{"id":932,"date":"2023-10-27T18:11:04","date_gmt":"2023-10-27T10:11:04","guid":{"rendered":"https:\/\/www.1ai.net\/?p=932"},"modified":"2023-10-27T18:11:04","modified_gmt":"2023-10-27T10:11:04","slug":"midjourney-prompt-%e5%9f%ba%e6%9c%ac%e7%bb%93%e6%9e%84","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/932.html","title":{"rendered":"Midjourney Prompt Basic Structure"},"content":{"rendered":"<p>exist <a href=\"https:\/\/www.1ai.net\/en\/tag\/midjourney\" title=\"_Other Organiser\" target=\"_blank\" >Midjourney<\/a> The official introductory documentation for the simplest of the <a href=\"https:\/\/www.1ai.net\/en\/tag\/prompt\" title=\"[View articles tagged with [Prompt]]\" target=\"_blank\" >Prompt<\/a> The structure is this:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-934\" title=\"MJ154\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/10\/MJ154.png\" alt=\"MJ154\" width=\"1124\" height=\"314\" \/><\/p>\n<p>But I think the above Prompt is too simple \ud83d\ude02, instead Advanced Prompt is better for learning:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-933\" title=\"MJ155\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/10\/MJ155.png\" alt=\"MJ155\" width=\"2382\" height=\"322\" \/><\/p>\n<h2 id=\"image-prompts\u9009\u586b\" class=\"anchor anchorWithStickyNavbar_LWe7\">Image Prompts (optional)<a class=\"hash-link\" title=\"Direct link to Image Prompts (optional)\" href=\"https:\/\/learningprompt.wiki\/zh-Hans\/docs\/midjourney\/mj-tutorial-basics\/midjourney-basics-prompt#image-prompts%E9%80%89%E5%A1%AB\" aria-label=\"Direct link to Image Prompts (optional)\">\u200b<\/a><\/h2>\n<p>Prompt is divided into three parts. The first one is Image, which is optional and can be filled in or not.<\/p>\n<p>Let's start with what this Image URL is for, there are a lot of ways to play with it, such as merging two images into one, you can see the example below, where I am uploading an image of a marble statue and flowers to Discord:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-936\" title=\"MJ156\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/10\/MJ156.png\" alt=\"MJ156\" width=\"1180\" height=\"586\" \/><\/p>\n<p>Then, after letting Midjourney blend (more on this in the next section on blending), you can create an image like the one below:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-935\" title=\"MJ157\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/10\/MJ157.png\" alt=\"MJ157\" width=\"1090\" height=\"1010\" \/><\/p>\n<p>Something to keep in mind:<\/p>\n<ul class=\"\">\n<li>You enter the URL address of the image, and it must be publicly accessible.<\/li>\n<li>Only png, gif and jpg image formats are supported.<\/li>\n<li>You can only put up to two image URLs, or one image URL + a paragraph.<\/li>\n<\/ul>\n<p>If you don't want to upload the image to some image bed server, you can also use Discord's image bed, you can chat privately with Midjourney Bot and then send the image to Discord first by uploading the image, then right click to copy the image link, like this:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-937\" title=\"AnimatedImage\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/10\/AnimatedImage.gif\" alt=\"AnimatedImage\" width=\"800\" height=\"497\" \/><\/p>\n<h2 id=\"text-prompt\" class=\"anchor anchorWithStickyNavbar_LWe7\">Text Prompt<a class=\"hash-link\" title=\"Direct link to Text Prompt\" href=\"https:\/\/learningprompt.wiki\/zh-Hans\/docs\/midjourney\/mj-tutorial-basics\/midjourney-basics-prompt#text-prompt\" aria-label=\"Direct link to Text Prompt\">\u200b<\/a><\/h2>\n<p>This is the description of the image you want AI to generate. There are very many tricks to this one, more on that later. Here I'd like to mention that Midjourney is a bit different from ChatGPT:<\/p>\n<ol>\n<li>Inability to understand sentence structure and syntax: Midjourney doesn't understand what you're saying the way ChatGPT does. By analogy, Midjourney is more like imperative programming, and ChatGPT is more like declarative programming, where you need to give Midjourney complete instructions before it can produce results you're happy with.<\/li>\n<li>Midjourney is designed with banned words: some words can't be entered, like the \ud83c\udf51 emoji can't be entered because the emoji is slang for butts, which often leads to the model generating not-so-nice images, so it's banned as well.<\/li>\n<\/ol>\n<div class=\"theme-admonition theme-admonition-tip alert alert--success admonition_LlT9\"><\/div>\n<h2 id=\"parameter\u53c2\u6570\" class=\"anchor anchorWithStickyNavbar_LWe7\">Parameter<a class=\"hash-link\" title=\"Direct link to Parameter\" href=\"https:\/\/learningprompt.wiki\/zh-Hans\/docs\/midjourney\/mj-tutorial-basics\/midjourney-basics-prompt#parameter%E5%8F%82%E6%95%B0\" aria-label=\"Direct link to Parameter\">\u200b<\/a><\/h2>\n<p>Midjourney has about 20 parameter settings, and I'll cover a few common ones in the next chapter. Once you understand the basic parameters, you should be able to generate good diagrams with Midjourney.<\/p>","protected":false},"excerpt":{"rendered":"<p>In Midjourney's official introductory document, the simplest Prompt structure is described like this: But I think the above Prompt is too simple \ud83d\ude02, instead, the Advanced Prompt is more suitable for learning: Image Prompts (optional) Prompts are divided into three parts. The first one is Image, which is optional and can be filled in or not. There are many ways to play with it, such as combining two images into one, you can see the example below, I uploaded an image of a marble statue and a flower to Discord: and then asked Midjourney to blen<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[149],"tags":[186,192,303],"collection":[302],"class_list":["post-932","post","type-post","status-publish","format-standard","hentry","category-jiaocheng","tag-midjourney","tag-prompt","tag-text-prompt","collection-prompt"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/932","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=932"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/932\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=932"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=932"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=932"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=932"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}