As this is a merge based off PonyDiffusion v6 I HIGHLY recommend you read the description of that model for information regarding prompting, tags, and baked in characters.

TL;DR Generation Settings:

• Sampler - Euler a

• Sampling Steps - 24

• Hi-res - 1.5x, 12 steps

• Dimensions - 832x1216, 1216x832, or 1024x1024

• CFG Scale - 6

• One pass of ADetailer

  • face_yolo8n or @Anzhc Face seg 640 v2 y8n with nothing in positive or negative

  • This might not be needed so much on XL

I use the following positive and negative prompt.

• score_9, score_8_up,score_7_up, source_anime, {prompt}

• NO NEGATIVE PROMPT OR EMBEDDINGS REQUIRED

  • 3d, monochrome, simple background, can be used as a default negative

  • watermark, patreon username, artist name, signature, text can help with watermarks generating if you run into that issue