CivArchive
    Preview 23046596
    Preview 23046593

    Last updated - 31/10/2026

    React to this model, this post and the taglist to support blue team!

    (Likes for the model might be locked behind downloads due to the fee, apologies for that. Articles should be fine, though most are only visible on Civitai.Red)

    Work on V7.1 is on hold until Civitai's Kohya trainer is fixed. I'll do what I can in the meantime, but unfortunately AI-Toolkit simply isn't comparable in terms of performance. Work on the Anima version has also stalled as I'd much rather wait and maintain parity than do them separately again, but there's likely still some performance gains I could get from doing captions rather than tags so in the worst-case scenario I'll probably just resume there. More details here.

    In spite of that, I've set a download fee of 100 buzz to support future training costs, no changes to on-site generation, so when I'm able to resume I can do so using a stockpile without further restrictions. This is solely due to changes in free (on-site gen) compensation, which would make this project unsustainable using it alone, having gone from ~300 buzz a day to ~40, of the 4k needed per run.

    Also, to be transparent, I don't plan on withdrawing any buzz, but if I earned enough to buy a good GPU to train locally I'd consider it. This is unlikely to happen, so it will instead be used primarily for on-site training, and potentially for things like cosmetic uploads on occasion. (I believe I'd need an unusually high amount of VRAM for my model because tests I've done with Runpod were drawing ~40GB at current settings, so unless there's some LowVRAM setting that doesn't impact the results I'd be paying thousands at the minimum)

    I also have a few cosmetics available for those who'd like some, (500 buzz each) they're all stickers for the time being but I'll make more if I see enough interest. I've got some profile-pic borders ready to upload, but as it costs me 10k per item I'll only do so if it's worthwhile.

    Keep an eye on the pinned comments and/or my profile's announcement tab for more updates.

    :ruby_smile:

    Model description:

    This is an attempt at an all-in-one lora for generating the monster girls of MGE, which allows for extensive customisation and feature-mixing. Refer to these articles for more information. Not everything works perfectly, so good results may require a bit of experimentation at times.

    For updates on future versions, I generally post what I'm working on in my profile's announcement tab. It'll probably be MGE-related, but in addition to this one I occasionally make standalone concept-loras for monsters that would benefit from having one.

    Background info:

    "MGE" Refers to the monster girl encyclopedia book series by Kenkou Cross. For more information, see the MGE wiki here.

    Additionally, while I'm not affiliated with them, the wiki recently opened donations so you can donate here if you'd like. They have a $12/month upkeep cost apparently, so I'm sure they'd appreciate the generosity. Be sure to mention where you got the link from too, for the model's sake :).

    "Non-entertainment" usage:

    Any "commercial projects" must be transformative, so no posting your results to Patreon and asking for money. Using it as part of a larger project is fine though, and I'm happy to help if you reach out with questions, or simply to tell me an interesting use-case you have. Bear in mind that if you're creating stuff linked to MGE specifically, they must also adhere to the creator of MGE's terms here.

    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 haven't done this preemptively due to the huge number of dead source links in the archive, but if you reach out (with some proof of identity to avoid trolls) I'll remove any of your content from my dataset/s.

    Reuploads:

    If you reupload this, please link both this model page and my taglist for ease of use. I'd also appreciate you letting me know where you've uploaded it, so I can keep track of where it's being used.

    Description

    Test to see whether training on SDXL helps with more unique features (manticore tail, barometz fruit, etc.). So far it seems to generally be worse at anatomy, but it allows for more control over textures.

    FAQ

    LORA
    SDXL 1.0

    Details

    Downloads
    635
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/5/2024
    Updated
    11/5/2026
    Deleted
    -

    Files

    MGE_SDXL.safetensors

    Mirrors

    CivitAI (1 mirrors)