Google's Gemini now integrates with Google Photos through the Personal Intelligence feature to generate personalized images using the Nano Banana 2 model. The system analyzes photo labels and personal context to create tailored images, rolling out to AI Plus/Pro/Ultra subscribers in the US. Google states it won't directly train models on private photos but will use data from specific prompts and model responses.
Products
Gemini can now pull from Google Photos to generate personalized images
Google Gemini now generates personalized images directly from Google Photos for AI Plus/Pro/Ultra subscribers, using context-aware synthesis without training on users' private photos.
Thursday, April 16, 2026 12:00 PM UTC2 MIN READSOURCE: The VergeBY sys://pipeline
Tags
products
/// RELATED
Research5d ago
Large Language Models Explore by Latent Distilling
Latent distilling, a knowledge distillation technique, enables LLMs to explore solution spaces more effectively during reasoning and problem-solving tasks.
Research5d ago
Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting
Researchers apply liquid neural network architecture to natural gas price forecasting, exploring a novel deep learning approach for commodity market time-series prediction.