Google launched a new way to search the web using text and images at the same time. The new, AI-driven capability, called Multisearch, is available in Google Lens. It is designed for searches where a single image or text phrase are insufficient.

You can ask Google a question about an object in front of you, and use text to refine your search by color, brand, or a visual attribute. Here instances when you can use Multisearch:

  • Screenshot a stylish orange dress and add the query “green” to find it in another color
  • Take a photo of your dining set and add the query “coffee table” to find a matching table
  • Take a picture of your rosemary plant and add the query “care instructions”

To use Google Multisearch, first download the latest version of your Google app, then follow these steps:

  • Open the Google app on Android or iOS
  • Tap the Lens camera icon
  • Upload an image or take a photo of the world around you
  • Swipe up and tap the “+ Add to your search” button to add text

Google is currently exploring ways to use the multitask unified model to further improve search results.