Using the style lora dataset originally trained on SDXL, completely different results were achieved. Not sure why, but it worked to some extent and could be used to test lora usage in sd3.
Below is the effect of this dataset in sdxl
描述:
训练词语: black light style
名称: bl_64.safetensors
大小 (KB): 73752
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接：https://1111down.com/1075313.html，转载请注明出处
