Sign In

Matikanetannhauser (umamusume)

378
4.1k
15
Verified:
SafeTensor
Type
LyCORIS
Stats
4,131
Reviews
Uploaded
Mar 26, 2023
Base Model
SD 1.5
Training
Steps: 4,510
Epochs: 10
Trigger Words
matikanetannhauser \(umamusume\)
Training Images
Download
Hash
AutoV2
D0386C2CDE
0
0
0
0

LoHa of Matikanetannhauser (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>

えい、えい、むん!

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

      • matikanetannhauser \(umamusume\)

      • Cabbie hat is not included!

    • Hat

      • cabbie hat

    • Racing competition costume :

      • cabbie hat, blue headwear, blue bowtie, cape, white shirt, collared shirt, shoulder cutout, puffy long sleeves, center frills, corset, belt pouch, belt, blue skirt, frilled skirt, brown footwear, lace-up boots, knee boots, high heel boots

    • Casual :

      • casual, beret, red headwear, neck ribbon, long sleeves, collared shirt, pink shirt, open clothes, blue cardigan, shirt tucked in, plaid skirt, brown skirt

    • 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.

  • based on Animefull-pruned model

  • 192 images consist of

    • 4x low quality 63 images

    • 8x medium quality 64 images

    • 16x high quality 65 images

    • => 1 epoch = 1804 images

  • replaced character feature tags with matikanetannhauser (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.