LoHa of Cheval Grand (umamusume). Please install extension on WebUI.

After installing extension, put LoHa file in your sd/models/lora folder and use LoRA notation in prompt to applying LoHa. <lora: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 around 0.7

• Trigger words

  • Base

    • cheval grand \(umamusume\)

  • Racing competition costume :

    • long sleeves, cape, sailor collar, white shirt, yellow ascot, white jacket, white gloves, belt, black shorts, black socks, shoes, white footwear

  • 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

  • Casual :

    • She has no official casual clothes

  • Other clothes :

    • Baseball sports wear :

      • alternate costume, white headwear, short over long sleeves, white shirt, sportswear, baseball uniform, belt, white pants, socks, shoes, black footwear

    • Casual ?

      • causal, denim jacket, white shirt, black pants

      • grey hoodie, hands in pocket, clothes writing, black pants

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

• 37 images of

  • 4x low quality 10 images

  • 8x medium quality 13 images

  • 16x high quality 14 images

  • => 1 epoch = 368 images

• replaced character feature tags with cheval grand \(umamusume\)

  • 1girl, hair between eyes, short hair, hat, tail, brown hair, green eyes, simple background, solo, horse ears, streaked hair, animal ears, bangs, horse girl, white headwear, black hair, medium hair, white hair, horse tail, blue eyes, multicolored hair, two-tone hair, ears through headwear

  • I think these tags are

    • the essentials of Cheval Grand

    • or unnecessary for training because of duplication.

• 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.