{"id":6263,"date":"2024-03-26T09:32:47","date_gmt":"2024-03-26T01:32:47","guid":{"rendered":"https:\/\/www.1ai.net\/?p=6263"},"modified":"2024-03-26T09:32:47","modified_gmt":"2024-03-26T01:32:47","slug":"%e9%ad%94%e6%90%ad%e7%a4%be%e5%8c%ba%e5%bc%80%e6%ba%90data-juicer-%e3%80%81-lite-sora-%e7%b1%bb-sora-%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/6263.html","title":{"rendered":"The MoDa community open-sources Data-Juicer and lite-Sora Sora-like models"},"content":{"rendered":"<p>At the 2024 Global Developer Pioneer Conference,<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%ad%94%e6%90%ad%e7%a4%be%e5%8c%ba\" title=\"[Sees the article with the tags]\" target=\"_blank\" >MoDa Community<\/a>Launched &quot;ModelScope-Sora <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>The project aims to promote the development of Chinese <a href=\"https:\/\/www.1ai.net\/en\/tag\/sora%e6%a8%a1%e5%9e%8b\" title=\"_Other Organiser\" target=\"_blank\" >Sora Model<\/a>exploration and innovation.<\/p>\n<p>The program provides a one-stop tool chain, including data processing tools, multimodal datasets, Sora-like basic models, training and inference tools, etc.<\/p>\n<p class=\"article-content__img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-6264\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/03\/6384695323096461273761756.jpg\" alt=\"\" width=\"1000\" height=\"477\" \/><\/p>\n<p>MoDa has released Data-Juicer, a multimodal data processing system that contains more than 100 efficient operators, which can greatly improve the efficiency and quality of video data processing. Data-Juicer supports text, image, audio, and video processing, and developers can freely combine operators, such as editing videos, enhancing resolution, etc.<\/p>\n<p>In addition, MoDa has also launched a basic Sora-like model, lite-Sora, and will hold a &quot;ModelScope-Sora Challenge&quot; to encourage developers to participate in the development of Sora-like models.<\/p>\n<p>In the future, MoDa plans to build an open high-quality multimodal dataset in Chinese to help the development of China&#039;s multimodal big models.<\/p>\n<article>\n<ul>\n<li>Data-Juicer page: https:\/\/github.com\/modelscope\/data-juicer<\/li>\n<li>lite-Sora page: https:\/\/github.com\/modelscope\/lite-sora<\/li>\n<\/ul>\n<\/article>","protected":false},"excerpt":{"rendered":"<p>At the 2024 Global Developer Pioneer Conference, the Magic Hitch community launched the ModelScope-Sora Open Source Program, which aims to promote the exploration and innovation of Sora-like models in China through the power of open source. The program provides a one-stop tool chain, including data processing tools, multimodal datasets, Sora-like basic models, and training inference tools. MagicBuilder released Data-Juicer, a multimodal data processing system that contains more than 100 kinds of efficient operators, which can dramatically improve the efficiency and quality of video data processing.Data-Juicer supports text, image, audio, and video processing, and developers are free to combine operators, such as editing video, enhancing resolution, etc. In addition, MagicBuilder also launched a basic class of Sora-like models, which can be used to improve the quality and efficiency of video processing. In addition, MagicBuilder also launched the basic class Sora model lite-So<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1272,219,1869],"collection":[],"class_list":["post-6263","post","type-post","status-publish","format-standard","hentry","category-news","tag-sora","tag-219","tag-1869"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/6263","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=6263"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/6263\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=6263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=6263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=6263"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=6263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}