HappyHorse Video API · Unified video generation and editing interface

HappyHorse Video API

Use a stable REST API for text-to-video, first-frame image-to-video, reference image-to-video, and video editing. Ideal for integrating creative storyboards, product assets, character references, and post-production workflows into your own product.

4 actions720P / 1080PAsynchronous callbacks + task queries
🎬
4
Generation and editing modes
⏱️
3-15s
Output video duration
🖼️
1-9
Number of reference images
📡
REST
Unified API entry point

Covering key video production tasks

Use a unified request structure to complete common video generation and editing tasks.

✍️

Text-to-video

Enter shot descriptions, scenes, and actions to quickly generate short video prototypes.

🖼️

First-frame image-to-video

Use a fixed first frame to control composition and bring static visual assets to life naturally.

🎭

Reference image-to-video

Use multiple reference images to constrain characters, props, styles, and visual elements.

✂️

Video editing

Perform style transfer, outfit changes, and local replacements based on input videos and reference images.

curl
curl -X POST 'https://api.acedata.cloud/happyhorse/videos' \
  -H 'authorization: Bearer YOUR_API_KEY' \
  -H 'accept: application/json' \
  -H 'content-type: application/json' \
  -d '{
    "action": "image_to_video",
    "model": "happyhorse-1.1-i2v",
    "image_url": "https://cdn.acedata.cloud/b1c82e4937.png",
    "prompt": "A cinematic white horse lifts its head, the mane moves gently in the sunrise wind, slow camera push in, warm film lighting",
    "resolution": "720P",
    "duration": 5,
    "async": true
  }'

Submit a video task with one request

Use async to immediately return a task ID, then query the result through /happyhorse/tasks; if callback_url is provided, the final result will be pushed to your service after the task is completed.

1

Choose an action

Text-to-video, image-to-video, reference images, and editing all use the same endpoint.

2

Provide assets

Images and videos must be publicly accessible URLs; using Ace Data Cloud CDN is recommended.

3

Query results

Use task_id to obtain the final CDN video URL, duration, and resolution.

Three scenarios for real product integration

From marketing assets to content tools, HappyHorse is better suited as a reliable video capability module rather than a one-time toy.

Brand short film prototypes

Quickly generate short clips of products, characters, and scenes from text and first frames to validate visual direction.

Character and prop consistency

Use multiple reference images to lock in characters, clothing, props, and visual style.

Video post-production editing

Apply style transfer, local replacement, and audio preservation strategies to existing clips.

Launch video capabilities in three steps

Reuse Ace Data Cloud's unified authentication, billing, task, and callback model for a clear and controllable integration path.

01

Request a Token

Create an application in the console to obtain a unified Bearer Token.

02

Submit a task

Provide prompt, image_url, image_urls, or video_url according to the action.

03

Retrieve results

Get a downloadable CDN video URL through the task API or callback.

Why use a unified API?

Consolidate model invocation, task polling, CDN transfer, error classification, and billing records on the platform side.

EndpointsAce Data Cloud HappyHorseSome Others
Multiple video actionsUnified /happyhorse/videosManually combine multiple endpoints
Output filesAutomatic CDN transferTemporary URLs commonly expire
BillingCharged by actual duration in secondsA separate usage ledger is required
Failure handlingStructured error codesInconsistent error messages

Choose a Model by Task

1.1 models are prioritized for generation tasks; video editing currently uses 1.0 video-edit.

T2V

happyhorse-1.1-t2v

The default text-to-video model, suitable for generating short videos from scripts and shot descriptions.

I2V

happyhorse-1.1-i2v

Controls composition and visual tone with a first-frame image, suitable for animating product and character images.

R2V

happyhorse-1.1-r2v

Uses multiple reference images to constrain characters and props, suitable for scenarios with higher consistency requirements.

EDIT

happyhorse-1.0-video-edit

Edits based on input video, with the option to preserve the original audio.

Clear per-second pricing

Failed tasks are not billed; video editing is billed based on the combined input and output duration.

720P generation

低至 $0.105 / 秒
  • Ideal for rapid prototyping
  • Supports t2v / i2v / r2v
  • 3–15 second output
查看价格

Video editing

按实际秒数
  • Input + output duration
  • Supports reference images
  • Original audio can be retained
查看参数

Frequently Asked Questions

The parameters, assets, and billing questions you are most likely to care about before launch.

What input assets does HappyHorse support?

Text-to-video requires only a prompt; first-frame image-to-video requires image_url; reference-image-to-video requires 1–9 image_urls; video editing requires video_url and optionally supports 0–5 reference images.

Do the returned video URLs expire?

The documentation and API responses provide accessible CDN URLs.

How should long-running generation be handled?

It is recommended to use async or callback_url. The API first returns a task_id; you can actively query /happyhorse/tasks or wait for the callback.

Are failed tasks charged?

No. Only tasks that complete successfully and record results are billed based on duration and resolution.

Integrate HappyHorse into Your Video Product

Use unified Tokens, unified billing, and unified task queries to reliably integrate video generation and editing capabilities into your application.