Kontext-万能去马赛克

专为去马赛克处理效果，可用于人像、物品等
该模型的训练数据集包含 51 对图集

提示词【通用】：image display,perform mosaic review,detect all forms of review in the image - including mosaic,blur,black and white stripe review,pixelation,filled areas,and identity review - and accurately restore the reviewed area,based on logical structure and visual background,prioritize faithfully reconstructing the original uncensored content,ensure that the repaired area retains the expected texture,shape,and details of the uncensored version,

使用方法：

1、图生图

2、填入提示词【通用】

image display,perform mosaic review,detect all forms of review in the image - including mosaic,blur,black and white stripe review,pixelation,filled areas,and identity review - and accurately restore the reviewed area,based on logical structure and visual background,prioritize faithfully reconstructing the original uncensored content,ensure that the repaired area retains the expected texture,shape,and details of the uncensored version,

3、选择LORA 权重 0.8【把LORA加入收藏就可以找到了】，选择要去马赛克的图片

4、开始生图

贴一下例图的马赛克原始图片