Eonsang style for Pony Diffusion XL
This is a LoRA to replicate the style of Eonsang.
The results are most likely not optimal - these are my first experiments with PDXL. Expect better stuff!
Version 1.0a NEW
Weight
A weight value of 1 is totally fine.
Trigger words
No trigger words.
Known issues
You may need to lower the weight in certain situations. I would also suggest putting 'watermark' in the negative prompt.
Version 0.2
Weight
A weight value of 1 is totally fine.
Trigger words
No trigger words.
Known issues
It works very well with NSFW stuff (and this is not surprising), so if you use NSFW keywords in your prompt, you can expect something close to the artist's style.
If you DON'T use NSFW keywords, it doesn't work particularly well.
Description
This is version 1.0a: I've used a rather small dataset for training (around 120 pictures) in which the artist's most recent works are included. A different training process has been used (compared to version 0.2).