找回密码
 立即注册
查看: 1299|回复: 0

[传统艺术] [SD 1.5][LORA]Kincora Style LoRA (6.6 MB) 8 dim UNET only (FOR NAI/AnythingV3 based models)

[复制链接]

3869

主题

36

回帖

4329

积分

管理员

积分
4329
发表于 2023-6-7 20:05:32 | 显示全部楼层 |阅读模式

基础数据

样图
基本模型:
SD 1.5
小模型:
Lora 
下载链接:
您必须是网站正式用户方可进行下载。

Kincora Style LoRA

This is a style LoRA inspired by Kincora's art style (https://twitter.com/KIncoraK )

Please, do not harass them and do not sell image generated with that LoRA.

I'm still doing some experiments with low net dim LoRA (8 net dim / 1 Alpha). I only trained the UNET part (without the text encoder) because I wanted it to avoid learning characters from the learning set (and reduce the risk of overfitting). I wonder if I should re-train my previous LoRAs since 160/128 dim is overkill and tend to overfit.

This LoRA was trained on 177 images (half of them are cowboy shot,upper body versions of the second half) and most of them come from Azur Lane this mean that this LoRA can generate suggestive outfits (big cleavage, swimsuit, maids,etc...) if you don't prompt an outfit.

Weight:

I only tested it at weight 1.0 but you will probably have to decrease it weight (or other LoRA weight) if you want to use it with some character LoRA (especially high dim ones)

I have not tested this on default NAI so I don't know if it's too strong for the base model.

Recommended prompt:

That LoRA doesn't have any activation prompt or recommended pormpt (this is a style LoRA and not a character one).

Maybe eyelashes for close up or portrait shot ?

Model used for the example:

AnythingV4.5

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

Archiver|手机版|小黑屋|金房子

GMT+8, 2024-10-31 10:17 , Processed in 0.035257 second(s), 23 queries .

© 2023 金房子|AI发烧友社区

快速回复 返回顶部 返回列表