{"id":3491,"date":"2024-02-01T10:04:15","date_gmt":"2024-02-01T02:04:15","guid":{"rendered":"https:\/\/www.1ai.net\/?p=3491"},"modified":"2024-02-01T10:05:09","modified_gmt":"2024-02-01T02:05:09","slug":"%e5%85%8d%e8%b4%b9%e5%95%86%e7%94%a8%ef%bc%81-midjourney%e8%bf%9b%e9%98%b6%e6%8a%80%e5%b7%a7%e3%80%81%e5%85%b3%e9%94%ae%e8%af%8d%e5%a4%a7%e5%85%a8%e3%80%81%e7%bb%8f%e9%aa%8c%e6%80%bb%e7%bb%93%e8%b6%85","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/3491.html","title":{"rendered":"Free for commercial use! Midjourney advanced skills, keyword list, experience summary"},"content":{"rendered":"

After this weekend's attempts at midjourney and self-study, I've summarized some of my experiences and tips to share, as well as compiled some of the mjKeywords<\/a>libraries and related tools.<\/p>\n

For the self-taught image generator, the creation of accurate images relies on the accurate input of keywords, which usually consists of three main parts: subject description, design style, and screen settings. While this structure is suitable for beginners, in-depth exploration will reveal that it is not enough. It is also necessary to consider the effect of the order in which the keywords are entered on the final screen and the possible contradictions between keywords. This requires more experimentation and practice to master the rules than learning to use existing software. It is also recommended that you purchase a $30 membership as a group to experience the features of the v5 version, which is far more effective and cost-effective than the v4 version. For a group of six people, each person pays about 35 RMB per month, which is a very good deal, even if you buy individually.<\/p>\n

Talk about keywords<\/strong><\/p>\n

This weekend tried many styles of ai out of the picture, general picture content we will be divided into two-dimensional illustration as well as three-dimensional three-dimensional two main forms of expression. In order to generate the picture you want, the above mentioned 3 structures can really help us roughly output the picture we want:<\/p>\n

1. Subject description:<\/strong><\/p>\n

It is possible to describe a scene or a story and its constituent elements, the details of an object or a character. For example, a zoo with tigers, lions, giraffes, trees, fences, etc. or a small woman pitching a tent in the forest, wearing a red dress and a white hat, but sometimesai may not be able to recognize every element of the description, if you want to describe a character in the scene, we remember to carry out an independent description, do not use a long string of text to express, ai will not be recognized!<\/strong>, for example, a boy in red armor standing on top of a mountain, then we'd better break him down as follows:A boy, in red armor, standing on top of a mountain, which would be closer to the scene we want.<\/strong>But details of multiple characters in a large scene are not so easy to generate by keywords.<\/p>\n

2. Design style:<\/strong><\/p>\n

Design style in fact many designers have no way to directly express it, so we will go in this step to find some style type of keyword reference or you find a picture of the style you want, put it in, this kind of we call it pad map \/ micrographs, so that the ai according to the style of the picture we give, combined with our theme description to generate the style of the picture.<\/p>\n

Also I for example I researched keywords for glass, clear plastic, neon colors and some materials like transparent and reflective.For example, if you want to make the surface of an object transparent, but do not reflect the mechanical structure inside the object, you may need to add some designer style, it is difficult to achieve the requirements by simply controlling the material<\/strong>Because the system judges that the surface is transparent you can certainly see the structure, but with the structure of the object will be very complex, not advanced. So there are a lot of keywords in here, and at the moment we can only go through the \"spell test\" individually for a certain style.<\/p>\n

\"640\"<\/section>\n
\"640-1\"<\/section>\n
No style added just description of material<\/section>\n
<\/section>\n
\"640-2\"\"640-3\"<\/p>\n

\"640-4\"<\/p>\n<\/section>\n

After adding a style, the material remains unchanged<\/section>\n
<\/section>\n
style type keywords I integrated in today'sShared in the resources at the end of the article.<\/strong><\/section>\n
<\/section>\n
3. Screen Settings<\/strong><\/section>\n
The screen settings will be more useful for 3D design. Because there will be a need to involve the type of rendering, lighting control, the gap will be huge.<\/section>\n
<\/section>\n
There are also some advanced techniques on the use of instructions tips, we can check the official document to get the use of methods, such as double colon, this symbol is more important in our weight settings and split information, such as here listed hot dog and hot dog, are hot dog, if you want to ai recognition, then you can use hot:: dog. you can also in the double colon followed by plus a number to indicate the weight, the higher the number the greater the weight, the weight can also be set to a negative number.\u00a0<\/section>\n
\"640-5\"<\/section>\n
\"640-6\"<\/section>\n
Official Tutorial Documentation<\/strong><\/section>\n
<\/section>\n
The official document is like our UI design guide will tell you a lot of commands, parameter usage and rules, many training courses are also extended with this document, so this part can be completely self-taught. As long as you can memorize the use of these commands, basically able to generate the effect you want.<\/section>\n
<\/section>\n
\"640-7\"<\/section>\n
<\/section>\n
Overall, the number of keywords is very large, the combination of different keywords, order, context will cause different results, but at present, the official did not give a set of standardized formulas, and we can not be very accurate output like using conventional tools, but at present, the effect alone is indeed very bullish. Many designers are also currently in a certain few styles in-depth attempts to spell collocation and feasibility, hoping to output some meaningful laws.<\/section>\n
<\/section>\n
I'm sending out a picture of the last few days of play for the guys to see, along with keywords, so you can save it if you like it:<\/section>\n
<\/section>\n
cyberpunk<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-8\"<\/section>\n
<\/section>\n
<\/section>\n
Keywords: A dog<\/section>\n
<\/section>\n
<\/section>\n
Pixar Animation<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-9\"<\/section>\n
Keywords: At night, a little girl is running in the forest, surrounded by fireflies, the moonlight is very bright, carrying a lantern, chinese style, c4d, octane render, atmosphere, high-quality pictures, 3d art, animation lighting, Pixar trend<\/section>\n
<\/section>\n
<\/section>\n
Original drawings of scenes in a certain designer style<\/strong><\/section>\n
<\/section>\n
\"640-10\"<\/section>\n
Keywords:<\/section>\n
<\/section>\n
<\/section>\n
Cartoon avatar<\/strong><\/section>\n
<\/section>\n
\"640-11\"<\/p>\n
<\/section>\n

Keywords: feed chart + cartoon boy,PIXAR STYLE<\/p>\n<\/section>\n

<\/section>\n
Miyazaki style illustration<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-12\"<\/p>\n
<\/section>\n

Keywords: studio ghibli,blueberry,flowerRich details,girl and boy<\/p>\n<\/section>\n

<\/section>\n
<\/section>\n
Lego Style Scenery<\/strong><\/section>\n
<\/section>\n
\"640-13\"<\/section>\n
Keywords: chibi boy made of lego,domsday survival,8k,HD,cinematography,photorealistic,epic,compositio<\/section>\n
<\/section>\n
miniature scene<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-14\"Keywords: Tiny cut\u00e9 laboratory, 3d blueder render, soft smoothlighting, science and technology background, 100mm lens, 4k UHD<\/p>\n

\"640-15\"<\/p>\n<\/section>\n

Keywords: Tiny cuteforest laboratory, 3d blender render, soft lighting, rain background, 100mm lens, 4k UHD, thilt-shift -ar 3:4<\/section>\n
<\/section>\n
<\/section>\n
\"640-16\"<\/section>\n
Keywords: Tiny cute space status, 3d blueder render, soft softlighting, clean background, 100mm lens, 4k UHD, timec, tilt-shift-ar 3:4<\/section>\n
<\/section>\n
Colorful \/ Neon Series<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640\"<\/section>\n
Keywords:<\/strong>there's a certain controller, holographic, smooth history, colorful transformation by diegregation, high ground, 4k, industrial design, white ground, solid, profile, sleek glass pickness, studio lighting, 4K by 3:4<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-17\"<\/section>\n
Keywords: a earphone, neon color, holographic, smooth history, rich detail, white background, studio lighting, 4K, tilt-ship-ar 3:4<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
Cartoon Bubble Mart Dolls<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-18\"<\/section>\n
Keywords: a Super Reporters boy Wearing a Diving Unit, Bigeyes, Whole Body, Clean Light and Enderse, Dreamy, excised, IP by Pop Maart, High Detail, HyperQuality, Bright Light, Markupblind Box Toy, Distney Still, Fine Luster, 3D Render, 8kbrightfront Lighting, Face Shotford Luster<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
Axonometric Stereoscopic Scene<\/strong><\/section>\n
\"640-19\"\"640-20\"<\/p>\n<\/section>\n
Keywords: The goest house, the broom, the pumpkin lantern, halloweenday, the dead trees, the vines, Bats, dark envirment, the trees, astrology, old door, Game Assembly style in a low poly model, Western, tilt-shift, 16bit pixel art 16, trendy IP by pop mat, IPMockup, blind box toy, fine lunster, white background, 3D render, oc render, 4K, beast Quest, multilaterally-aid, night light light \u2013<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-21\"<\/p>\n
\u00a0<\/strong><\/section>\n

Keywords: A arena, bear, fights, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads, heads<\/strong><\/p>\n<\/section>\n

\u00a0<\/strong><\/section>\n
\"640-22\"<\/section>\n
Keywords: Bus stop, pink chirry trye, document little girl, the bus, sign, Game Assembly stage in a low level model, asmetric, tilt-Shift, 16bit pixel art 16, complete IP by pop mart, IP mockup, blind box to follow, fine ruler, white background, 3D render, ocnder, 4K, best quality, mixed<\/strong><\/section>\n
\u00a0<\/strong><\/section>\n
\"640-23\"<\/section>\n
Keywords:<\/strong>An emergency park, the Ferris team, the bank, the banker, the milly-go-round torists, the shipkeepers, Games Assets in a low-poor model, Western, 16bit pixel at 16, rather than IP by pop mart, IPMockup, blind box toy, fine ruler, white background, 3D render, ocnder, 4K, most effective, 3:4<\/strong><\/section>","protected":false},"excerpt":{"rendered":"

following this weekend ' s attempts and self-learning on midjourney, some lessons and techniques were shared, and key vocabulary and related tools on mj were compiled. for those who learn self-generated images, the creation of accurate images depends on the accurate input of keywords, which usually consists of three main parts: a subject description, design style and graphic setting. while this structure is suitable for beginners, in-depth exploration will find that it alone is not sufficient. there is also a need to consider the impact of the sequence of keyword entry on the final picture and possible contradictions between keywords. this requires more effort and practice to keep track than learning to use existing software. in addition, you are recommended to buy $30 as a team to experience the v5 functionality, which is far more effective than v4<\/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":[186,192,1070],"collection":[260,302],"class_list":["post-3491","post","type-post","status-publish","format-standard","hentry","category-jiaocheng","category-baike","tag-midjourney","tag-prompt","tag-1070","collection-midjourney","collection-prompt"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3491","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=3491"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3491\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=3491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=3491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=3491"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=3491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}