Pinterest uses AI to identify diverse skin tones, body types, and hair patterns across billions of images on its platform, then uses those signals to ensure that search results and recommendations reflect a broader range of human appearances. Users can filter fashion search results by body type ranges, skin tone ranges, and hair patterns. The body type technology launched in September 2023, with public user filters rolling out in March 2024; skin tone ranges have been available since 2018.

The body type system uses computer vision to classify shape, size, and form across more than 5 billion images — a task Pinterest describes as a first for the industry at this scale. These classifications feed into a diversity-aware ranking layer that adjusts search result ordering to prevent any single body type from dominating results. Pinterest reports a 454% improvement in body type representation on women's fashion searches, and users who applied body type range filters had a 66% higher engagement rate per session. The skin tone detection system uses the Monk Skin Tone Scale (a 10-point scale developed by Harvard sociologist Ellis Monk) to classify images, which users can then filter by. Hair pattern search allows users to filter by curl type. The systems were developed in consultation with external advocates including NAAFA and model Tess Holliday.