details. Show several views of the same object on one page (front view, side view, top view, and a small cutaway view that suggests inner structure), all drawn with thin sepia ink lines, cross-hatching and subtle shading. Place all sketches on aged, yellowed parchment paper with visible paper fibers, stains, ink bleed and slightly torn, darkened edges. The background MUST look like real old paper, not clean white. Around the sketches, add small arrows and handwritten annotations in dense, flowing cursive script that closely resembles Leonardo da Vinci’s mirror-writing: narrow letters, right-to-left direction, old Italian feel, but use illegible pseudo-text, not real words. The ink should look like brown iron-gall ink, slightly faded and uneven. Soft, natural lighting, like a scanned historical notebook page. No modern elements, no user interface, no logos, no printed fonts. The entire image must feel like an authentic page torn from Leonardo da Vinci’s personal notebook, dedicated to the study of {OBJECT}.

🍌 Pro = 把论文可视化?! Nano Banana Pro 很擅长做 Diagram/分析图! 🍌 Pro 在多语言和长文字生成以及可视化上比较厉害! 你可以把一篇论文丢给他,然后让他画个中英双语的分析图/Diagram,文字很准确 05|测试系列|Nano Banana Pro|ZHNO
I can't stop making voxel icons in ChatGPT 4o. Here's how I do it (includes prompt and reference photo):

If the X app were designed by Wes Anderson. The X app mobile interface if it was designed by Wes Anderson. Make the style hyper realistic skeuomorphism Give it a try and QT what you make with it!