<h2 id="heading-2">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 DoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.-MoCSee about this version for model details 👉

Mila Amour (Samadhi) SDXL

<ul><li>My first DoRA attempt, based off the quality derived from this first attempt, not seeing a reason to stick to standard LoRAs anymore.</li><li>Dataset gathered and trained on a single concept, ranging across this model's career.</li><li>~11 hour Kohya_ss training in 15975 steps across 25 epochs @base dim (rank): 32.</li><li>1248x1248px training resolution base</li><li>Used a wide variety of resolutions in training data, however by far the most common bucketed resolutions were @ 1024x1472 &amp; 1216x1216px.</li></ul>

Files with SHA256: 98adda5ece2713c38092804e20c263961a1b99fa72667bdc61f85b70b9ff977d