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
Inpaint Version for 1.8
FAQ
Comments (3)
I have 2 comments: (1). I may just be doing something wrong, but it feels like The output of this model is only amazing... sometimes. It seems like it is more demanding in terms of prompting than most other popular models. Or, it's just less likely to get great results. Whatever the case, I've been giving each new version a chance but end up switching back to others where I have greater rate of success. (2). For those unaware, inpainting models have been obsoleted by the Controlnet Inpainting model.
It's possible that it may require more specific or detailed prompts compared to other popular models. Since i rarely use other models (i created Juggernaut/StaVis to be my personal modell, so that i dont have to switch models) i can´t really compare. But you can check the gallerys under each version, there is a lot of output now...Some basic prompts, some more advanced...its both possible.
I can´t promise that you (personally) will have a better output in the future with Juggernaut. But i am gonna Redo Juggernaut from the Scratch with Version 2 (i guess in 2-4 weeks), and maybe it works better then for you :)
For the second one:
People ask me about it in the past, and since its no hard work i provide it to them for every version . I personally dont use it :D
also control net uses extra resources, limiting how many other controlnets one can use simultaniously, so its good to still have both options, thx for providing, kandoo<3
Details
Files
juggernaut_v18-inpainting.yaml
Mirrors
juggernaut_v2-inpainting.yaml
juggernaut_aftermath-inpainting.yaml
juggernaut_v21-inpainting.yaml
photomerge_v12-inpainting.yaml
photomerge_v10-inpainting.yaml
uberRealisticPornMergeURPM_urpmCE3Alpha.yaml
uberRealisticPornMergeURPM_urpmCE2Alpha.yaml
uberRealisticPornMergeURPM_urpmCE1Alpha.yaml
uberRealisticPornMerge_urpmv12-inpainting.yaml
animerge_v10-inpainting.yaml
juggernaut_final-inpainting.yaml
juggernaut_v19-inpainting.yaml
uberRealisticPornMerge_urpmv13Inpainting.yaml
juggernaut_v18-inpainting.yaml
juggernaut_v15-inpainting.yaml
juggernaut_v16-inpainting.yaml
juggernaut_v17-inpainting.yaml
juggernaut_v22-inpainting.yaml
juggernaut_v14-inpainting.yaml
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.