<h2 id="mixedup-3d-blend-experiment">MixedUp 3D Blend 🎨 [Experiment]</h2><p>This LoRA is trained on a mixed dataset focusing mostly on video game screenshots with ray-tracing as well some ue5 projects screenshots, I wanted to isolate what made them pop inside this LoRA.</p><p></p><hr /><h3 id="usage-tips-:">Usage Tips :</h3><ul><li><p>I personally use it at the weight of <span style="color:rgb(18, 184, 134)"><strong>0.9 </strong></span>so i recommend that</p></li><li><p><span style="color:rgb(64, 192, 87)">the LoRA needs to have its trigger words "</span><code>nv-vg3ds, detailed, realistic,</code><span style="color:rgb(64, 192, 87)">" in the prompt</span></p><ul><li><p>I your character loses depth or still have anime face then add  <code> (3d:0.5),</code> rather then upping the lora weight</p></li></ul></li><li><p>you might need to used adetailer or inpaint for fix far away faces</p></li><li><p>so far only tested on <a target="_blank" rel="ugc" href="https://civarchive.com/models/827184?modelVersionId=1761560"><strong>WAI-NSFW-illustrious-SDXL V14</strong></a> (used in the showcase pics)</p></li></ul><h3 id="observations-:">Observations  :</h3><ul><li><p>while the result fell a little bit short of my expectation when i comes to character is somehow exceeded them when it comes to scenes especially urban ones, i think it might cuz of the cyberpunk2077 screenshots i added later on.</p></li></ul><hr /><h2 id="feel-free-to-rate-this-resource-if-you-like-it"><em>Feel free to rate this resource if you like it 💚</em></h2><p></p>

Files with SHA256: 4c132628a8408c96c3d3b1f24ba1d81a3a2f182a65b887becb475c6d838d2319