Nano Banana 2 (Gemini 3.1 Flash Image) is Google's latest state-of-the-art image model that brings the advanced world knowledge, quality and reasoning of Nano Banana Pro at lightning-fast speed. This image generation model combines Pro capabilities with Flash speed, making rapid edits and iteration possible.

The model offers advanced world knowledge by pulling from Gemini's real-world knowledge base and is powered by real-time information and images from web search to accurately render specific subjects. It provides precision text rendering and translation capabilities for generating accurate, legible text and localizing text within images. Nano Banana 2 maintains subject consistency of up to five characters and the fidelity of up to 14 objects in a single workflow. It features enhanced instruction following that adheres strictly to complex requests and offers production-ready specs with full control of various aspect ratios and resolutions from 512px to 4K.

Nano Banana 2 brings the high-speed intelligence of Gemini Flash to visual generation, dramatically closing the gap between speed and visual fidelity. The model delivers vibrant lighting, richer textures and sharper details while maintaining high-quality aesthetics at Flash speed.

The model enables users to create infographics, turn notes into diagrams, generate data visualizations, create marketing mockups, greeting cards, and storyboard narratives without altering the appearance of inputs. It helps create attention-grabbing assets for vertical social posts or wide-screen backdrops.

Nano Banana 2 is rolling out across Google products including the Gemini app, Search, AI Studio, Gemini API, Google Cloud Vertex AI, Flow, and Google Ads. It replaces Nano Banana Pro across Fast, Thinking and Pro models in Gemini app and is available to Google AI Pro and Ultra subscribers for specialized tasks.