← 返回首页
技能

Ai Image Prompts

tencent_skillhub · 1.0.9 · 下载量 2,051 · 热度分 56.5

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 5717 条

Felt toy character prompt for Nano Banana Pro

product-marketing

A flexible template prompt for generating full-body felt toy characters in different places, lighting, and moods, ideal for cute, soft-looking illustrations.

展开提示词全文
Felt toys

Full body {argument name="subject" default="[Subject]"} toy, {argument name="attributes and accessories" default="[attributes/accessories]"}, {argument name="expression" default="[expression]"}, made of felt, in a {argument name="place" default="[place]"}, {argument name="lighting" default="[lighting]"}, with a friendly, cartoonish appearance and rich, soft textures.

Packaging mockup with tiny text test prompt

product-marketing

A concise English prompt used to test tiny text rendering and deep reasoning by asking Nano Banana Pro to generate a herbal tea box packaging mockup with accurate labels and instructions.

展开提示词全文
Packaging mockup for a herbal tea box, with an accurate nutrition label, barcode, and small-print brewing instructions.

Turn booth sketch into perspective drawing

product-marketing

A Nano Banana Pro prompt that takes a rough exhibition booth sketch and turns it into a usable perspective illustration for presentations.

展开提示词全文
Create a perspective drawing from the rough sketch of an exhibition booth.

Futuristic facial age-checker infographic portrait

product-marketing

A long, detailed prompt for creating a hyper-realistic portrait infographic that analyzes facial aging factors with overlays and labeled percentages, styled like a premium cosmetic-tech ad.

展开提示词全文
A hyper-realistic, high-resolution portrait infographic based on ({argument name="reference_photo_en" default="your photo"}). Keep the same person, identity, hairstyle, clothing, and natural skin tone from ({argument name="reference_photo_short_en" default="your photo"}), with a neutral studio background. Overlay a subtle, semi-transparent facial analysis grid over the entire face, similar to a 3D face-scanning mesh: thin, soft white lines following the facial contours, slightly glowing but not hiding the skin details. Add one clean vertical red laser line running down one side of the face, like a futuristic scan. All analysis lines must be soft, minimal, and elegant, exactly like a cosmetic-tech advertisement.

Create a clean medical–aesthetic infographic that evaluates 5 aging factors using global data percentages:
1. Fine lines and wrinkles
2. Skin texture and elasticity
3. Facial volume and sagging
4. Eye area aging signs
5. Skin tone and pigmentation

For each factor, place a small label with a thin line pointing to the relevant facial area, and next to it write a short title and a realistic percentage score from 0–100% (based on global data), for example:
“Fine lines & wrinkles – 18%”
“Skin texture & elasticity – 72%”
“Facial volume & sagging – 35%”
“Eye area aging signs – 41%”
“Skin tone & pigmentation – 63%”

Use clean, modern sans-serif typography and small technical-style text, like a scientific facial analysis UI. At the bottom of the image, in the center, write a large bold text showing the final estimated real age based on the analysis, for example:
“ESTIMATED AGE: (random number based on face analysis)”

Overall style: futuristic AI-guided skincare analysis, minimalistic, premium editorial lighting, no gender specified, suitable for any human face.

Technical exploded view diagram of a device

product-marketing

A reusable prompt template for creating labeled exploded view diagrams of any subject in a square format, useful for product breakdowns or educational visuals.

展开提示词全文
Create a technical exploded view diagram of a {argument name="subject_en" default="[SUBJECT]"} in {argument name="dimension_en" default="1080x1080"} dimensions. The device should be deconstructed, showing all individual components floating in space, separated to reveal the internal parts. Each major component is labeled.

Editorial denim portrait preserving face identity

product-marketing

A JSON-style prompt for creating an 8K editorial fashion portrait of a person in a denim outfit and shearling jacket, while keeping their face identical to the reference photo.

展开提示词全文
{
  "photo": {
    "type": "editorial_fashion_photo",
    "quality": "8k photorealistic",
    "lens": "50mm shallow depth of field",
    "composition": "medium portrait, editorial framing, no text, no watermark",
    "face": {
      "preserve_original": true,
      "reference_match": true,
      "description": "The model's face must remain 100% identical to the provided reference picture in all facial features, proportions, makeup style, and expression."
    },
    "model_pose": {
      "position": "seated",
      "legs": "relaxed pose with one leg bent",
      "hands": "one hand supporting the head",
      "expression": "calm, minimalist mood"
    },
    "wardrobe": {
      "jacket": {
        "type": "cream shearling jacket",
        "texture": "shaggy, fluffy, tactile"
      },
      "shirt": {
        "type": "denim shirt",
        "layered": true
      },
      "pants": {
        "type": "light blue jeans"
      },
      "boots": {
        "type": "black leather Chelsea boots",
        "texture": "smooth polished leather"
      },
      "socks": {
        "color": "beige"
      }
    },
    "textures": {
      "emphasis": [
        "fluffy shearling fibers",
        "rugged denim fabric",
        "smooth leather boots",
        "visible seams",
        "visible stitches"
      ]
    },
    "environment": {
      "backdrop": "clean light gray studio backdrop",
      "lighting": {
        "style": "soft natural studio lighting",
        "key_light": "gentle side key light",
        "fill_light": "subtle fill",
        "shadows": "soft shadows"
      }
    },
    "color_grade": {
      "type": "cinematic",
      "balance": "neutral warm-cool tone balance"
    }
  }
}

Knolling-style exploded flat-lay photo

product-marketing

A detailed prompt for turning any object into an ultra-realistic knolling-style 8K flat-lay image with labeled disassembled parts.

展开提示词全文
Ultra-realistic 8K flat-lay photo in strict knolling style. A top-down 90º shot of the object from the attached image, fully disassembled into {argument name="min_parts_en" default="8"}–{argument name="max_parts_en" default="12"} key parts and arranged in a clean grid or radial pattern on a minimalist {argument name="surface_material_en" default="wooden or matte gray"} table. Use even spacing, perfect alignment, no overlaps, and no extra objects. Light the scene with soft, diffused multi-source lighting, creating subtle shadows, neutral color balance, and crisp focus across the entire frame. Show highly detailed real-world materials (metal, plastic, rubber grips, circuit boards, screws). For every part, add a thin white rectangular frame and a short, sharp English label in clean sans-serif text, placed next to the component without covering it; annotations must be legible but unobtrusive.

High-angle fashion portrait on marble staircase

product-marketing

A detailed fashion portrait prompt for an Asian male model leaning on a marble staircase, preserving the reference subject’s facial features and specifying hairstyle, clothing, and pose, great for editorial-style shots or profile images.

展开提示词全文
High-angle fashion portrait of a {argument name="age_en" default="25-year-old"} {argument name="ethnicity_en" default="Asian"} man, with the same facial features as the man in the reference photo, messy hairstyle framing his face, leaning casually on a {argument name="stair_material_en" default="white marble"} staircase banister. He is wearing an oversized {argument name="shirt_colors_en" default="light blue and white"} plaid shirt over a

Header image with uploaded person introducing Nano Banana Pro

product-marketing

A structured Japanese prompt to recreate an uploaded person and place them in a 16:9 header image for a note article explaining Google’s Nano Banana Pro, using a simple white and blue style.

展开提示词全文
Fully recreate the uploaded person.
Create a note article header image where that person is introducing “Nano Banana Pro.”
Use a 16:9 horizontal size.
Style and colors: simple, italic, white and blue.
Title: “{argument name="title_en" default="In-depth guide to Google’s new AI ‘Nano Banana Pro’"}”.

Train-ad style book advertisement image

product-marketing

A detailed Japanese prompt for generating a 16:9 business-book-style advertisement featuring a specific book image with Japanese copy points.

展开提示词全文
Please generate an advertisement image.

==== Ad specifications ===
- Aspect ratio: 16:9 (horizontal)
- Product to advertise: the book in the first attached image
- Main eye-catcher: place the book from the first attached image in a three-dimensional way
- Language: Japanese
- Taste: advertisement for a business book

# Text to include:
- Pre-head copy: 【New print run decided about one week after release】

Book “{argument name="book_title_en" default="Designing from Zero with AI"}” now on sale and doing well.

Amazon Best Seller Ranking
Ranked No.1 in commercial design sales (as of 10/15)
https://t.co/QxbYpfFVj6

Luxurious header image with uploaded person for Nano Banana Pro article

product-marketing

A template-style Japanese prompt that recreates an uploaded person and places them in a luxurious, impactful 16:9 note article header for a Nano Banana Pro explainer.

展开提示词全文
Fully recreate the uploaded person.
Create a note article header image where that person is introducing “Nano Banana Pro” (do not display text about this part itself).
Use a 16:9 horizontal size.
Emphasize a luxurious feel, gradients, and impact, with italic styling.
Title: “{argument name="title_en" default="In-depth guide to Google’s new AI ‘Nano Banana Pro’"}”.

Clothing laid out separately on a bed

product-marketing

A short English prompt for generating an image where each piece of a girl’s clothing is placed separately on a bed.

展开提示词全文
Give each piece of her clothing separately on the bed.
上一页 473 / 477 下一页

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。一节课的讲解也能做成课程口播。

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。

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,在海报排版上搭配清晰视觉层级、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。

自动化克隆数字人口播混剪视频

免费增值需申请 Key

抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip

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。