AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Alibaba's HappyHorse 1.1. A clip from a prompt or one opening picture, or from reference pictures you name. Audio is part of the model.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
HappyHorse 1.1 is Alibaba's HappyHorse video model, the upgrade to HappyHorse 1.0. Use it for a clip from a sentence, from one picture that starts the motion, or from several pictures that have to stay consistent.
Alibaba describes HappyHorse 1.1 as smoother, more coherent motion, steadier products, characters, and scenes from several reference pictures, a closer reading of what you asked for, richer visual detail, and audio that stays in step with the picture.
Write the shot, or give one picture as the opening frame. Or open HappyHorse 1.1 Reference, attach two to nine pictures, and name them @image1 onward in the prompt. There is no separate sound switch. There is no closing frame.
HappyHorse 1.0 is Alibaba's earlier HappyHorse, with the same way of starting a clip. Wan 3.0 can take an opening and a closing frame and has a sound switch. HappyHorse starts from one picture, or from the reference set.
Two to nine pictures on HappyHorse 1.1 Reference, named @image1 onward.
There is no sound switch. Alibaba describes audio that stays in step with the HappyHorse 1.1 clip.
No. One picture is the opening frame. A closing frame is Wan 3.0 or Kling 3.0.
1.0 is the earlier model, with the same prompt, opening picture, or named reference pictures. 1.1 is the upgrade Alibaba describes for motion and for holding those pictures steady.
