PDXL Version

Not much to say here other than it's a retrain of an old model. If you're curious about the last image it was made by accident while trying to get non-portrait shots. I just included portrait in the negative and got some weird burnt outputs, but they also looked cool so I included one for reference. Anyway, enjoy!

SD 1.5 Version

Another old LoRA I never posted. Sort of painterly?

Note: The "nipples" negative should be unnecessary. It was left in from before.

Why doesn't my output look like yours?

1. Check the negatives in my examples. Do you have those embeds?

2. I used !ADetailer because it's just a set and forget quality bump.

3. The images were genned at 512x768 then upscaled 1.5 times using 8x_NMKD-Superscale_150000_G with denoising 0.45. You can find it with a quick Google. Note that this upscaler is non-deterministic from my testing so your images may vary slightly. (Check the bottom of this post for info on the cover image.)

Settings and Training:

Trained on Anything v3
Genned on Anything v4.5
LoRA weight 0.8

描述:

initial release

训练词语: