{"id":37263,"date":"2025-06-16T09:21:24","date_gmt":"2025-06-16T01:21:24","guid":{"rendered":"https:\/\/www.1ai.net\/?p=37263"},"modified":"2025-06-12T12:34:52","modified_gmt":"2025-06-12T04:34:52","slug":"%e6%80%8e%e6%a0%b7%e4%bd%bf%e7%94%a8ai%e5%88%b6%e4%bd%9c%e5%af%b9%e5%8f%a3%e5%9e%8b%e8%a7%86%e9%a2%91%ef%bc%9f%e6%95%99%e4%bd%a0%e7%94%a8%e5%8f%af%e7%81%b5ai%e5%88%b6%e4%bd%9c%e5%a4%9a%e8%a7%92","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/37263.html","title":{"rendered":"How to make a lip-sync video with ai? Teach you to use Keling AI to create a multi-character character lip-synching video"},"content":{"rendered":"

I had made a video of two people having a real conversation using beanbags and instant dreams.shape of mouth<\/a>It matches the subtitles better and is more realistic. But the details leave something to be desired.<\/p>\n

How to make a video with two people talking? Teach you to use AI to make \"two people talk\" pop video!<\/a><\/p>\n

Multi-character lip-synching, as it should be at the momentAI skits<\/a>One of the major difficulties of the<\/p>\n

KeLing AI<\/a>It has just been updated with the Multi-Person Counterpoint feature, a feature that allows users to create videos containing multiple characters, greatly enriching the flexibility and expressiveness of video production.<\/p>\n

Currently, the merged generation of multiple dubs with multiple character tracks is not supported.<\/p>\n

It still needs to be generated individually by role, exported and merged for video post editing.<\/p>\n

Korin has been used less in recent times, and now that it's been introduced, it's a good time to see how it works.<\/p>\n

AI Tools<\/p>\n

Beanbag: https:\/\/www.doubao.com\/chat<\/p>\n

i.e. Dream: https:\/\/jimeng.jianying.com<\/p>\n

Korin: https:\/\/app.klingai.com\/cn<\/p>\n

Screening: PC Professional<\/p>\n

Bean bag - Generated multiple photos<\/strong><\/p>\n

First of all, you need to generate a picture with more than one person, in order to reduce the difficulty, here only generate a picture of 2 people. In fact, you can also directly use the last article, the picture of the 2 people in the conversation, the effect of experiments in the Korin.<\/p>\n

The easiest way to do this is to just tell the beanbag to generate a picture of 2 people having a conversation.<\/p>\n

However, I'm using a beanbag here to combine 2 images into one. Upload the 2 images first, then generate the prompt words according to your needs, as I'll demonstrate below:<\/p>\n

\"374ed63aj00sxq6uh001nd000si00ftp\"<\/p>\n

\"27fa74e7j00sxq6un001vd000sc00g6p\"<\/p>\n

\"7b6ebe06j00sxq6uu001md000qo00blp\"<\/p>\n

\"3129f89aj00sxq6v00013d000rc00bup\"<\/p>\n

\"b95f1dbdj00sxq6v80027d000u000f3p\"<\/p>\n

It's a dream<\/strong><\/p>\n

For this step, use this image above to generate 2 separate 5s clips. You can use a beanbag and use can be used i.e. Dream.<\/p>\n

I'm using Instant Dream Video 3.0 here.<\/p>\n

Women smile and talk, men smile and don't talk<\/p>\n

\"0c561a99j00sxq6vh001md000u000c8p\"<\/p>\n

Men smile and talk, women smile and don't talk<\/p>\n

\"22836640j00sxq6vn001ed000u000b3p\"<\/p>\n

3 Bean bag - Generate an oral text<\/strong><\/p>\n

Open Beanbag, upload the image above, and enter the prompt: based on this image, design a dialog to match it. Output as male, female, dialog<\/p>\n

\"dfdde950j00sxq6vx002dd000s600hmp\"<\/p>\n

If you are not satisfied, continue to optimize<\/p>\n

\"4bf8bb9ej00sxq6w6001md000qe009yp\"<\/p>\n

\"cf518434j00sxq6wl002fd000qg00g0p\"<\/p>\n

You can have beanbags and generate concise copy. Otherwise it takes too much time and expense to produce.<\/p>\n

Then like the previous post, put together the copy.<\/p>\n

4. CLIN - Generate multi-faceted video<\/strong><\/p>\n

Open Korin and click [Counterpoint].<\/p>\n

\"fe189438j00sxq6ww000ud000ix00kpp\"<\/p>\n

Upload the clip of the boys talking and the girls not talking first<\/p>\n

\"ddac53f5j00sxq6x3001od000u000cpp\"<\/p>\n

It is important to note that character 1 above, selecting the boys, corresponds to the video clip, and then it is a matter of entering the text, selecting the timbre, and not exceeding 5s in duration, which is the most painful of all.<\/p>\n

It's a test of patience if you're going to make a video that's a couple minutes long.<\/p>\n

Ditto for uploading another clip of the girl talking, entering the text, choosing character 2, timbre, etc.<\/p>\n

\"ff20a271j00sxq6xa001td000u000cup\"<\/p>\n

And so it goes, one clip at a time is generated. Those not long enough for 5s are edited later in the cutscene.<\/p>\n

5. Cutting and editing<\/strong><\/p>\n

Open the cutout, import the video clip, and add the stickers.<\/p>\n

\"96bbed2bj00sxq6xk001yd000u000glp\"<\/p>","protected":false},"excerpt":{"rendered":"

I MADE A VIDEO OF A REAL TWO-PERSON CONVERSATION WITH A BEAN BAG AND A DREAM. TASTES AND SUBTITLES ARE MORE CONSISTENT AND MORE AUTHENTIC. HOWEVER, THE DETAILS NEED TO BE UPGRADED. HOW DOES A VIDEO OF TWO PEOPLE TALKING? I'LL TEACH YOU HOW TO MAKE A DOUBLE-TALK VIDEO! MULTI-PERSON MOUTH-TO-MOUTH SHOULD BE A MAJOR DIFFICULTY FOR NOW IN THE AI SHORT PLAY. IT HAS JUST UPDATED A MULTI-PERSON MOUTH-TO-MOUTH FEATURE THAT ALLOWS USERS TO CREATE VIDEO WITH MULTIPLE CHARACTERS, GREATLY ENRICHING THE FLEXIBILITY AND PERFORMANCE OF VIDEO PRODUCTION. AT PRESENT, MULTIPLE MODULATIONS AND MULTI-ROLE TRACKS ARE NOT SUPPORTED. THERE IS ALSO A NEED FOR SEPARATE ROLE GENERATION AND POST-EDITING AFTER EXPORT. IT'S BEEN A WHILE SINCE I'VE USED A LITTLE MORE<\/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":[5014,4080,5321,6885,3676],"collection":[],"class_list":{"0":"post-37263","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-ai","11":"tag-6885"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/37263","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=37263"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/37263\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=37263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=37263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=37263"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=37263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}