<h3 id="heading-807">2023/10/21 update</h3><p>Update dataset. Retrain the model using new craft. Using <a rel="ugc" href="https://civarchive.com/articles/2479/2023-10-7-survey-of-v14-training-automation-and-planning-of-version-v15"><strong><span style="color:#228be6">CCIP metric</span></strong></a> to measure model performance. The accuracy of this version under CCIP metric is about 97%. </p><h3 id="heading-808">2023/4/9 update</h3><p>Update dataset. Upload lycoris version. <strong>v1.0 version is conventional LoRA model. The preview images are generated using 1.6 version (original) </strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/9139/yesmix"><strong>YesMix.</strong></a></p><h1 id="heading-809">Introduction</h1><p><strong>A conventional LORA model</strong> of musashi (azur lane) trained using 160 highres images, including nsfw. The NAI's VAE is recommended. 0.6~0.8 weights are good.</p><h1 id="heading-810">Cautions (Must Read)</h1><ul><li><p>Some preview images are generated using hires fix. Thus, <strong>if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.</strong></p><p></p></li><li><p><strong>The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). </strong>Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.</p><p></p></li><li><p>For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, <strong>make sure add '--no-half-vae' in command line of webui to prevent generating black images.</strong> See <a target="_blank" rel="ugc" href="https://rentry.org/voldy"><strong>voldy's log</strong></a> for the details of edit method. <strong>For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.</strong></p></li></ul>

Files with SHA256: 143ed0ea5064baf2617a9ee8690e10220ed036a6e4b573ff1372a37a25e549a3