<h3 id="heading-21">2023/12/26 update</h3><p><span style="color:rgb(34, 34, 34)">Update dataset. Retrain the model using the latest technology to make generated images more similar to the dataset.</span></p><h3 id="heading-22">2023/7/19 update</h3><p><span style="color:rgb(0, 0, 0)">Update dataset and training strategy.</span></p><h1 id="heading-272">Introduction</h1><p><span style="color:rgb(0, 0, 0)">A LoRA model of Hindenburg from Azur Lane. </span><strong>The trigger tag is </strong><code>hindenburg \(azur lane\)</code><strong>. The key features are </strong><code>red hair, demon girl, demon horns, ahoge, underboob, elbow gloves, pointy ears</code><strong>.</strong><span style="color:rgb(0, 0, 0)"> 0.6 ~ 0.8 weights are good. </span><strong><span style="color:rgb(37, 38, 43)">The preview images are generated using 1.6 version, 2.0 version </span></strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/9139/checkpointyesmix"><strong><span style="color:rgb(34, 139, 230)">Yesmix</span></strong></a><strong><span style="color:rgb(37, 38, 43)"> and </span></strong><a target="_blank" rel="ugc" href="https://civarchive.com/models/7240/meinamix"><strong><span style="color:rgb(34, 139, 230)">MeinaMix</span></strong></a><strong><span style="color:rgb(37, 38, 43)"> to verify the compatibility of this LoRA model on different base models.</span></strong></p><h2 id="heading-273"><strong><span style="color:rgb(250, 82, 82)">This model still requires more images to improve its generalization ability.</span></strong></h2><p></p><h1 id="heading-538">Cautions (Must Read)</h1><h2 id="heading-539"><strong>For anime model,</strong></h2><h2 id="heading-540"><strong>pls disable 'face restoration' during generating.</strong></h2><h2 id="heading-541"><strong>pls disable 'face restoration' during generating.</strong></h2><h2 id="heading-542"><strong>pls disable 'face restoration' during generating.</strong></h2><ul><li><p>Some preview images are generated using 'Hires Fix' and upscaled using 'SD Upscale'. 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></ul><h3 id="heading-543"><strong><u>BTW, make sure set this option in 'Stable Diffusion' settings to 'CPU' to successfully regenerate the preview images with the same seed.</u></strong></h3><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c1e77cab-093f-44e5-803b-1afcf2d42df4/width=525/c1e77cab-093f-44e5-803b-1afcf2d42df4.jpeg" /></p><p></p><ul><li><p><strong>The training resolution of this model is 1024x1024, so generating resolution must not exceed this range. </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>

【Character】Hindenburg (Azur Lane)

<p>Update dataset. Retrain the model using the latest technology to make generated images more similar to the dataset.</p>

Files with SHA256: 9ca624800a6e0cee0c1e09653bdbb6399e69eace93e7f53cb57a9b31114f3fd6