Goth * Swrrt * Qi * Wa * PonyXL young women's clothing styles from the Victorian and Rococo periods. / ロリータ系ファッション
详情
下载文件
关于此版本
模型描述
为了解决大量图像管理的繁琐问题,我写了个脚本,结果没怎么上传,一晃就过了好几个月——好歹现在能用了,顺便做个测试:
- 美化图像的脚本
- 优化标签的脚本
本 LoRA 的主题是带有大量荷叶边的甜美风格服饰,以及绘制起来相当费时的复杂设计。作为初版,标签整理尚不完善,主要以插画素材为主。为进一步提升学习效果,建议补充模特穿着的图像和详细的特写照片。此外,我曾尝试使用 LoraPlus,但尚未充分挖掘其潜力。
我清楚模型训练尚不完全,但已取得一定成果,因此决定作为初版发布。
- 网络秩: 16
- 学习率: UNet 0.001 / 文本编码器 0.0001
- 调度器: CosineAnnealingLR(T_max=860, eta_min=1e-7)
婉转表达
英文版在 Civitai 上会被屏蔽,所以文件名定为 goth-XLPony_009,但哥特风格仅作为隐藏元素略微存在,地雷系也带了一点点。
洛丽塔时尚的子类别多到爆炸:从主流的哥特洛丽塔,到甜系洛丽塔、和风洛丽塔、中式洛丽塔等等,根本顾不过来。
本以为如此,结果
上传样本时,Civitai 的推荐标签里居然出现了“洛丽塔时尚”
看来 Civitai 现在终于肯放过我了
---
---
### ENG
This LoRA was created to alleviate the burden of managing a large number of images, utilizing some automation tools:
- [Script for improving images](https://github.com/NEXTAltair/Lorayougazouwoiroirosurusukuriputo)
- [Script for refining tags](https://github.com/NEXTAltair/genai-tag-db-tools)
The theme of this LoRA revolves around girly clothes adorned with frills and intricate designs that require significant drawing effort. The initial version lacks well-organized tags and is mainly based on illustration materials. To improve the model, including photos with mannequins and close-up images would be essential. Although I attempted to use LoraPlus, I couldn't fully leverage its potential.
While acknowledging the imperfections, the model is reasonably complete for a first release.
---
### Training Parameters
#### Key Points
- Network Rank: 16
- Learning Rate: UNet 0.001 / Text Encoder 0.0001
- Scheduler: CosineAnnealingLR (T_max=860, eta_min=1e-7)
---
### Example Execution Command
---


















