
LoHa of Kawakami Princess (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 around 0.7
-
Trigger words
-
Base
-
kawakami princess \(umamusume\)
-
-
Racing competition costume :
-
ear ornament, pink dress, bare shoulders, cleavage, sleeveless dress, detached sleeves, pink sleeves, white thighhighs, pink footwear, boots
-
-
SSR Speed (Wedding) :
-
official alternate costume, hair ornament, hair flower, tiara, bridal veil, frilled choker, blue choker, pearl necklace, jewelry, collarbone, wedding dress, strapless dress, aqua dress, bare shoulders, cleavage, elbow gloves, wrist cuffs, white gloves, bridal garter, aqua footwear, high heels
-
-
Casual :
-
casual, ear ornament, red dress, plaid dress, white jacket, open clothes, puffy short sleeves, cropped jacket, black bow, belt, black socks, red footwear
-
-
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, frilled skirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers
-
-
Tracen winter uniform :
-
tracen school uniform, winter uniform, puffy long sleeves, sailor collar, sailor shirt, purple shirt, white bowtie, horseshoe ornament, purple skirt, frills, brown footwear, loafers
-
-
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
-
206 images consist of
-
4x low quality 105 images
-
8x medium quality 66 images
-
16x high quality 35 images
-
=> 1 epoch = 1508 images
-
-
replaced character feature tags with kawakami princess \(umamusume\)
-
1girl, very long hair, braid, horse ears, aqua eyes, simple background, brown hair, asymmetrical bangs, hair intakes, bangs, green eyes, orange hair, official alternate costume, french braid, pink hair, parted bangs, long hair, half updo, red hair, ahoge, grey eyes, crown braid, sidelocks, blue eyes, horse tail, animal ears, horse girl, solo, forehead, ponytail, twintails, alternate costume, alternate hairstyle
-
I think these tags are the essentials of Kawakami Princess or
-
unnecessary for training because of duplication.
-
-
resolution : 768x768 with aspect ratio bucketing.
-
other training settings is included in training data or metadata of LoRA file.
All uploaded images are generated by AOM3A1
And, special thanks to my best friend. DH.
描述:
LoHa of Kawakami Princess (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:your_loha_name:weight>
训练词语: kawakami princess \(umamusume\)
名称: img.zip
大小 (KB): 602049
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: kawakami_princess_loha.safetensors
大小 (KB): 19260
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success