LORA trained on 588 images of artist <a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/177784">森倉円 </a>(Morikura En).Doesn't require trigger words, recommended weight is 1.Training and dataset parameters:<ul><li>Images are scrapped from gelbooru, tagged by WD tagger;</li><li>Trained using kohya-ss LORA training GUI, rank 32, resolution 768x768,other settings were default;</li><li>Trained on anything-v4.5-pruned-fp16 model;</li><li>15 epochs, 1 repeat per image.</li></ul>

Files with SHA256: a70d00d5198d79d2a4e0f101209bab32fa7aba33378b26c073bb7b61e82d72c6