Gemini Can Now Create AI-Powered Images Using Your Own Photos and Videos.
The Gemini app has long been able to interact with other Google apps, but earlier this year, these integrations became even tighter and more seamless thanks to the Personal Intelligence feature. Now, Personal Intelligence is expanding to Google Photos, bringing AI-powered image creation capabilities to the Nano Banana 2.
The idea is that you don’t have to manually select an image in Google Photos and give the AI a command. Instead, you simply enter a query, such as “create a cartoon showing my family enjoying their favorite activities,” and Gemini will do the rest—finding the necessary information and people in your Google Photos library.
Another example of a Google prompt: “Create a watercolor image of my dream home in my favorite place.” You can see how these new integrations save you time—you don’t have to explain what your dream home or favorite place looks like when Gemini can figure it out from your photos.
“Because this feature is built into the standard Gemini app experience, no additional setup is required,” Google states . “If you’ve already linked your Google apps, this personalized context will be ready and waiting for you when you start creating images… results will automatically reflect your specific tastes and lifestyle, derived from your connected Google apps.”
The updated Personal Intelligence feature is already available to Gemini app users in the US, but access requires a paid customer with an AI Plus, AI Pro, or AI Ultra plan. Google says more users will be able to access it, along with support for Gemini in Chrome, coming soon.
How it works and how to turn it off
This feature is currently rolling out to Google AI subscribers in the US, so if you’re one of them, you won’t need to take any special action to get the new feature in Gemini on the web or mobile. You may see a pop-up message within the app notifying you that you’ve received the update, as Google often does.
By selecting the “Create Image” option, you can simply enter the text you want to see, and Gemini will take care of the rest. For example, “create a sketch of my family on vacation at the beach” or “make a photo collage of things I would take with me to a desert island” should work if Google Photos has enough information.
Google claims that Gemini will analyze the tags you’ve entered in Google Photos, such as people’s and pets’ names, to try to understand what you’re asking for. Clearly, the AI at work here involves quite a bit of guesswork, and, according to Google, “Gemini may not always select the exact photo or detail you had in mind the first time.”
You can always click the “Sources” button below the AI-generated image to see the photos Gemini has selected as references and ask Gemini to make adjustments to the generated image using additional suggestions. You can also click the “+” (plus) button in the suggestion field if you want to point Gemini to a different reference photo.
There’s something a little creepy about asking Gemini to use these intimate details of your life, but the novelty lies in the integration between the apps: if you use Google Photos, the app constantly uses AI to recognize the content of your photos so you can better sort and organize them, including photos of family members and pets.
Google states that Gemini doesn’t train its AI models “directly” on your photos, but instead uses “limited” information from them to improve the user experience. Connecting Google Photos to Gemini remains voluntary, and you can undo it at any time: in the Gemini app, tap the gear icon (on the web) or tap your profile photo (on mobile), then select “Connected Apps” to make changes.