← 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

Generating Pokémon Zukan (Illustrated Guide) Style Art

infographic-edu-visual

The user generated Pokémon Zukan-style illustrations of their characters using Nano Banana (not Pro) to celebrate Pokémon's 30th anniversary. The prompt is shared in the ALT text.

展开提示词全文
Referencing this character, generate a Pokémon Zukan-style illustration. The Zukan No. is {argument name="Zukan Number" default="[Enter Zukan No.]"}. The background is white. The Zukan description text is {argument name="Description Text" default="[Enter description text]"}. Reproduce the Zukan layout and design.

Infographic Creation with Simple Text Prompt

infographic-edu-visual

A simple text prompt used with Adobe Firefly Boards and Nano Banana 2 (with Google Search enabled) to create an infographic about the 1969 Woodstock Festival.

展开提示词全文
Create an info graphic about the 1969 Woodstock Festival

Conceptual Isometric Office Tower Model

infographic-edu-visual

A prompt for generating a conceptual architectural isometric model (diorama style) of an organic-form corporate office tower, viewed from a top-down perspective, emphasizing fluid spatial flow, soft pastel colors, ribbed wood, and controlled studio lighting.

展开提示词全文
A conceptual architectural isometric model of an organic-form corporate office tower, presented as an exhibition-scale diorama. The building is shown with a cutaway section, exposing fluid spatial flow, curved meeting rooms, and lounge zoning from a top-down isometric perspective. Volumes are lightly separated by seamlessly curved translucent partitions to suggest circulation and function. Warm micro-LEDs illuminate the individual floors from within. Strong use of negative space and clear compositional hierarchy. Thin structural outlines, soft pastel lavender and mint, ribbed wood and dark terrazzo tones, minimal abstract signage, subtle human-scale markers. Smooth surfaces, pill-shaped rounded edges, dramatic controlled studio lighting, architectural model photography style, clean dark neutral background, high-detail yet minimal.

Infographic Generation with Chinese Text Support

infographic-edu-visual

A demonstration of Nano Banana 2's improved Chinese font support and integration of autonomous search, allowing for shorter prompts. The example prompt generates an infographic about using Openclaw + Obsidian for a personal second brain/productivity tool.

展开提示词全文
Design an infographic explaining how Openclaw + Obsidian can create a personal second brain + productivity tool. Output in Chinese, handwritten font. Gen-Z Aesthetic style.

Sports Equipment Infographic Layout of Victor Osimhen

infographic-edu-visual

A complex JSON prompt for creating a 3:4 vertical sports equipment breakdown infographic layout featuring Victor Osimhen. The left panel displays product images (mask, jersey, cleats) on a premium ivory background, while the right panel shows an authentic smartphone photograph of Osimhen celebrating a goal.

展开提示词全文
{
  "Objective": "Create a 3:4 vertical sports equipment breakdown layout of Victor Osimhen with a more visually appealing and premium left panel design.",
  "AspectRatio": "3:4",
  "Layout": {
    "Type": "Vertical split infographic",
    "LeftPanel": {
      "Width": "38%",
      "Background": {
        "BaseColor": "Soft warm ivory",
        "Texture": "Subtle luxury paper texture",
        "Overlay": "Very light gradient from top left (brighter) to bottom right (slightly darker)",
        "AccentElements": [
          "Faint abstract stadium-light glow in background",
          "Soft diagonal shadow for depth"
        ]
      },
      "LightingStyle": "Soft studio lighting from upper left",
      "ShadowStyle": {
        "UnderItems": "Soft drop shadows beneath each product",
        "SideShadow": "Gentle panel shadow near split line for dimensional separation",
        "Realism": "Natural soft shadows, not harsh"
      },
      "ItemsDisplayedAsImages": true,
      "ItemPresentation": {
        "Layout": "Vertical stack with breathing space",
        "CardStyle": "Each item slightly elevated with subtle shadow",
        "Spacing": "Balanced luxury spacing between elements"
      },
      "Items": [
        {
          "ItemName": "Protective Face Mask",
          "ImageStyle": "Isolated product image floating slightly with soft shadow",
          "TextPlacement": "Centered underneath in refined typography"
        },
        {
          "ItemName": "Galatasaray Home Jersey",
          "ImageStyle": "Front-facing flat-lay with realistic fabric texture",
          "TextPlacement": "Centered underneath"
        },
        {
          "ItemName": "Match Shorts",
          "ImageStyle": "Clean product cut-out with depth shadow",
          "TextPlacement": "Centered underneath"
        },
        {
          "ItemName": "Elite Football Cleats",
          "ImageStyle": "Angled product shot with subtle reflective shadow",
          "TextPlacement": "Centered underneath"
        },
        {
          "ItemName": "Performance Socks",
          "ImageStyle": "Minimal isolated display with soft grounding shadow",
          "TextPlacement": "Centered underneath"
        }
      ],
      "Typography": {
        "Font": "Modern elegant sans-serif",
        "Weight": "Medium",
        "Color": "Deep charcoal",
        "Spacing": "Generous letter spacing for premium feel"
      }
    },
    "RightPanel": {
      "Width": "62%",
      "ImageStyle": "Smartphone photograph",
      "Scene": {
        "Subject": "Victor Osimhen celebrating a goal",
        "Action": "Running with a smile, slight fist pump",
        "Location": "Football pitch",
        "Lighting": "Natural stadium lighting",
        "Background": "Crowd naturally blurred",
        "Realism": "Authentic phone camera clarity"
      }
    }
  },
  "VisualStyle": {
    "OverallLook": "Premium modern sports editorial",
    "Dept

Technical Architectural Blueprint of KÖFTE & PATATES

infographic-edu-visual

A highly detailed, structured prompt for Gemini Nano Banana Pro, requesting a hyperrealistic image of the Turkish dish Köfte & Patates rendered as a technical architectural blueprint. It specifies colors, lighting, labeling (CAD style), ingredients, and mood, aiming for clinical precision and appetite appeal.

展开提示词全文
Technical architectural blueprint of KÖFTE & PATATES on deep navy blue drafting paper #0A1628. Hyperrealistic photorealistic food hero centered and dramatically lit — warm studio spotlight from upper left, soft fill from right, visible steam wisps and sauce drips frozen mid-motion in full color. Food rendered with obsessive detail: glistening textures, visible moisture, char marks, melting elements catching light. Blueprint linework in crisp electric blue #4A90D9 — precise measurement lines, dimension arrows, cross-section callouts, grid overlay, compass rose bottom-left, scale bar bottom-center, revision block top-right.
LABELS: Each ingredient connected by a thin glowing electric blue line with a sharp 90-degree elbow joint — exactly like a professional CAD drawing. Label text in bright white Helvetica Neue Light uppercase, ingredient name bold, descriptor below in thin italic: "INGREDIENT NAME — qty: X — preparation method, texture descriptor, origin".
Food positioned left-of-center. All labels clustered right side and top, lines fanning outward cleanly with no crossovers.
Main components from top to bottom:
- PİDE EKMEĞİ — butter-toasted, golden edges, 110mm DIA. sesame-sprinkled optional.
- DOMATES DİLİMLERİ — vine-ripened, jewel-red, thick-cut 8mm THICK.
- SOĞAN HALKALARI — thinly sliced, sharp, translucent.
- KÖFTE — qty: 3-4 — 80g each, hand-minced dana kıyma + baharat (kimyon, pul biber, soğan rendesi, maydanoz), grilled/charred edges, juicy center, 90mm DIA smashed style.
- PATATES — qty: generous portion — ince uzun kesilmiş, double-fried, extra crispy exterior, fluffy interior, golden-brown, 120mm length avg.
- ZEYTİNYAĞLI SALÇA SOS / ACUKA — tangy-spicy, rich red, drizzled 25g.
- MAYDANOZ & SUMAK — fresh green, bright red dusting.
Bottom-right title block with double border: "DISH: KÖFTE & PATATES TABAK // CLASSIFICATION: TÜRK EGE USULÜ // BUILD SPEC: çıtır çıtır patates, sulu köfte, tam kararında pişmiş, bağımlılık garantili."
Mood: NASA food engineering meets Michelin lokanta — clinical precision with irresistible appetite appeal. Dramatic, extraordinary, craveable. 4K, tack sharp, electric blue linework glowing softly, warm food tones popping against cool navy.

Nano Banana 2 Feature Showcase (Cooking Instructions)

infographic-edu-visual

A detailed showcase of Nano Banana 2 (Gemini 3.1 Flash Image) features, including high quality at Flash speed, accurate text rendering, and character consistency. The example prompt provided is a set of cooking instructions rendered in a colored pencil style.

展开提示词全文
Wipe the oil off the surface of the deep-fried tofu with a paper towel. This saves the trouble of boiling water to remove the oil. Then, cut it into bite-sized squares with a knife.

16 Decades of Fashion Portrait Grid Prompt

infographic-edu-visual

A complex prompt instructing the generation of a 4x4 grid of portraits featuring the same female model styled across 16 different decades, from the 1880s to the 2020s, requiring era-accurate styling, photography techniques, and consistent model identity.

展开提示词全文
Create a 4×4 portrait grid of the same female model styled across 16 different decades from the 1880s to the 2020s. Row 1 – 1880s → 1910s: Victorian and Edwardian silhouettes, high-neck dresses, lace detailing, period-accurate hairstyles, sepia or monochrome tone. Row 2 – 1920s → 1950s: Flapper-style drop-waist dress (1920s), satin bias-cut slip dress (1930s), structured mid-century fashion (1940s), elegant suburban 1950s outfit. Black-and-white or muted analog tones. Row 3 – 1960s → 1990s: 1960s mod dress, 1970s bohemian look, 1980s colorful aerobics/casual style, 1990s grunge or minimalist polka-dot aesthetic. Row 4 – 1990s/2000s/2020s: Late-90s Y2K crop top/low-rise look, early-2000s glossy editorial, 2020s modern minimalist or clean streetwear. Include era-accurate hairstyles, makeup, and lighting. Each portrait should feel like a real photograph from its decade — matching film grain, color profiles, lenses, and studio backgrounds. The model’s face, identity, and proportions must stay consistent in all 16 portraits. High-resolution, editorial-quality rendering.

Anthropomorphizing LLMs

infographic-edu-visual

A prompt used to generate images of anthropomorphized LLMs (ChatGPT-5.2 think, Gemini 3.1 pro, Claude, Grok) with specific expressions and poses. The first image was generated by Nano Banana Pro, the second by ChatGPT.

展开提示词全文
Extremely anthropomorphize ChatGPT-5.2 think, Gemini 3.1 pro, Claude, and Grok, characterizing them with creative expressions and poses, and arranging them in an image.

Fake News Image Creation Prompt

infographic-edu-visual

A prompt for Nano Banana Pro to create a fake news image based on a screenshot of the user's X post. The prompt specifies text overlays for a watermark, headline, and scrolling text.

展开提示词全文
Create a fake news image introducing the reference image.
Add the watermark text "FAKE NEWS" in the upper left corner of the screen. 
Add the headline "Rapid increase in young people aiming for FIRE (Financial Independence, Retire Early)" in the upper right corner of the screen. 
Add the scrolling text "Even investors aiming for FIRE at age 5 have appeared" at the bottom of the screen.

Technical Infographic Template for Objects

infographic-edu-visual

A template prompt for creating a technical infographic of any object, using a 45-degree isometric 3D perspective, combining photorealism with black ink annotations and color-coded arrows for function/flow.

展开提示词全文
Create a technical infographic of {argument name="object name" default="[OBJECT NAME]"} with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension.
Combine a realistic photoreal render with black ink technical annotations on pure white background. Include:
Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections
Measurements, dimensions, and precise scale markers Material callouts and quantities 
Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics)
Simple schematics or cross-sectional diagrams where relevant 
Place “OBJECT NAME” title in a hand-drawn technical box (top-left corner).
Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space.
Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual.
Colors: ~10–15% accent density. Black dominant. White background.
Output: 1080×1080, ultra-crisp, social-feed optimized.

Architectural Tiramisu Cross-Section

infographic-edu-visual

A highly specific prompt for generating a hyperreal, architectural food photograph of a tiramisu cross-section, detailing visible layers, textures, lighting (dramatic left side lighting), and labeling the ingredients like a scientific illustration, inspired by Wes Anderson aesthetics.

展开提示词全文
Perfect cinematic cross-section cut through a tiramisu, sliced cleanly down the center, cut face straight-on to camera like a geological flavor diagram. Clearly visible layers: cocoa powder dusting, mascarpone cream, espresso-soaked ladyfingers, mascarpone cream base — each layer labeled with thin horizontal line to the right, uppercase sans-serif ingredient name with italic descriptor below. Flat matte neutral beige background. Dramatic left side lighting casting long shadows, single warm spotlight illuminating the cut face. Hyperreal textures — visible cocoa dust, creamy air pockets, soaked sponge structure, slight moisture and softness. Mood: architectural food photography meets scientific illustration. Title “TIRAMISU” in large elegant type at top. Subtitle: “Layers of Espresso & Cream.” 4K, tack sharp, Wes Anderson symmetry meets Michelin-star kitchen.

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。