Explore Alibaba Cloud's HappyHorse audio-video generation family for text-led scenes, first-frame animation, visual references and documented editing workflows.
HappyHorse overview
A Model Studio family for short audio-video generation.
HappyHorse models are documented through Alibaba Cloud Model Studio. The family supports prompt-led scenes, first-frame animation and reference-led generation, with audio included in the documented generation endpoints.
Version 1.1 is the newer recommended generation for text, first-frame and reference workflows. The official text-instruction video editing endpoint remains assigned to HappyHorse 1.0.
Capabilities
Choose the endpoint that matches the source material and task.
Version guide
Generation and editing are not exposed through the same version set.
| Model | Official workflows | Page-safe summary |
|---|---|---|
| HappyHorse 1.0 | T2V, I2V, R2V, video editing | First documented generation, including a dedicated text-instruction editing endpoint. |
| HappyHorse 1.1 | T2V, I2V, R2V | Newer generation for text, first-frame and reference-led audio-video creation. |
Workflows
Use cases
HappyHorse FAQ
Review its official endpoint matrix and availability boundaries.