<s>This is an experimental early release. I believe Mr. </s><a target="_blank" rel="ugc" href="https://civarchive.com/models/1488059"><s>MetalchromeX</s></a><s> will likely come up with something even better than this LoRA.</s> <a target="_blank" rel="ugc" href="https://civarchive.com/models/2634049">V1 has been released</a>, yay!The training data focuses specifically on "pressed-up buttocks" and "skin ripples/waves" from various angles and positions. Please note that it may not be ideally suited for "imminent penetration" scenes, as the emphasis is on the physical contact and pressure.

Ass ripple

Major Changes: v0.0.0 to v0.1.0 TL;DR (v0.1.0 Update Summary)* Dataset Cleaned: Removed AI images and semi-transparent ghost penis references. Resolves the bug where X-ray elements bleed into non-X-ray prompts. * Artist-Centric: Now trained on 25 hand-drawn illustrations, causing some positional bias but significantly minimizing artstyle contamination.* Tag Experiment: Added <code>ass_ripple</code> (1 ripple) and <code>excessive_ass_ripple</code> (2+ ripples), though intensity control remains limited.* Settings Overhaul: Switched to Cosine (Dim 16 / Alpha 8, 10 Epochs, 1250 Steps) at 512x512 resolution. Improves compatibility with specific artist tags.1. Dataset Refinement (Silhouette Filter &amp; Artist-Centric Source)<ul><li>X-ray Adjustment: Removed the dataset images featuring semi-transparent penises, which were previously causing a bug where a semi-transparent penis would appear in outputs even without specifying the <code>x-ray</code> tag. However, please note that one specific artist illustration featuring an internal cumshot (X-ray view) is still included in the dataset.</li><li>Artist-Centric Dataset: Completely removed all AI-generated images from the training data. Version 0.1.0 is trained on 25 hand-drawn artist illustrations.<ul><li>Note from Creator: Please be aware that this change may not be entirely beneficial, as relying solely on artist illustrations has introduced a heavy bias toward specific camera angles and sexual positions.</li></ul></li></ul>2. Trigger Word Classification (Experimental)<ul><li>To differentiate the intensity of the effect, I categorized the tags based on the number of ripples:<ul><li><code>ass_ripple</code>: For images featuring a single ripple.</li><li><code>excessive_ass_ripple</code>: For images featuring two or more ripples.</li></ul></li><li>Limitation: Unfortunately, this classification attempt was not very effective. Even when using only the standard <code>ass_ripple</code> tag, multiple ripples may still frequently appear in the generated output.</li></ul>3. Training Settings OverhaulI completely restructured the training parameters to improve flexibility and texture:<ul><li>v0.0.0: <code>Constant</code> | Dim: 64 / Alpha: 32 | 3 Epochs | 624 Steps | 26 Dataset Images</li><li>v0.1.0: <code>Cosine</code> | Dim: 16 / Alpha: 8 | 10 Epochs | 1,250 Steps | 25 Dataset Images</li><li>Result: This overhaul successfully suppresses unintended artstyle alterations and improves compatibility with specific artist tags.</li></ul>4. Image Upscaling &amp; Resolution<ul><li>No upscaling was applied for this version. The dataset continues to use 512x512 resolution, just like the previous version.</li><li>I will continue testing and utilizing this version for my own generations first. If the overall feel and usability look good based on my personal testing, I might retrain the model in a future update using a higher 768x768 resolution.</li></ul>

Files with SHA256: 2f19110374d373822b8e952037277e8b8aa2b1f1d6c6038857595e19c7c3a988