Video · Alibaba

HappyHorse API

Text, image, and edit-video generation with 720p and 1080p output, duration control, first-frame image support, ordered reference images for character-guided clips, and source-video editing.

可正常運作 · 7 variants · 由 $0.480

在 playground 試用 API reference →

runapi.ai

curl -X POST https://runapi.ai/api/v1/happyhorse/image_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "happyhorse-text-to-video",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night."
}'

import { HappyhorseClient } from "@runapi.ai/happyhorse";

const client = new HappyhorseClient();
const result = await client.imageToVideo.run({
    model: "happyhorse-text-to-video",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night.",
});

<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\Happyhorse\HappyhorseClient;

$client = new HappyhorseClient();
$result = $client->imageToVideo->run([
        'model' => 'happyhorse-text-to-video',
        'image_url' => 'https://cdn.runapi.ai/public/samples/image.jpg',
        'prompt' => 'Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night.',
]);

require "runapi/happyhorse"

client = RunApi::Happyhorse::Client.new
result = client.image_to_video.run(
    model: "happyhorse-text-to-video",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night."
)

npx skills add runapi-ai/happyhorse -g

# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor

@runapi.ai/happyhorse v1

OVERVIEW

HappyHorse creates text, image, and edit-video clips with selectable 720p or 1080p output, deterministic seed control, first-frame image guidance, ordered reference-image guidance for the character model, and source-video edit instructions.

多個變體，對應不同速度／品質層級
Model skill 包含文件、schema 與 setup 備註
支援 app-focused coding workflows
生成失敗不收費

VARIANTS

比較所有 API 變體

Variant	Billing	From
happyhorse-1.0-i2v	second	$0.540	查看 →
happyhorse-1.0-r2v	second	$0.540	查看 →
happyhorse-1.0-t2v	second	$0.540	查看 →
happyhorse-character	second	$0.480	查看 →
happyhorse-edit-video	second	$0.480	查看 →
happyhorse-image-to-video	second	$0.480	查看 →
happyhorse-text-to-video	second	$0.480	查看 →

SKILLS

為 app 開發安裝 HappyHorse skill

將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。

# Install the model skill for app development workflows
npx skills add runapi-ai/happyhorse -g

Installs docs, schemas, pricing context, and setup notes into your developer workspace.

Or use this setup request in your coding tool:

Install the HappyHorse skill for this app:

1. Add runapi-ai/happyhorse with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.

運作方式

從 model skill 到第一次結果，只需四步

選擇模型

挑選符合輸出類型、品質門檻與延遲目標的模型與變體。

設定

設定 RunAPI key，並在 coding workspace 安裝 model skill。

開發

使用 skill 指引，在你的 app 內加入模型功能。

接收

透過 task ID 查詢、在支援時串流，或處理 webhook callback。

CONTEXT

HappyHorse API 是甚麼？

HappyHorse belongs to the Alibaba catalog on RunAPI and exposes canonical text-to-video, image-to-video, and edit-video capabilities across API, SDK, CLI, Bruno, and docs surfaces.

Provider

Alibaba

Modality

Video

點解揀 RunAPI

為何透過 RunAPI 使用 HappyHorse API

一個驗證，對應所有 provider

一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶，亦無需為每個整合輪換密鑰。

統一定價與計費

按次以 USD 收費，每月結算。失敗的生成不會收費。

內含 schema 的 skill

型別化 schema 與 setup 備註打包在 model skill 內，讓實作從正確契約開始。

FAQ

常見問題

What can HappyHorse create?

HappyHorse offers text-to-video from a prompt, character-guided text-to-video from a prompt plus ordered reference images, image-to-video from one first-frame image, and edit-video from one source clip.

What resolutions does HappyHorse support?

All HappyHorse video endpoints support 720p and 1080p output. 1080p is the default, while 720p is useful for drafts and social clips.

How long can HappyHorse videos be?

HappyHorse video generation endpoints support integer durations from 3 to 15 seconds, while edit-video accepts a 3-60 second source video.

How does image-to-video use the input image?

Image-to-video accepts exactly one public image URL and treats it as the first frame before generating motion from the prompt and settings.

How does the character model use reference images?

The character model accepts 1-9 public image URLs on the text-to-video endpoint; their order maps to character1, character2, and later references in the prompt.

How does edit-video use the source video?

Edit-video accepts one public MP4 or MOV source video, an edit instruction, and up to 5 optional reference images.

Can I reproduce a HappyHorse result?

You can pass a seed to make generation more deterministic for the same prompt, media, and resolution.

我應該先用邊個版本？

先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本，之後再升級到 pro 用於正式生產。

有免費方案嗎？

新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。

你哋支援串流結果嗎？

如有提供串流，RunAPI 會端到端串流。

失敗會點樣收費？

生成失敗不會收費。