A 2d anime LoRA model for vflower.
base model: NovelAI 7G
example images are generated with Anything-4.5 and MeinaPastelV2
prompt: vflower, <lora:vflower_v2:0.6>, purple hair
PS: the prompt "purp hair" is needed because some models seems to paint the hair pure white.le
虚拟歌手 花花的模型
基于NovelAI 7G训练
效果图使用Anything-4.5和MeinaPastelV2生成
prompt: vflower, <lora:vflower_v2:0.6>, purple hair
我测试当中发现头发默认是白色的,所以需要加上"purple hair"这个prompt增强效果
V2 and V1 differences:
less watermarks ( at least doesn't occur in conspicuous place )
needs less prompt
better effect?
V2和V1的区别:
去除了水印 (至少不会出现在显眼的地方)
需要更少的prompt
可能有更好的质量