LORA trained on 83 images of artist はなこ (Hanako) - https://www.pixiv.net/en/users/15141389 on relatively low amount of steps.

Doesn't require trigger words, recommended weight is 1.

Training and dataset parameters:

• Images are scrapped from Pixiv (sketches excluded), tagged by WD tagger;

• Trained using kohya-ss LORA training GUI, rank 32, resolution 512x768, no regularisation folder, other settings were default;

• Trained on anything-v4.5-pruned-fp16 model;

• 34 epochs, 1 step per image.