lora-training / fubuki /README.md
khanon's picture
adds new Fubuki LoRA
cf1b983
|
raw
history blame
2.35 kB

Nemugaki Fubuki (Blue Archive)

合歓垣フブキ (ブルーアーカイブ) / 네무가키 후부키 (블루 아카이브) / 合歓垣吹雪 (碧蓝档案)

Download here.

Table of Contents

Preview

Fubuki portrait Fubuki preview 1 Fubuki preview 2 Uses this first-pass ControlNet input (scribble preproessor).

Fubuki preview 3

Usage

Use any or all of the following tags to summon Fubuki: fubuki, 1girl, twintails, streaked hair, antenna hair, heart hair ornament, red eyes

For her normal outfit: police uniform, white jacket, blue vest, blue necktie, collared shirt, pencil skirt, black pantyhose, red sneakers

For her accessories: doughnut, holding food, police badge, traffic baton, police hat

For her smug expression: smug, jitome, smile + closed mouth / open mouth

  • jitome refers to the flat-topped eye shape and can be used without smug if you prefer.
  • Using smug without specifying closed mouth or open mouth tends to look strange, as though the AI tries to do both.

Here is a list of all tags including in the training dataset, sorted by frequency.

Training

Exact parameters are provided in the accompanying JSON files.

  • Trained on a set of 137 images.
    • 72 without "holding food" (10 repeats)
    • 65 "holding food" (8 repeats)
      • Fubuki is so commonly seen holding a doughnut that these needed to be reduced to avoid overfitting.
    • 3 batch size, 4 epochs
    • (72 * 10 + 65 * 8) / 3 * 4 = 1654 steps
  • 0.083 loss
  • 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)
    • Resized to 32 after training
  • Training resolution 832x832.
    • For some reason, 832 performed better than 768 on Fubuki's LoRA, unlike the Junko's. The difference was not substantial, however.
  • Trained without VAE.

Revisions

  • v1b (2023-02-18)
    • Initial release.