hailuo-video — Claude Code skill: AI video generation
hailuo-video generates video from text or animates images via AceDataCloud's Hailuo (MiniMax) API. Supports text-to-video, image-to-video, and director mode for precise camera and motion control.
Apache-2.0 235 installs ★ 17 updated 2026-10-25
npx skills add AceDataCloud/Skills --skill hailuo-video -a claude-codeWhat hailuo-video does
The skill calls Hailuo, MiniMax's video generator, through AceDataCloud. Three models: minimax-t2v creates clips from text prompts, minimax-i2v animates still images, minimax-i2v-director offers fine-grained camera and object motion control. Requests are async: the server returns a task ID that must be polled via /hailuo/tasks until completion.
Requires an AceDataCloud API key in ACEDATACLOUD_API_TOKEN inside ~/.openclaw/.env. Get the key from the Applications section at platform.acedata.cloud; use the service API key (starts with platform-...), not a management token. If Allowed APIs restrictions are on, include /hailuo/videos and /hailuo/tasks.
Models minimax-i2v and minimax-i2v-director require the first_image_url parameter pointing to the source image. Pricing is flat per generation across all models; control quality differs.
What it helps with
- generate video from a text scene description
- animate a static image into a short clip
- control camera movement and object motion via director mode
- poll video generation task status through
/hailuo/tasks
Example prompts for the agent
- Generate a video: dolphin jumping out of water at sunset, use
minimax-t2v - Animate
scene.jpg: gentle wind, leaves falling,minimax-i2v-directormodel - Check Hailuo task status for ID
abc123via/hailuo/tasks
How to install hailuo-video
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill hailuo-video -a claude-code2Manually: put the files in place
~/.claude/skills/hailuo-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/hailuo-video/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill hailuo-video -a codex2Manually: put the files in place
.agents/skills/hailuo-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill hailuo-video -a cursor2Manually: put the files in place
.cursor/skills/hailuo-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AceDataCloud/Skills skills/hailuo-video2Manually: put the files in place
.github/skills/hailuo-video/SKILL.md1Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill hailuo-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/AceDataCloud/Skills --path skills/hailuo-videoManually: put the files in place
.devin/skills/hailuo-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AceDataCloud/Skills --skill hailuo-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about hailuo-video
How to install hailuo-video in Claude Code?
Run npx skills add AceDataCloud/Skills --skill hailuo-video -a claude-code, then open ~/.claude/skills/hailuo-video/SKILL.md.
What does hailuo-video do?
Generates video from text or animates images via AceDataCloud's Hailuo (MiniMax) API. Three models: text-to-video, image-to-video, and director mode.
How does director mode differ from standard image animation?
minimax-i2v-director gives finer control over camera and object motion than standard minimax-i2v.
Source text
SKILL.md · Apache-2.0
---
name: hailuo-video
description: Generate AI videos with Hailuo (MiniMax) via AceDataCloud API. Use when creating videos from text descriptions or animating images into video. Supports text-to-video and image-to-video with director mode for precise control.
license: Apache-2.0
metadata:
author: acedatacloud
version: "1.0"
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (get an API key at https://platform.acedata.cloud/console/applications).
---
# Hailuo Video Generation
Generate AI videos through AceDataCloud's Hailuo (MiniMax) API.
## First-time setup
1. Install the official Skill with `clawhub install @acedatacloud/hailuo`. Check that the ClawHub publisher is **@acedatacloud**.
2. Sign in at [AceDataCloud → Applications](https://platform.acedata.cloud/console/applications), open **General application**, and check Hailuo access, balance, and current pricing. Copy its API key, or select **Manage Keys → Create** for a separate key. Copy the key value without `Bearer `; a `platform-...` management token is not a service API key.
3. If you enable **Allowed APIs** restrictions, include `/hailuo/videos` and `/hailuo/tasks`. Advanced workflows below may call additional routes.
4. On the OpenClaw Gateway host, put `ACEDATACLOUD_API_TOKEN=your_api_key_here` in `~/.openclaw/.env`, then restart the Gateway and start a new session. For a direct terminal test, run `export ACEDATACLOUD_API_TOKEN="your_api_key_here"` in that shell. Never put the key in a prompt or commit an `.env` file.
5. Run the **Quick Start** below. If this workflow returns a task ID, query that same task until it finishes; do not submit the same billable request again just to check progress.
[Illustrated key setup, first run, and troubleshooting](https://github.com/AceDataCloud/Skills#first-run-with-clawhub-and-openclaw) · [Token details](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/authentication.md)
## Quick Start
```bash
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"}'
```
> **Async:** See [async task polling](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/async-tasks.md). Poll via `POST /hailuo/tasks` with `{"id": "..."}`.
## Models
| Model | Type | Best For |
|-------|------|----------|
| `minimax-t2v` | Text-to-Video | Creating video from text description |
| `minimax-i2v` | Image-to-Video | Animating a still image |
| `minimax-i2v-director` | Image-to-Video (Director) | Precise control over animation from image |
## Workflows
### 1. Text-to-Video
```json
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.
```json
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.
```json
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
| Parameter | Required | Values | Description |
|-----------|----------|--------|-------------|
| `action` | Yes | `"generate"` | Action type |
| `prompt` | Yes | string | Video description |
| `model` | Yes | `"minimax-t2v"`, `"minimax-i2v"`, `"minimax-i2v-director"` | Model |
| `first_image_url` | For i2v | string | Source image URL (required for image-to-video) |
| `callback_url` | No | string | Async callback URL |
## 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
© acedatacloud · Apache-2.0 · AceDataCloud/Skills