CivArchive
    Courteney Cox - V1
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Courtney Cox is most famous for her role in the TV-Series Friends. She also starred in the Scream series, 3000 Miles To Graceland, Cougar Town.

    Description

    Since the model is made using custom merge, the simple prompts may return dull results. It's best to be creative and play with the strength of the token keywords.

    Merge included HassanBlend and Pyros which means that there should be less anatomically incorrect poses (and yes, you could use it in the way HassanBlend and Pyros were trained for as well).

    FAQ

    Comments (4)

    scruffynerfDec 18, 2022
    CivitAI
    There is NO reason to make an entire checkpoint for this. A single person's images can be made into an embedding, which will make it about 20k or less, and used with ANY checkpoint. Reducing from 2gig to 20k is a massive savings. Please consider replacing this with an embedding, or supply your image set that you trained with, and someone else can make the embedding (or walk you thru making it yourself) Nothing personal, adding to a bunch of these 'checkpoints for one person's images'
    cooperdkDec 22, 2022
    CivitAI
    Her name is COURTENEY COX, as most of your training images state... Anyway, this needs to be a hypernetwork, not a checkpoint. It will require less training data, and it will be much more precise, while taking up maybe 10% of the space. Someone mentioned that "accuracy is more important than space". He seems to not understand that a larger file also means longer computing time.
    malcolmrey
    Author
    Jan 1, 2023

    wow, thanks for pointing that out; for almost 20 years i thought it was Courtney and didn't believe you until I've rechecked... and indeed it is Courteney. Title has been fixed.

    as for the hypernetwork comment, feel free to use the training data that i have provided and make a new hypernetwork! :-)

    i have not made a hypernetwork yet but if i see one that can be mistaken for dreambooth quality-wise then i guess i would be actually interested in researching the hypernetwork training :-)

    "He seems to not understand that a larger file also means longer computing time."

    by "He" you mean me? i run most of the dreambooths while I sleep or am at work so the longer computing time is a non issue for me

    bigger issue is preparing the training set data (it's a bit tedious), otherwise I would be doing 4 dreambooths every night :)

    cheers!

    mv20Jan 13, 2023· 5 reactions
    CivitAI

    All the people claiming a full checkpoint isn't needed need to look into it more. A textual inversion doesn't ADD anything to the checkpoint, only helps SD create better images of what you want. A fully trained CKPT adds more images that produce a LOT better results. Try it.

    Checkpoint
    SD 1.5

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    418
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    12/18/2022
    Updated
    5/14/2026
    Deleted
    5/23/2025
    Trigger Words:
    sks woman
    (sks woman)

    Files

    courteneyCox_v1_trainingData.zip

    Mirrors

    courteneyCox_v1.ckpt

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.