Google has introduced Nano Banana 2 (Gemini 3.1 Flash Image), its latest image generation model.
The model is designed for quicker image generation and editing with improved accuracy and detail.
It uses Gemini’s knowledge base and real-time web data to better render specific subjects. It can also generate infographics, diagrams, and other data visualizations.
Nano Banana 2 improves text rendering inside images, making text clearer for mockups and visual materials. It also supports translating and localizing text within images into different languages.
According to Google, the model improves subject consistency, allowing up to five characters and up to 14 objects to remain consistent within a single workflow. It is also built to follow more detailed prompts more closely. Users can generate images in different aspect ratios and resolutions, from 512px up to 4K.
Google says users can choose Nano Banana 2 for faster generation and editing, while Nano Banana Pro remains available for tasks that require higher factual accuracy and more advanced control.
Nano Banana 2 is rolling out across Google services, including the Gemini app, where it replaces Nano Banana Pro in Fast, Thinking, and Pro modes. Meanwhile, Google AI Pro and Ultra subscribers can still access Nano Banana Pro for specific tasks.
The model is also available in Google Search, including AI Mode and Lens, on mobile and desktop. It is currently in preview in AI Studio, through the Gemini API, and on Google Cloud Vertex AI.
In Flow, it is now the default image generation model. It is also being integrated into Google Ads for image suggestions during campaign creation.
ManilaShaker is a tech media producing insightful and helpful content for our local and growing international audience. Our goal is to create a premier Philippine digital consumer electronics resource that provides the most objective reviews and comparisons globally.
