Declare: VirtualGirl series LoRA was created to avoid the problems of real photos and copyrighted portraits, I don't want this LoRA to be used with models containing real photos or copyrighted portraits.
宣言: VirtualGirlシリーズLoRAは、実際の写真や著作権で保護されたポートレートの問題を回避するために作成されました, このLoRAを実際の写真や著作権で保護されたポートレートを含むモデルで使用したくない.
선언: VirtualGirl 시리즈 LoRA는 실제 사진 및 저작권이있는 인물 사진의 문제를 피하기 위해 만들어졌습니다., 나는이 LoRA가 실제 사진이나 저작권이있는 인물 사진이 포함 된 모델과 함께 사용되는 것을 원하지 않습니다.
声明： VirtualGirl系列 LoRA 的创建是为了避免真实照片和受版权保护的肖像的问题， 我不希望这个 LoRA 与包含真实照片或受版权保护的肖像的模型一起使用.
VirtualGirl, Type-1, Aim
name: Aim
age: 1041 epoch
blood type: ChilloutMix
height: 768 pix
weight: 144 MB
body size: 128/1e-4/5e-5
name is Aim, means this girl born in AI data mixing
not a real person
no portrait right
welcome to merge
If you need help, you can join my dicord. On the help channel, I can accept questions in any language, but I can only use English, 日本語 and 中文 to help you.
If you like it, and if you want, you can buy me a coffee ☕
Description
Iterative training version for full body and reducing the weight of lora.
Now, you can draw Aim's face with only 0.3 weight and leave more weight to other Lora.
When drawing a full body, Aim's face shape is maintained as much as possible, but the side length of the drawn picture cannot be less than 1024 pixels, otherwise there will not be enough pixels to draw the face (which will cause face deformation).
I suggest to keep the v2.0 version. The upper body drawn in this version is still the best.
Thanks very much for everybody's support, thank you for pushing me to the Top100, you are my best partner!
Thank JustMaier in discord help me solve the problem that I can't upload images. You are great!