<h1 id="heading-29">HEZI Niji style quadratic</h1>This model is trained using nearly 1000 Niji style image footage, generalization is very good, need to turn on HD repair.Trigger words: HEZI,Niji, just add a few character descriptors to easily create a detailed, dramatic picture,Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,Sampler recommendation: DPM++ 3M SDE ExponentialRecommended number of iteration steps: 30It is recommended to open HD repair: the amplification algorithm is 4x-UltraSharp,ADetailer is enabled. Recommended AD model: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>lora weight is recommended 0.6-0.8CFG: 7CLIP Recommended: 2VAE recommendation: vae- FT-MSE-84000-EMA-Pruned.safetensorsThe generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank youThis 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<h1 id="heading-30">HEZI_Niji风格二次元</h1>这个模型使用近1000张Niji风格图像素材训练而成，泛化性很好，需要开启高清修复。触发词：HEZI,Niji，只需再加一些人物描述词就可以轻松生成一张细节丰富，画面有张力的图片，底模推荐：全网首发｜SHMILY古典炫彩_v1.0，采样器推荐：DPM++ 3M SDE Exponential迭代步数推荐：30推荐开启高清修复：放大算法为4x-UltraSharp，ADetailer开启，AD模型推荐：face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>lora权重推荐0.6-0.8CFG为：7CLIP推荐：2VAE推荐：vae-ft-mse-840000-ema-pruned.safetensors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

HEZI Niji style quadratic<HEZI_Niji风格二次元>

HEZI_Niji风格-000026.safetensors

v1.0

这个模型使用近1000张Niji风格图像素材训练而成，泛化性很好，需要开启高清修复。触发词：HEZI,Niji，只需再加一些人物描述词就可以轻松生成一张细节丰富，画面有张力的图片，底模推荐：全网首发｜SHMILY古典炫彩_v1.0，采样器推荐：DPM++ 3M SDE Exponential迭代步数推荐：30推荐开启高清修复：放大算法为4x-UltraSharp，ADetailer开启，AD模型推荐：face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>lora权重推荐0.6-0.8CFG为：7CLIP推荐：2VAE推荐：vae-ft-mse-840000-ema-pruned.safetensors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

Files with SHA256: 26397d74bb37dad921b84c539d964f8e0e0df76a83cad4ead74be0e055fd0760