CivArchive
    VanGoghBrushwork SD XL 1.0 - VanGoghBrushwork SDXL 1.0
    Preview 2824415
    Preview 2824410
    Preview 2824411
    Preview 2824412
    Preview 2824414
    Preview 2824416
    Preview 2824413
    Preview 2824421
    Preview 2824417
    Preview 2824419
    Preview 2824418
    Preview 2824420
    Preview 2824424
    Preview 2824422
    Preview 2824425
    Preview 2824428
    Preview 2824423
    Preview 2824429
    Preview 2824430
    Preview 2824427

    VanGoghBrushwork - Transforming Images into Van Gogh's Painted World


    Description:

    Introducing VanGoghBrushwork, an innovative LoRa (Text to Image) model that transports your ordinary images into the enchanting world of Vincent van Gogh's paintings. With VanGoghBrushwork, you can effortlessly infuse your visuals with the timeless brushstrokes and vibrant colors of van Gogh, creating a captivating artistic experience that echoes the genius of this master artist.


    Use trigger words: v0ng44g, p14nt1ng


    Trained on 3000 steps from a highly detailed by hand captioned large dataset.


    - Special thanks the people who help me and who I care a lot about:

    @MarkOREZ

    @masslevel

    @osiworx

    @mix

    @Thibaud

    @Kamikaze(Elon Musk)

    Description

    FAQ

    Comments (8)

    slickytailOct 12, 2023· 2 reactions
    CivitAI

    Hello, I'm working on creating a general-purpose oil painting model, and am in the data-collection phase. Is there any chance you'd be willing to share some of the training data? Thanks!

    Thaevilone
    Author
    Oct 13, 2023

    Hey there, thanks a lot for your support. :)
    For now I would like to keep it private to use in other projects such as SD 1.5 maybe.
    I can tell if you do a bit of searching it is not hard to obtain the whole dataset.
    However captioning them properly will take a bit longer. :)

    slickytailOct 13, 2023· 1 reaction

    @Thaevilone I totally understand, and I look forward to seeing what else you do with it. Yes, the captions are indeed the issue :)

    Thaevilone
    Author
    Oct 13, 2023

    @slickytail What can help a lot is to use the official art work: year and name into your captions.
    Ive done so with all van Goghs but forgot to mention you can do so lol.
    My upcomming one will also be able to do this and I will include the list this time.
    But more easy your could go to google, look up a art work you like and include it in the prompt to force the output more towards that input. :)

    slickytailOct 27, 2023

    @Thaevilone Ultimately what I settled on is, following the methodology of pixart-alpha, I used llava-generated captions, along with the title and artist. Works great !

    CrowyoteFeb 10, 2025· 1 reaction
    CivitAI

    This is hands-down the best LORA for acheiving Van Gogh like brushstrokes I've tried and it mixes well with others.

    Due to the elegance and refinement of my prompts I don't use this keyword, yet even without it it works fine.

    I hope that you can continue to create more excellent models around various artist if you can find the spare time and it's worth your effort.

    I think you could make the end-all-be-all painting model. Hit me up if you want to expand your training set for such a project, I have hard drives full of quality work of the old masters.

    Thaevilone
    Author
    Apr 5, 2025

    Hey there, thanks a lot.
    Yeah sure feel free to contact me via DM.

    CrowyoteApr 24, 2025

    @Thaevilone Awesome. Haven't been on in a while. I'll send ya word.

    LORA
    SDXL 1.0

    Details

    Downloads
    3,171
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/6/2023
    Updated
    5/11/2026
    Deleted
    -
    Trigger Words:
    v0ng44g
    p14nt1ng

    Available On (2 platforms)

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