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License information is collected from official sources and may be outdated or missing.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
Vintage Photo Restoration to DSLR Quality Prompt (Truncated)
othersA prompt snippet for restoring an old photo into a professional, high-definition portrait with DSLR quality, focusing on retaining exact facial features and clarity using an advanced upscaling algorithm.
Show full prompt
"Restore this old photo into professional portrait of DLSR - quality colour and detail, using an advanced upscaling algorithm comparable to the results from canon EOS R6 II. Ensure the restored the image looks natural, retains exact facial features, has great clarity......"
Vintage Photo Restoration to Modern Portrait Prompt
othersA prompt designed to restore and transform an old vintage photo into an ultra-realistic, high-quality digital portrait, maintaining 99% facial likeness while upgrading colors, skin texture, lighting, and modernizing the outfit and background.
Show full prompt
Create an ultra-realistic modern recreation of an old vintage photo, maintaining 99% facial likeness with no changes to the original face. Transform it into a high-quality digital portrait featuring vibrant, updated colors, smooth natural skin texture, and soft realistic lighting. Upgrade the outfit and background to a clean, contemporary style, while preserving the authentic pose, emotion, and essence of the original image.
Caravaggio-style Moral Painting of Cheating at Mahjong
othersA prompt for Nano Banana Pro (Gemini 3 Pro Image) requesting a moralistic painting in the style of Caravaggio, depicting cheating, specifically within the context of Mahjong.
Show full prompt
Cheating theme
A moralistic painting like Caravaggio, set in {argument name="game" default="Mahjong"}
Eiffel Tower Golden Hour Miniskirt Legs
othersA detailed image generation prompt for Nano Banana Pro (Gemini 3 Pro Image) focusing on capturing a photorealistic scene at the Eiffel Tower during golden hour, emphasizing the aesthetic of legs in a miniskirt from an extreme low angle.
Show full prompt
Take this base image, strictly Eiffel Tower at golden hour, extreme low angle on legs, miniskirt {argument name="miniskirt length" default="15cm"}, emphasize thigh gap and smooth leg lines, photoreal sunset lighting, high detail on skin texture and fabric movement
Fantasy Watercolor Illustration of an Elevated Rail Bridge over Flooded Forest
othersA detailed prompt for generating a fantasy watercolor illustration featuring a high-speed train on an elevated rail bridge spanning a mysterious flooded forest valley, emphasizing traditional watercolor techniques and a soft, atmospheric palette.
Show full prompt
Scene: A sleek high-speed train glides across an elevated rail bridge spanning an enormous flooded forest valley. Half-submerged ancient tree trunks rise from still reflective water while small patches of moss-covered land hold abandoned wooden cabins and broken docks. Morning fog drifts between the skeletal trees, and distant mountains fade into pale atmospheric haze. The bridge stretches far into the distance, its repeating supports creating strong cinematic perspective lines across the quiet, mysterious landscape. Style: Fantasy hand-drawn watercolor illustration style. Traditional watercolor rendering with visible pigment splashes, fluid paint diffusion, and softly blended tonal transitions. Delicate hand-illustrated linework with expressive drawn detailing and organic sketch-like contours. Soft, gentle color palette emphasizing airy tones and subtle saturation rather than strong contrast. Painterly layered watercolor textures combined with illustrative fantasy art aesthetics. Decorative, richly illustrated environments with numerous small background details integrated into the composition. Elegant full illustration treatment prioritizing handcrafted visual charm, artistic softness, and classic storybook-inspired fantasy rendering.
Scene Composition Control with Visual Reference
othersA detailed prompt for video generation using a visual reference image to control environment, lighting, texture, depth of field, and color tone. It specifies the final composition but instructs the generation to start with an empty scene, excluding the hand and bottle from the first frame.
Show full prompt
Use the uploaded image as the exact visual reference for environment, lighting mood, window background, blanket texture, depth of field, and color tone. Important: The reference image represents the FINAL composition only. The first frame must NOT contain the hand. The first frame must NOT contain the bottle. Start with an empty scene. Starting Frame: A cozy blanket in the foreground. Soft warm natural light coming through the window. Background window blurred. No hand.
Nano Banana Pro Prompt: Tarot Card 18 (The Moon) with Mális Mizer and Pisces
othersA complex prompt for Nano Banana Pro (Gemini 3 Pro Image) to generate an image based on the Tarot card 18 (The Moon), incorporating elements reminiscent of the visual kei band Mális Mizer, Eros and Aphrodite, and a circle of Pisces in the margin.
Show full prompt
Tarot Card 18 The Moon Like Mális Mizer... Next Include Eros and Aphrodite Front and back Make Pisces circle the margin
Cyberpunk Apollo's Fountain Generation
othersA prompt combining the cyberpunk aesthetic with the historical location of Apollo's Fountain at the Palace of Versailles, aiming for a futuristic prediction.
Show full prompt
Cyberpunk
Palace of Versailles
{argument name="location" default="Apollo's Fountain"}
Cyberpunk Versailles Palace Generation
othersA creative prompt combining the cyberpunk aesthetic with the historical setting of Marie Antoinette's bedroom in the Palace of Versailles.
Show full prompt
Cyberpunk
Palace of Versailles
{argument name="room" default="Marie Antoinette's bedroom"}
Cyberpunk Marie Antoinette Carriage
othersA prompt requesting a cyberpunk setting featuring a lavish, ruffled carriage that Marie Antoinette might ride, generated using Nano Banana Pro.
Show full prompt
Overall framework: Cyberpunk Include a lavish, ruffled carriage That Antoinette might ride!
Database Mascot Boxing Match
othersA creative and humorous prompt for generating an image depicting a boxing match between database mascots: PostgreSQL elephants eating popcorn in the arena, watching a fight between a MySQL dolphin and a MariaDB sea lion.
Show full prompt
postgresql elephants sitting in a boxing arena eating popcorn an watching a boxing fight between a mysql dolphin and a mariadb sea lion.
Ultimate Designer Stress Test: Minimal Abstract Visual
othersA concise, high-level prompt designed as a quality benchmark for generative models, focusing on the most challenging aspects of design: extreme minimalism, perfect balance of negative space, realistic material shading, and sophisticated lighting with a single sculptural form.
Show full prompt
Extremely minimal abstract visual. Single sculptural form, single soft light source, single color family, perfect negative space balance, realistic material shading, no decorative elements, gallery-level composition.
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.