← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 1,827 · 热度分 55.6

产品介绍

从包含10,000+真实图像生成提示的精选库中推荐提示。兼容任何AI图像模型,包括Nano Banana Pro、Nano Banana 2、Seedream等。

资源信息

作者:dophinl
分类:图文音视频多模态生成
版本:1.0.9
认证方式: 无需认证
是否付费: 官方未说明

许可证信息摘自官方源,可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。

标签
图片生成

提示词库 · 2.3万

数据源:社区提示词库(MIT 许可,每日同步)

共 15141 条提示词,按 11 个用途归类;同一条可归入多个用途,因此分类条数相加会大于去重后的总数。

命中 605 条

20-Panel Cartoon Robot Drawing Guide Prompt

infographic-edu-visual

A detailed, step-by-step prompt for Nano Banana Pro (on LeonardoAi) instructing the model to create a 20-panel layout guide for drawing a cute cartoon robot, with each panel adding one specific, cumulative change, starting from basic guidelines to final details like claw hands and shadows.

展开提示词全文
Create a 20-panel layout guide for drawing a cute cartoon robot. Each panel keeps everything from before and adds one clear change.

1. Light guide lines: vertical center, horizontal center, and a ground line.
2. Add torso: rounded rectangle above the ground.
3. Add torso centerline.
4. Add head: smaller rounded square above torso.
5. Add neck connector: short rounded block.
6. Add left eye circle.
7. Add right eye circle.
8. Add pupils inside both eyes.
9. Add thin rim rings around both eyes.
10. Add mouth rectangle below eyes.
11. Add evenly spaced vertical slats in the mouth.
12. Add left shoulder joint circle on torso side.
13. Add right shoulder joint circle.
14. Add left upper arm cylinder from left shoulder.
15. Add left elbow circle and left forearm cylinder.
16. Add left claw hand (base curve + two prongs).
17. Add right upper arm cylinder from right shoulder.
18. Add right elbow circle and right forearm cylinder.
19. Add right claw hand to match left.
20. Add legs and feet as simple blocks: two short legs from torso bottom and two rounded trapezoid feet, plus a small ground shadow.

Cinematic 3x3 Workout Contact Sheet Generation Prompt

infographic-edu-visual

A detailed prompt for Nano Banana Pro to create a cinematic 3x3 contact sheet from an uploaded image, preserving the athlete's identity, clothing, and mat, but changing the environment to an outdoor, midday setting. The prompt specifies the exact pose and label for nine different workout exercises, ensuring consistency in style and composition across all frames.

展开提示词全文
Create a cinematic 3×3 contact sheet from the uploaded image. Keep the same athlete, face, body proportions, workout lingerie, workout mat, and workout location across all nine frames. Update the environment to an outdoor setting. Set time of day to midday with natural overhead sunlight. The workout mat stays identical in color, position, texture, and orientation in every frame. Use a mix of wide shots and close-up shots. Apply consistent cinematic color grading, soft contrast, and film-style lighting adapted to bright midday conditions. Every frame appears as a film still from the same outdoor workout session.

Environment details
• Outdoor location such as {argument name="outdoor location" default="rooftop, park, terrace, or open concrete space"}
• Clear midday sky
• Bright natural light from above
• Soft natural shadows under the athlete
• No background changes between frames

Workout lingerie details
• Fitted sleeveless workout top
• High-waist compression leggings
• Seamless matte athletic fabric
• Wavy {argument name="lingerie pattern color" default="purple, green, and blue"} pattern
• Practical training-focused fit
• Lightweight workout shoes
• Stable sole for balance

For each cell
• Show the correct exercise pose matching the workout label
• Add a workout exercise label at the top left
• Match label text exactly to the exercise shown
• Place text on a solid black background
• Keep a clear margin from the image edge
• Add padding inside the label
• Use a small corner radius
• Use clean sans-serif text in white
• Keep label size consistent across all cells
• Add a 1px solid black border around each cell

Top row
• Squat, athlete performing a squat
• Slow Burpees, athlete mid controlled burpee
• Knee Tuck Crunch, athlete performing knee tuck crunch

Middle row
• Reach Through, athlete performing reach through
• Russian Twist, athlete seated performing Russian twist
• Bird Dog, athlete performing bird dog on the mat

Bottom row
• Superman Hold, athlete holding superman position
• Jumping Jacks, athlete mid jumping jack
• Lateral Steps, athlete performing lateral side steps

Rules
• No identity change
• Same workout lingerie across all frames
• Same workout mat across all frames
• No body shape change
• Outdoor location stays consistent
• No added equipment
• Same lighting direction across all frames
• Film still style, no collage

Data Visualization based on Storytelling with Data

infographic-edu-visual

A prompt template designed to generate sleek data visualizations by instructing the AI to adhere to the principles outlined in the book 'Storytelling with Data', allowing the user to input their specific data.

展开提示词全文
Visualize according to the visualization principles in the book Storytelling with Data: [{argument name="add the data" default="add the data"}]

Calculus Symbols as Futuristic Architecture

infographic-edu-visual

A short, vague prompt designed to generate a 2x2 grid of four futuristic architectural landmarks. The landmarks are based on important calculus symbols and are set in a utopian solarpunk city, emphasizing clean materials, bright midday lighting, and a sense of scale.

展开提示词全文
A 2x2 grid of 4 futuristic architectural landmarks based on important calculus symbols, Set in a utopian solarpunk city, bright midday sunlight, clean white materials, glass and steel, cyan sky, architectural photography, Lumion render, wide angle, high exposure, sense of scale

Surreal Diorama and Don Quixote Miniature Prompts

infographic-edu-visual

Two detailed image generation prompts used with Nano Banana Pro. The first creates a surreal, clinical diorama of a futuristic hatching laboratory emerging from an open vintage book of 'Brave New World.' The second generates a hyper-realistic miniature sculpture diorama of a Spanish landscape and windmill scene from 'Don Quixote' within an open aged book.

展开提示词全文
1. Surreal diorama emerging from an open vintage book of "{argument name="book title 1" default="Brave New World"}" by {argument name="author 1" default="Aldous Huxley"}: the pages form a futuristic hatching laboratory with rows of glowing test tubes containing embryonic figures on conveyor belts, lab-coated workers in white uniforms operating machines, a large all-seeing eye symbol on the wall, conveyor belts moving via hidden mechanisms, cool blue neon lighting, hyper-detailed miniature sculpture, clinical and eerie atmosphere, photorealistic.

2. Detailed miniature diorama in an open aged book for "{argument name="book title 2" default="Don Quixote"}" by {argument name="author 2" default="Cervantes"}: left page with "{argument name="engraving text" default="DON QUIXOTE"}" engraved, right pages sculpted into a Spanish landscape with a massive wooden windmill turning slowly, tiny knight on horseback charging with lance raised, Sancho Panza on donkey following, dusty plains and gears for windmill blades, warm golden hour lighting, hyper-realistic handcrafted sculpture, whimsical yet epic scale.

WordPress Blog Setup Diagram Generation Prompt

infographic-edu-visual

A simple prompt used to compare ChatGPT Images and Nano Banana Pro, instructing the AI to generate a diagram illustrating the steps for setting up a WordPress blog.

展开提示词全文
Please generate an illustrative image of the steps for setting up a WordPress blog.

Slide Generation Prompt for Nano Banana Pro

infographic-edu-visual

This prompt is used with the 'Slides' feature powered by Nano Banana Pro to automatically generate a presentation. The user specifies the topic and the desired number of slides, and the AI handles the structure, text, diagrams, and design.

展开提示词全文
"Create {argument name="number of slides" default="20"} slides about {argument name="topic" default="XX"}"

Technical Schematic Overlay Prompt

infographic-edu-visual

A prompt used to test another model's capability against Nano Banana, generating a high-resolution, realistic photograph with a mixed-media overlay of white, hand-drawn technical schematics and engineering diagrams, creating an educational infographic aesthetic.

展开提示词全文
A high-resolution, realistic photograph of {argument name="subject" default="Golden Gate Bridge"}. The image features a mixed-media overlay of white, hand-drawn technical schematics and engineering diagrams superimposed on the subject. Elements include dimension lines, arrows indicating movement or force, text labels, and a cross-section detail. The aesthetic is an educational infographic, blending real-world photography with precise white chalk-style technical analysis, 4k resolution.

Handwritten Notes to Whiteboard Conversion Prompt

infographic-edu-visual

A simple text prompt instructing the model to convert messy handwritten notes into a structured, photorealistic image of a whiteboard, useful for digitizing and organizing information.

展开提示词全文
"Convert messy notes into a structured, photorealistic whiteboard"

2025 Scrapbook Mosaic Stone Aesthetic

infographic-edu-visual

A structured prompt for generating a visual scrapbook or 'Year in Review' using a mosaic stone aesthetic. It lists various memories and provides specific visual descriptions for how each memory should be represented as an inlaid illustration on a textured stone background.

展开提示词全文
{
  "title": "MY 2025 SCRAPBOOK",
  "theme": "Personal Year in Review / Mosaic Stone Aesthetic",
  "visual_style": "Textured stone background with inlaid illustrations representing different memories.",
  "memories": [
    {
      "category": "Biggest Achievement",
      "content": "Ran a marathon",
      "visual_description": "A man raising his hands in victory on a ribbon banner."
    },
    {
      "category": "Overcame",
      "content": "Procrastination",
      "visual_description": "A man breaking free from chains."
    },
    {
      "category": "Unlocked",
      "content": "Gymnastic skills",
      "visual_description": "A man performing a handstand on a green book."
    },
    {
      "category": "Core Memory",
      "content": "Grandma's 75th Birthday!",
      "visual_description": "A framed picture of the man hugging an elderly woman with a birthday cake."
    },
    {
      "category": "One for the soul",
      "content": "First Solo trip",
      "visual_description": "A hiker with a backpack looking toward a mountain peak."
    },
    {
      "category": "Trip Memory",
      "content": "Bali",
      "visual_description": "A ticket stub illustration showing the man near a traditional Balinese temple."
    },
    {
      "category": "I ate the most",
      "content": "Ramen",
      "visual_description": "A man eating noodles with chopsticks from a bowl."
    },
    {
      "category": "Overused Gemini prompt",
      "content": "Plan my schedule",
      "visual_description": "A man working on a laptop."
    },
    {
      "category": "My motto for 2026",
      "content": "Visit Italy",
      "visual_description": "A toy rocket ship blasting off."
    }
  ]
}

Pop-Up Paper Engineering of Mathematical Symbols

infographic-edu-visual

A prompt for Nano Banana Pro requesting a 2x2 grid image featuring four large mathematical symbols (Integral, Sigma, Pi, Klein bottle) constructed as hyper-realistic pop-up paper engineering sculptures on an opened book, emphasizing miniature realism and editorial lighting.

展开提示词全文
A 2x2 grid of 4 large mathematical symbols built as pop-up paper engineering on an opened book
[Top Left: The Integral (∫) as a towering paper archway, cut-paper strata, printed equations as microtext wallpaper]
[Top Right: The Sigma (Σ) as a folded paper museum with sharp origami cantilevers, shadow play, diagram callouts]
[Bottom Left: The Pi (π) as a pop-up classical gate in layered cardstock, weathered ink textures, tiny paper pedestrians]
[Bottom Right: The Klein bottle silhouette as an impossible pop-up sculpture, paper tabs and join lines visible, elegant paradox geometry]
Tabletop editorial lighting, shallow DOF, crisp paper fibers, bookbinding details, inked diagrams, swiss grid layout, hyper-clean miniature realism.

News Article Diagram Generation

infographic-edu-visual

A prompt used to compare Nano Banana Pro and GPT Image 1.5 by instructing the model to visualize a news article into a single slide diagram.

展开提示词全文
https://t.co/QLQaHeytKz

Illustrate this news article onto a single slide.

提示词模型无关,可直接用于 Midjourney / DALL·E / Flux / Stable Diffusion 等任意文生图模型。

信息边界说明

本页信息摘自官方文档,仅作技术信息呈现,不代表本站的判断或推荐。价格、配额、可用性以官方最新说明为准。你离开本站后的任何行为(申请 Key、付费、部署、商用),本站不做任何承诺与担保。

同类推荐

视频短视频图片音乐音频配音口播数字人全能创作

官方标注收费

通过同一个AI创作工具完成AI图片、视频、音乐与语音创作,查找公开社交数据,编辑视觉成果,并集中查看和管理生成资产。Beatra 全能创作支持AI图片生成(文生图)、AI视频生成(图生视频)和AI视频编辑,通过AI音乐生成把想法做成歌曲或纯音乐,也可用AI语音生成(文字转语音)、多语言旁白和AI语音克隆完成跨媒介内容;还能查找抖音数据、小红书数据,以及 YouTube、TikTok、Instagram 与 X 上的公开帖子、笔记、评论、账号和趋势,把社交媒体数据用于竞品调研和创作。它是一款面向AI内容创作与多模态内容创作的AI创作套件,用起来就是一个把图片、视频、音乐与语音收在同一处的AI创作助手,适用于社交内容、产品展示、营销素材、课程、播客、短片和跨媒介项目;还能在不同媒介间复用原始素材、已有成果和查到的公开资料,查看制作进度、返回文件、实际用量和积分记录。

AI数字人口播与虚拟主播视频

官方标注收费

用一张人像和一段短脚本或语音,制作有明确讲述内容的数字人口播视频。可使用现成录音,也可以先选择音色,把脚本生成旁白,让画面中的人物随声音完成稳定、自然的口播。适合 AI 主播、虚拟主播视频、数字人讲解、让照片说话、照片说话视频、产品讲解视频、数字人培训视频、公告和社交口播,并在交付后检查人物一致性、声音清晰度、口型同步和动作稳定性。

罗斯蒙德可视化图形生成

官方未说明

【罗斯蒙德可视化图形生成】南京罗斯蒙德基于已交付项目沉淀的可视化图形生成场景:根据业务描述或系统需求,自动生成可编辑的架构图、流程图、ER 图、时序图、状态图与 C4 图。采用「统一图模型」一次建模、多格式输出:结构化文本(Mermaid / PlantUML,可嵌入 Markdown、进 Git 版本管理)、可编辑图形文件(drawio / Excalidraw,可拖拽修改节点与样式)、静态图(SVG 自渲染,PNG 给转换命令),并输出图形说明(图的含义 + 关键节点解释)。内置样式系统统一配色与命名,内置布局引擎自动排布,校验脚本拦截孤立节点、悬挂连线与语义缺漏。触发词:画架构图、画流程图、画 ER 图、画时序图、画状态图、C4 图、系统架构图、部署架构图、数据流程图、实体关系图、生成 drawio、生成 Excalidraw、导出 mermaid、导出 PlantUML、导出 SVG、导出 PNG、可编辑的图、图转可编辑、架构图可编辑、流程图二次修改、画图、出图、画个图。

架构图一键生成

官方标注收费需申请 Key

使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。

AI Image Prompts · 绘画提示词库

官方标注免费

Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques

架构图一键生成

官方标注收费需申请 Key

使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。

什么是技能

技能(Skill)是封装好的单项能力,比如文字识别、文档摘要、关键词提取。开发者把调用逻辑和提示词打包,使用者像用插件一样加载即可,无需了解底层模型。启枢技能 收录大量技能,可直接试跑或编入方案。