alibaba/happyhorse-1.1/text-to-videoHappyHorse 1.1 text-to-video is Alibaba's video model turning a written brief into a 3 to 15 second clip with generated sound. Choose 720p or 1080p and one of nine aspect ratios from 21:9 to 9:21; the default is 720p at 16:9.
Filtering differs by endpoint: Image to video — Uncensored, Reference to video — Uncensored, Text to video — Filtered.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
motel-blinds-boots A whole chain of movement — heel against toe, a boot coming off, a slow fall backwards — held inside the five seconds this endpoint runs by default at 720p. Nothing lights the room except the prompt, and the blind bars crawling across her are the part worth watching.
- 720p
- 16:9
- 5s
- Output6s
rain-hood-convenience Written from nothing at `aspect_ratio` `9:16` and `resolution` `1080p` for six seconds, the vertical end of the nine frames this endpoint offers. The brief spends its words on one continuous action away from camera and on the light behind her, which is what the rain has to read against. Sound is generated in the same pass, so the rain on the awning arrives with the picture instead of being laid under it afterwards.
- 1080p
- 9:16
- 6s
- Output5s
desert-tailgate The written brief behind the clip on this page: backlight, dust and flare all described in one paragraph, at five seconds and 720p.
- 720p
- 16:9
- 5s
- Output5s
karaoke-room Two people in one vertical frame, plus a deliberately degraded phone-camera look. The karaoke room comes back with generated sound, even though no endpoint in this family has an audio field.
- 720p
- 9:16
- 5s
This example starts at $0.14 per output second. The Playground updates the estimate when you change the settings.