<h2 id="heading-4">Posted for <a target="_blank" rel="ugc" href="http://civarchive.com">civitai.com</a> and <a target="_blank" rel="ugc" href="http://tensor.art">tensor.art</a> only</h2>Each of these LoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.-MoC

Vi Kolodko XL

<ul><li>32 Rank experiment is proving fruitful. No longer will I create excessively large LoRAs</li><li>revised dataset selection process, you should be able to get extreme clarity out of headshots with this LoRA</li><li>Will need to be more detailed about clothing worn and it's color and sometimes use emphasis for this LoRA</li><li>1216px training base</li><li>Native resolutions to try: 1088x1344/1408 and 1216x1216</li></ul>

Files with SHA256: de825ebbb41bc2014c58337655f452a356ada361476961a67c04af03c19000cd