Video

HappyHorse

HappyHorse is Alibaba's video generation and editing model for text-to-video, image-to-video, reference-guided generation, and video editing. Create cinematic short-form clips, ecommerce ads, digital-human presenter videos, and social content in one place.

Start creating API Docs

HappyHorse 720p / 1080p

HappyHorse 3–15 seconds

HappyHorse text, image, reference, edit

HappyHorse native audio output

$0.125 / second

Generated preview

HappyHorse

Start now

Create with HappyHorse

Loading workspace...

Authentication & Integration

Checking API access...

Sign in to claim free credits and create with this model.

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

POSThttps://api.apixo.ai/api/v1/generateTask/happyHorseCreate task

GEThttps://api.apixo.ai/api/v1/statusTask/happyHorse?taskId={taskId}Poll status

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

Parameters

moderequired

Typeselect

Choose whether HappyHorse should create a clip from text, animate one image, follow multiple references, or edit an existing video.text-to-video · image-to-video · reference-to-video · video-edit

promptrequired

Typestring

Describe the scene, subject, motion, camera language, style, and audio cues. Prompt quality has a direct impact on video quality.

resolutionrequired

Typeselect

720p is the lowest-cost production option. Choose 1080p when higher output detail matters.720p · 1080p

durationrequired

Typeselect

Output length for text-to-video, image-to-video, and reference-to-video. Video-edit billing uses input video duration instead.3 · 5 · 10 · 15Only in mode=text-to-video | image-to-video | reference-to-video

ratioconditional

Typeselect

Supported for text-to-video and reference-to-video. Image-to-video follows the uploaded first frame.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video | reference-to-video

audio_settingconditional

Typeselect

Video-edit only. Auto lets HappyHorse infer audio, while origin keeps source-video audio when supported.auto · originOnly in mode=video-edit

watermarkoptional

Typeboolean

Add or remove a watermark on the generated output.

seedoptional

Typetext

Optional random seed from 0 to 2147483647 for repeatable generations.

Parameter	Type	Required	Description
`mode`	select	required	Choose whether HappyHorse should create a clip from text, animate one image, follow multiple references, or edit an existing video.text-to-video · image-to-video · reference-to-video · video-edit
`prompt`	string	required	Describe the scene, subject, motion, camera language, style, and audio cues. Prompt quality has a direct impact on video quality.
`resolution`	select	required	720p is the lowest-cost production option. Choose 1080p when higher output detail matters.720p · 1080p
`duration`	select	required	Output length for text-to-video, image-to-video, and reference-to-video. Video-edit billing uses input video duration instead.3 · 5 · 10 · 15Only in mode=text-to-video \| image-to-video \| reference-to-video
`ratio`	select	conditional	Supported for text-to-video and reference-to-video. Image-to-video follows the uploaded first frame.16:9 · 9:16 · 1:1 · 4:3 · 3:4Only in mode=text-to-video \| reference-to-video
`audio_setting`	select	conditional	Video-edit only. Auto lets HappyHorse infer audio, while origin keeps source-video audio when supported.auto · originOnly in mode=video-edit
`watermark`	boolean	optional	Add or remove a watermark on the generated output.
`seed`	text	optional	Optional random seed from 0 to 2147483647 for repeatable generations.

File parameters (URL arrays)

image_urls[mode=image-to-video | reference-to-video | video-edit]Image-to-video requires exactly one first-frame image. Reference-to-video supports 1–9 reference images. Video edit accepts up to 5 optional reference images.Only in mode=image-to-video | reference-to-video | video-edit

video_urls[mode=video-edit]Upload exactly one source video for video-edit mode.Only in mode=video-edit

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/happyHorse" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic rainy night in tokyo",
      "resolution": "720p",
      "ratio": "16:9",
      "duration": 5,
      "watermark": false
    }
  }'

Full API documentation

HappyHorse Tips

Create more with HappyHorse

Create

Start with an idea

Pick a model, tune the settings, and create in one place.

Write an idea

Describe what you want to make.

Use an example

Start from a ready-made style.

Adjust the look

Tune the key settings quickly.

Create

Generate when everything feels right.

Keep results

Save what you want to revisit.

Try again

Make the next version faster.

HappyHorse model details

Key HappyHorse options available on APIXO.

HappyHorse Modes

Text, image, reference, video edit

HappyHorse Image References

1 image or 1–9 references

HappyHorse Resolution

720p and 1080p

HappyHorse Workflow

Async task with polling or callback

Capabilities

Key HappyHorse capabilities

HappyHorse short-drama detail

HappyHorse performs well in short-drama production where plot detail, lighting atmosphere, and character consistency need to hold across a compact scene.

HappyHorse ecommerce ad production

The HappyHorse API supports natural digital-human presenter videos and high instruction following, making it useful for batch production of merchant ad materials.

HappyHorse social creative iteration

HappyHorse can quickly produce polished, tightly paced clips that adapt to multiple social styles, with especially useful image-to-video behavior for lowering production effort.

What can you build with HappyHorse?

HappyHorse film and short-drama scenes

Use HappyHorse to generate story beats with controlled atmosphere, character action, and cinematic framing for concept validation or short-form narrative production.

HappyHorse product and ecommerce ads

Turn product stills, campaign prompts, and presenter concepts into HappyHorse motion assets for listings, landing pages, and paid social.

HappyHorse digital-human presenter clips

Create HappyHorse presenter-style videos where script direction, gesture, and brand tone need to stay aligned with the prompt.

HappyHorse social creative videos

Produce visually polished HappyHorse clips for short-video platforms, from surreal ideas to realistic lifestyle scenes and fast meme-driven concepts.

Read FAQ

HappyHorse notes and questions

HappyHorse API prompt is required for text-to-video, reference-to-video, and video-edit, and can be up to 2500 characters.

HappyHorse image-to-video requires exactly one image. The image locks the first frame, so crop it to the target composition before upload.

HappyHorse reference-to-video requires 1–9 reference images and uses those images as visual guidance, not as a fixed first frame.

HappyHorse video-edit requires exactly one input video and can accept 0–5 optional reference images.

HappyHorse video-edit does not expose public output duration; billing is based on min(input video duration, 15) × 2 × the selected resolution rate.

HappyHorse output includes audio by default, and inference audio cannot be fully disabled.

For long-running tasks, callback mode is recommended over frequent polling.

HappyHorse image-to-video starts from exactly one image and locks it as the first frame. HappyHorse reference-to-video uses 1–9 images as style, subject, or scene references while generating a new video.

APIXO

Create with HappyHorse

Write a prompt, adjust the style, and generate your next image in one place.

Start creating View API docs