Hey @zone - the call for this in JS is similar to the other models:
// do something with response
// there was an error
The response will differ a lot from our regular Face Detection Model since the latter simply gives you a bounding box of the faces that it finds, and the former returns numerical vectors that represent each detected face in the image in a 1024-dimensional space. Typically this is useful for Data Scientists and others looking to dig deeper into the data, but in terms of accuracy the two models are essentially giving the same results in different formats.