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.転載モデルは学習・共有目的のみで使用し、著作権は原作者に帰属します
2.モデルの認証は公式チャンネルでご連絡ください。クリエイターの権利保護に努めています クリックして認証
