LoRA was trained on Flux images.

The LoRA model was created using 19 images taken from publicly available sources online.

LoRA was trained on the FLUX_1_Dev model.

CFG scale: 2-3.5, experiment with values.

Steps: 14-30, experiment with values.

Weight: 0.5-1.5.

Visible effects will begin to appear at values ​​of 0.5+.

Works well in the range (0.6-1.2), depending on your preference, experiment with weights up to 1.2. Experiment with values.

Depending on the model, LoRA's weight can be significantly increased.

High-quality hints reduce the negative effect.