Hailuo Video Generation

Generate AI videos through AceDataCloud's Hailuo (MiniMax) API.

Authentication

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Start

curl -X POST https://api.acedata.cloud/hailuo/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "generate", "prompt": "a dolphin jumping through ocean waves at golden hour", "model": "minimax-t2v"}'

Models

Workflows

1. Text-to-Video

POST /hailuo/videos
{
  "action": "generate",
  "prompt": "a time-lapse of flowers blooming in a meadow",
  "model": "minimax-t2v"
}

2. Image-to-Video

Animate a still image into a video clip.

POST /hailuo/videos
{
  "action": "generate",
  "prompt": "gentle wind blows through the scene",
  "model": "minimax-i2v",
  "first_image_url": "https://example.com/landscape.jpg"
}

3. Image-to-Video (Director Mode)

More precise control over the animation.

POST /hailuo/videos
{
  "action": "generate",
  "prompt": "camera slowly zooms in while leaves fall gently",
  "model": "minimax-i2v-director",
  "first_image_url": "https://example.com/scene.jpg"
}

Parameters

Task Polling

POST /hailuo/tasks
{"task_id": "your-task-id"}

States: processing → succeed or failed.

Gotchas

• first_image_url is required for minimax-i2v and minimax-i2v-director models
• Director mode (minimax-i2v-director) provides finer camera/motion control than standard i2v
• The action field currently only supports "generate" — no extend or edit
• Flat pricing per generation regardless of model
• Use mirror: true to horizontally flip the output if needed