Google is pushing things to the next level with the integration of Gemini into Google Photos. With the introduction of Ask Photos, it will make it easier for you to look for a specific memory or recall information included in your gallery.
“Ask Photos can help you search your memories more deeply. For example, you might be reminiscing about your daughter Lucia’s early milestones. Now, you can ask Photos: “When did Lucia learn to swim?”” Google’s head Sundar Pichai explained.
You can ask basic questions using Ask Photos, such as “Show me the best photo from each national park I’ve visited.” Google Photos can save you time and scrolling by displaying the information you need.
Also Read: Google is integrating Gemini straight into the Android OS, and more features unveiled
Taking advantage of Gemini’s multimodal capabilities, Ask Photos helps users remember crucial details and better capture memories by understanding the context and subject of photos. Therefore this will allow users to extract details like location, themes, and decorations. For example, you can ask questions about your life, like where you camped last year or when your vouchers expire.
“You can ask: “What themes have we had for Lena’s birthday parties?”. Ask Photos will understand details, like what decorations are in the background or on the birthday cake, to give you the answer,” Google explained.
Google Photos now simplifies tasks with Gemini models, such as creating trip highlights. Ask Photos suggests top pictures and personalised captions for easy sharing on social media, making it easier to manage and curate photos.’
According to Google after understanding your query, Ask Photos puts together a plan to find the answer. Along with identifying relevant keywords like places, people and dates it also conducts an advanced search on your behalf and delivers natural language concepts like “themed birthday party.”
Also Read: Google introduced a new AI model Gemini 1.5 Flash, upgrading Gemini 1.5 Pro
It then examines the search results and determines which appear to be what you’re looking for and which are the most relevant. Using the Gemini’s multimodal capabilities it can help understand exactly what’s happening in each photo and can even read text in the image if required.
