SDXL 1.0
此版本没有设置触发词.
TAG:1girl,solo,jewelry,bare shoulders,open clothes,long sleeves,bracelet,white dress,white jacket
服装的还原度稍微存在一些问题。
TAG:white_dress,white_coat,off_shoulder,yellow_gloves,bare_shoulders,collarbone,open_coat,strapless_dress,long_sleeves,green_hair,
特别感谢CyberHarem数据集支持：huggingface dataset - CyberHarem/shu_arknights
他们是全网第一个训练此角色的lora模型的（非常快）
传送门：Shu/黍 (Arknights) - v1.5 | Stable Diffusion LoRA | Civitai
Training model: Animagine XL V3
Inference model: Animagine XL V3
Training resolution: 1024*1024
Recommended output resolution: 1024*1280
Recommended model weight: 0.8~1