转载自作者：KandooAl
For business inquires, commercial licensing, custom models, and consultation contact me under juggernaut@rundiffusion.com
Update: Try out the Inpaint for V8 from sevenof9247
A big thanks for Version 8 goes to RunDiffusion (Photo Model) and Adam, who diligently helped me test :) (Leave some love for them ;) )
And here I am again :),
today, let's dive straight into the details.
Please read the following text so you have an idea of what to expect with V8 :) :
The focus for V8 was on hands, feet, skin details, and photographic output. However, hands and feet are an ongoing project and are far from perfect in V8. In a direct comparison with V7, we did notice an improvement. Ultimately, I didn't want to keep you waiting any longer and can at least show you the initial progress in this direction :)
Another important focus was on skin details and the overall photographic output. Common skin details should now all be present (freckles, moles, dirty skin, sweat, pure skin, scars, acne, and so on). For the past two days, the model has already been running on RunDiffusion, and the initial feedback has been positive :)
Regarding NSFW content: When CivitAI transitioned its Generation Service and Juggernaut became the only NSFW model to generate with, it came as a bit of a surprise to me. I was already deep into the work on V8. Therefore, there won't be a significant content update in the NSFW area for this version. However, I will provide that with V9 :) But do not expect explicit NSFW material; Juggernaut will not evolve in that direction.
Regarding Turbo & DPO Model: I'll briefly touch on this since it's a question that comes up from time to time. It is not planned in that direction. Never say never, but in the near future, you shouldn't expect anything in that direction.
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)
Negative: Start with no negative, and add afterwards the Stuff you don´t wanna see in that image. I don´t recommend using my Negative Prompt, i simply use it because i am lazy :D
VAE is already Baked In
HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise
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
Skin Details
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)
Hide
Suggested Resources
为了尊重作者，我原文复制，也不加自己的联系方式。有条件的，希望到原作者下载，因我深知很多人下载不了，特意转载。
V8的重点是手、脚、皮肤细节和照片输出。然而，手和脚是一个正在进行的项目，在V8中远非完美。
另一个重要的焦点是皮肤细节和整体的照片输出。常见的皮肤细节现在都应该出现了(雀斑、痣、脏皮肤、汗液纯皮肤、疤痕、控疮等)。
