LoRA of Admire Vega (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

    • admire vega \(umamusume\)

  • Racing competition clothes :

    • white necktie, skirt, long sleeves, white footwear, thigh strap, black pantyhose, boots, shirt, puffy sleeves, pleated skirt, buttons, corset, capelet, fingerless gloves, black gloves, mismatched footwear

    • (optional) skirt -> white skirt,

  • Tracen school uniform :

    • tracen school uniform, purple shirt, white skirt, puffy short sleeves, sailor collar, bowtie, pleated skirt, sailor shirt, miniskirt, zettai ryouiki, white thighhighs

  • Casual clothes:

    • pants, long sleeves, blue sweater, turtleneck sweater, ribbed sweater, jeans, jewelry, casual, necklace

    • (optional) object hug, pillow, bed sheet

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

• trained on sd-scripts by kohya_ss. Thank you a lot!

• based on Animefull-pruned

• 154 images of fine motion

  • 4x low quality 46 images

  • 8x medium quality 53 images

  • 16x high quality 55 images

  • => 1 epoch = 1488 images

• replaced character feature tags with admire vega \(umamusume\)

  • horse girl, horse tail, brown hair, purple 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