← 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

Cinematic Urban Night Street Portrait Prompt

product-marketing

A highly detailed, structured JSON prompt for Gemini Nano Banana Pro, designed to generate an ultra-realistic, cinematic urban night street portrait featuring two subjects standing in front of Mercedes G-Wagons with strong headlight backlight, fog, and wet reflective surfaces.

展开提示词全文
{
  "image_generation_task": {
    "metadata": {
      "genre": "Urban Night Street Portrait",
      "style": "Ultra-realistic, cinematic, high-definition",
      "lighting": "Foggy night lighting, strong car headlight backlight, soft ambient city glow"
    },
    "scene": {
      "setting": {
        "location": "Empty city street at night",
        "background_elements": [
          "modern buildings on both sides",
          "street lights creating bokeh",
          "wet reflective road surface",
          "light fog enhancing depth"
        ]
      },
      "subjects": [
        {
          "label": "Person A",
          "position": "standing in front of a {argument name="car color 1" default="blue"} Mercedes G-Wagon",
          "clothing": {
            "top": "oversized beige t-shirt",
            "bottom": "black joggers",
            "shoes": "white sneakers"
          },
          "pose": "relaxed stance, arms by side, looking at camera"
        },
        {
          "label": "Person B",
          "position": "standing in front of a {argument name="car color 2" default="black"} Mercedes G-Wagon",
          "clothing": {
            "top": "bright neon green hoodie",
            "bottom": "black joggers",
            "shoes": "white sneakers"
          },
          "pose": "confident stance, hands relaxed, facing camera"
        }
      ],
      "vehicles": [
        {
          "model": "Mercedes G-Wagon",
          "color": "Blue",
          "lights": "headlights on, emitting strong beams through fog"
        },
        {
          "model": "Mercedes G-Wagon",
          "color": "Black",
          "lights": "headlights on, casting dramatic rim light"
        }
      ],
      "camera": {
        "angle": "eye-level wide shot",
        "lens": "35mm",
        "depth_of_field": "shallow, with cinematic bokeh",
        "vibe": "moody, powerful, urban cinematic"
      }
    }
  }
}

Font Change Prompt

product-marketing

A simple prompt used within a compositor workflow to instruct Nano Banana Pro to change the font of an existing image element to a specific style (Bebas Neue Pro/Signia Pro thick) and then transform the image into a rap CD cover.

展开提示词全文
change the font to {argument name="font name" default="Bebas Neue Pro/Signia Pro thick"} -- free fonts 🤷‍♂️

Make it a rap cd cover

Layered Acrylic Artwork Product Photography

product-marketing

A highly specific prompt for generating product photography of an illustration reconstructed using ultra-clear, highly luminous tinted acrylic sheets. It mandates strict preservation of the original art style, detailed composition rules (base panel, metallic standoffs, clear margin), and material physics rules for light transmission and color. The lighting must be strong and cool, casting bright, glowing, highly translucent colorful caustics onto the wall.

展开提示词全文
Product photography, perfectly straight-on frontal view. CRITICAL: The original art style, linework, and character features of the input illustration MUST BE STRICTLY PRESERVED. Do not abstract or simplify the drawing itself.

The artwork is a physical multi-layered construction mounted on a white wall.
**COMPOSITION RULE:**
1. The aspect ratio and orientation of the final product photography should match the dimensions of the input source image.
2. A large clear base panel is secured with visible metallic standoffs.
3. Crucially, the entire die-cut illustration (all layers) MUST be contained entirely within the boundaries of this base panel.
4. There should be an appropriate clear margin between the edges of the illustration and the edges of the base panel.

**MATERIAL PHYSICS RULE (HIGH TRANSMISSION):**
On top of the base, the illustration is reconstructed using **ultra-clear, highly luminous tinted acrylic sheets** designed for maximal light transmission.
1. The colors are the color of the transparent material itself (glass-like), not painted.
2. **For Skin/White Areas:** MUST be **pure, colorless, ultra-clear glass-like acrylic**.
3. **For Colored Areas (Hair/Clothes):** Use **highly translucent colored acrylic**. The color is vibrant but extremely see-through, allowing significant light to pass.

**LIGHTING & SHADOWS:**
Strong cool diagonal lighting passes through the highly transparent artwork. **Instead of creating dark or heavy shadows, the light casts bright, glowing, highly translucent colorful caustics onto the wall, showing the wall's texture underneath.** The shadow area should feel light and airy, revealing the original colors as bright projections. 8k resolution, ultra-detailed.

Surreal deep sea storage illusion prompt

product-marketing

A prompt for Nano Banana Pro that creates a surreal illusion of a subject lifting a wave like a carpet to reveal an object lying deep underneath, suggesting a transition from cloud storage to deep sea storage.

展开提示词全文
A {argument name="subject" default="SUBJECT"} is crouching on the beach, lifting a wave like a carpet to reveal a {argument name="object" default="OBJECT"} lying underneath deep inside. The ocean is calm with a clear blue sky in the background. The scene creates a clever illusion, in a surreal manner, with the wave being lifted as if it is a tangible object

Monochromatic Snowy Forest Fashion Shoot

product-marketing

A highly structured prompt for Nano Banana Pro detailing a fashion shoot in a snowy forest, emphasizing a vertical triptych composition, a cold monochromatic palette (white, silver, bluish-gray), and a model wearing luxurious white fur earmuffs and coat, with specific details like frost on false eyelashes.

展开提示词全文
/ Fashion shoot in a snowy forest.
• Composition: Vertical triptych, focus on the model and details of her look.
• Color Palette: Cold, monochromatic, mainly white, silver, bluish-gray.
• Mood: Mysterious, majestic, cold, pure.
 2. Model Description
• Gender/Age: Young woman, model-like.
• Hairstyle: Long wavy hair, top braided, bottom loose.
• Skin: Smooth, porcelain.
• Eyes: Bright light blue or gray, expressive makeup.
• Feature: False eyelashes with frost/snowflake crystals.
• Eyebrows: Light, neat.
• Lips: Full, nude or pale pink.
 3. Clothing and Accessories
• Key Accessory: Large fluffy white fur earmuffs, fully covering ears.
• Outerwear: Luxurious white coat or fur coat with high, voluminous collar. Soft, expensive-looking (natural or faux fur).
 4. Environment and Background
• Location: Snowy forest, dark tree trunks, snow-covered branches.
• Weather: Heavy, large snowflakes.
• Lighting: Soft diffused daylight, cloudy winter day or twilight.
 5. Frame Details
• Top: Close-up of face and shoulders, f

Mockup generation prompt for screen replacement

product-marketing

A prompt designed for creating high-quality mockups by instructing the AI to place a website image (second photo) onto the screen of a computer (first photo), replace the background to match the website's aesthetic, and change the table material.

展开提示词全文
"Place the website in the second photo onto the screen of the computer in the first photo. Replace the background with something that fits the aesthetic and style of the website. Maybe an office looking out at grassy mountains and hills. Change the table to something more like white oak or aluminum."

Hidden Word Embedding Prompt

product-marketing

A clever prompt for Nano Banana Pro designed to embed a specific word, '{argument name="word to hide" default="Toolfolio"}', into an image composition (a group of dogs on a farm) so subtly that it is difficult to spot without close inspection.

展开提示词全文
Make a photo with a hidden word embedded into it, make the word hard to see until you spot it, then you can't unsee it. Use the word "{argument name="word to hide" default="Toolfolio"}". Form the word out of a group of dogs in a farm. Make the word so hard to see that I can't spot it without squinting my eyes.

JSON prompt for construction site AR blueprint overlay

product-marketing

A structured JSON prompt for generating an editorial-style image of a construction site, where an uploaded subject holds up a holographic architectural blueprint projection over the unfinished structure, detailing the scene, subject, overlay object, and technical camera settings.

展开提示词全文
{
 "promptDetails": {
 "description": "A construction site scene with the uploaded subject holding up an AR projection of a blueprint over the unfinished structure.",
 "styleTags": [
 "Industrial",
 "Modern Architecture",
 "Midday Light",
 "Technical Schematics"
 ]
 },
 "scene": {
 "background": {
 "setting": "The top floor of a new skyscraper under construction (exposed concrete and rebar)",
 "details": "Distant city skyline visible through open walls, safety netting, hard hats, dust motes in the air, strong texture of raw concrete floor."
 },
 "subject": {
 "description": "The person defined by `[UPLOADED IMAGE]`, wearing a safety vest and hard hat, looking professional.",
 "pose": "Standing near the edge, holding an invisible tablet (or hand outstretched) projecting the overlay, looking critically at the structure.",
 "focus": "Subject and the projected blueprint are sharp; the background city is slightly softened."
 }
 },
 "overlayObject": {
 "type": "Holographic Architectural Blueprint",
 "relationshipToEnvironment": "The overlay appears as a complex, translucent blue-line schematic *over* a section of the exposed rebar/wall.",
 "transform": "Slightly angled in 3D perspective to match the construction site's structure.",
 "surfaceInteraction": "Vibrant, electric blue lines with sharp white measurements, casting a subtle blue light onto the subject's vest and concrete floor.",
 "components": {
 "section": "Load-Bearing Wall A-4",
 "measurement": "Height: 4.2m +/- 0.01m",
 "position": "Projected mid-frame, aligned with the structure."
 }
 },
 "technicalStyle": {
 "aspectRatio": "16:9",
 "photographyStyle": "Editorial, High Detail, Commercial",
 "camera": {
 "shotType": "Medium Shot",
 "angle": "Eye-level, dynamic composition emphasizing vertical lines.",
 "depthOfField": "Moderate, ensuring the raw background textures are visible but not distracting."
 },
 "lighting": {
 "type": "Harsh, Clear Midday Sun",
 "description": "Strong, directional sunlight creating sharp shadows and bright highlights on metal and concrete."
 },
 "color": {
 "palette": "Concrete grays, safety vest orange/yellow, and electric blue."
 }
 }
}

Basic Product Shot Prompt for Moving Parts

product-marketing

A simple prompt for generating product shots of a robot using Nano Banana Pro, specifically instructing the AI to show the robot in a pose doing something with its arms to ensure consistency across different outputs, particularly for parts that move.

展开提示词全文
show the robot in a pose doing something with it's arms

Image prompt for a whimsical, high-detail, 3D rendered banana character

product-marketing

This is an image generation prompt for a 3D rendering of a whimsical banana character. The prompt specifies a high level of detail, a cute style, and a specific lighting setup (cinematic, volumetric light) to achieve a visually striking and professional result.

展开提示词全文
A whimsical banana character, cute, high detail, 3d render, cinematic volumetric light, octane render, unreal engine, 8k, hyper detailed, professional photography

Product Shoot Prompt for Advertising

product-marketing

This is an image generation prompt used for a product shoot advertisement comparison between Seedream 4.2 and Nano Banana Pro 2K. The prompt describes a high-end, professional product photography setup featuring a luxurious, minimalist aesthetic with a focus on lighting and texture.

展开提示词全文
Professional product photography, high-end advertising, luxury, minimalist, clean background, soft studio lighting, focus on texture and detail, sharp, hyper-realistic, 8k, a single {argument name="product name" default="sleek black object"} on a polished marble surface, subtle reflections, dramatic shadows, cinematic composition, depth of field, neutral color palette, commercial style

JSON prompt for high-end beach fashion photography

product-marketing

A highly structured JSON prompt designed to generate a photorealistic, professional full-frame camera beach photoshoot image of an elegant woman in a stylish bikini, detailing composition, subject attributes, environment, lighting, and camera settings.

展开提示词全文
{
  "intent": "Generate a photorealistic professional full-frame camera beach photoshoot image featuring an elegant woman posing along a sunlit shoreline in a stylish bikini.",
  "frame": {
    "aspect_ratio": "9:16",
    "composition": "Vertical fashion-portrait, three-quarter standing pose captured from a slightly low angle. Natural wide perspective with soft shallow depth of field.",
    "style_mode": "high_end_fashion_photography, professional_full_frame_raw_capture"
  },
  "subject": {
    "identity": "A young adult woman styled for a modern beach fashion photoshoot.",
    "physical_attributes": "Sun-kissed skin with an even warm glow. Smooth complexion, expressive eyes catching sunlight, subtle natural makeup, soft glossy lips. Long hair styled in loose beach waves moving gently with the wind.",
    "expression": "Relaxed, confident smile with direct eye contact toward the camera.",
    "wardrobe": "A elegant two-piece bikini in a warm neutral tone ({argument name="bikini color" default="sand beige or soft cream"}). The top has clean, minimalistic lines with a supportive fashion-forward cut. The matching bikini bottoms have a tasteful, modern high-waisted style. A sheer white beach cover-up or sarong drapes loosely from one hand for added movement.",
    "accessories": "Simple gold hoop earrings, a minimal braided anklet, and a thin wrist cord bracelet.",
    "pose": "Standing at the shoreline with one foot in shallow water. Right hand lightly holding her cover-up, left hand brushing hair away from the face. Confident, natural runway-model posture."
  },
  "environment": {
    "location": "A bright tropical beach with turquoise water and smooth golden sand.",
    "architecture": "No buildings; distant palm trees and soft rock formations blurred in the background.",
    "atmosphere": "Clear sky, warm midday sunlight, gentle breeze giving movement to hair and fabric.",
    "details": "Soft ocean waves rolling behind her, shimmering reflections on water, subtle natural lens flare from the sun angle."
  },
  "props": {
    "main": "A lightweight sheer beach cover-up creating movement when lifted by the wind.",
    "side": "A woven beach tote set gently in the sand.",
    "additional": "Scattered seashells and driftwood pieces naturally present on the shore."
  },
  "lighting": {
    "type": "Direct natural sunlight with high dynamic range RAW capture.",
    "source": "Primary: Midday sun at approx 5500K. Secondary: Warm reflected fill from sand and cool ocean blue bounce light.",
    "color_temperature": "Warm, balanced daylight on skin with cooler water reflections adding dimensionality.",
    "quality": "Crisp highlights, soft shadows, subtle rim-lighting on hair and shoulders."
  },
  "camera": {
    "model": "Canon EOS R5 (Professional Full-Frame Mirrorless)",
    "sensor_format": "45MP Full-Frame CMOS sensor with 14-bit RAW output.",
    "lens": "Canon RF 50mm f/1.2L USM portrait lens.",
    "settings": "Aperture f/2.0, ISO 100, Shutter Speed 1/2500"
}
上一页 467 / 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。