<h3 id="heading-100">Features</h3>It was trained with photos of actual persons, especially close-up shots.Various colors available. Basics are pink, purple, and blue.<h3 id="heading-101">How to Use</h3>Recommended LoRA weight is up to 0.2.Shapes can be controlled with prompts. For example:<ul><li>short sleeves</li><li>long sleeves</li><li>frill</li><li>standing split (useful pose!)</li></ul><h3 id="heading-103">LoRA Block Weight Plugin</h3>To reduce unintended effects, I recommend to use LoRA Block Weight plugin.Recommended parameters as follows, or can be seen on this gallery:<pre><code>&lt;lora:simpleLeotard10:0.20:0,0,0,0,0,0,0,0,0,1,1,0,1,0,0,0,0&gt;</code></pre>But, depend on your model, you may also need to adjust.<h3 id="heading-104">Term of Use</h3><ul><li>Not for corporate activities</li><li>Prohibit redistribution</li></ul><h3 id="heading-105">Donate me if you feel, like that your life will be good</h3>I wouldn't like to activate monetization now.<ul><li>Coffee to me: <a target="_blank" rel="ugc" href="https://ko-fi.com/kanaejun">https://ko-fi.com/kanaejun</a></li><li>BitCoin: 3H33ahQnpL84S4kSKWxCPzKMoEjtdgMBRy</li><li>LiteCoin: MWYA5K8jNo9AoCadvPpoMHs9bCEB23QYuk</li></ul><h3 id="heading-106">Author</h3>kanaejun, Japan

Files with SHA256: e99d5b22d8af32014bac67513d20f885ab3e42ca45b6c01aad76cf6039a09793