IrisRainbowNeko/DreamArtist-stable-diffusion

one shot training results are extremely poor, I cannot reproduce the results of the paper

Opened this issue · 0 comments

When I train with a picture from the paper
image
my training results are as follows with the prompt "a painting of city, art by ch_fg4; ch_fg-neg" :
image
image

but the results in the paper are like this:
image

My training parameters are as follows:
image
image
image

Is there something wrong with my training process causing this poor result?

Thanks!