阿里发布电影级视频模型万相2.6

Core Viewpoint - Alibaba has launched the new generation of the Wanshang 2.6 model, which is the first video model in China to support role-playing functions, aimed at professional film production and image creation scenarios [1][3]. Group 1: Model Features - The Wanshang 2.6 model includes features such as audio-visual synchronization, multi-camera generation, and sound-driven capabilities [1][3]. - It has improved video quality, sound effects, and instruction adherence, achieving the highest single video duration of 15 seconds in China [1][3]. - The model allows for one-click completion of videos featuring single or multiple characters, as well as automatic multi-camera switching to meet professional film-level requirements [1][3]. Group 2: User Experience - Users can upload personal videos and input sci-fi or suspense-themed prompts, enabling the model to quickly design storyboards, perform character portrayals, and provide voiceovers, resulting in a complete short film in just a few minutes [1][3]. - The model can generate complete narrative shorts for advertising and short drama production by inputting continuous prompts, maintaining consistency in key information during multi-camera transitions [2][4]. Group 3: Accessibility and Applications - The Wanshang 2.6 model is now available for direct experience on the Wanshang official website, and enterprise users can access the model API through Alibaba Cloud [2][4]. - The Wanshang model family supports over ten visual creation capabilities, including text-to-image, image editing, text-to-video, image-to-video, voice generation, action generation, role-playing, and general video editing, widely applied in AI comics, advertising design, and short video creation [2][4].