Calling Methods<\/p>\n<\/td>\n
Use Cases<\/p>\n<\/td>\n
Precautions<\/p>\n<\/td>\n<\/tr>\n
Add a space after the keyword, and then the version parameter:<\/p>\n
- \n
- \u2013v or \u2013v<\/li>\n
- \u2013version or \u2013version<\/li>\n<\/ul>\n<\/td>\n
\n i don't know<\/p>\n<\/td>\n
\n Only versions 1, 2, 3, 4, and 5 are supported.<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Because you can add version parameters directly in the prompt and set the version in the settings, you may encounter a situation like the following (I want to generate a version 1 chart, but the settings are set to 5, what should I do?):<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/77889MJ015.jpeg\")
<\/div>\nAt this point, the model will run these parameters in order from left to right. According to the above example, the generated image is actually the V1 version, which can be compared with the V5 version below:<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/41256MJ016.jpeg\")
<\/div>\nAspect Ratios<\/h1>\n
The first parameter is the aspect ratio of the image. It is used as follows, and the version differences are as follows:<\/p>\n
\n\n
\n \n Calling Methods<\/p>\n<\/td>\n
\n Use Cases<\/p>\n<\/td>\n
\n Precautions<\/p>\n<\/td>\n
\n V5<\/p>\n<\/td>\n
\n V4<\/p>\n<\/td>\n
\n V3<\/p>\n<\/td>\n
\n niji<\/p>\n<\/td>\n<\/tr>\n
\n \n \n
\n
\n
\n
Add a space after the keyword, and then the aspect ratio parameter:<\/p>\n
- \n
- - ar, or--<\/li>\n
- \u2013aspect or \u2013aspect<\/li>\n<\/ul>\n<\/td>\n
\n i'm sorry<\/p>\n<\/td>\n
\n - \n
- The default ratio is 1:1.<\/li>\n
- The ratio needs to be an integer, for example, 1.3:1 is not acceptable, but 13:10 is acceptable.<\/li>\n
- the long width ratio affects the shape and structure of the image. when you zoom in, some long-width ratios can change slightly. for example, \u2013ar 16:9 (1.75) the resulting picture could be 7:4 (1.74)\u3002<\/li>\n<\/ul>\n<\/td>\n
\n \u2705 Any ratio is supported. However, aspect ratios above 2:1 are experimental and may produce unpredictable results.<\/p>\n<\/td>\n
\n \u2705 1:2 to 2:1<\/p>\n<\/td>\n
\n \u2705 5:2 to 2:5<\/p>\n<\/td>\n
\n \u2705 1:2 to 2:1<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
In addition, there are also best practices for aspect ratio in the industry:<\/p>\n
- \n
- 5:4 is mostly used for traditional printing<\/li>\n
- 3:2 is mostly used for photo printing<\/li>\n
- 7:4 ratio is close to the ratio of HD TV or smartphone<\/li>\n<\/ul>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/48451MJ017.png\")
<\/div>\nNo<\/h1>\n
This parameter means "no". If you don't want trees to appear in the AI-generated images, just enter plants:<\/p>\n
\n\n
\n \n Calling Methods<\/p>\n<\/td>\n
\n Use Cases<\/p>\n<\/td>\n
\n Precautions<\/p>\n<\/td>\n
\n V5<\/p>\n<\/td>\n
\n V4<\/p>\n<\/td>\n
\n V3<\/p>\n<\/td>\n
\n niji<\/p>\n<\/td>\n<\/tr>\n
\n \n Add a space after the keyword, and then the content you don\u2019t want the AI to generate:<\/p>\n
- \n
- \u2013no, or \u2013no<\/li>\n<\/ul>\n<\/td>\n
\n \u2014no plants<\/p>\n<\/td>\n
\n none<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Chaos<\/h1>\n
This parameter is a bit like Top P in ChatGPT, which mainly controls the randomness of the model. The higher the number, the more likely it is to produce some unexpected results. The lower the number, the higher the consistency. Look at the official example, prompt is watermelon owl hybrid.<\/p>\n
This is when Chaos is 0. The consistency is relatively high. The way the watermelon and the owl are merged is similar in the four outputs. In addition, in a single output, the style similarity of the four pictures (four squares) is also relatively high:<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/96998MJ158.png\")
<\/div>\nThis is when Chaos is 100. You will find that the fusion styles of multiple outputs are different, and even in a single output, the styles of the four images are quite different. If you want AI to help you do some exploratory things, I suggest you turn up Chaos a little bit in the early stage, and the results will be more divergent.<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/98126MJ159.png\")
<\/div>\n\n\n
\n \n Calling Methods<\/p>\n<\/td>\n
\n Use Cases<\/p>\n<\/td>\n
\n Precautions<\/p>\n<\/td>\n
\n V5<\/p>\n<\/td>\n
\n V4<\/p>\n<\/td>\n
\n V3<\/p>\n<\/td>\n
\n niji<\/p>\n<\/td>\n<\/tr>\n
\n \n Add a space after the keyword, followed by a number:<\/p>\n
- \n
- \u2013c or \u2013c<\/li>\n<\/ul>\n
- \n
- \u2013chaos or \u2013chaos<\/li>\n<\/ul>\n<\/td>\n
\n \u2014c 10<\/p>\n<\/td>\n
\n Enter 0-100, default 0<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Stylize\u200b<\/h1>\n
This parameter is a bit like Temperature in ChatGPT, and it mainly controls the stylization of the generated image. Simply put, the lower the value, the more it fits the description of the prompt, and the higher the value, the stronger the artistic quality, but the weaker the correlation with the prompt.<\/p>\n
Let's take a look at the official examples. The prompts are all colorful risographs of a fig. Risograph is a digital printing machine that uses templates and special inks to produce printed products. Risograph is usually used to produce low-cost printed products such as posters and brochures. This printing machine can produce special color and texture effects. The first three pictures basically fit the style of risograph, but the four pictures in the lower right corner are very different. The model adds a lot of drama.<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/15399MJ160.png\")
<\/div>\nIn addition to entering it in the prompt, you can also adjust the default version in the settings. For related tutorials, please refer to Midjourney Basic Settings.<\/p>\n
\n\n
\n \n Calling Methods<\/p>\n<\/td>\n
\n Use Cases<\/p>\n<\/td>\n
\n Precautions<\/p>\n<\/td>\n
\n V5<\/p>\n<\/td>\n
\n V4<\/p>\n<\/td>\n
\n V3<\/p>\n<\/td>\n
\n niji<\/p>\n<\/td>\n<\/tr>\n
\n \n Add a space after the keyword, followed by a number:<\/p>\n
- \n
- \u2013 or \u2013<\/li>\n<\/ul>\n
- \n
- \u2013stylize or \u2013stylize<\/li>\n<\/ul>\n<\/td>\n
\n \u2014s 50<\/p>\n<\/td>\n
\n The default is 100<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n
\n \u2705<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
Niji<\/h1>\n
In fact, the Niji model was developed by Midjourney and Spellbrush. "Niji" is Japanese "\u306b\u3058", which means "rainbow" or "2D".<\/p>\n
It is good at generating anime-like images. For example, the prompt is fancy peacock, the left picture is the v5 model, and the right picture is the niji v5 model. The right picture is more cartoon-like:<\/p>\n
![\"Midjourney](\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/96439MJ127.png\")
<\/div>\nThe usage is similar to Version. Just enter \u2014niji at the end of the text prompt.<\/p>\n
\n\n
\n \n Calling Methods<\/p>\n<\/td>\n
\n Use Cases<\/p>\n<\/td>\n
\n Precautions<\/p>\n<\/td>\n<\/tr>\n
\n \n Add a space after the keyword, and then the version parameter:<\/p>\n
- \n
- \u2013niji or \u2013niji<\/li>\n<\/ul>\n<\/td>\n
\n i'm sorry, but i'm sorry<\/p>\n<\/td>\n
\n Some parameters are not valid for Niji. You can check which parameters are not valid for Niji in the complete list.<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\n
<\/p>","protected":false},"excerpt":{"rendered":"
In short, you can interpret these parameters as official fixed prompt templates, and this template contains special characters that allow the model to ensure 100% consistency of output results while increasing the accuracy and input efficiency of prompt. If you've used ChatGPT, then you've seen it: using the same prompt template as everyone else, but without a decree, ChatGPT produces the same content. And Midjourney, because it's a picture category, it's relatively vertical, so they make a template for the generic prompt statements of a lot of the picture categories, such as the size ratio, which is 1:1, 2:3, 4:7 and so on, if you continue the ChatGPT<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[144],"tags":[186,192],"collection":[260],"class_list":["post-9210","post","type-post","status-publish","format-standard","hentry","category-baike","tag-midjourney","tag-prompt","collection-midjourney"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9210","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=9210"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/9210\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=9210"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=9210"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=9210"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=9210"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
- \u2013niji or \u2013niji<\/li>\n<\/ul>\n<\/td>\n
- \u2013stylize or \u2013stylize<\/li>\n<\/ul>\n<\/td>\n
- \u2013 or \u2013<\/li>\n<\/ul>\n
- \u2013chaos or \u2013chaos<\/li>\n<\/ul>\n<\/td>\n
- \u2013c or \u2013c<\/li>\n<\/ul>\n
- \u2013no, or \u2013no<\/li>\n<\/ul>\n<\/td>\n