<h3 id="heading-857">2023/12/24 update</h3><p><span style="color:rgb(34, 34, 34)">New version is retrained using the latest technology to make generated images more similar to the dataset. Merry Christmas ! XD</span></p><h3 id="heading-857">2023/6/26 update</h3><p>Update dataset. Retrain the model using new craft. (<strong>The latest version is LoRA model</strong>).</p><h3 id="heading-858">2023/4/15 update</h3><p>Update dataset and upload lycoris version. <strong>Adjust trigger tag to </strong><code>soyincapazz</code>, username of this artist. <strong>The preview images of the new model are generated using 'Hires Fix' and upscaled with 'SD Upscale'.</strong></p><h3 id="heading-859">2023/4/1 upate</h3><p>Fix the compatibility problem of non-NAI-based checkpoints. Now arbitrary anime model with NAI's VAE or kl-f8-anime2 VAE can also generate good results using this LoRA, theoretically.</p><h3 id="heading-860">2023/3/1 update</h3><p>Reduce loss to 0.09. 0.6 and 0.7 weight should be enough.</p><h1 id="heading-861">Introduction</h1><p>A LORA model of <a target="_blank" rel="ugc" href="https://www.pixiv.net/users/5745007"><strong>Tsuki no i-min</strong></a> style. The 784MB VAEs are recommended. 0.6~0.8 weights are good.</p><h1 id="heading-862">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>

【Art Style】Soyincapazz Style

<p>Reduce loss to 0.09. 0.6 and 0.7 weight should be enough.</p>

tsukinoimin-lora-v1.5-32dim-18ep.safetensors

v1.5

Files with SHA256: 2865eef68bcab0f019de5e998bc4bcee3b43997f48e1b1395addfd8d55cfa2b4