Juggernaut XL
For business inquires, commercial licensing, custom models, and consultation contact me under [email protected]
Here I am again ;)
Before diving back into the details, I want to express a huge thank you to all of you. Over 40k downloads for Version 6 alone is absolutely amazing. It was a great pleasure to see your images in the gallery, and I hope the excitement continues seamlessly with Version 7 :)
A big thanks for Version 7 goes to RunDiffusion (Photo Model) and Adam, who diligently helped me test :) (Leave some love for them ;) )
For Version 7, I've slightly reduced the RunDiffusion Photo Model (from 0.35 to 0.3) and added a new Cinematic Set with 120k training steps. Additionally, I tinkered with some small details. Version 7 doesn't differ greatly from Version 6 but, thanks to its new update, it has significantly increased contrast (there were a few complaints about the desaturated look), and the lighting conditions appear somewhat more natural.
With the new Cinematic Set, this version is particularly well-suited for the newly released Stable Diffusion Video, so feel free to give it a try :)
Now, here are some additional tips to make prompting easier for you:
Sampler: DPM++ 2M Karras
Steps: 30-40
CFG: 3-7 (less is a bit more realistic)
VAE is already Baked In
And a few keywords/tokens that I regularly use in training, which might help you achieve the optimal result from the version:
Architecture Photography
Wildlife Photography
Car Photography
Food Photography
Interior Photography
Landscape Photography
Hyperdetailed Photography
Cinematic
Movie Still
Mid Shot Photo
Full Body Photo
I added also some Comparison Shot in the Gallery below and also some additional Images :)
And now, have fun trying it out. As always, I'm eagerly waiting for your pictures in the Gallery :)
If you liked the model, please leave a review. In the end, that's what helps me the most as a creator on CivitAI. :)
Last but not least, I'd like to thank a few people without whom Juggernaut XL probably wouldn't have come to fruition:
Dreamlook.AI (Trained 3 Side Sets)