Prompt library

Nano Banana 2 Prompts

15 tested prompts across product, architecture, portrait, poster and more.

Price check

Up to 35% cheaper than the official Nano Banana 2 API

Try now
ResolutionOfficial Google APIOn VidneyYou save
1K$0.067$0.04435% off
2K$0.101$0.07328% off
4K$0.151$0.11623% off

Prices at the Creator annual rate. Official price is the Nano Banana 2 API list price published by Google, checked September 5, 2026.

Exploded product view with inner mechanics revealed

Exploded product view with inner mechanics revealed

Why this one One bracket to fill and you get an engineering-style exploded render on seamless white, the single most reposted product-ad look of the year.

Prompt library
Create an exploded products with inner mechanics [product], high-end product advertising, white seamless background, exploded view with inner mechanics revealed, outer shell hovering above core, micro screws and components suspended, perfect alignment guides implied, crisp soft shadow, ultra realistic, macro product photography, 100mm lens look, f/8, 8k, 1:1

Fill in [product]

Mode
Text to image
Aspect ratio
1:1
Resolution
1K
Cost
$0.044 per image

Tip For this sample the bracket [product] was filled with a matte black wireless earbud charging case.

Source Prompt by Amira Zairi (@azed_ai) · found via MeiGen.ai (jau123/nanobanana-trending-prompts)

CC BY 4.0 · Licensed by MeiGen.ai (jau123/nanobanana-trending-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Try now

No API key, no subscription

Turn a messy phone snapshot into a clean listing photo

Turn a messy phone snapshot into a clean listing photo

Why this one Removes the hands and the clutter, drops the product on pure white with a real contact shadow. The most immediately useful edit for anyone selling online.

Prompt library
Identify the main product in the uploaded photo (automatically removing any hands holding it or messy background details). Recreate it as a premium e-commerce product shot . Subject Isolation : Cleanly extract the product, completely removing any fingers, hands, or clutter . Background : Place the product on a pure white studio background (RGB 255, 255, 255) with a subtle, natural contact shadow at the base to ground it. Lighting : Use soft, commercial studio lighting to highlight the product's texture and material. Ensure even illumination with no harsh glare. Retouching : Automatically fix any lens distortion, improve sharpness, and color-correct to make the product look brand new and professional .
Mode
Image to image
Aspect ratio
1:1
Resolution
1K
Cost
$0.044 per image
Input
A casual snapshot of a product; hands or clutter in the frame are fine as long as the subject is clear (your own photo or a royalty-free product image).

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Isometric miniature city card with live weather

Isometric miniature city card with live weather

Why this one Google's flagship sample prompt: swap London for any city and the model renders landmarks, weather and a full text header in one pass.

Prompt library
Present a clear, 45° top-down isometric miniature 3D cartoon scene of London, featuring its most iconic landmarks and architectural elements. Use soft, refined textures with realistic PBR materials and gentle, lifelike lighting and shadows. Integrate the current weather conditions directly into the city environment to create an immersive atmospheric mood. Use a clean, minimalistic composition with a soft, solid-colored background. At the top-center, place the title "London" in large bold text, a prominent weather icon beneath it, then the date (small text) and temperature (medium text). All text must be centered with consistent spacing, and may subtly overlap the tops of the buildings.
Mode
Text to image
Aspect ratio
1:1
Resolution
1K
Cost
$0.044 per image

Tip This prompt already has the city filled in as London; swap London for another city when you reuse it (placeholder concept: CITY).

Source Prompt by Google · From the model's own documentation

Try now

No API key, no subscription

A room pulled apart in 3D, every surface still lit

A room pulled apart in 3D, every surface still lit

Why this one An exploded axonometric of an interior with its original light sources still firing across the gaps. Reads as an architecture-school poster, fully driven by placeholders.

Prompt library
[ROOM TYPE] pulled apart in 3D, every surface and object  floating at its exact position, slightly separated.  EXPLOSION: ceiling lifted, four walls sliding outward,  floor dropped, furniture floating in place,  objects orbiting their surfaces, light sources  still emitting across the exploded void.  The ghost of the room readable in the arrangement.  Labels on architectural elements only: "[SURFACE]" / "[MATERIAL]" / "[DIMENSION]"  LIGHTING: each element still lit by its original source,  windows casting light across the gap, lamps throwing cones  into empty space.  BACKGROUND: deep dark, the room floats in void. TITLE: "[ROOM NAME]" / SUBTITLE: "[BUILDING TYPE] [PERIOD]"  Mood: architectural model that became a universe. 4K, extraordinary spatial clarity, tack sharp.

Fill in [ROOM TYPE] [SURFACE] [MATERIAL] [DIMENSION] [ROOM NAME] [BUILDING TYPE] [PERIOD]

Mode
Text to image
Aspect ratio
16:9
Resolution
1K
Cost
$0.044 per image

Tip For this sample the seven brackets were filled to describe a 1930s hotel reading room: coffered ceiling, walnut panelling, 6.4 m span, titled The Reading Room, Grand Hotel, 1931.

Source Prompt by Alexandra Aisling (@AllaAisling) · found via MeiGen.ai (jau123/nanobanana-trending-prompts)

CC BY 4.0 · Licensed by MeiGen.ai (jau123/nanobanana-trending-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Try now

No API key, no subscription

Casual selfie into a studio business headshot

Casual selfie into a studio business headshot

Why this one Specifies the lens, the three-point rig and visible skin pores, so the result reads as a real studio session instead of an airbrushed filter.

Prompt library
Keep the facial features of the person in the uploaded image exactly consistent . Dress them in a professional navy blue business suit with a white shirt, similar to the reference image. Background : Place the subject against a clean, solid dark gray studio photography backdrop . The background should have a subtle gradient , slightly lighter behind the subject and darker towards the edges (vignette effect). There should be no other objects. Photography Style : Shot on a Sony A7III with an 85mm f/1.4 lens , creating a flattering portrait compression. Lighting : Use a classic three-point lighting setup . The main key light should create soft, defining shadows on the face. A subtle rim light should separate the subject's shoulders and hair from the dark background. Crucial Details : Render natural skin texture with visible pores , not an airbrushed look. Add natural catchlights to the eyes . The fabric of the suit should show a subtle wool texture.Final image should be an ultra-realistic, 8k professional headshot.
Mode
Image to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image
Input
A front-facing selfie or half-body casual photo with clear, unobstructed facial features.

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Relight a flat portrait into golden-hour film

Relight a flat portrait into golden-hour film

Why this one The classic one-prompt lighting fix: same face, new hour of the day, Kodak Portra grain and window-side warmth. Side-by-side before/after sells itself.

Prompt library
Keep the facial features of the person in the uploaded image exactly consistent . Style : A cinematic, emotional portrait shot on Kodak Portra 400 film . Setting : An urban street coffee shop window at Golden Hour (sunset) . Warm, nostalgic lighting hitting the side of the face. Atmosphere : Apply a subtle film grain and soft focus to create a dreamy, storytelling vibe. Action : The subject is looking slightly away from the camera, holding a coffee cup, with a relaxed, candid expression. Details : High quality, depth of field, bokeh background of city lights.
Mode
Image to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image
Input
An ordinary indoor or flatly lit portrait; dull lighting is fine, this prompt exists to fix exactly that.

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Promotional poster with three tiers of real text

Promotional poster with three tiers of real text

Why this one Tests the thing people actually care about: title, offer badge and footer all spelled correctly and sitting inside the photo's depth of field.

Prompt library
Design a professional promotional poster for a [Coffee Shop]. Composition : A cinematic close-up of a steaming cup of cappuccino on a rustic wooden table, autumn leaves in the background (cozy atmosphere). Text Integration :
1. Main Title : 'Autumn Special' written in elegant, gold serif typography at the top.
2. Offer : 'Buy One Get One Free' clearly displayed in a modern badge or sticker style on the side.
3. Footer : 'Limited Time Only' in small, clean text at the bottom. Quality : Ensure all text is perfectly spelled, centered, and integrated into the image's depth of field.

Fill in [Coffee Shop]

Mode
Text to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image

Tip For this sample the bracket [Coffee Shop] was kept at its own worked example value; swap it for any other business name.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Vintage patent filing for any invention you name

Vintage patent filing for any invention you name

Why this one Fills one slot with any object and returns a full 1800s patent page: numbered figures, fountain-pen notes, foxed paper and a wax seal. A dense text-rendering stress test.

Prompt library
A vintage patent document for {argument name="invention" default="INVENTION"}, styled after late 1800s United States Patent Office filings. The page features precise technical drawings with numbered callouts (Fig. 1, Fig. 2, Fig. 3) showing front, side, and exploded views. Handwritten annotations in fountain-pen ink describe mechanisms. The paper is aged ivory with foxing stains and soft fold creases. An official embossed seal and red wax stamp appear in the corner. A hand-signed inventor's name and date appear at the bottom. The entire image feels like a recovered archival document—authoritative, historic, and slightly mysterious.

Fill in {argument name="invention" default="INVENTION"}

Mode
Text to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image

Tip For this sample the invention slot was filled with a mechanical typewriter.

Source Prompt by Alexandra Aisling (@AllaAisling) · found via YouMind OpenLab (YouMind-OpenLab/awesome-nano-banana-pro-prompts)

CC BY 4.0 · Licensed by YouMind OpenLab (YouMind-OpenLab/awesome-nano-banana-pro-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Try now

No API key, no subscription

Exploded vertical infographic of any dish

Exploded vertical infographic of any dish

Why this one Layers of one dish float apart on white with pointer labels. Works for a burger, a latte or a bowl of noodles by changing a single word.

Prompt library
Create a hyper-realistic exploded vertical infographic composition of [FOOD].
At the top, characteristic particles, droplets, or garnishes associated with the food, frozen mid-air.
Below it, the primary surface or topping layer with rich texture and realistic material detail.
Underneath, the core ingredient layer showing structure, depth, and natural variation.
Below that, the supporting base or interior layer, slightly separated to reveal construction.
At the bottom, a minimal plate, bowl, cup, or base appropriate to the food’s presentation.
Pure white background, soft studio lighting, subtle shadows beneath each floating element, ultra-sharp focus, DSLR macro photography, clean infographic text labels with thin pointer lines, premium editorial food photography aesthetic, 8K quality.

Fill in [FOOD]

Mode
Text to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image

Tip For this sample the bracket [FOOD] was filled with a double cheeseburger.

Source Prompt by TechieSA (@TechieBySA) · found via MeiGen.ai (jau123/nanobanana-trending-prompts)

CC BY 4.0 · Licensed by MeiGen.ai (jau123/nanobanana-trending-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Try now

No API key, no subscription

Levitating stacked food advertising on seamless white

Levitating stacked food advertising on seamless white

Why this one A short keyword-style prompt that reliably lands the high-key floating-food look used in packaged-goods ads. Cheap to iterate, obvious when it works.

Prompt library
[subject], premium food advertising, white seamless background, high key studio lighting, floating stacked composition, levitating pieces, [ingredient_bits] scattered, clean minimal layout, crisp soft shadow on surface, ultra realistic, macro product photography, 100mm lens look, f/8 sharp focus, subtle texture detail, editorial commercial, 8k

Fill in [subject] [ingredient_bits]

Mode
Text to image
Aspect ratio
1:1
Resolution
1K
Cost
$0.044 per image

Tip For this sample the brackets [subject] and [ingredient_bits] were filled with a stack of blueberry pancakes and blueberries and butter curls.

Source Prompt by Amira Zairi (@azed_ai) · found via MeiGen.ai (jau123/nanobanana-trending-prompts)

CC BY 4.0 · Licensed by MeiGen.ai (jau123/nanobanana-trending-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Try now

No API key, no subscription

Tiny 3D figures bagged like a collectible drop

Tiny 3D figures bagged like a collectible drop

Why this one A blind-box product shot in four lines: transparent bag, ribbon, printed tag. Reads as a real photograph and takes any subject you drop into the bracket.

Prompt library
A high-resolution photograph of a clear plastic drawstring bag placed on a light gray background. Inside the bag are multiple tiny 3D [subject] figures arranged neatly. The bag is tied with a soft white ribbon and has a black label tag that reads ‘[LABEL TEXT]’. Soft lighting and clean shadows emphasize the realistic textures and details

Fill in [subject] [LABEL TEXT]

Mode
Text to image
Aspect ratio
1:1
Resolution
1K
Cost
$0.044 per image

Tip For this sample the brackets [subject] and [LABEL TEXT] were filled with astronaut and MINI CREW.

Try now

No API key, no subscription

Napkin wireframe into a high-fidelity app mockup

Napkin wireframe into a high-fidelity app mockup

Why this one Reads scribbles as components: rectangles become gradient buttons, lines become text blocks, and the whole screen lands inside a phone frame. Before/after is unmistakable.

Prompt library
Transform this rough wireframe sketch into a high-fidelity UI design mockups for a mobile app. Design System : Apply a modern, clean aesthetics similar to iOS 18 or Material Design 3 . Use rounded corners, soft drop shadows, and a vibrant primary color. Components : Intelligently interpret the sketch: turn scribbles into high-quality placeholder images , convert rough rectangles into proper buttons with gradients , and turn lines into realistic text blocks . Layout : Ensure perfect padding and consistent spacing between elements. Context : Place the design inside a realistic iPhone 16 frame mockups.
Mode
Image to image
Aspect ratio
3:4
Resolution
1K
Cost
$0.044 per image
Input
A hand-drawn app wireframe sketch (on paper or a whiteboard, either works) with recognizable boxes and text lines.

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Flat isometric illustration sized for a web hero

Flat isometric illustration sized for a web hero

Why this one The pastel isometric vector look every SaaS landing page uses, on a white or light-gradient ground so it drops straight into a hero section.

Prompt library
A flat isometric digital illustration of [describe the subject: e.g., a modern workspace, a city block, a group of app icons, a sports shop], clean lines and geometric forms, bright pastel colors, simplified perspective with 3D depth, minimal shading, white background or light gradient. Style resembles modern vector infographics, ideal for UI, app design or web visuals.

Fill in [describe the subject: e.g., a modern workspace, a city block, a group of app icons, a sports shop]

Mode
Text to image
Aspect ratio
16:9
Resolution
1K
Cost
$0.044 per image

Tip For this sample the subject bracket was filled with a modern home workspace with a desk, a laptop, shelves and potted plants.

Try now

No API key, no subscription

Clear the tourists out of your holiday photo

Clear the tourists out of your holiday photo

Why this one Deletes background crowds and refills the space with matching pavement, benches or grass at the same grain and focus depth. The demo everyone understands without explanation.

Prompt library
Remove all the tourists/people in the background behind the main subject. Intelligent Fill : Replace them with realistic background elements that logically fit the scene (e.g., extend the cobblestone pavement, empty park benches, or grass textures). Consistency : Ensure no blurry artifacts or 'smudges' remain. The filled area must have the same grain, focus depth, and lighting as the rest of the photo.
Mode
Image to image
Aspect ratio
4:3
Resolution
1K
Cost
$0.044 per image
Input
A group photo at a landmark with a clear subject and passersby cluttering the background.

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

Expand a cramped photo into a 16:9 wallpaper

Expand a cramped photo into a 16:9 wallpaper

Why this one Extends both sides with matching light, weather and texture and completes objects cut by the original frame. Turns any tight shot into a usable banner or wallpaper.

Prompt library
Zoom out and expand this image to a 16:9 aspect ratio (computer wallpaper size). Context Awareness : Seamlessly extend the scenery on both left and right sides. Match the original lighting, weather, and texture perfectly. Logical Completion : If there are cut-off objects (like a shoulder, a tree branch, or a building edge) on the borders, complete them naturally based on logical inference. Do not distort the original center image.
Mode
Image to image
Aspect ratio
16:9
Resolution
1K
Cost
$0.044 per image
Input
A tightly framed photo (landscape or portrait both work) with scenery at the edges that can plausibly be extended.

Tip The before photo used for this sample was generated in-house with this model's text-to-image mode, not sourced from the web or a real photo.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Try now

No API key, no subscription

What this model cannot do

Prompts we ran and did not ship. Each one failed the same way twice.

Turn a 2D floor plan into an interior design board

Prompt library
Based on the uploaded 2D floor plan, generate a professional interior design presentation board in a single image. Layout : The final image should be a collage with one large main image at the top, and several smaller images below it. Content of Each Panel :
1. Main Image (Top) : A wide-angle perspective view of the main living area , showing the connection between the living room and dining area.
2. Small Image (Bottom Left) : A view of the Master Bedroom , focusing on the bed and window.
3. Small Image (Bottom Middle) : A view of the Home Office / Study room .
4. Small Image (Bottom Right) : A 3D top-down floor plan view showing the furniture layout. Overall Style : Apply a consistent Modern Minimalist style with warm oak wood flooring and off-white walls across ALL images. Quality : Photorealistic rendering, soft natural lighting.

How it failed Both runs garbled the room labels in the 3D floor plan: the first spelled BATH as BATN and turned a dimension into 5.7in a 4.0m; the second spelled KITCHEN as KITCHCN, turned the master bedroom dimension into a string of noise characters, and added an extra, cropped duplicate floor plan on the right. The panel count also missed the one large plus three small layout the prompt asked for.

Source Prompt by 01Founder (WeChat) · found via ZeroLu (ZeroLu/awesome-nanobanana-pro) · Quoted with credit and a link to the original

Nine-expression 3D sticker set from one selfie

Prompt library
Using the uploaded selfie as the ONLY and exclusive face reference, generate a Pixar-style 3D character sticker set. The character must be clearly recognizable as the person from the selfie. Create a neat 3×3 grid collage (nine stickers total). Final aspect ratio is strictly 4:5. Each cell shows a distinct pose and facial expression. Style and tone: Pixar-style 3D animation with a meme-oriented feel. Exaggerated, slightly absurd emotions, playful overacting. 

Highly readable expressions at small sizes, with expressive eyes, eyebrows, and mouth. Subtle hand gestures where appropriate. Background and output: Fully transparent background (PNG). No backdrop, no background shadows. No text, captions, logos, or UI elements. Stickers must be ready for direct use in messengers. Consistency: Same hairstyle, clothing, colors, and character proportions across all nine stickers. Only facial expression and pose change.

Clean, polished 3D sticker look. Emotions (one per sticker, 3×3 grid): Surprised, Annoyed, Confused, Frustrated, Thoughtful, Sarcastic, Worried, Bored, Curious.

How it failed Both runs failed to produce a transparent background: the model painted the grey and white checkerboard that represents transparency directly into the image as a pattern, and the output itself carries no alpha channel. The second run also broke the explicit no text, captions instruction from the prompt by adding a caption naming the emotion under each of the nine cells.

Source Prompt by Oogie (@oggii_0) · found via MeiGen.ai (jau123/nanobanana-trending-prompts)

CC BY 4.0 · Licensed by MeiGen.ai (jau123/nanobanana-trending-prompts). Prompt text unchanged. Not an endorsement of Vidney.

Where to take this instead

  • Nano Banana Pro is the model we would point at dense in-image type, so the same request has a chance there. Nano Banana Pro model page

Frequently asked questions

Can I use these prompts for free?

Yes. Copy any prompt and run it wherever you like. Each card names the original author and the licence it was published under, so you can check the terms yourself. The ones written by us are free to reuse with no conditions.

Do I need an account to run one?

Copying a prompt needs no account at all. Generating on Vidney does, and every new account starts with free credits, so the first runs cost you nothing.

What are the words in square brackets?

They are the parts you swap out. Replace them with your own subject and leave the rest of the sentence alone, because the wording around them is what holds the result together.

How much does one image cost?

Every card shows the credit cost for the settings listed next to it, read from our live price table rather than typed in by hand. Change the resolution and the cost moves with it.

Why is there a list of prompts that failed?

Because knowing the ceiling is as useful as knowing the floor. Anything that failed the same way twice goes in that section with a note on how it failed, instead of quietly disappearing.

Run all 15 prompts for about $0.65