<h2 id="heading-829"><span style="color:rgb(250, 176, 5)">Warning⚠️: Prompting on this lora might be extremely hard or getting bad result easily</span></h2><h2 id="heading-279"><strong><span style="color:rgb(64, 192, 87)">New Sampling Method: DPM++ 3M SDE with 40 steps</span></strong></h2><h3 id="heading-280"><strong><span style="color:rgb(250, 176, 5)">U can use default sampling if u want: Euler a with 28 steps</span></strong></h3><h1 id="heading-830"><strong>HOW TO USE:</strong></h1><h3 id="heading-160"><strong>Method 1:</strong></h3><ol><li><p>Use <a target="_blank" rel="ugc" href="https://civarchive.com/models/124189/aidxlv01-anime-illust-diffusion-xl-xl">AIDXL</a> Model</p></li><li><p>Please add <strong><span style="color:rgb(250, 82, 82)">(aesthetic:1.5)</span></strong> into the prompt</p></li><li><p>Recommend negative: <strong><span style="color:rgb(250, 82, 82)">unfinised, sketch, lineart, aidxlv05_neg, (worst quality, low quality:1.2), lowres, messy, (jpeg artifacts:1.2)</span></strong></p></li><li><p>Recommend weights is around 0.6-1</p></li><li><p>Try put "<span style="color:rgb(34, 139, 230)">hatsune miku</span>" or "<span style="color:rgb(34, 139, 230)">twintails</span>" on negative if it necessary</p></li></ol><p><strong>Output:</strong></p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e1124fce-f327-4fd4-a792-2a5cb4aed236/width=525/e1124fce-f327-4fd4-a792-2a5cb4aed236.jpeg" /></p><p></p><h3 id="heading-12"><strong>Method 2:</strong></h3><ol><li><p>Load this <a target="_blank" rel="ugc" href="https://civarchive.com/models/152040?modelVersionId=264491">VAE</a></p></li><li><p>Use quality tags</p></li><li><p>No negative needed</p></li><li><p>Recommend weights is around 0.6-1</p></li><li><p>Try put "<span style="color:rgb(34, 139, 230)">hatsune miku</span>" or "<span style="color:rgb(34, 139, 230)">twintails</span>" on negative if it necessary</p></li></ol><p><strong>Output:</strong></p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/508836a8-dbc1-4833-8c51-23917c3e2fb3/width=525/508836a8-dbc1-4833-8c51-23917c3e2fb3.jpeg" /></p><p></p><h2 id="heading-831">Lora trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3">Animagine XL V3.1</a></h2>

Files with SHA256: 5f45aa757af96b3cb81e3af16bb54e84961673445078bc23ecd6da23c72e7a2d