LoHa of Daring Tact (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

    • daring tact \(umamusume\)

  • Racing competition costume :

    • blue ascot, black gloves, wrist cuffs, long sleeves, halterneck shirt, white shirt, open jacket, layered skirt, collared shirt, white jacket, belt, white skirt, frills, black pantyhose

    • I think race clothes need more data.

  • Casual :

    • There is no official casual clothes of Daring Tact. So, I tried some clothes.

    • long sleeves, brown coat, open coat, yellow shirt, shirt stuck in skirt, suspenders, plaid skirt, black skirt, brown shorts

    • turtleneck sweater, black sweater, ribbed sweater, long sleeves, bracelet, denim pants, belt

  • 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, frills, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers

  • Tracen winter uniform :

    • tracen school uniform, winter uniform, puffy long sleeves, sailor collar, purple shirt, white bowtie, horseshoe ornament, purple skirt, pleated skirt, 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

• 55 images consist of

  • 4x low quality 19 images

  • 8x medium quality 17 images

  • 16x high quality 19 images

  • => 1 epoch = 516 images

• replaced character feature tags with daring tact \(umamusume\)

  • 1girl, green eyes, tail, long hair, aqua eyes, hair ornament, horse tail, multicolored hair, animal ears, medium hair, horse girl, black hair, hair between eyes, streaked hair, ahoge, simple background, solo, blue eyes, horse ears, brown hair, star hair ornament

  • I think these tags are the essentials of daring tact.

  • 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.