A lora based on the velvet room attendant from the newly released <a rel="ugc" href="https://p5x.wanmei.com/index.html?entrance=weibo">Persona5x</a> <a rel="ugc" href="https://megamitensei.fandom.com/wiki/Merope">merope</a>Trained with 18 images <ul><li>Model used <a target="_blank" rel="ugc" href="https://civarchive.com/models/5245/kotosmix">kotomix</a></li><li>Very small dataset to have an outfit lora(just use blue dress/blue jacket to get her velvet room clothes)</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>Training settings can be found by installing the additional networks extension in auto1111<h3>Extensions -&gt; available -&gt; load from -&gt; additional networks</h3>Restart webuiplace lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\loraGo to additional network tab -&gt; choose model -&gt; training paramters

Files with SHA256: e05f80f18d63510ada69dc4bfb55a6c5e0885b6cf022aa508562baaa573988ea