CivArchive
    Bad artist Negative embedding - Bad artist
    Preview 52078

    I AM NOT THE ORIGINAL CREATOR OF THIS EMBEDDING

    HE IS -

    https://huggingface.co/nick-x-hacker/bad-artist

    The images above were generated with only "solo" in the positive prompt, and "sketch by bad-artist" (this embedding) in the negative.
    The embedding uses only 2 tokens.

    Textual-inversion embedding for use in unconditional (negative) prompt.
    Inspired partly by https://huggingface.co/datasets/Nerfgun3/bad_prompt.

    There are currently 2 version:

    • 'bad-artist': Not as strong, but produces pretty unique images (recommended)

    • 'bad-artist-anime': More generic anime style (this was the first version uploaded)

    I recommend using with 'by', so for example "sketch by bad-artist", or "painting by bad-artist", or "photograph by bad-artist", etc.

    Trained with 2 vectors per token for 15000 (1850x8) steps, at 500x500, on an Anything-v3-based model.

    Full generation parameters for images above (using the 'bad-artist' version, not the 'bad-artist-anime' version):

    solo
    Negative prompt: sketch by bad-artist
    Steps: 15, Sampler: DPM++ 2M Karras, CFG scale: 4, Seed: 1476197242, Size: 512x640, Clip skip: 2

    Description

    FAQ

    Comments (29)

    alkindMar 22, 2023· 2 reactions
    CivitAI

    Hi I'm using GCollab and this model is unreadable with sd-civitai-browser extension, is there any solution other than manual download?

    deformednipplesMar 27, 2023· 1 reaction

    I'm using colab by camenduru so I'll paste this in runtime

    !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://civitai.com/api/download/models/6056 -d /content/stable-diffusion-webui/embeddings -o By_bad_artist_neg.pt

    bakaboy1234Apr 20, 2023· 1 reaction
    CivitAI

    unreadable with sd-civitai-browser extension, can this be fixed?

    oceanesApr 21, 2023

    Base Model: sd1.5 & sd 2.1 ?

    X3I4Apr 24, 2023· 3 reactions
    CivitAI

    the trigger word in details says "by bad artist" but the description says "sketch by bad artist" so what is it?

    hestiacummingsJun 10, 2023· 4 reactions

    it takes 30 seconds to find out, try it?!

    Click on the huggingface link in the description for nick-x-hacker and just read the Model Card.

    Basilisk_xApr 29, 2023· 24 reactions
    CivitAI

    what is the difference between "by bad-artist" and

    "by bad-artist -neg"?

    JigglePhysicsJun 1, 2023· 1 reaction

    the filename is supposed to by labelled as bad-artist and the anime one bad-artist-anime, at least that's what its labelled on hugging face

    exxterixsJun 10, 2023

    that is just another trigger word, you can see them in "Details"

    wiyac33524204May 4, 2023· 33 reactions
    CivitAI

    This is a really good embedding, but could you also make a safetensor variant?

    KoiArtNov 16, 2023· 9 reactions
    CivitAI

    I suggest that a category tag named 'Tool' be added to the tags

    1315085Dec 12, 2023· 6 reactions
    CivitAI

    How do you make an embedding? How can I make a negative embed? I want to make some as well. I'm tired of my workflows not being what I need.

    2236741Dec 19, 2023

    this file should be placed in the sd/embeddings folder. it will be in the "textual inversion" tab

    1315085Dec 19, 2023

    @void1243 No, I know that much. I am genuinely asking how a person would make their own negative embed.

    jingxi0421Jan 12, 2024· 2 reactions

    第一步,文件放在embeddings文件夹中

    第二步,用的时候,在负面关键词中输入作者强调的关键词,另外,我还习惯在光标在负面词输入框里的时候,点击负面模型,这就好比你用lora的时候,在正面关键词中点击lora,会出现相关关键词并生效一样

    1315085Jan 12, 2024

    @jingxi0421 I want to create a negative embedding, not use this one. Once again, I said I know how to use these. I want to create my own negative embedding because I am unsatisfied with the negative embeddings I've been using.

    AI_IllusionistJan 20, 2024

    @xSatouMatsuzakax Are you using AUTOMATIC1111? This is official tutorial: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion

    1315085Jan 20, 2024

    @MySlientWind Much appreciation. I have only one question. I don't understand how to train a negative embed because they clearly use a whole bunch of images and then only have one trigger word for everything. Do I tag every image the exact same way even if it's multiple concepts? Like for the easynegative embed if I had made that would I have tagged everything with easynegative and just that, or would i have tried to tag everythign and added the tag easynegative to it at the start of my tagging?

    ahmadnjadm232Mar 8, 2024
    CivitAI

    🫂❤️

    NelmenJun 24, 2024· 7 reactions
    CivitAI

    I keep seeing this embed used on Pony models/checkpoints on here, but when I'm using auto1111 it won't load up... is there a way to make it appear? or does that GUI just not let you use embeds that are set to a certain model base?

    MisteltoeJul 5, 2024· 2 reactions

    in webui it won't show because this is made for sd 1.5. Which means it won't work with SDXL based models

    216396Nov 23, 2024
    CivitAI

    I;m confused, do I place it in Embedding?

    5184793Nov 29, 2024

    Place the file in the SD embedding folder then place the prompt in the negative prompts section

    216396Nov 29, 2024

    @jjhodges89 Ok thanks

    5184793Dec 1, 2024

    @Steeltron2000 Np. Took me a while to figure out embeddings as well

    216396Dec 1, 2024

    @jjhodges89 Do I make an SD folder for the Embedding folder?

    5184793Dec 2, 2024

    @Steeltron2000 You shouldn't need to make any folder it should be premade. Directory-wise it should just be webui>embeddings. I just used SD to refer to your Stable Diffusion folder as a whole sorry if I confused you

    216396Dec 2, 2024

    @jjhodges89 Ok, thanks.

    TextualInversion
    SD 1.5

    Details

    Downloads
    114,580
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/25/2023
    Updated
    5/15/2026
    Deleted
    -
    Trigger Words:
    By bad artist

    Files

    By bad artist -neg.pt

    Mirrors

    HuggingFace (188 mirrors)
    CivitAI (1 mirrors)
    TensorArt (1 mirrors)

    Available On (1 platform)

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