A model of Nashandra, trained over 44 images for 1024 using NoobAI Epsilon-pred 1.1 as a training model
Boss/True Form:
Trigger word: nashanoss
Looks tags: monster, colored skin, giant, crown, long hair, black hair, hollow eyes, skull, mask, sharp teeth, shoulder spikes, skeleton, bone, ribs
Optional tags: holding scythe
Weight: 1 is perfect
Human/False Form:
Trigger word: nashanormal
Looks tags: short hair, blonde hair, sidelocks, hair bun, hair up, blue eyes, necklace, high collar, yellow dress, long sleeves, wide sleeves, sleeves past wrists, lace-trimmed sleeves
Weight: 1 is perfect
Additional information:
Webui I use
AAA Anime VAE SDXL v2 as VAE
Sampling method: Euler a
Schedule type I set it to SGM Uniform
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