Updated 13.07.23:

2 Words about big model:

1) you can click on "Training Images Download", there non training images, it's wildcard file with trigger words;

2) 21k steps x4 batch size(80k steps is scare if you don't know what it have like 16 subsets and small learning rates) -> don't use it with power 1.0, use it with 0.7 or even less. Yes it not so much flexible, it more about character Details.

Old:

Train LoRa is time and resource expensive, you can support my future works here:

❤️Boosty Donation link

it would be great if you could show some of the results of your work as a post/review

Haiyore! Nyaruko-san

Nyaruko

Cthuko

Hasuta

Mahiro Yasaka

Ghutatan

Yoriko Yasaka

Tamao Kurei

Luhy Distone //read about this version block

Shantak-kun (girl form)

Tsuruko

Cthune

Atoko Shirogane

//info will be updated later(on monday i think, after i start to upload other characters)

Why my LoRa's? Because it's close to anime style, and this style is ~simple in details and can change without mutating target style more easy than artistic one. And it's hard to get quality anime style pictures from LoRa's with more artistic dataset with gradients and complex lighting.