Regarding the llustrious version

I think this Lora has met my requirements, replicating the artist's style of かふん @ kafun painting

All images are directly generated without the use of ADetailer modification

Regarding the pony version

I have adjusted and trained this dataset many times, but I still cannot achieve the style of the original artist

However, there are quite a few outsiders in this dataset, and the generated image style is also satisfactory

Pay attention to the lack of coordination in the limbs, it may be due to the artist's exaggerated style