
V4 update note: I am sorry for being misleading earlier, but this is definitely the final version. This is simply the one character LoRA i wanted to make as good as possible, and the previous "final" version was undercooked.
Trained on AnyLora
To get the best results, please read the description below:
-
For V4.0:
-
Recommended weight: 0.7-1
-
Activation word: NamiFinal
-
-
For V3.0:
-
Recommended weight: 0.6-0.8
-
Activation word: NamiV3
-
-
For V2.0:
-
Recommended weight: 0.7-0.85
-
Activation word: NamiV2
-
-
For V1.0:
-
Recommended weight: 0.7-0.9
-
Activation word: NamiChan
-
-
Upscale to 1.5
-
To avoid her tattoo appearing on the right shoulder or on both, use such negative prompts as: (right shoulder tattoo, multiple tattoos)
I would appreciate any reviews, positive or negative!
If you have any suggestions on what LoRA i should do next, please share them in the comments
Enjoy :)
描述:
Version 2 - trained on 117 images
训练词语: NamiV2
名称: NamiV2.safetensors
大小 (KB): 36995
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success