Enjoy the empty eyes and hypnotized face!
I trained this LoRA using the images I created with my LoRA.
https://civarchive.com/models/577707/testmy-art-style-xenon3134mc-style
Description
Pony version
FAQ
Comments (7)
This may be just what I needed. I'll give it a try in anticipation.
And submit it to Gallery.
Since these LoRAs are created with images generated by AnythingXL, the SDXL versions would be more effective. Also, a slightly lower weight may give better results.
@xenon3134_mc
Oh, is this an XL base? I assumed it was a pony base since it says [Base Model Pony] in the summary column.
I have no complaints about the potency. I didn't feel the need to weaken it.
It was a bit of a problem when I tried to make a violent or different expression because of the nice blank eyes, so I may have needed to adjust it in that case.
(Original text. If you don't understand the intent, please translate this.)
あらっ、これはXLベースでしたか。概要欄に[Base Model Pony]とあるからponyベースだとばかり。
効力に関しては不満なし。弱める必要までは感じなかったかな。
いい感じに目が虚ろなので、暴力的な、別の表現をしようとしたときにうまくいかなかったので、そういうときは調整が必要だったかもしれない。
@kurodahuga843
No, the base model for this Pony version of LoRA is the HassakuXL, which is a Pony model.
When I say AnythingXL, I am not referring to the base model for LoRA training, but to the model used to generate the images used for training.
It would be easier to use images that are similar in artstyle to the base model for training.
It does affect the overall style, you probably put too many epochs
This fucks up the Pony LoRa models I use namely the all in one W.I.T.C.H. LoRa Model.
I love the style it adds ❤️❤️
Details
Files
Available On (4 platforms)
Same model published on other platforms. May have additional downloads or version variants.