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.
Diminutive street musician
a diminutive street musician, no taller than a wine bottle, performing atop a stack of vintage leather-bound books in a cozy Parisian bookshop. The tiny violinist wears a patchwork coat of jewel-toned velvet scraps and miniature brass butto…
Full prompt and result
Disposable camera picture with the classic harsh flash
A disposable camera picture with the classic harsh flash, capturing a messy living room after a chaotic party night. The mood is silly, slightly drunk, chaotic, and humorous. In the center of the scene is a low wooden coffee table completel…
Full prompt and result
Donald Trump Miniature in Suitcase - Political Novelty
{ "prompt": "Create a hyper-realistic, ultra-detailed cinematic photo featuring a MINIATURE version of the person from the provided reference image (preserve facial likeness, skin tone, hairstyle, and overall identity). The tiny character…
Full prompt and result
Dramatic contrast
Hyper-detailed, ultra-realistic illustration of an owl emerging from dense jungle foliage. The owl has glowing amber eyes, sharp intricate feather textures, and an intense forward gaze. Surrounding leaves are stylized in deep blacks and gre…
Full prompt and result
Dramatic, low-angle portrait of a woman standing in a dark
A dramatic, low-angle portrait of a woman standing in a dark, minimalist space, illuminated by a sharp beam of light that carves across her face and shoulders. She wears transparent, modern glasses that catch the glow, adding geometric refl…
Full prompt and result
Draw a detailed pet shop scene and label every object with E
Draw a detailed {{pet shop}} scene and label every object with English words. Label format: - First line: English word - Second line: IPA pronunciation - Third line: {Chinese} translation
Full prompt and result
Draw an anime poster for the 2025 World Series: The Dodgers
Draw an anime poster for the 2025 World Series: The Dodgers vs. Blue Jays, featuring the starting lineups for both teams. The players' jersey numbers must match real-life. The best hitters and starting pitchers for both teams should be incl…
Full prompt and result
Draw an illustration of GARP biology for Tregs
Draw an illustration of GARP biology for Tregs
Full prompt and result
Drawing from this photo without changing the face
Create a drawing from this photo without changing the face. Subject: Woman with ash brown hair, wolf cut. Wearing the outfit shown in the second image. White sneakers. Small, cat-eye sunglasses. Position: The subject is sitting leaning agai…
Full prompt and result
Dynamic Chocolate Chip Cookies & Milk Splash Food Photo
{ "production_manifest": { "metadata": { "series_id": "CIN-FOOD-2025", "aspect_ratio": "9:16", "resolution_target": "8k_uhd" }, "technical_stack": { "hardware": { "camera": "ARRI Alexa 65",…
Full prompt and result
Dystopian Mega-Corp Skyscraper: Futuristic Architecture Concept
Step 2: Scale this object up by 5000%. It is now the headquarters for a villainous mega-corporation in a Brutalist concrete future. Analyze the geometry to create habitable floors." Step 3 Output: 2x2 Grid. Grid 1 & 2: Blueprints of the "O…
Full prompt and result
Edit the photo to be standing casually in a modern style elevator with reflectiv
Edit the photo to be standing casually in a modern style elevator with reflective metal walls. He is wearing an all black outfit: a black suit and trousers, wearing sunglasses and holding a cup of take-away coffee. Elegant and edgy style wi…
Full prompt and result
Edit This Photo Into A Vertical Portrait, Hyper-Realistic,
Edit this photo into a vertical portrait, hyper-realistic, shot in 1080x1920 format, with cinematic lighting featuring sharp, intense contrast. Captured from a slightly low angle pointing upward, emphasizing the subject’s jawline and neck,…
Full prompt and result
Edit this photo without changing the face turning it into an artistic portrait T
Edit this photo without changing the face turning it into an artistic portrait The woman should be elegantly seated on the floor, wearing a modern black top, soft loose gray jeans, and chunky gray and white sneakers. She has long, waist-len…
Full prompt and result
Editorial fashion photo, medium portrait, seated model wearing a cream shearling
Editorial fashion photo, medium portrait, seated model wearing a cream shearling jacket (shaggy texture), denim shirt layered, light blue jeans, black leather Chelsea boots, beige socks, relaxed pose with one leg bent, hand supporting the h…
Full prompt and result
Edo-period Ukiyo-e reinterpretation of a modern scene
A Japanese Edo-period Ukiyo-e woodblock print. The overall feeling is a surreal collaboration between masters like Hokusai and Hiroshige, reimagining modern technology through an ancient lens. **The scene:** {argument name="modern scene" d…
Full prompt and result
Einstein would totally wear Patagonia and an Apple Watch
Einstein would totally wear Patagonia and an Apple Watch
Full prompt and result
Elegant Backless Dress Portrait at Sunset | Golden Hour Fashion
{ "image_prompt": { "reference": { "face_identity": "use uploaded female reference image", "identity_lock": true, "face_accuracy": "100% identical to reference — same facial structure, proportions, skin texture, eye…
Full prompt and result
Elegant Black Dress Woman Christmas Staircase Fashion Shoot
{ "shot_type": "A medium shot portrait", "subject": "a young woman", "hair": "long, wavy hair", "pose": "standing on a curved staircase with dark wrought-iron railings and stone steps. She poses looking back over her right shoulder…
Full prompt and result
Elegant Blonde Woman Night Portrait in Red Strapless Dress
{ "meta": { "project": "Night_Elegance_RedDress_Blonde_Flux_V5.2", "target_engine": "Flux.1 [dev] / Nano Banana Pro", "version": "5.2.0 (Balanced Natural Beauty)", "created_at": "2025-12-26T03:45:00Z" }, "engine_config…
Full prompt and result
Elegant Man in Black on Urban Balcony | Night City Fashion
{ "prompt": "A hyper-realistic 8k cinematic medium-wide shot captured with a 35mm lens at a low authoritative angle. A person with the uploaded face as reference stands alone on a polished marble balcony of a high-rise penthouse overlooki…
Full prompt and result
Elegant Woman in Black Dress on Grand Staircase - Fashion
{ "image_analysis_prompt": { "subject": { "demographics": "Young woman, slender build, light skin tone", "hair": "Dark brunette, styled in a sleek, tight low bun with a middle part", "expression": "Neutral, elegant,…
Full prompt and result
Elegant Woman in Luxury Car - Fashion Portrait
{ "project_constraints": { "facial_rendering": "100% original facial features (Do not edit the face)", "resolution": "1200x1200px", "output_quality": "Photo-realistic, 8K resolution" }, "camera_and_style": { "device_em…
Full prompt and result
Elegant Woman in Red Satin Dress | Grand Hall Fashion
{Use the face without any change. "image_generation_prompt": { "subject": { "type": "Young woman", "hair": "Long, dark brunette, loose waves, parted in the middle", "pose": "Standing full-body, leaning backwards agai…
Full prompt and result
Elegant Women, Formal Dresses, Fireworks Night Event
{ "prompt_type": "Ultra Photorealistic Group Portrait", "subject_details": { "main_subjects": "Group of four young women celebrating", "subject_1_left": "Young woman with long dark wavy hair, wearing a beige/gold sleeveless sequ…
Full prompt and result
Elon Musk Volcanic Rock Bust 3D Render - Digital Art
{ "task": "image_to_image_style_transfer", "input_image": "{{USER_IMAGE}}", "prompt": "Reimagine the subject as a hyper-real fragmented volcanic basalt construct, assembled from jagged, sharply defined basalt plates suspended in space…
Full prompt and result
Environment:sunny_boardwalk
{"scene":{"environment":"sunny_boardwalk","details":"wooden_planks, colorful_stalls, people_walking, distant_umbrellas","lighting":"bright_midday_sun","sky":"clear_blue"},"camera":{"lens":"ultra_wide_fisheye_12mm","distance":"very_close_up"…
Full prompt and result
Epic Sunset Sky: Sun Rays Piercing Dark Storm Clouds
Prompt on Nano Banana Pro : A dramatic sky photo where swirling storm clouds naturally form the unmistakable shape of a [SUBJECT]. The illusion should be “found shape”: at first it’s just clouds; then the creature silhouette pops out. Reali…
Full prompt and result
Evening Cityscape Portrait on a Bridge,
{ "title": "Evening Cityscape Portrait on a Bridge", "prompt_text": "A full-body portrait of a young adult female model standing on an ornate stone bridge railing at dusk. She has wavy, shoulder-length dark brown hair, styled with volum…
Full prompt and result
Every known meme character in the style of Wheres Wally
Every known meme character in the style of "Where's Wally"
Full prompt and result
Everyone is capturing this special moment, celebrating "WORLD PEACE 2025
Everyone is capturing this special moment, celebrating "WORLD PEACE 2025"
Full prompt and result
Extreme Close-up: Broken Pencil, Graphite & Wood Texture
Prompt : Imagine a pencil tip seen through a microscope. Imagine how the pencil tip would look and create an image.
Full prompt and result
Extreme Wide Angle Phone Screen Replacement
{ "edit_type": "extreme_wide_angle_phone_edit", "source": { "_hint": "Base for editing the person, clothing, and atmosphere of the original image. No new characters allowed.", "mode": "EDIT", "preserve_elements": ["Person",…
Full prompt and result
Face Detection CCTV Simulation
Create a high angle CCTV surveillance shot using the uploaded image as the source. Detect every visible person in the image and automatically draw a white rectangular bounding box around each face. For the most prominent person, add a large…
Full prompt and result
Fashion editorial interpretation of the image provided
Create a fashion editorial interpretation of the image provided, maintaining the nano-level of accuracy of all key elements. Maintain an intellectual understanding of the scene: leave the girl's initial pose, the soft movement of her hair,…
Full prompt and result
Fashion Editorial Interpretation
{"project_directive":"Fashion Editorial Interpretation","resolution":"1200x1200px","scene_composition":{"preservation_mandate":{"accuracy_level":"Nano-level of accuracy of all key elements","subject_pose":"Maintain initial pose, soft moveme…
Full prompt and result
Fashion Portrait: Woman in Black Jumpsuit on City Street
{ "overall_description": { "style": "Ultra-photorealistic fashion editorial", "mood": "Moody, cinematic, sensual, confident, urban elegance", "setting": "Urban city street with shallow depth of field and blurred traffic lights…
Full prompt and result
Fashion Portrait: Woman in Red Dress, Elegant Balustrade
{ "image_generation_prompt": { "subject": { "type": "Young woman", "hair": "Long, dark brunette, loose waves, parted in the middle", "pose": "Standing full-body, leaning backwards against a stone balustrade, one hand…
Full prompt and result
Female_model,
{ "subject": { "type": "female_model", "ethnicity": "western", "hair": { "length": "long", "texture": "straight", "bangs": "wispy" }, "skin": "flawless", "tattoo": { "location": "upper left…
Full prompt and result
Find the latest NASA data on Mars rover discoveries this month and create an edu
Find the latest NASA data on Mars rover discoveries this month and create an educational poster for middle schoolers
Full prompt and result
Fisheye Movie Character Selfie
A film-like fisheye wide-angle 360-degree selfie without any camera or phone visible in the subject's hands. A real and exaggerated selfie of [person from uploaded image] with [CHARACTERS]. They are making faces at the camera. (more detail…
Full prompt and result
Fit Woman Gym Workout - Squat & Cable Cross Fitness
{ "scene": { "layout": "1x3_grid", "aspect_ratio": "3:2", "background": "modern_fitness_gym_with_neutral_lighting", "style": "hyper_realistic_photography" }, "subject": { "description": "the same beautiful, athlet…
Full prompt and result
Fitness Lifestyle: Woman, Workout Gear & Apple Watch
{ "task": "four_grid_lifestyle_collage", "reference_face": { "identity_lock": true, "face_match_accuracy": "100_percent_identical", "notes": "No facial changes allowed. Preserve exact facial structure, proportions, eye shape…
Full prompt and result
Floating Country Island Diorama
Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [COUNTRY], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like forests, mountains, or beaches), and cultural elem…
Full prompt and result
Format:photograph
{"image_specifications":{"format":"photograph","style":"highly detailed, Y2K-inspired, gritty","lens":"fisheye","angle":"low-angle","shot":"close-up","lighting":"harsh, high contrast","colors":"saturated","background":{"setting":"urban, dar…
Full prompt and result
Four distinct
Generate four distinct, hyper-realistic images, each depicting a world-renowned landmark. For each image, include a comprehensive and clearly legible set of annotations directly overlaid onto key architectural features, historical elements,…
Full prompt and result
Four Seasons Tree Landscape - Vibrant Nature Cycle
Hyper-realistic digital illustration of {Scene}, presented as a single continuous composition showcasing the cycle of seasons. The scene flows seamlessly from left to right in a natural progression: Winter, Spring, Summer, and Autumn. The…
Full prompt and result
Game Asset - Billie Eilish Fortnite-Style 3D Character Render
{ "subject": { "name": "Billie Eilish", "style": "Fortnite stylized 3D character model", "pose": "Dynamic mid-air jump, forward-leaning, action-oriented", "features": { "hair": "Two high space buns, black hair with v…
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