Makes images similar in style to the artist <a target="_blank" rel="ugc" href="https://gelbooru.com/index.php?page=post&amp;s=list&amp;tags=pantsu-ripper">Pantsu-Ripper / AMLOgamer.</a>How to use This artist has a rather unique style mixing sketchlike elements along with 3D and cell-shading influences with some outlines sprinkled on top. The dataset contained various numbers of girls in different settings so the LoRA should be fairly versatile. Samplers can modify the outputs slightly, Euler A generally producing more smooth results and DPM++ 2M slightly more gritty variants. For basic character prompting I recommend specified background, "simple background" or a color for best results, unless you have something else you want to prompt there. NSFW wasn't overly represented in the dataset and fairly mild mostly just revealing clothing and the occasional partial nudity.MISC Trained on Illustrious with a dataset of 131 images at 1024 resolution. All images are raw txt2img, no inpainting or helper embeddings used for quality transparence, e.g. - things should look better if you do. The training was done on a small subset of imagery, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the <a target="_blank" rel="ugc" href="https://x.com/AMLOgamer/">artist </a>if you want the good stuff.

Files with SHA256: c879a16246829c5e0206eebf9415fd227a1371b31e243bdbae3069fb8f5dbee5