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License information is collected from official sources and may be outdated or missing.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
Cute Character Walking Illustration
othersA user generated a cute illustration of a character named Rukutan walking well, using Nano Banana Pro.
Show full prompt
Kopokopo☺️ Kopokopo☺️ Rukutan is good at walking (っ ◜ω◝ c) is good at walking (っ ◜ω◝ c)✨
Instructing Costume Correction via Reference Image
othersA user used Nano Banana Pro to instruct a costume correction by referencing an existing image and a character sheet. The resulting image was slightly larger but deemed acceptable for the final step.
Show full prompt
Referenced image ②① and the character sheet to nanobanana pro and instructed a costume correction.
Using a 'Miracle Wake-Up' Prompt
othersA user borrowed a prompt and generated an image related to a 'miracle where you make it on time even if you oversleep,' resulting in a great fortune (Daigikichi) image.
Show full prompt
A miracle where you somehow make it on time even if you oversleep... it turned into a wonderful great fortune
Difficulty Resizing Text in Nano Banana Pro
othersA user notes that while Nano Banana Pro is powerful, it struggles to follow instructions to reduce the size of specific text, such as 'by すごい改善' (by Sugoi Kaizen).
Show full prompt
Please reduce the font size of "by Sugoi Kaizen"
Stylizing Characters with a Specific Prompt
othersThis tweet introduces a prompt shared by another user (@_3912657840) that can be used with Nano Banana Pro to transform cute characters into a more stylish and cool aesthetic.
Show full prompt
A prompt that makes characters stylish
Four-Panel Comic Strip Generation
othersA user created a four-panel comic strip using Nano Banana Pro centered around the theme of 'hot and cold.' This demonstrates the tool's capability for generating sequential art or short narratives.
Show full prompt
Today's theme is {argument name="theme" default="hot and cold"}
Watercolor Semi-Realistic Fantasy Animation Style Prompt
othersA style prompt combining multiple artistic techniques to achieve a specific visual aesthetic: a watercolor semi-realistic fantasy animation look, enhanced with impasto and oil painting textures, utilizing traditional art materials.
Show full prompt
(masterpiece, highest quality, high resolution: 1.2), watercolor semi-realistic fantasy animation, impasto, oil painting, traditional art materials
Retro-Future Pinup Background Conversion Prompt
othersA detailed image-to-image prompt designed for Nano Banana Pro to transform a white background into a retro-futuristic, American pinup-style scene. It incorporates elements of Space Age and Googie architecture, maintaining the original character's pose and expression while focusing on high-resolution background generation with subtle neon and ambient lighting effects.
Show full prompt
Change the white background to an American retro pinup-style background.
Design a high-sense background incorporating elements such as retro-future, Space Age, and Googie architecture.
Add a thin border like an old photograph.
Generate the background in high resolution,
adding a slight sense of realism to the texture and details.
Use expressions that suggest neon or indirect lighting.
Mainly generate only the background, without significantly changing the character's pose, expression, clothing, or coloring.
Design the background to match the character's pose.
The setting is: [{argument name="setting" default="airport"}]
NanoBanana AI Correction for Handheld Device Image
othersThis is a description of a successful use case for the NanoBanana AI tool. The user initially generated an image of a handheld device using Stable Diffusion, but the result was strange. By using NanoBanana and providing correction instructions, the user was able to fix the image to look like a proper handheld device, correct the fingers, and remove a mysterious cable.
Show full prompt
I gave it appropriate correction instructions, and it became a proper handheld device even in high-speed mode. Additionally, I requested corrections for the fingers and the removal of a mysterious cable, and it worked well.
Nano Banana LLM Prompt for System Message Modification
othersA simple, yet effective prompt used with Nano Banana (presumably an LLM or AI tool) to modify the system message or context. The user was impressed by how easily the AI adopted the new instruction, which was to state that it was not raining and only write that specific system message.
Show full prompt
It is not raining. Write only this as the system message.
Nano Banana Pro Style Variations
othersA simple list of four distinct artistic styles that can be applied using Nano Banana Pro, including painterly, realistic, Pixar-like animation, and modern American comic style.
Show full prompt
1. painterly quality 2. realistic version 3. Pixar-like animation style 4. the modern American comic style
Branded gifts postcard illustration prompt
othersA highly detailed prompt for generating a hand-drawn fashion illustration of a Christmas tree constructed from a chaotic stack of branded product boxes. It specifies composition, strict adherence to the brand's color palette and typography, and an 'Alcohol Marker and Ink' sketch art style on a white paper background.
Show full prompt
[A charming, hand-drawn fashion illustration of a Christmas tree constructed entirely from a chaotic stack of [{argument name="brand name" default="BRAND NAME"}] product boxes.
**COMPOSITION:**
The boxes are piled in a pyramid shape to mimic the silhouette of a Christmas tree. The boxes vary slightly in size and angle, creating a playful, unstable, organic look. At the very top, there is a simple golden star.
**BRAND PALETTE & AESTHETICS (CRITICAL):**
The boxes must be colored strictly according to [{argument name="brand name" default="BRAND NAME"}]'s official color palette (e.g., Tiffany Blue for Tiffany, Orange/Brown for Louis Vuitton, Red/White for Supreme).
* **Details:** Visible [{argument name="brand name" default="BRAND NAME"}] logos are printed on the sides of the boxes. Add realistic packaging details like small shipping labels, barcodes, and tape to enhance the "delivery box" vibe.
**ART STYLE (MARKER SKETCH):**
The image is NOT a 3D render. It is a high-quality "Alcohol Marker and Ink" sketch on white paper. The style is loose, artistic, and vibrant, typical of fashion design sketches. The colors have the texture of markers; the outlines are done in fine black ink.
**TYPOGRAPHY (STRICT BRAND MATCH):**
At the very bottom of the illustration, centered, write the phrase: "{argument name="holiday message" default="Happy New Year!"}".
1. **Font Style:** The font must mimic the official typographic language of [{argument name="brand name" default="BRAND NAME"}] (e.g., if Nike: use a heavy Condensed Sans-Serif; if Gucci: use a refined Serif). The text style must feel like an extension of the brand's identity.
2. **Size:** The text must be very small and discreet. It should occupy a maximum of 20% of the total image width.
**BACKGROUND:**
Clean white paper texture background.]
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.