{"id":14812,"date":"2024-07-05T09:19:26","date_gmt":"2024-07-05T01:19:26","guid":{"rendered":"https:\/\/www.1ai.net\/?p=14812"},"modified":"2024-07-05T09:19:26","modified_gmt":"2024-07-05T01:19:26","slug":"%e4%b8%80%e5%bc%a0%e7%85%a7%e7%89%87%e5%88%9b%e9%80%a0-1-%e5%88%86%e9%92%9f%e4%ba%ba%e7%89%a9%e8%a7%86%e9%a2%91%ef%bc%8c%e5%95%86%e6%b1%a4%e5%8f%91%e5%b8%83%e9%a6%96%e4%b8%aa%e5%8f%af","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/14812.html","title":{"rendered":"SenseTime releases Vimi, the first &quot;controllable&quot; large model for generating character videos, to create a 1-minute character video from a photo"},"content":{"rendered":"<p data-vmark=\"13b0\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%95%86%e6%b1%a4%e7%a7%91%e6%8a%80\" title=\"[View articles tagged with [quotidian technology]]\" target=\"_blank\" >SenseTime<\/a>exist<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e4%b8%96%e7%95%8c%e4%ba%ba%e5%b7%a5%e6%99%ba%e8%83%bd%e5%a4%a7%e4%bc%9a\" title=\"[Sees articles with tags of the World Congress of Artificial Intelligence]\" target=\"_blank\" >World Artificial Intelligence Conference<\/a>(WAIC) launched the first \"controlled\" character<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"_Other Organiser\" target=\"_blank\" >Video Generation of Large Models<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/vimi\" title=\"_Other Organiser\" target=\"_blank\" >Vimi<\/a>, a character video consistent with the target action can be generated through a photo of any style, and it supports multiple driving methods, and can be driven by existing character videos, animations, sounds, texts and other elements.<\/p>\n<p data-vmark=\"67b3\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-14813\" title=\"66f4e83c-1bd2-42bd-a786-88eaeadbd6b5\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/66f4e83c-1bd2-42bd-a786-88eaeadbd6b5.png\" alt=\"66f4e83c-1bd2-42bd-a786-88eaeadbd6b5\" width=\"1267\" height=\"713\" \/><\/p>\n<p data-vmark=\"cfae\">Unlike image expression control technologies that can only control head movements, Shangtang says that Vimi can not only realize precise character expression control, but also realize<strong>Control the natural limb changes of the people in the photo in the half-body area<\/strong>and automatically generates character-matching hair, clothing, and background changes.<\/p>\n<p data-vmark=\"67a6\">Meanwhile, Vimi can<strong>Stabilized generation of 1-minute single-camera character-based videos<\/strong>The image effect will not deteriorate or be distorted over time, which meets the needs of entertainment and interaction that require stable video generation over a long period of time.<\/p>\n<p data-vmark=\"af33\">Vimi will<strong>Fully open to C-support users<\/strong>The user only needs to upload high-definition pictures of people from different angles to automatically generate digital doppelgangers and different styles of portrait videos.<\/p>\n<p data-vmark=\"ee4c\">Video characters generated by Vimi are no longer just dull movements of the five senses, but are paired with gestures, limbs, hair, etc. to form a more complete and unified character movement, allowing creators to edit and re-create based on the generated video footage.<\/p>\n<p data-vmark=\"6ab6\">Shangtang said it will announce more details of Vimi tomorrow, and IT Home will continue to pay attention and bring follow-up reports.<\/p>","protected":false},"excerpt":{"rendered":"<p>Shangtang Technology released the first \"controllable\" character video generation model Vimi at the World Artificial Intelligence Conference (WAIC), which can generate a character video consistent with the target action through a photo of any style, and supports a variety of driving methods, which can be driven by the existing character video, animation, sound, text and other elements. Driven by existing character video, animation, sound, text and other elements. Unlike image expression control technology that can only control head expression movements, Shangtang says that Vimi can not only realize accurate character expression control, but also control the natural body changes of the character in the photo within the half-body area, and automatically generate hair, clothing and background changes that match the character. At the same time, Vimi can stably generate 1-minute single-camera character videos, with no deterioration or distortion over time, to meet the needs of the entertainment industry.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3343,1538,2171,2958],"collection":[],"class_list":["post-14812","post","type-post","status-publish","format-standard","hentry","category-news","tag-vimi","tag-1538","tag-2171","tag-2958"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/14812","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=14812"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/14812\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=14812"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=14812"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=14812"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=14812"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}