Pinterest has introduced a new visual search feature targeting “a more personalised discovery experience”. It’s be available for women’s fashion content across the UK, US and Canada, and “will expand to more categories and countries over time”.

The company said that “most online searches start with words, but describing a vibe, style or aesthetic can be hard and limiting. As a visual search platform, Pinterest enables people to overcome this obstacle, by using images at the starting point for a search”.

Essentially it comes up with words to reflect the images they’re seeing, which sounds simple but actually requires a lot of complex tech to make it happen.

The new features allows users to further interact with image Pins so they can “more intuitively discover, refine and shop the ideas that perfectly match their personal tastes”.

VP of design Dana Cho said its “visual search technology represents a shift in how users interact with and discover inspiration. We’re not simply delivering search results – we’re curating a personalised journey of discovery that empowers individuals to find their unique style, and shop it too”.

It’s breaking down and decoding images “so users can quickly search and shop for the details of an outfit. Whether it’s an overall aesthetic, a colour palette, a specific fit, or product category, when users view a Pin, we’ll now generate the words they can use to figure out what they like about the image, and then further explore and shop. To help users more easily identify and select the objects that they want to see and shop more of, we’ve added a new animated glow”.

As part of the overall enhancements it’s adding a new refinement bar to help users narrow their search results. For example, if a user spots an outfit they like, they can use the ‘style’ refinement to see similar outfits but more Y2K. Or if they love, say, a blue blazer, and use the ‘occasion’ refinement, they’ll see more formal options.

And it’s expanding where users can access its visual search features, including the ‘Search image’ button, by enabling users to long press on any Pin on their home feed.

Of course, as might be obvious by now, this is all due to advances in AI. It’s using Visual Language Models (VLMs), a form of generative AI, to provide users with a more expansive visual “vocabulary” to “describe” their style ideas. And it said it’s “integrated industry-leading multimodal embedding models to provide users with the tools to more easily search using a combination of image and text to find the exact content matching their specific tastes”.
 
In theory it means “no more settling for generic search results or feeling limited by not having the right words. With our new visual search features, users can more intuitively discover, refine and shop, turning their inspiration into reality,” Pinterest said.