LoHa of Srius Symboli (umamusume). Put LoHa file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoHa. <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. 👍

Recommended options

• LoRA weight 0.7 ~ 0.8

• Trigger words

  • Base

    • srius symboli \(umamusume\)

  • Racing competition costume :

    • black choker, jewelry, cleavage, long sleeves, black gloves, fingerless gloves, crop top, grey shirt, green jacket, open jacket, open clothes, navel, midriff, belt, shirt, green pants, brown footwear, high heel boots

  • SSR Wisdom :

    • official alternate costume, formal, tuxedo, blue bowtie, long sleeves, white gloves, butler, black jacket, collared shirt, white shirt, black pants, pant suit, tailcoat, black footwear, high heels

  • Casual :

    • Casual clothes of Srius Symboli is not included.

  • 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

  • Tracen uniform?

    • official alternate costume, choker, long sleeves, wristband, cropped jacket, white shirt, white jacket, red vest, midriff, red shorts, short shorts, garter straps, thighhighs, white footwear

  • Other costume :

    • black bowtie, white shirt, long sleeves, detached collar, clothing cutout, cleavage cutout, shirt tucked in, black skirt, pencil skirt, collared shirt, side slit

    • nontraditional playboy bunny, bare shoulders, black bowtie, wrist cuffs, detached collar, black leotard, strapless leotard, side-tie leotard, black pantyhose, fishnet pantyhose

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

• 85 images consist of

  • 4x low quality 31 images

  • 8x medium quality 24 images

  • 16x high quality 30 images

  • => 1 epoch = 796 images

• replaced character feature tags with srius symboli (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.