This is more of a character pack than a style, but I found better results using the style tag rather than the character tag during LoRA training. You may notice some issues with backgrounds or occasional deformations. If any generation issues are consistent, please let me know so I can address them in the next version. The characters are listed in order based on how much training data they were given. For example, Yasmin, near the bottom, probably only had about 3 photos, whereas Brittany probably had 80, so keep that in mind. Enjoy!
IMPORTANT NOTE: All of my models were trained and tagged using Danbooru-style tagging conventions (e.g., courtney_(fellatrix), bob_cut, medium_hair, etc.)
Description
This is gonna be my last model for a little while until I get a larger data set and more buzz. Just wanted to update my oldest version for pony. Hope you enjoy as always.
FAQ
Comments (1)
Awesome style, i hope in the future i can see a comic animated with this style