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License information is collected from official sources and may be outdated or missing.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.
5717 matches
Hero-style product advertising poster
product-marketingA detailed Arabic prompt for creating a surreal, realistic hero-style advertising poster that automatically adapts to a product name and category, great for branded promotional visuals.
Show full prompt
Creative, realistic and surreal advertising design for a product {argument name="product_name" default="[product name]"} from the category {argument name="product_type" default="[product type]"}, where the product appears as a heroic element in the center of the frame and visually forms in a smart way that automatically reflects the spirit and identity of the brand.
A clean background that matches the brand colors, soft cinematic lighting, ultra-realistic materials, precise shadows, and strong visual composition.
Macro close-up product detail prompt
product-marketingAn edit prompt to generate macro close-ups of specific clothing and accessory details from a starting image, useful for fashion or product photography mockups.
Show full prompt
Generate a macro close-up on {argument name="detail_1_en" default="her jumper pattern detail"}, {argument name="detail_2_en" default="boots"}, etc.
Structured rooftop winter portrait (JSON)
product-marketingA detailed JSON-style English prompt that describes a woman on a snowy rooftop in three vertical thirds, focusing on her eyes, body, and face with retro Y2K and neon winter vibes.
Show full prompt
{
"image_description": {
"upper_third": {
"focus": "{argument name=\"upper_focus_en\" default=\"Her eyes\"}",
"details": [
"Reflecting blurred city lights below",
"A thin layer of frost touching her lashes",
"Wind pushing a few strands of hair across her forehead"
],
"vibe": "{argument name=\"upper_vibe_en\" default=\"Sharp retro-Y2K\"}"
},
"middle_third": {
"focus": "{argument name=\"middle_focus_en\" default=\"Her body and immediate surroundings\"}",
"details": [
"Lying on a rooftop lounge chair dusted with snow",
"Wrapped in a white faux-fur jacket over a sequined winter dress",
"Soft neon glow bouncing off snowflakes on her sleeves"
]
},
"lower_third": {
"focus": "{argument name=\"lower_focus_en\" default=\"Close-up of her face and hands\"}",
"details": [
"Facing the camera with one hand above her eyes",
"Shielding a bright pinkish neon light",
"Snowflakes clinging to her jewelry",
"Tiny drops forming near her lips"
]
}
}
}
Various redesign commands for Stitch’s Redesign Agent
product-marketingContains multiple English natural-language commands for AI-based UI editing; these are valid prompts for an AI redesign agent powered by Nano Banana Pro.
Show full prompt
젊은 세대를 위해 이 페이지를 재설계하세요 다음에 나올 가능성이 가장 높은 페이지를 만들어 보세요 카트에 추가하는 사용자 수를 늘리세요 버튼을 10픽셀 아래로 이동
Generate a 100-inch MacBook image
product-marketingA Japanese prompt asking Nano Banana Pro to generate an image of a 100-inch MacBook, suitable for humorous or conceptual visuals.
Show full prompt
Generate an image of a {argument name="size_en" default="100-inch"} MacBook.
World-class cool film camera poster (2:3)
product-marketingA long Japanese prompt to create a 2:3, cool and modern artistic camera poster featuring a person holding an SLR, with carefully positioned Japanese text elements and a command to start image generation.
Show full prompt
Create a 2:3 cool, modern, and artistic poster for a camera that is the most stylish in the world right now.
- The person's image is the main focus.
- They are holding a single-lens reflex camera vertically, looking through the viewfinder, trying to shoot toward us.
- Arrange the following text in a stylish way within the poster (do not display the text inside parentheses).
- Keep the font sizes modern and minimalist.
- {argument name="product_name_en" default="Olympus OM-2"}
- {argument name="main_catch_en" default="In the age of AI, choose film photography that is not just data"}
- {argument name="sub_catch_en" default="Embrace the hassle"}
Start executing the image generation.
New oyakodon menu poster for a fictional diner
product-marketingA Japanese prompt to generate an image announcing that a fictional diner called Teishokuya Nagame has started serving oyakodon.
Show full prompt
It can output Japanese perfectly. I had it create an image showing that the fictional diner "{argument name="shop_name_en" default="Teishokuya Nagame"}" has started serving {argument name="new_menu_en" default="oyakodon"}.
Supermarket sale flyer in Japanese
product-marketingA minimal Japanese prompt to generate a typical supermarket special sale flyer, with only the store name specified as a variable.
Show full prompt
Create a special sale flyer for a supermarket. Please also include the store name {argument name="store_name_en" default="[store name]"}.
Instagram-style Japanese handwritten cosmetic ad
product-marketingA detailed Japanese prompt to create an Instagram-like organic handwritten text ad for a sensitive-skin cosmetic serum, using purple and pink colors and strong first-time discount messaging.
Show full prompt
Make it an ad in the style of an organic handwritten Instagram post, in Japanese. The color taste should be {argument name="color_en" default="purple and pink"}. The selling points are {argument name="selling_point1_en" default="for sensitive skin"} and {argument name="selling_point2_en" default="price"}. Emphasize that the price is {argument name="price_hook_en" default="for a limited time only"}. Please also mention the texture and volume of the serum. Include phrases like “{argument name="phrase1_en" default="Try it first"}”, “{argument name="phrase2_en" default="Must see"}”, and “{argument name="phrase3_en" default="First-time 40% off"}”.
Japanese tourists enjoying a Taiwanese night market
product-marketingAn English prompt to generate a realistic photo-like image of Japanese people traveling in Taiwan and enjoying the night market, with Chinese text rendered correctly.
Show full prompt
{argument name="nationality_en" default="Japanese"} people who are traveling to {argument name="destination_en" default="Taiwan"}. They are enjoying the night market.
A realistic photo-like image.
Cosplayer with itasha at Shibuya Scramble Crossing
product-marketingA Japanese prompt for generating a powerful photo of a cosplayer, matching a provided character image, posing with an itasha-wrapped car at Shibuya Scramble Crossing, with readable Japanese and English signage.
Show full prompt
Generate a powerful, impactful photo where a cosplayer of the character in the provided image is standing at the center of Shibuya Scramble Crossing together with a car wrapped in the illustration from the image. Checklist: - For the text on signs and billboards, make sure Japanese and English characters are rendered correctly without garbling.
Ad manga for a radio show with a gorilla and rabbit
product-marketingA prompt to turn attached gorilla and rabbit characters into a one-page color advertisement manga for a late-night radio show, including sound effects and broadcast info.
Show full prompt
Use the attached images of the gorilla and the rabbit. Create an advertisement manga for the radio program “Genki no Deru Radio,” where the gorilla and rabbit are the personalities. It airs every Wednesday at 10:15 p.m. on X Spaces. One-page manga, in color, with sound effect text included.
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。一节课的讲解也能做成课程口播。
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。
自动化克隆数字人口播混剪视频
FreemiumAPI key required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
海报设计工作室
FreemiumAPI key required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。
MiniMax H3 AI视频创作
Not specified用 MiniMax H3 这款 AI视频生成器创作高质感 2K AI 视频。从文字创意出发完成文生视频,让静态图片自然动起来,用首尾画面做首尾帧视频的完整转场,也可以结合图片、视频和音频参考,以多模态视频生成塑造统一场景。适合 AI 广告视频、电商产品视频、品牌宣传视频、动态海报、游戏 UI、电影片头和社交短视频创作,形成电影感画面与同步的原生立体声。使用 Beatra 账号即可开始,创作进度与成片集中管理。
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.