<h1 id="heading-1863">Introduction</h1>Loooooooong time nooooooooo see XD ! This is a LORA model of Rio from Blue Archive.<h1 id="heading-1864">Usage</h1><ul><li>Trigger tag: <code>rio \(blue archive\)</code></li><li>Key Feature: halo, hairclip, red eyes, turtleneck, sweater, jacket, mature female, parted lips.</li></ul><h2 id="heading-1865">Generating Settings</h2><ul><li>Base Model: Arbitrary anime model</li><li>Sampler: DPM++2M Karras, DPM++3M Karras and other DPM samplers are recommended.</li><li>Eta noise delta: 31337 or 0</li><li>Upscale Method: HiresFix+<a target="_blank" rel="ugc" href="https://huggingface.co/konohashinobi4/4xAnimesharp/tree/main">4xAnimeSharp</a></li><li>Max Resolution without Upscaling: 768x768</li><li>VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt">kl-f8-anime2</a> is recommended.</li><li>LORA Weights: 0.65~0.8 are recommended.</li></ul><h1 id="heading-1866">Cautions</h1><ul><li>For Anime model, pls disable 'face restoration' during generating.</li><li>Make sure set this option in 'Stable Diffusion' settings to 'CPU' to successfully regenerate the preview images with the same seed.</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c1e77cab-093f-44e5-803b-1afcf2d42df4/width=525/c1e77cab-093f-44e5-803b-1afcf2d42df4.jpeg" /><ul><li>The training resolution of this model is 768x768, so generating resolution must not exceed this range. Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.</li></ul>

Files with SHA256: c1e5b17f2067cf7ca62d829f1ff49604f373d90bc570909003cbb0d49970c9ee