Iterative LoRA Training Model

Suggested tags for consistent results:

colette bg, blonde hair, blue eyes, capelet, choker, long hair, pantyhose, jewelry

Recommended settings:

• DPM++ 2M or Euler a

• Karras

• Sampling Steps: 25-35

• CFG Scale: 4-6

• Model Weight: 0.75-1 (I've had good success with weight 1)

I haven't attempted NSFW, but considering the tests that I've preformed, it should pan out.

As a personal preference, I generally use ADetailer for the faces of any generation, although this model is fairly consistent with it's accuracy.

I have had success with multiple Checkpoints, so anything you want to use, should be good.

I would love to see what you create with this LoRA. If you have any feedback, I'd be be interested in hearing it.

I'll be updating this LoRA as I better learn the process of creating them.