A mature female mage casting an ice magic spell in a dynamic pose amidst a snowy wasteland, wearing a corset and anchor necklace with blue eyes and white-blonde braided hair.
Anime illustration of a female scientist with long brown hair, wearing a white lab coat, glasses, and a blue-orange outfit, created using Stable Diffusion AI.

Recommended Prompts

score_9, score_7_up, BREAK {prompt}

score_9, score_8_up, score_7_up, score_6_up

Recommended Negative Prompts

watermark, signature, artist name, patreon username, text, monochrome, loli

Recommended Parameters

samplers

Euler a

steps

25

cfg

7

clip skip

2

resolution

832x1216, 1216x832, 832x832, 1216x832, 832x1216

Recommended Hires (High-Resolution) Parameters

upscaler

4X AnimeSharp, 4x-AnimeSharp

upscale

2

steps

10

denoising strength

0.4

Tips

Put 'teeth' in negative prompts to reduce unwanted teeth in smile/grin/smirk tags.

Do not use source tags like source_anime or source_furry for better results.

Including '3d, realistic' in negative prompts can increase the anime look.

Add negative prompts like 'watermark, patreon username, artist name, signature, text' if watermark issues appear.

One pass of ADetailer with face_yolo8n is helpful but might not be essential for XL version.

Creator Sponsors

Released in collaboration with FallenIncursio. Check his new Meme Diffusion for Pony!

That's a lot of consonants.

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.

Released in collaboration with FallenIncursio. Check his new Meme Diffusion for Pony!

TL;DR Generation Settings:

  • Sampler - Euler a

  • Sampling Steps - 25

  • I upscale using this process and the upscaler below:

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

  • CFG Scale - 7

  • One pass of ADetailer

    • face_yolo8n with nothing in positive or negative

    • This might not be needed so much on XL

I use the following positive and negative prompt. I DO NOT USE ANY SOURCE TAGS (source_anime, source_furry etc) :

  • score_9, score_7_up, BREAK {prompt}

  • NO NEGATIVE PROMPT OR EMBEDDINGS REQUIRED

    • 3d, realistic in the negative will give a more anime look

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

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.

The model has a tendency to draw teeth on characters with tags like smile/grin/smirk. Putting teeth in the negative can help offset this. See sample images for more examples of prompting.

Previous
Not Artists Styles for Pony Diffusion V6 XL - Summer Night
Next
Dan Mora [Illustrious] Style Lora - v1.0

Model Details

Model type

Checkpoint

Base model

Pony

Model version

v1.0

Model hash

529c72f6c3

Discussion

Please log in to leave a comment.

Images by MFCG PDXL - v1.0

anime Images

base model Images

female Images

porn Images

sexy Images