V1First Lora published, but I have been working on this dataset and tagging for about a year. Trained on only 16 images which have been highly edited to remove any watermarks, color discrepancies, and body deformations. Tends towards creating women without tops on, but as can be seen with images it can create safe for work content just fine after a few tries. Can handle simple and complex prompts. <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">Keep in mind all images shown are generated without using negative prompts, using negative prompts will make image results far better.

Epoch 5 came out the best, fingers and toes came out great.

Files with SHA256: 571a706db12d3dde8b55625d9096b8fdc1350ea5155c7e2439a9bea8c3979555