this LORA on the Illustrious-XLv0.1/NoobAI-XL (NAI-XL) training standard, it is recommended to keep the weights between -2 and +2 (usually). As shown in the figure, the function of this LoRA is to deepen/lighten the line art in the image. Different effects can be achieved by using positive or negative weights.

For different versions, please read About this version .

Compared to models like pony lineart adjuster, the artist name of the IL/noob series models has a significant influence on the model's style, and it will have some effect on the results of model adjustments.

Warning:

In some complex scenes or scenes with monotonous tones, this model may produce elements that differ significantly from the original image.

I might try to make adjustments later.

2024/12/08: try: add a model used "mult images" to train, improve generalization.