Based on v60, dreamshaper_v8, and midjourney loras.
A similar but different model for v35, it’s a model with a strong Midjourney photorealistic style and HDR.
Trained with Midjourney images, could probably do a lot of MJ realistic styles.
Note that this model doesn’t like tails, tends to do ferals, also the character’s body may not be fully covered by fur (or become human xd).
Clip skip = 1.
中文:
基于v60,dreamshaper_v8和自炼的mj照片写实lora。
相似,但和v35不太一样的一个模型,带有非常强烈的照片写实风格而且可以画很暗的图像。
可能可以画与mj不相上下的福瑞照片写实图片。
这个模型基本出不了尾巴,画狼倾向于画成纯狼,角色身体覆毛也有问题,出的狗子经常看起来像得了皮肤病()或者直接底特律变人
clip跳过必须用1.