Download
1 variant available
1260 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
5050 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
2190 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
(12)
Jun 1, 2024
Syndra now has her own tag (Syndra). Can be used in pos/neg prompt
Reduced LoRA file size
Improved watermark detection. enforce with negative prompt watermark
Might be slightly overtrained. Use weight 0.6-1 depending on use case
Show more

1840 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
1180 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
8940 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
License:
CreativeML Open RAIL++-MArtist Style Lora for Kumiko Aleron. Trained on Pony.
Activation tag: kumiko_aleron_style
Additional character tag: Syndra (from League of Legends; due to her being in a lot of good training images)
Best weight seems to be 0.6-0.8. 0.7 works best for me personally.
Trained on a lot of nsfw images due to the artists preferences, but generates sfw without issue.
V4 is out! V4 removes patreon watermarks entirely and improves dataset variety and tagging.