CivArchive
    Preview 1498247
    Preview 1498249
    Preview 1498261
    Preview 1498516
    Preview 1498248
    Preview 1498250
    Preview 1498437
    Preview 1498251
    Preview 1498268
    Preview 1498420
    Preview 1498508
    Preview 1498651
    Preview 1498686
    Preview 1498728
    Preview 1500250

    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

    30k more Steps.

    Also the NinjaFix got updated for Juggernaut

    FAQ

    Comments (14)

    xixxixJul 10, 2023· 3 reactions
    CivitAI

    You did really great work with this one, thank you!

    KandooAI
    Author
    Jul 10, 2023· 1 reaction

    Thank you very much :)

    bamboochaJul 10, 2023· 1 reaction
    CivitAI

    The model looks amazing! Just a question: is the final version with baked in VAE and if yes, do you plan to release a non-VAE version? Training loras is better without a VAE in my experience.

    KandooAI
    Author
    Jul 10, 2023· 3 reactions

    It´s without the VAE, i upload the Baked Version in 2-3 Days

    513820Jul 10, 2023· 4 reactions
    CivitAI

    Man it feels like the end of an era, kind of a sad day, all these great models being ended in anticipation of SDXL. It better make our waifus good, or it will go the way of SD2x lol

    KandooAI
    Author
    Jul 10, 2023· 5 reactions

    I guess we will see at the End of the Month if model creators like me can finetune the base model to do the NSFW Stuff...otherwise it will fail like SD2x

    sophialynJul 10, 2023

    heard it takes a lot of power to even run it, so i don't see it becoming anything special anytime soon.

    DukeNukem47Jul 10, 2023· 5 reactions

    @KandooAI yes, if it cant do NSFW then it will fail and become obsolete as did SD2 and stability will be set backwards greatly because of that error in terms of keeping up with midjourney. people only put work into models that people download,support and use. No use for the community if its another woke censored attempt. nobody will bother it.

    CK_GENERALJul 11, 2023· 4 reactions
    CivitAI

    I am using it to create Japanese. I don't know if the author intended It is very convenient to be able to create more realistic Japanese than you can imagine.

    KandooAI
    Author
    Jul 11, 2023· 1 reaction

    Didnt intend that...i didnt focus any nationality....so all should be equal :D But glad Japanese ones are working well for you :)

    zeeyuJul 11, 2023· 4 reactions
    CivitAI

    thanks for what you do for this model,it's my main model in my work,it's really helpful,hope you can keep creating more intresting stuff,looking forward to meeting next time!

    darammsammsammJul 12, 2023· 1 reaction
    CivitAI

    Very good results, thank you for the checkpoint!

    I do have some questions though:

    - I assume the current "Final" version is without baked VAE?

    - Will there be an inpaint-version of "Final"?

    - Is there a non-pruned version without baked VAE to allow LoRA-training?

    Thank you and sorry if those questions have already been answered without me noticing.

    KandooAI
    Author
    Jul 12, 2023· 1 reaction

    1. The Baked VAE Version for the Final one is gonna be released in the next couple of day (2-3 Days)

    2. The Inpaint Version will be released in the next 24 hours :)

    3. The current Version with the Filesize (5,28 GB) is non-pruned and without a baked vae. I always put up 2 Files when i upload a new Version. The Non-Pruned one (With the bigger Size) and the Pruned Version (Most of the times 1,99 GB big)

    darammsammsammJul 13, 2023· 1 reaction

    Great, thank you! (And for your fast and helpful response, too :) )

    Checkpoint
    SD 1.5

    Details

    Downloads
    16,915
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/10/2023
    Updated
    5/14/2026
    Deleted
    -

    Files

    juggernaut_final.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    Available On (3 platforms)

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