That's a lot of consonants.Spiritual successor to my SD 1.5 Doll model. Merged using a LoRA from images generated by myself on my old 1.5 models blended into the exceptional AutismMix_confetti. This is a pretty horny model with the primary goal of generating female characters. As such, it may not be suitable or flexible enough for all scenarios and use cases.Released in collaboration with FallenIncursio. Check his new Meme Diffusion for Pony!As this is a merge based off PonDiffusion v6 I HIGHLY recommend you read the description of that model for information regarding prompting, tags, and baked in characters.The baked-in artist styles for PD should work, but as this is effectively a style merge, they will defeat the purpose of this model.All sample images were generated using without the use of any LoRAs or embeddings. My typical settings are below:Sampler - Euler a/DPM++ 2M KarrasSampling Steps - 25I upscale using this process and the upscaler below:4X AnimeSharp upscalerDimensions - 832x1216, 1216x832, or 832x832CFG Scale - 7One pass of ADetailerface_yolo8n with nothing in positive or negativeThis might not be needed so much on XLI tend to use the following positive and negative prompt. You shouldn't need any schizo negatives by default. I don't use any of the source tags as I don't find them necessary, but YMMV:score_9, score_8_up, score_7_up, BREAK {prompt}score_3_up, score_4_up, score_5_up, {prompt}3d, realistic in the negative will give a more anime lookwatermark, patreon username, artist name, signature, text might help with watermarks generating if you run into that issueThe model has a tendency to draw teeth on characters with tags like smile/grin/smirk. Putting teeth in the negative can help offset this.I am still no expert when it comes to SDXL (and SD in general) so I would recommend experimenting with these settings to find what suits you. See sample images for more examples of prompting.All credit to the original model authors, please check them out.
