CivArchive
    CoolerINKER style (ILLUST & PONY & SD1.5) - PDXL - epoch 07
    NSFW
    Preview undefined
    Preview undefined

    Trained on everything from CoolerINKER (also known as Inker-Shike)'s newgrounds to capture their style. Trained on AnyLora.

    If you like this model, please support the original artist. If you are the original artist and don't want this to be public, contact me please.

    This is my first lora, so I'm not sure what else to say...

    22.04.2024 - Updated to PonyXL. Same dataset. Used the on-site training this time and tinkered with the parameters a bit.

    14.02.2025 - Updated to IllustriousXL. Different dataset, different parameters, still on-site training. Consider putting constricted pupils, sketch in the negatives if you experience the corresponding phenomena.

    22.07.2025 - Note: it appears the trigger word can have a side effect on some models, where a cooler (a box that keeps food frozen) appears in the images. Add cooler to the negative if you experience that. Sorry for the inconvenience. Back when I made the dataset for this LoRA, base models didn't really know objects well enough to present this problem.

    If you like the style, please support the original author

    Description

    FAQ

    Comments (9)

    Abel1502
    Author
    Apr 22, 2024
    CivitAI

    I ran a test of epochs 2-15, and 7 seemed closest to the original style to me. I've uploaded the comparison chart, so tell me if you're interested in another epoch as well. I don't want to upload all of them, mostly because it would be tedious. Other than that, have fun, and I hope you like this!

    chaoslegesApr 22, 2024
    CivitAI

    Great! I like it.

    xmattarFeb 13, 2025· 3 reactions
    CivitAI

    hell yeah competition evolved

    any plans for illustrious?

    Abel1502
    Author
    Feb 13, 2025

    It is on my to-do list, though I think I'll need a better dataset. The old one is scraped from Newgrounds and AI-tagged, and now I'd much rather use manual tags from Gelbooru

    Abel1502
    Author
    Feb 13, 2025

    Okay, I've gathered a dataset and queued the training. Expect the new version tomorrow, if all goes well. On a side note, fuck civitai. Now "disney" is an inappropriate tag in a dataset, it turns out. Would've been nice to learn that any other way than trial and error. I like the community spirit and the free on-site LoRA training, but the level of censorship as of recently is really upsetting(

    xmattarFeb 14, 2025

    @Abel1502 do what i do

    google collab, its free without any buzz or any similar credit system

    basically unlimited aslong as u have more gmail accounts

    the only catch is that it needs 1-2 days to recharge

    Abel1502
    Author
    Feb 14, 2025

    @xmattar I'm considering Kaggle instead, given that it's apparently more generous with GPU usage, but I haven't yet taken the time to familiarize myself with a notebook

    Abel1502
    Author
    Feb 14, 2025

    Okay, Illustrious version is up. Have fun!

    xmattarFeb 14, 2025

    @Abel1502 yippe

    LORA
    Pony

    Details

    Downloads
    913
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/22/2024
    Updated
    4/30/2026
    Deleted
    -

    Files

    CoolerINKER_style_PDXL-000007.safetensors

    Mirrors