
!!! 제작자와 상의 없이 이미지 제작 판매 및 이미지 생성 서비스 등 다양한 특수 목적으로 무단 사용하는 사례가 너무 많습니다.
!!! 해당 데이터는 개인 사용자가 비영리 목적으로 사용하는 것을 목적으로 공유하고 있으며, 별도의 서비스나 이용에 대해서는 제발 제작자와 먼저 상의해주시길 부탁드립니다.
You may not use it for commercial purposes other than personal use.
LoRA for women's hanbok has a high amount and stability of datasets, and is relatively well normalized, so it can be used comfortably in various environments.
It provides stable image output without screen tearing even at the basic weight of 1.0, and it is LoRA with a high reproduction rate of hanbok even in the weight range of 0.5 or more.
In particular, it works well regardless of real/semi-realistic/anime models, and it can be used in various environments with relatively little noise and chromatic aberration.
Recommended trigger: hanbok
描述:
In Anithing and Abyss series of animation style models where the existing LoRA would create an image without a separate appearance prompt, the face style was fixed.
To improve this, the female face normalization data was refined again so that various types of facial expressions could be generated.
Along with this, the phenomenon that the hairstyle was fixed with a side parted hair and the phenomenon that the hair accessories were overexpressed has been improved.
In order to correct this phenomenon, we manually modified all the hair parts of the existing dataset photos and images.
Now you can freely express your face style, expression, and hairstyle.
In addition, the newly shared LoRA doubled the learning rate compared to the previous LoRA, and deliberately overfitted it.
This is a part that has been adjusted to be advantageous for combination by lowering the weight when used in combination with other models or LoRA.
The advantage of low weight is that it can suppress image breakage caused by model characteristics or LoRA combinations.
Even if various prompts are applied, it has the effect of responding to stable image generation.
Recommended trigger: hanbok
Recommended weight: 0.3 ~ 0.8 (The default value of 1 can be used, but chromatic aberration, such as image breakage, becomes more pronounced.)
训练词语: hanbok
名称: hanbok_w_v10.safetensors
大小 (KB): 147573
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success