
V3 update note: This is the Final version. From the time i posted the previous version of this LoRA i have gained experience on how to make my LoRA's better, so this is me fixing my previous mistakes. All models of main/side-main characters of One Piece will receive a similar amount of attention from me :)
Trained on AnyLora
To get the best results, please read the description below:
-
For V3.0:
-
Activation word: NicoRobinV3
-
Recommended weight: 0.6-0.8
-
-
For V2.0:
-
Activation word: NicoRobinV2
-
Recommended weight: 0.7-0.9
-
-
For V1.0:
-
Activation word: NicoRobin
-
Recommended weight: 0.7-0.9
-
-
Upscale to 1.5
I would appreciate any reviews, positive or negative!
I would very much appreciate you sharing your results ^_^
If you have any suggestions on what LoRA i should do next, please share them in the comments
Enjoy :)
描述:
Version 2:
-
improved dataset quality and quantity of images
-
Trained on 83 images
-
improved model training resolution (512 -> 1024) for better details
训练词语: NicoRobinV2
名称: NicoRobinV2.safetensors
大小 (KB): 36992
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success