This is an experimental merge that turned out surprisingly well, so I thought I'd share it with y'all. Pretty flexible with the right prompts.
Works really well on 768x768, but use the right size for any lora you're using.
CFG scale either 3.5 or 7 depending on what you're doing.
I like euler a at 30 steps myself, but should work with any sampler.
First merge is of HassakuHentai and Dreamshaper8, but more will be coming.
Initial release
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights.