LORA trained on 970 images of artist <a target="_blank" rel="ugc" href="https://twitter.com/RailgunKy">ぺんたごん </a>(Pentagon).Doesn't require trigger words, recommended weight is 1.Training and dataset parameters:<ul><li>Images are scrapped from gelbooru (upside down portraits excluded), tagged by WD tagger;</li><li>Trained using kohya-ss LORA training GUI, rank 32, resolution 512x768, no regularisation folder, other settings were default;</li><li>Trained on anything-v4.5-pruned-fp16 model;</li><li>6 epochs, 6 steps per image for 40 close-up portraits cropped out of some of images in dataset, 1 step per image for the rest 970 images.</li></ul>

Files with SHA256: 0e20b50d7dbf82ae6c5536c4ed5ba856994b49283bdabefff978af3ecadf4465