[Other][LORA]Pentagon (Railgun) Style v1
<p>LORA trained on 970 images of artist <a target="_blank" rel="ugc" href="https://twitter.com/RailgunKy">ぺんたごん </a>(Pentagon).</p><p>Doesn't require trigger words, recommended weight is 1.</p><p>Training and dataset parameters:</p><ul><li><p>Images are scrapped from gelbooru (upside down portraits excluded), tagged by WD tagger;</p></li><li><p>Trained using kohya-ss LORA training GUI, rank 32, resolution 512x768, no regularisation folder, other settings were default;</p></li><li><p>Trained on anything-v4.5-pruned-fp16 model;</p></li><li><p>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.</p></li></ul>
页:
[1]