zlacker

Diffusion models don't copy the pixels you show them. You cannot generally tell which training images inspired which output images.

(That's as opposed to a large language model, which does memorize text.)

Also, you can train it to imitate an artist's style just by showing it textual descriptions of the style. It doesn't have to see any images.

>>astran+(OP)
> Also, you can train it to imitate an artist's style just by showing it textual descriptions of the style. It doesn't have to see any images.

And the weights. The weights it has learned come originally from the images.