This is a stylized Lora that uses regularization training to avoid overfitting, allowing for the use of weights greater than 1. Its generalizability is extremely strong and it is suitable for all large models.
Usage recommendations:

1. CLIP termination layer: 2
2. Weight range: 0.5 to 1.5, recommended using 0.7, above 1.1 will gradually develop a gentle style!
   Example graphs I used three large models for demonstration, respectively for simplified 2D, 2.7D fantasy, and realistic writing
   Recommended using "lbc_Simple_simplified", "lbc_Fantasy_fantasy_2.7D", or "lbc_Realistic_realistic" large models for better results.
   If you like my trained model style, please give me plenty of likes! I'm grateful beyond words, if you want to train a specific style or character, feel free to leave a comment below, and I'll be happy to help you for free, sharing beautiful things together!
   For conditionally-privileged friends who want to download other models that are not suitable for release in mainland China, please go to C-site support: https://civitai.com/user/fuaneng/models