Type | |
Stats | 547 |
Reviews | (92) |
Published | Aug 12, 2024 |
Base Model | |
Hash | AutoV2 820E6D097B |
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 / Restart / DPM++ 2M Karras
Sampling Steps - 25
I upscale to 4x using this process and the upscaler below:
Dimensions - 832x1216, 1216x832, or 1024x1024
CFG Scale - 7 or higher
One or more passes of ADetailer
Some combination of the following for faces and eyes
I use the following positive and negative prompt. I DO NOT USE ANY SOURCE TAGS (source_anime, source_furry etc) :
score_9, score_8_up, score_7_up, BREAK {prompt}
tags such as realistic, bokeh, depth of field can help enhance the realistic look
NO NEGATIVE PROMPT OR EMBEDDINGS REQUIRED
simply prompt for what you don't want to see as it comes up
See sample images for examples.
Experimental attempt to bring the Semi-Realistic 2.5d style of my old Pseudo Mix to Pony. Works best with character-centric prompts. Hands are still fairly messy at this point. Resources I used are listed in the Suggested Resources.
As with most of my mixes, this is intended to produce female characters and leans towards NSFW.