<h1><strong>Nasu Artstyle LoRA</strong></h1><h1>Use Cases</h1><p>The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.</p><p>The LoRA itself was trained with the token: <code>skistyle</code>.</p><p><strong>I personally prefer AbyssOrangeMix2_hard for this LoRA!</strong></p><p>The models mentioned right now</p><ol><li><p>AbyssOrangeMix2_hard or AbyssOrangeMix2_sfw from <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs"><strong><u>WarriorMama777</u></strong></a></p></li><li><p>Kenshi Model from <a target="_blank" rel="ugc" href="https://huggingface.co/SweetLuna/Kenshi"><strong><u>Luna</u></strong></a></p></li></ol><h2>Strength</h2><p>I would personally use these strength with the assosiated model:</p><ul><li><p>0.85-1 for AbyssOrangeMix2</p></li><li><p>0.70-0.85 for Kenshi</p></li></ul><h2>Disclaimer</h2><p>I still use the LoRA extension personally, since I prefer it. So if you try to recreate the preview images, please use the following extension: <a rel="ugc" href="https://github.com/kohya-ss/sd-webui-additional-networks">extension</a></p>

Files with SHA256: 5a9da75a852a3ac50df01ad58409d6294ec50229684e72eb1c6a686dfb5a9bc1