AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Alibaba's earlier HappyHorse. A clip from a prompt or one opening picture, or from reference pictures you name in the prompt.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
HappyHorse 1.0 is Alibaba's earlier HappyHorse video model. It is the same kind of clip as HappyHorse 1.1: text, one opening picture, or reference pictures.
Alibaba lists HappyHorse 1.0 beside 1.1 for text-to-video, a first-frame picture, and reference-to-video. 1.1 is the model they describe with the newer motion and the steadier multi-picture reference. 1.0 is the earlier model in that family.
Write the shot, or give one picture as the opening frame. Or open HappyHorse 1.0 Reference, attach two to nine pictures, and name them @image1 onward. There is no closing frame and no sound switch.
HappyHorse 1.1 is the later model Alibaba recommends for this job. Wan 2.7 takes an opening and a closing frame and has Enhance. HappyHorse 1.0 takes one opening picture, or the named reference set.
Alibaba's current description of improved motion and reference stability is on 1.1. 1.0 remains the earlier model with the same way of starting a clip.
Two to nine, named @image1 onward.
No. One opening picture, or text, or the reference set.
No.
