Google Launches Nano Banana 2

Google launched Nano Banana 2 on Thursday (Feb 26), the latest version of its popular artificial intelligence (AI) image generation model. Powered by real-time information and images from web search, the new model can create more realistic images than its predecessor and will be the default option in the Gemini app for its Fast, Thinking, and Pro modes.

“Nano Banana 2 brings the high-speed intelligence of Gemini Flash to visual generation, making rapid edits and iteration possible. It makes once-exclusive Pro features accessible to a wider audience,” Google said in a statement.

The new model can create media with more vibrant lighting, richer textures and sharper detail. It retains some of the high-fidelity characteristics of the Pro model but produces images faster. The company highlighted that users can create images with a resolution ranging from 512px to 4K, in different aspect ratios.

Google rolled out the Nano Banana AI image editor in August last year, which instantly became a viral hit. By mid-October, the model had generated more than five billion images. The tech giant followed up the success with the release of the upgraded Nano Banana Pro in November.

Features Of Nano Banana 2:
Advanced world knowledge: The new model utilises Gemini’s real-world knowledge base, and is powered by real-time information and images from web search to more accurately render specific subjects.
Advanced text rendering and translation: Nano Banana 2 allows users to generate accurate, legible text for marketing mockups or greeting cards. Users can also translate and localise text within an image to share their ideas globally.
Complex instruction following: The new model has enhanced instruction following, meaning it adheres more strictly to a user’s complex requests so that the image they receive is what they had asked for.
Production-ready specs: From 512px to 4K, the users have full control of aspect ratio and resolution to produce assets can be readily deployed.
Configurable thinking levels: Users have more control over the model’s reasoning. They can adjust thinking levels to allow the model to reason through complex prompts before rendering.
How To Use Nano Banana 2:
Gemini app: Open the Gemini app and access Nano Banana 2, which will replace Nano Banana Pro across the Fast, Thinking and Pro models.
Google search: The new model is available through AI Mode and Lens in the Google app, mobile and desktop across 141 new countries and territories in eight additional languages.
Google Cloud: Available in preview with the Gemini API in Vertex AI.
Google Ads: Nano Banana 2 is available now, powering suggestions while creating campaigns in Google Ads.