AI Prompt Library

The attachment is my portfolio as an individual investor. Please create an overview diagram of the policy for explaining this portfolio’s strategy to others.

Create an image of {argument name="coordinates_1_en" default="37°31'11.24"N 126°56'25.11"E"} at night. Create an image of {argument name="coordinates_2_en" default="37° 30' 40.4424'' N and 127° 5' 52.9080'' E"}. Focus on a landmark, not a random scene.

Generate an image of the person from the uploaded reference image, keeping the face and hairstyle exactly the same as in the uploaded image. Dress the person in the clothing from the uploaded clothing image, preserving the style, color, and details of the garment. Pose the person in a cute and natural pose, looking towards the camera. Realistic photo style, natural lighting, high resolution. The background is optional, either neutral or a {argument name="background_location_en" default="Tokyo street"} setting.

Create a Japanese four-panel manga in which the character from the reference image explains the origins of Bitcoin from a cypherpunk perspective.

A full comic page bringing {argument name="character_1_en" default="Ben 10"} into the {argument name="universe_en" default="TMNT"} universe, with expressive panels, clean linework, and vibrant colors that feel straight out of an official crossover issue.

The text appears with flashy effects and animation.

Create an image that explains the problems of document creation and what Think-cell can solve.

Edit it so that it looks like it is raining. When it rains, Vietnamese people wear raincoats and ride motorbikes.

Convert this long text material into a Chinese professor-style whiteboard image to help me understand the information.

Use blue HUD color. task: "edit-image: add full-screen analysis HUD overlay only"

A physicist on a hammock, with a glass and an S.P.A. Only their legs without shoes, and trees and vegetation are shown.

Generate a single photorealistic 16:9 image and split its composition into left and right halves. On each side, depict the same place, [LOCATION_NAME: {argument name="location_name_en" default="(any location)"}], at different eras. Left side: {argument name="left_year_en" default="(any year)"} · {argument name="left_time_en" default="(time)"} Right side: {argument name="right_year_en" default="(any year)"} · {argument name="right_time_en" default="(time)"} Keep the camera position exactly the same and use the following coordinates: [LATITUDE,LONGITUDE: {argument name="coordinates_en" default="(latitude and longitude of any place)"}] Do not include any text in the image (years, labels, watermarks, etc.). Do not specify detailed visuals. Leave all aspects such as architecture, light, cars, people, signs, materials, atmosphere, and composition up to Nano Banana Pro. Each era should feel natural and together form a side-by-side time comparison image within a single 16:9 frame. --ar 16:9 --stylize 800 --v 6

Based on the attached image, include the following content. Keep it within two lines and place it vertically centered. ↓ {argument name="text_en" default="Google unveils its ultimate image generation AI, ‘Nano Banana Pro’"}

On the classroom blackboard, draw a chalk illustration of a rabbit king and also write the text "うさ王様参上！" (The Rabbit King has arrived!). Show a real classroom scene with sunset light streaming in through the window from a diagonal angle.

Take the image of the hand-drawn-style idol character flyer and visually depict it as if it is stuck to a vending machine for steamed buns at a convenience store. Ensure the flyer is realistically integrated with the machine, maintaining consistent lighting and perspective with the surrounding environment.

Generate a four-panel manga in a typical Japanese anime style. The image is a vertically long rectangle with four panels arranged from top to bottom. [Character settings] * Name: {argument name="character_name_en" default="Rookie"} * Race: {argument name="race_en" default="Panda-human (a human girl with round panda ears on her head)"} * Hair: {argument name="hairstyle_en" default="Silver twin-tails"}

An amateur photograph from {argument name="year_en" default="1998"} of a middle-aged artist copying an image by hand from a computer screen to an oil painting on stretched canvas, but the image is itself the photo of the artist painting the recursive image.

Use extremely little text and focus on graphical expression. Suppress Japanese character garbling. Use Hiragino Gothic as the main font. Keep the content as is, but make the colors and design similar to Microsoft 365. Use a flat and simple design.

Use the man photo as if he is slipping off the building edge, the woman is reaching out, match the sketch pose and composition precisely, use {argument name="city_style_en" default="NYC"} as the style reference for the scene. High-quality action shot from the 1990s.

A Where’s Waldo-style image showing all {argument name="franchise_en" default="Lord of the Rings"} characters in the {argument name="location_en" default="Shire"}.

Create a {argument name="grid_layout_en" default="2 by 3"} grid of step-by-step visual folding instructions, from a flat sheet to the final model. Each step should include a person completing that step.

Move the moon that is painted in the background of the woman to the left side from the viewer’s perspective. Change the painting style to transparent watercolor.

Write as many cute handwritten notes and highlights as possible on the photo!

Create an image of {argument name="coordinates_en" default="7°36′28″S 110°12′14″E"} at {argument name="time_en" default="sunset"}.