{"id":16470,"date":"2024-07-26T09:28:22","date_gmt":"2024-07-26T01:28:22","guid":{"rendered":"https:\/\/www.1ai.net\/?p=16470"},"modified":"2024-07-26T09:28:22","modified_gmt":"2024-07-26T01:28:22","slug":"%e7%88%b1%e8%af%97%e7%a7%91%e6%8a%80aisphere%e5%8f%91%e5%b8%83%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e4%ba%a7%e5%93%81pixverse-v2%ef%bc%8c%e5%8d%95%e7%89%87%e6%ae%b5%e5%8f%af%e8%be%be8%e7%a7%92","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/16470.html","title":{"rendered":"AIsphere releases video generation product PixVerse V2, which can generate video clips up to 8 seconds for a single clip and 40 seconds for multiple clips"},"content":{"rendered":"<p data-pm-slice=\"0 0 []\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e7%88%b1%e8%af%97%e7%a7%91%e6%8a%80\" title=\"Look at the article that contains the labels\" target=\"_blank\" >Aishi Technology<\/a>recently released its video generation product<a href=\"https:\/\/www.1ai.net\/en\/tag\/pixverse-v2\" title=\"[Sees articles with [PixVerse V2] labels]\" target=\"_blank\" >PixVerse V2<\/a>It's a program based on the<a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e8%a7%86%e9%a2%91\" title=\"[View articles tagged with [AI Video]]\" target=\"_blank\" >AI Video<\/a>A large model of innovative tools designed to help users unleash their creative potential, PixVerse V2 utilizes the Diffusion+Transformer (DiT) infrastructure with several technological innovations that make video generation smoother, more consistent, and more fun.<\/p>\n<div class=\"pgc-img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-16471\" title=\"get-816\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/get-816.jpg\" alt=\"get-816\" width=\"1000\" height=\"644\" \/><\/div>\n<p data-track=\"36\">Key features include:<\/p>\n<ul>\n<li data-track=\"37\">Spatio-temporal Attention Mechanism:PixVerse V2 introduces a self-developed spatio-temporal attention mechanism, which improves the ability to perceive space and time, especially when dealing with complex scenes.<\/li>\n<li data-track=\"38\">Text comprehension:With the multimodal model, PixVerse V2 is able to align text information and video information more accurately, which enhances the model's comprehension and expression.<\/li>\n<li data-track=\"39\">Optimized Model Training:Based on the traditional flow model, PixVerse V2 promotes faster and better convergence of the model through weighted loss, improving the overall training efficiency.<\/li>\n<li data-track=\"40\">Video Generation Capability:PixVerse V2 supports the generation of multiple video clips at a time, up to 8 seconds for a single clip and up to 40 seconds for multiple clips, while maintaining consistency between clips.<\/li>\n<li data-track=\"41\">User-Friendly Functions:PixVerse V2 supports one-click generation of 1-5 consecutive video content, and maintains the consistency of the subject image, screen style and scene elements between segments. In addition, users can also edit the generated results to flexibly replace and adjust the video content.<\/li>\n<\/ul>\n<p data-track=\"42\">The Aishi Technology team plans to make several iterations and upgrades in the next 3 months to provide a better AI video generation experience.The goal of PixVerse V2 is to make AI video creation easier and more efficient, whether it's documenting daily life or telling a video story.<\/p>\n<p>&nbsp;<\/p>","protected":false},"excerpt":{"rendered":"<p>Aishi Technology recently announced its video generation product, PixVerse V2, an innovative tool based on the AI Video Big Model designed to help users unlock their creative potential.PixVerse V2 utilizes the Diffusion+Transformer (DiT) infrastructure and introduces technological innovations in a number of areas that make video generation smoother, more consistent and fun. Key features include: Spatio-Temporal Attention Mechanism: PixVerse V2 introduces a self-developed Spatio-Temporal Attention Mechanism, which improves spatial and temporal awareness, especially when dealing with complex scenes. Text comprehension: Through the multimodal model, PixVerse V2 is able to align text and video information more accurately, which enhances the modality of text comprehension.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[956,1044,3708,3707],"collection":[],"class_list":["post-16470","post","type-post","status-publish","format-standard","hentry","category-news","tag-ai","tag-pixverse","tag-pixverse-v2","tag-3707"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16470","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=16470"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/16470\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=16470"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=16470"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=16470"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=16470"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}