Video · Alibaba

HappyHorse

文生视频、图生视频和视频编辑生成，支持 720p/1080p 输出、时长控制、首帧图片、角色模型有序参考图和源视频编辑。

运行中 · 4 variants · 起价 $0.480

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/happyhorse -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the HappyHorse skill for me:

1. Clone https://github.com/runapi-ai/happyhorse
2. Copy the skills/happyhorse/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

概览

HappyHorse 可根据提示词、首帧图片、角色模型有序参考图或源视频编辑指令创建视频片段，支持 720p 或 1080p 输出和 seed 控制。

多变体覆盖不同速度/质量层级
每种能力一个端点——text-to-X、image-to-X 等
按变体支持流式与异步模式
失败的生成不计费

变体

对比全部变体

Variant	Billing	From
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 →

AGENT USAGE

从 prompt 到工具调用

Typed schema · 调用前已验证

# User prompt to the agent
"生成一段 5 秒 1080p 电影感视频：纸马在夜晚的迷你纸板城市中奔跑。"

// Code generated by the agent via @runapi.ai/happyhorse
import { HappyhorseClient } from '@runapi.ai/happyhorse';

const client = new HappyhorseClient();
const result = await client.textToVideo.run({
  model: 'happyhorse-character',
  prompt: '生成一段 5 秒 1080p 电影感视频：纸马在夜晚的迷你纸板城市中奔跑。',
});

@runapi.ai/happyhorse npm

工作流程

四步从安装到首次结果

安装

一条 CLI 命令把技能包装进 agent。

配置

设置变体 ID 与 RunAPI key。配置就这么简单。

调用

Agent 发出一个 typed 工具调用。Schema 已校验，无 glue code。

接收

把结果流回 agent loop。已缓存、已签名、即可用。

SDK QUICKSTART

直接从代码调用

runapi.ai

curl -X POST https://runapi.ai/api/v1/happyhorse/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "happyhorse-character",
  "prompt": "生成一段 5 秒 1080p 电影感视频：纸马在夜晚的迷你纸板城市中奔跑。"
}'

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

const client = new HappyhorseClient();
const result = await client.textToVideo.run({
    model: "happyhorse-character",
    prompt: "生成一段 5 秒 1080p 电影感视频：纸马在夜晚的迷你纸板城市中奔跑。",
});

require "runapi/happyhorse"

client = RunApi::Happyhorse::Client.new
result = client.text_to_video.run(
    model: "happyhorse-character",
    prompt: "生成一段 5 秒 1080p 电影感视频：纸马在夜晚的迷你纸板城市中奔跑。"
)

@runapi.ai/happyhorse v1

背景