【SD】一致性角色 - 同一人物 不同姿势 - 2

首先生成4张不同姿势的图片

masterpiece,high quality,(white background:1.6),(simple background:1.4),1gril,solo,black footwear,black hair,brown eyes,closed mouth,full body,glasses,jacket,long hair,long sleeves,lookig at viewer,plaid,plaid skirt,pleated shirt,school uniform,shoes,skirt,smile,solo,black pantyhose,

bad anatomy,(nsfw:1.5),lowres,bad anatomy,bad hands,text,error,missing,fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,bad feer,?

生成人物 如果是openpose XL模型? 必须使用openpose2

打开depth1 2 3 4 分别导入4张图

depth_midas????????diffusers_xl_depth_full [2f51180b]

打开ip-adapta 导入 你想融合的图片

ip-adapter_clip_sdxl plus_vith??????? 设置为：ip-adapter-plus-face_sdxl_vit-h

参数：0.5-1

Each ControlNet unit for each image in a batch

[StyleAlign] Align image style in the batch.

设置每批数量：4

---

下面是优化方案：

启用：freeu

勾选enable????????

?

?同时打开Enable ADetailer

然后在负面提示词添加embbing。。。。