If you like my contributions to the community, please consider <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/Rjox">Buying Me A Coffee</a> or check out my other sites on <a target="_blank" rel="ugc" href="https://allmylinks.com/rjo-x">AllMyLinks</a><h3 id="recommended-settings">RECOMMENDED SETTINGS</h3>CFG SCALE IMPORTANT - Use CFG of 3-5. Anything over 5 might suck.PROMPTS - "Smiling", "from behind" and others are trained into the LoRA. For a full list of the prompts/captioned used for training, check the Lora file's metadata in your webguiTXT2IMG - A weight of 0.7-0.9 will give the best mix of likeness and flexibility.INPAINTING - A weight of 0.75-85 will give the best low-noise likeness. If you want the absolute best likeness, switch your checkpoint to SD15 since that's the model on which it was trained.FACE RESTORATION - isn't usually necessary, but I recommend setting your face restoration strength inside auto1111 settings to something like 0.7-0.8 which makes the effect less than the default setting of 0.5.<h3 id="training-info">TRAINING INFO</h3><ul><li>v1 &amp; v2 were trained on 128 photos (face &amp; full body) v3 &amp; v4 were trained on 224 photos (face &amp; full body) and reproduces both with more detail and accuracy</li><li>v1, v2 and v3 were trained at 768 resolution, so 768x768 inpainting works great</li><li>v4 was trained at 1024 resolution, so 1024x1024 inpainting works great</li></ul><h3 id="recommended-settings">GETTING THE BEST LIKENESS WITH LORA'S</h3>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.

Dakota Tyler

TRAINING INFOTrained on 128 photos (face &amp; full body) 4992 steps 1 epoch Trained at 768 resolution, so 768x768 inpainting works great "Smiling" and "from behind" are also trained into the LoRA, so adding them to your prompts should give a decent result.RECOMMENDED SETTINGSFor txt2img, a weight of 0.7-0.9 will give a little more flexibility, but 1.0 is noise-free. A weight of 1.0 works really well for inpainting. Face restoration isn't usually necessary, but I recommend setting your face restoration strength inside auto1111 settings to something like 0.7-0.8 which makes the effect less than the default setting of 0.5.

DakotaTyler1.safetensors

Files with SHA256: 9f325af659180b04049b4a4f29a7d8637a1b187d168864a2b897de7b0865ec54