🙏👍*** If you like it, like it! ***👍🙏

Based on the internet model Vyvan Le.

Experimented by using 300+ images to create this lora, capturing her face and body. Originally used 20 epochs, but found 14 epochs gave the best images.

The goal is to capture as much of the person as possible with my LORA. With little or no prompting the full body should appear. To ensure the face doesn't get lost, I make sure to train at least 1/3 of my LORA with high quality close-ups from varying angles and with varying expressions.

On ComfyUI, I've found anywhere from 3.5 to 7.0 cfg produce consistent results.