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.
Coffee Shop Art: Anime, Sketch & Claymation Characters
With Nano Banana Pro it's easy to combine different styles in a single image. In this photo we've included an anime character, a sketched character and a claymation one, all with just a prompt.
Full prompt and result
Collage of four portraits
A collage of four portraits, each featuring a young Asian woman with long, wavy brown hair, styled with a small checkered bow clip on the right side. She has soft, natural makeup. Top Left: The woman is holding a light brown mug with a bear…
Full prompt and result
Comic / Storyboard - 12-Panel Sticker/Emoji Grid Generation Prompt
Generate 4 images based on the prompt, maintaining consistency in style with the original image. Each image should have 12 panels, and the prompt for each panel is as follows. Image aspect ratio: Vertical 4:3: 1 Full of energy Go! {argumen…
Full prompt and result
Comic / Storyboard - 3D Animated Scene of Chicks and a Monster on Lily Pads
Two small fluffy chicks seen from behind, standing together on a floating green lily pad, their backs fully facing the camera, maintaining their exact proportions and silhouettes. The chicks are positioned at the very bottom foreground of…
Full prompt and result
Comic / Storyboard - B2B Meta Ad Carousel Story Creation Prompt
Just give instructions like turning the carousel story into a comic creative
Full prompt and result
Comic / Storyboard - Cinematic 3x2 storyboard grid from a single image reference
Use the uploaded photograph as the only visual reference. The person’s identity must be preserved with maximum accuracy: face, facial features, age, gender, body proportions, and overall appearance must remain unchanged. Do not invent or ad…
Full prompt and result
Comic / Storyboard - Comic Book Poster Illustration Template
{ "meta": { "purpose": "Comic book poster illustration for viral sci-fi storytelling or graphic novels", "style": "Modern comic/graphic novel with halftone and dynamic effects, 4K resolution" }, "reference_image": { "use":…
Full prompt and result
Comic / Storyboard - Converting Video to 4-Panel Manga
From Kling video footage to 4-panel manga using Nano Banana Pro
Full prompt and result
Comic / Storyboard - Detailed Cinematic Wuxia Scene Prompt: Dark Raven vs. Azure Frost
Overall Style Prompt: Chinese Wuxia fantasy style, cinematic quality, motion blur, abandoned ancient temple in heavy rain, gloomy sky, lightning occasionally illuminating raindrops and broken eaves, the image is full of power and speed. •…
Full prompt and result
Comic / Storyboard - Dramatic Historical Scene Generation with Emotional Dialogue
Xiao Jingheng, his face covered in blood, draws his sword and points it at Shen Qingtang, shouting hysterically: "I have accompanied you through ninety-nine reincarnations, yet you still haven't defeated him! My intolerance for stupidity is…
Full prompt and result
Comic / Storyboard - Image-to-Image Action Generation Template
Please generate an image where the person in the first image {argument name="action" default="does XXX"} within the second image.
Full prompt and result
Comic / Storyboard - Multi-panel black and white film photo of model
Attractive model wearing white bodycon dress, Kodak 35mm black and white film, multi-panel composed of three vertical photos, flash photography, no edits, 35mm film grain dust scratches, analog aesthetics. Aspect ratio 16:9.
Full prompt and result
Compact Camera Screen Display
Use facial feature of attached photo. A close-up shot of a young woman displayed on the screen of a compact Canon digital camera. The camera body surrounds the image with its buttons, dials, and textured surface visible, including the FUNC/…
Full prompt and result
Completing the look with a chunky silver chain around his ne
completing the look with a chunky silver chain around his neck, dark round frame sunglasses and a wristwatch. The subject holds a metallic baseball bat and poses with one hand in his pocket, displaying a confident, defiant attitude. The bac…
Full prompt and result
Concept:Hyper-realistic Morning Selfie
{"image_request":{"concept":"Hyper-realistic Morning Selfie","reference_preservation":{"target_area":"Face","preservation_level":"100%","method_suggestion":"ControlNet (IP-Adapter/FaceID) or Reactor Plugin"},"prompts":{"positive":"Hyper-rea…
Full prompt and result
Conceptual Photo: Woman's Mascara Cleaned by Mini Worker
{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "text_to_image_surreal_photoreal_concept_ad", "version": "v3.0_MASCARA_CLEANUP_CLIMBER_CONCEPT", "priority": "highest" },…
Full prompt and result
Confident Woman in Pink Activewear at Modern Gym
{ "meta_instructions": { "priority_level": "CRITICAL", "directive": "IDENTITY_LOCK_PROTOCOL", "description": "The generation engine must prioritize maintaining the exact facial structure, features, and specific body topography…
Full prompt and result
Confident Woman on Harley-Davidson Motorcycle Fashion
{ "use_reference_image": true, "strict_identity_lock": true, "alter_face": false, "notes": "Preserve 100% of the woman’s facial features, proportions, skin texture, hairstyle, and expression exactly as in the reference image…
Full prompt and result
Couple Making Snow Angels in Heart | Winter Romance Photo
{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_cinematic_winter_couple_snow_heart_close", "version": "v1.2_SNOW_HEART_COUPLE_FACE_VISIBLE_CLOSER", "priority": "highes…
Full prompt and result
Cozy Autumn Couple Illustration in City Street Scene
{ "design_system": { "metadata": { "style_name": "Cozy Storybook Illustration", "target_audience": "Children / Family", "reference_source": "Uploaded Image", "version": "3.0" }, "visual_parameters": {…
Full prompt and result
Cozy indoor portrait of a young woman sitting on a sofa
A cozy indoor portrait of a young woman sitting on a sofa, wearing a loose, off-shoulder knitted sweater. She is quietly reading a book while blowing a small pink bubble with chewing gum. Her hair is tied in a relaxed messy bun, and a warm…
Full prompt and result
Create a 4 panel manga titled I was reincarnated into anothe
create a 4 panel manga titled "I was reincarnated into another world as an ai researcher"
Full prompt and result
Create a cinematic vintage-romantic portrait featuring a sty
{"Objective":"Create a cinematic vintage-romantic portrait featuring a stylish girl in long boots with curly hair smoking, standing beside a mysterious man in a black coat and classic hat. Capture them in an old Rome–like street with warm r…
Full prompt and result
Create a hyper-realistic portrait of the beautiful woman from the reference phot
Create a hyper-realistic portrait of the beautiful woman from the reference photo, presented inside an oversized Instagram post frame that dominates the scene. Her facial features remain identical to the reference delicate yet sharp, clean,…
Full prompt and result
Create a natural winter portrait featuring a young woman and
{"Objective":"Create a natural winter portrait featuring a young woman and her small puppy with realistic emotional warmth.","Persona_Details":{"Primary_Subject":{"Type":"Young woman","Characteristics":{"Hair":"Soft, long wavy dark-brown ha…
Full prompt and result
Create a photo of python code to calculate the fibonacci num
create a photo of python code to calculate the fibonacci numbers drawn on a glass whiteboard with coloring markers
Full prompt and result
Create a photo-realistic close-up portrait based on the prov
{"Objective":"Create a photo-realistic close-up portrait based on the provided description.","Subject":{"Person":"Man in uploaded picture","Facial_Requirement":"Use the same face and facial features as the uploaded image","Expression":"Look…
Full prompt and result
Create a portraitt of A beautiful young woman standing near
Create a portraitt of A beautiful young woman standing near a window during sunset holding a small bouquet of soft pastel roses. She has long wavy dark brown hair that shines gently in the fading light cascading over her shoulders. Her skin…
Full prompt and result
Create a realistic portrait image of a young woman (face 100% identical to the o
Create a realistic portrait image of a young woman (face 100% identical to the original attached image) Asian fashion of a slender young woman. She wears a thick green knit crop top with a Christmas reindeer toy attached, white jeans, stand…
Full prompt and result
Create a realistic portrait of a young woman (keep the face
Create a realistic portrait of a young woman (keep the face and appearance 100% identical to the reference — do not alter anything). The woman is in the water beside a metal pool ladder at night. The poolside tiles are small gray squares. I…
Full prompt and result
Create or analyze an image based on a detailed scene descrip
{"Objective":"Create or analyze an image based on a detailed scene description with enhanced customization options.","Persona_Details":{"Primary_Subject":{"Type":"Young woman","Characteristics":{"Hair":"Long, wavy brown hair","Clothing":"Br…
Full prompt and result
Created with nano banana pro:
Created with nano banana pro: Cinematic high grain 90s portrait Dutch angle tilted shot, 23-year-old woman leaning against tree taking picture dynamic composition, wearing oversized flannel shirt layers winter, long hair hanging sideways, s…
Full prompt and result
Culinary Atlas: Chicken & Bacon Dishes, Global Food History
Nano Banana Pro vs. GPT Image 1.5 for my food recommendation prompt. Just give it a couple of ingredients. <instruction> Inputs: Ingredients = [User Choice, e.g., Chicken, Bacon] Step 1: Global Analysis Analyze the ingredients. Select 4…
Full prompt and result
Cutaway illustration of a cruise ship
A cutaway illustration of a cruise ship. We see the engine room, the ballroom, the pool deck, the cabins. Tiny people doing different things in each room. 'Where's Waldo' level of detail. Vector art style.
Full prompt and result
Cute 3D Render Character: Pink Hair Girl with Modern Outfit
{ "subject": { "type": "chibi-style 3D character", "gender": "female", "features": { "hair": "pastel pink bob cut with soft bangs, stylized 3D strands", "eyes": "large expressive dark eyes, looking upward and to th…
Full prompt and result
Cute and aesthetic winter portrait featuring a woman in an oversized pastel hood
Cute and aesthetic winter portrait featuring a woman in an oversized pastel hoodie, sleeves covering her hands as she warms them with her breath. Add minimal makeup, soft cold-blush cheeks, and straight hair falling naturally. Background: b…
Full prompt and result
Cybernetic Samurai Gear, Robots & Sci-Fi City Scenes
Panel 8) portrait of fierce cyber-samurai warrior centered on pure white background. Professional product photography style.
Full prompt and result
Cyberpunk female assassin stands in the pouring rain
A cyberpunk female assassin stands in the pouring rain, gripping a glowing red katana as neon lights reflect off the wet pavement. Her slick, drenched black outfit clings to her form while her futuristic goggles emit intense red illuminatio…
Full prompt and result
D-Day Landing WWII Soldiers Omaha Beach Black White Photo
"create an image at [COORDINATES], [DATE & TIME]."
Full prompt and result
Delicious Burger Exploded View - Fresh Ingredients
The burger fills approximately 90% of the frame, centered, fully visible, not a macro close-up. Exactly five clearly readable layers: glossy brioche bun, juicy beef patty, melted cheese, fresh lettuce, ripe tomato. Shot at a clean three-qu…
Full prompt and result
Depth and architectural lines
{"prompt_structure":{"subject_preservation":{"face_and_body":"Strict adherence to reference image facial features and body proportions","hair_modification":"Original hairstyle retained but refined with enhanced soft volume, definition, and…
Full prompt and result
Depth and visual clutter in the background
{"label":"direct-flash-gamer-girl","tags":["direct-flash","retro-gamer-room","90s-photography","film-aesthetic","gamer-girl","collectibles-shelf","low-angle","sitting-pose"],"CompositionalPortrait":1,"Style":["direct-flash-photography-3","8…
Full prompt and result
Depth and volume in two-dimensional works
Chiaroscuro is an artistic technique using strong light-dark contrasts to create depth and volume in two-dimensional works. The Italian term means “light-dark.” While used throughout art history, it became especially prominent during the Re…
Full prompt and result
Describe in an illustration the events for a cytotoxic T cell recognizing & kill
Describe in an illustration the events for a cytotoxic T cell recognizing & killing a cancer cell.
Full prompt and result
Description": "A low-angle, full-body cinematic portrait.",
{ "description": "A low-angle, full-body cinematic portrait.", "subject": { "description": "A young woman (face identical to the reference photo).", "position": "Sitting directly on the hood of an old, rusty car.", "gaze": "…
Full prompt and result
Descriptionscenea Glamorous Woman Posing Dramatically In A Hotel
{"description":{"scene":"A glamorous woman posing dramatically in a hotel corridor, framed inside an elevator.","appearance":{"hair":"Light brown hair styled in soft waves.","makeup":"Bold red lipstick with a darker eye makeup look.","acces…
Full prompt and result
Descriptionthe Image Depicts A Woman Sitting On A
{"description":"The image depicts a woman sitting on a black leather chair, wearing a black bodysuit with a mesh overlay adorned with black polka dots. She has long, wavy blonde hair and is accessorized with a black watch and tan high heels…
Full prompt and result
Detailed mirror-selfie otaku room scene
### Scene Mirror selfie in an otaku-style computer corner, blue color tone. ### Subject * Gender expression: female * Age: around 25 * Ethnicity: East Asian * Body type: slim, with a defined waist; natural body proportions * Skin tone: lig…
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