This lora trained on Luma and i can't guarantee that it will work properly with other models.
Why it's trained on Luma? Cause it's my daily basis model, that i want to make a multifunctional tool, so some styles i will train only on Luma for best compatibility with this model.
Trained with Clip Skip 2.
Recommended embeddings: 1. easynegative 2. bad-hands-5 3. badhandv4 Recommended extensions: 1. AutoChar 2. AfterDetailer Strength 0.6-0.8 is optimal.
Useful Tags: outline in the end of simple short prompt for more flat images. simple background, white background for white background, duh. (useful for full-body concepts) night, dark atmosphere, dark scene for extra contrast. realistic for less-flat and more-3d look. blurry background, bokeh for better character focus.
PLEASE CHECK YOUR LORA NAME AFTER DOWNLOAD.
This lora works well without any trigger word, but you may use nijistyle to increase strenght of it.
ENJOY AND SHARE YOUR FEEDBACK.
