EDIT:
Version 3 is here. I added 100 new sci-fi themed images and re-trained model with the entire dataset (800 images), 30000 steps, 8 epochs.
CFG sweetspot - 4
Version 2:
This is a pure Finetune, trained in 2 iterations so far, 12 epochs and about 20000 steps on nvidia RTX A6000. I will definitely continue to work on it. I have (intentionally) generated all images without high-res fix, so that you can have a better insight into the basic capabilities of this model.
Negative prompts are not necessary, i advise you to experiment with them.
In addition to captions, the model is also trained with tags. which have strong impact on image generation. For example, a large part of the dataset consists of images of ninja and samurai warriors, and they are tagged with: ninja style, samurai style, ninjutsu, katana, buddhist.
1st iteration: dark style, darkness, fantasy, gothic, horror
2nd iteration:
fantasy style, dark, surreal, horror, epic
ninja style, samurai style, ninjutsu, katana, buddhist
CFG sweetspot: 4-6
U can support my work here:
https://www.buymeacoffee.com/nenadkuzmao
Description
SDXL 1.0
FAQ
Comments (4)
Going early access could hurt the visibility and ratings of a model. I gave it a 5 star because it looks like pretty cool and I think it deserves it. Hope you get more views!
Not really. LMAO Making it early access allows those who are willing to donate and help the creator. Don't be so selfish.
Cool model! Nice to see some variety in style, thanks
I'v added 100 more new pictures (weird sci-fi) to dataset and started new training with all images from previous 2 training phases. 800 images, 28315 steps in total, 24hours training. It will be more consistent and less cfg sensitive. You can try it in 14 hours
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.