详情
推荐
Rabbit v2
Rabbit v1
Rabbit | wlsdnjs950 | erabi_ - Style LoRA

Rabbit | wlsdnjs950 | erabi_ - Style LoRA

35.9K
602
25
#风格
#ArtStyle
#兔子
#洛拉
#wlsdnjs950
#erabi_
#角色设计

Please, check the description, there is a little bit of useful information.

Indroduction:

This LoRA is supposed to represent Rabbit's artstyle.

Be aware! Try not to use any "quality" embeddings with style LoRAs.

Should work good with most character or concept LoRAs.


Artist's main features:

  • Cute anime-styled faces

  • Soft silky skin

  • Thick and long eyelashes

  • Puffy ??????? and areolae


Recommendations:

  • 1.0 emphasis.

  • Anything VAE is more close to original colors.

  • Precise prompting for ???? generations.

    • For example - adding "???????" or "?????" tag to "????" in prompt

  • Don't use too high emphasis values on tags.

  • Don't use "quality" embeddings with any Style LoRAs. Embeddings are chaging style too.

  • If you want to use "covered ???????" tag, be sure you've put "see-through" in negs.

  • If you want the same eyes quality use Adetailer or UDetailer extensions.


If you're ran into any problems with this LoRA, you can always dm me on discord:

troubledarkness - discord nickaname

I'll be glad to help | Буду рад помочь.

Credits:

Dataset of 150 pictures (v1), 20 epochs, Clip Skip - 2

Dataset of 165 pictures (v2), 20 epochs, Clip Skip - 2

Really big thanks to:

查看译文

评分与评论

5.0 /5
0个评分

尚未收到足够的评分或评论

avatar
公告
2023-05-19
发布模型
2024-02-12
更新模型信息
模型详情
类型
LORA
发布时间
2024-02-12
基础模型
SD 1.5
版本介绍

In this version:

1. Better and closer to original artstyle.

2. Still a lot, but less different issues with clothes comparing to first release, author is drawing a lot of clothes that you just can't describe with booru tagging system, so, those issues are happening because of that.

3. Expanded and retagged dataset, now it has 165 images instead of 150.

4. More NSFW-fiendly but you need to prompt more for it. For example - prompting for ??????? even with "????" tag applied. Artist not drawing too much ???? still.

许可范围
来源: civitai

1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。

2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领

创作许可范围
在线生图
进行融合
允许下载
商业许可范围
生成图片可出售或用于商业目的
允许模型转售或融合后出售
QR Code
下载SeaArt App
在移动端继续你的AI创作之旅