Vodka (umamusume)

LoRA of Vodka (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. 👍

Recommend options

• LoRA weight 0.7~1.0

• Trigger words

  • base

    • vodka \(umamusume\)

  • Racing competition clothes :

    • crop top, yellow shirt, necklace, long sleeves, black jacket, open clothes, open jacket, navel, black shorts, belt, short shorts, jewelry, groin, thighhighs, thigh boots, black footwear

    • (optional) ground vehicle, motor vehicle, motorcycle

  • Christmas costume :

    • official alternate costume, christmas ornaments, red shirt, long sleeves, necktie, white gloves, sack, red footwear, shoes, white pants, black jacket, fur trim, belt, boots, vest

  • Casual clothes :

    • yellow shirt, black footwear, black jacket, boots, long sleeves, standing, black pants, leather jacket, belt

  • 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

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

• 171 images of vodka

  • 4x low quality 57 images

  • 8x medium quality 47 images

  • 16x high quality 67 images

  • => 1 epoch = 1676 images

• replaced character feature tags with vodka \(umamusume\)

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

• resolution : 768x768

• rank=alpha=16

• batch size = 4, 8 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