<h1 id="v2-3qoq47bwa"><strong><span style="color:rgb(250, 82, 82)">V2</span></strong></h1><p>Last version I used too many images (93 I think), this version I used 24 images to capture a certain look. The difference in this lora with my others is I actually tested many epochs and found the best setting(in my humble opinion). I never did before because of laziness. Anyway I am not putting the trigger or strength in the normal spot because I want people to read the description or even just look at the prompts in sample images. To get the same results I got just look at the things below, it's not complicated and will save u some hassle. <strong>There will be more sample images hours after I post, some will be taken down for review by civit.</strong></p><p></p><h2 id="what-to-start-the-prompt-with-x7nn1tmzj"><strong>What to start the prompt with</strong></h2><p>You need to put "photo of m4d1s0n a woman" at the start. It's what I did while testing and what I found to be best. If you want a half body photo put "half body photo of m4d1s0n a woman". For full body- "full body photo of m4d1s0n a woman" etc.</p><p></p><h2 id="strength-it-works-best-at-mdtybdgax"><strong>Strength it works best at</strong></h2><p>I've tried a variety of strengths and what always works best for me is 0.8. More than that usually messes up hands plus doesn't add to the likeness, at least in my opinion.</p><h2 id="-yfre3xf5d"></h2><h2 id="you-don't-need-to-tag-her-regular-features-mbonnolpr"><strong>You don't need to tag her regular features</strong></h2><p>You do not need to describe her eye color, hair color, body type, etc. Unless you're in the mood with her having blonde hair or something.</p><p></p><h2 id="what-to-put-in-the-negative-prompt-zwl7nm0c6"><strong>What to put in the negative prompt</strong></h2><pre><code>ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teeth visible</code></pre><h2 id="what-models-this-works-best-with-ture05f3s"><strong>What models this works best with</strong></h2><p>I haven't had time to test with anything except Amalgamation but these are all the models my Loras usually work well with:</p><p>Himeros: <a target="_blank" rel="ugc" href="https://civarchive.com/models/255907?modelVersionId=423235">https://civarchive.com/models/255907?modelVersionId=423235</a></p><p>Amalgamation: <a target="_blank" rel="ugc" href="https://civarchive.com/models/287016?modelVersionId=456815">https://civarchive.com/models/287016?modelVersionId=456815</a></p><p>Juggernaut: <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005?modelVersionId=240840">https://civarchive.com/models/133005?modelVersionId=240840</a></p><p>Psychosis: <a target="_blank" rel="ugc" href="https://civarchive.com/models/449888?modelVersionId=515453">https://civarchive.com/models/449888?modelVersionId=515453</a></p><p></p><p></p><h3 id="v1-49n6utcn4"><strong><span style="color:rgb(250, 82, 82)">V1</span></strong></h3><p></p><p>She is hard to get a good likeness of but I tried my best. 2024 madison/ recent Madison. Use strength of 0.8. Should work with most models but I like it best with <strong>amalgamation and himeros</strong>. I recommend using steps from 30-40. Sample images are 832x1216 with Adetailer. I recommend putting this in negative prompt: <strong>ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open</strong></p>

Files with SHA256: 6c830f9bcd612c0540d4f9bac88584de6833cc0daa1549a954d8936abc0808fb