[SD 1.5][LORA]Arcane Style LoRA offset
<h2>Arcane Style LoRA</h2><p><strong>Making models is expensive. Do you like what I do? Feel free to </strong><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/lykon"><strong>buy me a coffee</strong></a><strong> ☕</strong></p><p>Greatest show of 2021, time to bring this style to 2023 Stable Diffusion with LoRA.</p><p>This should be used with <strong>Anything4.5</strong> (that's neutral enough) at <strong>around 1 weight for the offset version, 0.65 weight for the original one</strong> (with highres fix R-ESRGAN 0.4 denoise for better results). Trigger is <code>arcane style</code> but I noticed this often works even without it.</p><p>Allow me to remind <strong>this is not a character LoRA </strong>(I didn't tag characters in the dataset). Still ,as you can see, it can get pretty close to the original characters with accurate prompting. This should also work with most of my character LoRA's (used Ahri and Lucy to test).</p><p>Please enjoy.</p><p><br /><strong>How to use LoRA's in auto1111:</strong></p><ul><li><p>Update webui (use <code>git pull</code> <a target="_blank" rel="ugc" href="https://www.youtube.com/embed/mn8fMF10XN4?start=31&end=60">like here</a> or redownload it)</p></li><li><p>Copy the file to <code>stable-diffusion-webui/models/lora</code></p></li><li><p>Select your LoRA like in <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=-bMeyXOZwN0">this video</a></p></li><li><p><strong>Make sure to change the weight if needed</strong> (by default it's <code>:1</code>)</p></li></ul><p><br /></p>
页:
[1]