After posting <a target="_blank" rel="ugc" href="https://civarchive.com/models/2289084?modelVersionId=2576020">https://civarchive.com/models/2289084?modelVersionId=2576020</a> the most common request was to attempt a more realistic looking lora. This is my first attempt at training with real images, so it's not perfect, but it does output some great shots! Experiment with the lora <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">strength. If you are getting deformed bodies, turn it down! I've had some good results even at 0.5<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Trained using ai-toolkit with the base qwen 2512 model.

Files with SHA256: 4d56883db96ffed8f6c6cebc543d4ef7f1df8cbd89354e0f9c44a194a2afe11e