Larger training set, better captioning.


Olivia Wilde, born 1984 in New York City is an American actress, director, and producer. v2.0 was trained on 154 publicly available photos in various SDXL compatible resolutions.
Recommendations
Use trigger oliviawilde and LoRA weight 1.0.
Photorealistic models such as LEOSAM's HelloWorld tend to produce the best results.
Trained with Clip Skip 1, results without Clip Skip vary.
Negative prompt (eye) makeup, mascara may be helpful.
CFG values between 3 and but 8 seem to be fine.
v1.0 was trained on 66 publicly available photos in 1024x1024, 896x1152, and 832x1216.
Recommendations
Use trigger oliviawilde and LoRA weight 0.9 - 1.0.
Photorealistic models such as LEOSAM's HelloWorld tend to produce the best results.
Trained with Clip Skip 1, results without Clip Skip vary.
Negative prompts earrings and (eye) makeup may be needed.
I didn't do much testing with CFG values, but 8 seems to be fine.
Larger training set, better captioning.
1. Quyền đối với các mô hình được đăng lại thuộc về người sáng tạo ban đầu.
2. Người sáng tạo gốc muốn xác nhận mô hình vui lòng liên hệ nhân viên SeaArt AI qua kênh chính thức. Nhấp để xác nhận
