wan-video

Generate animated MP4 video clips from static images using Wan 2.2.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/MCERQUA/jam-skills --skill wan-video-mcerqua
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wan-video
Source: https://github.com/MCERQUA/jam-skills/tree/main/wan-video
Command: npx skills add https://github.com/MCERQUA/jam-skills --skill wan-video-mcerqua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for image-to-video animation capabilities, converting static images into short, animated video clips.

Core Features & Use Cases

  • Image-to-Video Animation: Animate any still image into a cinematic video clip using the Wan 2.2 AI model.
  • Customization: Offers control over the motion and duration of the animation.
  • Use Case: Ideal for creating product demonstrations, promotional content, or engaging UI elements for web pages.

Quick Start

Generate a video animation of a product image using 'product.jpg' with the following prompt: 'camera zooms in slowly, highlighting the design details' and a duration of 5 seconds.

Frequently Asked Questions about wan-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I animate a still image into a cinematic video?

To animate a still image into a cinematic video, provide the image file, a prompt describing the desired motion, and a duration. The Wan 2.2 AI model generates the animation and outputs an MP4 file via a server URL.

What do I need to generate an MP4 video from a static image?

Generating an MP4 video from a static image requires an input image file and a clear text prompt specifying the animation details. You also need to define the desired duration for the video clip.

How does image-to-video AI transformation work for product images?

Image-to-video AI transformation for product images works by using the Wan 2.2 model to interpret a text prompt, such as 'camera zooms in slowly', and apply that motion to the static product image to create a dynamic video clip.

Can I control the camera motion and duration of an image-to-video animation?

Yes, you can control the camera motion and duration of an image-to-video animation by providing a specific text prompt detailing the movement and explicitly stating the required clip duration.