zlacker

[parent] [thread] 0 comments
1. dymk+(OP)[view] [source] 2023-01-14 16:37:28
Not being able to reproduce the inputs (each image is contributing single bytes to the neural network) is relevant. Torrent files are a means to exactly reproduce their inputs. Diffusion models are trained to not reproduce their inputs, nor do they have the means to.
[go to top]