As this is a merge based off <a target="_blank" rel="ugc" href="https://civarchive.com/models/257749/pony-diffusion-v6-xl">PonyDiffusion v6</a> I HIGHLY recommend you read the description of that model for information regarding prompting, tags, and baked in characters.<h3 id="tldr-generation-settings:-i8xlnwpsn">TL;DR Generation Settings:</h3><ul><li>Sampler - Euler a</li><li>Sampling Steps - 24</li><li>Hi-res - 1.5x, 12 steps</li><li>Dimensions - 832x1216, 1216x832, or 1024x1024</li><li>CFG Scale - 6</li><li>One pass of <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer</a><ul><li>face_yolo8n or @Anzhc <a target="_blank" rel="ugc" href="https://civarchive.com/models/293448/anzhcs-face-segmentation-prototype-or-yolov8-or-adetailer-model">Face seg 640 v2 y8n</a> with nothing in positive or negative</li><li>This might not be needed so much on XL</li></ul></li></ul>I use the following positive and negative prompt. <ul><li>score_9, score_8_up,score_7_up, source_anime, {prompt}</li><li>NO NEGATIVE PROMPT OR EMBEDDINGS REQUIRED<ul><li>3d, monochrome, simple background, can be used as a default negative</li><li>watermark, patreon username, artist name, signature, text can help with watermarks generating if you run into that issue</li></ul></li></ul>

Files with SHA256: 00b98c5859baf4d479a1f6d5442904bcf1f475bbf170a847da385bc47d4b0e83