santa hat
deerdeer nosedeer glow
Sign In

blindbox/大概是盲盒

13.8k
164.6k
742
Updated: Oct 5, 2024
styleanimeartstylechibicute
Type
LoRA
Stats
5,674
Reviews
Published
Apr 17, 2023
Base Model
SD 1.5
Hash
AutoV2
976D161B85

BlindBox Artstyle

更新了V3版本,调整了眼睛,俗话说眼睛是心灵的窗口。但是目前还是实验性质的,从稳定性上还是推荐v1_mix版本。

如果你喜欢我的作品,可以点个Like,或者请我 喝杯咖啡

爱来自瓷器。

[机翻英语]

Updated v3 version, adjusted the eyes, as the saying goes, the eyes are the windows to the soul. But it is still experimental, from the stability or recommended v1_mix version.

If you like my work, you can click "Like" or buy me a coffee.

Love from China.

blindbox_v1_mix 👍

  • Add the prompt full body,chibi,

  • weigh : 1

  • checkpoint : RevAnimated or other you like

mix PVC material, is good.

🖖I would appreciate it if you could share with me the results of your use.

blindbox v1

  • Add the prompt full body,chibi,

  • Recommeneded weigh : 1

  • checkpoint : RevAnimated

Other checkpoint may produce fantastic results, try it yourself.

Can be used with other LoRA.

blindbox v2

  • Reduces the probability of a big head (maybe)

  • Lowered network_dim value, smaller file size

  • More Chibi, Less blindbox

v1 version has good blindbox artstyle

blindbox v3

  • 调整眼部细节

ーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーー

盲盒风格的LoRA,一开始是这么想的。

v1版本 还是比较盲盒的。

增加了PVC的质感,更新了v1_mix,效果很不错,建议使用👍

增加关键词chibi, full body,

减少负面描述会好一点,也可自行尝试。

经过测试,如果要和别的LoRA一起使用,还是把那些负面关键词加上吧😅

推荐使用RevAnimated模型。

跟一些角色LoRA也有比较好的相性。

v2版本减少了大头的概率,更偏向二头身。

适合一些动漫画风了,也许。

有问题可以去B站问,如果我能解决的话😄

姑且放上一个没人气的视频

https://www.bilibili.com/video/BV1Ah411G7Zs/