/imagine 18-year-old Swedish prince named Arthur with striking blue eyes and blonde hair, immersed in a medieval world, combining the whimsy of Disney and Pixar with exceptional detail and atmospheric lighting
/imagine blue and white jacket with gold detailing for a young medieval prince, immersed in a medieval world, combining the whimsy of Disney and Pixar with exceptional detail and atmospheric lighting
/imagine <img-1> <img-2> wearing blue and white jacket with gold detailing, 18-year-old Swedish prince named Arthur with striking blue eyes and blonde hair, immersed in a medieval world, combining the whimsy of Disney and Pixar with exceptional detail and atmospheric lighting
/imagine Prince Rodrick the Great, elderly medieval prince, character design, in style of Rembrandt — seed 3299135161
这将产生与上述相同的四个图像块(这个提示是我编的;它不是我用来产生上述图像的提示)。我所说的基本提示是 Prince Rodrick the Great, elderly medieval prince, character design, in style of Rembrandt.
然后,你要在基本提示前加上一个面部表情,例如俏皮的微笑。你可以把这称为 “预提示”。
/imagine playful smile::Prince Rodrick the Great, elderly medieval prince, character design, in style of Rembrandt — seed 3299135161
然后,你要在基础提示中添加一个重量:
/imagine playful smile::Prince Rodrick the Great, elderly medieval prince, character design, in style of Rembrandt::1.5 — seed 3299135161
/imagine [IMAGE URL]::Prince Rodrick the Great, elderly medieval prince, character design, in style of Rembrandt::1.5 — seed 3299135161
同样,基本图像块是:
在基本提示权重为1,风格化值为800的情况下,我得到了:
在基础提示权重为1.5,风格化值为800的情况下,我得到了:
基础提示权重为3,风格化值为800,我得到了:
如果基本提示权重为0.25,风格化值为8,你得到的图像就更像图像提示:
我还试验了背景。例如,简单地加入 in a dark forest as a ‘pre-prompt.”
同样,基础提示图像是:
基础提示权重为1,风格化值为800,我得到了:
基础提示权重为2,风格化值为800,我得到了:
基本提示重量为3,风格化价值为800,我得到的是:
黑客帝国的风格
我想尝试改变人物的风格,通过添加提示次 style of the Matrix 到我的基本提示,并给它一个2的权重。 所以提示看起来像 style of the Matrix::2::[Character Name, Character Description] — seed [seed ID]
它实际上工作得很好,我可能可以通过改变权重和风格来调整它:
所以你可以看到,结果可能是参差不齐的,但似乎有很大的空间来创造一致的角色的面部表情,以及结合图像提示和背景。我一直在试验身体的姿势,希望能很快公布我的结果。我希望你觉得这很有用。
评论区 (0)
最新评论登录后发布评论并参与互动。
暂无评论,欢迎抢沙发。