{"id":33743,"date":"2025-04-21T18:43:14","date_gmt":"2025-04-21T10:43:14","guid":{"rendered":"https:\/\/www.1ai.net\/?p=33743"},"modified":"2025-04-21T18:43:14","modified_gmt":"2025-04-21T10:43:14","slug":"%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4%e5%bc%80%e6%ba%90-skyreels-v2-%e6%a8%a1%e5%9e%8b%ef%bc%8c%e5%bc%80%e5%90%af%e7%94%9f%e6%88%90%e6%97%a0%e9%99%90%e6%97%b6%e9%95%bf%e8%a7%86","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/33743.html","title":{"rendered":"Open Source SkyReels-V2 Model Opens the Era of Generating \"Unlimited Duration\" Video"},"content":{"rendered":"<p>April 21st.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4\" title=\"[Sees articles with [Konlen] tags]\" target=\"_blank\" >Kunlun Wanwei<\/a>Officially released today and<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> <a href=\"https:\/\/www.1ai.net\/en\/tag\/skyreels\" title=\"_Other Organiser\" target=\"_blank\" >SkyReels<\/a>-V2 - the first in the world to use<strong>A Model for Infinite Duration Movie Generation in the Diffusion-forcing (Diffusion-Forcing) Framework<\/strong>The new model is based on a combination of Multi-Modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning and Diffusion-forcing frameworks to achieve collaborative optimization. Officially, the model will break through the boundaries of video generation technology and open up a new era of \"unlimited-length movie generation\".<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-33744\" title=\"0947fb4bj00sv2dqg001pd000m80065p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/04\/0947fb4bj00sv2dqg001pd000m80065p.jpg\" alt=\"0947fb4bj00sv2dqg001pd000m80065p\" width=\"800\" height=\"221\" \/><\/p>\n<p>1AI attached open source address below:<\/p>\n<p>SkyReels-V2<\/p>\n<ul>\n<li><strong>GitHub address:<\/strong>https:\/\/github.com\/SkyworkAI\/SkyReels-V2<\/li>\n<li><strong>Paper address:<\/strong>https:\/\/arxiv.org\/abs\/2504.13074<\/li>\n<\/ul>\n<p>SkyReels-A2<\/p>\n<ul>\n<li><strong>HuggingFace Address:<\/strong>https:\/\/huggingface.co\/ Skywork \/ SkyReels-A2<\/li>\n<li><strong>GitHub address:<\/strong>https:\/\/github.com\/SkyworkAI\/SkyReels-A2<\/li>\n<li><strong>Paper address:<\/strong>https:\/\/arxiv.org\/ pdf\/2504.02436<\/li>\n<\/ul>\n<p>It is reported that existing techniques often sacrifice motion dynamics when enhancing stable visual quality, limit video duration (typically 5-10 seconds) in order to prioritize high resolution, and lead to insufficient shot-aware generation due to the inability of the Universal Multimodal Large Language Model (MLLM) to decode cinematic syntax (e.g., shot composition, actor expression, and camera motion). These interrelated limitations hinder realistic compositing and professional cinematic style generation for long videos.<\/p>\n<p>SkyReels-V2 is a technological breakthrough that also provides a variety of useful application scenarios, including story generation, graphic video, mirror experts and multi-subject consistent video generation (SkyReels-A2).<\/p>\n<p>SkyReels-V2 is now supported<strong>Generate 30-second, 40-second videos<\/strong>and has the ability to generate high motion quality, high consistency, and high fidelity video.<\/p>\n<p>Officially, SkyReels-V2 excels in motion dynamics, generating smooth and lifelike video content that meets the demand for high-quality motion dynamics in movie production.<\/p>","protected":false},"excerpt":{"rendered":"<p>April 21, 2011 - Kunlun World Wide Web today officially released and open-sourced SkyReels-V2, the world's first unlimited duration movie generation model using the Diffusion-forcing framework, which achieves synergistic optimization by combining Multimodal Large Language Modeling (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion-forcing frameworks. It achieves synergistic optimization by combining MLLM, Multi-stage Pretraining, Reinforcement Learning and Diffusion-forcing frameworks. Officially, the model will break through the boundaries of video generation technology, opening up a new era of \"unlimited time movie generation. 1AI with open source address as follows: SkyReels-V2 Git<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[4071,219,1050],"collection":[],"class_list":["post-33743","post","type-post","status-publish","format-standard","hentry","category-news","tag-skyreels","tag-219","tag-1050"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/33743","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=33743"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/33743\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=33743"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=33743"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=33743"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=33743"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}