<h2 id="heading-921">Miranda Cohen by 𝓝𝓞𝓑𝓞𝓓𝓨</h2><h3 id="heading-923">This LoRA was trained with 100 images of the Fitness Influencer Miranda Cohen, each sized 768x768.</h3>The preview images were generated using the model epiCRealism - pure Evolution V5<h3 id="heading-924">Settings used in the preview images:</h3><ul><li>LoRA Weight: (Operates from 0.6 to 1.0) - Recommended: (0.8 to 1)</li></ul><ul><li>Default Resolution: 768x768</li><li>Recommended Resolution: Depending on what you want (NOTE BELOW)</li></ul><ul><li>Sampler: DPM++ 3M SDE Exponential</li></ul><ul><li>Steps: 20</li></ul><ul><li>Cfg Scale: 2 (Depending on your model)</li><li>Keyword (Not required but helpful): cohenfit</li></ul>Note:This model works well at most resolutions, so you won't have many problems. However, in case you get distorted or warped faces, simply try in other resolution. In the preview images, you'll notice that lower resolutions are used for close-up faces, while higher resolutions are used for full-body shots. So, always try to play around the resolution and give a try to this LoRA.<h3 id="heading-10">Find my other LoRAs <a target="_blank" rel="ugc" href="https://civarchive.com/user/ITISJUSTNOBODY/models?sort=Newest">HERE</a>! :)</h3>

Files with SHA256: 3ab263e1fa43b1edff5d642ef8651ea435cf30a344110444b16a032844b34538