<p><strong>If you like my contributions to the community, please consider </strong><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/Rjox"><strong>Buying Me A Coffee</strong></a><strong> or check out my other sites on </strong><a target="_blank" rel="ugc" href="https://allmylinks.com/rjo-x"><strong>AllMyLinks</strong></a></p><h3 id="training-info"><strong>TRAINING INFO</strong></h3><ul><li><p>Trained on 17 photos (face only)</p></li><li><p>Trained at 768 resolution, so 768x768 inpainting works great.</p></li></ul><h3 id="recommended-settings"><strong>RECOMMENDED SETTINGS</strong></h3><p>The training images used were cropped in from shitty early 2000's dslr's, so image quality wasn't great. I recommend using 'restore faces' but in your auto1111 settings, lower the restore faces strength to something like 0.7-0.8 which makes the effect less than the default setting of 0.5.</p><p>For txt2img, a weight of 0.7-0.9 will give a little more flexibility, but 1.0 isn't bad. A weight of 1.0 works really well for inpainting.</p><h3 id="recommended-settings"><strong><u>GETTING THE BEST LIKENESS WITH LORA'S</u></strong></h3><p>The checkpoint you use can heavily influence the likeness of a celebrity Lora. I train my Lora's on SD15, so you'll get the best likeness on any model that used SD15 as the base model. <a target="_blank" rel="ugc" href="https://civarchive.com/articles/81/how-checkpoints-can-influence-a-celebrity-lora">See this example</a> for how a checkpoint can influence the look of a Lora.</p>

Files with SHA256: e4bf9fd28a1d01fdc5c092c0ed4046e6ff0c44257f950b886e61b4b09cce45d2