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.
Beautiful young woman
{"subject":{"description":"Beautiful young woman","age":"young adult","hair":{"color":"dark brown","length":"long","style":"straight"},"skin":{"texture":"soft, glowing","freckles":"subtle, natural across nose and cheeks"},"expression":"bold…
Full prompt and result
Behind the scene shots of new live action remake of Quake -
behind the scene shots of new live action remake of Quake - by Nano Banana Pro
Full prompt and result
Ben 10 Cinematic Poster: Photorealistic & Animated Duo
Ultra-high-resolution 8K studio portrait featuring a real human woman standing beside a stylized cartoon character of choice, full-body composition, both subjects clearly visible and centered. Human subject: young adult woman with natural…
Full prompt and result
Better visuals
Generate better visuals with more accurate, legible text directly in the image in multiple languages
Full prompt and result
Big Lebowski Pixel Art: Dude, Walter, Retro Game Screen
Have fun! Share your bests.
Full prompt and result
Black and white portrait of an elderly bearded man, full face, deep set eyes, fi
Black and white portrait of an elderly bearded man, full face, deep set eyes, fine wrinkles, strong natural light from a side, high resolution, very realistic photo-style
Full prompt and result
Black Panther Character Design - Futuristic Neon Superhero
{ "image_type": "Ultra-photorealistic studio portrait", "theme": "Wakanda Forever", "subject_details": { "view": "full body", "woman_reference": "uploaded woman (reference image given)", "attire": { "outfit": "sleek…
Full prompt and result
Blonde Woman & Pink Panther Fashion Portrait | Pink Aesthetic
{ "image_generation": { "quality": "hyper-realistic", "face": { "preserve_original": true }, "subject": { "description": "A stylish person with the same face", "clothing": { "top": { "ty…
Full prompt and result
Blonde Woman Portrait Colosseum Rome Travel Photography
{ "scene_manifest": { "version": "3.1.0", "request_type": "photorealistic_generation", "compositional_settings": { "aspect_ratio": "3:4", "framing": "Medium shot", "camera_angle": "Eye-level", "subject_…
Full prompt and result
Bohemian Fashion Woman in Marketplace - Travel Style
{ "resolution": "8K_UHD", "aspect_ratio": "2:3", "style": "travel_photography", "lighting": "natural_afternoon_sunlight" }, "subject": { "identity": "female with wavy brown hair and gold thin-rimmed glasses", "ex…
Full prompt and result
Bohemian Fashion: Woman in Red Dress Mirror Selfie Cafe
{ "image_generation_prompt": { "subject": { "reference_adherence": "Strictly match the provided reference photo face exactly", "facial_features": [ "Preserve exact face shape", "Match eye structure and eyeb…
Full prompt and result
Bratz Rock Angelz Cartoon Woman Digital Art | Pastel Aesthetic
{ "image_generation": { "face_preservation": { "preserve_original": true, "match_reference_face": true, "accuracy": "100% identical to the reference photo", "details": [ "same facial proportions",…
Full prompt and result
Bugdroid Internal Scan | Sci-Fi Thermal X-Ray Robot Art
The Google Android robot, presented in a high-contrast scientific studio render against a pure black void. This tight right-side profile features a false-color thermal X-ray aesthetic, where the transparent shell reveals a sharply detailed…
Full prompt and result
Candid 90s Party Photo | Young Man Laughing, Red-Eye
A flash photography snapshot taken on a disposable camera in 1998. A man at a chaotic house party. Red-eye effect, harsh shadows, motion blur, and film grain. The composition is slightly tilted and messy.
Full prompt and result
Candid Portrait of Young Woman in Rainy Night Car
{ "image_generation_prompt": { "subject": { "description": "Young Asian woman with long, straight dark hair, looking directly at the camera.", "attire": "Black spaghetti-strap top or dress, delicate gold necklace.",…
Full prompt and result
Canon IXUS Aesthetic Portrait
{ "image_parameters": { "style": "Canon IXUS aesthetic", "type": "Point-and-shoot photography", "quality": "Hyper-realistic", "tone": "Sharp, direct", "lighting_and_atmosphere": "Realistic, flash-style/direct lighting"…
Full prompt and result
Casual Black Athleisure Mirror Selfie - Woman's Style
{ "composition_request": { "subject_definition": { "demographics": { "gender": "female" }, "physical_attributes": { "hair": { "color": "dark brown", "texture": "straight",…
Full prompt and result
Casual Man: Photorealistic Photo to Vector Art Character
{ "prompt": "64K DSLR ultra-sharp split-reality street art portrait using the uploaded image as exact face reference. Vertical frame, man leaning against a light-gray concrete wall. Left side photorealistic: red cap, black hoodie, loose g…
Full prompt and result
Chalkboard-style AI news summary
Using the following content, summarize the news in a chalkboard-style, hand‑written look, and break it down with diagrams and easy‑to‑understand expressions as if a teacher had written it. —- Search results from Grok
Full prompt and result
Character Consistency Selfie with Movie Character
"I'm taking a selfie with [movie character] on the set of [movie name]. Keep the person exactly as shown in the reference image with 100% identical facial features, bone structure, skin tone, facial expression, pose, and appearance. 1:1 as…
Full prompt and result
Characters
{"prompt":{"characters":[{"name":"Miyeon","description":"beautiful young Korean woman, smiling, long black hair, wearing a white strapless top with black stars, silver necklace"},{"name":"Judy Hopps","description":"Disney character from Zoo…
Full prompt and result
Che Guevara leading the revolution, even in 2025
Che Guevara leading the revolution, even in 2025
Full prompt and result
Cheerful Portrait of Woman with Bugs Bunny on Purple
{ "image_generation": { "quality": "hyper-realistic, professional fashion photoshoot", "face": { "preserve_original": true }, "subject": { "clothing": "soft lavender knitted sweater, white high-waisted jeans, white sneak…
Full prompt and result
Cheerful Woman Eating Cookie in Modern Kitchen
{ "image_details": { "subject": { "demographics": "Young adult female", "hair": "Long, blonde, layered, straight with slight wave", "expression": "Playful, looking back at camera over shoulder, smiling with cookie ne…
Full prompt and result
Cheerful Woman in Tom & Jerry Sweater with Cartoon Pals
{ "description": "A stylish person with the same face.", “clothing":{ "Top": ("type": "knitted sweater", "color": "light grey (Tom Theme) ". } "pants": ("type": "high-waisted jeans", "color": "denim blue". "shoes":("type": "high-top sneake…
Full prompt and result
Cheerful Woman Posing with Pikachu - Pokémon Studio Photo
[ { "image_generation": { "quality": "hyper-realistic", "face": { "preserve_original": true }, "subject": { "clothing": "light grey knitted sweater, blue high-waisted jeans, white high-top sneakers",…
Full prompt and result
Cheerful Woman Selfie in Miami Convertible - University of Miami
{ "subject": { "description": "A young American woman taking a convertible car selfie, wind blowing through her hair, one hand playfully touching her face while smiling, Miami Beach ocean visible behind her", "mirror_rules": "N/A…
Full prompt and result
Christmas Market in Chicago
Christmas Market in Chicago A low-resolution digital picture focuses on a woman in a thick winter coat holding a mug of hot cocoa, laughing. Festive lights and blurred market stalls with holiday decorations fill the background under a ligh…
Full prompt and result
Christmas Ornament 3D Character
A transparent Christmas bauble hanging by a red ribbon. Inside, a tiny diorama of the person from the reference reimagined as a cute 3d chibi character. He works at a mini futuristic AI desk with three glowing holo-screens showing neural ne…
Full prompt and result
Cinematic 3D Night Market Alley | Rainy Urban Street Scene
open source prompt to 3D. create and explore entire worlds with your imagination using nano banana. https://sharp-ml.vercel.app built with @cursor_ai in 1hr. contributions welcome!
Full prompt and result
Cinematic Desert Walk: Solitary Figure in Orange Haze
{ "description": "A lone figure in a long coat walking across a barren landscape in thick orange-red fog.", "subject": { "type": "lone figure", "attire": "long coat", "action": "walking" }, "setting": { "location": "…
Full prompt and result
Cinematic full-body portrait of a rugged man holding a shotgun, standing beside
Cinematic full-body portrait of a rugged man holding a shotgun, standing beside an old, rusted helicopter in front of a weathered wooden building on an abandoned farm. The ground is dry and cracked, tall brown grass sways in the wind, and t…
Full prompt and result
Cinematic Keyframe Generator
<role> You are an award-winning trailer director + cinematographer + storyboard artist. Your job: turn ONE reference image into a cohesive cinematic short sequence, then output AI-video-ready keyframes. </role> <input> User provides: one r…
Full prompt and result
Cinematic, low-light photograph of a young man with dark
A cinematic, low-light photograph of a young man with dark, messy curly hair leaning casually against the railing of an outdoor industrial metal staircase at night. He is wearing a slate-grey bomber jacket open over a plain white t-shirt an…
Full prompt and result
Cinematic photograph of a stylish young blonde woman in a bikini, with a black p
Cinematic photograph of a stylish young blonde woman in a bikini, with a black phanter near her, in a pastel windbreaker in a small bikini, sipping a tropical soda inside a retro diner, super cute, vintage 1980s Miami vibes, pastel neon col…
Full prompt and result
Cinematic Portrait: Woman on Rural Road at Dusk
{ "subject": { "type": "young woman", "age": "early 20s", "appearance": { "hair": "short silver-gray hair, slightly messy", "expression": "calm, introspective, emotionally distant", "skin_tone": "natural, sof…
Full prompt and result
Cinematic Urban Night Portrait - Woman in Neon City Street
{ "request_id": "portrait_neon_urban_001", "configuration": { "model": "v6. 0_or_latest", "output_settings": { "dimensions": { "width": 1080, "height": 1920, "aspect_ratio": "9:16", "target_…
Full prompt and result
Cinematic, warm-toned beach scene at sunset
Create an ultra-cinematic, warm-toned beach scene at sunset. Center a young beautiful asian woman standing confidently at the shoreline, looking straight into the camera with a calm, almost mythic energy. She has wet, wavy hair from the oce…
Full prompt and result
Cinematic Winter Triptych
{"metadata":{"title":"Cinematic Winter Triptych","genre":"Portrait Collage","style":"Ultra-realistic, Cinematic"},"composition":{"layout_type":"Vertical stack","panels":3,"orientation":"Horizontal panels"},"subject":{"reference":"Use provid…
Full prompt and result
Cinematic_full_body_vintage_film
{"photo":{"type":"cinematic_full_body_vintage_film","face":{"preserve_original":true,"reference_match":true,"description":"The woman's face must remain exactly the same as the provided reference image, with identical features and expression…
Full prompt and result
City Evolution: Byzantion, Constantinople, Istanbul Map
Epic 3D isometric atlas scene: a massive ancient map of [SUBJECT] erupts from an unfurled parchment scroll, filling nearly the entire frame. Ink lines ignite into living terrain: mountain ranges push upward, cities rise in vertical layers,…
Full prompt and result
Class photo featuring famous manga characters such as Goku,
{"subject":"Class photo featuring famous manga characters such as Goku, Naruto, Luffy, Ichigo, Sailor Moon, Deku, and other iconic anime heroes","scene":"School gym or classroom setting with all characters standing in rows like a traditiona…
Full prompt and result
Classroom blackboard
Generate an image of a classroom blackboard with the Pythagoras theorem being solved step by step.
Full prompt and result
Close-up, eye-level selfie portrait of a young woman
Create a close-up, eye-level selfie portrait of a young woman with a fair flawless complexion, captivating light brown eyes, and long, cascading wavy brown hair with subtle highlights. Her hair is parted down the side, framing her face and…
Full prompt and result
Close-up, medium shot captures a man dressed as Batman
A close-up, medium shot captures a man dressed as Batman, appearing to be in the midst of a dramatic, action sequence. The man, who appears to be an adult, wears a dark, armored Batsuit, which covers his head and upper body with the charact…
Full prompt and result
Close-up Portrait: Woman with Wet Face, Green Eyes
{ "prompt": "Extreme wet close-up portrait, side profile of a young woman. Dark wet hair strands naturally glued to the skin. Fine droplets of water and thin sweat glistening realistically on face. Focus on bright natural green and hazel…
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