LoRA of Sakura Bakushin O (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. 👍

BAKUSHIN~ BAKUSHIN~ BAKUSHIN~

Notice : Her floral eyes are dimly(?) visible.

Recommend options

• LoRA weight 0.7~0.9

• Trigger words

  • base

    • sakura bakushin o \(umamusume\)

  • Racing competition clothes :

    • epaulettes, sleeveless shirt, pink shirt, sailor collar, capelet, yellow neckerchief, asymmetrical gloves, mismatched gloves, black gloves, white gloves, black shorts, white thighhighs, asymmetrical footwear, mismatched footwear, high heel boots

    • (optional) smile, smiling eyes,

    • If you want to shrink prompts, remove below

      • asymmetrical footwear, high heel boots, asymmetrical gloves, black gloves, white gloves

  • Tracen school uniform :

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

  • Casual clothes :

    • white shorts, short shorts, open clothes, blue jacket, open jacket, black shirt, long sleeves, shirt tucked in, floral print, casual

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 highres. fix to get higher quality image

    • Upscaler : 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

• 116 images of sakura bakushin o

  • 4x low quality 46 images

  • 8x medium quality 31 images

  • 16x high quality 39 images

  • => 1 epoch = 1056 images

• replaced character feature tags with sakura bakushin o \(umamusume\)

  • horse girl, horse tail, brown hair, pink eyes, etc.

• resolution : 768x768

• rank=alpha=16

• batch size = 4, 7 epochs trained

• other training settings included in training_data.zip

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

All uploaded images are generated by AOM3A1