Find Art by Similarity
Upload any image and discover the artworks closest to it in visual character.
Customers upload any image—a piece they love, a photo from a magazine or a screenshot—and the system returns the artworks that are closest in visual character.
At the core is a vision encoder from a contrastively trained vision-language model. At query time, the image is encoded into a vector and a nearest-neighbour search across precomputed portfolio embeddings returns the closest matches.
The result is a discovery experience that works the way intuition does: not through tags or categories, but through visual affinity.