Kita Ikuyo XL 喜多郁代 きた いくよ 孤独摇滚

详情

下载文件

模型描述

2.0 SDXL 版本:

使用了1000张图片训练。

训练模型:Animagine XL V3

推理模型:Animagine XL V3

训练分辨率:1024*1024

推荐输出分辨率:1024*1280

推荐模型权重:0.8~1

特别鸣谢:算力赞助 / GPU Sponsor: nieta.art

英文部分由 GPT 翻译,可能存在错误。

值得注意的是,在该模型的训练中,我使用 waifuc 来搜集和处理训练集,它可以轻松过滤掉我不需要的双人图、杂图和黑白图片,从而提升了我的训练集质量。

https://deepghs.github.io/waifuc/main/tutorials-CN/installation/index.html

It is worth noting that in the training of this model, I used waifuc to collect and process the training dataset. It can easily filter out unwanted images such as double exposure, miscellaneous images, and black and white images, which improves the quality of my training dataset.

https://deepghs.github.io/waifuc/main/index.html

喜多,喜多

全标训练

使用 DIM4 训练,体积大小只有 27M 左右

Full mark training.

Training with DIM4, the volume size is only around 27M.

训练模型:SDXL1.0 官模

测试模型:Kohaku-XL

建议权重:0.8 或根据实际情况自由调整。

触发词:1girl,solo,red_hair,white_background,shirt,long_hair,green_eyes,one_side_up,bangs,hair_between_eyes,yellow_eyes

推荐模型:Kohaku-XL ,X2 Anime 二次元通用模型 【Final】

Training model: SDXL1.0 Official Model

Testing model: Kohaku-XL

Recommended weights: 0.8 or adjust them freely according to the situation.

keyword:1girl,solo,red_hair,white_background,shirt,long_hair,green_eyes,one_side_up,bangs,hair_between_eyes,yellow_eyes

此模型生成的图像

未找到图像。