Nano Banana 2

Google

Google DeepMind's image generation and editing model, formally named Gemini 3.1 Flash Image and marketed as Nano Banana 2. It pairs Nano Banana Pro's capability with Flash-level speed, holds character consistency across up to 5 characters and 14 objects, renders legible text directly into images, grounds generations in real-world knowledge via web search, and upscales to 2K and 4K.

Strengths

Pro-level image generation and editing at Flash-level speed
Character consistency across up to 5 characters and 14 objects
Renders legible text directly into generated images
Grounds generations in real-world knowledge using web search
Upscales output to 2K and 4K, across square, portrait and landscape formats

Caveats

Proprietary - Google API and consumer surfaces only
The API id is a preview identifier (gemini-3.1-flash-image-preview)
Google reports Elo results only as approximate chart values, so no scores are recorded here
No release date is stated on the model page

Vendor: Google
License: Proprietary
Modalities: text
image

Capabilities

Vision

Audio

Video

Tool Use

Resources

API Documentation

Pricing

Usage-based per-image pricing via the Gemini API and Google AI Studio; also available in the Gemini app and AI Mode in Search.