<h2>Shingeki no Kyojin (Attack on Titan) Anime style LoRA</h2><h3>(season 1)</h3><p><strong>Making models can be expensive. Do you like what I do? Consider supporting me on </strong><a target="_blank" rel="ugc" href="https://www.patreon.com/Lykon275"><strong>Patreon</strong></a><strong> 🅿️ or feel free to </strong><a target="_blank" rel="ugc" href="https://snipfeed.co/lykon"><strong>buy me a coffee</strong></a><strong> ☕</strong></p><p>Requested by <strong>DenjiBased</strong> on Discord, who also curated the dataset. This LoRA aims at recreating AoT anime screencaps. Despite being a style LoRA trained on a relatively small dataset from the first episodes, it's also able to reproduce some characters pretty well. In the Examples I also showed how it's possible to mix it with other LoRA's to introduce other fictional characters in this world. Works well at <strong>around 0.7 weight</strong> on Anything V4.5 and AbyssOrangeMix2 (better for female characters, but tends to make male characters a bit more feminine). Trigger is <code>aot style</code>.</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&amp;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</strong> (by default it's <code>:1</code> which is usually too high)</p></li></ul>