lora-training / sora /README.md
khanon's picture
adds loss values to most LoRAs
6e1c7b7
|
raw
history blame
2.27 kB

Sora (Blue Archive)

ソラ (ブルーアーカイブ) / 소라 (블루 아카이브) / 空 (碧蓝档案)

Be forewarned that this LoRA is prone to generating NSFW results since Sora has an unusually high proportion of extremely lewd art. Use nsfw, naked apron etc in the negative prompt to prevent this.

Download here.

Table of Contents

Preview

Sora portrait Sora Sora fallen

Usage

Use any or all of the following tags to summon Sora: sora, halo, mini wings, white wings, two side up, blonde hair, forehead

For her usual outfit: blue apron, white shirt, (black pleated skirt:0.8)

  • If needed, you can also add off-shoulder, strap slip, bowtie, short sleeves
  • Sora's skirt is not visible in most training art. Consider adding black pleated skirt and negative prompt miniskirt, pencil skirt for more accuracy.

Sometimes her wings appear too high; low wings can help with this.

Weight 1 is suggested.

Training

Exact parameters are provided in the accompanying JSON files.

  • Trained on a set of 128 images
    • 9 repeats
    • 3 batch size, 4 epochs
    • (128*9) / 3 * 4 = 1536 steps
  • 0.0791 loss
  • 768x768 training resolution
  • constant_with_warmup scheduler instead of cosine
  • Initially tagged with WD1.4 Convnextv2 model. Tags minimally pruned/edited.
  • Used network_dimension 128 (same as usual) / network alpha 128 (default)
  • Trained without VAE.
  • Training dataset available here.

Revisions

  • v3 (2023-02-06)
    • Completely re-trained to correct issue where caption files were not being loaded correctly. New version should have more flexibility but requires additional outfit prompting.
  • v2b (2023-02-01)