<h3 id="heading-679">For previous version</h3><p>3 nakajima youko from <strong>THE TWELVE KINGDOMS </strong>lora</p><p>v1 is the simple and rough one,I can hardly remember the parameter</p><p>v2 trained with 6000*2+6000*2 steps and the network rank is 64</p><p>v3 trained with 6000*2+6000*2 steps and the network rank is 128</p><p>I would recommend v3 most of the time </p><p>for v1,weight 0.6~0.7 is recommended</p><p></p><h3 id="heading-680">New version : v4n</h3><p>Set network alpha much larger, which largely effect learning rate.</p><p>Outputs result better and more stable , which could means less stylized.</p><p><span style="color:rgb(194, 189, 181)">Also perform well with simple prompts (last 4 posts for example)</span></p><h3 id="heading-684"></h3><p><strong>Without trigger words the outputs result slightly different, maybe worthwhile to try.</strong></p>

Files with SHA256: ebf9d9b3f0c87a4fedc346298ae2eab453f05365995a26c1d54930fa1a6eb9f4