What Is HappyHorse? Alibaba's Video Model, Explained From the Schema
HappyHorse 1.1 does three jobs and conspicuously not a fourth. The actual parameters, the two defaults that waste your first generation, and where it beats better-known models.
HappyHorse is Alibaba's video generation model, and it is the one doing most of the quiet work in vertical creator content in 2026 — well known to people building pipelines, largely unknown to people buying subscriptions. Here is what it actually is, taken from the endpoint schema rather than the marketing.
Three endpoints, and one that does not exist
HappyHorse 1.1 ships text-to-video, image-to-video and reference-to-video. The family's video-edit endpoint exists too, but it is still version 1.0.
That split is the single most important fact about it. The 1.1 generators cannot ingest a source video, so they cannot copy a specific clip's choreography or replace a performer in existing footage. If that is your job, the 1.1 endpoints are the wrong tool: use the 1.0 video-edit model (what our autopilot runs) or, for choreography, Kling Motion Control. Note also that a competing replace-a-person model, MiniMax H3 Max Recast, appeared on fal in October 2026; we have not yet tested it against HappyHorse on our own clips, and say so in our Recast guide.
The 1.1 release in June 2026 added native audio, multilingual lip-sync, up to nine character references and 1080p. It did not upgrade the video-edit model, which stayed at 1.0.
What reference-to-video actually takes
From the endpoint schema:
| Parameter | Values | Default |
|---|---|---|
image_urls | 1–9 reference images | required |
prompt | up to 2,500 characters | required |
duration | 3–15 seconds | 5 |
resolution | 720p, 1080p | 1080p |
aspect_ratio | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5 | 16:9 |
seed | 0–2147483647 | random |
enable_safety_checker | boolean | true |
Reference images must be JPEG, PNG or WEBP, shortest side at least 400px (720p or better recommended), max 20 MB each.
The two defaults that waste your first run
aspect_ratio defaults to 16:9. For a model whose main audience is vertical creators, that is a landscape clip you cannot post. Set it to 9:16 for Reels, TikTok and Shorts, or 4:5 for feed. Nine ratios are supported, including both vertical options — the full set of verticals is genuinely rare and one of the strongest reasons to pick this model.
duration defaults to 5 seconds — which is actually the right default, because identity holds best in the 5–8 second band. Resist raising it.
The thing nobody explains: how references work
You do not just upload photos. You cite them in the prompt as character1 through character9, in the order they appear in image_urls. So the prompt is not "a woman in a kitchen" — it is a description that names character1 and says what they do.
This is why supplying one frontal selfie produces poor results and why nine references produce good ones: the model is matching a named subject across angles, and you have given it one angle to work from.
Price and positioning
$0.14 per second on both image-to-video and reference-to-video at 720p (read live from fal.ai; 18 October 2026 confirmed it). 1080p, the endpoint default, bills about twice that, so set resolution deliberately.
A 5-second 720p clip is $0.70; the 15-second maximum is $2.10.
Against alternatives at the same job: Kling 3.0 Pro image-to-video is also $0.14/s; MiniMax H3 (first generation) reference-to-video was $0.26/s. HappyHorse's edge is the aspect-ratio coverage and native multilingual lip-sync in the same call. MiniMax H3 Max now lists reference-to-video at $0.05 per second base (768P), so the "$0.26" for the first H3 generation is out of date for the Max line.
When to use it
Yes: you have photos of a person and want them in a scene you describe; you want a talking-head clip with lip-sync in one call; you need real 9:16 or 4:5 output.
No: the movement has to match an existing clip, or the original background has to survive. Neither is what the 1.1 generators do, and no prompt makes it.
How to do this without code: HappyHorse reference-to-video is the model behind the Me in scene tool. In AutoHustle this is the Me in scene tool: a few photos of you and one sentence describing the scene (about 2 credits per second, quoted before you press Generate). See How to put yourself in any scene and Put yourself in a movie scene.
Related reading: HappyHorse 1.1 Reference-to-Video: How Many Photos You Really Need and What It Costs (October 2026) · Kling O3 Reference-to-Video on fal: Put a Character From Photos Into a New Scene (October 2026)