Generate and edit from natural-language prompts
Describe the image you want, generate a first result, then ask for specific changes. Move from an idea to a refined visual without rebuilding the concept from scratch.
Nano Banana 2 online
Nano Banana 2 AI Image Generator & Editor
Generate and edit AI images with precise text, subject consistency, localization, flexible aspect ratios, and up to 4K output.
Model overview
What Is Nano Banana 2?
Nano Banana 2 is Google DeepMind's image generation and editing model, also identified as Gemini 3.1 Flash Image. It is built for fast image creation and editing while bringing advanced image capabilities to a Flash-class model.
The model can generate images from prompts, edit existing visuals, render text inside images, localize image content, keep subjects more consistent across a workflow, and output images at 2K or 4K.
This image model is useful for creators, marketing teams, e-commerce brands, designers, and teams that need visual concepts, campaign assets, infographics, posters, or repeatable characters.
Features
Features for Faster Visual Creation
A quick look at what Nano Banana 2 supports before you start a generation.
Create clearer text inside images
Generate posters, greeting cards, marketing mockups, and other visuals that need words inside the image. Review spelling and fine text details before publishing.
Use real-world knowledge for visuals
Create specific subjects, infographics, diagrams, and visual explanations with help from Gemini's real-world knowledge.
Localize images for different markets
Translate text inside images and adapt the visual context for different audiences. Review grammar, spelling, and cultural nuance before use.
Keep characters and objects more consistent
Build stories, campaigns, and multi-scene concepts with stronger subject consistency — up to four characters and ten objects across a single workflow.
Choose higher-resolution output
Move between square, portrait, and landscape layouts, and generate at 2K or 4K for sharper social posts, ads, presentations, and larger creative assets.
Examples
Image Generation and Editing Examples
Start from a proven scene. Reuse the prompt, change the subject or setting, and generate a new version.
How to use
How to Use Nano Banana 2
Start with a clear prompt, add reference images when you need control, then generate an image you can review and refine.
- 01
Describe the image you want
Write a clear prompt with the subject, setting, composition, text, style, and intended use. More specific instructions give the model more context.
- 02
Add reference images when needed
Upload images that show the character, object, visual style, or source material you want to preserve or reinterpret.
- 03
Choose the layout and output settings
Select a square, portrait, or landscape aspect ratio, then choose the 1K, 2K, or 4K output level that fits your final asset.
- 04
Generate, review, and refine
Generate the image, check text and fine details, then use follow-up edit instructions to adjust composition, subjects, colors, or other elements.
Use cases
Built for Real Creative Workflows
Create images for the places where your audience already looks: social feeds, campaigns, product pages, and internal presentations.
Content Creators
Create Instagram posts, TikTok graphics, YouTube thumbnails, storyboards, illustrated sequences, posters, and personal creative concepts. Use text-to-image generation for new ideas, reference images for recurring subjects, and different aspect ratios to adapt one visual direction across social channels.
Create this imageMarketing & Ad Teams
Develop campaign concepts, ad creatives, marketing mockups, posters, localized graphics, product launch visuals, and presentation-ready ideas. Precise text rendering and image localization can help teams explore creative directions for different markets before final design review.
Create this imageE-commerce & Brands
Create product scene concepts, promotional graphics, lifestyle imagery, seasonal campaign assets, and branded visual ideas. Use prompt-based image editing to test backgrounds, layouts, and creative directions while keeping important subjects recognizable across related assets.
Create this imageEnterprise & Industry
Turn notes and structured information into diagrams, infographics, visual explainers, training concepts, and presentation graphics. Gemini's real-world knowledge can help with specific subjects, but factual labels, data, and technical details should be checked before external use.
Create this imagePricing
Nano Banana 2 Pricing & Access
Choose a one-time PWZ credit pack for image generation and editing workflows. The exact Nano Banana 2 credit cost is shown with the selected generation settings before you create.
600 credits · $0.042 per credit
Perfect for trying out PWZ — get started with a credit balance for your first generations.
- 600 credits
- High-resolution output support
2,000 credits · $0.030 per credit
For creators generating regularly — better per-credit value for daily PWZ workflows.
- 2,000 credits
- About 28% lower cost per credit
4,000 credits · $0.025 per credit
Best value for teams and content pipelines — more generations at the lowest per-credit cost.
- 4,000 credits
- About 40% lower cost per credit
- Priority processing speed
Compare
Nano Banana 2 vs Nano Banana Pro
Both models deliver high-quality image generation and editing, but Nano Banana 2 prioritizes speed and efficiency, while Nano Banana Pro focuses on precision, consistency, and professional-grade output.
ComparisonNano Banana 2Nano Banana Pro
Best forFast, everyday image generation and editingComplex, professional visual work
SpeedFaster, ideal for rapid iterationSlower, optimized for higher-quality results
Image qualityStrong quality for most use casesHigher fidelity and finer details
Instruction followingReliable for most prompts and revisionsBetter for complex or highly specific requests
Accuracy & consistencyGood for general creative tasksStronger for factual, brand, and visual consistency
Cost efficiencyBetter for frequent and high-volume useHigher cost, best for quality-critical work
FAQ
Nano Banana 2 FAQ
What is Nano Banana 2?
Nano Banana 2 is Google DeepMind's image generation and editing model, officially identified as Gemini 3.1 Flash Image. It supports image creation, editing, text rendering, localization, subject consistency, and higher-resolution workflows.
Can Nano Banana 2 generate and edit images?
Yes. The model is designed for both AI image generation and image editing. You can create an image from a prompt and refine existing or generated visuals with additional instructions.
Can Nano Banana 2 generate text inside images?
Yes, but you should review the result. Google highlights precise text rendering as a capability, while its model page also notes that spelling, small details, and long text can still contain errors.
Can Nano Banana 2 keep characters consistent?
Yes, with limitations. Google states that the model can preserve the resemblance of up to four characters and the fidelity of up to ten objects across a single workflow, though consistency is not guaranteed in every result.
Can Nano Banana 2 translate or localize images?
Yes. The model can translate text and localize content inside images. Google also warns that grammar, spelling, idioms, and cultural nuance may need human review.
Can I use Nano Banana 2 images commercially?
Commercial use is subject to the current PWZ and Google terms. Review both before publishing, licensing, or selling generated images.
Nano Banana 2 vs Nano Banana Pro: what is the difference?
Google positions Nano Banana Pro for high-fidelity work that needs maximum factual accuracy, while Nano Banana 2 emphasizes rapid generation, precise instruction following, and integrated image-search grounding. Choose based on the workflow rather than assuming one model is better for every task.
Ready to create
Create Your Next Image with Nano Banana 2
Generate a new visual, edit an existing concept, add text, localize creative assets, or build a consistent image sequence with the model on PWZ.
Start Creating