Google's Gemini has introduced the ability to create personalized images by utilizing Nano Banana 2 and your Google Photos library, provided you connect it to Gemini. This integration allows users to generate images with less extensive prompts, as the context of your photos will be automatically considered.
If you have enabled Personal Intelligence in Gemini and connected your Photos library, no additional setup is necessary. You can now request images with prompts like "design my dream house" or "illustrate my desert island essentials", resulting in outputs that feel tailored to you.
Furthermore, by tagging individuals in your Photos library, you can prompt Gemini with requests such as "create a claymation image of me and my family enjoying our favorite activity". Gemini will recognize your family members and the specific activity involved.
Google acknowledges that Gemini "might not always pick the exact photo or detail you had in mind on the first try," given this is a new feature. If the generated result doesn’t meet your expectations, you can provide feedback on what was inaccurate, upload a reference photo, and check how your context was applied by clicking the Sources button. You can also inquire with Gemini about attributions and sources for specific images.
Google assures users that it does not directly train its models on your private Google Photos library; instead, it only uses limited information, such as specific prompts and model responses, to enhance functionality over time.
The personalized image creation feature is set to roll out "over the next few days" within the Gemini app for eligible subscribers of the Google AI Plus, Pro, and Ultra plans in the US, with further expansion to Gemini on Chrome and additional users to follow "soon".
Source
