Doha:Google has launched Nano Banana 2.1, the newest version of its AI image generation and editing model, featuring sharper visual quality, more precise editing, and improved consistency for characters and objects across multiple images and edits.
According to Qatar News Agency, this model builds on its predecessor, Nano Banana 2, also known as Gemini 3.1 Flash Image, and is based on Gemini 3.6 Flash. The upgrade aims to enhance image creation and editing capabilities while maintaining the speed and efficiency of the Flash architecture.
Nano Banana 2.1 offers improvements in visual design, mask-based editing, and subject consistency, enabling more sophisticated visual compositions and natural-looking images. Enhanced mask-based editing allows users to make precise changes to specific parts of an image without affecting the rest of the scene, facilitating faster iterations.
The model ensures consistency across characters and objects, helping maintain recognizable appearances across multiple images and edits, making it suitable for visual storytelling and product development. It also enhances text rendering, infographic design, and can utilize Google's real-world knowledge for accurate visual representations. Additionally, it supports image upscaling to 2K and 4K resolutions and offers flexible aspect ratios.
Google is integrating Nano Banana 2.1 into its ecosystem, including the Gemini app, Google Search AI Mode, Google AI Studio, Google Flow, Google Stitch, Google Ads, and Gemini Enterprise. It is also accessible to developers through the Gemini API under the identifier gemini-nano-banana-2.1, supporting a variety of input types such as text, image, video, and PDF.