LibTV has launched an Agent feature and built-in Skill Hub, offering over 100 video skills covering
wuxia movies, Pixar animated ads, e-commerce broadcasts, and more. After users input ideas, the Agent analyzes the requirements and asks for directions, automatically generating video storyboards and linking them into a complete node workflow, with each node able to view and modify prompts. After generation, LibTV will activate a self-check mechanism to automatically detect and repair problematic footage. Storyboard View provides an overview of image and video assets, supporting direct access to the editing timeline within the finished video for fine adjustments. Users can also create their own Skills by uploading three files without coding. In actual testing, Agent can output coherent storylines with Cantonese dubbing and supports bilingual subtitle generation.
LibTV推出Agent功能并内置Skill Hub,提供100多个覆盖武侠电影、皮克斯动画广告、电商口播等类型的视频Skill。
用户输入想法后,Agent会分析需求并询问方向,自动生成视频分镜并串联成完整节点工作流,每个节点可查看和修改提示语。
生成后LibTV会启动自查机制,自动检测并返修有问题的镜头。
故事板视图提供图片与视频资产总览,支持在成片中直接打开剪辑时间线进行精细调整。
用户还可自行创建Skill,上传三个文件即可,无需编程。
实测中,Agent能输出剧情连贯、带粤语配音的成片,并支持双语字幕生成。
The readable text on this page was extracted from the public source and organized with attribution, publication time and the original link. Copyright remains with the original author and publisher.