← 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 725 条

Isometric Photo Generation Prompt

game-asset

A specific image generation prompt for Nano Banana Pro designed to create a photograph with a perfectly isometric perspective, emphasizing that the image should look like a captured photo rather than a miniature model. It includes instructions to apply a tilt-shift effect at the end.

展开提示词全文
Make a photo that is perfectly isometric. It is not a miniature; it is a captured photo that just happens to be perfectly isometric. It is a photo of {argument name="subject" default="[subject]"}. Apply tilt-shift effect at the end.

Royal Cartographer Fantasy World Map Prompt (Detailed Scenario)

game-asset

A highly detailed system prompt for Nano Banana Pro Agent V1.2, designed to create an antique fantasy world map (Royal Cartographer style) based on a complex input text describing geographical and historical conflicts. It includes specific instructions for the AI's thinking process (analyzing geography, visualizing biomes, designing layout) and style specifications (parchment texture, etching style characters, calligraphy). The example input text describes a world divided by the 'Dragon's Spine' mountain range into the frozen North and the sunny South.

展开提示词全文
You are a legendary Royal Cartographer.
Deeply analyze the content of the input text provided at the end and generate a detailed and beautiful image of a 'Fictional World Map' that reflects historical background and geographical features.

In doing so, incorporate the attached reference character into the map using the style of an old map's pen drawing or watercolor, placing them as a 'Guardian of the World' or 'Symbolic Portrait' decorating the map's margins, compass rose, or legend. Maintain character consistency while naturally blending them into the map design.

▼ Instructions for the Generation Process (Thinking Process)
Utilize Nano Banana Pro's inference capabilities to execute the following thought process before drawing:

1.  [Step 1: Analysis of Geographical and Historical Correlation]: [Extract the conflict structure between nations, the formation of civilizations, and climatic conditions from the input text. Logically infer why borders exist there (mountains, rivers, resources)]
2.  [Step 2: Visualization of Biomes]: [Determine how the described terrain (e.g., forest filled with magic, desolate wasteland) should be represented using map symbols and colors (ink density, contour lines)]
3.  [Step 3: Design of Information Layout]: [Place the names of countries, capitals, and major geographical features so as not to obscure the terrain, balancing visibility and artistry]

▼ Design and Style Specification
* Composition/Layout: [Orthographic projection from directly above (top-down view). A detailed overall map written meticulously to the four corners of the paper]
* Taste: [Antique fantasy map style drawn on parchment. Aged paper texture, handwritten ink lines, and coloring with pale watercolors]
* Text: [Clearly place country names and major city names using a serif font suitable for the world setting (Japanese compatible). The title should be written in decorative calligraphy]
* Character: Draw the reference character in an [etching (copperplate engraving) style] and specify a [pose pointing to the map's 'Legend,' or a composition integrated with the compass rose].

▼ Input Text

Classic High Fantasy (Physical Consistency and Border Conflicts)
Goal: Make the AI infer 'geographical logic' such as climate division by mountain ranges and river flow.

World Setting: The world is divided into North and South by the gigantic mountain range 'Dragon's Spine' running east-west across the center of the continent.

Northern 'Glacies, the Empire of Ice':

Climate: Extreme cold, permafrost.

Terrain: Steep glaciers and coniferous forests.

Capital: The fortress city 'Winter's Fang' at the foot of the mountain range.

Southern 'Solaris, the Kingdom of the Sun':

Climate: Warm and fertile land.

Terrain: The great river 'River of Life' flowing from the mountain range irrigates vast plains and flows into the southern sea. A vast desert spreads to the west.

Capital: The water city 'Aurora' in the river delta.

Instructions for the Map:

Write the country names '氷の帝国グラキエス' (Glacies, the Empire of Ice) on the north side and '太陽の王国ソラリス' (Solaris, the Kingdom of the Sun) on the south side of the map in large Japanese text.

Draw the central mountain range, river flow, and desert locations correctly geographically.

Draw decorations symbolizing the Four Great Spirits of this world (Fire, Water, Wind, Earth) in the four corners of the map.

3D Dance Game Screen Prompt for Nano Banana Pro

game-asset

A detailed image generation prompt to create a screenshot of a 3D dance game, featuring a character based on a reference image, specific UI elements, lighting, and camera angles, designed to look like an immersive arcade rhythm game.

展开提示词全文
A vibrant rhythm game screenshot featuring a 3D anime character from the reference photo.
[{argument name="character description" default="Girl wearing a cloak"}]

Maintaining a confident dance pose on the left side of the screen.
Immersive cinematic lighting glowing in neon yellow and pink
Glossy, reflective dance floor shining under a spotlight
Dynamic 3D anime style.

Immersive UI rhythm game screen: no reflection display
Score display at the top
Colorful music waveform animation synchronized with the beat
Stage timer countdown
Floating combo numbers
Energy bar
Neon particle effects
Four falling button instruction arrows from top to bottom on the right side of the screen
Button arrow direction and color are fixed for each column (Left: Red, Up: Blue, Down: Green, Right: Yellow)

Highly detailed game atmosphere created with immersive arcade rhythm game HUD elements
Ultra-detailed, cinematic, immersive, 3D animation.

Two-Step Power Release Transformation Prompt (Japanese)

game-asset

A complex, two-step Japanese prompt for transforming a character's pose into an 'Awakening Stance' and then generating a 'Power Release' effect, where energy spheres expand and the ground/walls are dramatically excavated or destroyed. It uses structured JSON-like input for precise control over composition, action, and style, requiring a reference image of the character.

展开提示词全文
[Awakening Pose Prompt]
subject: >
  Use the same character as reference A.
  Preserve all facial features, hairstyle, clothing, body proportions, colors,
  line weight, shading, and art style exactly as in the reference.

composition: >
  IMPORTANT: Change the framing from the reference.
  The camera must be positioned **much farther away** so the character’s entire body
  is fully visible **with extra space above, below, and around** the character.
  The character must appear **significantly smaller** than in reference A,
  occupying only about **20–30% of the frame height**.
  Place the character exactly at the center of the frame with wide open space
  surrounding them for later energy effects.
  The field of view should be noticeably wider than the reference.
  The final image must be rendered in a **16:9 aspect ratio**.

action: >
  Set the character in the awakening stance shown in reference B:
    - feet shoulder-width apart
    - both hands tightly clenched into fists
    - arms slightly bent and tense
    - chest slightly forward, posture firm and braced
    - intense, focused expression

location: >
  Reuse the same background environment as reference A.
  Expand the visible portion of the background **significantly**
  to match the widened, zoomed-out framing.
  Maintain the same textures, perspective, colors, and drawing style.

style: >
  Match the exact style of reference A:
  identical linework, shading, coloring, and background rendering.

camera_lighting: >
  Use the same lighting conditions as in reference A.

edit_instructions: >
  Recreate the character and background from reference A exactly.
  BUT modify the camera distance so the entire character fits in the frame
  with **substantial space** around them.
  The camera should be pulled back enough that the character appears small
  within a much wider environment.
  Change only:
    - the camera distance (strong zoom out)
    - the char

Isometric 3D Miniature Room with Chibi Character

game-asset

A detailed template prompt for generating an isometric 3D miniature room (a true cube cutaway) featuring a chibi-style figurine character. It requires the user to describe the room, the character's appearance (based on an uploaded photo), action, expression, lighting, and technical camera details to ensure a photorealistic, clean composition.

展开提示词全文
An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is [{argument name="room description" default="ROOM DESCRIPTION: Describe the theme, furniture, specific clutter, wall decorations, and key items in detail"}].
Character: a chibi/figurine-style — [{argument name="character description" default="INSERT DESCRIPTION OF THE PERSON FROM YOUR UPLOADED PHOTO HERE"}]. The character is [{argument name="action" default="ACTION: e.g., sitting on a chair typing, standing and cooking, playing guitar"}], with a [{argument name="expression" default="EXPRESSION: e.g., focused, happy, smiling"}] expression. Figure material looks like matte PVC, with big head / small body proportions. Lighting: [{argument name="atmosphere name" default="ATMOSPHERE NAME"}]: [{argument name="light sources" default="LIGHT SOURCES: e.g., neon blue glow, warm sunlight, golden lamp light"}]; realistic reflections and colored shadows. Camera: slightly elevated isometric three-quarter view, front cube edge centered; no elements protruding outside the cube. Photoreal materials with fine detail; neutral backdrop. Ultra-detailed, clean composition; no watermark.

Cyberpunk Mountain Peak Girl

game-asset

A prompt for generating a cyberpunk sci-fi image of a girl standing on a neon-lit mountain peak, overlooking a futuristic world with holograms and glowing cities, using a neon blue and pink color palette.

展开提示词全文
{
  "prompt": "A beautiful girl standing on a neon-lit mountain peak overlooking a futuristic cyberpunk world. Holograms in the sky, glowing lights from distant cities, metallic textures, neon blue and pink colour palette.",
  "style": "cyberpunk sci-fi",
  "lighting": "neon rim light",
  "details": {
    "tech_elements": ["holograms", "light trails"],
    "mood": "bold, adventurous"
  }
}

Gritty Post-Apocalyptic Survivor Scene

game-asset

A prompt for generating a cinematic, hyper-realistic image of three armed survivors—a determined woman and two men—walking down an abandoned, decayed city street, emphasizing the gritty atmosphere, tactical gear, and dramatic lighting.

展开提示词全文
A gritty post-apocalyptic scene featuring three armed survivors walking down an abandoned, decayed city street. The central character is a determined woman with long dark hair, wearing tactical gear, cargo pants, and combat boots, carrying a pistol and rifle magazines on her vest. On her left is a bearded man with a tactical backpack and military clothing. On her right is a rugged man in a denim jacket holding a shotgun. The environment is ruined and overgrown with debris, broken cars, and damaged buildings under a cloudy, grey sky. Cinematic, dramatic lighting, realistic textures, intense atmosphere.

Super Robot Wars Style Witch Rejecting Friday

game-asset

A creative prompt based on a modified 'Super Robot Wars Battle Production' style prompt, generating an image of a witch named Marieshe Fold performing a special move called 'Friday Crash' with the catchphrase, 'Friday is not a holiday.'

展开提示词全文
Let's play with Nano Banana Pro 
[Improved Super Robot Wars Battle Production Prompt]

{argument name="character name" default="Marieshe Fold"}
Special Move Name: "{argument name="special move name" default="Friday Crash"}"
Catchphrase: "{argument name="catchphrase" default="Friday is not a holiday"}"

Image-to-Image Prompt for Character and UI Generation

game-asset

A three-step process prompt in Chinese for image generation, requiring the user to provide a character prototype and a mobile interface screenshot to be used alongside the prompt text.

展开提示词全文
1. Prepare the character prototype
2. Prepare the mobile interface screenshot
3. Send along with the prompt text

Transform Image into LEGO Version

game-asset

A prompt used to transform an existing image or concept into a LEGO version, specifically instructing the model to include typical LEGO features like yellow skin, shrunken size, square edges, and pixels.

展开提示词全文
"Make it in LEGO version. Include the typical LEGO features (yellow skin, shrunken person size, and square edges and pixels)"

Isometric 3D Miniature Room with Chibi Character Prompt

game-asset

A detailed prompt template for generating an isometric 3D cube-shaped miniature room scene, featuring a chibi-style character based on an uploaded photo. The prompt allows customization of the room's theme, the character's action and expression, and the specific lighting and atmosphere.

展开提示词全文
An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is {argument name="room description" default="[Describe the theme, furniture, specific clutter, wall decorations, and key items in detail]"}.
Character: a chibi/figurine-style — {argument name="character description" default="[INSERT DESCRIPTION OF THE PERSON FROM YOUR UPLOADED PHOTO HERE]"}. The character is {argument name="action" default="[ACTION: e.g., sitting on a chair typing, standing and cooking, playing guitar]"}, with a {argument name="expression" default="[EXPRESSION: e.g., focused, happy, smiling]"} expression. Figure material looks like matte PVC, with big head / small body proportions. Lighting: {argument name="atmosphere name" default="[ATMOSPHERE NAME]"}: {argument name="light sources" default="[LIGHT SOURCES: e.g., neon blue glow, warm sunlight, golden lamp light]"}; realistic reflections and colored shadows. Camera: slightly elevated isometric three-quarter view, front cube edge centered; no elements protruding outside the cube. Photoreal materials with fine detail; neutral backdrop. Ultra-detailed, clean composition; no watermark.

Dark fantasy portrait with metal lion mask

game-asset

An image generation prompt for Nano Banana Pro, creating an extreme close-up portrait with a dark fantasy aesthetic. The subject is a pale woman partially obscured by an intricately carved black metal lion helmet/mask, emphasizing dramatic low-key lighting, hyper-realistic metal textures, and a muted color palette.

展开提示词全文
Extreme close-up portrait of a pale young woman with freckled, dusty skin and ice-blue eyes, half of her face hidden behind an intricately carved black metal lion helmet/mask with detailed mane and golden accents, wearing an ornate blackened golden crown with gothic filigree and jewels, long reddish-brown hair partially visible, dramatic low-key cinematic lighting with strong rim light highlighting metal textures and dust on skin, muted desaturated color palette with gold and black dominance, dark fantasy atmosphere, hyper-realistic metal.

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。

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。

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。

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

海报设计工作室

免费增值需申请 Key

将一段活动描述、一张产品照片或品牌参考图,转化为抓人眼球的活动海报、宣传 banner 或社交媒体配图。这款 AI海报设计与制作工具生成图片丰富的海报,搭配清晰视觉层级、按品类匹配的风格和预留文字区域,覆盖活动、音乐节、电影、产品发布和促销场景。你可以把它当作 AI宣传单制作工具来制作促销宣传单,当作活动海报设计工具,当作电影海报生成器,当作音乐节海报设计工具,当作产品发布会海报的 banner设计 AI,或当作平面设计海报工作室。从活动主题出发,用品牌风格参考图变换产品或场景照片,或在已认可草稿上做定向精修,完成可印刷或可分享的成品。

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。