Google Releases Nano Banana 2 With Faster AI Image Generation, Enhanced Text Rendering Capabilities

Google released Nano Banana AI image generator in August last year. Also known as the Gemini 2.5 Flash Image AI model, the company claimed at launch that the new tool introduces faster image generation, enhanced element-based image editing, and improved character consistency capabilities. Later, in November 2025, the search giant started rolling out the Gemini 3 Pro-powered Nano Banana Pro with the ability to generate up to 4K resolution images, calling it the state-of-the-art (SOTA) image generation and editing model. Now, Nano Banana 2, Google's new AI image generation tool, has been launched by the Mountain View-based tech conglomerate, bringing the Pro model's quality at faster speeds.

Nano Banana 2 Availability, Capabilities

On Thursday, in a blog post, the Mountain View-based AI giant announced that Nano Banana 2 has started rolling out. Users can now try the company's latest Gemini 3.1 Flash Image AI model, also called Nano Banana 2, through multiple Google products. Nano Banana 2 replaces Nano Banana Pro for Gemini 3 series Fast, Thinking, and Pro AI models in the Gemini app. However, Google AI Pro and Ultra users will still be able to access it for “specialised tasks” by regenerating images in the app.

The Nano Banana 2 AI image editing and generation tool is also available in 141 new countries, including India, and eight new languages in Search in AI Mode and Google Lens via the Google app, phone browsers, and PC browsers. Moreover, people can access Nano Banana 2 as a preview in AI Studio, Gemini API, and Vertex AI.

It is now the default image generation model in Flow, Google Labs' high-fidelity video creation tool, and it will be available to all Flow users for zero credits. Lastly, Nano Banana 2 is also available in Google Ads. The tech giant claims that it can help users create campaigns and banners, while also providing suggestions for the ads.

Coming to its capabilities and the improvements, Google said that Nano Banana 2 leverages “Gemini's advanced knowledge base” and can utilise real-time information and images from web search. This allows the AI image editing and generation tool to offer enhanced subject-wise rendering capabilities faster. Moreover, it allows Nano Banana 2 to generate infographics, diagrams, and data visualisations with greater detail.

On top of this, Nano Banana 2 is capable of creating “precise” and “legible text” for marketing campaigns, greeting cards, and more. It also allows users to translate and contextualise text in an image. Google claims that Nano Banana 2 is also capable of generating high-quality “photorealistic imagery” at speed. It can maintain subject consistency of up to five characters, while also maintaining visual fidelity of up to 14 objects in one workflow.

Nano Banana 2 ships with improved “instruction following” capabilities, too. It can stick to more complex user queries, while also being able to understand nuances in user prompts. Similar to the Nano Banana Pro tool, Nano Banana 2 can also create up to 4K resolution images, while also integrating vibrant lighting, richer textures, and sharper details, Google highlighted.