Nano Banana Pro: Google's Gemini 3 Pro Image Model for Text, Edits, and 4K

Name: Nano Banana Pro
Author: Google

Up to 4K: Resolution
Up to 14: Reference images
Up to 5: Consistent characters
Up to 4: Images per request

Overview

About Nano Banana Pro

Nano Banana Pro is Google DeepMind's Gemini 3 Pro image model, the Pro tier of the Nano Banana family alongside the faster Flash model, Nano Banana 2.1. It plans a composition before it renders, which helps with layered briefs, in-image text, and edits that must keep the rest of a picture intact.

In Masonry it generates and edits from a prompt plus up to 14 reference images, with three ways to combine them (blend, combine, or merge). Sizes run from square 1K to 4K and wide or tall formats, with custom widths and heights up to 6336 pixels, three quality levels, up to 4 images per request, a seed for repeatable results, and PNG, JPG, or WebP output.

In our six-prompt photorealism test it produced the most natural skin of the three current models we compared, with visible pores, freckles, and fine lines. It also read some prompts as a casual phone photo rather than a styled shot, so say the style you want explicitly.

Real prompts

Prompts behind these Nano Banana Pro images

Actual prompts from Nano Banana Pro renders by the Masonry community. Copy any prompt, then remix it into your own creation.

I want this image in cinematic product photoshoot with edgy backdrop.
bag
Remix

Use the images as a reference and make a fit, athletic adult 26 year old Indian male athlete looking man wearing the tank t-shirt running alone down a quiet city street during early morning golden hour. He is wearing a sleeveless blue athletic top, beige running shorts, and modern running shoes. The runner is centered in the frame, captured mid-stride with a focused, determined expression. Warm sunlight filters through leafy trees lining the street, creating soft lens flare and long shadows on the pavement. Urban buildings with classic architecture appear slightly blurred in the background, suggesting motion and depth. The scene feels energetic, healthy, and motivational. Shot at eye level with a shallow depth of field, natural light, realistic color grading, high-resolution, commercial fitness photography style.
athlete
Remix

A highly detailed, cinematic close-up lifestyle portrait of [inserted image], worn by a young woman with dark hair, captured in contemplative side profile gazing into the distance with a calm, reflective expression. Warm, natural golden-hour sunlight casting gentle highlights on the face, hair, and clothing for a serene, immersive 3D depth with a slight breeze moving the hair. Blurred lush green forest background evoking peace, escape, and connection with nature, shallow depth of field with razor-sharp focus on facial details, skin texture, and shirt material, high contrast, ultra-high resolution, professional activewear/outdoor apparel advertisement style conveying mindfulness, freedom, and the need for space to breathe similar to Technosport promotions.
fashion
Remix

A striking close-up portrait of a vividly colored lizard perched on a textured rock, captured at eye level with shallow depth of field. The reptile features an extraordinary gradient of saturated hues—electric blue scales along the body, fiery orange and red tones on the head and limbs, and subtle purple transitions across the neck and torso. Fine scale textures are sharply detailed, with glossy highlights catching the light. One large, reflective eye is in crisp focus, conveying alertness and curiosity. The background fades into a dark, softly blurred gradient, isolating the subject and enhancing contrast. Lighting is dramatic yet controlled, emphasizing color vibrancy and surface detail. The overall mood is bold, exotic, and visually arresting, ideal for wildlife art, fantasy realism, or high-end digital illustration.
Remix

a realistic Vogue magazine cover–style fashion portrait using the uploaded face as the original face reference (100% face identity preservation). A young elegant woman posing confidently, maintaining her original facial features and natural beauty. She is winking with her left eye and making a playful duck-face expression. Both hands are raised, forming a love/heart gesture near her face. She is surrounded by multiple DSLR cameras and smartphones held around her, as if paparazzi and photographers are capturing her from all directions. Some phones show her live image on their screens. Appearance & styling: flawless glowing skin, natural makeup with glossy pink lips, soft blush, subtle highlights. Light brown hair styled in a low, neat updo with a few loose strands. Outfit & accessories: elegant minimalist beige-white strapless evening dress, Louis Vuitton necklace, diamond ring, luxury fashion jewelry. Photography style: close-up to half-body fashion portrait, Vogue editorial aesthetic, cinematic professional studio lighting, soft HDR background, shallow depth of field, realistic skin texture, ultra-detailed, 8K quality. Camera & lens look: professional DSLR look, 85mm lens feel, f/1.8 aperture, crisp focus with smooth background bokeh. Composition: Vogue magazine layout with large bold logo at the top, editorial fashion cover framing, clean and elegant design. Mood & vibe: playful yet luxurious, high-fashion beauty editorial, realistic, not AI-looking, photographed by a professional fashion photographer.
Remix

An American guy with buzz cut and hoodie wearing this headphone is shown in a side-profile view (facing left), with his head tilted slightly downward and his eyes closed, giving a serene, contemplative, or introspective expression. It is professional photoshoot ad. Same lighting and backdrop . Generate 16:9 ratio.

advertising headphones

Remix

Generate an image of Kylie jenner applying vitamin c serum on her left cheek while holding the bottle on the right hand. Background is a pink swimming pool. It is top angle closeup shot on her skin.
beauty cosmetics
Remix

A highly detailed, cinematic close-up macro photograph of [insert product name here, e.g., a red canvas tote bag], angled slightly from the side to focus on the textured red fabric, stitched details, and attached black adjustable strap with metal hardware. Dramatic warm side lighting casting golden highlights on the metal elements and soft shadows in the fabric folds for pronounced texture and premium depth. Blurred warm wooden or neutral background with bokeh lights evoking a cozy indoor setting, high contrast, shallow depth of field with razor-sharp focus on zipper and stitching, ultra-high resolution, professional accessory advertisement style similar to luxury bag promotions.
Remix

A close-up wildlife portrait of a majestic stag standing still in a snowy forest during active snowfall. The deer faces the camera directly, with large symmetrical antlers coated in fresh snow, creating a striking and powerful composition. Its fur is a rich warm brown, lightly dusted with snowflakes, contrasting against the soft white foreground and cool gray-blue background. The background features blurred winter trees with shallow depth of field, producing a dreamy, atmospheric bokeh effect. Lighting is soft and diffused, typical of overcast winter conditions, emphasizing fine details in the fur, antlers, and snow texture. The mood is calm, serene, and slightly dramatic, evoking wilderness, nature, and seasonal beauty. Shot at eye level with a centered composition, high realism, no text, ideal for commercial wildlife, winter, or holiday-themed stock imagery.
Remix

The polished wooden dock of an exclusive yacht club at golden hour. A woman (age 30-45, random ethnicity), with an appealing, athletic physique, stands perfectly still, gazing out at the marina. Her structurally recognizable tennis outfit—a short, pleated skirt and top—is rendered in an unconventional, randomized blend of heavy, opaque nautical blue silk and subtle, sheer white mesh panels. A sleek, modern tennis racket is propped naturally against a polished metal dock cleat beside her. Her expression is one of elegant calm, enjoying the sea breeze. The camera steadily pushes in toward her, isolating her against the backdrop of luxury yachts. Detailed Elements (Fusing Nautical Luxury, Elegance, and Subtle Tennis Cues) Subject & Mood: Woman (age 30-45, random ethnicity). Her appealing, athletic physique is gracefully highlighted by the sharp, fitted attire. Her expression is elegant, calm, and composed, reflecting the serene, high-class environment. Attire (Subtly Incorporating Constraints): A sophisticated, short, pleated tennis skirt and a structured top. The garment features a randomized, unconventional material mix of heavy, opaque, nautical blue silk and subtle, sheer white mesh panels (implying randomized material, opacity, transparency, and color). This maintains the tennis structure while delivering high-fashion, nautical appeal. Setting & Atmosphere: A pristine, polished wooden dock at a high-end yacht club. The background is a dynamic, high-fashion blur of massive white yachts, sailing masts, and the sparkling blue water at golden hour. The mood is luxurious, serene, and exclusive. Key Props (Undeniable Tennis, Natural Placement): A single, sleek, modern tennis racket (perhaps in white and navy) is propped naturally against a large, polished metal dock cleat, visible in the foreground. Cinematography (New Standing Instruction): A slow, steady 7-second push-in (dolly shot). The camera starts wide, capturing her full figure against the backdrop of yachts and sparkling water, and smoothly advances directly toward her, ending on an elegant medium close-up of her calm, composed expression. Style: High-fashion, luxury realism, warm golden-hour lighting, 4K. Focus on the striking contrast between her perfect, elegant stillness and the gentle, affluent motion of the marina.
automotive fashion
Remix

Ultra macro cinematic shot focusing on the eye of a real tiger, capturing the intricate textures of the iris and fur around it. The reflection in the tiger’s eye clearly shows a deer standing in the forest, slightly trembling and alert. The camera remains locked on the eye — showing micro movements of the pupil, subtle breathing vibrations, and golden fur details glinting under sunlight. The atmosphere is tense and silent except for faint forest sounds — rustling leaves and distant bird calls. Lighting emphasizes the contrast between the tiger’s amber eye and the reflected deer silhouette, creating a sense of predatory focus and wild intensity.
Remix

Studio shot, bold sporty-casual mood. Female model with the attached face. Wearing a white athletic crop top with thick straps and a visible 'Calvin Klein' band, layered with a necklace and a bracelet. Extremely baggy, distressed light-wash jeans with heavy rips at the knees and thighs. Seated on the floor against a bright plain white background, with legs bent and crossed. Right arm is up with the hand resting on the head. Direct and intense gaze at the camera. Long dark-brown loose waves flowing over the shoulders. A tattoo of the name 'Maham' written in stylish Arabic script is visible on her shoulder.
fashion
Remix

Creative photorealistic surreal 3D advertising shot for “Nike Vapormax”, featuring the main product as the hero object transformed into a bold surreal visual metaphor that instantly communicates the brand’s core message, with a clean color-matched background, ultra-realistic materials and shadows, and a clever unexpected twist in the product’s form. Add a tiny human interacting with the scene to show scale. Place a strong three-word slogan at the bottom and the real brand logo on top. Minimal, premium, visually shocking, concept-driven, high-end commercial style.
Remix

luxury fashion editorial of the woman sitting elegantly on a beige tennis bench, holding an olive green matt tennis racket, wearing a chic structured olive green shirt tucked into high-waisted ivory shorts, gold pointy heels, beige nike wristbands, and a beige nike visor, her skin shows natural texture and pores, subtle makeup with soft bronzed tones and a hint of gloss, no airbrushed perfection. sleek ponytail with a few loose strands catching the light, expression poised yet effortless. she is surrounded by a transparent bag filled with beige tennis balls with the nike logo, harsh midday lighting with defined shadows, muted green tennis court background, high-fashion composition, photographed on 120mm film, styled like a Vogue or Dior Sport editorial, minimalist luxury aesthetic, crisp and polished tone
fashion sports
Remix

Browse the full gallery

Why teams choose Nano Banana Pro

Choose Nano Banana Pro when a close-up needs believable skin, when an image must carry readable text, or when you are combining many references into one scene. In our tests it gave the most natural skin of the current models we compared, while Seedream 5 Pro followed briefs more closely, so try both on your own prompt. For faster, lower-cost drafts, start with Nano Banana 2.1.

Capabilities

What Nano Banana Pro can do

The capabilities that set Nano Banana Pro apart and earn its place in a brief

Legible text in the image

Renders short taglines through to longer copy on posters, packaging, and infographics, in several languages. Quote every string you need and proof it at full size.

Plans before it renders

A Gemini 3 Pro reasoning pass plans the composition first, which helps it hold layered briefs together instead of dropping details.

1K to 4K Output

Choose a preset from 1K to 4K or set a custom width and height up to 6336 pixels, at low, medium, or high quality.

Consistency across people and products

Hold up to 5 people consistent and blend up to 14 reference inputs into a single image, keeping the same subject in new scenes, outfits, and angles.

Director-level editing controls

Relight a scene from day to night, shift color grades, change camera angle and depth of field, and switch aspect ratios for any platform, all from a prompt.

Multilingual text and localization

Generate text in multiple languages, or localize and translate the text inside an existing image for global campaigns.

Use cases

Where teams reach for Nano Banana Pro

Creating professional slide decks and presentations
Designing infographics and data visualizations
Generating marketing materials with accurate typography
Building consistent brand assets across campaigns

Signature strengths

What sets Nano Banana Pro apart

The strengths teams reach for, shown on real renders.

Text you can actually read

Ask for "Café de Flore" on a storefront and that's exactly what renders, with clean, legible type across many languages, including complex scripts like Arabic, Thai, and Japanese. Posters, packaging, and ad headlines usually come out clean, though you should still proof every word at full size.

The same character, every shot

Lock in a face or product once and carry it across an entire campaign, keeping the same subject in new scenes, outfits, and angles. Hold up to 5 people consistent and blend up to 14 reference inputs, so nothing drifts to "close enough" between frames.

Direct it like a cinematographer

Relight the scene to golden hour, drop the camera lower, shift the color grade, change the aspect ratio for another platform. Nano Banana Pro understands f-stops, depth of field, and lighting language, and applies them the way the brief intends.

Explore related categories

Browse adjacent categories and creative directions teams are exploring

FAQ

Frequently asked questions

What teams need to know about creating with Nano Banana Pro in Masonry

How did Nano Banana Pro do in Masonry's own tests?

In our six-prompt photorealism test (October 2026) it produced the most natural skin texture, with visible pores, freckles, and fine lines, and it was the only model to follow a one-glove detail literally. It also read some prompts as a casual phone photo and once drew an impossible selfie pose, so check composition and hands. One run per prompt.

What is Nano Banana Pro?

Nano Banana Pro is an AI image generation model from Google, available inside Masonry, the AI creative agent teams use to produce marketing, product, and brand images.

How does my team use Nano Banana Pro in Masonry?

Open a Masonry canvas, pick Nano Banana Pro from the model selector, and describe the image you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine Nano Banana Pro with other models in one workspace.

Is Nano Banana Pro free to try?

New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. Nano Banana Pro is included in every paid plan, and the editor shows the exact credit cost before you generate.

How do I write good prompts for Nano Banana Pro?

Nano Banana Pro reasons about complex briefs, so you can write longer, layered prompts. Describe the scene, the exact text you want rendered, and any layout constraints in full sentences, and it will hold them together rather than dropping details. See the prompt gallery on this page for real Nano Banana Pro prompts you can copy and adapt.

Who makes Nano Banana Pro?

Nano Banana Pro is built by Google. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.

Can I see examples made with Nano Banana Pro?

Yes, the prompt gallery on this page shows real images teams have generated with Nano Banana Pro in Masonry, each paired with the exact prompt you can copy and adapt for your own brand.

Start creating with Nano Banana Pro

Generate, edit, and compare across 50+ models in one workspace.

Create with Nano Banana Pro

Guides for Nano Banana Pro

Prompt walkthroughs and examples from the Masonry blog

Blender-Like AI Product Animation: A Motorcycle Workflow Nano Banana 2 Lite Guide: Speed, Price, Limits, and Examples

Explore more AI models

Compare Nano Banana Pro with other models teams run in Masonry

Gemini 3.1 Flash Lite ImageGoogle · Image Imagen 4Google · Image Nano BananaGoogle · Image Nano Banana 2.1Google · Image Gemini Omni 1.2 FlashGoogle · Video Veo 3.1Google · Video