Abstract: An event based personalized item generation system recommends available items in inventory to users based on upcoming events. The event based personalized item generation system includes a storage system and an event based item generator. The event based personalized item generation system receives available inventory information, user information for a user, and event information for an upcoming event, and generates a list of recommended items the system predicts will be of interest to the user attending the event. The event information is obtained from LLMs, AI models, stored data, scraping, or user input and includes event type, location, event setting, climate, local culture, and other event-related information. The user information indicates buying preferences of the user, including price range, designer or item source, taxon, color, sizing, gender, historical purchases, and other user preference information. In one embodiment, the inventory is provided by a single SKU (stock keeping unit) provider.

Abstract: An outfit recommender system includes an outfit recommender and a storage system. The storage system stores embedding information for available inventory and for preconfigured outfits. Available inventory changes dynamically as items are added or sold by a provider. Preconfigured items are grouped together to form outfits and are generated from any source regardless of whether such items are available or exist in the market. After a customer selects an item to view, a preconfigured item most visually similar to the selected item is obtained. The preconfigured item has associated preconfigured complementary items that together form the preconfigured outfit. Next, complementary items in available inventory most visually similar to the preconfigured complementary items are obtained and presented to the customer. The novel outfit recommender provides dynamic outfit recommendations that change as available inventory changes based on static, pre-curated outfits.

Abstract: Methods and apparatus for automated retouching of studio images are disclosed. In one embodiment, a method is provided that includes receiving an image that shows an item and a prop. The prop supports the item and includes a joint that forms a seam that is visible in the image. The method also includes modifying the image such that the seam is not visible in the image and the item in the image is unaltered.

Abstract: A product description generating system dynamically generates a description of an item based on one or more images. The product description generating system includes an attribute machine learning system that receives images of the item and determines at least one attribute value and corresponding prediction confidence value based on the image data. The user review interface provides an interface for reviewing attribute values generated by the attribute machine learning system. If the prediction confidence value is outside a threshold, then the attribute value is reviewed by a user via the user review interface. If, on the other hand, the prediction confidence value is within a threshold, then the attribute value is used to generate the description without user review. The user review interface groups items to be reviewed by taxon and facilitates user review of many items at scale.