HappyHorse 1.0 is an AI video model from Alibaba which was released int he end of April 2026. It can make 1080p videos from text, images and other videos. It also adds synced sound and lip sync in more than one language.
The model showed up first on test sites without a clear owner. It moved up fast in text-to-video and image-to-video rankings. Alibaba later said it made the model through its ATH AI unit.
HappyHorse-1.0 supports text-to-video, image-to-video, reference-based video and video editing with simple text prompts. It can use up to 5 image references. It also supports 16:9, 9:16, 1:1, 4:3 and 3:4 formats.
The model is offered through paid API. Its license has not been shared.
Its main strength is short clips. Early users say 3 to 5 second videos can look strong-ish. But longer clips up to 15 seconds reportedly can lose quality, with motion and realism issues.
If you'd like to access this model, you can explore the following possibilities:
