It's a retrained Locon model which should work better with clothes. It works better with the anime base model. This LoRA needs to be used in with negative embedding models such as EasyNegative, Deep Negative, etc.Two separate clothing tags can be used:<ul><li>skirt: do not use other skirt modifier tags (like red skirt, long skirt), or they may not be recognized.</li><li>dress, dress lift: other dress modifier tags may also reduce recognition.</li><li>Add tags like nude if you don't want clothes.</li></ul>Suggestions for realistic base models:<ul><li>Add stain ribbon tag to stabilize the ribbon material.</li><li>Added negative tag (rope:1.8) to remove rope texture.</li><li>Reduce the Hires. fix denoising strength to avoid distortion (around 0.52).</li></ul>You can check out my example images to use. Unfortunately, I know that this LoRA tends to produce strange and distorted output on many base models.

ribbon bondage

Use regularized training datasets. Bigger breasts and richness in the background.

Files with SHA256: af6fbbd80aa428aa6259d357a1641c8950d6f15b2719cdde92251fd08bfe4115