A lora for generating a breast grab paizuri sceneV2.0 IS A LORA NOT A LYCORISV 2.0 Changes-Much more consistent-doesn't mess up with gigantic breasts as much as v1.0-works with other loras much better-less over trained-more flexibleTrained on <s>102 </s> 138 images<h2 id="heading-556"></h2><h2 id="heading-557">Image info</h2><ul><li>Model used <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/Models/AbyssOrangeMix2/AbyssOrangeMix2_hard.safetensors">abyssorange2hard</a></li><li>model used <a rel="ugc" href="https://huggingface.co/AnonymousM/Based-mixes/blob/main/Based64mix-V3.safetensors">based 64</a></li><li>Model used <a target="_blank" rel="ugc" href="https://civarchive.com/models/5245/kotosmix">kotosmix</a></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-558">Notes</h2><ul><li>Smaller breasts are VERY inconsistent<s> (cant grab what you cant see)</s></li></ul><h2 id="heading-559">Training settings?</h2><h3 id="heading-560">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 paramters

Files with SHA256: 1ed7cae98ca03ea95ffaff7ebb111fdacf8ab849f462448f1233bb3018505451