You will notice that there are two versions one called All in One and God Soul Standalone, the reason for it being while testing the god soul form it worked great as a standalone but then when I merge it with her normal form for some reason it didn't want to do the god soul form consistently but the God Soul Standalone can do it with any issues, you can try with the All in One but you will get it maybe 1 in 20 images but the standalone version does it without any effort
A model of Dimaria Yesta from Fairy Tail, trained over 118 images at 1024 using Initium as a training model
All in One
Trigger word: Dimaria
Weight: 1 is perfect
Appearance tags: brown eyes, bangs, short hair, blonde hair, hair between eyes
Outfit tags:
1. Bodysuit: multicolored bodysuit, blue bodysuit, black bodysuit, yellow trim, skin tight, single pauldron, yellow pauldron, single gauntlet, yellow gauntlet, blue knee boots
2. Armor: detached collar, red collar, red bandeau, strapless, bare shoulders, cleavage, single pauldron, yellow pauldron, single gauntlet, yellow gauntlet, black clothes around waist, black jacket around waist, black and red striped pants, sandals
God Soul same applies for both versions
Trigger word: Dimariags
Weight: 1 is perfect
Appearance tags: glowing, aura, floating hair, glowing hair, long hair, one eye, no pupils, glowing eye, neon trim, colored skin, black skin
Additional information:
Webui I use
AAA Anime VAE SDXL v1.5 as VAE
Sampling method: Euler a
Schedule type I set it to Karras
Sampling steps I go 20-30
4xNomos8kDAT as an Upscaler
Hires steps I go 8-15 (I don't always use hires fix)
Denoising strength I go 0.4
Upscale by 1.2 to 2.0 depending on the starting image dimensions
Imagine dimensions vary depending on what I'm trying to do
I use 6 CFG Scale
uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face
If you wanna support me ko-fi