This LoRA is designed to generate a single tongue afterimage depicting a tongue moving either horizontally or vertically.For v0.0.0, I trained the LoRA on 30 images in total:<ul><li>25 training images, with manga panels and multi-scene illustrations cropped down to a single panel where necessary</li><li>5 cropped images focusing on the specific area targeted by the LoRA</li></ul>Of the 30 images, 26 feature <code>1girl</code>, while the remaining 4 feature <code>2girls</code> in cooperative fellatio. As a result, reproducibility tends to decrease when more than one person is involved.<h3 id="changes-from-2way-afterimage_tongue_v0.0.0">Changes from <a target="_blank" rel="ugc" href="https://civarchive.com/models/2723087/deprecated-concept-greater-2way-afterimage?modelVersionId=3099850">2way-afterimage_tongue_v0.0.0</a></h3>The training images were completely replaced, the training resolution was increased, and the optimizer was changed.Previous version: <code>dim16/alpha8, Lion8bit, UNet LR 1e-05, cosine_with_restarts[2] 1,400 steps, 10 images (512² resolution), 1,400 steps</code>v0.0.0: <code>dim16/alpha16, AdamW8bit, UNet LR 1e-04, cosine 1,200 steps, 30 images (1024² resolution)</code>The most noticeable improvement is the reduction in image quality degradation. The new version preserves image quality more effectively compared to the previous LoRA.

Concept > Afterimage (tongue)

Initial.dim16/alpha16, AdamW8bit, UNet LR 1e-04 cosine 1,200steps, 30 images(1024² reso).

Files with SHA256: 9bffe2d3e9ee7f9508c2d210a04e8b89af203d4faef709bd37d80dc3f19e0339