提示词:Flat illustration style
正面提示词建议少点,像示例图的一样
ADetailer启用(要开)
After Detailer 模型:mediapipe_face_full
采样方式:DPM++ 2M Karras
迭代步数:20步左右
高分迭代步数:20
放大算法:ScuNET GAN、R-ESRGAN 4x+ Anime6B和Latent (nearest-exact)
重绘幅度:0.7-0.5
图像分辨率:随便
模型自带vae
LoRA权重:0.8左右
提示词:Flat illustration style
正面提示词建议少点,像示例图的一样
ADetailer启用(要开)
After Detailer 模型:mediapipe_face_full
采样方式:DPM++ 2M Karras
迭代步数:20步左右
高分迭代步数:20
放大算法:ScuNET GAN、R-ESRGAN 4x+ Anime6B和Latent (nearest-exact)
重绘幅度:0.7-0.5
图像分辨率:随便
模型自带vae
LoRA权重:0.8左右
Use in 吐司 Online
As a online training base model on 吐司
Use without crediting me
Share merges of this model
Use different permissions on merges
Sell generated contents
Use on generation services
Sell this model or merges