
Default prefix: hezi,Naruto character design,(headband:1.3)
Trigger word: HEZI
Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,
Recommended sampler: Euler a
Recommended number of iteration steps: 30
It is recommended to open the HD repair: the amplification algorithm is R-ESRGAN 4x+ Anime6B,
The ADetailer is enabled. Recommended AD model: face_yolov8n.pt,mediapipe_face_mesh_eyes_only
The recommended weight for lora is 0.6
CFG: 5 to 7
CLIP Recommended: 2
The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank you
This model is only used for communication and learning, and is not commercially available. It is open to download on various platforms. If it is integrated, please mark the original model to avoid unnecessary trouble
默认前缀:hezi,Naruto character design,(headband:1.3)
触发词:HEZI
底模推荐:全网首发|SHMILY古典炫彩_v1.0,
采样器推荐:Euler a
迭代步数推荐:30
推荐开启高清修复:放大算法为R-ESRGAN 4x+ Anime6B,
ADetailer开启,AD模型推荐:face_yolov8n.pt,mediapipe_face_mesh_eyes_only
lora权重推荐0.6
CFG为:5~7
CLIP推荐:2
泛化性很好可结合其他lora,希望大家多返图多点赞,谢谢
此模型仅用作交流和学习,不可商用,在各个平台开放下载,如果融合请标注原模型以免不必要的麻烦
描述:
训练词语: hezi
名称: 火影人物设计2.0-000014.safetensors
大小 (KB): 96870
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success