LoRA of Oguri Cap (umamusume)

All of my works is free. If you'd like to support me, feel free to buy me a coffee. 👍

Recommend options

• LoRA weight 0.5~0.9

• Trigger words

  • base

    • oguri cap \(umamusume\)

  • Racing competition clothes :

    • navel, blue skirt, long sleeves, pleated skirt, sailor collar, red neckerchief, belt, black pantyhose, white jacket, white shirt, grey footwear, fur-trimmed boots

  • Casual clothes(maybe) :

    • white shirt, light brown cardigan, open clothes

  • Christmas costume :

    • christmas hair ornament, white gloves, white jacket, black pantyhose, white shirt, frills, white skirt, white vest, belt, grey legwear

• Use animefull based model

• Settings

  • DPM++ SDE Karras

  • 20 steps, CFG scale 4.5~6.5

  • kl-f8-anime2.vae

  • CLIP skip = 1

  • If using highres

    • Latent (bicubic antialiased)

    • Denoising strength 0.5~0.65

LoRA training info

• based on Animefull-pruned

• 160 images of oguri cap

  • 8x low quality 50 images

  • 16x medium quality 60 images

  • 32x high quality 50 images

  • => 1 epoch = 2960 images

• replaced character feature tags with oguri cap \(umamusume\)

  • horse girl, horse tail, grey hair, blue eyes, etc.

• using aspect ratio bucketing

• resolution : 768x768

• rank=alpha=16

• using dadaptation

• batch size = 4, 7 epochs trained

• clip skip = 1

This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)

All uploaded images are output of AbyssOrangeMix2-nsfw, kl-f8-anime2.vae