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License information is collected from official sources and may be outdated or missing.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
Ink painting style Abé-chan with a sword
othersA brief prompt to draw a character named Abe-chan in a sumi-e (ink painting) style, holding a sword from the side view.
Show full prompt
Abe-chan in ink-painting style, holding a sword in a ready stance seen from the side.
4 types of 4‑panel manga about Nano Banana Pro
othersA detailed prompt that generates four different Japanese four-panel manga using provided character and panel-layout reference images, explaining Nano Banana Pro with an entertaining twist at the end.
Show full prompt
Please create a Japanese 4‑panel manga featuring the male and female characters from the reference images. Use the panel layout from the reference image. The theme should be the newly announced {argument name="subject_en" default="Nano Banana Pro"}, and in the final, fourth panel, add a funny punchline. Make the structure intuitive so that even users unfamiliar with generative AI can easily understand what {argument name="subject_en_again" default="Nano Banana Pro"} is about. Under these conditions, create four different 4‑panel manga.
Dopamine and schizophrenia synapse diagram
othersA prompt to generate a wide explanatory diagram showing dopamine and D2 receptors at the synaptic cleft and how they relate to schizophrenia, including the effect of antipsychotic drugs in three different states.
Show full prompt
I want an illustrated diagram explaining the roles of dopamine and D2 receptors in the synaptic cleft between neurons, and how they relate to schizophrenia. Antipsychotic drugs exert their effects by blocking D2 receptors. Please diagram this for the three cases: healthy person | hallucination and delusion state | under antipsychotic medication. Generate a horizontally oriented image.
Chibi character LINE stickers set
othersA prompt to convert an attached character into a chibi style and generate a 12‑piece LINE sticker set with different expressions, poses, and speech bubbles.
Show full prompt
Turn the character in the attached image into a chibi character. Create LINE stickers, with different expressions, poses, and speech bubbles, in {argument name="num_stamps_en" default="12"} variations.
Blackboard summary of pasted content
othersA simple prompt that takes some given text and turns it into a single blackboard-style visual summary.
Show full prompt
Please clearly summarize the following content on a single blackboard.
Single-slide illustration of a Yahoo News article
othersA prompt that converts a Yahoo News article into one illustrated slide explaining the topic clearly.
Show full prompt
Generate an image that clearly summarizes the following {argument name="news_source_en" default="Yahoo News"} article in a single slide, using diagrams and illustrations.
---
{argument name="news_body_en" default="{paste the Yahoo News article here}"}
Monochrome rom-com manga page from an illustration
othersA bilingual prompt that turns a given illustration into a single-page monochrome manga in the style of a Japanese romantic comedy.
Show full prompt
From this illustration, infer and create one page of a monochrome manga. It is a Japanese romantic comedy. -- Please infer one page of a monochrome manga from this illustration. It's a Japanese romantic comedy.
YouTube thumbnail for Nano Banana Pro features
othersA prompt that uses a specific character to design a 1280×720 YouTube thumbnail about Nano Banana Pro’s top ten features, with the character looking surprised at the Nano Banana icon.
Show full prompt
Using this character, create a YouTube thumbnail-style image with the title “{argument name="title_text_en" default="What’s Amazing About Nano Banana Pro! 10 Features You Can Use Right Now"}”. Have the character look at the {argument name="focus_object_en" default="Nano Banana icon"} with a surprised expression. Set the image size to the YouTube thumbnail size of {argument name="thumb_size_en" default="1280×720 pixels"}.
High-detail story-art layout with frames and speech bubbles
othersA replacement for the word “manga” that describes a three-frame high-resolution story-art layout with detailed characters, full-color backgrounds, and speech bubbles, mimicking an art-book style.
Show full prompt
Composition: A “high-resolution story art” layout divided into {argument name="num_frames_en" default="three"} frames.
The background should have full-color background-art quality.
Characters are rendered with densely detailed depiction, and their dialogue is expressed via speech bubbles.
The overall layout should feel like a high-end art book “art layout.”
Faithfully reproduce the art style of the reference image, with delicate linework and a highly detailed finish.
Figure-style product page design for a heartbreak girl figure
othersA detailed prompt for turning an image into an ultra-detailed figure-style product page, including logos, zoomed-in details, and layout like a professional figure product listing.
Show full prompt
Turn this image into an ultra-detailed figure-style rendering and design a product introduction page.
The product name is “{argument name="product_name_en" default="Heartbreak Girls"}”.
It is a 1/{argument name="scale_en" default="7"} scale figure.
The manufacturer name is “{argument name="manufacturer_en" default="TENNEN"}”.
The logo should be the word {argument name="logo_text_en" default="TENNEN"} inside a rounded blue square. Break the line after “{argument name="logo_top_en" default="TEN"}”, and align the next line “{argument name="logo_bottom_en" default="NEN"}” at the start of the line, placing it as large as possible within the rounded blue square.
Place zoomed-in detail views, etc., so that it looks like a product introduction and has a professional, visually appealing design.
Also make the “{argument name="product_name_en_again" default="Heartbreak Girls"}” lettering look like a logo.
Make it look like a proper product introduction page.
Scheduled for release in {argument name="release_season_en" default="Winter 2025"}.
Prototype sculptor: {argument name="sculptor_name_en" default="Tennen"}.
Cute chibi cat-eared girl illustration
othersA straightforward prompt for generating a cute chibi-style cat-eared girl with frilly clothes and long pink hair.
Show full prompt
Generate an illustration of a cute cat-eared girl. Make her in a chibi style, wearing frilly clothes, with long {argument name="hair_color_en" default="pink"} hair.
A4 visual explainer about Watamote’s cultural significance
othersA prompt that creates an A4-sized explanatory image with illustrations, explaining the history and appeal of the manga “Watashi ga Motenai no wa Dou Kangaete mo Omaera ga Warui!” for a presentation at a cultural affairs meeting.
Show full prompt
To be able to present at a meeting of the Agency for Cultural Affairs, please create an A4 {argument name="num_pages_en" default="single"}-page explanatory image, with illustrations, about the history and appeal of the manga “{argument name="work_title_en" default="No Matter How I Look at It, It’s You Guys’ Fault I’m Not Popular!"}”.
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。
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。
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。
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
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,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。
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.