CivArchive
    vector-art - vector-art-beta
    NSFW
    Preview 61832
    Preview 43590
    Preview 61830
    Preview 40494
    Preview 40507
    Preview 40506
    Preview 40505
    Preview 40504
    Preview 40503
    Preview 40502
    Preview 40501
    Preview 40500
    Preview 40498
    Preview 40496
    Preview 43583
    Preview 61829
    Preview 63887

    About model:
    Style model for Stable Diffusion mimicking "vector style". This model is open source so you can share, merge or use for monetization as you like (that will apply to other versions as well)

    License and support:

    If you like what I am doing and you want to support my current and upcoming projects: here is my coffee jar

    You can use this model as you like. I love open source so have fun with it. :) If you like it I appreciate your support ^^
    Cheers!


    Installation:
    As it is model based on 2.1 to make it work you need to use .yaml file with name of a model (vector-art.yaml). The yaml file is included here as well to download. Simply copy paste to the same folder as selected model file. Usually this is the models/Stable-diffusion one.

    Versions:

    There are two versions of this model - they both give a bit different output. Pulp one is great for "oldschool poster" stuff and comic book related. The vector-beta vanilla is more focused on mimicing vector style. (tshirt design, vector-style posters and stickers). I am working on tshirt and sticker model now -so this one will get a general update next time to be more vector-focused but giving more versatile results and styles as well.

    Black images issue:

    2.1 models need to have a web-ui config modified - if you are getting black images - go to your config file and add to COMMANDLINE_ARGS= --no-half - potentially it could work with --xformers instead (if supported). This line might slow your generations a bit but will not affect negatively your output.


    Other:
    The model has been trained the way it is not overfitted and same time give you it's strong style.

    Try-out some prompts below, dont be afraid to use different encoders:

    Example prompts:

    portrait of a very handsome man made of fruit by guiseppe arcimboldo and greg rutkowski, donato giancola, joseph christian leyendecker, wlop, boris vallejo, breathtaking, 8 k resolution, extremely detailed, beautiful, establishing shot, artistic, hyperrealistic, beautiful face, octane render, cinematic lighting, dramatic lighting, masterpiece by vector-art

    `e-sport logo illustration of a spectral gorilla-punk in astronaut suit by guiseppe arcimboldo and greg rutkowski, donato giancola, joseph christian leyendecker, wlop, boris vallejo, breathtaking, 8 k resolution, extremely detailed, beautiful, establishing shot, artistic, hyperrealistic, beautiful face, octane render, cinematic lighting, dramatic lighting, masterpiece by vector-art`


    Negative prompt: low poly, tetric, mosaic, disfigured, kitsch, ugly, oversaturated, grain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, mutilated, mangled, old, surreal, pixel-art, black and white, childish, watermark

    Separated subjects:

    `die-cut sticker illustration of monk skateboarding, full body on black background, standing, cinematic lighting, dramatic lighting, masterpiece by vector-art, apparel artwork style by vector-art`

    `black eagle on a light background vector-art, cinematic lighting, dramatic lighting, masterpiece by vector-art, apparel artwork style by vector-art`

    Negative Prompt:

    low poly, tetric, mosaic, disfigured, kitsch, ugly, oversaturated, grain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, mutilated, mangled, old, surreal, pixel-art, black and white, childish, (((watermark))), (((dreamstime))), (((stock image)))

    Stickers:

    ((die_cut sticker)) colored punk animal illustration, die_cut sticker in style of vector-art

    ((die_cut sticker)) colored tiger illustration on white background, centered, die_cut sticker in style of vector-art


    Negative prompt: low poly, tetric, mosaic, disfigured, kitsch, ugly, oversaturated, grain, low-res, Deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ugly, disgusting, poorly drawn, mutilated, mangled, old, surreal, pixel-art, black and white, childish

    I will add some more interesting prompts here.

    Img2Img:

    Keep things simple, use negative. There are some screenshots with examples and prompt part. Experiment with generated images.

    Description

    FAQ

    Comments (24)

    CCPCJan 16, 2023
    CivitAI

    Can you make possible to generate directly into a vector?

    pmejna
    Author
    Jan 16, 2023· 2 reactions

    Not really. This is just style model. I think that there is an extension for Automatic1111 which can do that. I haven't tried it yet.

    evelryuJan 16, 2023· 2 reactions
    CivitAI

    You are amazing man.

    juvesatrianiJan 16, 2023
    CivitAI

    So we can use this one without special Yaml ?

    pmejna
    Author
    Jan 16, 2023

    Unfortunately still needs yaml file. You can get it from here: https://huggingface.co/irateas/vector-art/tree/main or just copy one from any 2.x SD model and rename it ;)

    juvesatrianiJan 16, 2023

    thanks for information

    zhalimutoJan 16, 2023
    CivitAI

    I have got, error"The most likely cause of this is you are trying to load Stable Diffusion 2.0 model without specifying its connfig file.

    See https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20 for how to solve this.' and I downloaded yaml file as well, didnt work

    zhalimutoJan 16, 2023· 3 reactions

    nver mind, rename the yaml file, hope other people will notice this trick

    pmejna
    Author
    Jan 16, 2023· 1 reaction

    Thx for noticing - I have added instruction and link to yaml file (civitaai supports only model)

    mnitantJan 16, 2023· 3 reactions
    CivitAI

    safetensor?????

    pmejna
    Author
    Jan 16, 2023

    I have updated repo so there is safetensor file now as well

    mnitantJan 31, 2023· 1 reaction

    thank you so much its really nice

    Mike67Jan 16, 2023
    CivitAI

    How to download this model to google colab?

    pmejna
    Author
    Jan 16, 2023

    the best would be to copy model + yaml file (included now) to your google drive and connect to colab - then point to the file ;)

    Mike67Jan 16, 2023· 3 reactions
    glupazooJan 26, 2023

    @Mike67 you can also add -O /content/gdrive/MyDrive/sd/stable-diffusion-webui/models/Stable-diffusion/"nameofthemodel.safetensors" and download directly on your Gdrive :)

    Nix0npolskaJan 16, 2023· 1 reaction
    CivitAI

    That's great model! Good balance between style and prompts used. Not overtrained (based on a few generations I did for myself).

    Can you possibly share your fine-tuning method and parameters used? (Local Dreambooth or collab notebook or maybe sth else)

    pmejna
    Author
    Jan 16, 2023

    Thx mate :)

    saldiamneoJan 17, 2023
    CivitAI

    What denoising would you recommend to transform photos into vector on img2img?

    pmejna
    Author
    Jan 17, 2023

    I would start with about 68-78 ;) - you can try loopback script in your Automatic1111 - this might help as well

    DFDKJan 21, 2023
    CivitAI

    Thanks for this. I am using Stable Duffusion Automatic1111. I placed the Check Point and yaml file in models/Stable-diffusion. The interface recognizes the Check Point however on Generate the script just closes. Any ideas?

    Thanks

    DFDKJan 21, 2023

    Found the error :-) NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try using --no-half commandline argument to fix this.

    --no-half didn't help

    DFDKJan 21, 2023

    Picked up the fix from another comment here. Renamed vectorArt_vectorArtBeta.ckpt to vector-art.ckpt and vectorArt_vectorArtBeta.yaml to vector-art.yaml fixed it.

    DFDKJan 21, 2023

    Check that. Not working

    Checkpoint
    SD 2.1 768

    Details

    Downloads
    11,460
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/16/2023
    Updated
    5/11/2026
    Deleted
    -
    Trigger Words:
    vector-art

    Files

    vectorArt_vectorArtBeta.ckpt

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    vectorArt_vectorArtBeta.yaml

    Mirrors

    CivitAI (83 mirrors)

    Available On (1 platform)

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