{"id":27580,"date":"2025-01-28T10:29:34","date_gmt":"2025-01-28T02:29:34","guid":{"rendered":"https:\/\/www.1ai.net\/?p=27580"},"modified":"2025-01-22T10:36:15","modified_gmt":"2025-01-22T02:36:15","slug":"%e7%94%a8%e5%8d%b3%e6%a2%a6ai%e5%88%b6%e4%bd%9c%e5%8a%a8%e7%94%bb%e8%a7%86%e9%a2%91%e6%95%85%e4%ba%8b%ef%bc%8c%e8%a7%a3%e5%86%b3ai%e7%94%9f%e6%88%90%e5%9b%be%e7%89%87%e8%a7%92%e8%89%b2%e4%b8%80","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/27580.html","title":{"rendered":"Creating animated video stories with Instant Dream AI, solving the problem of consistency of AI-generated image characters"},"content":{"rendered":"

Recently, there are a lot of partners who want to make animated stories with AI, and we also see a lot of accounts with good data for animated stories with AI.<\/p>\n

But unlike doing a 5-10 secondShort Video<\/a>, character consistency is one of the most critical issues for mid-length videos.<\/strong><\/p>\n

After all, you can't change a characterization from one scene to the next for the protagonist of a story, can you?<\/p>\n

The method of how to keep a consistent character image in AI videos is usually done using MJ or SD, which is relatively complex and not friendly to the little guy.<\/p>\n

Today, I'll share a more simple approach that I've recently tested, so that even a white person doing an animated story can simply do consistent characterization.<\/p>\n

Primary tool use: i.e. Dream AI<\/strong>. It's friendly to white people.<\/p>\n

First, use that dream AI to generate the character three views<\/p>\n

We can use Instant Dream AI to directly generate character three-views to create an important character in a story.<\/p>\n

Put together a fairly stable set of cue words that people can just use.<\/p>\n

Tips:Three views, full body, front, side, back. cg anime style character ip* design.<\/strong>Ancient Chinese beauty, dressed in a green hanbok with her hair in a bun.Exquisite features, high detail, best quality, UHD.<\/strong><\/p>\n

(The bolded parts stay fixed, the rest can be modified to suit the character's traits.)<\/p>\n

\"b70a4665j00sqgxmx001od000u000a8p\"<\/p>\n

Let's choose one of our favorites and hi-resize it. We can see the character's features from all different angles in the picture.<\/p>\n

\"467530f6j00sqgxn8001ud000u000f5p\"<\/p>\n

Second, the use of namely dream reference raw figure to maintain the consistency of the characters<\/p>\n

Click on Import Reference Image, select the character's lookalike, and then remember to save it.<\/p>\n

\"370ad855j00sqgxnh002cd000u000pgp\"<\/p>\n

Then enter the rest of the cue words, preferably repeating the description of the character's features, and then add the scene and action.<\/strong><\/p>\n

For example: CG anime style, ancient Chinese garden, ancient Chinese beauty, wearing green Chinese dress, hair coiled into a bun, delicate features, woman sitting in a gazebo, stone table in front of her, books, tea cups and teapots.<\/p>\n

\"8d5c3c94j00sqgxns001ud000u000bhp\"<\/p>\n

Choose one of the more appropriate ones and HD-ize it so you can see the results:<\/p>\n

\"2c560a40j00sqgxo60030d000u000f7p\"<\/p>\n

You can see that the consistency of the generated figure drawing, and the initially generated three-view figure, is well maintained.<\/p>\n

Is not very simple. I believe we can all quickly generate consistent character images afterward, as well as make better animated stories with AI.<\/p>","protected":false},"excerpt":{"rendered":"

RECENTLY, A NUMBER OF SMALL PARTNERS HAVE WANTED TO MAKE ANIMATED STORIES USING AI, AND MANY ACCOUNT DATA USING ANIMATED STORIES ARE GOOD. BUT UNLIKE SHORT VIDEO FOR 5-10 SECONDS, CHARACTER CONSISTENCY IS ONE OF THE MOST CRITICAL ISSUES FOR MEDIUM- AND LONG-SIZED VIDEO. AFTER ALL, YOU CAN'T CHANGE A SCENE FOR A CHARACTER, CAN YOU? THE WAY TO KEEP THE IMAGE OF THE PERSON IN THE AI VIDEO IS GENERALLY DONE USING MJ OR SD, WHICH IS RELATIVELY COMPLEX AND UNFRIENDLY TO WHITE. A SIMPLER WAY TO SHARE A RECENT TEST IS TO SHARE TODAY, SO THAT WHITE CAN MAKE ANIMATED STORIES CAN BE SIMPLE AND CONSISTENT. THE MAIN TOOL IS USED: DREAM AI. IT'S NICE TO WHITE. I. THE USE OF DREAM AI TO CREATE A THIRD VIEW OF A PERSON CAN BE USED TO CREATE A THIRD VIEW OF A PERSON DIRECTLY FROM DREAM AI<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[149,144],"tags":[1751,3765,5321,1007],"collection":[],"class_list":{"0":"post-27580","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-ai","11":"tag-1007"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/27580","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=27580"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/27580\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=27580"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=27580"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=27580"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=27580"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}