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.
Game Asset - Character Generation from Google Slides Shapes
Such a cute character was created from Google Slides shapes!!
Full prompt and result
Game Asset - Chibi-Style NBA Matchup
Generate a screenshot of a real NBA game where Kobe Bryant is matched up against LeBron James at the Lakers' home court. James is defending Kobe's fadeaway jumper, and Kobe is depicted as a chibi-style baby.
Full prompt and result
Game Asset - Disintegration Effect Function Prompt
``python def disintegrate(Subject): Direction = "{argument name="disintegration direction" default="Left to Right"}" Wind_Speed = "{argument name="wind speed" default="100 km/h"}" Particle_Type = "{argument name="particle type" default="Bla…
Full prompt and result
Game Asset - Humanoid Mech Generator for Urban Life
Design a full-body humanoid mech adapted to everyday urban life. Mechanical head with a strong abstract silhouette, no human or anime facial features. Futuristic wear. Exposed mechanical limbs and joints with clean panel seams and functiona…
Full prompt and result
Game Asset - Inflatable Character Creation Prompt
Create inflatable characters using this prompt
Full prompt and result
Game Asset - Macro Shot of Miniature Sniper Scene
A hyper-realistic, 8k, high-fidelity close-up shot captured with a macro lens, showcasing a giant human hand holding a keyring against an extremely blurred background of a rugged outdoor forest range. The hand holds a rugged, olive drab par…
Full prompt and result
Game Asset - Maze Generation Failure in Nano Banana
I tried generating a maze, but I see that this kind of thing isn't possible due to the mechanism...
Full prompt and result
Game Asset - Miniature Metropolis Inside a Vintage Pocket Watch
Create a hyper-realistic macro photograph depicting a sprawling miniature metropolis nestled within a vintage pocket watch for the hyper-realistic isometric 3D render of a miniature. The intricate gears and springs of the watch form the fou…
Full prompt and result
Game Asset - Nano Banana's Understanding of Fallout Terminology
Proper nouns like Nuka-Launcher and Ghoul are understood.
Full prompt and result
Game Asset - Octane-Rendered Floating Ecological Island
[SUBJECT] A massive floating island captured as a photoreal, physically plausible environment, rendered with Octane-level realism. The island is a living ecological system integrated with inhabitable architecture grown from stone, crystal,…
Full prompt and result
Game Asset - Split Identity Vinyl Toy Engine
Do this for a random character: <instruction> Split Identity Vinyl Toy Engine: Input A is a Character with duality. Select 4 lesser-known characters with internal conflict. Sculpt each toy split vertically or horizontally into two contras…
Full prompt and result
Game Asset - Vast Open-World Game Environment Generator
[THEME] = "{argument name="theme" default="Enter a theme here"}" Make a wide cinematic fantasy game environment illustration inspired by [THEME]. Use a distant environment-focused camera with an expansive sense of scale and exploration. S…
Full prompt and result
Gamer Girl with Retro Video Game Collection
{ "label": "direct-flash-gamer-girl", "tags": [ "direct-flash", "retro-gamer-room", "90s-photography", "film-aesthetic", "gamer-girl", "collectibles-shelf", "low-angle", "sitting-pose" ], "Composition…
Full prompt and result
Gemini 3 Prompting Best Practices | AI Prompt Engineering Guide
Here are my Gemini 3 Prompting Best Practices for General Usage. https://philschmid.de/gemini-3-prompt-practices… - visualized by Nano Banana Pro
Full prompt and result
Gemini Nano Banana Pro
{ "subject": { "description": "Young woman lying on a bed", "pose": "Lying on stomach, propped up on elbows, legs raised and crossed at the ankles behind her", "expression": "Pouting lips, looking directly at the camera",…
Full prompt and result
Gender:female
{"subject":{"gender":"female","age":"young adult","hair":{"color":"dark","length":"long","texture":"glossy","style":"loose, cascading over shoulders"},"pose":{"left_hand":"touching back of head","right_hand":"on hip","stance":"confident"},"…
Full prompt and result
Generate a 8k Instagram-style portrait of an Indian woman sitting in a trendy ca
Generate a 8k Instagram-style portrait of an Indian woman sitting in a trendy café. Add warm ambient lighting, latte tones, and aesthetic decor. Outfit should be modern—crop top, oversized shirt, or denim jacket. Pose relaxed with chin rest…
Full prompt and result
Generate a 9-image ‘photo dump’ grid of this person’s weekend: a mirror selfie,
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.
Full prompt and result
Generate a cinematic, high-resolution photographic image des
{"Objective":"Generate a cinematic, high-resolution photographic image description.","Scene_Details":{"Setting":"Vast English landscape with rolling golden-brown hills.","Atmosphere":"Moody and atmospheric with dark, brooding clouds.","Ligh…
Full prompt and result
Generate a cinematic, photo-realistic image of the person in
{"objective":"Generate a cinematic, photo-realistic image of the person in the uploaded image","scene_description":{"setting":{"location":"Rain-soaked flyover bench at dusk","environment_details":["wet pavement with puddle reflections","mis…
Full prompt and result
Generate a hyperrealistic realistic-anime portrait of a female character
Generate a hyperrealistic realistic-anime portrait of a female character standing in a completely black background. Lighting: use a **narrow beam spotlight** focused only on the center of the face. The edges of the light must be sharp and…
Full prompt and result
Generate a photorealistic image of Time Square on a saturday in Fall 2006, it's
Generate a photorealistic image of Time Square on a saturday in Fall 2006, it's a beautiful late October day, people are busy. in focus should be a young blonde - rest can be blurred. the photo should be reminiscent of that a digital camera…
Full prompt and result
Generate a structured JSON version of a cinematic portrait p
{"Objective":"Generate a structured JSON version of a cinematic portrait prompt describing a young man in a modern art gallery.","Scene_Details":{"Environment":"Modern art gallery with polished concrete floors, soft reflected lighting, and…
Full prompt and result
Generate an 8K ultra-realistic full-body portrait based on t
{"Objective":"Generate an 8K ultra-realistic full-body portrait based on the user's reference image.","Scene_Description":{"Environment":{"Setting":"Indoor room with a clean, light-grey wall","Atmosphere":"Professional, modern, minimal","Pr…
Full prompt and result
Generate an image based on a detailed character portrait des
{"objective":"Generate an image based on a detailed character portrait description.","image_generation_prompt":{"subject":{"gender":"female","portrait_type":"close-up","angle":"side angle","aesthetic":"edgy, modern, mysterious, confident, s…
Full prompt and result
Generate an ultra-realistic full-body cinematic fashion port
{"Objective":"Generate an ultra-realistic full-body cinematic fashion portrait of a stylish young man.","Scene_Description":{"Environment":{"Setting":"Outdoors against a vibrant hot-pink textured wall","Lighting":{"Type":"Bright cinematic l…
Full prompt and result
Generate an ultra-realistic street-fashion portrait of a you
{"Objective":"Generate an ultra-realistic street-fashion portrait of a young man walking confidently outdoors based on the provided reference image.","Scene_Description":{"Environment":{"Setting":"Wet pavement near a modern café","Backgroun…
Full prompt and result
Generate leaked photo BTS from KPOP Demon Hunters live action movie set
Generate leaked photo BTS from KPOP Demon Hunters live action movie set
Full prompt and result
Generate the holiday photo of this person through the ages up to 80 years old
Generate the holiday photo of this person through the ages up to 80 years old
Full prompt and result
Generation_Constraintsidentity_Preservationstrict Full Identity Lock On Both Subjects From
{"generation_constraints":{"identity_preservation":"Strict full identity lock on both subjects from reference photo","facial_features":"Do not alter faces, proportions, or natural expressions","style_reference":"Raw Y2K night-photo style"},…
Full prompt and result
Generation_Parametersdimensions1200X1200Px,Output_Modeblack And White,Quality_Presetultra-Realistic 4Khd,Reference_Constraintsfacial_Fidelitystrictly Preserve Facial Featur
{"generation_parameters":{"dimensions":"1200x1200px","output_mode":"Black and White","quality_preset":"Ultra-realistic 4KHD","reference_constraints":{"facial_fidelity":"Strictly preserve facial features of the woman from the input image","c…
Full prompt and result
Generation_Parametersresolution1200X1200Px,Overall_Aestheticvogue Holiday Editorial, Cinematic Glow, Ultra High Quality,Color_Paletteblush
{"generation_parameters":{"resolution":"1200x1200px","overall_aesthetic":"Vogue holiday editorial, cinematic glow, ultra high quality","color_palette":["blush pink","champagne gold","creamy white","warm Christmas lights"],"reference_usage":…
Full prompt and result
Generation_Tasktitlecinematic Flash Selfie - Film Noir Style,Version2.0,Strict_Constraintsface_Preservationface Must
{"generation_task":{"title":"Cinematic Flash Selfie - Film Noir Style","version":"2.0","strict_constraints":{"face_preservation":"Face must remain 100% unaltered from reference.","lighting_type":"Direct on-camera flash only.","view_angle":"…
Full prompt and result
German soldiers waving the flag in Berlin
German soldiers waving the flag in Berlin
Full prompt and result
Giant 3D Kitten Billboard in Tokyo Cityscape - Shibuya
An enormous L-shaped glasses-free 3D LED screen situated prominently at a bustling urban intersection, designed in an iconic architectural style reminiscent of Shinjuku in Tokyo or Taikoo Li in Chengdu. The screen displays a captivating gla…
Full prompt and result
Giant 3D Red Panda Digital Billboard in Urban Cityscape
An enormous L-shaped glasses-free 3D LED screen situated prominently at a bustling urban intersection, designed in an iconic architectural style reminiscent of Shinjuku in Tokyo or Taikoo Li in Chengdu. The screen displays a captivating gla…
Full prompt and result
Giant Pencil Cityscape: Surreal Urban Construction
Transform [EVERYDAY OBJECT] into a massive real-world monument. Surface materials are physically accurate, with visible wear, scratches, dust, and scale references like people and vehicles. Shot from a low-angle cinematic perspective, reali…
Full prompt and result
Glamorous Woman in Red Gown, Fireworks over City at Night
{ "subject": { "person": "Woman", "appearance": { "hair": "Blonde, sleek ponytail", "makeup": "Glamorous, defined brows, nude lips", "skin": "Tanned", "expression": "Looking at camera with a slight smile"…
Full prompt and result
Glamorous Woman in Silver Dress | Fashion Photoshoot
{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "text_to_image_photoreal_editorial_portrait", "version": "v1.0", "priority": "high" }, "references": { "character_re…
Full prompt and result
Glamorous Woman in Sparkling Mini Dress with Cocktail
{ "image_prompt": { "subject": { "type": "Young woman", "appearance": { "hair": "Sleek blonde hair pulled back into a tight bun", "skin": "Glowing, tanned complexion", "expression": "Playful 'kissy…
Full prompt and result
Glowing Transparent 3D Render Gaming & Lifestyle Products
{ "subject": "target_style": { "style_name": "ultra-modern transparent black hyperrealism", "visual_language": [ "sleek", "futuristic", "minimalistic", "floating design", "high-gloss transparency"…
Full prompt and result
Golden Fried Chicken Splashing in Creamy Dill Sauce
{ "food_photography_series": { "subject": "Fried Chicken Thigh", "technical_specs": { "style": "Hyper-realistic hero shot", "aspect_ratio": "3:4", "lighting": "Cinematic / Studio" }, "variations": […
Full prompt and result
Golden hour portrait with tree shadows cast on wall.
Golden hour portrait with tree shadows cast on wall. Subject in white blouse, warm highlights, soft tones. 85mm lens, f/2.2, ISO 200, 1/500s. Film look: Kodak Gold 200, nostalgic sunlight hue.
Full prompt and result
Google (GOOG) Stock Price & Tech City 3D Render
{User input, default 1:1} * Date: {User input, current date} * Company name or stock ticker: {User input} --- Company Name / Stock Ticker: Google Date: 12/3/2025
Full prompt and result
Gorgeous redhead Caucasian woman with long wavy crimson hair
{"style":"sharp indoor cosplay selfie, soft even lighting, ultra-realistic photography, cinematic color grade","subject":"gorgeous redhead Caucasian woman with long wavy crimson hair, emerald eyes, heavy black winged eyeliner, pale freckled…
Full prompt and result
Gourmet Burger Food Photography | Appetizing Menu Design
{ "food_photography_series": { "subject": "Hot Burger", "technical_specs": { "style": "Hyper-realistic hero shot", "aspect_ratio": "3:4", "lighting": "Cinematic / Studio" }, "variations": [ {…
Full prompt and result
Hagia Sophia Istanbul Aerial Golden Hour Cityscape Bosphorus
{ "customInputs": { "landmark": "{INSERT_LANDMARK_NAME}", "aspectRatio": "{INSERT_ASPECT_RATIO}", "timeOfDay": "{INSERT_TIME_OF_DAY}", "weather": "{INSERT_WEATHER_CONDITION}" }, "promptDetails": { "description": "…
Full prompt and result
Hand-drawn style header image prompt from photo
Completely recreate the uploaded person. Make it a header image for a note article where that person introduces “Nano Banana Pro”. Aspect ratio: horizontal 16:9. Style and colors: simple, hand-drawn style, italic, with a blue and green grad…
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