This LoRA was trained on 76 training images in which the breasts appear to move back and forth between two points through the use of a solid form and afterimages.As a result, afterimages tend to appear in bottom-to-top, top-to-bottom, diagonally upward, or diagonally downward directions.One important limitation is that, in v0.0.0, most of the training images feature vertical up-and-down movement. Therefore, this LoRA is not capable of reliably reproducing intense side-to-side movement from a direct side view.

Concept > Afterimage (breasts)

Changes from v0.0.0<ul><li>Training image count and resolution: The dataset has been reduced from 76 images at 512² resolution to 40 carefully selected images at 1024² resolution.<ul><li>Images with clearly defined nipples in the afterimage were selected, while training images with blurry or poorly defined afterimages were removed.</li></ul></li><li>Reduced tendency to enlarge <code>small breasts</code> and <code>flat chest</code>: This was caused by the lack of training images featuring smaller breasts. Of the 40 newly selected images, 10 feature <code>small breasts</code>, and 3 feature <code>flat chest</code> (including 1 cropped image). The remaining 27 images continue to feature the large-breast afterimages used in the previous version.</li></ul>Unlike v0.0.0, the effect where the afterimage becomes stretched between the original image and the afterimage, creating a ghost-like smear frame, is more subdued.Depending on the situation, the previous version may produce a stronger or more desirable effect, so keep this in mind when choosing between the two versions.dim16/alpha16, AdamW8bit, UNet LR 1e-04 constant 800 steps, 1024² resolution, 40 images.

Files with SHA256: dd4445c3894e19155e0edb2548e1f38858e8d6aba0c994f7b6062603a2df857a