Download
1 variant available
3750 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
4.2K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
6310 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(69)
Apr 17, 2024

1540 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.1K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
5.6K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
CreativeML Open RAIL++-MLora trained for Pony Diffusion XL, depicting Soraka, mostly based on her Wild Rift version.
Use activation tag:
soraka (wild rift)
General recommended tags should look somewhat like this:
score_9, score_8_up, score_7_up, source_anime <lora:SorakaXL:1> soraka (wild rift), soraka, purple skin, purple tattoos, pointy ears, long white hair, yellow horn, yellow eyes, hooves, goat hooves, belt, jewelry, crescent moon staff, orange shirt/dress
I would also suggest putting something like:
multiple horns, two horns
into the negative tags, the model can have some issues with that.
Most of the images I used in training didn't include her crescent moon staff so that too is somewhat finicky.
Overall though, the Lora works well.

