In a literal sense, no, it does not use reference boards. I was being glib, perhaps too glib. A less objectionable rephrasing might be “the AI is composing a bunch of visual features together into a coherent image; it’s cool that this tool can show you images in the training set where the AI might have learned those visual features from.” It may still be inaccurate to say “reference boards” at all, because the temporality is reversed: human artist has a reference board, then does some black box process in their brain to draw inspiration from them, then outputs the final art piece. The AI draws on all the training data to produce the final image and it’s only by analyzing the final image that you can reconstruct which images in the training set were important.

Mostly I was just tickled by the fact that you can now get something that looks like a reference board for the generated image. There are some parallels to the human process, but maybe there are not enough parallels or the parallels don’t run deep enough to make it sensible to call this “the AI is using a reference board”.