Add image to text and image to image directly from the generators and and add more details to text to image generators , available model of image gen is too bad in realistic and anime style no clear details add samplers and loras selection also

1 comment

sorted by: hot top controversial new old
[–] 1 point 11 months ago

they need image to text since i noticed even those are often censored or freemium image to image can also be cool. there are some things that are possible in perchance but i don't know how to describe them in a way that the ai understands .while other stuff just seems impossible or the ai struggles with it for

  • source