Google has rolled out a major upgrade to its AI image model, which has been informally referred to as “nano bananas” in the AI community. The new model, officially named Gemini 2.5 Flash Image, is integrated into the Gemini app and is also available to developers. This update represents a significant leap forward in image creation and editing capabilities, with a particular focus on improving consistency and control.
A key feature of the new model is its ability to maintain a subject’s likeness across multiple images, making it easier to place the same character or object in different scenes. It also introduces more precise, prompt-based editing, allowing users to make targeted changes like removing an object or altering a subject’s pose with simple text commands. In addition, the model can perform “multi-image fusion,” blending elements from multiple photos to create a new composite image.
All images created with Gemini 2.5 Flash Image will include both a visible watermark and an invisible SynthID digital watermark to ensure transparency and clearly identify them as AI-generated. The company’s goal is to give users and developers powerful new tools for creative expression while also building in safeguards.
