The LoRA model was created from 50 images taken from the public domain on the Internet.

LoRA was trained on the FLUX model

CFG Scale: 2.0 - 3.5 experiment with the values

Steps: 14 - 22 experiment with the values

Weight: 0.3 - 1.

Works well with weight: (0.8 - 1), experiment with weights up to 1.3

It depends on the model, but you can raise the Lora weight quite high.

High quality prompts reduce the negative effect.