AI Prompt Library

A fashion-edit prompt that swaps the user’s clothes to match those shown in a reference image while keeping everything else intact.

A straightforward prompt for generating a cute chibi-style cat-eared girl with frilly clothes and long pink hair.

An English/Chinese mixed prompt describing a pixelated game character trying to crawl out of a TV into a living room while a real player pushes it back with a controller, great for playful surreal scenes.

A 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.

A Chinese prompt depicting Bruce Lee in his yellow jumpsuit playfully sparring with Yoda in a traditional Chinese dojo, great for fun crossover fan art.

A very short Japanese prompt to create an eye-catching thumbnail announcing that Nano Banana Pro has been released.

A Chinese prompt describing Einstein trying to take a selfie with a smartphone while Elon Musk stands beside him and teaches him, with a humorous line on the phone screen.

A prompt to turn a research paper into a Chinese whiteboard-style teaching slide that helps visualize and understand the content.

A prompt for producing an anime-style isometric living room layout that matches an uploaded sofa, set in a modern single-story home for a couple.

A prompt to generate a colorful, pop-style flyer image that promotes a specific Note article at a 3:4 aspect ratio.

A prompt for creating a textbook teaching illustration for the classical Chinese poem “Linjiangxian · Rolling Yangtze River Flows East,” suitable for literature education.

Two sequential edit prompts: first convert a city scene into rainy weather, then add Vietnamese people riding motorbikes in raincoats, useful for weather and cultural context edits.

Takes a hand-drawn idol character flyer and composites it as if it’s realistically adhered to a steamed bun vending machine at a convenience store, preserving lighting and perspective.

Generates a Japanese four-panel manga where a reference character explains the origins of Bitcoin from a cypherpunk perspective.

A simple prompt to generate an image from the point of view of a light gray rabbit.

A detailed prompt to generate a single 16:9 photorealistic image split into left and right halves, each showing the same geolocated place at different years and times, letting Nano Banana Pro handle era-appropriate details.

A detailed prompt for creating a vertical 4-panel Japanese gag manga featuring a young woman named Nanami eating Jiro-style ramen, with proper Japanese layout and speech direction.

Provides styling instructions for Nano Banana Pro to create simplified, flat-design infographics with minimal Japanese text and Microsoft 365-like aesthetics, helpful for clear business visuals.

A very short Japanese prompt that asks for a couple made of anthropomorphized apple and banana rather than humans.

Short prompt to create flashy, animated text reveal effects suitable for motion-like image generation or keyframe animation pipelines.

A two-part setup: a first line to set the HUD color and a core task prompt that overlays a full-screen scouter-style analysis HUD with a battle power value chosen by Nano Banana Pro from the image’s impression.

Instructs Nano Banana Pro to create an explanatory image about document creation problems and how Think-cell can solve them, useful for product or sales visuals.

Generates a vertical four-panel manga in typical Japanese anime style featuring a silver twin-tailed panda-human girl named Rookie, great for character-based comic strips.

A prompt to generate a Japanese headline-style image about Google releasing Nano Banana Pro, ideal for news thumbnails or blog headers.

A Japanese prompt that tells the model to research sources like Teikoku Databank and create an infographic about the past month’s achievements and issues of the Takaichi administration.

A pose-edit and wardrobe-change prompt from the replies, asking to change a one-piece swimsuit to a bikini and add high heels while keeping style and background.

A Korean example prompt for using reference images to keep a character’s appearance consistent while only changing clothing.

A playful prompt to create a humorous anatomical diagram of an uploaded pet photo, with funny labels and annotations.

An English natural-language prompt used to reimagine a person’s photo as if they were into goth music at the time, letting the model infer what to change.

A prompt for generating a bookstore POP display photo featuring an acrylic marker illustration labeled “neko no shippo,” placed as a standout decoration in front of new books.

An English prompt for creating a full comic page where Ben 10 crosses over into the Teenage Mutant Ninja Turtles universe, with expressive panels, clean linework, and vibrant, official-looking colors.

Creates a classroom chalkboard artwork of a rabbit king with Japanese text, in a real classroom scene with sunset light coming through the window from an oblique angle.

Creates a 2x3 grid of step-by-step visual folding instructions from a flat sheet to a final model, each step including a person performing it, great for tutorials or manuals.

Generates a scene of a physicist’s legs on a hammock with a drink and spa setting, surrounded only by trees and vegetation, ideal for relaxed conceptual imagery.

An English engineering prompt that generates a shear and moment diagram for a simply supported beam with a uniform load.

A short prompt that asks Nano Banana Pro to create a slide summarizing the advantages of investing in Vietnam.

Asks Nano Banana Pro to create a diagram summarizing the strategy behind a personal investment portfolio shown in an attached image.

Instructs Nano Banana Pro to add two centered lines of Japanese text about Google’s Nano Banana Pro over an attached image, suitable for fast thumbnail creation.

A Japanese prompt that transforms the adult woman from the first image into an elderly close-up with older-style clothing and a home background, used for visualizing growth or aging.

A Chinese prompt that generates a grid of the top 30 Water Margin characters in Chinese gongbi painting style, with names labeled on each cell.

A prompt asking the model to clean up a comic by mirroring the second panel and changing the interviewer’s line to a specific phrase.

A simple Japanese prompt requesting an image that summarizes the concept of basic income.

Two geo-based prompts to generate night scenes: one of Yeouido’s 63 Building and another focusing on Lotte World Tower, using latitude and longitude with an optional landmark-focus instruction.

Three Nano Banana Pro prompts for generating physics law infographics, English conversation scene cards, and Tang poetry learning cards, suitable for educational materials and bulk creation.

A simple prompt for generating a video advertisement for a new artisan bakery, suitable as a base for commercial spots.

A prompt to create a 12-piece LINE sticker set using an attached character, with varied expressions, poses, and on-theme, easy-to-use phrases.

A prompt to create an image that visually explains the pros and cons of real estate investment, ideal for educational or marketing posts.

A prompt idea for turning an uploaded image into a blue glowing 3D wireframe over a black background, optionally adding red wireframe tanks, useful for schematic or sci-fi visuals.

A prompt that turns an attached illustration into a character-based LINE sticker set with 16 variations of expressions, poses, and phrases.

Creates an amateur 1998-style photograph of a middle-aged artist copying an image from a computer screen to canvas, where the image itself is a photo of the artist painting the recursive image, ideal for mind-bending meta scenes.

A multi-line prompt for dressing the person from an uploaded reference image in clothes from another uploaded image, keeping the face and hair, posing them cutely, and rendering in realistic style with an optional neutral or Tokyo street background.

A refined geolocation prompt instructing Nano Banana Pro to generate an image at given Seoul coordinates while focusing on the landmark instead of a random surrounding scene.