Google’s Nano Banana 2, its latest image-generation model, is now available in the Middle East and North Africa.
The model can be accessed on desktop and mobile versions of Gemini as well as through Google Search via Google Lens and AI Mode, the company said.
Nano Banana 2 introduces visual-generation capabilities built on Gemini Flash technology, allowing users to create and edit images with faster processing speeds. The rollout also expands access to features previously limited to higher-tier models.
Among the capabilities is integration with Gemini’s knowledge base and real-time web search, allowing the model to draw on up-to-date information and images when generating visuals.
The model also supports text rendering and translation within images, enabling users to produce marketing materials, greeting cards and other visual content with legible text that can be localised into different languages.
Nano Banana 2 allows users to maintain visual consistency across multiple elements within a project, supporting resemblance for up to five characters and fidelity for up to 14 objects within a single workflow.
The system also provides control over image specifications, including aspect ratios and resolutions ranging from 512 pixels to 4K, allowing visuals to be adapted for formats such as social media posts or widescreen displays.
Google said the model delivers improved lighting and sharper detail while maintaining the processing speed associated with Gemini Flash.
Nano Banana 2 is being rolled out across Google products starting this week, including Gemini applications and Google Search.
The model is also available in preview through AI Studio and the Gemini API.
