First version released, this is still experimental. This LoRA has over 20 epochs, and this is the one that gave me the least amount of artifacts without losing the style I tried to go for.
Recommended:
Strength 0.9 definitely the best option.
As for the cfg, same as my other LoRAs, 3.5 or lower, as anything above 4.0 will start giving you overblown results.
Thank you again for using my LoRA, you can support me through either donating Buzz, or you can use one of the links provided beneath my profile.
Version v2.5:
New version aiming for a more stable and consistent style, basically re-did the whole dataset like I did the Classic Disney, changed a few settings when training and threw it over to the RNG gods, the result, well, definitely a bit more consistent and high quality but there were a few images that came out with some artifacts specially around the navel, like duplicated navels and whatnot, I still don't know how to tackle those issues specifically but it is what it is.