This LyCORIS has been trained after carefully selecting 54 images. All photos have been enhanced to make the most of them. I hope you like it!
Sophia Lillis (born February 13, 2002) is an American actress. She starred as Beverly Marsh in the horror films It (2017) and It: Chapter Two (2019), as well as Sydney Novak in the Netflix drama series I Am Not Okay With This (2020). Lillis has also appeared in the HBO psychological thriller miniseries Sharp Objects (2018) and the film Dungeons & Dragons: Honor Among Thieves (2023).
I don't ask for anything but any respectful constructive review (after having tested the model) would be highly appreciated or at least press Like if you're happy with results after trying it out! Thanks in advance and enjoy it!
From my experience it runs best with Edge Of Realism, pirsusEpicRealism, epicDiffusion ,RealisticVision, CyberRealistic, Deliberate checkpoints, among others, although I think it will be just fine in other SD 1.5 models as well.
CFG scale should be between 4-7.
LyCORIS weights should be between 0.9-1.2
Notice: This free work is intended for art and illustration purposes of emergent technology and not intended nor' trained for making illicit images, as the author I've taken care to not use any private data in the training process or designed it for such purposes. By downloading this model you are agreeing with the aforementioned intent and that you will not use my work to create / share images of a potentially immoral and / or illegal nature.
Description
FAQ
Comments (5)
Good model for headshots, but if you try to try to make images that are a bit more distant from it, it easily loses fidelity.
It happens with every model. Therefore you should use ADetailer and results are pretty awesome! Thanks for comments.
@astragartist Well, maybe it´s bad luck. Anyway, I will look for that ADetailer, I haven´t heard of it but maybe it can help me. Thanks!
@Blacksmith It's an extension for automatic1111. Try it and report any issue. I will help you if possible! ;)
This works great, can you give a bit more detail on how you trained it? What was your base model, some parameters etc. because I am genuinely impressed with how well it works