Question 1

What is Happy Horse Image-to-Video?

Accepted Answer

Happy Horse Image-to-Video animates a still image into 1080p video with synchronized native audio and multilingual lip-sync. Drop in a portrait, product shot, or scene; the model fills in motion that's consistent with the source. If the image contains a face, lips track any generated dialogue across 30+ languages.

Question 2

How much does Happy Horse Image-to-Video cost on Runflow?

Accepted Answer

$0.14 per second of output at 720p, and $0.28 per second at 1080p. Per-second billing, no minimums. A typical 5-second 720p clip costs $0.70.

Question 3

What image formats and sizes are supported?

Accepted Answer

JPEG, JPG, PNG, BMP, and WEBP up to 10 MB. The shortest side must be at least 300 pixels. Aspect ratio must be between 1:2.5 and 2.5:1 — output preserves the source ratio.

Question 4

How long does a generation take?

Accepted Answer

Typical latency is 60-180 seconds for a 5-second clip. Image-to-video is slightly slower than text-to-video because the model encodes the source image first. Runflow routes across regions to keep latency stable during demand spikes.

Question 5

Can I use Happy Horse output commercially?

Accepted Answer

Yes — Runflow grants commercial use rights for everything generated via the API, including ads, e-commerce, and SaaS products. No additional licensing.

Question 6

Do I need to manage GPUs or infrastructure?

Accepted Answer

No. Runflow handles GPU provisioning, queueing, multi-region failover, and scaling. One HTTP call returns a video URL. No DevOps team needed.

Parameter	Type	Required	Description
image_url	image	required	URL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Dimensions must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1. Max 10 MB.
duration	integer	optional	Output video duration in seconds (3-15).
prompt	string	optional	Optional text prompt guiding the animation. Max 2500 characters.
enable_safety_checker	boolean	optional	Enable content moderation for input and output.
resolution	string	optional	Output video resolution tier.
seed	integer	optional	Random seed for reproducibility (0-2147483647).

Field	Type	Description
outputs	json	Unified output array — one entry per generated artifact with url/type/width/height/duration/etc.
seed	json	Deterministic seed used for generation, or null if the provider doesn't return one.
timing	json	Provider timing info (inference_ms etc.), or null.
nsfw_detected	json	true if the provider flagged output as NSFW, false if cleared, null if not checked.

alibaba/happy-horse/image-to-video

Install

Run the model

Input schema

Output schema

Related models

Start generating with Happy Horse Image-to-Video