<p>A lora based on the character <a target="_blank" rel="ugc" href="https://lastorigin.fandom.com/wiki/Cerberus">Cerberus </a>from <a target="_blank" rel="ugc" href="https://lastorigin.fandom.com/wiki/Last_Origin_Wiki"><strong>Last Origin</strong></a></p><p></p><p>Trained with 167 images</p><h2 id="heading-1401"></h2><h2 id="heading-1402">Image info</h2><ul><li><p>Model used anything4.5</p></li><li><p><a target="_blank" rel="ugc" href="https://huggingface.co/yesyeahvh/bad-hands-5/blob/main/bad-hands-5.pt">bad hands embedding</a></p></li></ul><p></p><h2 id="heading-1402">Notes</h2><ul><li><p>Use the provided trigger words to get her outfits</p></li><li><p>No trigger word is needed if you dont want any of her outfits</p></li><li><p>the wedding dress outfit is slightly overbaked due to the low amount of images so lower the lora weight to 0.8 for it. (the rest of the outfits can be left at 1)</p></li></ul><h2 id="heading-1403"></h2><h2 id="heading-1404">Training settings?</h2><h3 id="heading-1405">The most important part of training is getting a good dataset!</h3><p>Training settings can be found by installing the additional networks extension in auto1111</p><p>Extensions -&gt; available -&gt; load from -&gt; additional networks</p><p>Restart webui</p><p>place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora</p><p>To view the training settings</p><p>Go to additional network tab -&gt; choose model -&gt; training paramters</p>

Files with SHA256: e4ab62a15a6595313a30a0eca79a33a8e5377e9e48db26256d2264ad94db1915