The wild journey continues with Juggernaut, but this time based on SDXL. Just like with Juggernaut's SD 1.5 version, I will take you on the entire journey, so Juggernaut's output will change significantly over the next updates.

Time for Version 5

First and foremost, I would like to thank you for now over 100k downloads on CivitAI (all my models combined) and over 500k runs on Tensor.Art. These are numbers that completely blow me away and constantly amaze me :)

With Version 5, I present to you a more stable and qualitatively superior version of JuggernautXL. For the first time, I am providing you with the 12 GB file, in case you plan to train based on Juggernaut. Version 5 is the first version where I feel the community could train effectively with it. Of course, the pruned 6 GB version is also included :)

The new side set focusing on architecture, landscapes/backgrounds was trained again with the help of Dreamlook.ai. Moreover, the base model received its final touch, and we have now achieved 600k steps.

However, updates will become a bit scarcer now. Next, I want to return to the core theme of Juggernaut (Cinematic) and train a new and larger model and eventually integrate it with Juggernaut. This will take more time than the recent update pace ;)

The Examples are the first Output. I just HiRes Fixed the images to get you better looking ones :D

Cant wait to see your output in the Gallery Section :)

Last but not least, I'd like to thank a few people without whom Juggernaut XL probably wouldn't have come to fruition:

ThinkDiffusion

RunDiffusion

Dreamlook.AI (Trained 2 Side Sets)

Chillpixel

SilasAI6609