该lora衣服的泛化性较差，但姿势方面的没问题，此外，他并不一定会生成3头图像（通过 3 heads 控制）,参考词请看例图。
The lora garment is less generalizable, but the pose is fine, and in addition, he does not necessarily generate a 3-head image (controlled by 3 heads), see the example diagram for the reference words.
Model reprinted from : https://civitai.com/models/354877/cerberusfortnite-or
Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.
