Version 6.0

1. Use at 0.5-1.0

2. 99% for light skin colors to apply tan lines. (With minimal prompting)

3. Tested up-scaling up to 1024x1024 and 768x1280

Realistic Vision did better with Dark skin at 512x512 but had some issues up scaling. (Reduce Lora down from 1.0 when up-scaling with Realistic Vision)

Juggernaut Aftermath preformed better when up-scaling with LORA at 1.0

Version 5.0

This version was trained on AI images and caused issues with some models.

Version 1.0

This version was high rank and ignored clip in some cases.

Thank you for continuing to support my training addiction with your tip (By default I know) of just 1 buzz per generation while using this lora.

An example of my cost:

1. 11¢ per hour for training power consumption

2. 15¢ per hour for amortization of equipment cost over 3 years