I wouldn't say this is better or worse than the v2 but more like a different version of it, but I'm releasing it in case anyone wants to give it a try.

I'm releasing this separately from the main caucasian men lora because it's a bit different.

This needs more strength than the actual v2, but it depends on the image, I'd say start at 0.7-0.9. You should also be more descriptive of what the man looks like.

There are 2 main reasons I made this:

1. more diverse outputs

2. work better with other loras

This may output:

1. worse anatomy

2. less handsome men than the actual v2

In the sample images id say the generated images are mostly 1-3 chosen out of every 3-6 images. This should work better with other loras than the actual v2. The reason this can be worse at ??????? is because technically im pretty sure its undertrained. I don't recommend using low CFG but it can output nice images every so often.

And thank you for the support on the actual v2!