<h1 id="&quot;pnte&quot;-negative-stable-diffusion-lora-qfre35cbd"><strong>"PNTE" Negative Stable Diffusion LoRA</strong></h1><p>Increase the quality and amount of details in images with these negative LoRAs for Stable Diffusion models.</p><h2 id="how-to-use:-8cttjcgyk"><br />How to use:</h2><p><strong>THESE ARE MEANT TO BE USED WITH NEGATIVE STRENGTH VALUES.</strong><br />To do this simply add the LoRA to the negative prompt or manually adjust the LoRA strength depending on the diffusion interface you are using.</p><p>For ease of use, ComfyUI users can use the <a target="_blank" rel="ugc" href="https://github.com/DoctorDiffusion/ComfyUI-SnakeOil">SnakeOil </a>custom_node suite I created. This node not only automatically inverts negative LoRAs but it also looks for them in <code>models/nloras</code> folder rather than the normal <code>models/loras</code> folder. This helps with organization and keeping our ever growing lists of LoRAs a little shorter.</p><p></p><h3 id="sd3.5l:-buoo5d6w3"><strong>SD3.5L:</strong></h3><p>The most recent updated version my "point-e" negative embedding for use with Stable Diffusion 3.5 Large was trained with my experimental custom config for aitoolkit.</p><p><br />I set CLIP to 0 as I did not train the text encoders.<br />LoRA strength can range from -0.01 to -2.00 but there will often be deterioration past -0.75 in most cases. -0.45 is a good place to start. Works as low as -0.01.</p>

Detail Enhancer - Doctor Diffusion's "pnte" Negative Stable Diffusion SD3.5 Large LoRA

<p>Trained with my experimental aitoolkit config file. See article below for more information. </p><p>This works very well as an incremental detail slider. I normally start around -0.45 for overall better results. Things can get a little strange the closer to -1 you get and there are at times a noticeable shift between -0.78 to -0.98. Use as low as -0.01 for extremely subtle quality increases. </p><p>This version was trained with a network rank of 64</p>

Files with SHA256: 337177f3ec909032c8d1fdff1387f7cc1bff9c60b17c77e33141f8b63f004e58