Nano Banana - The Ultimate Gemini Image Prompt Library

$Zoom in on the bee

$Design a Yu‑Gi‑Oh! magic card. Draw the illustration in the style of official Yu‑Gi‑Oh! artwork, making it appealing. The theme of the card is "Bitcoin crash." Write the description in Japanese, and do not use furigana or ruby text. The outer background of the card should be white.

$Please create a YouTube thumbnail using this character. - Use only the upper body, with a cheerful pose and expression. - Include large text that says “雑談” and add the furigana “ざつだん”. - Give it a pop feel, but make the background simple and composed of stripes.

$A YouTube thumbnail where this man is introducing Nano Banana Pro. Style: for businesspeople. Font: dynamic, glossy, italic. Target: for Japanese viewers. Text: In-depth guide to Google’s new AI ‘Nano Banana Pro’.

$Using this character, create a YouTube thumbnail-style image with the title “What’s Amazing About Nano Banana Pro! 10 Features You Can Use Right Now”. Have the character look at the Nano Banana icon with a surprised expression. Set the image size to the YouTube thumbnail size of 1280×720 pixels.

$This is a YouTube thumbnail where, on the right side, there is an image of a person wearing a white mask being interviewed. Using this aesthetic, I want to share the information architecture for the thumbnail with the AI and have it create the thumbnail, so please think of a prompt. The reference image is only for the masked person on the right (Eru); use that as the reference, and make the layout, text size, and design so that the click-through rate is maximized. The target audience is men in their late 20s to 30s who struggle with communication skills. # Thumbnail information architecture <Left side> Three layers of conversation (small) Express them as an inverted triangle Divide into three colors In reality, from top to bottom, the following three (blur the text): ・Abstract ・Facts ・Concrete <Right side> Eru (the masked person) “This is all there is to conversation” (put this in a speech bubble) <Bottom> “With this, conversations go on forever” (stretch across the full width)

$Create an infographic for my YouTube channel everlastai.

$Two koi fish swim in the water, forming a perfect yin-yang Taiji pattern. One fish is made of black ink-like smoke, and the other is composed of glowing white light. Overhead view, ripples on the water surface. Zen vibe, minimalist style.

$Convert this into a YAML prompt, including the image size and all visual details, and output it inside a code box.

$على صورة لنهر النيل اكتب تحيا مصر

$Create a 2:3 cool, modern, and artistic poster for a camera that is the most stylish in the world right now. - The person's image is the main focus. - They are holding a single-lens reflex camera vertically, looking through the viewfinder, trying to shoot toward us. - Arrange the following text in a stylish way within the poster (do not display the text inside parentheses). - Keep the font sizes modern and minimalist. - Olympus OM-2 - In the age of AI, choose film photography that is not just data - Embrace the hassle Start executing the image generation.

$make this a blue glowing 3D wireframe over black background. Add red wireframe tanks if you want.

$生成一张Windows 11操作系统的桌面截图，截图中已打开Google Chrome浏览器，并在浏览器窗口内展示YouTube网站上Mr. Beast的视频缩略图。

$A wide quote card featuring a famous person, with a brown background and a light-gold serif font for the quote: “Stay Hungry, Stay Foolish” and smaller text: “—Steve Jobs.” There is a large, subtle quotation mark before the text. The portrait of the person is on the left, the text on the right. The text occupies two-thirds of the image and the portrait one-third, with a slight gradient transition effect on the portrait.

$Convert this paper into a Chinese professor-style whiteboard image to help me understand the information.

$Turn this text into a simple whiteboard-style diagram. Points: - Place the main concept in the center - Use arrows to show flow and relationships - Enclose important parts in boxes - Keep explanations short and focused only on key points Make the size 16:9 and design a clean diagram that is easy to view on a smartphone.

$A where is waldo image showing all Lord of the Rings characters in Shire

$A where is waldo image showing all Star Wars characters on Tatooine

$the most weird mundane photo you can imagine

$Generate a 9-image ‘photo dump’ grid of this person’s weekend: a mirror selfie, a café shot, friends at dinner, a blurry party photo, a walking shot, a laptop/coffee work shot, a pet moment, a sunset, and a candid laugh.

$Please create a design based on the text in the reference image. Ignore the layout. Design it like a professional designer would. Create a clean, well‑organized design with a beautiful flow.

$A cross-sectional view of a giant watermelon. The red flesh is actually a swimming pool filled with red water. The black watermelon seeds are swim rings. Miniature people are swimming and sunbathing on the watermelon rind. Summer vibe.

$a full map of the US with all states labeled with their abbreviations (in watercolor style & creative illustrations)

$Generate a map of Germany in watercolor style, on which all federal states are labeled in ballpoint pen.

$Generate an image of the top 30 characters from "Water Margin" in a grid format, in the style of Chinese gongbi painting, with each character’s name written in the lower‑right corner of their cell.

$i need a flowchart for how to toast bread, make it as wacky and over the top and complicated as possible.

$Have the person standing on the ground, but you don’t need to show the ground. Add a character that matches this background, and make it a character that would work as a VTuber. I want a stylish thumbnail. Make the design similar to what you often see with VTubers. Use bold, street-style fonts for the text. The text should feel like a feature in a fashion magazine. Use a vertical composition. Start image generation.

$I want you to create a visual story cartoon for this joke واحد مبوق شاف واحد البنت رقيقة بزاف سولها: فاش خدامة؟ قالت ليه: عارضة قال ليها: ف إينا ملعب؟

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

$Generate an image of the person from the uploaded reference image, keeping the face and hairstyle exactly 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. Background optional, neutral or Tokyo street setting.

$Please create a vintage-style engineering exploded view diagram of the Zhuge repeating crossbow, with all labels and text in Chinese.

$Turn this ramen into a cute recipe page with illustrations in the style of a vintage cookbook that was hand-drawn. A carefully drawn ingredients with labels, measures, and implements like bowls, whisks, or spoons should surround the composition's focal point. To create a homey, nostalgic vibe, use textured shading, warm pastel colors, and fine, ink-like outlines. Add recipe writing in the handwritten manner, including the ingredients and directions organically into the layout. Make sure the page has an artistic and educational tone, combining the beauty of colorful illustrations with a cookbook aesthetic

${ "image_info": { "width": 4096, "height": 8192, "aspect_ratio": "1:2", "orientation": "vertical" }, "technical": { "resolution": "8k", "dimensions": "4096x8192 or higher ,"quality": "ultra high detail" } }

$--- generation_parameters: aspect_ratio: "1:3" manga_page_generation_prompt: layout_structure: type: Full page vertical 4-panel comic strip (yon-koma layout). arrangement: Four roughly square panels stacked perfectly vertically from top to bottom. spacing: Clear white gutters (margins) separating each of the four panels. title_area: (Optional) A small space at the very top for a title. overall_aesthetic: Printed comic magazine page look, slightly textured paper. art_style: description: 1970s-80s Japanese Gekiga style. Gritty, heavy shadows, serious tone. color_palette: Desaturated, heavy oil-painting colors, seppia tones, dark atmosphere. texture: Rough ink lines, analog brushwork, dramatic cross-hatching shadows, ink bleed effect. manga_elements: speech_bubbles: - Presence: Multiple hand-drawn speech bubbles (fukidashi) within panel boundaries. Style: Rough, organic outlines, containing placeholder Japanese marks. sound_effects: - Presence: Bold Katakana sound effects (onomatopoeia) integrated into the art. Style: Rough calligraphy (e.g., "ドォォォン", "ゴゴゴゴ"). panel_content_sequence: panel_1_top (起): - Scene: [Wide angle] Knight Alex (grim face, full armor) standing stiffly behind a modern convenience store counter. - Text/FX: Speech bubble with formal greeting. Small "ウィーン" (door sound). panel_2_upper_mid (承): - Scene: A scared salaryman customer shrinking away. Alex glaring intensely, leaning forward over the counter. - Text/FX: Customer's scared bubble. Large "ゴゴゴゴ" (menacing FX) around Alex. panel_3_lower_mid (転): - Scene: [Dramatic close-up] Alex pulling out his giant claymore sword just to point at a bento box. - Text/FX: Spiky shout bubble "貴様の糧はこれか!!". Intense "ジャキィィン！" (sword FX). panel_4_bottom (結): - Scene: The exhausted store manager (looser art style) smacking Alex's head with a rolled magazine. Alex looks comically dejected. - Text/FX: Manager's angry bubble "剣をしまうんだよ！". Sharp "スパン！" (slap FX). negative_prompt: - single illustration, square image, landscape orientation - panels arranged horizontally, grid layout (2x2) - modern clean digital art, anime style - bright cheerful colors, no shadows

$젊은 세대를 위해 이 페이지를 재설계하세요 다음에 나올 가능성이 가장 높은 페이지를 만들어 보세요 카트에 추가하는 사용자 수를 늘리세요 버튼을 10픽셀 아래로 이동

$A imagem impossível: "Crie um relógio com ponteiro marcando 12:30"

$a richly detailed night scene of the varanasi ghats during the evening aarti, captured from a viewpoint directly across the ganges. the top half of the image shows the present-day city: crowds gathered on the steps, priests performing synchronized aarti with large flaming lamps, electric lights strung across balconies, recent renovations on temple facades, and the mix of old structures with modern signage. firelight and scattered diyas illuminate the smoke drifting softly above the ghats.the bottom half, seen as a perfect mirror on the still surface of the ganges, shows the same ghats but in an older historical era. the reflection must depict subtle architectural differences: fewer electric lights, oil lamps instead; weathered stone surfaces without modern repairs; wooden boats of older design; people in period-accurate clothing; and temple towers in their earlier structural forms. the water should be glassy, with minimal distortion, allowing both timelines to align precisely like a split reality. lighting, ripples, and reflections must follow correct physics while maintaining the illusion of two coexisting centuries. the result should feel like a single photograph capturing present above and past below, bound together by the river’s mirror.

$Unplanned paparazzi style portrait, an intense, close-up moment capturing a man with striking features as he looks over his shoulder with a confident smirk. Shot from a slightly low angle, showing only his face and shoulders amidst a blurred, bustling crowd. The image feels raw and spontaneous, lit by a harsh flash, high-ISO texture. He's wearing a dark turtleneck and stylish sunglasses, embodying effortless street style chic, the energy and atmosphere reminiscent of Paris Fashion Week chaos.

$Unpack the items from the bag and place them on the bed withe some of them scattered on the floor

$Ultra-realistic Roronoa Zoro portrait.

${ "project": "Ultra-Realistic Portrait", "reference_settings": { "use_reference_image": true, "fidelity_strength": "100%", "instruction": "Face and outfit must match reference photo 100% with absolutely no alterations." } }

$Generate an ultra-realistic film photo of this scene. No interface. Make it look like a real-life scene. Landscape format. Not literal; retell the story visually, making it look real as if it could have happened in real life. Style: 1990s family photo, casual, not a movie shot.

$Redesign this page for a younger audience Create the page that most likely comes next Increase the number of users who add to cart Move the button down 10 pixels Fix usability on this page. Decrease the bounce rate of https://t.co/Ct6uyBtKmB

$Make a super tacky slide that introduces Einstein.

$1ro: crea una imagen de una persona agregando la indicación: "Su piel tiene poros y detalles". 2do: luego introduce el siguiente prompt al resultado generado "Acerca al rostro en primer plano.".

$Generate a scene where the character from the second image is hugging the person in the first photo from behind, wrapping their arms around to the front, and they are shown together in the shot.

$Generate a diagram of a two-layer neural network in the style of Stephen Biesty

$make it a diorama

$make this a lamborghini ad

$Turning the whole Netflix screen into a western version

$Nano Banana Pro로 손그림을 만화 캐릭터로 만든다.

$Create a perspective drawing from the rough sketch of an exhibition booth.

$Analyze my bio and come up with a video game that would be me if I was a video game. Make a NES cartridge closeup with a blurred background. A room of a teenager on the background. Make it look like a product photo. Make sure to include my name.

$Take this paper and transform in the image of a professor whiteboard image: diagrams, arrows, boxes, and captions explaining the core idea visually. Use colors as well [论文内容整体复制到这]

$Trompe l'oeil illusion of A (subject) (attire) steps out of a large screen displaying xyz social media interface. The screen shows the username "@" 1K likes, and 12- 20 comments, with floating emojis (heart-eyes, smiley) around it. your preferred background.

$A majestic, translucent blue whale, made of seawater with visible fish schools inside, swimming through fluffy white clouds at golden hour, sunlight creating a rainbow through its body, surreal and grand scene.

$Please translate this manga into Japanese and turn it into an image.

$Transform a building into a robot.

$Please generate an advertisement image. ==== Ad specifications === - Aspect ratio: 16:9 (horizontal) - Product to advertise: the book in the first attached image - Main eye-catcher: place the book from the first attached image in a three-dimensional way - Language: Japanese - Taste: advertisement for a business book # Text to include: - Pre-head copy: 【New print run decided about one week after release】 Book “Designing from Zero with AI” now on sale and doing well. Amazon Best Seller Ranking Ranked No.1 in commercial design sales (as of 10/15) https://t.co/QxbYpfFVj6

$Create an image that is a design of a tower defense mobile app displayed on an iPhone in landscape mode. Make it a 3x2 grid of iPhones each displaying a different state of the game. This will be something handed off to a a developer for implementation