Google recently announced that Gemini's Personal Intelligence feature will incorporate "Nano Banana-powered" image generation, designed to create images with personalized context. This new capability allows AI images to be generated based on Gemini's understanding of a user's likes and interests, eliminating the need for explicit details in the prompt.
This functionality is enabled by Gemini's existing access to user data context through connected Google accounts, such as Gmail and Google Photos. Consequently, users can now simply say, "Design my dream home," instead of providing detailed prompts like, "Generate an image of my dream home, my interests are tennis and music."
Furthermore, the Nano Banana-powered connection can leverage labels within Google Photos to comprehend names and group descriptors like "Family." For example, users can now generate an image by simply stating, "Generate an image of my family and me doing our favorite activity."
Google stated that a "sources" button would allow users to see how Gemini derived the context for image generation. Google cautioned that, similar to other connected features, Gemini might occasionally misinterpret context, and users are encouraged to provide feedback. Additionally, users can supply reference photos for image generation by clicking the "+" icon.
This image generation feature will be rolled out to Gemini Plus, Pro, and Ultra subscribers in the U.S. within the coming days. Google intends to extend the feature to Gemini in Chrome desktop and other users shortly thereafter.
Personal Intelligence itself was initially launched by Google earlier this year, becoming available to all U.S. users in March. Earlier this week, Google expanded this feature to additional users in countries such as India and Japan.