<h3 id="heading-311">2023/6/24 update</h3><p>Update dataset. Retrain the model using new craft.</p><h3 id="heading-312">2023/3/1 update</h3><p>Reduce loss to 0.09. Adjust rank to 32 to balance file size and quality.</p><h3 id="heading-313">2023/2/17 update</h3><p>Use offset noise to improve generating ability for lighter/darker images. Reduce model file size to ~1MB. <strong>The preview images are generated using latest version of </strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/9139/yesmix"><strong>YesMix</strong></a><strong>.</strong></p><h1 id="heading-314">Introduction</h1><p>A LORA model trained with ~110 images of Signora from Genshin Impact. The 784mb VAEs (NAI, Orangemix, Anything, Counterfeit) are recommended. 0.6~0.8 weights should be enough.</p>

【Character】Signora (Genshin Impact)

<p>Use offset noise to improve generating ability for lighter/darker images. Reduce model file size to ~1MB. <strong>The preview images are generated using latest version of </strong><a target="_blank" rel="ugc" href="https://civitai.com/models/9139/yesmix"><strong>YesMix</strong></a><strong>.</strong></p>

Files with SHA256: bed10b5cf27bd2363c1e123538a9151ccdd7ba6f41e78dc4d1c61f3cd1851be1