LoCon of Super Creek (umamusume)
Please install extension on WebUI.
All of my works is free. If you'd like to support me, feel free to buy me a coffee. 👍
Recommend options
LoCon weight around 0.7
Trigger words
base
super creek \(umamusume\)
Original racing clothes (SSR stamina) :
detached sleeves, long sleeves, bare shoulders, sleeveless sweater, ribbed sweater, white sweater, turtleneck sweater, wrist cuffs, strap between breasts, handbag, shoulder bag, blue dress, thighhighs, zettai ryouiki, thigh boots, mismatched footwear, asysmetrical footwear
Racing competition clothes :
blue scarf, detached sleeves, bare shoulders, o-ring, clothing cutout, wrist cuffs, scrunchie, strap between breasts, handbag, shoulder bag, blue dress, white skirt, zettai ryouiki, thigh boots
Mummy Creek :
official alternate costume, halloween costume, mummy costume, ear ornament, choker, cleavage, wrist cuffs, bare shoulders, bandages, bandaged arm, fingernails, nail polish, torn clothes, navel, skirt, frills, bandaged leg
Casual clothes :
puffy long sleeves, sailor collar, yellow shirt, brown shirt, white shirt, pink bowtie, necklace, belt, pleated skirt, blue skirt, brown footwear, high heel boots
(optional) mimikaki
Tracen school uniform :
white thighhighs, tracen school uniform, purple shirt, pleated skirt, puffy short sleeves, white skirt, puffy sleeves, summer uniform, frilled skirt, sailor collar, sailor shirt, miniskirt, frills
Use animefull based model
Settings
DPM++ Series(SDE Karras, 2M Karras, etc.)
about 20 steps, CFG scale 3.5~6.5
CLIP skip = 1
Use Hires.fix to get higher quality image
Up-scaler : Latent series
Denoising strength 0.50~0.65
LoRA training info
trained on sd-scripts by kohya_ss. Thank you a lot!
based on Animefull-pruned
134 images of super creek
4x low quality 39 images
8x medium quality 47 images
16x high quality 48 images
=> 1 epoch = 1300 images
replaced character feature tags with super creek \(umamusume\)
horse girl, horse tail, brown hair, blue eyes, etc.
resolution : 768x768
rank=alpha=16
conv_rank=conv_alpha=16
batch size = 4
other training settings is included in training_data.zip
This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)
All uploaded images are generated by AOM3A1
Thank you KohakuBlueleaf for introducing LoCon.
And, special thanks to my best friend. DH.