Alibaba's HappyHorse 1.1 video model hits No. 2 on Arena rankings as Sora and Seedance exit market
AI video model releases
Alibaba's HappyHorse 1.1 video model hits No. 2 on Arena rankings as Sora and Seedance exit market
Alibaba Cloud released HappyHorse 1.1 on Sunday, an upgraded AI video generation model live on Alibaba Cloud Model Studio with full API access and a 40% launch discount for two weeks
On the Artificial Analysis Video Arena, HappyHorse 1.0 ranks No. 2 across all three leaderboards, scoring 1,444 in both text-to-video and image-to-video, beating Google's Veo-3.1 by 69 points and xAI's Grok-Imagine-Video by 23 points
The release follows OpenAI's discontinuation of Sora for being financially unsustainable and ByteDance's indefinite shelving of Seedance 2.0's international rollout after Hollywood copyright complaints
HappyHorse is built on a 15-billion-parameter unified self-attention Transformer that processes text, image, video, and audio tokens in a single generation pass, avoiding separate dubbing or post-processing tools
The 1.1 upgrade adds R2V (Reference-to-Video), letting users upload multiple character reference images to keep identity consistent across shots, plus improved motion modeling and visual texture for commercial production use
cho.sh