This is the LoRa model trained with some of the comics artists that I liked. (3~4 artists)
I used AbyssOrangeMix2.
Description
FAQ
Comments (6)
Looks cool
Thanks. I really like that more non anime cartoon styles are getting love. You think you could share the artist names? I'm curious.
Well, that could make some trouble so I couldn't.
@quack_quack_22 I understand, better to not risk getting it taken down. Great job tho.
Hello, I met some problem when I used it. Is the sd1.4 could not run it, or it's my problem?
it said NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
How can I solve it? I really like this kind of art! thanks!
Will this be back with on-site gen?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.