Changed the tagging of the images to allow for easier outfit swapping. See the 3rd and 4th sample image prompts for examples.



A SD1.5 based LoRA based on Mitsurugi from Soulcalibur VI. Trained at a resolution of 576 x 576, so use that as your base resolution and upscale with Hires fix if needed. The optimal strength for this LoRA ranges between 0.8-1.0
v1.1 changes the tagging of the images to allow for easier outfit swapping. See the 3rd and 4th sample image prompts for examples.
Changed the tagging of the images to allow for easier outfit swapping. See the 3rd and 4th sample image prompts for examples.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
