
This is a mix of different artist styles from NAI, the mix is :
[artist:ningenmame], [artist:ciloranko], [artist:sho{{sho_lwlw}}], [[artist:tianliang_duohe_fangdongye, artist:as109]]
Dataset of around 60 images made from NAI with that artist mix, each images was then reworked and any issue was fixed with either inpainting or GIMP.
Tagging was done using the structural settings with PromptGen v1.5 large model and reviewed manually.
There is no trigger word. But if the result looks too realistic, just add "in a manga style" and that should fix it.
The training settings (you'll need at least 24Gb vram for it) and captions I used can be found in the training data zip, training was done with LoRa_Easy_Training_Script.
Sometimes body proportions are a bit weird legs/torso, hands tend to not look that good on far shots, inpainting works well to fix those issues.
描述:
68 images, 3repeat, batch 6
训练词语:
名称: yue_v2_2.safetensors
大小 (KB): 149729
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: yue_v2_2.zip
大小 (KB): 7
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success