LoHa of Gold Ship (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 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 around 0.7

• Trigger words

  • Base

    • gold ship \(umamusume\)

  • Racing competition costume :

    • pillbox hat, brown headwear, red bowtie, bare shoulders, red dress, sleeveless dress, armband, white gloves, buttons, pouch, white pantyhose, thigh strap, white footwear, knee boots, high heel boots

  • Casual :

    • casual, pillbox hat, brown headwear, red jacket, open jacket, open clothes, ribbed shirt, white shirt, long sleeves, jeans, blue pants

  • Summer :

    • official alternate costume, sunglasses, necklace, jewelry, black one-piece swimsuit, casual one-piece swimsuit, cleavage, bare shoulders, arm tattoo, bracelet, thigh strap, black footwear, sandals

    • (optional) water gun

  • Tracen summer uniform :

    • tracen school uniform, summer uniform, pillbox hat, brown headwear, serafuku, puffy short sleeves, bowtie, horseshoe ornament, sailor collar, sailor shirt, purple shirt, white skirt, frills, 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

• 255 images consist of

  • 4x low quality 80 images

  • 8x medium quality 100 images

  • 16x high quality 75 images

  • => 1 epoch = 2320 images

• replaced character feature tags with gold ship \(umamusume\)

• 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.