Nano Banana Prompts: 600+ Copy-Paste Examples
600+ Nano Banana prompts from the Hooked library, plus a guide to Google's prompt formula for text-to-image and reference-based edits. "Nano Banana" now usually means Nano Banana 2 (Gemini 3.1 Flash Image); the original was Gemini 2.5 Flash Image. The library was written for Nano Banana Pro and works on Nano Banana 2 too.
★★★★★ 4.9/5 · 27,000+ users
Updated September 25, 2026.
Prompt structure
The Nano Banana prompt formula
Google's prompting guide (Google Cloud blog, March 2026) gives a five-part text-to-image formula and a separate one for references: say what each image is for ('use the sketch as structure and the fabric as texture') and then describe the new scene. Because the model reasons before it renders, full sentences that describe a scene work better than keyword lists. Editing is conversational: say what to change and, explicitly, what to keep.
Strengths and limits
What Nano Banana is good at
Good at
- Fast generation and conversational editing: change one thing in a follow-up turn and keep the rest
- Combining up to 14 reference images in one generation
- Real-time Google Search grounding, so it can draw current subjects, weather or data
- Readable text in images and translating it into other languages, for posters, labels and ads
- Very wide or tall formats: 1:4, 4:1, 1:8 and 8:1 on top of the usual ratios
Limits
- Resolutions: 512px, 1K, 2K and 4K on Nano Banana 2; Flash Lite is limited to 1K
- Aspect ratios: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, plus 1:4, 4:1, 1:8, 8:1 on Nano Banana 2
- Knowledge cutoff January 2025 for the model itself; use search grounding for anything newer
- Every generated image carries an invisible SynthID watermark
- Output formats JPEG and PNG
From prompt to posted video
Paste the prompt, get the video, post it
Hooked Pro is $29 a month for 1,000 credits across Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana Pro and GPT Image 2, plus AI UGC ads, captions and TikTok slideshows in the same plan. Or pay $89 once for the Studio and run it on your own API keys, at the provider's price.
Better results
Tips that make a difference
Do
- Describe the scene in sentences instead of listing keywords; the guide lists 'generic keyword lists' among things to avoid.
- Phrase exclusions positively: 'an empty street', not 'no cars'.
- Put any text you want rendered in quotes and name the font style: 'the headline "SUMMER DROP" in bold white sans-serif'.
- Direct like a photographer: name the lighting set-up ('three-point softbox', 'golden-hour backlight'), the lens ('f/1.8 shallow depth of field', 'macro') and the camera feel ('disposable camera', 'GoPro').
- Name materials, not categories: 'navy tweed blazer' rather than 'suit jacket', 'matte ceramic mug' rather than 'mug'.
- When editing, state what must stay unchanged (face, product label, background) along with the change.
- With several references, say which image supplies what: the character, the product, the style.
- For time-sensitive visuals (weather, scores, events), ask it to search first and then say how to turn the result into an image.
- Iterate in small follow-up turns rather than rewriting the whole prompt.
Common mistakes
- Keyword soup ('4k, ultra detailed, trending, masterpiece') instead of a described scene
- Negative phrasing ('no people', 'without text') instead of describing what should be there
- Editing without saying what to preserve, so faces or labels change
- Uploading several references without assigning a role to each one
- Expecting current facts from the model without turning on search grounding
Tested prompts
634 Nano Banana prompts from the Hooked library
Each prompt was run and kept with its result. Open one to see the full text and the output.
In an illustration describe all of the stages of CAR-T cell
In an illustration describe all of the stages of CAR-T cell therapy from lab to patients.
Full prompt and result
Infographic / Edu Visual - Abstract Microscopic View of Living Coffee Crema
"Abstract microscopic view of living coffee crema, delicate glowing tendrils and fractal networks spreading naturally across the dark espresso base, subtle bioluminescent effects in emerald and magenta hues, organic flowing forms with intri…
Full prompt and result
Infographic / Edu Visual - Cinematic Food Infographic with Floating Ingredients
Ultra-realistic cinematic food photography of a traditional dish presented on a rustic wooden table. Finished dish placed in the foreground grape-leaf rolls soup with meatballs with steam rising naturally. Ingredients floating above the dis…
Full prompt and result
Intense Cinematic Zombie Apocalypse Survivor Scene
My photo as a 20 year-old American man, dressed for adventure, leaning against the back of a damaged sedan after a shootout. He held the pistol with his right hand while lying on the asphalt covered in glass shards and dust. His face looked…
Full prompt and result
Intentgenerate A Photorealistic Mirror Selfie Captured On An
{"intent":"Generate a photorealistic mirror selfie captured on an iPhone 15 Pro Max, depicting a glamorous pop idol in a highly cluttered, messy bedroom environment.","frame":{"aspect_ratio":"9:16","composition":"Vertical full-body mirror s…
Full prompt and result
Interleukin (IL-2, IL-4, IL-6, IL-12) Signaling Pathways
I can’t get enough of Nano Banana Pro! The way it generates scientifically precise illustrations from simple prompts is nothing short of mind blowing! One of those true inflection points in the age of AI! Prompt: In multi panels create İL-…
Full prompt and result
Is elegant
subject in image made of shining marble. The sculpture should display smooth and reflective marble surface, emphasizing its luster and artistic craftsmanship. The design is elegant, highlighting the beauty and depth of marble. The lighting…
Full prompt and result
It all at once or separately
① Create a "{argument name="character 1" default="Polar Bear"}" and a "{argument name="character 2" default="Panda"}" wearing ice skates, and the background location. Normal chat-based input is also OK. Whether you generate it all at once o…
Full prompt and result
Japan City Life Anime Art: Urban Exploration & Travel
{ "posters": [ { "title": "Italy Side Stories: City Life – Volume 1", "art_style": "Anime-style digital poster, GTA V–style comic grid, nostalgic European energy", "center_panel": "A relaxed character leaning on a sc…
Full prompt and result
Japanese Cuisine: Miniature Okonomiyaki & Food History
Analysis: Extract key ingredients, cooking techniques, and cultural food elements Goal: A cookbook where ingredients and dishes emerge in delicious detail Rules: Base: A vintage cookbook with stained pages and fabric cover, historical timel…
Full prompt and result
Japanese High School Student Snap Photo
A daily snapshot taken with a low-quality disposable camera. A clumsy photo taken by a Japanese high school student. (Aspect ratio 3:2 is recommended)
Full prompt and result
Japanese photo collage, young woman in cozy living room, morning sunlight, shoji
Japanese photo collage, young woman in cozy living room, morning sunlight, shoji windows, 90s cinematic tone, soft film grain, nostalgic mood, calm atmosphere, multiple shots showing small daily moments, warm colors
Full prompt and result
Joyful Child Riding Giant Bee in Fantasy Wildflower Meadow
1. high-definition, hyper-realistic macro photograph of a tiny, miniature girl with long dark hair wearing a flowing brown linen dress, sitting peacefully on the back of a large red ladybug with black spots. The ladybug is perched on a vib…
Full prompt and result
Joyful Couple Christmas Portrait with Festive Gifts
{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "text_to_image_photoreal_couple_christmas_lifestyle", "version": "v1.1", "priority": "high" }, "references": { "refe…
Full prompt and result
Keep 100% of the facial features from the uploaded image — do not alter the face
Keep 100% of the facial features from the uploaded image — do not alter the face, proportions, or expression in any way. A cinematic ultra-realistic portrait of a young woman standing in a cotton flower field during golden hour, bathed in…
Full prompt and result
Kids' Crayon Travel Journal Illustrator
--- Prompt --- Please create a vibrant, child-like crayon-style vertical (9:16) illustration titled "{City Name} Travel Journal." The artwork should look as if it were drawn by a curious child using colorful crayons, featuring a soft, wa…
Full prompt and result
Laptop cover
create a laptop cover with stickers that belong to someone who works at hugging face
Full prompt and result
Laptop with stickers
nano banana - generate a laptop with stickers. the laptop belongs to a fan of open source ML models
Full prompt and result
Leaf Dragon Art on Forest Floor: Autumn Nature Photography
wow, you don’t need long, detailed prompts to make something amazing on Nano Banana Pro! Prompt : A photorealistic image of a leaf that looks like it’s in the shape of a dragon.
Full prompt and result
Lincoln, one of the top CEOs in the country
Lincoln, one of the top CEOs in the country
Full prompt and result
Lionel Messi Fan Photo at Football Game - Cheerful Selfie
{ "type": "image_generation_prompt", "style": "photorealistic, natural smartphone photography, sports lifestyle", "composition": { "shot_type": "medium close-up", "camera_angle": "eye-level", "capture_device": "latest iPho…
Full prompt and result
List of well-known figures walk across a pedestrian crossing
[List of well-known figures] walk across a pedestrian crossing like in the Beatles' Abbey Road photo.
Full prompt and result
London Underground Station
London Underground Station A digital snapshot captures a student with a backpack and headphones waiting on a crowded subway platform. The blurred image shows a train pulling in and other commuters.
Full prompt and result
Look up the weather in San Francisco, CA and create an image of a 5-day forecast
Look up the weather in San Francisco, CA and create an image of a 5-day forecast
Full prompt and result
Luxury Home Interior Design with Wood & Herringbone Floor
Did some experimenting and figured out the workflow for AI design transformations: Start with a base image of a room with no furniture. Then prompt on Nano Banana Pro to add what you'd like (e.g. a cool door frame, loft, or pool). Take…
Full prompt and result
Make a 4×4 grid starting with the 1880s.
Make a 4×4 grid starting with the 1880s. In each section, I should appear styled according to that decade (clothing, hairstyle, facial hair, accessories). Use colors, background, & film style accordingly.
Full prompt and result
Make a highly detailed original Construction plan of Laxmi Vilas Palace based on
Make a highly detailed original Construction plan of Laxmi Vilas Palace based on the image I provide you.
Full prompt and result
Male model
A male model, dressed in a brown bomber jacket, dark trousers, is perched on the edge of a fire escape platform. One leg dangles freely while the other is bent. Should he set on stairs He looks contemplatively into the distance. Monogrammed…
Full prompt and result
Man in Street Fashion: Urban Style, Cargo Pants & Graphic Tee
{ "prompt": "A candid photograph of a young man leaning against a large glass building wall on a sunny day. Oversized khaki graphic t-shirt with abstract orange, white and black print. Black cargo pants with multiple pockets. White sneake…
Full prompt and result
Man with Augmented Reality Music Players on Urban Street
{ "A hyper-realistic, cinematic 8k image of a man standing in a bustling Indian street market at night. He is wearing a plain grey t-shirt, green cargo pants, and white sneakers, holding a smartphone. The scene is overlaid with a detailed…
Full prompt and result
Man with Handcrafted Paper Art: Origami & Miniature Doll
{ "imageStructureAndComposition": { "framingAndAngle": "The image has a horizontal framing (landscape format), acting as a close-up that fills the frame with the main subject. The viewing angle is slightly downward (high-angle) in rel…
Full prompt and result
Man with Iconic Pop Culture Characters | Photorealistic AI
{ "scene_1_woody_buzz": { "prompt": "A hyperrealistic, editorial fashion photograph in a studio setting. A real human model with a natural, confident expression and a preserved face stands between giant, photorealistic 3D animated cha…
Full prompt and result
Marilyn in Times Square holding her iPhone in her hand
Marilyn in Times Square holding her iPhone in her hand
Full prompt and result
Men's Outdoor Style: Mountain Adventure Fashion
{ "type": "image_generation", "style": "cinematic_fashion_editorial", "aspect_ratio": "3:4", "resolution": "8K", "camera": { "model": "Leica SL2", "lens": "35mm", "angle": "low-angle shot", "depth_of_field": "shall…
Full prompt and result
Message:Share the Magic of Christmas
{"narrativeIntent":{"message":"Share the Magic of Christmas","emotion":"Warmth, nostalgia, joy","concept":"A cinematic Christmas Coca-Cola scene filled with festive lights, snow, and holiday magic."},"subject":{"primary":"Classic Coca-Cola…
Full prompt and result
Miniature Construction Crew on Giant Pepsi Can in Diner Scene
{ "image_generation_prompts": [ { "id": 1, "title": "Pepsi Skyscraper Construction", "subject": { "main_element": "Giant Black Pepsi can", "orientation": "Positioned horizontally like a skyscraper",…
Full prompt and result
Miniature Construction on Air Jordan 1 Sneaker Art Diorama
{ "project_title": "Miniature Engineering: The Nike Colossus Series", "global_style_profile": { "aesthetic": "Hyper-realistic, cinematic commercial, macro photography", "rendering_engine": "Octane Render / Unreal Engine 5.4",…
Full prompt and result
Miniature Man Resting on Plant Seedling - Photorealistic
{ "image_generation_prompt": { "subject": { "description": "A tiny man sitting and leaning against a tall young bean sprout", "clothing": "Casual pink t-shirt and black shorts", "pose": "Sitting relaxed on the ground…
Full prompt and result
Miniature Soccer Game on Smartphone Screen - Digital Sports
{ "type": "image_generation", "style": "hyper_realistic", "quality": "8K DSLR", "aspect_ratio": "4:5", "camera": { "angle": "slightly tilted cinematic perspective", "lens": "50mm DSLR", "depth_of_field": "shallow",…
Full prompt and result
Miniature Swimming Pool Diorama
Surreal miniature-world collage poster featuring an oversized open blue Nivea-style tin repurposed as a whimsical swimming pool filled with glossy white "cream-water." Tiny sunbathers float in pastel swim rings, lounge on miniature deck ch…
Full prompt and result
Modern Apple Store in Urban Cityscape - Minimalist Design
{ "type": "image_generation", "style": "ultra_photorealistic", "aspect_ratio": "1:1", "resolution": "8K", "quality": "high_detail_realism", "scene": { "location": "modern city business district", "environment": "open pla…
Full prompt and result
Modern House Exterior | Residential Architecture & Yard
في البداية خذ صورة مثل الأولى ، ثم استخدم (Nano Banana Pro) واكتب هذه المطالبة (Prompt): "غير واجهة المبنى إلى واجهة مودرن جميلة، وأضف مسبحاً وجلسة خارجية في الحوش". بعد ذلك، اختر (Veo 3.1) من Gemini ، وارفع الصورة الأولى والصورة الثانية…
Full prompt and result
Modern Men's Casual Fashion: T-shirt, Jeans & White Sneakers
{ "prompt": "Studio portrait of a young man, same appearance as the reference, posing confidently with relaxed body language. Minimal studio lighting, soft directional light fully focused on him while background remains subtle. He is wear…
Full prompt and result
Mona Lisa Charcuterie Board Food Art - Creative Culinary
Input A: Mona Lisa . <instructions> Act as a world class food expert and artist. Input A: Masterpiece painting (e.g., Mona Lisa, Starry Night, The Scream). Analyze composition, colors, mood, elements. Pick the right food ingredients re…
Full prompt and result
Monochrome Portrait of Man with Glasses & Watch
{ "image_type": "photographic portrait", "style": "fine art editorial portrait", "color_palette": { "mode": "monochrome", "dominant_tones": ["charcoal black", "deep gray", "soft mid-gray"], "contrast": "high", "saturation": "none" }, "light…
Full prompt and result
Moody cinematic portrait
"moody cinematic portrait, lone young man in tall grass field at dusk, overcast sky, teal-green color grade, wearing white buttoned shirt, matte silver over-ear headphones, side profile, head tilted back toward sky, eyes closed, arms open a…
Full prompt and result
Moody Urban Fashion: Woman & Porsche at Night Gas Station
{ "prompt": { "scene": { "location": "gas station", "time_of_day": "night", "elements": [ "black Porsche GT3 RS", "wet ground reflecting colorful urban lights", "gas station elements",…
Full prompt and result
FAQ
Frequently asked questions
Which model is Nano Banana?
Today the name usually refers to Nano Banana 2, Google's Gemini 3.1 Flash Image, launched on February 26, 2026. The original Nano Banana was Gemini 2.5 Flash Image, now a legacy model.
What is the difference between Nano Banana 2 and Nano Banana Pro?
Nano Banana 2 is the faster and cheaper model for quick generation and edits. Nano Banana Pro (Gemini 3 Pro Image) is meant for images that have to be correct, such as infographics, diagrams and designs with text.
Do these prompts work on Nano Banana 2?
Yes. The library was written for Nano Banana Pro, and the prompts also run on Nano Banana 2.
How do I edit an image without changing the face or product?
Say what to change and, in the same prompt, what must stay the same, such as the face, the label or the background. Make changes in small follow-up turns.
Does Nano Banana add a watermark?
Every image carries an invisible SynthID watermark from Google.
Keep exploring
Related prompt libraries and pricing
Sources
- https://cloud.google.com/blog/products/ai-machine-learning/ultimate-prompting-guide-for-nano-banana
- https://ai.google.dev/gemini-api/docs/image-generation
- https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/
- https://blog.google/innovation-and-ai/technology/developers-tools/build-with-nano-banana-2/
- https://deepmind.google/models/gemini-image/flash/
Two ways in · pick yours
Every template here opens in the app — 1,600+ and counting.
Pay monthly and we run the AI for you, credits included — or pay $89 once, own the app for life and bring your own keys.
Pro
Most flexibleWe run the AI for you. No API keys, nothing to set up — open the app and generate.
1,000 credits a month · cancel anytime
Secure checkout by Stripe · Cancel anytime
- About 10 UGC ads or 250 images a month
- Every video format: UGC, avatars, slideshows…
- 83 AI avatars & 76 voices in 25 languages
- Publish to TikTok, Instagram & YouTube
- 3 channels, 3 auto-channels, API included
Need more? One-time credit packs from $19. They never expire.
4.9/5 · 27,000+ users create with Hooked