This is an LCM version of the TRUALITY ENGINE (PRO) model by CivitAI user Tower13studios. Thank or tip that user, not me.
https://civarchive.com/models/158621/the-truality-engine
https://civarchive.com/user/Tower13Studios
It works quite well for AnimateDiff, cutting down generation times by quite a lot whilst still having decent quality.
8-10 steps works well for both regular image generation and AnimateDiff. For inpainting (including Adetailer) and hires fix it seems best to reduce the steps to 4. And just like all LCM models you have to keep the CFG scale low (1-2).
I'd like to find out how to reduce the blur, or other strange quality issues, which seems to be a problem with non-LCM models too.
I saw the non-LCM model of this recommended in an AnimateDiff guide, so that's why I chose it to make an LCM with.
Please like and follow and feel free to ask questions.
My Socials
Patreon: https://www.patreon.com/slashkey
X/Twitter: https://x.com/SlashkeyStudio
YouTube: https://www.youtube.com/@slashkeystudio/featured
Instagram: https://www.instagram.com/slashkeystudio/
Description
FAQ
Comments (3)
when i do portraits, proportions are all wrong, like the stomach will be so small, how do I fix it. I have put accurate body proportions but that doesn't work
Please post an image in the gallery so I can see what you're referring to and your prompt and such. :)
@slashkey thanks for the reply my friend. How about, instead, you make an updated version 2? this is a really good LCM checkpoint, I think it could be even better! just make sure the sample doesn't have to be LCM, diffusion bee doesn't offer that, but it does allow LCM models, and its super quick that way, so please do an updated v2 model.