{"id":15369,"date":"2024-07-12T08:49:54","date_gmt":"2024-07-12T00:49:54","guid":{"rendered":"https:\/\/www.1ai.net\/?p=15369"},"modified":"2024-07-12T08:49:54","modified_gmt":"2024-07-12T00:49:54","slug":"ai-%e6%a0%b9%e6%8d%ae%e5%a3%b0%e9%9f%b3%e5%86%85%e5%ae%b9%e5%b8%ae%e7%85%a7%e7%89%87%e5%af%b9%e5%8f%a3%e5%9e%8b%ef%bc%8c%e8%9a%82%e8%9a%81%e9%9b%86%e5%9b%a2%e5%bc%80%e6%ba%90-echomim","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/15369.html","title":{"rendered":"AI helps photos &quot;lip sync&quot; based on the sound content, Ant Group open sources EchoMimic project"},"content":{"rendered":"<p data-vmark=\"2637\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%9a%82%e8%9a%81%e9%9b%86%e5%9b%a2\" title=\"[Sees articles with labels]\" target=\"_blank\" >Ant Group<\/a> 10th<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>Named <a href=\"https:\/\/www.1ai.net\/en\/tag\/echomimic\" title=\"[See article with [EchoMimic] label]\" target=\"_blank\" >EchoMimic<\/a> new projects that can be<strong>Portrait facial features<\/strong>and<strong>Audio<\/strong>Come help the character&quot;<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%af%b9%e5%8f%a3%e5%9e%8b\" title=\"[Sees articles with [portal] labels]\" target=\"_blank\" >Lip Sync<\/a>\u201d, combining facial landmarks and audio content to generate more stable and natural videos.<\/p>\n<p data-vmark=\"31c2\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-15370\" title=\"a7d67879-86b0-428e-9ffb-0523e2a76344\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/a7d67879-86b0-428e-9ffb-0523e2a76344.png\" alt=\"a7d67879-86b0-428e-9ffb-0523e2a76344\" width=\"840\" height=\"419\" \/><\/p>\n<p data-vmark=\"80ad\">The project has high stability and naturalness. By fusing the features of audio and facial landmarks (key facial features and structures, usually located at the eyes, nose, mouth, etc.), it can generate<strong>More in line with real facial movements and expression changes<\/strong>Video.<\/p>\n<p data-vmark=\"5578\">It supports the use of audio or facial landmarks to generate portrait videos, and also supports combining audio and portrait photos to create a &quot;lip sync&quot; effect. It is reported that it supports multiple languages (including Mandarin Chinese and English) and multiple styles, and can also handle<strong>Sing<\/strong>And other scenes.<\/p>\n<p data-vmark=\"3464\"><span class=\"referenceTitle\">Attached related links:<\/span><\/p>\n<ul class=\"custom_reference list-paddingleft-1\">\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"131f\"><strong>Project address:<\/strong><a href=\"https:\/\/badtobest.github.io\/echomimic.html\" target=\"_blank\" rel=\"noopener\"><span class=\"link-text-start-with-http\">https:\/\/badtobest.github.io\/echomimic.html<\/span><\/a><\/p>\n<\/li>\n<li class=\"list-undefined list-reference-paddingleft\">\n<p data-vmark=\"1a18\"><strong>Github:<\/strong><a href=\"https:\/\/github.com\/BadToBest\/EchoMimic\" target=\"_blank\" rel=\"noopener\"><span class=\"link-text-start-with-http\">https:\/\/github.com\/BadToBest\/EchoMimic<\/span><\/a><\/p>\n<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>Ant Group on the 10th open source a new project called EchoMimic, which can help characters through the portrait of facial features and audio to \"lip-sync\", combined with facial markers and audio content to generate a more stable, natural video. The project is highly stable and naturalistic, and by combining audio and features of facial landmarks (key facial features and structures, usually located in the eyes, nose, mouth, etc.), it can generate video that is more consistent with real facial movements and expression changes. It supports the use of audio or facial markers alone to generate portrait video, but also supports the combination of audio and portrait photos to make \"lip-sync\" general effect. It is reported that it supports multi-language (including Chinese Mandarin, English) and multi-style, but also to deal with singing and other scenes. With related links: project address: http<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3447,3446,219,1030],"collection":[],"class_list":["post-15369","post","type-post","status-publish","format-standard","hentry","category-news","tag-echomimic","tag-3446","tag-219","tag-1030"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15369","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=15369"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15369\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=15369"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=15369"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=15369"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=15369"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}