lora-training / seia /README.md
khanon's picture
adds Seia LoRA
a0d2fa7
|
raw
history blame
1.96 kB

Yurizono Seia (Blue Archive)

百合園セイア (ブルーアーカイブ) / 유리조노 세이아 (블루 아카이브) / 百合園圣娅 (蔚藍檔案)

Download here.

Table of Contents

Preview

Seia portrait Seia preview 1 Seia preview 2

Usage

Use any or all of the following tags to summon Arona: seia, 1girl, fox ears, parted bangs, halo, multicolored eyes, flower wreath, blonde hair

For her normal outfit: white dress, sleeveless dress, blue necktie, sleeves past wrists, sleeves past fingers, detached sleeves, white pantyhose, high heels

  • Her dress was also tagged with collared dress and frilled dress if those elements were visible.
  • Choose sleeves past wrists or sleeves past fingers depending on whether her fingers should be visible.
  • Negative prompt detached sleeves for alternative outfits where she should not be wearing the dress.

For her expressions: expressionless / light smile / parted lips

  • Use half-closed eyes, sleepy or tareme if her eyes are too wide.

Training

Exact parameters are provided in the accompanying JSON files.

  • Trained on a set of 96 images.
    • 13 repeats
    • 3 batch size, 4 epochs
    • (96 * 13) / 3 * 4 = 1664 steps
  • Initially tagged with WD1.4 swin-v2 model. Tags pruned/edited for consistency.
  • constant_with_warmup scheduler
  • 1.5e-5 text encoder LR
  • 1.5e-4 unet LR
  • 1e-5 optimizer LR
  • Used network_dimension 128 (same as usual) / network alpha 128 (default)
  • Training resolution 832x832.
  • Trained without VAE.
  • Dataset can be found on the mega.co.nz repository.

Revisions

  • v1 (2023-02-12)
    • Initial release.