Gemini Can Now Create Personalized Images Grounded in Users’ Google Photos Libraries

Google’s Gemini AI can now create personalized images that take inspiration from the content of users’ Google Photos libraries. The new feature, which is part of the “Personal Intelligence” capability that connects Gemini to Gmail, Photos, and other Google apps, may help users to get more relevant results without the need for a very detailed prompt.

“One of the biggest hurdles in AI image generation is finding the right prompt. Previously, to get a result that felt truly personal, you had to write long, detailed descriptions and manually upload a reference photo just to give Gemini the right context. Now, Personal Intelligence gives Gemini an inherent understanding of your preferences from the start,” Google explained today.

Connecting a Google Photos library to Personal Intelligence in Gemini settings allows the chatbot to understand users’ interests and the people they care about. Gemini can also use data from user-created labels in Google Photos to create more personalized images. Google suggested a prompt like “create a claymation image of me and my family enjoying our favorite activity” to highlight Gemini’s ability to understand users’ tastes and who their close relatives are.

Personalizing images in the @GeminiApp just got easier — and you’re in total control. ✨

We’re introducing new ways for Personal Intelligence and Nano Banana 2 to generate images that can reflect your life, interests, and the things you care about most.

Here’s how it works 🧵 pic.twitter.com/F2gu4VExY0

— Google (@Google) April 16, 2026

Of course, despite getting this additional context, Gemini may still get some details in a generated image wrong. In that case, users can refine results by telling Gemini what was wrong or suggesting other pictures to use as inspiration. Clicking on the Sources button will also show which pictures the chatbot used as a reference.

This new personalized image creation experience is entirely optional, and Google emphasized today that it doesn’t use private Google Photos libraries to train its Nano Banana image generation models. “We train on limited info, like specific prompts in Gemini and the model’s responses, to improve functionality over time,” the company said.

Creating personalized images in the Gemini app will roll out first to Google AI Plus, Pro, and Ultra subscribers in the U.S. Google also plans to bring this new image generation experience to Gemini in Chrome soon.