ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

alicloud-ai-video-wan-video

Generate videos with Model Studio DashScope SDK using Wan i2v models (wan2.6-i2v-flash, wan2.6-i2v, wan2.6-i2v-us). Use when implementing or documenting video.generate requests/responses, mapping prompt/negative_prompt/duration/fps/size/seed/reference_image/motion_strength, or integrating video generation into the video-agent pipeline.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cinience/alicloud-ai-video-wan-video
Or

What This Skill Does

The alicloud-ai-video-wan-video skill provides seamless integration between OpenClaw AI and the Alibaba Cloud Model Studio (DashScope) video generation API. It enables the creation of high-quality video content using the cutting-edge Wan (Wide-Area Network) model series, including both text-to-video (t2v) and image-to-video (i2v) capabilities. The skill manages the lifecycle of video generation tasks, from request submission using standardized parameters like prompt, resolution, duration, and frame rate, to monitoring asynchronous task completion. It serves as a unified interface for the Wan 2.2 and 2.6 model families, ensuring that users can easily transition between different model versions based on their specific performance requirements (flash, standard, or enterprise-grade models).

Installation

To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/cinience/alicloud-ai-video-wan-video. Ensure your environment has the necessary dependencies by setting up a virtual environment and installing the DashScope SDK: python -m pip install dashscope. Finally, authenticate the skill by setting your DASHSCOPE_API_KEY as an environment variable, or configure your credentials file located at ~/.alibabacloud/credentials with the dashscope_api_key key.

Use Cases

This skill is designed for automated content creation pipelines. Common use cases include: generating consistent video assets from static imagery for social media marketing, creating cinematic motion sequences from detailed text prompts for narrative storytelling, and integrating AI-generated background video elements into automated news or training material workflows. It is particularly effective for teams looking to standardize video output quality across varied creative projects.

Example Prompts

  1. "Generate a 4-second video of a cyberpunk cityscape at night using the wan2.6-i2v model, with a size of 1280x720, set to 24fps."
  2. "Use the image at ./input/character.png to create a 5-second cinematic motion video with a motion strength of 8, using wan2.6-i2v-flash."
  3. "Create a video showing a sunset over the ocean, prompt: 'golden hour, calm waves, 4k resolution', duration 6 seconds, fps 30, size 1920x1080."

Tips & Limitations

For optimal results, ensure your input resolution matches the model's capabilities. Note that i2v tasks require a valid image source (URL or file path) to trigger the generation. Asynchronous tasks can take time depending on the load; monitor your task logs within the output/alicloud-ai-video-wan-video/ directory to track progress. Keep in mind that high-resolution outputs with longer durations will incur higher API usage costs. Always verify your network connectivity, as this skill relies on external calls to the DashScope cloud infrastructure.

Metadata

Author@cinience
Stars3562
Views0
Updated2026-03-29
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cinience-alicloud-ai-video-wan-video": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#video-generation#wan-models#ai-video#dashscope#automation
Safety Score: 4/5

Flags: network-access, file-write, file-read, external-api