Makes image similar in style to the artist <a rel="ugc" href="https://gelbooru.com/index.php?page=post&amp;s=list&amp;tags=gesugesu_ahoaho">Gesugesu ahoaho</a>.How to use This artist draws heavily both style and content-wise from the Monogatari universe. Themes this LoRA likes are blush stickers, shadows, outlines, shiny skin, smuggies and general 1girl stuff. For best results I recommend specifying a simple or colored background but there's also a couple depth of field images in the dataset so that should work too. The amount of useable images for training was somewhat on the small side so you might have to increase the LoRA strength to prompt outside the above themes or on models with more 3D mixed in.MISC Trained on Pony XL with a dataset of 29 images. All images are raw txt2img upscaled, no inpainting or helper embeddings used for quality transparence, e.g. - things should look even better if you do. The training was done on a small subset of images, 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://skeb.jp/@yocto_mako">artist </a>if you want the good stuff.

Files with SHA256: f768faf9f73e9020db11274aa6f7694881e234ff6de384d11ff2b348ad02cf8d