<h3 id="heading-78">2023/6/17 update</h3><p><span style="color:rgb(0, 0, 0)">Fix the problem of poor image quality generated by using </span><a target="_blank" rel="ugc" href="https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt"><strong>WD VAE</strong></a><span style="color:rgb(0, 0, 0)">. </span><strong><span style="color:rgb(0, 0, 0)">The </span><span style="color:rgb(36, 41, 47)">preview images are generated using 1.6 version, 2.0 version </span></strong><a rel="ugc" href="https://civarchive.com/models/9139/checkpointyesmix"><strong><span style="color:#228be6">Yesmix</span></strong></a><strong><span style="color:rgb(36, 41, 47)"> and </span></strong><a rel="ugc" href="https://civarchive.com/models/7240?modelVersionId=80511"><strong><span style="color:#228be6">MeinaMix</span></strong></a><strong><span style="color:rgb(36, 41, 47)"> to verify the compatibility of this LoRA model on different base models.</span></strong></p><h3 id="2023529-update">2023/5/29 update</h3><p><span style="color:rgb(0, 0, 0)">Update dataset. New version is trained using new craft.</span></p><h1 id="introduction">Introduction</h1><p>The original intention of creating the <a target="_blank" rel="ugc" href="https://civarchive.com/models/8217/character-art-stylefashion-girl"><strong>Fashion Girl</strong></a> model was to generate fashionable anime girl images (2.5d girl images). The idea of creating a new model emerged in order to generate more rebellious and cooler girl images. Therefore, this LoRA model can be used to generate cooler and naughtier girl images compared to the <a target="_blank" rel="ugc" href="https://civarchive.com/models/8217/character-art-stylefashion-girl"><strong>Fashion Girl</strong></a> model. <strong>The trigger tag is 'bad-girl'.</strong> The 784mb VAEs (NovelAI, Anythingv3, <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs"><strong>Orangemix</strong></a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/4468/counterfeit-v25"><strong>Counterfeit</strong></a>) are recommended. 0.6 ~ 0.8 weights are good. <strong>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><p></p><h2 id="this-model-will-be-continuously-updated-as-the-dataset-is-updated-although-images-that-satisfy-the-conditions-are-not-much"><strong>This model will be continuously updated as the dataset is updated (although images that satisfy the conditions are not much).</strong></h2><p></p><h1 id="cautions-must-read">Cautions (Must Read)</h1><h2 id="for-anime-model"><strong>For anime model,</strong></h2><h2 id="pls-disable-face-restoration-during-generating"><strong>pls disable 'face restoration' during generating.</strong></h2><h2 id="pls-disable-face-restoration-during-generating"><strong>pls disable 'face restoration' during generating.</strong></h2><h2 id="pls-disable-face-restoration-during-generating"><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="btw-make-sure-set-this-option-in-stable-diffusion-settings-to-cpu-to-successfully-regenerate-the-preview-images-with-the-same-seed"><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 / Art Style】Bad Girl

<p>Update dataset. New version is trained using new craft.</p>

Files with SHA256: 8eeca3f3dc9f3ef88a81394d1b8aceb6fdac6fca7eb64c7ab2bdcf0d19c67a4f