Nano Banana 2

Fast image generation with readable text and strong reference-driven edits.

From $0.065 an image on paid plans.

Professional images for every use case

Product photography.

Creates clean ecommerce shots and brand visuals with realistic lighting, controlled composition, and polished materials.

Posters and infographics.

Useful for posters, menus, explainers, and ads where short in-image text needs to stay readable.

Character storyboards.

Maintains character identity and scene logic better across panels, angles, and iterative edits.

Localized ad creatives.

Generate one campaign concept, then adapt text and visuals for different languages and markets.

Reference-based fashion mockups.

Combine people, products, and styling references into polished composites for catalogs and campaigns.

More reliable text inside images

Nano Banana 2 is useful when the image itself needs readable copy, not just decoration. It handles short headlines, labels, menus, and UI-like elements more reliably than the general AI-image baseline, though tiny print and long paragraphs are still harder.

•Best with short, explicit text strings
•Useful for posters, menus, stickers, and explainers
•Supports multilingual in-image localization
•Good for labels, diagrams, and simple UI copy
•Tiny text and long paragraphs can still fail

Reference-driven editing and composition

This model is built for image-to-image workflows, not just one-shot text prompts. You can combine multiple uploads, preserve important faces or logos, and keep characters more consistent across edits and new angles.

•Up to 14 total reference images
•Up to 10 object references
•Up to 4 character references
•Good for product inserts and outfit swaps
•Helpful for multi-turn character turnarounds
•Describe protected details for better preservation

Reference-driven editing and composition

Wide formats and 4K-ready output

Nano Banana 2 covers both fast drafts and higher-resolution final assets in the same model. Native aspect ratios let you create social posts, slides, reels, banners, and ultra-wide layouts without awkward cropping.

•512, 1K, 2K, and 4K output
•Aspect ratios from 1:1 to 21:9, includes 1:4, 4:1, 1:8, and 8:1
•Useful for drafts and final exports
•Square is the default when no size is set

Search-grounded visuals for real-world topics

For real-world subjects, Nano Banana 2 can use web search and image search as extra visual context during generation. That helps with factual graphics, places, species, and other real-world visuals, though image search cannot be used for people.

•Web search and image search can be combined
•Helpful for weather and current-event graphics
•Useful for accurate places, objects, and species
•Available on Gemini 3.1 Flash Image workflows
•Image search grounding does not support people

Search-grounded visuals for real-world topics

How it works

Describe your image

Start with the subject, setting, style, and mood. If the image needs readable words, include the exact text so the model knows what must appear.

Add references and set format

Add reference images when you want a product, character, or style carried into the result. Then choose an aspect ratio and resolution that match the final placement.

Generate and refine

Generate the first pass, inspect the details, and refine with short follow-up instructions. Specific edits like text, lighting, background, or composition changes usually work better than rewriting everything.

Top community creations

Recent Nano Banana 2 images shared by the BudgetPixel community.

Warm sun-baked palette of ochre, sand and terracotta set against a clean cool cerulean, high-key daylight with strong directional light modeling raised planes into bright highlights and warm reflected shadows. Rendered in confident oil brushwork, visible loaded strokes and softened edges that dissolve into atmospheric bokeh toward distant forms while foreground detail stays crisp. Naturalistic skin luminosity, subtle impasto on lit surfaces, painterly texture throughout. Balanced central composition with open negative space and gentle tonal recession conveying heat and sunlit solitude.

A woman warrior with dark tousled shoulder-length hair, wearing a torn pale cropped top, a leather crossbody harness, a wide belt with hip pouches, cloth arm wraps and a turquoise pendant, holding a long sword.

Medium full-body shot at eye level, figure standing and facing forward with body angled slightly, gaze directed off to the side, one hand gripping a downward sword at her side, subject sharp in the foreground with the landscape softening into shallow depth behind.

Scene set in a vast sand-dune desert during clear midday, with dry hot stillness, featuring rolling dunes, scattered rocks and sparse tufts of brush under an open blue sky.

@justrob

product design, Ford pickup F150, exploded view diagram, white background, three-dimensional, highly detailed internal components, studio lighting, product photography, best quality

Tamara de Lempicka + Korean Minhwa folk art, where Lempicka’s sculptural, polished Art Deco aesthetic defines the subject’s poised elegance, Minhwa’s symbolic motifs and bold traditional Korean colors infuse the composition with cultural depth, and the fusion manifests as a sophisticated, highly stylized artwork with dynamic contrasts and fluid, decorative patterns. Dramatic lighting enhances the sculptural forms, while intricate folk art elements add layers of symbolism and texture, creating a seamless blend of modern refinement and timeless cultural storytelling.

Direct, bold eye contact, 2024 blond with pink tipped hair, pin up woman standing full body, dress

Painterly oil rendering with visible directional brushwork and soft blended edges that dissolve form into atmospheric haze. A muted, earthy palette pairs warm ochre and sandy tans against cool bruised violets and near-black shadows, punctuated by sparse saturated crimson accents. Low-key lighting yields deep shadow pooling, a subdued glow through dusty air, and gentle luminous modeling on raised planes. Surfaces read as slick lacquered sheen against matte granular ground. Composition is centered and grounded, with elongated proportions and a solemn, brooding cinematic stillness.

A woman with pale skin, short black hair, curved red-and-black horns, and a long slender tail, wearing a glossy dark bodysuit with a high pointed collar, red bustier detailing, and circular hip ornaments.

Full-body shot at a slightly low eye-level angle, the figure walking straight toward the camera with head tilted down, direct piercing gaze, arms relaxed at her sides and tail curling behind, her long cast shadow stretching across the ground, background receding into soft distant blur.

Scene set in a barren desert plain at night, with a desolate quiet atmosphere, featuring scattered rocks, distant city silhouettes, and faint colored lights on the horizon.

Monochromatic amber-and-sepia palette, single warm key bleeding into near-black grounds with a golden inner glow and tight chroma range. High tenebrist contrast: lit forms surfacing from deep shadow, soft halation around highlights. Airbrushed sprayed gradients held in tension with loose diluted ink-wash blooms and dry-brush granulation. Aged parchment substrate, foxed and streaked with brushstroke grain. Layered, theatrical, vintage-poster density — luminous warmth dissolving into smoky dark.

Direct, bold eye contact, 2024 blond with pink tipped hair, pin up woman standing full body, short metallic cyan satin dress

Rendered in saturated crimson and molten-orange firelight set against deep near-black shadow, with high contrast and a warm dramatic key that carves figures out of darkness. A hot rim glow traces contours while cooler pockets recede into gloom. Surfaces are glossy and photorealistic with crisp micro-detail on edges, hair and fabric, softening into atmospheric haze and floating embers. Composition is theatrical and vertically stacked, layered with smoke and drifting light for cinematic depth. Colour ranges from ember-red skies to charred umber foreground, painterly yet photographic.

A woman with long platinum-white hair in a flowing white gown conjuring swirling flame at her fingertips, and a man with dark tousled hair in a black leather coat holding a longsword.

Medium full-length two-shot at slightly low eye-level, the pale figure turned three-quarter toward her raised glowing hand with downcast focus, the dark figure standing tall and forward beside and slightly behind her gripping the sword downward, gaze fixed ahead, bodies overlapping in staggered depth against a receding backdrop.

Scene set at a ruined stone castle during a stormy night, with an ominous fiery atmosphere, featuring a blood-red sky, drifting smoke, glowing embers and crumbling walls.

Chiaroscuro creates dimensional drama through stark light-shadow contrast, commercial precision produces polished luminosity via smooth tonal gradations, and spaghetti western cinema infuses sun-bleached tension. The fusion manifests as warm amber-ochre palettes with dusty atmospheric haze, intensified contrast ratios, and crisp edge definition against soft backgrounds, transforming any subject through operatic lighting and nostalgic saturation.

Three rugged post-apocalyptic wasteland warriors in scavenged leather-and-metal armor, faces streaked with dark war paint, wearing scarves, buckled belts, harnesses and holstered weapons, two men and one woman carrying firearms.

Medium wide shot at near eye-level, the three figures grouped close and slightly staggered in depth facing the camera with steady defiant gazes, the foremost man cropped at the thighs on the right, the woman centered gripping a pistol, a masked figure between and behind them, chaotic action layered in soft-focus distance.

Scene set in a barren desert wasteland during harsh daytime, with a tense embattled atmosphere, featuring wrecked armored vehicles, a mounted gun spewing fire and black smoke, distant fighters, mountains and a fortified scrap tower.

An ultra-detailed 2D vector illustration of an epic sea adventure. A vintage wooden sailboat cutting through deep blue ocean waves, spray of water droplets catching the sunlight. A solo sailor (use character from the reference image) at the wooden steering wheel, looking forward with determination. The art style is clean vector art with sharp lines, flat shapes, precise geometric curves, and smooth gradients. Use a vibrant color palette of deep navy, teal, aqua, burnt orange, and gold. The composition is highly detailed, emphasizing layered depths, crisp outlines, flat shading, and no textures, capturing a sense of high-stakes exploration.

Merciless noon light creates bleached surfaces and knife-sharp shadows that amplify tension, tenebrism produces dramatic diagonal light that heightens confrontation, and Spaghetti Western aesthetics infuse operatic grandeur through extreme depth, weathered textures, and dust-filled atmosphere. The fusion manifests as harsh contrasts, hyperreal details, and mythic weight, preserving original subjects and settings.

Three rugged post-apocalyptic wasteland warriors in scavenged leather-and-metal armor, faces streaked with dark war paint, wearing scarves, buckled belts, harnesses and holstered weapons, two men and one woman carrying firearms.

Medium wide shot at near eye-level, the three figures grouped close and slightly staggered in depth facing the camera with steady defiant gazes, the foremost man cropped at the thighs on the right, the woman centered gripping a pistol, a masked figure between and behind them, chaotic action layered in soft-focus distance.

Scene set in a barren desert wasteland during harsh daytime, with a tense embattled atmosphere, featuring wrecked armored vehicles, a mounted gun spewing fire and black smoke, distant fighters, mountains and a fortified scrap tower.

Mid-century animation background design + rural dry-brush realism + golden-hour cel-animation reverie, where the flat graphic layout builds bold geometric color-field forms through stylized angular abstraction and clean edges, the dry-brush layering grounds them in weathered earth-tone patina via granular tactile glazing, and golden-hour reverie infuses warm amber diffusion with retro surreal stillness. The fusion manifests as burnished rust-and-coral tonal fields, soft luminous glow over flat modeled planes, and mid-century graphic rhythm, transforming any subject through terracotta-mauve harmonies, hazy backlit warmth, and crisp stylized silhouettes interrupted by granular textural grit.

Three rugged post-apocalyptic wasteland warriors in scavenged leather-and-metal armor, faces streaked with dark war paint, wearing scarves, buckled belts, harnesses and holstered weapons, two men and one woman carrying firearms.

Medium wide shot at near eye-level, the three figures grouped close and slightly staggered in depth facing the camera with steady defiant gazes, the foremost man cropped at the thighs on the right, the woman centered gripping a pistol, a masked figure between and behind them, chaotic action layered in soft-focus distance.

Scene set in a barren desert wasteland during harsh daytime, with a tense embattled atmosphere, featuring wrecked armored vehicles, a mounted gun spewing fire and black smoke, distant fighters, mountains and a fortified scrap tower.

Desaturated palette with hard lighting amplifies austere elegance, and atmospheric grain with industrial decay heightens isolation. The fusion manifests as bleached colors with textured desolation, preserving original subjects and settings.

Three rugged post-apocalyptic wasteland warriors in scavenged leather-and-metal armor, faces streaked with dark war paint, wearing scarves, buckled belts, harnesses and holstered weapons, two men and one woman carrying firearms.

Medium wide shot at near eye-level, the three figures grouped close and slightly staggered in depth facing the camera with steady defiant gazes, the foremost man cropped at the thighs on the right, the woman centered gripping a pistol, a masked figure between and behind them, chaotic action layered in soft-focus distance.

Scene set in a barren desert wasteland during harsh daytime, with a tense embattled atmosphere, featuring wrecked armored vehicles, a mounted gun spewing fire and black smoke, distant fighters, mountains and a fortified scrap tower.

Theatrical sidelighting creates dramatic tonal separation through high-contrast blacks and luminous highlights, precise warm tonal gradation produces rich textural detail via grainy film emulsion and nuanced shadow rendering, and illicit luxury ambiance infuses forbidden elegance and clandestine glamour into the atmosphere. The fusion manifests as period film grain texture, sepia-warm tonal palette, and theatrical chiaroscuro lighting, transforming any subject through moody contrast ratios and candid luminosity.

Three rugged post-apocalyptic wasteland warriors in scavenged leather-and-metal armor, faces streaked with dark war paint, wearing scarves, buckled belts, harnesses and holstered weapons, two men and one woman carrying firearms.

Medium wide shot at near eye-level, the three figures grouped close and slightly staggered in depth facing the camera with steady defiant gazes, the foremost man cropped at the thighs on the right, the woman centered gripping a pistol, a masked figure between and behind them, chaotic action layered in soft-focus distance.

Scene set in a barren desert wasteland during harsh daytime, with a tense embattled atmosphere, featuring wrecked armored vehicles, a mounted gun spewing fire and black smoke, distant fighters, mountains and a fortified scrap tower.

A fusion of analog distortion where photographic elements dissolve into painterly distortions, featuring deliberate signal degradation, smeared textures that suggest motion or decay, and heavy impasto techniques rendered digitally with physical-looking media artifacts that enhance emotional impact without altering subject identity or environment.

1950s italian curvy pin up woman, bold expression with direct eye contact, bold crimson lipstick, standing, wearing short pleated skirt, black high heels, black purse, full body on a busy city sidewalk

Warm amber-and-umber palette built on candlelit low-key lighting, with deep shadow pools swallowing edges and gentle golden glow pooling on raised planes. Background lights melt into soft round bokeh against near-black darkness. Rendering is naturalistic and cinematic, fine grained, with soft-focus atmospheric depth and low contrast in the midtones giving a filmic tenderness. Skin and surfaces catch a subtle rim glow. Composition is intimate and balanced, close and quiet, emphasizing hushed nocturnal warmth.

A man with a dark mustache in a tan corduroy jacket over a white shirt, and a woman with long wavy brown hair in a dark denim jacket.

Medium close-up at eye-level, the woman leaning her head against the man's shoulder with a soft smile and closed contentment, her arm wrapped around him, both facing forward, tightly framed together with softly blurred foliage and glowing lights behind.

Scene set in a garden at night, with a warm romantic atmosphere, featuring lit candles, blurred foliage, and distant lamp lights.

Dense storybook crosshatched linework + Venetian translucent glazing + modern steamy romance atmosphere, where the crosshatching creates tactile surface vibration through layered ink striation, the glazing produces inner luminosity via warm underpainting glowing beneath cooled upper tones, and romance-novel heat infuses saturated candlelit intimacy. The fusion manifests as engraved texture beneath velvet glazes, deep crimson-ochre-umber harmonies, and low golden light pooling into soft shadow, transforming any subject through smoldering warmth, granular hatched detail, and rich chromatic depth held in a shallow tonal range.

Direct, bold eye contact, 2024 blond with teal tipped hair, pin up woman standing full body, wearing a short modesty skirt

Pricing for Nano Banana 2

Runs on credits — no per-model surcharges, no surprise billing.

65credits

per generation

65 credits per image

Show pricing details▾

ResolutionCredits

1Kdefault65/ generation
0.5K50/ generation
2K100/ generation
4K150/ generation

Credits work across every plan. See /pricing for credit packages.

Start free See all plans

Compare all 5 versions

All 5 run on the same credits in the same workshop — here is what each costs and what it is for.

Nano Banana 2

65credits per generation

Resolution:: 0.5K 50 credits · 1K 65 credits · 2K 100 credits · 4K 150 credits

High-efficiency image generation with Gemini 3.1 Flash. Features 0.5K/1K/2K/4K resolution, Google Image Search grounding, advanced text rendering, and multi-image fusion (up to 6 references).

Try Nano Banana 2 →

Nano Banana (Gemini 2.5 Image)

40credits per generation

Google's latest model for image editing and multi-image fusion. Fast and accurate object removal and inpainting.

Try Nano Banana (Gemini 2.5 Image) →

Nano Banana 2.1

45credits per generation

Resolution:: 1K 45 credits · 2K 70 credits · 4K 150 credits

Google's Nano Banana 2.1: fast text-to-image and image editing with sharper output and cleaner in-image text than Nano Banana 2. Edit or compose from up to 9 reference images at no extra cost, render at 1K, 2K or 4K, and optionally ground the image in live Google Search results or web images.

Try Nano Banana 2.1 →

Nano Banana Pro

120credits per generation

Resolution:: 4K 180 credits

Professional asset production with Gemini 3 Pro. Features Google Search grounding, advanced reasoning, 1K/2K/4K resolution support, and multi-image fusion (up to 6 references).

Try Nano Banana Pro →

Nano Banana 2 Lite

40credits per generation

Try Nano Banana 2 Lite →

Use Nano Banana 2 via the API

Nano Banana 2 is available through the BudgetPixel developer API — the same model the studio runs, supporting text-to-image, and image editing / references. Pricing is metered in credits (50 credits/image at 0.5K, 65 credits/image at 1K, 100 credits/image at 2K, 150 credits/image at 4K), charged only on success, with an API key available on Premium plans and above.

curl -X POST https://api.budgetpixel.com/v1/images/nano-banana-2 \
  -H "Authorization: Bearer $BUDGETPIXEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "your prompt here"}'

Read the API docs Get an API key

No code? Use Nano Banana 2 from Claude or Cursor

Nano Banana 2 is also available through the BudgetPixel MCP server. Connect your account to Claude, Cursor, or any MCP-enabled agent and generate with Nano Banana 2 by asking in plain language — same credits, same pricing, no code required.

Set up the MCP server Or use it in ComfyUI, WordPress or Cursor →

Nano Banana 2 at a glance

Text-to-image
Image editing
Multi-image fusion
Google Image Search grounding
Advanced text rendering
0.5K/1K/2K/4K resolution
High-efficiency generation

How Nano Banana 2 compares

The differences that actually change which one you pick.

Nano Banana 2 vs Nano Banana Pro: Pro excels at complex professional assets with advanced reasoning. Nano Banana 2 offers better speed-to-quality ratio for high-volume use.
Nano Banana 2 vs Nano Banana: Nano Banana 2 is the successor with higher resolution support, Image Search grounding, and advanced text rendering.

Frequently asked questions

What is Nano Banana 2?▾

Nano Banana 2 is the common name for Google DeepMind’s Gemini 3.1 Flash Image model. It is designed for fast image generation and editing, with stronger text rendering, reference-image workflows, and optional search grounding.

How does Nano Banana 2 work?▾

You can prompt it with text, images, or both. The model uses a built-in thinking process to plan composition before rendering, and it can also use web or image search grounding when you need more factual visuals.

How much does Nano Banana 2 cost?▾

Cost depends on where you access it, how many images you generate, and what resolution you choose. In general, quick drafts use fewer credits, while larger outputs and heavier production use more.

How does Nano Banana 2 compare to other AI image generators?▾

Nano Banana 2 is especially useful when you need fast edits, readable short text, and reference-driven workflows. Its strength is production-style control: iterative edits, structured prompts, multi-image composition, and flexible output formats.

Can I use Nano Banana 2 commercially?▾

Generally yes, but you should review the provider’s current terms and the platform terms for your account type and use case. Google says it does not claim ownership over generated content, while you remain responsible for legal compliance, input rights, and any required attribution.

Does Nano Banana 2 render text well?▾

It is stronger on text than the general AI-image baseline, especially for short headlines, labels, menus, posters, and simple infographics. Very small text, dense paragraphs, and full-page document layouts can still be unreliable.

What resolutions and aspect ratios does Nano Banana 2 support?▾

Nano Banana 2 supports 512, 1K, 2K, and 4K output. Supported aspect ratios include 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, and 21:9.

Does Nano Banana 2 support reference images?▾

Yes. Gemini 3.1 Flash Image supports up to 14 total reference images in one workflow, including up to 10 object references and up to 4 character references. That makes it useful for consistent characters, product inserts, and multi-image composites.

Can Nano Banana 2 edit existing images?▾

Yes. You can add or remove elements, make local edits, transfer style, combine multiple images, or turn rough sketches into finished scenes. For better preservation of faces or logos, describe the protected details explicitly in your prompt.

Does Google use my prompts and images for training when I use Nano Banana 2?▾

If you use Nano Banana 2 directly through Google’s unpaid access, Google says submitted content and generated outputs may be used to improve products, and human reviewers may inspect them. For Google’s paid services, Google says prompts and responses are not used to improve its products. Third-party platforms may add their own retention policies, so check the terms where you generate.

Does Nano Banana 2 have an API?▾

Yes — Nano Banana 2 is available through the BudgetPixel developer API via the `POST /v1/images/nano-banana-2` endpoint, supporting text-to-image, and image editing / references. Generate an API key from the developer console (available on Premium plans and above) and see the full reference at docs.budgetpixel.com.

How much does the Nano Banana 2 API cost?▾

API usage is billed in credits from the same balance your plan includes, at the standard metered rate: 50 credits/image at 0.5K, 65 credits/image at 1K, 100 credits/image at 2K, 150 credits/image at 4K. Failed generations are never charged. You can estimate any request's exact cost with POST /v1/cost before running it.

Can I use Nano Banana 2 with Claude or other AI agents (MCP)?▾

Yes — Nano Banana 2 is exposed through the BudgetPixel MCP server, so Claude, Cursor, and any MCP-compatible agent can generate with it from a plain-language request. Connect your account at budgetpixel.com/mcp; generations use the same credit balance and pricing as the web studio and the API.

Keep exploring

Nano Banana Pro Nano Banana 2 Lite

Explore more models

Nano Banana 2.1

FLUX 3 Image

Ideogram V4.5

Seedream 5.0 Flash

Flux 2 Pro

Flux 2 Dev

Midjourney Niji 7

Wan 2.7 Pro

Try Nano Banana 2