Midjourney
Midjourney 是另一個 AI 影象生成器。與 Stable Diffusion 不同,Midjourney 使用 Discord Bot 作為 AI 影象生成的介面(在此加入 Discord,或在 Learn Prompting Discord 中嘗試該 Bot)。不過,使用 Midjourney Bot 的遵循相同的影象提示基本原則。
基本用法
Midjourney 的基本結構是 /imagine prompt: [IMAGE PROMPT] [--OPTIONAL PARAMETERS]
. 例如:
/imagine prompt: astronaut on a horse
更多關於影象提示引數的資訊可以在這裡找到:Midjourney Documentation - Parameter List
例如:
/imagine prompt: astronaut on a horse --ar 3:2 --c 70 --q 2 --seed 1000
進階用法
多重提示
Midjourney 預設情況下會整體理解你的提示語。使用雙冒號 :: 可以讓 Midjourney 分別理解提示語的每個部分。例如:
/imagine prompt: astronaut and horse
/imagine prompt: astronaut:: and horse
影象提示
透過將一個圖片上傳到 Discord,並在提示語中使用它的 URL,你可以指示 Midjourney 使用該圖片來影響你的結果的內容、樣式和構成。例如: Astronaut (Source: Wikipedia)
/imagine prompt: [image URL], impressionist painting
Notes
Needs more content!
Sander Schulhoff
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.