Google Gemini can now generate personalised images using Google Photos: Here is how

Google has announced a new update for the Gemini app that makes AI image generation more personal. The company says Gemini can now create images based on a user’s interests, preferences and photos stored in their Google Photos library. The goal is to make image creation easier and reduce the need for long and complicated prompts.

Survey

Until now, users often had to write detailed prompts and upload reference photos to generate images that felt personal. With the new update, Gemini can understand more about the user from connected Google apps and automatically use that information while creating images. 

Also read: OpenAI introduces GPT Rosalind for scientific research: What it can do

How Google’s Gemini personalised image creation works

The feature is powered by Google’s Personal Intelligence system and its Nano Banana 2 image generation model. Together, they allow Gemini to use context from Google apps that a user has connected to their account.

For example, instead of writing a long description, users can simply type prompts like ‘Design my dream house’ or ‘Create a picture of my desert island essentials. Gemini will then generate images that reflect the user’s preferences using information gathered from connected apps.

Also read: OpenAI upgrades Codex with computer control, image generation to rival Claude Code

If users link their Google Photos library, Gemini can use labelled photos of people and pets to guide the image creation process. This allows the AI to include real people from the user’s life in the generated images.

For instance, users can ask Gemini to ‘create a claymation image of me and my family enjoying our favorite activity,’ and the AI can generate an image using photos from the library as references. Users can also try different art styles such as watercolour paintings, charcoal sketches and oil paintings. If the generated image is not accurate, users can give additional instructions to refine it. Users can also manually choose a different reference photo from their Google Photos library.

Google explains that Gemini does not directly train its models using a user’s private Google Photos library. 

Also read: Is AI replacing jobs or creating them? Here is what LinkedIn data says

Availability

The new personalized image creation experience in the Gemini app is rolling out over the next few days to eligible Google AI Plus, Pro and Ultra subscribers in the US. Google plans to bring the feature to Gemini in Chrome desktops and more users soon.

Ayushi Jain

Ayushi works as Chief Copy Editor at Digit, covering everything from breaking tech news to in-depth smartphone reviews. Prior to Digit, she was part of the editorial team at IANS. View Full Profile