Midjourney 是另一个 AI 图像生成器。与 Stable Diffusion 不同,Midjourney 使用 Discord Bot 作为 AI 图像生成的接口(在此加入 Discord,或在 Learn Prompting Discord 中尝试该 Bot)。不过,使用 Midjourney Bot 的遵循相同的图像提示基本原则。
Midjourney 的基本结构是 /imagine prompt: [IMAGE PROMPT] [--OPTIONAL PARAMETERS]
. 例如:
/imagine prompt: astronaut on a horse
更多关于图像提示参数的信息可以在这里找到:Midjourney Documentation - Parameter List
例如:
/imagine prompt: astronaut on a horse --ar 3:2 --c 70 --q 2 --seed 1000
Midjourney 默认情况下会整体理解你的提示语。使用双冒号 :: 可以让 Midjourney 分别理解提示语的每个部分。例如:
/imagine prompt: astronaut and horse
/imagine prompt: astronaut:: and horse
通过将一个图片上传到 Discord,并在提示语中使用它的 URL,你可以指示 Midjourney 使用该图片来影响你的结果的内容、样式和构成。例如: Astronaut (Source: Wikipedia)
/imagine prompt: [image URL], impressionist painting
Needs more content!
Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.