On Thursday, Google revealed that Gemini’s Personal Intelligence will include a Nano Banana-powered image generation feature, allowing images to be created with personalized context. This means that AI images can be generated using Gemini’s understanding of your preferences without needing them to be explicitly stated in the prompt.
This capability is feasible because Gemini has access to your data through Google account connections, such as Gmail and Google Photos. So instead of typing detailed prompts like “Generate an image of my dream home, my interests are tennis and music,” a simple “Design my dream home” will suffice.
Moreover, the Nano Banana-powered connection utilizes labels from Google Photos to understand names and terms describing groups like “Family.” For example, you can say, “Generate an image of my family and me doing our favorite activity” for image creation.
The “sources” button will display how Gemini derived context for generating images. However, Google acknowledged that the AI might sometimes interpret context incorrectly, inviting feedback. Users can also provide reference photos by using the “+” icon.
The image generation feature will be available to Plus, Pro, and Ultra subscribers in the U.S. in the coming days, with plans to expand it to Gemini in Chrome desktop and to other users soon.
Google initially launched Personal Intelligence earlier this year and made it available to all U.S. users in March. This week, the company extended the feature to more users in India and Japan.