Sign In

Diathorn Style [NAI]

101
828
7
Updated: Nov 5, 2024
style
Verified:
SafeTensor
Type
LoRA
Stats
828
Reviews
Published
Jun 2, 2023
Base Model
Other
Hash
AutoV2
0965B95780
default creator card background decoration
AnyKey's Avatar
AnyKey

Another request, a versatile style mixing both 3D and 2D elements with a slight oil painting touch. How it works depends largely on your setup, used as is it'll 3D-fy things which will work better or worse depending on what your model and other active LoRAs are specialized at. Please see the separate image for how this work on AOM2 for example.

How to use
Prompt as usual, dataset contains only females with a fairly broad mix covering muscular, pointy ears, all kinds of larger sized breasts, futanari etc so most tags should work.
Other things to try is "3D" or "2D" in negatives to push the style one way or another. Medium tags like "oil painting" can also give interesting results.

Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<

Misc
Dataset of 95 content filtered gelbooru images. 512 resolution trained on NAI without noise offset option for best LoRA compatibility.