Download
1 variant available
650 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5460 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
1320 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
(17)
Oct 7, 2024

600 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
250 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Created on Civitai
License:
CreativeML Open RAIL++-MHector from Netflix series Castlevania
My first attempt to training my own LoRA. The result was not as bad as I expected. However, many mistakes were made.
The source was snapshots from the second season of the series from Netflix. Therefore, there is only one suit.
Recommendations for use:
Weight 0.8-1.0
Sampler: Euler a
Use source_anime in your prompt.
Sometimes it's worth adding muscular, beard to a negative prompt
Use ADetailer for upper and full body image
