Makes images similar in style to the artist <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/posts?tags=fumio_%28rsqkr%29">Fumio</a>.How to use Prompt as normal. Things this artist likes are breasts, hips, tight clothing, covered nipples, panty shots, shiny skin and dynamic poses with arms flailing wildly. Things this artist doesn't seem to like as much is drawing the finishing touches on hands, often leaving them in a semi-sketch state. The quality tags of Pony XL seem to saturate the colors pretty heavily, if this is a problem try adjusting LoRA strength or changing/turning off the VAE. To reign in the hands I recommend prompting them in whatever place you want them to be.For further prompt tips please see the sample images and the uploaded zip of training tags.MISC Trained on Pony XL with a dataset of 106 images at 1024 resolution. All sample images are raw txt2img with no helper embeddings/negatives used. E.g. - things should look better if you do use them yourself. The training was done on a small subset of art, 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://twitter.com/fumio9361">artist </a>if you want the good stuff.

Files with SHA256: 1beefa3c4a7c30890307e935d8aa80a0a3e69ef569c801059d0017afae314ee9