MGE Monster Girls - V6.1 - Illustrious
Prompts Recomendados
masterpiece, best quality, amazing quality, 1girl, perfect face, looking at viewer
Prompts Negativos Recomendados
bad quality, worst quality, worst detail, sketch, censor, border, text
Parâmetros Recomendados
samplers
steps
cfg
resolution
vae
other models
Parâmetros Recomendados para Alta Resolução
upscaler
upscale
steps
denoising strength
Dicas
Refer to the detailed taglist for feature customization at https://civitai.com/articles/7194/mge-monster-girls-taglist.
Experimentation may be necessary to get good results as not all features work perfectly.
The model is a fun solo project, not intended for commercial use or monetization.
Contact the creator if you are an artist who does not want your work used in this model.
Do not reupload the model without permission; sharing via links is acceptable.
Destaques da Versão
This version cleans up a number of issues with V6.0, adds a number of new "theme" tags, for which I've created a small article to compare both them and various artstyles, and improves the performance of many monsters, especially slime-girls. I've also added Alterkyon's artstyle (NSFW warning), as I've used enough images to get a consistent style.
Full changelog:
Expanded "see-through [feature]" to include slime-girls, which makes it significantly easier to get things like the dark-slime's "slime-core" working properly. See the "WIP" section of this article to see my progress there.
Also changed the colour tags for slime-girls to reduce the number of tags required, so you can now use "[color] slime, slime-colored skin, slime-hair" instead of doing them separately. This also allows them to be used as negatives, which allows for more control and improves monsters like the sea slime.
Fixed "spike-feet", which now applies to all arachnes and a few other monsters too (updated in taglist).
Also changed feet-tagging to be consistent across feet-types (eg: "3-toed feet, animal feet" instead of "animal-feet_3t"), which seems to work a bit better, albeit not as well as I'd like.
Expanded the "arthropod-girl" tag to allow for better control (with things like "arthropod arms, arthropod-legs", etc.), due to the variety in limb-designs between monsters (eg: arachne vs devil bug).
Adjusted the criteria for lamias, so now anything (with a lamia tail) that has a segmented underside is a "lamia", now including the oomukade, while anything with a fully smooth underside is a "lamia-like", which covers the green/wonderworm and unagi-joro.
Added "wings down" and "wings crossed" to better control wing positions. Also applies to "insect wings", which instead of horizontal/vertical, now just use nothing or "wings down" respectively. Performance is limited, but for harpies it allows for more interesting positions than just being fixed above/beside their heads.
Fixed the lesser-succubus, which now uses "breast-fur, groin-fur, navel-fur, covered navel, nude" for the related features. Still not as consistent as I'd like though, as any mention of "navel" makes it prioritise showing skin or a leotard. Other monsters that use those tags are also less consistent, which'll be a proirity for me next time.
Significantly improved horn performance, especially smooth ones, and added dedicated colour tags to the taglist for consistency, to no longer have it be species-dependent.
Added "fake horns" (primarily for the gandharva).
"Gradient horns" should work more often, although colour accuracy still varies for some monsters like the Pyrow.
I've also moved away from the horn-direction thing I tried last time, although the tags are still there, as it was too complicated and limiting to be used properly.
Made slight adustments to a number of tags for consistency (eg: "floppy head-fins" to "head-fins_floppy").
Added perspective tags to every reference image, so most features should now be more consistent at different viewing angles.
Added a number of experimental "theme tags", which mostly affect clothing designs. Some work better/more often than others, and their effects can vary based on the rest of an image's contents.
Last updated - 06/03/2025
Model description:
This is an attempt at an all-in-one lora for generating the monster girls of MGE, with a focus on customisability and being able to select the features you want individually. Refer to the taglist for more details, there's a lot of them. Not everything works perfectly, so good results may require a bit of experimentation at times.
Background info:
"MGE" Refers to the monster girl encyclopedia book series by Kenkou Cross. For more information, see the MGE wiki here.
"Non-entertainment" usage:
I've had my first question regarding legalities and commercial use, so: I am in no way affiliated with the creator, nor anyone involved in anything regarding MGE. This is a solo project, created solely for fun, which I've uploaded here because I assume other people will also enjoy using it. I haven't, nor do I intend to make any money with this beyond the buzz on this site, and I don't condone anyone else doing so*. I don't feel that strongly about it, and I appreciate being asked, just be aware that if you try I'm not getting involved in any disputes.
*So it turns out you can now exchange Buzz for real money... This section was written in the context of external projects like pay-walled Patreon content, or using generated images in larger "commercial projects", both due to a lack of legal knowledge, and feeling like it oversteps a boundary with my personal ethics. I don't intend to change my stance on this, as I think the negative online perception around generative AI stems from the immediate rush to monetise it, and I think most "ethical concerns" would have taken years to be brought up, if ever, if things like ChatGPT remained as niche research projects.
Actual artists:
If any artists dislike the idea of their stuff being used for this (and you've drawn things from MGE), let me know and I'll avoid your work. I understand that AI is a very divisive topic, and I didn't make this with the intention of pissing people off. As I don't intend to make money using my model, thid is more-so a thing for artstyles, because obviously impersonators will become harder to distinguish the better AI gets.
Reuploads:
I've decided to prevent unrequested reuploads of this (and my other stuff) on other sites as I've found the claiming process to be quite tedious, and there's little to no reason to allow it. I'll take direct requests for uploads, as if there's a reason to put it somewhere (say, for instance, a new startup has really good servers/features), then there’s a valid reason for doing so. I'm just not comfortable with stuff I've spent a significant amount of time making being spread to places I'm not aware of, nor people that did nothing to help benefitting from it. If you want to spread it elsewhere through links or something, go ahead, just don't reupload it to get yourself some free credits.
Detalhes do Modelo
Tipo de modelo
Modelo base
Versão do modelo
Hash do modelo
Criador
Discussão
Por favor, faça log in para deixar um comentário.




