{"id":7623,"date":"2024-04-10T11:09:37","date_gmt":"2024-04-10T03:09:37","guid":{"rendered":"https:\/\/www.1ai.net\/?p=7623"},"modified":"2024-04-10T11:09:37","modified_gmt":"2024-04-10T03:09:37","slug":"midjourney%e6%95%99%e7%a8%8b%ef%bc%8c%e5%a6%82%e4%bd%95%e8%ae%a9midjourney%e8%a7%92%e8%89%b2%e8%be%be%e5%88%b0%e4%b8%80%e8%87%b4%e6%80%a7%ef%bc%9f%e8%af%95%e8%af%95%e8%bf%99%e4%b8%aa%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/7623.html","title":{"rendered":"Midjourney tutorial, how to make Midjourney characters consistent? Try this method"},"content":{"rendered":"<p data-pm-slice=\"0 0 []\">Many people are using<a href=\"https:\/\/www.1ai.net\/en\/tag\/midjourney\" title=\"_Other Organiser\" target=\"_blank\" >Midjourney<\/a>When generating characters, we basically encounter a problem, that is, it is difficult to maintain the consistency of the character. Today, I will share with you the method of controlling the consistency of the character, I hope it will be useful to you.<\/p>\n<p data-pm-slice=\"0 0 []\">The character consistency tutorial is here again!<\/p>\n<p data-track=\"146\"><strong>Preparation:<\/strong><\/p>\n<p><strong>1. Midjourney account<\/strong><\/p>\n<p>a. New registered users have 25 free uses<\/p>\n<p>b. The cheapest membership price is $10\/month (200 generation quotas)<\/p>\n<p><strong>2. Unable to communicate in Chinese<\/strong>, you need to learn how to write prompt<\/p>\n<p>3. For those who know less about MJ,<strong>I suggest you follow my tutorial first.<\/strong>Then study other prompts yourself<\/p>\n<p data-track=\"154\"><strong>First understand two instructions<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7624\" title=\"get-248\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-248.jpg\" alt=\"get-248\" width=\"894\" height=\"185\" \/><\/div>\n<p data-track=\"155\">It doesn\u2019t matter if you don\u2019t understand. Next, we will carry out the actual operation. I will put the prompt of each step in text form for your convenience to copy.<\/p>\n<p data-track=\"156\"><strong>1. Generate pictures<\/strong><\/p>\n<p data-track=\"157\">In the dialogue interface<strong>Input\/imagine<\/strong>,Then<strong>Input prompt<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7625\" title=\"get-249\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-249.jpg\" alt=\"get-249\" width=\"1067\" height=\"170\" \/><\/div>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7626\" title=\"get-250\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-250.jpg\" alt=\"get-250\" width=\"945\" height=\"555\" \/><\/div>\n<table>\n<tbody>\n<tr>\n<td>\n<p data-track=\"158\">Create a highly detailed, Pixar 3D render of a game character on a white background, full body shot. The character is a teenager cute girl, wearing black hoodie, and blue jeans<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p data-track=\"160\"><strong>2. Copy the image link<\/strong><\/p>\n<p data-track=\"161\">Selected pictures, directly<strong>Right button<\/strong>Select [Copy link]<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7627\" title=\"get-251\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-251.jpg\" alt=\"get-251\" width=\"1039\" height=\"901\" \/><\/div>\n<p data-track=\"163\"><strong>3. Change the character&#039;s actions<\/strong><\/p>\n<p data-track=\"164\">In the dialogue interface<strong>Input\/imagine<\/strong>,Then<strong>Input prompt<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7628\" title=\"get-252\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-252.jpg\" alt=\"get-252\" width=\"1080\" height=\"249\" \/><\/div>\n<p data-track=\"165\"><strong>This step is important<\/strong>, let&#039;s take a look at the prompt disassembly<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7633\" title=\"get-257\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-257.jpg\" alt=\"get-257\" width=\"932\" height=\"185\" \/><\/div>\n<ol start=\"1\">\n<li data-track=\"166\">The white words in front are the prompts of the first picture (reference picture).<strong>Don&#039;t change<\/strong>,<strong>Copy it directly<\/strong><\/li>\n<li data-track=\"167\">At the end of the previous prompt,<strong>Adding Actions<\/strong>\u3010She is waving (She is waving)\u3011<\/li>\n<li data-track=\"168\">Then enter<strong>[space] [space] [ paste link]<\/strong><\/li>\n<li data-track=\"169\">Must have<strong>Space<\/strong>! Otherwise it will go wrong!<\/li>\n<\/ol>\n<p data-track=\"171\">Then we get the different actions of the same character<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7629\" title=\"get-253\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-253.jpg\" alt=\"get-253\" width=\"1012\" height=\"609\" \/><\/div>\n<p data-track=\"172\">Isn\u2019t it quite simple?<\/p>\n<p data-track=\"173\">Next, let\u2019s look at other attempts.<\/p>\n<p data-track=\"175\"><strong>4. Real-life style pictures<\/strong><\/p>\n<p data-track=\"176\">pass<strong>prompt to let MJ generate a real person picture<\/strong>Maintain consistency<strong>The effect is pretty good<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7630\" title=\"get-254\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-254.jpg\" alt=\"get-254\" width=\"1080\" height=\"538\" \/><\/div>\n<p data-track=\"178\">Prompt\ud83d\udc47\ud83d\udc47\ud83d\udc47<\/p>\n<table>\n<tbody>\n<tr>\n<td>\n<p data-track=\"179\">Reference Image<\/p>\n<\/td>\n<td>\n<p data-track=\"180\">photo of an asian woman with black long hair, brown eyes and tan skin. She is wearing a white shirt<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"181\">Change background<\/p>\n<\/td>\n<td>\n<p data-track=\"182\">photo of an asian woman with black long hair, brown eyes and tan skin. <strong>Behind her is a futuristic city a night with neon lights.<\/strong> She is wearing a white shirt <strong>\u2013cref photo link<\/strong><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"183\">Change expression<\/p>\n<\/td>\n<td>\n<p data-track=\"184\">photo of an asian woman with black long hair, brown eyes and tan skin. <strong>She is shocked and surprised.<\/strong> She is wearing a white shirt <strong>\u2013cref photo link<\/strong><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p data-track=\"185\">The red text is based on the reference picture prompt<strong>Added change prompt<\/strong><\/p>\n<p data-track=\"187\">But if it is<strong>Upload a photo<\/strong>Trying to maintain consistency, but the results are not satisfactory<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7631\" title=\"get-255\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-255.jpg\" alt=\"get-255\" width=\"1080\" height=\"538\" \/><\/div>\n<p data-track=\"188\">Foreign stars can at least look a little bit like them (such as the one in the upper right corner)<\/p>\n<p data-track=\"189\">Let&#039;s take a look at the domestic stars, Lao Guo<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7632\" title=\"get-256\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-256.jpg\" alt=\"get-256\" width=\"1080\" height=\"601\" \/><\/div>\n<p data-track=\"190\">Not at all<\/p>\n<p data-track=\"192\"><strong>5. Anime style pictures<\/strong><\/p>\n<p data-track=\"193\">The consistency of anime style pictures,<strong>I personally think it is very good<\/strong>Let me show you the Sauron I made.<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7634\" title=\"get-258\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-258.jpg\" alt=\"get-258\" width=\"1080\" height=\"539\" \/><\/div>\n<p data-track=\"194\">It should be noted that when using MJ to make anime-style pictures, you need<strong>Set to Niji mode first<\/strong><\/p>\n<p data-track=\"195\">Enter in the dialogue box<strong>\/settings<\/strong>, Enter to send<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7635\" title=\"get-259\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-259.jpg\" alt=\"get-259\" width=\"936\" height=\"304\" \/><\/div>\n<p data-track=\"196\">You can refer to my settings<\/p>\n<p data-track=\"198\">Prompt\ud83d\udc47\ud83d\udc47\ud83d\udc47<\/p>\n<table>\n<tbody>\n<tr>\n<td>\n<p data-track=\"199\">refer to<\/p>\n<\/td>\n<td>\n<p data-track=\"200\">Roronoa Zoro<\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"201\">Figure 1<\/p>\n<\/td>\n<td>\n<p data-track=\"202\">Roronoa Zoro <strong>linking a black suit -cw 0<\/strong><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"203\">Figure \u2461<\/p>\n<\/td>\n<td>\n<p data-track=\"204\">Roronoa Zoro <strong>linking a pink and blue suit \u2013cw 0<\/strong><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"205\">Figure \u2462<\/p>\n<\/td>\n<td>\n<p data-track=\"206\">Roronoa Zoro <strong>when a black suit with open shirt-cref<\/strong><\/p>\n<\/td>\n<\/tr>\n<tr>\n<td>\n<p data-track=\"207\">Figure \u2463<\/p>\n<\/td>\n<td>\n<p data-track=\"208\">Roronoa Zoro <strong>is waving-cref photo links<\/strong><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p data-track=\"209\">I used the character consistency of Zoro.<strong>command<\/strong><\/p>\n<p data-track=\"210\">A comparison of the Promp and the corresponding picture should understand exactly what the command controls<\/p>\n<ul>\n<li data-track=\"211\">Figure 4, I didn't use [-cw], and Midjourney would default on [-cw 100], i.e., the person's face, hair and clothes are the same, only to make changes in action based on my new hint\u3002<\/li>\n<li data-track=\"212\">Figure 1, 2 and 3, I used [-cw 0], i.e. Midjourney only keeps the face of the reference and then changes the image according to my new hint\u3002<strong>Give AI more space\u3002<\/strong><\/li>\n<\/ul>\n<p data-track=\"214\"><strong>6. Other consistency<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7636\" title=\"get-260\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-260.jpg\" alt=\"get-260\" width=\"1030\" height=\"390\" \/><\/div>\n<p data-track=\"215\">Friends in the exchange group mentioned<strong>\u3010Other consistency\u3011<\/strong>I also tried<\/p>\n<p data-track=\"217\"><strong>Product Chart - Apple Watch<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7637\" title=\"get-261\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-261.jpg\" alt=\"get-261\" width=\"1080\" height=\"538\" \/><\/div>\n<p data-track=\"219\"><strong>Animal Illustrations-Pixar Style<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7638\" title=\"get-262\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-262.jpg\" alt=\"get-262\" width=\"1080\" height=\"538\" \/><\/div>\n<p data-track=\"221\"><strong>Animal Pictures-Non-Existent Animals<\/strong><\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-7639\" title=\"get-263\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/get-263.jpg\" alt=\"get-263\" width=\"1080\" height=\"538\" \/><\/div>\n<p data-track=\"223\"><strong>Summarize<\/strong><\/p>\n<p data-track=\"224\">Compared with the character consistency of ChatGPT, Midjourney is obviously much more complicated to operate.<strong>But more professional:<\/strong>The generated images have more options and more editable parts<\/p>\n<p data-track=\"225\">Midjourney finally took an important step forward in terms of character consistency.<\/p>\n<p data-track=\"226\">Although it may<strong>Not yet fully consistent with standards<\/strong>, but for the 70%~80% task, I think it brings a significant efficiency improvement.<\/p>\n<p data-track=\"227\">At the same time, unlike Stable Diffusion, Midjourney does not require difficult and costly LoRA self-training, but only requires providing\/producing a picture.<\/p>\n<p data-track=\"228\">Everything will fall into place.<\/p>","protected":false},"excerpt":{"rendered":"<p>When many people use Midjourney to create roles, it is basically a problem that it is difficult to keep roles consistent. Today, it is hoped that a way to control the coherence of roles will be useful for you. Here we go again! Preparation: 1. Midjourney account number a. The new registered user has 25 free-of-charge access levels b. The cheapest member slot is $10\/month (200 generation levels) 2. Can't communicate in Chinese and needs to learn prompt writing 3. Less well known friends of MJ, suggest that we follow my teaching post and then study the other prompts before we understand the two instructions, and then we do the actual exercise, and I'll take the prompt of each step and I'll take it to the point<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[149,144],"tags":[186,1664],"collection":[260],"class_list":{"0":"post-7623","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-midjourney","10":"collection-midjourney"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/7623","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=7623"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/7623\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=7623"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=7623"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=7623"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=7623"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}