Ai Image Prompts
Introduction
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。
Resource Information
License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.
Prompt Library · 22.8K
Source: community prompt library (MIT, synced daily)15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.
1099 matches
Frosted Glass Effect Prompt
othersA detailed Nano Banana prompt designed to transform an uploaded image so that it appears behind a heavily frosted glass panel, with only a small, clear window revealing sharp detail. The prompt specifies the visual effects, composition, and style for hyper-realistic optical simulation.
Show full prompt
You are a world-class visual effects designer and photographic compositor specializing in glass, refraction, and atmospheric diffusion. Your task is to transform the uploaded image so that it appears behind a thick foggy frosted glass panel, while keeping only a very small selected region crystal clear. INPUT IMAGE: [UPLOAD IMAGE] INSTRUCTIONS: • Cover the entire image with a realistic frosted glass / fogged glass texture • The glass should create heavy diffusion, grainy micro-distortion, and refractive blur • The effect should resemble bathroom privacy glass or heavily steamed window glass • The distortion must include: micro ripples refractive glass warping light scattering blurred shapes behind the glass • Only a very small area must remain perfectly clear a narrow horizontal opening or small window sharp, fully visible detail inside that region the rest of the image remains strongly diffused • The clear area should look like a wipe in the condensation or a cleaned patch on the glass GLASS EFFECT DETAILS: • high density frosted glass texture • strong diffusion and noise pattern • subtle depth refraction • irregular organic blur pattern • soft lighting scattering through the glass STYLE: • hyper realistic optical glass simulation • photographic quality • cinematic lighting • modern editorial design aesthetic COMPOSITION: • subject visible through glass • tiny clear window revealing key detail (eyes / face / object) • rest of the frame heavily frosted and distorted IMPORTANT: The frosted glass must look physically real, not a simple blur filter. The clear region must be sharp and untouched, creating strong contrast with the fogged glass surface.
Jirai-kei Girl with Claymore in Bamboo Forest
othersA prompt for the Nano Banana Pro image generator (Gemini 3) to create an image of a 'Jirai-kei' (landmine style) fashion girl holding an M18A1 Claymore landmine in a bamboo forest setting.
Show full prompt
a Jirai-kei fashion girl with an M18A1 (Claymore land mine) in the bamboo forest
Kangaroo-Inspired Single-Celled Organism
othersA prompt for the Nano Banana Pro image generator (Gemini 3.1) to create an image of a single-celled organism inspired by a kangaroo.
Show full prompt
a single-celled organism lifeform that is inspired by a kangaroo
Japanese Suburb in 2000s Atmosphere (Part 2)
othersA prompt used with Google Gemini 3.1's image generator, Nano Banana Pro, to create an image of a Japanese suburb with a nostalgic, old footage atmosphere from the 2000s.
Show full prompt
"a Japanese suburb in the the 2000s atmosphere that like an old footage"
Cinematic Chiaroscuro Portrait Prompt
othersA detailed image generation prompt designed for creating a high-contrast, monochromatic, cinematic close-up portrait. It specifies a strict side profile, downward gaze, dark textured clothing, and harsh Chiaroscuro lighting with a deep black background, focusing on analog film grain and micro-contrast on the skin.
Show full prompt
Image from {argument name="subject" default="subject"}, cinematic close-up, strict side profile view, looking downward with a pensive expression. Wearing a dark, textured garment. High-contrast Chiaroscuro lighting, deep black void background with no environmental details. Monochromatic black and white color grading with crushed shadows and brilliant highlights. Harsh side light source casting a sharp rim-light on the profile while leaving the frontal plane in deep shadow. Heavy analog film grain and high micro-contrast on skin texture, focusing on the interplay of light and shadow on smooth skin surfaces.
Comparison Prompt for Midjourney V8 and Nano Banana 2
othersA comparison between Midjourney V8 and Google Nano Banana 2 using a French prompt describing a man who embraces disaster and avoids effort to feel better.
Show full prompt
"A man who loves disaster. At no point would he want to make the effort to feel better, even though all he would need to do is increase his antidepressant dose or do yoga"
Generate Dynaman Great Explosion
othersA prompt for Nano Banana Pro based on the concept of 'Dynaman Great Explosion,' noting that the AI interpreted 'Dynamite' from the prompt.
Show full prompt
Dynaman Great Explosion Image style What is Dynamite? It felt like that... Dynaman interpreted as Dynamite lol
Brutalist Concrete Museum Interior
othersA prompt for Nano Banana 2 to generate an image of a Brutalist concrete museum interior, emphasizing sharp geometric shadows created by a single sunbeam through a skylight. The scene includes a monochromatic palette accented by one red sculpture, inspired by the architectural style of Tadao Ando.
Show full prompt
"Brutalist concrete museum interior, single sunbeam through skylight, sharp geometric shadows, monochromatic + one {argument name="accent color" default="red"} accent sculpture, {argument name="architectural style" default="Tadao Ando"} inspired"
Jolivet's Pachinko for Two Pianos
othersAn image generation prompt for Nano Banana Pro (Gemini 3 Pro Image) to create a cyberpunk image related to the composer Jolivet and his piece 'Pachinko for Two Pianos,' featuring Jolivet and his doppelgänger as pianists.
Show full prompt
{argument name="composer" default="Jolivet"} (Composer)
{argument name="piece" default="Pachinko for Two Pianos"}
The pianists are
Jolivet and Jolivet's
Doppelgänger
{argument name="style" default="Cyberpunk"}
Image generation for Jolivet's 'Pachinko for Two Pianos'
othersA prompt for Nano Banana Pro (using Gemini 3 Pro Image) to generate an image based on the musical piece 'Pachinko for Two Pianos' by André Jolivet, featuring Jolivet and his doppelgänger as pianists.
Show full prompt
Jolivet (Composer) Pachinko for Two Pianos The pianists are Jolivet and Jolivet's Doppelgänger
Mozart's Don Giovanni: The Last Supper
othersA prompt for Nano Banana Pro (Gemini 3 Pro Image) to generate an image based on Mozart's opera Don Giovanni, specifically depicting 'The Last Supper,' likely featuring characters like Don Giovanni, Leporello, and the Commendatore's ghost.
Show full prompt
Mozart
Don Giovanni
{argument name="scene" default="The Last Supper"}
Mozart's Dies Irae Image Generation
othersA prompt for Nano Banana Pro (Gemini 3 Pro Image) to generate an image based on Mozart's Requiem in D minor, K.626, specifically the 'Dies Irae' (Day of Wrath).
Show full prompt
Mozart
From Requiem in D minor, K.626
{argument name="piece name" default="Dies Irae"}
Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.
Information boundary
Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.
Similar skills
视频短视频图片音乐音频配音口播数字人全能创作
Marked paid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
Marked paid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
Not specified【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
Marked paidAPI key required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
Marked freeRecommend 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
Marked paidAPI key required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。
What is a Skill
A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.