AI Prompts
AI 提示词资料库
沉淀可复用的图像、视频与工作流提示词,按模型、作者和场景整理,方便运营持续扩展。
按模型浏览
从 YouMind OpenLab 开源仓库同步后,这些模块会自动映射到对应模型页。
精选提示词
一位女士工作的扁平矢量插画
一个用于生成扁平矢量插画的提示,描绘了一位金发女性坐在办公桌前使用笔记本电脑工作的场景,适用于现代平面设计或网站素材。
GPT Image 1.5 提示词
儿童德语字母海报
一个德语提示,要求为儿童制作一张学习字母表的招贴画,招贴画上包含从 A 到 Z 的所有字母,每个字母下方都有一个对应的动物及其名称,并以可爱的卡通风格绘制。
GPT Image 1.5 提示词
滑板少年胶片摄影提示
一个详细的图像生成提示,旨在比较 GPT Image 1.5 和 Midjourney V7,重点描绘一个充满活力的场景:一名黑人青少年在涂鸦遍布的滑板公园里表演滑板特技,以柯达专业 PORTRA 400 胶片的审美风格呈现。
GPT Image 1.5 提示词
江户时代浮世绘风格的现代场景再现
一个高度结构化的图像提示,用于描绘一个被重新构想为江户时代日本浮世绘木版画的现代场景,并详细指导如何处理时代错位的科技、构图、纹理和色彩。
Nano Banana Pro 提示词
黑板风格的 AI 新闻摘要
一个日文提示,用于将 AI 新闻内容转化为手绘的、教师风格的黑板图,并附带解释。
Nano Banana Pro 提示词
一项发明的复古专利文件
一个旨在生成 19 世纪末美国复古专利文件图像的提示。它指定了精确的技术图纸、手写注释、陈旧的纸张纹理、锈斑、浮雕印章和蜡封等细节,非常适合历史或档案美学。
Nano Banana Pro 提示词
最新收录
按发布时间排序,保留模型和来源信息。
Moby Dick Book Diorama Prompt
A creative prompt designed to generate an image of an old, cloth-bound copy of 'Moby Dick' lying on a desk, from which a massive, hyper-realistic ocean wave made of paper and resin is exploding. The scene includes a tiny whaling ship and a white whale caught in the paper ocean, rendered in a museum diorama style with dramatic storm lighting.
Poster / Flyer
8K Product Photography of Lace Underwear
A detailed JSON prompt for generating ultra-detailed 8K product photography focusing on delicate lace underwear. It specifies the setting (indoor studio with purple/warm tones), the subject (female hand model holding the product), and technical details like soft diffused lighting, sharp focus on the lace texture, and a 4:5 portrait format to achieve a clean, aesthetic, and professional product showcase.
E-commerce Main Image
Generate Scene Five Minutes Earlier
A creative prompt used for image-to-image generation, asking the AI to analyze a provided image and generate a new image depicting the scene exactly five minutes before the original moment, specifically to explain the current emotional state of a subject.
Comic / Storyboard
Image Overlay Prompt for Insane Roast Scribble
A simple image editing prompt for Gemini Nano Banana Pro, instructing the model to overlay an existing image with aggressive, chaotic visual elements like red ink, doodles, and remarks, effectively 'roasting' the image.
Social Media Post
Overlay Image with Conspiracy Scribbles
A simple prompt instructing the model to overlay an existing image (implied, as this is a modification prompt) with chaotic, handwritten elements like schizophrenic conspiracy scribbles, doodles, remarks, and comments using red ink.
Comic / Storyboard
Cinematic Still of a Man in a Coffee Shop
A simple image generation prompt for creating a cinematic still image of a man reading a book inside a New York coffee shop, rendered with the aesthetic qualities of Kodak Vision3 film stock. This prompt was used to test the model's ability to handle specific objects (a book) and film styles.
Social Media Post
Surreal Library Scene with Trump, Mona Lisa, and Cave Art Hunter
A complex, multi-element prompt for Nano Banana Pro, generating a surreal scene inside a modern university library where Donald Trump, the Mona Lisa (stepping out of her frame), and a prehistoric hunter (embodied in Paleolithic cave art style) are present together.
Social Media Post
Nano Banana Pro 'Kanji of the Year' Announcement Prompt
A prompt for Nano Banana Pro to generate a photorealistic image of the 'Kanji of the Year' announcement ceremony, mimicking the traditional layout and setting at Kiyomizu Temple, but using specific latitude and longitude coordinates and asking the AI to determine the kanji based on the current year's events.
Social Media Post
Collectible Figure Product Showcase Prompt
A prompt designed to transform an existing character (implied by 'Transform this character') into a physical collectible PVC figure displayed in a product showcase setting. The scene includes the figure on a base, its product box, and a computer monitor showing the 3D modeling process in Blender.
E-commerce Main Image
Infographic Generation based on Real-Time News Data
A text prompt instructing an AI model (Nano Banana Pro, connected to Google Search) to generate an infographic based on real-time data and news from the previous week, specifically concerning the readiness of Iran and Israel for conflict.
Infographic / Edu Visual
Messed Up Psycho Image with Speech Bubble
A prompt instructing the AI to generate an extremely detailed, messed up, and weird image of a 'crazy psycho' character, including a speech bubble that says 'heading out?'. It requires a reference photo for the character.
Comic / Storyboard
Nano Banana Pro Manga Panel Style Transfer Prompt
A simple, effective prompt for Nano Banana Pro to transform an uploaded original illustration into the style of a panel from a Japanese weekly manga magazine, while preserving the character's identity.
Comic / Storyboard
Trolling Prompt with Red Ink Annotations (Simplified)
A slightly simplified version of the 'trolling' prompt, instructing the AI to generate an image and then annotate it with handwritten Chinese comments and doodles in red ink, specifically focused on criticizing the user/account content.
Social Media Post
Anime-style Graphic Recording from Web Search Results
This prompt is designed for Gemini to first search the web for information about a specific company or topic, and then use Nano Banana Pro to summarize that information into an anime-style graphic recording (grareco), narrated by a fun character like a cat. The process is claimed to take less than a minute.
Infographic / Edu Visual
Kanji of the Year Announcement Image Prompt (Geospatial)
A prompt for Nano Banana Pro that uses specific latitude and longitude coordinates (35.31903497521554, 139.55040689607867, near Kiyomizu-dera Temple) to generate an image mimicking the annual 'Kanji of the Year' announcement. It instructs the AI to integrate a reference character (live-action) as the chief priest writing the chosen kanji in a location characteristic of the coordinates, using a 9:16 vertical layout that resembles typical news coverage.
Social Media Post
Sydney Sweeney and Ana De Armas at McDonalds Image Prompt
A simple, direct prompt used with Nano Banana Pro on the Gemini App to generate an image featuring celebrities Sydney Sweeney and Ana De Armas at a McDonalds restaurant.
Social Media Post
Aerial View of a Film Set
A prompt to generate an image of a film set from a high-angle aerial perspective, with annotations indicating the film being shot is titled 'If Going to Work Were a Play'.
Comic / Storyboard
Mixed Media Cinematic Café Scene
A complex prompt designed to blend wildly different visual styles—anime, pencil sketch, and claymation—into a single, cohesive, ultra-realistic cinematic image of a busy breakfast café. It specifies the placement and rendering technique for each character style within the photographic depth-of-field.
Comic / Storyboard
Schizophrenic Conspiracy Scribbles Overlay
A short, destructive prompt instructing the AI to overlay an existing image (referenced by the tweet) with 'insane schizophrenic conspiracy scribbles, white ink, doodles, remarks, comments.'
Social Media Post
Image Generation Prompt for Nano Banana Pro
A simple, descriptive image generation prompt used across various models, including Nano Banana Pro, focusing on high quality, 4K resolution, realism, and a beautiful flower garden scene.
Product Marketing
Aggressive Trolling Prompt with Tieba Slang
An aggressive version of the 'trolling' prompt, instructing Nano Banana Pro to generate an image and annotate it with handwritten Chinese comments and doodles in red ink, specifically using the colloquial and often harsh language style of Tieba (a Chinese forum) users.
Social Media Post
8K Cinematic Winter Adventure Photo on a Vintage Train
A highly structured JSON prompt for generating an 8K cinematic photo. The objective is a high-detail winter adventure scene featuring a stylish young man leaning out of a vintage red and gold train, specifying his wardrobe, pose, the snowy mountain setting, and dramatic cinematic lighting.
Poster / Flyer
Y2K Kawaii Fashion Editorial Prompt
A highly detailed, structured JSON prompt for generating a multi-panel, consistent Y2K Kawaii-fashion editorial image, focusing on extreme wide-angle perspective, hyper-feminine aesthetic, and specific wardrobe and biometrics for the model.
Product Marketing
Comedic Giant Max Verstappen in Pit Lane
A creative, comedic prompt for generating an image of a giant Max Verstappen crouching in the pit lane, treating a miniature Red Bull F1 car like a toy, with tiny mechanics reacting dramatically, rendered in a low-angle, arcade-style lighting.
Comic / Storyboard