LoHa of Matikanetannhauser (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>

えい、えい、むん！

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

    • matikanetannhauser \(umamusume\)

    • Cabbie hat is not included!

  • Hat

    • cabbie hat

  • Racing competition costume :

    • cabbie hat, blue headwear, blue bowtie, cape, white shirt, collared shirt, shoulder cutout, puffy long sleeves, center frills, corset, belt pouch, belt, blue skirt, frilled skirt, brown footwear, lace-up boots, knee boots, high heel boots

  • Casual :

    • casual, beret, red headwear, neck ribbon, long sleeves, collared shirt, pink shirt, open clothes, blue cardigan, shirt tucked in, plaid skirt, brown skirt

  • Tracen summer uniform :

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

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

• 192 images consist of

  • 4x low quality 63 images

  • 8x medium quality 64 images

  • 16x high quality 65 images

  • => 1 epoch = 1804 images

• replaced character feature tags with matikanetannhauser (umamusume)

• resolution : 768x768 with aspect ratio bucketing.

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

All uploaded images are generated by AOM3A1

And, special thanks to my best friend. DH.