This is a lora based on my favourite artist <a target="_blank" rel="ugc" href="https://twitter.com/jujunaught">donaught</a>. He/she is well known for their very thick/curvy proportions and I wanted to try and replicate it.<h2 id="heading-501">Image info</h2><ul><li>Model used anything v4.5</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/yesyeahvh/bad-hands-5/blob/main/bad-hands-5.pt">bad hands embedding</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/NiXXerHATTER59/bad-artist/blob/main/bad-artist.pt">bad artist embedding</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/embed/bad_prompt/blob/main/bad_prompt_version2.pt">bad prompt embedding</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/4629/deep-negative-v1x">deep negative embedding</a></li></ul><h2 id="heading-502">Training settings?</h2><h3 id="heading-503">The most important part of training is getting a good dataset!</h3>Training settings can be found by installing the additional networks extension in auto1111Extensions -&gt; available -&gt; load from -&gt; additional networksRestart webuiplace lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\loraTo view the training settingsGo to additional network tab -&gt; choose model -&gt; training parameters

Files with SHA256: a1b0579749fe78a956548b20468bfe232a56ae4a17c2de824784a3c0e1d863c4