This LoRA was trained on full-body images, which tend to cause distortion in the eyes and hands. However, including 'upper body' or 'chibi' in the prompt can improve stability.
Additionally, since the training was done using images with a white background, the generated images are more likely to have a white background.
Please share your creations here!
描述:
训练词语:
名称: 732364_training_data.zip
大小 (KB): 11125
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: Shinra_Bansho_Style-000005.safetensors
大小 (KB): 223110
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
