<p>This is a loRA trained on the style of Cogecha's art</p><p></p><h3>Features</h3><ul><li><p>Is easily composable with character loras</p></li><li><p>Can generate both landscape and characters, <strong>though landscape will require the keyword "scenery"</strong>, and will occasionally have people pop up randomly.</p></li></ul><p></p><h3>Compatibility</h3><p>Trained on the NAI model, and is therefore compatible with any anime-styled model such as Anything, Counterfeit, AOM, and PastelMix, etc.</p><p></p><h3>Recommended Weight</h3><p>I recommend you use the lora at weight = 1.0. <strong>If the image fries when composed with another lora at weight = 1.0, it is most likely the fault of the other lora.</strong></p><p></p><h3>How do I prevent frying the image</h3><p>If your other loRA causes your image to fry, you can prevent this by downloading <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">https://github.com/mcmonkeyprojects/sd-dynamic-thresholding</a> and:</p><ul><li><p>enable dynamic thresholding</p></li><li><p>set your mimic CFG scale to some low number like 5 or 6</p></li><li><p>open up dynamic thresholding advanced options</p></li><li><p>select cosine down as the CFG scale scheduler</p></li></ul>

Files with SHA256: 163e99c1bc2706fe6464b3aaa0ea67640c576e39e438a35c068c9d87cbd05ea1