Merged (base SDXL) model with my own LORAs to make photorealistic and fantasy portraits.
I suggest using in ComfyUI due to its faster speed than Automatic1111.
The WF I am using should be sewn into the files.
Support Paweł Tomczuk on Ko-fi! ❤️. ko-fi.com/aderek514 - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.
Visit my DeviantArt page: Aderek - Hobbyist, Digital Artist | DeviantArt
Description
FAQ
Comments (6)
Not sure what you added to this but its super blurry. Did you add lightning or hyper? Because they don't mix well at all.
try add clip skip -1 or -2
same issues on comfyAi, using clip skip made the image really bad like a kids drawing,
prompt adherence is bad quality bad, i tried so many samplers and settings.
what do you use to merge loras to checkpoint.
also base being bad on its language training wouldn't using someone like juggernaut v9 be better?
so curious to learn
thanks, will try you model.