CivArchive
    Preview 986037
    Preview 986038
    Preview 986040
    Preview 986043

    SURPRISE ;)

    Merry Christmas, everyone.

    As a little Christmas gift for you all, I've been working on a new version for the SD 1.5 version of Juggernaut in my spare time for the past few weeks.

    I took a small portion of the JuggernautXL dataset and trained it on SD 1.5 (Base Juggernaut Final), while also updating the epiCRealism model in the merge. However, the RPG and Diva models that were added in the 'Aftermath' version have been removed.

    Images were created with the following settings:

    512*768

    Sampler: DPM++ 2M Karras

    Steps: 35

    CFG: 7

    HiRes Fix:

    Sampler: 4xNMKD Siax 200k

    Steps: 15

    Denoise: 0.5

    Upscale: 2

    Lastly, the recipe for the last Juggernaut (Aftermath) version on SD 1.5:

    SD 1.5 Base

    Training Set 1 (0.65)

    Absolute Reality (0.18)

    epiCRealism V3 (0.2)

    Humans (0.15)

    Skin Enhancer (0.15)

    Better Portrait Lighting (0.2)

    Training Set 2 (0.55)

    RPG 5 (0.38)

    Divas (0.15)

    And of course the NinjaFix made by @chillpixel

    Thanks all those Creators for their hard work :)

    Of Course you can run "Juggernaut" on Tensor.Art

    Description

    Inpainting for Version 1.9

    FAQ

    Comments (5)

    SerenityXMay 31, 2023· 1 reaction
    CivitAI

    I have a question about the config file. I use InvokeAI, and convert all models to their diffusers format (loads quicker, less GPU load, faster output).

    Do I still need the yaml file? I did search both on Google, and Invoke's Github, but couldn't find an answer...

    KandooAI
    Author
    May 31, 2023

    You just need the yaml file if you get bigger errors at the image generation...like artifacts or black squares...In 99 % you don´t need the yaml File

    SerenityXJun 1, 2023

    @KandooAI Awesome, thanks! 😁

    KandooAI
    Author
    Jun 13, 2023

    @kashiman290 Since i use it on Colab i cant say for sure. But in your Automatic1111 Folder Structure there should be a Folder called "Config" or "Configs", and thats the place for the .yaml File

    SerenityXJun 13, 2023

    @KandooAI I found InvokeAI doesn't need them if models end up as diffusers... 😁