CivArchive
    Jaime Pressly ti - chzJaimePv2
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Jaime Pressly is an American actress, fashion designer, and model. She's best known for her role as Joy Turner on the NBC sitcom My Name Is Earl.

    Update - While testing v1, I used a pair of new negative TIs that fooled me into thinking my embed was performing better than it was. The good news is that I can now confirm that SoCalGuitarist's negative embeds work some powerful mojo. They changed my pics with an over trained TI into straight fire! You can find them here: https://civarchive.com/models/8551/scg-embedding-toolkit-for-version-15-models-a-collection-of-tools-and-helpers-from-my-personal-kit

    Anyway, if v1 works for you, fantastic, but if not, v2 hopefully will.

    I don't drink coffee, so give your money to someone who does. Or keep it. I'm not qualified to make financial decisions like that for you.

    Description

    v1 is a bit over trained due to a couple of negative TIs I used during testing. Embarrassing! Since I'd already scrubbed most of the data, v2 represents fresh training. It looks great and makes me feel better about having it out there.

    FAQ

    Comments (2)

    maxhitmanMay 30, 2023· 1 reaction
    CivitAI

    Your FIRST version deserves a star rating. Its very well done. Congrats!

    There was no need for a version 2.

    ..........................

    Here is a friendly tip for the things you are doing wrong with your image creations.

    When you create a LORA or a T.I. , and you want to create photo-realistic images, it is best to create them using a checkpoint which is best at doing it.

    I will highly recommend to use Realistic-Vision version 1.3 ( NOT the version 2.0). It is the best for photorealistic-pictures. Your first version T.I. will look 10 times better using the same prompts and with using this checkpoint.

    If you use any other Checkpoint which mixes in ANIME/or/painted style faces, you will get distortion in your model faces and they will either look "painted" or look too "anime-Style". This depends on what you are actually trying to create with the face ... a photo-realistic face? an anime-style artwork?...or a painted-style look ?

    If you want to have a good mix of Checkpoint mergers for a photo-realistic image, then I will highly suggest this selection...

    .

    Your MAIN Checkpoint should be = Realistic Vision version 1.3

    In your "checkpoint merger" menu selection,

    place the following...

    A - ProtogenX3.4

    B - Clarity_1.9

    C - Deliberate

    - DO NOT FORGET to ALWAYS include in your written prompts the special "trigger words" used for each checkpoint you use. That way the A.I. can go and use that Checkpoint !

    .

    Your Menu settings should be CFG scale = 7 or 8, and use 40 or 70 steps on your images, not 33 as you some times use.

    Using the settings of 5 or 6 on your CFG-Scale will often create a "painted style" image. Less details and more Blurry-like visual effects.

    .

    Using a "negative-prompt" Lora or T.I (as you suggest) with your Negative prompts can be useful some times when creating ANIME style art and images, but usually don´t work so well with photo-realistic images. It is because the way they are written.

    One great negative prompt I usually use is this...

    for S.F.W. images...

    ((NSFW)), ((Nude)), (Naked), (pussy), (vagina), (nipples), monochrome, black and white, canvas frame, cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((black and white)), blurry, (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), ((bad proportions)), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), ((extra legs)), mutated hands, (fused fingers), (too many fingers), ((long neck)), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, 3d render,child, child-like, doll,

    ......

    for NSFW photo-realistic images...

    ((Clothes)), , ((Clothing)), (pants), (bikini), ((bra)), (underwear), (dress), (skirt), canvas frame, (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, fused lips and teeth:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, doll, child, un-detailed skin, monochrome, black and white,

    ......................

    portraitartist999132Oct 15, 2023
    CivitAI

    IMO, version 1 is closer to the real Jaime Pressly than version 2- I would like to request a LoRA of this. Please and thanks?

    TextualInversion
    SD 1.5

    Details

    Downloads
    805
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    5/30/2023
    Updated
    7/7/2025
    Deleted
    5/23/2025
    Trigger Words:
    chzJaimePv2

    Files

    Available On (1 platform)

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