google / nano-banana-2

Nano Banana 2 generates and edits images from natural language prompts, with optional reference images for style, character, product, or composition guidance.

The playground uses the same request-shaped fields as the public API: prompt, image_urls, aspect_ratio, and resolution.

Model Type:Text to imageImage editing
Pricing

Resolution pricing

sjolt exposes 1K, 2K, and 4K output for Nano Banana 2. Displayed prices are truncated to two decimal places.

1K image
$0.08
2K image
$0.12
4K image
$0.16
Input

Prompt, assets, and output parameters form one generation request.

Describe the image you want to generate.
Input media

Upload the media inputs configured for this model.

Waiting for assetsUploaded files will appear here for preview and removal.
Aspect ratioChoose the frame for the delivery channel.
ResolutionChoose the output image size.

Playground Examples

Try production-style prompt starters.

Luxury perfume product image generated with Nano Banana 2

A hyper-realistic product shot of a luxury perfume bottle on black marble, dramatic studio lighting with golden reflections.

Japanese garden painting generated with Nano Banana 2

An oil painting of a misty Japanese garden at dawn, koi pond with stone lanterns, soft morning light filtering through maple trees.

Cyberpunk street market generated with Nano Banana 2

A cyberpunk street market at night, neon signs in multiple languages, rain-slicked streets reflecting colorful lights, crowd of diverse characters.

Coffee tools flat-lay generated with Nano Banana 2

A minimalist flat-lay composition of artisan coffee tools on a white oak surface: pour-over dripper, hand grinder, ceramic mug, scattered beans.

Children's book illustration generated with Nano Banana 2

A whimsical children's book illustration of a fox and owl sharing tea in a treehouse, watercolor style with soft pastel colors.

Similar Models

Compare adjacent capabilities before switching models.

Google · Image

Nano Banana Pro

Google

Google's premium image generation and editing model for readable text, product mockups, visual explainers, and reference-guided brand assets.

OnlineTry model
OpenAI · Image

GPT Image 2

OpenAI

Image generation for complex instructions, text understanding, final visuals, brand assets, and creative production.

OnlineTry model

Model overview

Nano Banana 2 for Google image generation and reference-guided editing

Nano Banana 2 brings Google image generation to sjolt for text-to-image creation and image editing. Start from a prompt, add up to 6 reference images, and generate photorealistic product shots, illustrations, social visuals, and production-ready creative variants.

Nano Banana 2 generation example
01 · Image generation

Multi-reference image editing

Upload up to 6 reference images to guide style, character identity, product form, composition, and visual details in a single generation.

  • Supports Image editing and reference-asset generation workflows.
  • Fits product assets, ad previews, visual direction, and social content tests.
  • Adjust configured inputs, media, and switches before generation.
Reference asset control example
02 · Asset control

1K, 2K, and 4K output

Use 1K for fast drafts, 2K for balanced web and social output, or 4K for higher-detail production assets.

Reference images
Unified model API and result management example
03 · API integration

11 aspect ratios

Generate square, landscape, portrait, vertical, and ultra-wide frames including 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 2:3, 3:2, 4:5, and 5:4.

  • Compare available models from Google, OpenAI, ByteDance in one place.
  • Copy the request body directly to the server to reduce frontend/backend parameter drift.
  • Failure states, retries, result preview, and review checkpoints stay in the same workflow.

Model characteristics

Built for multi-reference image generation, 4K output, and flexible creative framing.

01

Text or reference-led creation

Start from a prompt, or upload reference images to guide the final style, subject, product, and composition.

02

Up to 6 reference images

Blend visual cues from multiple inputs for character consistency, style transfer, product variants, and scene composition.

03

1K, 2K, and 4K output

Use 1K for fast drafts, 2K for polished web assets, or 4K when the image needs extra detail.

04

11 aspect ratios

Create square, landscape, portrait, vertical, and ultra-wide images without cropping after generation.

FAQ

These are the first questions to answer when evaluating this model.

What makes Nano Banana 2 different from other image models on sjolt?

Nano Banana 2 supports text-to-image generation and reference-guided editing with up to 6 input images, 11 aspect ratios, and 1K to 4K output.

How much does Nano Banana 2 cost on sjolt?

Nano Banana 2 costs $0.08 for 1K, $0.12 for 2K, and $0.16 for 4K output.

How do reference images work?

Upload 1 to 6 images as visual references. Nano Banana 2 can use them for style, composition, character, product, or scene guidance while following your prompt.

Can Nano Banana 2 work without reference images?

Yes. Use the text-to-image variant with prompt, aspect_ratio, and resolution to generate from text only.

Which aspect ratios are supported?

sjolt exposes auto, 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 2:3, 3:2, 4:5, and 5:4. auto is kept local and not forwarded upstream.