A model trained on the (semi-niche??) 3D Virtual Youtuber, MonikaCinnyRoll.
Nothing can replace the real thing, so please, please go check her stuff out!
https://www.youtube.com/@MonikaCinnyRoll
https://www.twitch.tv/monikacinnyroll
Will be taken down if requested.
V2.1 is out.
Very slightly altered the tags.
Changed around some of the training parameters to try get something better.
It will probably be a long while before this model will get updated again, because most of the issues that the model has is (I feel) strictly due to the lack of photos in the training data. I got the tags as perfect as I could, but I just don't think I have enough photos, and super high-quality art is hard to come by from small creators.
Also, next time, I'm going to train it on WAI and not the base Illustrious Model. I also would want to make an Anima version at some point, but I have to mess around with it more and get a bit better at training models before I make any commitments.
V2 Notes
(Thank you to the one guy who gave me feedback :D)
Increased the dataset from ~20 to 30 images.
Doubled the epochs, from 10 to 20.
Replaced the half manual/half automatic tags with fully manual tags, removed some redundant tags, and added in some more detailed tags.
It should now be able to more properly follow your prompt, like hair length, eye color, outfit, expressions, or other more INAPPROPRIATE tags.
It's also more sensitive to previously mentioned INAPPROPRIATE tags, so even the most minuscule mention of "thick" can make her a bit too big sometimes; you have to get a bit more specific with what you want in regards to curves. If you use a style from an artist that makes curvy females, then good luck trying to make her smaller!
If the eyes keep coming out weird and unevenly colored, which you can see in some of the example images, then you can remove the specific colors and keep gradient eyes, or de-emphasize the colors with square brackets (which doesn't always work). Also, if the ears and tail refuse to go away even after removing them from your prompt, you can put the tags in the negative prompt.
It should also produce 3D images much better, although I haven't fully tested for that, as that wasn't what I was looking for. MILEAGE MAY VARY!
It's not perfect, but it's about as good as I could get it with what I had (which wasn't much).
Description
Increased the dataset from ~20 to 30 images.
Doubled the epochs, from 10 to 20.
Replaced the half manual/half automatic tags with fully manual tags, removed some redundant tags, and added in some more detailed tags.
The result is a MUCH more detailed model, particularly the face and the eyes.
It should also now be able to more properly follow your prompt, like hair length, eye color, outfit, expressions, or other more INAPPROPRIATE tags.
If the eyes keep coming out weird and unevenly colored, then you can de-emphasize them with square brackets.
It's not perfect, but it's about as good as I could get it with what I had (which wasn't much).