SamSuka
sd_hassan
sd_hassan

patreon


Hassans Eye + Skin Enhancer

This is another version of the enhancer. The previous one focused on eyes and portraits and skin and hair, this one focuses mainly on eyes and the surrounding skin around the eyes and top of the nose etc. 

Really adds a nice effect to make it more realistic. 

18,500 steps



Comments

both options can work depending on the way your image is created

Stupid question (maybe), using this hypernetwork is it better to disable 'Restore faces' ?

kaosnews

ha cheers, was hoping something like that

Nicholas

This means I trained it on 18500 steps, to use it you just use whatever normal step could you use for prompting but I just share training data for those interested

normally might do up to about 300, seems a lot unless im missing something, which I'm expecting.

Nicholas

Thanks for this Hassan. Is that 18,500 sampling steps?

Nicholas

This file is a Hypernetwork. You place it in your Models/Hypernetworks folder. To activate it, you go to your main WebUI settings tab and select it under the dropdown for Hypernetworks. Then you set the strength just below from 0.0 to 1.0 (how much impact this has on your final image) . Then just generate an image to see any difference

I'm just sorting out how all of this works. I'm using Automatic1111. The error I'm getting is that it can't identify this pt file as either textual inversion embedding or diffuser concept. Is there a simple explanation as to how to use this within Automatic1111? Thank you for your work.


More Creators