CivArchive
    2m3ta Style - V2
    NSFW
    Preview 111666662
    Preview 111666658
    Preview 111666663
    Preview 111666679
    Preview 111666656
    Preview 111666667
    Preview 111666664

    Used a few of my personal favorite generations to whip this up.


    As a result, it is essentially a style lora that mixes expressiveH, incase, and gothic-neon, all at around .5-.8
    I'm vanilla, so it's is very good at whipping up basic "ultra hot" girl, rule 34, bodies and expressions. Pretty good with multiple skin tones on both male and female subject as well.

    Works best at around 0.8-0.9, 30-50 steps, regular pony problems with weird faces/extra digits do occur, but easynegative type embeddings help a lot, don't forget to make sure the trigger word is in the prompt somewhere.

    Helps to have fairly specific prompts, I recommend using both my negative and positive prompts from the sample images as examples and editing them from there. Use r34 tags and the innate pony character tags as required.

    I made this to streamline my local generations, but I would love to hear feedback, and as soon as I have more images to feed it I will make an updated version.

    Enjoy :)

    Description

    Added many more training images that I personally in-filled and edited to enhance the results.

    Added many distinct tags, notably perspective and view tags to make it easier to frame the image. Too many to list here, but full training data is attached if you're curious.

    Skin colors and regular pony errors have been minimized.

    Use same prompts and weights. Sweet spot is between .75 and .9.

    Clip Skip between 0.5-1 for best results on most local generators.

    FAQ

    LORA
    Pony

    Details

    Downloads
    62
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/26/2025
    Updated
    4/23/2026
    Deleted
    -
    Trigger Words:
    2m3ta

    Files

    2m3ta_Style_V2.safetensors

    Mirrors

    CivitAI (1 mirrors)

    2m3taV2_training_data.zip

    Mirrors

    CivitAI (1 mirrors)