
LoHa of Symboli Kris S (umamusume). Put LoHa file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoHa. <lora:your_loha_name:weight>
All of my works is free. If you'd like to support me, feel free to buy me a coffee. ?
Recommended options
-
LoRA weight 0.7 ~ 0.8
-
Trigger words
-
Base
-
symboli kris s \(umamusume\)
-
-
Racing competition costume :
-
high collar, shoulder armor, black gloves, white ascot, clothing cutout, cleavage cutout, crop top, shirt, gold trim, cropped jacket, green jacket, open clothes, long sleeves, navel, midriff, black belt, green shorts, short shorts, thigh strap, black footwear, knee boots
-
(optional) closed mouth, serious
-
-
Casual :
-
Not inclueded.
-
-
Tracen summer uniform :
-
tracen school uniform, summer uniform, serafuku, puffy short sleeves, purple bowtie, horseshoe ornament, sailor collar, sailor shirt, purple shirt, white skirt, pleated skirt, frills, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers
-
-
Tracen winter uniform :
-
tracen school uniform, winter uniform, puffy long sleeves, sailor collar, purple shirt, white bowtie, horseshoe ornament, purple skirt, pleated skirt, brown footwear, loafers
-
-
Other clothes :
-
swimsuit, green bikini, string bikini, side-tie bikini bottom, off shoulder, cleavage, groin, stomach, layered bikini
-
black shirt, brown coat, open coat, denim pants
-
shoulder bag, bracelet, necklace, white shirt, shirt stuck in skirt, black skirt, pencil skirt
-
-
Use a model derived from or mixed with animefull model.
-
Settings
-
DPM++ Series(SDE Karras, 2M Karras, etc.)
-
about 20 steps, CFG scale 3.5~6.5
-
I recommend kl-f8-anime2.vae
-
CLIP skip = 1
-
Use Hires.fix to get higher quality image
-
Upscaler
-
Latent, Latent (nearest-exact), Latent (bicubic antialiased) or other Latent series.
-
-
Denoising strength 0.50~0.65
-
LoRA training info
-
trained on sd-scripts by kohya_ss.
-
Thank you all a lot!
-
based on Animefull-pruned model
-
37 images consist of
-
4x low quality 14 images
-
8x medium quality 10 images
-
16x high quality 13 images
-
=> 1 epoch = 344 images
-
-
replaced character feature tags with symboli kris s \(umamusume\)
-
1girl, dark skin, tail, aqua eyes, purple hair, long hair, multicolored hair, purple eyes, horse girl, brown hair, horse tail, hair between eyes, bangs, horse ears, ponytail, green eyes, simple background, single earring, earrings, dark-skinned female, blue eyes, very long hair, animal ears, black hair, ear ornament, solo, hair ornament, braid, ahoge, mole under eye
-
I think these tags are the essentials of symboli kris s.
-
or unnecessary for training because of duplication.
-
-
resolution : 768x768 with aspect ratio bucketing.
-
other training settings is included in training_data.zip or metadata in LoRA file.
All uploaded images are generated by AOM3A1
And, special thanks to my best friend. DH.
描述:
LoHa of Symboli Kris S (umamusume). Please install extension on WebUI.
After installing extension, put LoHa file in your sd/models/lora folder and write LoRA notation in prompt to applying LoHa. <lora:loha_name:weight>
训练词语: symboli kris s \(umamusume\)
名称: img.zip
大小 (KB): 107505
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: symboli_kris_s_loha-000010.safetensors
大小 (KB): 12367
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success