Another experiment that came out well, the idea was simply to make a lora that can do alot of the post processing i end doing to my images like adding film grain, edge blur, muted "cinimatic"/moody color grading etc.
I think along with ZIT's great prompting this can make pretty good images. Made it for personal use but i think some people might find a use for it :D
I think it can start to make strange artifacts with some schedulers/nodes, i stuck with the eular/simple combo to make it easy for people to replicate at 1.0 strength
PS. hands are a little broken i think no idea what i did to do that :(
Feel free to let me know what you think.
Description
Honestly its a bit meh, compared to the original ZIT version
FAQ
Comments (12)
"Honestly its a bit meh, compared to the original ZIT version"
I tried training flux2 stuff as well, it comes out okay, but ZIT is just way easier to train on without the body horrors. But you should give chroma1HD a try, its really good. But it still looks good, i'll try both. Thanks.
Thanks, I usually just stick to one model and ZIT is it for me, flux Klein is only really useful for when i need to edit stuff etc. but ill give it a shot :)
qu'est-ce que c'est?
I don't speak persian.
@purplelady maybe indian ?
@Reelai defiantly not Australian that i know
This LoRA is really nice. Will there be a Z base version? Because Z base has more composition possibilities.
thanks i mostly train on civitai's lora training thing and they don't have zimage base as an option which is why i never made a base version
Krea2? 🙏