千问APP升级视频创作能力，“照片唱跳”走红

Core Insights - The article highlights the launch of the latest model Wan2.5 by Alibaba's Wanxiang, which significantly enhances video creation capabilities, including improved motion accuracy and body coordination, making it the first mobile AI assistant to support simultaneous audio and video output [1] Group 1: Product Features - Wanxiang 2.5 is one of the few video models in the industry that supports audio-visual synchronization, capable of understanding and generating multiple tasks across various modalities including text, images, video, and audio [1] - Users can generate a 1080P HD singing and dancing video of up to 10 seconds by simply uploading a photo and a text description without needing a template, showcasing versatility with different types of images [1][2] Group 2: Market Impact - The introduction of the photo dancing feature by Alibaba last year gained immense popularity, leading to viral videos featuring various characters, which has now been further enhanced with the integration of Wanxiang 2.5 [2] - The new capabilities have reignited user creativity on social media platforms, allowing for more innovative "photo singing and dancing" content, such as merging images and generating dynamic video effects [3] - The app achieved over 10 million downloads within just one week of public testing, surpassing other AI applications like ChatGPT, marking it as the fastest-growing AI application in history [3]