This is a LORA trained on the style of Kan Liu.
Description
Reduced pose-locking and unprompted water issues. Distant faces are also improved over the last release. Should now be more responsive to tags like ink and hydrokinesis. and just generally do a better job of getting out of your way while still adding to the final result when this isn't the only style element you want to use. In testing I found the best range for this version to be between 0.7 and 0.9. Still strongly influences outfits and hair color/style, which should hopefully be fixed by the next release.
FAQ
Comments (5)
Which model with hash HDDDD did you use for your great renders ?
It's a personal merge, but a major part of it's Hentai Diffusion.
I don't feel comfortable releasing that one, since one of the models in there has a pretty gnarly license, so I'll just list the models contained in it. Hopefully people can forgive that I don't remember the ratios for everything; I put it all together months ago.
Hentai Diffusion H17
Dreamlike Diffusion v1
JWST Deep-Space Diffusion
Double-Exposure Diffusion
Thanks, we understand. Where can we find the Hentai Diffusion ? Here in CAI doesn't exist (so says the search engine).
@ritcher1 It's over on their Github page currently (seen it move from HF to Github to a dedicated site and back, so this link might not stay correct): https://github.com/Delcos/Hentai-Diffusion
I find it's a little scuffed out of the box, but merging it with Dreamlike did a lot to impart a nice base style on it and restored a lot of artist tag functionality. The rest of the stuff in the merge is specifically for adding good sparkles and a double-exposure effect when I want it.
@LeTree Perfect, thanks !