这是用户在 2024-3-14 2:19 为 https://waytoagi.feishu.cn/wiki/CIzXwGMNbicPFHklDDuc3jg5nce 保存的双语快照页面,由 沉浸式翻译 提供双语支持。了解如何保存?
立即编辑
登录/注册
  • 用飞书打开
  • 举报
  • 取消
请输入正文
Midjourney 人物一致性已上线
​ ​
🤖
You can use --cw to modify reference 'strength' from 100 to 0
您可以使用 --cw 将引用“强度”从 100 修改为 0
strength 100 (--cw 100) is default and uses the face, hair, and clothes
强度 100 (--CW 100) 是默认的,使用脸部、头发和衣服
At strength 0 (--cw 0) it'll just focus on face (good for changing outfits / hair etc)
在强度 0 (--cw 0) 时,它只会专注于脸部(适合换衣服/头发等)
What it's meant for 它的用途
This feature works best when using characters made from Midjourney images. It's not designed for real people / photos (and will likely distort them as regular image prompts do)
此功能在使用由 Midjourney 图像制作的角色时效果最佳。它不是为真实的人/照片设计的(并且可能会像常规图像提示那样扭曲它们)
Cref works similarly to regular image prompts except it 'focuses' on the character traits
Cref 的工作方式与常规图像提示类似,只是它“关注”了角色特征
The precision of this technique is limited, it won't copy exact dimples / freckles / or tshirt logos.
这种技术的精度是有限的,它不会复制精确的酒窝/雀斑/或T恤标志。
Cref works for both Niji and normal MJ models and also can be combined with --sref
Cref 适用于 Niji 和普通 MJ 模型,也可以与 --sref 结合使用
Advanced Features 高级功能
You can use more than one URL to blend the information /characters from multiple images like this --cref URL1 URL2 (this is similar to multiple image or style prompts)
您可以使用多个 URL 来混合来自多个图像的信息/字符,例如: --cref URL1 URL2(这类似于多个图像或样式提示)
How does it work on the web alpha?
它在 Web Alpha 版上是如何工作的?
Drag or paste an image into the imagine bar, it now has three icons. selecting these sets whether it is an image prompt, a style reference, or a character reference. Shift+select an option to use an image for multiple categories
将图像拖动或粘贴到想象栏中,它现在有三个图标。选择这些设置是图像提示、样式引用还是字符引用。Shift+选择一个选项以将图像用于多个类别
​ ​

通往AGI之路

H
H