Google announced today that the Gemini Personal Intelligence feature is now available in Nano Banana 2, the company’s popular AI image model.
Now, instead of uploading a photo, users can give Nano Banana access to their Google Photos library, which will allow Nano Banana to generate personalized images for users.
Don’t miss out on our latest stories: Add Mashable as a trusted news source in Google.
“One of the biggest hurdles in AI image generation is finding the right prompt,” reads a Google blog post. “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.”
Nano Banana is one of the web’s leading AI image generators, and it’s particularly good at editing photos. With Personal Intelligence, Nano Banana can reference your images and Labels to make photos based on you, your pets, or anything else in your library.
Mashable Light Speed
Google gives several examples of how this could be useful. For instance, instead of uploading an image of your family and writing a detailed prompt, you can simply tell Gemini to “Make a claymation image of my family.” Google also suggests prompts such as “Design my dream house” and “Create a picture of my desert island essentials.”
AI-GENERATED IMAGE
Credit: Google
AI-GENERATED IMAGE
Credit: Google
Users will need to organize and label their photos for the feature to work as intended, however.
Of course, before granting an AI tool like Gemini or Nano Banana access to your entire photo library, it’s important to understand how your images will be used.
Google says that Gemini will not “directly” train its models on your photos; however, it will be able to train its models with the photos, prompts, and AI-generated images that appear in the Gemini app.
“The Gemini app does not directly train its models on your private Google Photos library,” the blog post states. “We train on limited info, like specific prompts in Gemini and the model’s responses, to improve functionality over time. And connecting your Google apps to Gemini remains an opt-in experience that you can adjust in your settings at any time.”
As ever, it’s important to check the fine print before using a new feature like this. You can read more about training and privacy at the Google Gemini Privacy Hub.
Want to learn more about getting the best out of your tech? Sign up for Mashable’s Top Stories and Deals newsletters today.
