LoHa of Narita Top Road (umamusume). Please install extension on WebUI.

After installing extension, put LoHa file in your sd/models/lora folder and write LoRA notation in prompt to applying LoHa. <lora:loha_name:weight>

All uploaded images are generated by AOM3A1

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

Recommended options

• LoRA weight 0.7 ~ 0.8

• Trigger words

  • Base

    • narita top road \(umamusume\)

  • Racing competition costume :

    • ear cover, star hair ornament, brooch, sleeveless dress, purple dress, white bow, mismatched gloves, white gloves, black gloves, shoulder cutout, puffy long sleeves, detached sleeves, see-through sleeves, frills, shorts under dress, short shorts, purple shorts, thigh strap, knee boots, purple footwear

  • Tracen summer uniform :

    • tracen school uniform, summer uniform, serafuku, puffy short sleeves, purple bowtie, horseshoe ornament, sailor collar, sailor shirt, purple shirt, white skirt, pleated skirt, frilled skirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers

  • Tracen winter uniform :

    • tracen school uniform, winter uniform, puffy long sleeves, sailor collar, sailor shirt, purple shirt, white bowtie, horseshoe ornament, purple skirt, frills, brown footwear, loafers

Use a model derived from or mixed with animefull model.

• Settings

  • Stable Diffusion WebUI by Automatic1111

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

  • about 20 steps, CFG scale 3.5~6.5

  • I recommend kl-f8-anime2.vae

  • CLIP skip = 1

  • Use Hires.fix to get higher quality image

    • Upscaler

      • Latent, Latent (nearest-exact), Latent (bicubic antialiased) or other Latent series.

    • Denoising strength 0.50~0.65

LoRA training info

• trained on sd-scripts by kohya_ss.

  • LyCORIS by KohakuBlueleaf

  • Thank you all a lot!

• based on Animefull-pruned model

• 86 images consist of

  • 4x low quality 34 images

  • 8x medium quality 21 images

  • 16x high quality 31 images

  • => 1 epoch = 800 images

• replaced character feature tags with narita top road \(umamusume\)

  • 1girl, multicolored eyes, bangs, horse tail, simple background, brown eyes, horse girl, yellow eyes, tail, symbol in eye, orange eyes, parted bangs, purple eyes, blonde hair, pink hair, medium hair, solo, long hair, multicolored hair, streaked hair, short hair, animal ears, white hair, horse ears, pink eyes, light brown hair, red eyes, brown hair

  • I think these tags are the essentials of Narita Top Road or

  • unnecessary for training because of duplication.

• resolution : 768x768 with aspect ratio bucketing.

• other training settings is included in training_data.zip or metadata of LoRA file.

And, special thanks to my best friend. DH.