Bamboo Memory (umamusume)

LoHa of Bamboo Memory (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. 👍

'Bamboo' is strong tag. Because of it, bamboo forest occasionally come out. If you don't want it, write specific background tags. (e.g. indoor, ..)

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • bamboo memory \(umamusume\)

    • forehead band is not included!

  • Forehead band

    • hachimaki

  • Racing competition costume :

    • hairband, neck ribbon, white shirt, collared shirt, open coat, black coat, white gloves, armband, long sleeves, green skirt, black shorts, bike shorts, black socks, knee boots, high heel boots, white footwear

  • Original Art:

    • hachimaki, black necktie, white shirt, collared shirt, gray shirt, black jacket, white jacket, open jacket, armband, white gloves, long sleeves, pleated skirt, brown skirt, bike shorts under skirt, black shorts, miniskirt, white socks, boots, black footwear

  • Casual

    • Due to lack of dataset. LoRA can not reproduce casual clothes of Bamboo Memory.

  • 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

• 38 images consist of

  • 4x low quality 11 images

  • 8x medium quality 15 images

  • 16x high quality 12 images

  • => 1 epoch = 356 images

• replaced character feature tags with bamboo memory \(umamusume\)

  • I forgot what I removed. 😅

• 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.