CivArchive
    AllWorkForkRowk_InProgress_(SD2.1) - V0.2_Gamma_(FasterLR)_512
    NSFW
    Preview 2273318
    Preview 2273321
    Preview 2273320
    Preview 2273319
    Preview 2273323
    Preview 2273322
    Preview 2273325
    Preview 2273324
    Preview 2273328
    Preview 2273327
    Preview 2273326
    Preview 2273329
    Preview 2273592
    Preview 2273594
    Preview 2273595
    Preview 2273593
    Preview 2273596
    Preview 2273597
    Preview 2273598
    Preview 2273599

    USE THE NEW EMBEDDING!!!

    Completed.

    Although the model is far from perfect, this is where this particular experiment ends.

    I'll start over with a different training method.

    The final version can handle decently 1024x1024 resolution for most of its concepts.

    Right now I don't feel like posting the "keywords" the model was trained on, maybe I'll suffice later.

    Description

    Overall improvement, overfitting in the characters it had learned about, I'll fix it later and provide the list of the characters.

    FAQ

    Comments (14)

    sandro609Aug 30, 2023
    CivitAI

    SDXL version?

    Redigleb_Doppler2482
    Author
    Aug 30, 2023

    I don't have the hardware for SDXL, unfortunately.

    Redigleb_Doppler2482
    Author
    Aug 30, 2023

    But if anyone is interested I can provide a part of the dataset, maybe some people can train a SDXL model with my data.

    sandro609Aug 30, 2023

    I'm still very much a noob with all of this, I might get back to you once I've figured out how to do it :)

    Redigleb_Doppler2482
    Author
    Aug 30, 2023· 1 reaction

    @sandro609 By the way, even if it's not possible for my hardware to train a SDXL model, it is possible to have a SD2.1 in 1024x1024 resolution, and it is in my plans to do so. Are you interested? I might give it more priority if you stick around.

    ScreamingMurphyAug 30, 2023· 1 reaction
    CivitAI

    This is actually the first SD2.X model that has caught my interest. I'll play around with it a bit and leave a review with some images once I have some gens I am pleased with. Thanks for your hard work creating this!

    Redigleb_Doppler2482
    Author
    Aug 30, 2023

    It's quite unstable right now, but it has potential. It's recommended to use the embeddings, but they are just shortcuts for complex negative prompts that can be achieved with some patience. Thank you for showing up, I might also fine tune things on request on this model, let me know.

    Redigleb_Doppler2482
    Author
    Aug 31, 2023
    CivitAI

    I'll take a pause from this model, I worked all august on this. I hope that the people that can't run SDXL will find something good in ForkRowk, right now it has:
    1) better sharpness than most SDXL fine tunings.
    2) better prompt understanding than most SD1.5.
    3) completely uncensored text encoder, potentially better than most NSFW SD2X on CivitAI

    gsgsdgAug 31, 2023
    CivitAI

    I'll try to train a lora on this model, i have some computing units left on colab and i want to see if it can handle them. If so, we might have the best 2.1 model around.

    Redigleb_Doppler2482
    Author
    Sep 3, 2023
    CivitAI

    Looks like this model did not get much attention, I'll soon upload another version but I might as well stop there, seems like it's not worth the trouble.

    PanBacchusNov 8, 2023· 1 reaction
    CivitAI

    Maybe make a 1024 by 1024 or 768 by 768 version? Your model seems interesting.

    gsgsdgNov 14, 2023

    By golly we need this man to come back and continue the tuning on this ckpt

    Redigleb_Doppler2482
    Author
    Nov 21, 2023· 1 reaction

    I tried.

    gsgsdgNov 21, 2023

    @Redigleb_Doppler2482 YOOOOOOOOOOOOOOO

    Checkpoint
    SD 2.1 768

    Details

    Downloads
    491
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/29/2023
    Updated
    6/12/2026
    Deleted
    -

    Files