底模:Pony
主页:https://civitai.com/models/152085/genshinxl-yae-miko
版本:pony
Trigger Words |
BACHONG |
pony:
TAG:
bachong
Training model: Pony
Recommend model: Pony Diffusion V6 XL/T-ponynai3/AutismMix SDXL
Training resolution: 1024*1024
Recommended output resolution: 832*1216/1024*1280
2.5:
As more and more SDXL models are being built with built-in Genshin Impact characters, I found myself, a trainer specializing in training Genshin Impact Lora models, becoming "unemployed." Therefore, I decided to release the pre-trained Genshin Impact Lora model that I had previously trained and consider a career transition.
备注:神子的衣服,在C站就不能通过“safe”模式
另,我还在找一个能适应我二次元lora的三次元底膜
训练模型:SDXL1.0官模
测试模型:Kohaku-XL
建议权重:0.8 or adjust them freely according to the situation.
触发词:1girl,yae_miko,solo,long_hair,pink_hair,purple_eyes,breasts,detached_sleeves,japanese_clothes,
Testing model: Kohaku-XL
Recommended weights: 0.8 or adjust them freely according to the situation.
keyword:1girl,yae_miko,solo,long_hair,pink_hair,purple_eyes,breasts,detached_sleeves,japanese_clothes,
The English portion is translated by GPT and may contain errors.
值得注意的是,在该模型的训练中,我使用waifuc来通过搜集和处理训练集,他可以轻易过滤掉我所不需要的双人图,杂图和黑白图片,这使我的训练集的质量得到提高。
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
未经作者允许,禁止转载或以其他方式上传到其他平台