HappyHorse 1.0 I2V
AI generationAlibabaAlibaba ATH HappyHorse-1.0. Joint audio + video in one pass. #1 on Artificial Analysis I2V leaderboard. Identity-preserving on faces and subjects.
- Runs
- On our servers
- Typical time
- 30-180s
- Inputs
- 2
- Outputs
- 1
Inputs
| Port | Type | ID |
|---|---|---|
| Prompt | text | prompt-in |
| Image | image | image-in |
Outputs
| Port | Type | ID |
|---|---|---|
| Video | video | video-out |
Settings
| Setting | Type | Default | Options |
|---|---|---|---|
| DurationLength of the output. Joint audio scales with duration. | select | 5 | 3 seconds, 5 seconds, 8 seconds, 10 seconds |
| Resolution | select | 720p | 720p, 1080p |
| SeedFixed number for reproducible results, 0 = random | number | 0 | 0 to 2147483647 |
Prompting
Describe the motion + ambient audio. Joint audio is generated automatically (no toggle).
Maximum prompt length: 2000 characters.
What this connects into (19)
Computed from the port compatibility rules, so it stays correct as nodes change.
Node ID happyhorse-i2v. Open it in Studio with Tab, then type the name.