{"id":28953,"date":"2025-02-18T10:58:08","date_gmt":"2025-02-18T02:58:08","guid":{"rendered":"https:\/\/www.1ai.net\/?p=28953"},"modified":"2025-02-18T10:58:08","modified_gmt":"2025-02-18T02:58:08","slug":"%e6%98%86%e4%bb%91%e4%b8%87%e7%bb%b4%e5%bc%80%e6%ba%90%e5%9b%bd%e5%86%85%e9%a6%96%e4%b8%aa%e9%9d%a2%e5%90%91-ai%e7%9f%ad%e5%89%a7%e5%88%9b%e4%bd%9c%e7%9a%84%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/28953.html","title":{"rendered":"KunlunWanwei Open Source China's First Video Generation Model for AI Short Drama Creation SkyReels-V1"},"content":{"rendered":"<p>February 18th.<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>Announced today<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 first nationally oriented <a href=\"https:\/\/www.1ai.net\/en\/tag\/ai%e7%9f%ad%e5%89%a7\" title=\"[View articles tagged with [AI skit]]\" target=\"_blank\" >AI skits<\/a>creative<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a7%86%e9%a2%91%e7%94%9f%e6%88%90%e6%a8%a1%e5%9e%8b\" title=\"_Other Organiser\" target=\"_blank\" >Video Generation Model<\/a> <strong>SkyReels-V1<\/strong>The first SOTA-rated video base model-based algorithm for controlling facial expressions in China.\u00a0<strong>SkyReels-A1<\/strong>.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-28954\" title=\"5abce165j00sruyve009ud000m700cbp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/02\/5abce165j00sruyve009ud000m700cbp.jpg\" alt=\"5abce165j00sruyve009ud000m700cbp\" width=\"799\" height=\"443\" \/><\/p>\n<p>The official introduction of Kunlun Wanwei said that SkyReels-V1 made marking for the details of the performance, and also dealt with the emotions, scenes, and performance appeals.<strong>Training fine-tuning with \"10 million, high quality\" Hollywood-grade data<\/strong>.<\/p>\n<p>In addition, SkyReels-V1 realizes \"micro-expression generation for movie and TV characters\".<strong>Supports 33 character expressions and 400+ natural movement combinations<\/strong>It supports the generation of micro-expressions such as laughing, roaring, surprised, crying, etc. It also supports the generation of micro-expressions of real people's emotions.<\/p>\n<p>Based on Hollywood-grade movie and television data training, every frame generated by current SkyReels is claimed to have a \"<strong>Cinematic textures<\/strong>\u201d.<\/p>\n<p>SkyReels-V1 not only supports Vincennes videos.<strong>Also supports graphic video<\/strong>It is claimed to be \"the model with the largest parameter in the open source video generation model that supports graph-generated video\", and achieves the open source SOTA under the same resolution in various indexes.<\/p>\n<p>To summarize, SkyReels-V1 can deliver:<\/p>\n<ul>\n<li><strong>Movie Expressions Recognition System<\/strong>: 11 character expression comprehension for expressions of disdain, impatience, helplessness, and disgust in film and theater;<\/li>\n<li><strong>Character spatial location awareness<\/strong>Based on the human body 3D reconstruction technology, it realizes the understanding of the spatial relative relationship of multiple people in the video, and helps the model to generate film and television level character station;<\/li>\n<li><strong>Understanding of Behavioral Intent<\/strong>: Constructs more than 400 kinds of behavioral semantic units to achieve accurate understanding of character behavior;<\/li>\n<li><strong>Performance Scene Understanding<\/strong>: Realizing character-costume-scene-plot correlation analysis.<\/li>\n<\/ul>\n<p>In terms of performance, with the support of the self-developed inference optimization framework \"SkyReels-Infer\", the<strong>The model achieves 544p resolution, with inference based on a single 4090 in 80s, and also supports distributed multi-card parallelism.<\/strong>It supports Context Parallel, CFG Parallel, and VAE Parallel.<\/p>\n<p>In addition, the model adopts fp8 quantization and parameter-level offload to meet the running requirements of user-level graphics cards with low graphics memory; supports flash attention, SageAttention, and model compilation optimization to further optimize the latency; and is based on the open-source diffuser library to enhance the ease of use.<\/p>\n<p>In order to realize more accurate and controllable character video generation, KunlunWanwei has also open-sourced the SOTA-level<strong>A video pedestal model-based algorithm for controllable expression movements SkyReels-A1<\/strong>The SkyReels-A1 supports video-driven, movie-quality expression capture against Runway's Act-One.<\/p>\n<p>SkyReels-A1 can be based on any human scale (including portraits, half and full body compositions).<strong>Generate character motion video<\/strong>.<\/p>\n<p>As shown in the figure below, using both the reference image (top) and the driver video (bottom left) as inputs, a new video was generated with the power of SkyReels-A1 - \"grafting\" the facial expressions and performance details from the driver video onto the character given the reference image. the facial expressions and performance details from the drive video were \"grafted\" onto the character of the given reference image.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-28955\" title=\"9ed8b802j00sruyuy005md000m500chp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/02\/9ed8b802j00sruyuy005md000m500chp.jpg\" alt=\"9ed8b802j00sruyuy005md000m500chp\" width=\"797\" height=\"449\" \/><\/p>\n<p><strong>Attach the open source address below:<\/strong><\/p>\n<ul>\n<li>SkyReels-V1: https:\/\/github.com\/SkyworkAI\/SkyReels-V1<\/li>\n<li>SkyReels-A1: https:\/\/github.com\/SkyworkAI\/SkyReels-A1<\/li>\n<\/ul>\n<p><strong>Technical report:<\/strong><\/p>\n<ul>\n<li>https:\/\/skyworkai.github.io\/skyreels-a1.github.io\/report.pdf<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>February 18, 2011 - Kunlun World Wide announced today that it has open-sourced SkyReels-V1, the first video generation model for AI short drama creation in China, and SkyReels-A1, the first SOTA-level video base model-based expression action control algorithm in China. Kunlun World Wide's official introduction said that SkyReels-V1 marks the details of the performances, and also processes the emotions, scenes, and performance demands. SkyReels-V1 marks performance details, processes emotions, scenes, performance demands, etc., and utilizes \"ten million-level, high-quality\" Hollywood-level data for training and fine-tuning. In addition, SkyReels-V1 can realize \"film and television level character micro-expression performance generation\", supporting 33 kinds of character expressions and 400+ kinds of natural movement combinations, restoring real human emotion expression, supporting the generation of laughter, roar, surprise, crying, and so on.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[4080,219,1050,460],"collection":[],"class_list":["post-28953","post","type-post","status-publish","format-standard","hentry","category-news","tag-ai","tag-219","tag-1050","tag-460"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/28953","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=28953"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/28953\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=28953"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=28953"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=28953"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=28953"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}