Tosen Jordan (umamusume)

LoCon of Tosen Jordan (umamusume). Put LoRA file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoRA. <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. 👍

Notice

• Here are two version of LoCon.

• One is resized version using sv_fro method. If you interested in, visit here.

• First one used sv_fro method and param=0.99 with kohya_ss resize_lora.py

• I think it is good trade-off with file size and quality.

• The file size has been reduced from 37.2MB to 22.8MB (It saves 40%!).

• The other is original version of LoCon. No resizing.

• Settings of all preview images are same, only LoCon differs.

MAYBE NOT COMPATIBLE WITH AOM3A2, AOM3A3 model.

Recommend options

• LoCon weight around 0.5

• Trigger words

  • base

    • tosen jordan \(umamusume\)

  • Original Art clothes :

    • black choker, ring, collarbone, blue neckerchief, sailor collar, long sleeves, school uniform, green jacket, white skirt, belt, thigh strap, black footwear

  • Racing competition costume :

    • black choker, collar, crop top, fishnets, chain necklace, cropped jacket, open jacket, long sleeves, navel, midriff, nail polish, watch, bracelet, jewelry, purple belt, black skirt, gold chain, thigh strap, purple thighhighs, fishnet thighhighs, mismatched thighhihs, high heels

  • Casual clothes :

    • bra strap, white shirt, tied shirt, off shoulder, off-shoulder shirt, long sleeves, nail polish, ring, bracelet, jewelry, denim shorts, short shorts, bare legs, cutoffs

  • Tracen school uniform :

    • tracen school uniform, purple shirt, pleated skirt, puffy short sleeves, white skirt, puffy sleeves, summer uniform, frilled skirt, sailor collar, sailor shirt, miniskirt, frills, white thighhighs

Use animefull based model

• Settings

  • Stable Diffusion WebUI by Automatic1111

  • DPM++ Series(SDE Karras, 2M Karras, etc.)

  • about 20 steps, CFG scale 3.5~6.5

  • kl-f8-anime2.vae

  • 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

• 74 images of tosen jordan

  • 4x low quality 25 images

  • 8x medium quality 20 images

  • 16x high quality 29 images

  • => 1 epoch = 724 images

• replaced character feature tags with tosen jordan \(umamusume\)

  • 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.