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.
Description
FAQ
Comments (22)
Based Model as always 😎
God, thank you for this! The base model is VERY unstable. I love your MFCG Doll Mix model and will definitely try this xl version.
well... time to do the same thing as you did but with my models 😁 (making around 500 pics on my models and then merging them to pony)
Could you enable this for onsite generation please?
Damn good model! Thank you!
started using this a few days ago... after trying to generate an image at 832x1216 it is taking SOOO long. I know this probably sounds like a basic issue but I've never had issues with the speed of my generations until now. can anyone suggest how I speed them up?
The model looks very good and I've seen some great examples here, but I don't see any differences with Pony V6...
How is it better, what does it add?
Thanks
Just a question: why should I use another (6 GB) model instead of just using Pony with a prompt-infused LoRa? It's not like Pony was fine-tuned with new data, AFAIK.
smash
Looks interesting - will you be uploading it to Tensor.art as well?
my favorite model by far! The one down side is that it doesn't work with ControlNet :(
Is there a reason I can't use this on CIVITAI website?
Why can't I use this checkpoint?
Can youmake this model available for pony diffusion?
I install the model but i cant generate a thing, im using stable diffusion btw
It's really a bad model. All the girls have a dead look. They all stare into the camera. By default, their proportions are wrong. The bodies are nice. But the faces are terrible. Hardcore Hentai model is much better.
Out of a hundred attempts, only a few of them don't look like a plastic doll.
And the images have little details, compared to the HH.
It definitely works
will it be possible for a version where the female characters doesn't look like she hulk 😅
I found for myself the optimal unique combination that allows me to display and create exactly what I need without unnecessary movements. I actively use my personal top one. I treat it with great warmth. As a fact, it is natural to wish the point further development in the form of new versions.
Still new to AI generation but this has become my favourite checkpoint very quickly. Feels like nothing is impossible with MFCG
11/10
I'm now going to buy 1000 bottles of lotion (no Diddy)
it became my main checkpoint with semiPD. very good work
love this checkpoint! any chance of an illustrious version?
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.