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
My First Baked VAE Version.
I have tried several VAEs to see what would be the best fit for Juggernaut.
Since Juggernaut's focus is photography, I ultimately decided on the Tone Range Compressor VAE.
The softer contrast is perfect for photography. The whole thing works semi well in the artistic part.
If you're not satisfied, simply switch back to the original version 2.2 :)
FAQ
Comments (7)
I clicked that link to chillpixel's profile but I don't see anyhting called NinjaFix. Am I missing something? Did he rename it?
NinjaFix is baked into Juggernaut already. The model got the "fix" before being uploaded to CivitAI. There's nothing else to download. You have it now, inside Juggernaut! 🍻
@chillpixel Right on, thanks
Incredible work as always. I just have to weigh in and say I do actually prefer it without the Tone Compression baked in.
I agree with all the points you make about how it lends itself to realism to a degree, I just figure if I'm going for that particular look, I can always just modify that after the fact, rather than it be the default.
But yeah, like I mentioned before, incredible work, one of the best models around!
Totally fine with it :) I personally like the normal one also more. I was asked couple of times to do a version with a baked VAE inside of it. I tested a lot of VAE Types...but most of them didnt do anything for Juggernaut or just a tiny bit. And i wanted to provide a version that gave you an alternative Option to the normal one.
What is the config needed for? and where does it go.
I don´t know which UI u use. For example in Automatic 111 there should be a Folder called "Config" or "Configs", and thats the place for the .yaml File. But the .yaml File is really not needed in most cases...just if you have the feeling something is really wrong (artifacts, black square images, noise images)
Details
Files
v1-inference.yaml
Mirrors
matrixHentaiPlus_v231.yaml
theoneabovethemall_v10.yaml
PornMasterV1-pruned-FP32.yaml
Refined_v11.yaml
PornMaster-Fantasy-FP32.yaml
PornMaster-fantasy-FULL.yaml
v1-inference.yaml
PornMasterV1-pruned.yaml
PornMaster-AsianV1-FULL.yaml
Refined_v11_Dark.yaml
Dream-Factory.yaml
Pop-Factory.yaml
A-Zovya_Photoreal-V1-Ultra.yaml
v1-inference (3).yaml
Based_v1.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
PornMasterV1-FULL.yaml
v1-inference.yaml
v1-inference (1).yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
v1-inference.yaml
PornMaster-AsianV1-pruned-FP32.yaml
PornMasterAsianV1FP16.yaml
v1-inference (1).yaml
PornMaster-Fantasy-FP16.yaml
Visionary.yaml
Sweet-Factory.yaml
am i perfection v2.yaml
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.













