
Place in Negative Prompt. Can weight as high as :3 but I would stay around :1 - :1.6
As it is trained on flaws.
example :
Prompt: 1girl, twintails, lipstick, glasses, smirk, medium breasts, slender, boots,
Negative Prompt: low quality, <lora:Negative_LoraV1.13-000005:1>
Yes you can negative weight in the postive prompt but it changes the whole image if you go to far.
This is an experimental tool, when you have a pic you like but has minor flaws. You use same seed and regen. I use it from the start in negative prompt and go all willy nilly.
To each their own.
Don't normally share training data, but figured anyone interested would want to see how nuts on went on the concept.
描述:
训练词语:
名称: 1161696_training_data.zip
大小 (KB): 41820
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: Negative_LoraV1.13-000005.safetensors
大小 (KB): 223137
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success