← 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

Mixed Reality Retail Experience Prompt

infographic-edu-visual

A prompt for generating a hyper-realistic first-person perspective image inside a supermarket aisle, where human hands hold a product surrounded by a dynamic, multi-layered holographic Augmented Reality (AR) interface displaying nutritional data and a highlighted shopping list item.

展开提示词全文
First-person perspective inside a brightly lit supermarket aisle or section. Realistic human hands are holding {argument name="product name" default="[PRODUCT NAME]"} close to the camera. The product’s [key visual traits: color, texture, packaging, freshness details] are clearly visible under natural store lighting.

The {argument name="product name 2" default="[PRODUCT NAME]"} is surrounded by a multi-layered holographic augmented reality interface displaying relevant product information, including [nutritional or product data such as calories, protein/sugar/caffeine, vitamins, freshness indicator, origin, expiration date, usage or recipe suggestions].

The AR UI elements smoothly shift and reorganize based on the viewer’s gaze direction, as if dynamically responding to user focus. In the left peripheral vision, a vertical semi-transparent shopping list is visible with checked-off items, where {argument name="product name 3" default="[PRODUCT NAME]"} is highlighted as the currently active selection.

Hyper-realistic mixed reality, clean futuristic AR design, glass-like UI panels, soft ambient glow, realistic lighting and shadows, natural depth of field, immersive first-person interface, showcasing next-generation retail technology.

Prompt for Generating Logical Tree Diagrams with Nano Banana Pro

infographic-edu-visual

A user developed a specific prompt for Nano Banana Pro (using Gemini Pro mode) to generate logical tree diagrams or flowcharts based on a provided article text, emphasizing a technical, structured, and visually dense style.

展开提示词全文
Illustrate this article
```
({argument name="article text" default="Paste the article text you want to illustrate"})
```

This is how to illustrate it
```
A dense and expansive Japanese logic tree diagram drawn on a clean white page. The image is packed with structured information: neat hierarchical boxes, lists of bullet points, and precise connecting lines drawn with a fine-point pen.

There is no messiness; the "chaos" comes from the sheer overwhelming volume of organized data and Japanese text. It looks like a complex master plan or algorithm design. Important nodes are boxed in red. The handwriting is small, neat, and rapid.

Style: Technical diagram, neat handwriting, information visualization, minimalist background.
Quality: High definition, distinct Japanese text.

Technical Infographic for E-commerce Product Description

infographic-edu-visual

A highly detailed, multi-part prompt designed to generate a technical infographic for an e-commerce product, combining a realistic photograph of the object with hand-sketched, architectural-style annotations, measurements, and schematic diagrams on a pure white background. The example object is a Tudor North Flag watch.

展开提示词全文
Create an infographic image of {argument name="object" default="Tudor North Flag"}, combining a realistic photograph or photorealistic render of the object with technical annotation overlays placed directly on top.

Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background.

Include:
•Key component labels
•Internal cutaway or exploded-view outlines (where relevant)
•Measurements, dimensions, and scale markers
•Material callouts and quantities
•Arrows indicating function, force, or flow (air, sound, power, pressure, movement)
•Simple schematic or sectional diagrams where applicable

Place the title {argument name="object title" default="[OBJECT]"} inside a hand-drawn technical annotation box in one corner.

Style & layout rules:
•The real object remains clearly visible beneath the annotations
•Annotations look hand-sketched, technical, and architectural
•Clean composition with balanced negative space
•Educational, museum-exhibit / engineering-manual vibe

Visual style:
Minimal technical illustration aesthetic.
Black linework layered over realistic imagery.
Precise but slightly hand-drawn feel.

Color palette:
Pure white background.
Black annotation lines and text only.
No colors.

Output:
Ultra-crisp
Social-feed optimized
No watermark

Technical Infographic Overlay on a Photorealistic Object

infographic-edu-visual

A prompt template for generating an infographic image that combines a photorealistic render of an object with technical annotation overlays. It specifies black ink-style line drawings, key component labels, measurements, and schematic diagrams on a pure white background, creating an educational, engineering-manual aesthetic.

展开提示词全文
Create an infographic image of {argument name="object" default="[OBJECT]"}, combining a realistic photograph or photorealistic render of the object with technical annotation overlays placed directly on top.

Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background.

Include:
•Key component labels
•Internal cutaway or exploded-view outlines (where relevant)
•Measurements, dimensions, and scale markers
•Material callouts and quantities
•Arrows indicating function, force, or flow (air, sound, power, pressure, movement)
•Simple schematic or sectional diagrams where applicable

Place the title {argument name="object title" default="[OBJECT]"} inside a hand-drawn technical annotation box in one corner.

Style & layout rules:
•The real object remains clearly visible beneath the annotations
•Annotations look hand-sketched, technical, and architectural
•Clean composition with balanced negative space
•Educational, museum-exhibit / engineering-manual vibe

Visual style:
Minimal technical illustration aesthetic.
Black linework layered over realistic imagery.
Precise but slightly hand-drawn feel.

Color palette:
Pure white background.
Black annotation lines and text only.
No colors.

Output:
1080 × 1080 resolution
Ultra-crisp
Social-feed optimized
No watermark

Photorealistic Diorama Isometric Map Prompt

infographic-edu-visual

A structured prompt for generating a highly detailed, photorealistic miniature diorama-style isometric map of a city. It specifies a 45-degree top-down angle with a tilt-shift effect, emphasizing oversized landmarks, detailed miniature architecture, and placement on a vintage textured paper map base.

展开提示词全文
"description": "Create a highly detailed, photorealistic miniature diorama style isometric map of {argument name="city location" default="CITY/LOCATION"} placed on a vintage textured paper map.",
  "perspective": {
    "type": "isometric",
    "angle": "45 degree top down",
    "look": "macro photography with tilt-shift miniature effect"
  },
  "geography": {
    "shape": "follows real geographic shape of {argument name="city location" default="CITY/LOCATION"}",
    "landmarks": {
      "oversized": true,
      "dominant": true,
      "primary_focus": "monuments",
      "secondary_elements": "smaller and simplified"
    },
    "architecture": "ultra detailed miniature",
    "roads": "selective",
    "greenery": true,
    "water_bodies": true,
    "terrain": true,
    "materials": ["stone", "wood", "concrete", "glass", "foliage"]
  },
  "lighting": {
    "type": "soft cinematic daylight",
    "effects": ["natural shadows", "warm highlights", "subtle atmospheric depth"]
  },
  "water": {
    "rivers": true,
    "coastlines": true,
    "depth_gradients": "smooth",
    "reflections": "gentle"
  },
  "map_base": {
    "type": "old world cartographic paper",
    "features": ["visible grid lines", "paper grain", "printed place names"]
  },
  "focus": {
    "sharp_on_landmarks": true,
    "edge_falloff": "gentle"
  },
  "quality": {
    "museum_quality": true,
    "handcrafted_diorama_realism": true,
    "ultra_high_resolution": true
  },
  "background": {
    "color": "clean pure white",
    "restrictions": ["no floating text", "no logos", "no watermarks", "no futuristic or cartoon elements"]
  },
  "aspect_ratio": "4:5"
}

Atmospheric Product Interface Visual Prompt for SaaS UI

infographic-edu-visual

A prompt designed to generate a luxurious and calm visual representation of a modern SaaS product interface, emphasizing clarity, hierarchy, and a neutral color palette for a premium user experience.

展开提示词全文
Atmospheric product interface visual for a modern SaaS platform.
Clean hierarchy, balanced contrast,
soft shadows, neutral color palette,
focus on clarity and calm,
designed like a best-in-class SaaS experience.

Motion and Image Prompt for Ultra-Realistic Food Photography of Pasta

infographic-edu-visual

A dual prompt for generating a motion sequence and a still image of ultra-realistic food photography. The motion prompt describes a smooth, precise spin of a pasta cup with ingredients separating while maintaining alignment. The image prompt specifies a detailed, high-quality shot of creamy white sauce penne pasta, focusing on texture, lighting, and a clean, commercial presentation.

展开提示词全文
Motion Prompt: The pasta Cup start to round spin while ingredients separate gently and precisely, maintaining alignment and scale. The motion is smooth, with no extra effects.

IMAGE 1 - Ultra-realistic food photography of a prepared creamy white sauce penne pasta served in a minimal ceramic bowl. Perfectly cooked penne coated evenly in rich, glossy cream sauce, topped with freshly grated parmesan cheese and finely chopped green herbs. Clean white studio background, soft diffused lighting, gentle shadows under the bowl, natural highlights on the sauce, realistic texture and thickness. Centered composition, shallow depth of field, premium restaurant-style presentation, high-detail food styling, 8K quality, sharp focus, no text, no labels, no hands, no props, no watermark.

IMAGE 2 - Exploded view of a creamy pasta bowl, presented as a clean commercial breakdown.
Exactly five ingredients, evenly spaced in vertical order.
Ingredient order (top → bottom):
Grated parmesan cheese — 20 g
Fresh herbs garnish — 5 g
Creamy white sauce — 80 g
Cooked penne pasta — 150 g
Serving bowl base — 200 g (bottom)
Minimal infographic annotations, instructional food design.

First-Person AR Shopping Interface Overlay

infographic-edu-visual

This prompt generates a realistic first-person perspective (POV) image of holding strawberries, overlaid with a futuristic Augmented Reality (AR) interface displaying nutritional facts, freshness gauge, and a holographic shopping list, emphasizing high-tech, photorealistic lighting.

展开提示词全文
A realistic first-person perspective (POV) shot of a person's hands holding a bunch of fresh, red strawberries in a blurred supermarket aisle. The image features a futuristic Augmented Reality (AR) interface overlay. 

Glowing holographic graphics surround the strawberries displaying nutritional information like 'Calories {argument name="calories" default="50kcal"}', 'Vitamin C', 'Folate', and 'Fiber'. On the right, a digital gauge shows 'Freshness {argument name="freshness" default="95%"}' and recipe suggestions like 'Strawberry Smoothie'. On the left, a holographic shopping list checks off items like Milk and Bread. 

High-tech, smart shopping concept, photorealistic lighting, 8k resolution.

Newspaper Mid-Unfold Diorama Prompt

infographic-edu-visual

A creative prompt for generating an epic 3D scene where a massive broadsheet newspaper is mid-unfold, and its headlines physically erupt into miniature dioramas of the events they describe. It specifies that column text rises as city blocks and the ink smell is almost visible, aiming for an 8K photorealistic result.

展开提示词全文
Epic 3D scene: a massive broadsheet newspaper mid-unfold, its headlines erupting into the events they describe. Front page stories become dioramas pushing off the page. {argument name="headline event" default="[HEADLINE EVENT]"} manifests in miniature chaos. Photographs animate and expand into three dimensions. Column text rises as city blocks of information. Editorial section becomes a battlefield of arguing figures. Classifieds transform into tiny desperate lives. Different sections occupy different worlds: sports as stadium, business as trading floor, obituaries as memorial garden. Yesterday's news composites beneath as fading ghost layer. Ink smells almost visible as atmosphere. Newsstand visible at the edge, morning light, coffee steam, 8K, photorealistic.

Isometric 3D Diorama of Product Evolution Prompt

infographic-edu-visual

A complex, multi-step system instruction prompt designed to generate a hyper-realistic, isometric 3D diorama illustrating the evolution of a product (like bread or whiskey) across three phases (Source, Industry, Experience). The diorama is displayed on an unrolled antique map, with the path connecting the scenes made of the raw material itself, simulating an 'Anno 1800' strategy game aesthetic.

展开提示词全文
Input Variable:   {argument name="topic" default="[INSERT TOPIC]"} (e.g., The History of Bread, The Making of Whiskey, The Story of Silk, The Evolution of Paper)

  System Instruction:  
Generate a hyper-realistic, isometric 3D diorama displayed on an unrolled antique map. Use the following logic to procedurally generate the scene:

  1.  Deconstruction:  
      Analyze the Input:   Break the topic into   3 Phases of Production   (From Nature to Consumption).
      The Material Path:   Identify the raw unit of the topic (e.g., Coffee Beans, Wheat Grains, Silk Cocoons, Wood Chips). This material will form the physical "Road" connecting the scenes.

  2. Container (The Chart):  
      The Object:   A large, textured   Parchment Scroll   with curled edges, unrolled on a rich Mahogany wooden table.
      The Layout:   An   "S-Curve" Path   winds through the center of the scroll, connecting three distinct raised platforms.
      The Timeline:   Delicate black ink timeline markers (dates like 1600, 1850, 1920) run alongside the path.

  3.  Vignettes (The Production Line):  
  CRITICAL:   Do not generate Sci-Fi. Stick to   Historic and Modern Classic   aesthetics.

 Top Left - The Source):  
         Concept:  The Agricultural or Raw Origin.
         Visuals:  Rows of crops, a mine, or a forest growing directly out of a wooden block base.
         Figures:  Tiny farmers or laborers in period-appropriate rustic clothing harvesting the raw material.

 Top Right - The Industry):  
         Concept:  The Processing and Refinement (Industrial Revolution Era).
         Visuals:  A factory or mill with   Copper Stills, Brass Gears, Smokestacks, or Water Wheels  .
         Figures:  Workers operating machinery, steam rising from vents.

 Bottom Left - The Experience):  
         Concept:  The Final Consumption (The "Golden Age").
         Visuals:  A warm, inviting interior. A Victorian Pub, a Parisian Cafe, a Tailor Shop, or a Library.
         Figures:  Patrons enjoying the finished product in a social setting.

  4. The "Hero" Object (Bottom Right):  
    Instead of a fourth building, the path ends at a   Life-Sized "Hero" Object   sitting on the paper.
         (e.g., A perfect porcelain Cup of Coffee, A Loaf of Sourdough, A Crystal Whiskey Tumbler). 

  5. Visual Syntax:  
      The Path:   The road connecting the buildings is NOT dirt or asphalt. It is a   River of the Raw Material   (e.g., A road paved with Coffee Beans or Wheat grains).
      Typography:   An elegant Serif Header at the bottom: "The Evolution of [Input]".
      Lighting:   Warm, indoor "Library" lighting. Soft shadows, rich wood tones, no harsh neons.

  Output:   ONE image, 1:1 Aspect Ratio, Isometric Diorama, "Anno 1800" Strategy Game Aesthetic, High Texture,

Layered Diorama of Religious Architecture Evolution

infographic-edu-visual

A concise prompt for generating a layered diorama illustrating the evolution of religious architecture across different historical eras, specifying the arrangement of architectural styles from 5000 BC to 2025 AD, complete with era-coded tabs and relevant details like stained glass.

展开提示词全文
Layered Diorama: Evolution of Religious Architecture
Layers: Front ({argument name="era 1" default="5000 BC Architecture"}), middle 1 ({argument name="era 2" default="1200s Architecture"}), middle 2 ({argument name="era 3" default="1800s architecture"}) rear (2025 Architecture).
Details: Polished stone base with era-coded tabs (with appropriate materials and elements for each era). Details include stained glass windows, flying buttresses, and other era relevant elements. All years should be visible

Nano Banana Slide Generation Discussion

infographic-edu-visual

This tweet discusses using Nano Banana for generating slides, highlighting Manus's strength in combining powerful research with slide creation. It notes that the text in the slides is editable, making it potentially more convenient than using Gemini or NotebookLM.

展开提示词全文
Slide generation using Nano Banana

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。