Hello everyone,
this is one of my first training attempts of a character-lora from Sayori Wakaba from the anime "Vampire Knight".
recommended prompt:
1girl, solo, sayori wakaba, short hair, brown hair, brown eyes, necklace, hair between eyes
black school uniform, red bow, black skirt
quality tags i use:
oekaki, anime coloring, anime screencap, masterpiece, best quality, amazing quality
pls note: The Training-Data is from the anime in SD-Quality stretched to WQHD. Therefore especially the uniform is kinda blurry. I would recommend using an upscaler in img2img. Maybe the negative "blurry" does also the trick - didnt test it
My Settings (forge):
Checkpoint: waiNSFWIllustrious_v140
Sampler: Euler a
Scheduler: Automatic
Samplings Steps: 30
Hires.fix: R-ERSGAN 4x+Anime6B, 20 Hires steps, Denoising Strength: 0.5
Extentions (nice to have for little more Details):
Adetailer (highly recommended)
CFGRescale Integrated (forge)
CD Tuner
Detail Daemon
DynamicThresholding
FreeU
SelfAttentionGuidance