en.Wedoany.com Reported - Alibaba Cloud has launched an upgraded AI video generation model, HappyHorse 1.1, which now ranks second globally in AI video model scores after competitors like Seedance exited the market.

The new model is now available to developers and enterprise customers with full API access through Alibaba Cloud Model Studio. Alibaba is also offering a 40% introductory discount for the first two weeks after launch.

According to an independent benchmark platform based on blind user evaluations, HappyHorse ranks second on major AI video lists. In text-to-video generation tasks, the model surpasses several leading competitors, including Google's Veo 3.1, trailing only the top-ranked model.

HappyHorse 1.1 introduces multiple improvements, including support for multi-image references to maintain character consistency across scenes, smoother motion generation, more natural facial details, improved lip-sync accuracy, and better handling of complex prompts. Unlike many competing systems that rely on separate models for video and audio generation, HappyHorse adopts a unified architecture that can output more coordinated video and audio in a single generation process.

Currently, OpenAI has discontinued Sora, and ByteDance has paused the international release of Seedance 2.0 due to copyright issues. Alibaba is supporting this launch by establishing new data centers in France and Japan, aiming to attract enterprises developing AI video applications, and has positioned itself as a key player in the rapidly growing AI video generation market.

This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com