Google has enhanced its Gemini AI by allowing users to create personalized images through integration with their Google Photos library, utilizing the new Nano Banana 2 feature. By connecting their Photos library, users can generate images using simple prompts without the need for lengthy descriptions or reference photos. For example, users can request Gemini to 'design my dream house' or create a claymation image of their family enjoying a favorite activity. While Gemini aims to provide accurate results, it acknowledges that it may not always capture the desired details on the first attempt, allowing users to provide feedback or upload reference photos for better accuracy. Importantly, Google clarifies that it does not train its models directly on users' private Google Photos, instead using limited information to enhance functionality. This personalized image creation feature is set to roll out over the next few days for subscribers of the Google AI Plus, Pro, and Ultra plans in the United States, with plans for broader availability in the near future.