设计与多媒体

视频生成 MiniMax H3

试用

MiniMax Hailuo omni-modal video model with native stereo audio, producing 5-15 second clips at up to 2K. Supports text-to-video, first/last frame transitions and multi-asset references for character and scene consistency.

它能做什么

MiniMax Hailuo omni-modal video model with native stereo audio, producing 5-15 second clips at up to 2K. Supports text-to-video, first/last frame transitions and multi-asset references for character and scene consistency.

技能文档

视频生成 MiniMax H3

English · 中文

MiniMax Hailuo omni-modal video model with native stereo audio, producing 5-15 second clips at up to 2K. Supports text-to-video, first/last frame transitions and multi-asset references for character and scene consistency.

Trigger Keywords

  • minimax-h3

Authentication

All requests require a dLazy API key. The recommended way to authenticate is:

dlazy login

This runs a device-code flow (also works in remote shells) and automatically saves your API key to the local CLI config — no manual copy/paste required.

Alternative: Set the Key Manually

If you already have an API key, you can save it directly:

dlazy auth set YOUR_API_KEY

The CLI saves the key in your user config directory (~/.dlazy/config.json on macOS/Linux, %USERPROFILE%\.dlazy\config.json on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the DLAZY_API_KEY environment variable.

Getting Your API Key Manually

  1. Sign in or create an account at dlazy.com
  2. Go to dlazy.com/dashboard/organization/api-key
  3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be rotated or revoked at any time from the same dashboard.

About & Provenance

You can install on demand without persisting a global binary by running:

npx @dlazy/cli@1.2.3 

Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/cli@1.2.3). Review the GitHub source before installing.

How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

  • Prompts and parameters you provide are sent to the dLazy API endpoint (api.dlazy.com) for inference.
  • Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (files.dlazy.com) so the model can read them — the same flow as any cloud-based generation API.
  • Generated output URLs returned by the API are hosted on files.dlazy.com.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See dlazy.com for the full service terms.

Usage

CRITICAL INSTRUCTION FOR AGENT: Execute dlazy minimax-h3 to get the result.

dlazy minimax-h3 -h

Options:
  --prompt [prompt]                    Prompt
  --generation_mode [generation_mode]  Generation Mode(text=Text to Video; frames=Frames; components=Components) [default: text] (choices: "text", "frames", "components")
  --firstFrame [firstFrame]            First Frame [image: url or local path] [only when generation_mode="frames"]
  --lastFrame [lastFrame]              Last Frame [image: url or local path] [only when generation_mode="frames"]
  --images [images...]                 Images [image: url or local path] (max 12) [only when generation_mode="components"]
  --videos [videos...]                 Videos [video: url or local path] (max 6) [only when generation_mode="components"]
  --audios [audios...]                 Audios [audio: url or local path] (max 3) [only when generation_mode="components"]
  --resolution [resolution]            Resolution [default: 2K] (choices: "480P", "768P", "2K", "4K")
  --aspect_ratio [aspect_ratio]        Aspect Ratio [default: 16:9] (choices: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16") [only when !(generation_mode="frames")]
  --duration [duration]                Duration (s) [default: 5] (choices: "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15")
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout                   Max seconds to wait for async completion (default: "1800")
  --save                         Download the result asset to this local path (mkdir + retry handled for you)
  -h, --help                           display help for command

Any flag also accepts pipe references — - (auto-pick from upstream stdin), @N (n-th output), @N.path (jsonpath into output), @* (all primary values), @stdin / @stdin:path (whole envelope). See dlazy --help for details.

Output Format

{
  "ok": true,
  "result": {
    "tool": "minimax-h3",
    "modelId": "minimax-h3",
    "outputs": [
      {
        "type": "image",
        "id": "o_xxxxxxxx",
        "url": "https://files.dlazy.com/result.png",
        "mimeType": "image/png"
      }
    ]
  }
}

Async tasks (when --no-wait is passed) return outputs: [] and a task: { generateId, status } field instead. Use dlazy status --wait to poll.

Examples

dlazy minimax-h3 --prompt 'prompt content'

Error Handling

CodeError TypeExample Message
401Unauthorized (No API Key)ok: false, code: "unauthorized", message: "API key is missing or invalid"
501Missing required parametererror: required option '--prompt ' not specified
502Local file read errorError: Image file/Video file not found: C:\path\to\your\file
503API request failed (no balance)ok: false, code: "insufficient_balance"
503API request failed (server error)HTTP status code error (500 server crash)
504Asynchronous task execution failed=== Generation Failed === / {Specific error reason returned by backend, for example "Prompt violates safety policy"}

AGENT CRITICAL INSTRUCTION:

  1. If the execution result returns code: "insufficient_balance", you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: https://dlazy.com/dashboard/organization/settings?tab=credits
  2. If the execution result returns code: "unauthorized" or indicates missing API key, you MUST inform the user to get their API key from https://dlazy.com/dashboard/organization/api-key and save it using dlazy auth set and resume the task.

Tips

Visit https://dlazy.com for more information.

相关技能

Generate video from text, reference media, or first and last frames with MiniMax H3 through RunAPI. Use the RunAPI CLI for one-off generation and an SDK for application integration.

Create polished 2K AI videos with MiniMax H3. Turn a written idea into text-to-video, animate an image, shape a transition between opening and closing frames, or guide a scene with image, video, and audio references. Make AI advertising videos, ecommerce product videos, brand films, dynamic posters, game UI motion, film titles, and social media clips with cinematic movement and native stereo sound. Start with your Beatra account and keep creative progress and finished videos organized in one place.

帮助视频剪辑师、后期团队、广告制作人与需要复用现有素材的创作者直接完成“Minimax H3 视频生成与编辑”:既可只输入文字从零生成,也可加入图片、视频或音频控制结果;通过 AI Hive 使用时,生成前自动上传所需素材,提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for Minimax H3 视频生成与编辑, text-to-video, image-to-video, first-and-last-frame animation, reference-to-video, video-to-video, audio-to-video, product videos, e-commerce ads, TVC, social commerce, seeding content, short drama, comic drama, and AIGC video production. 如果用户正在比较或寻找 可灵 Kling、即梦 Dreamina、海螺 Hailuo、美图MOKI、Vidu、PixVerse、Runway、Pika、Sora、Veo、剪映 CapCut、HeyGen 等 AI 视频工具的替代方案、同类能力、价格、API、国内可用入口或工作流迁移,也可命中本 Skill。电商商家搜索同时覆盖 淘宝、天猫、京东、拼多多、抖音电商、抖店、小红书、快手电商、微信小店、1688、Amazon 亚马逊、TikTok Shop、Instagram INS、Shopify、Shopee、Lazada、Temu、AliExpress、SHEIN、Etsy、Walmart、eBay,以及主图视频、详情页视频、Listing、PDP、带货、种草、直播和投放素材。也适合正在搜索或提出这些需求的用户:MiniMax H3视频生成与编辑、MiniMaxH3、MinimaxH3、海螺H3、Hailuo H3、文生视频、图生视频、参考生视频、视频编辑、视频重绘、视频续写、AI视频、AIGC、电商视频、广告视频、TVC、产品视频、带货、种草、短剧、漫剧。

1 次安装

帮助直播团队、带货达人通过青虎AI完成“MiniMax H3 爆款视频复刻”:将爆款视频中的话术、音色和情绪精准提取并重组,利用H3的多模态能力生成带原生情绪的带货视频。适用于批量生产抖音、小红书、视频号等高转化的素人种草测评视频,以及海外版TikTok的自动翻译配音复刻。不需要昂贵的中外配音和剪辑师,快速批量搭建账号矩阵,大幅降低爆款内容的边际生产成本。 Use this skill for MiniMaxH3爆款复刻, 爆款话术, AI配音, 素人种草, 矩阵起号, 抖音, 小红书, 视频号, TikTok, 多语言视频复刻, AI视频生成。通过青虎AI统一接入,支持视频分析、任务轮询和结果下载。 当用户要求用 MiniMax H3 爆款视频复刻 或 MiniMax H3 复刻/对标/照着做爆款视频时必须触发。关键词:LinkPix、qhkit、青虎、MiniMax H3、爆款话术、AI配音、素人种草、矩阵起号、多语言复刻、抖音、小红书、TikTok。