LoRA of Silence Suzuka (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. 👍

With LoRA, you can generate big boob suzuka! :D

Recommend options

• LoRA weight 0.7~1.0

• Trigger words

  • base

    • silence suzuka \(umamusume\)

  • Racing competition clothes :

    • black gloves, white skirt, pleated skirt, black pantyhose, layered sleeves, puffy short sleeves, short over long sleeves, black bow, mismatched footwear, asymmetrical footwear

    • (optional) smile. she is serious when running

  • Casual clothes :

    • hair flower, black pantyhose, pleated skirt, blue skirt, white shirt, short sleeves

  • Alternate costume:

    • Suzuka has NO official alternate clothes. :(

• Use animefull based model

• Settings

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

  • about 20 steps, CFG scale 3.5~6.5

  • kl-f8-anime2.vae

  • CLIP skip = 1

  • If using highres

    • Latent series

    • Denoising strength 0.50~0.65

LoRA training info

• based on Animefull-pruned

• 226 images of silence suzuka

  • 4x low quality 80 images

  • 8x medium quality 71 images

  • 16x high quality 75 images

  • => 1 epoch = 2088 images

• replaced character feature tags with silence suzuka \(umamusume\)

  • horse girl, horse tail, orange 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 generated by AOM3A1