Video Generation

Generate videos from text or images using the z-ai-web-dev-sdk.

1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/fishyer/skills --skill video-generation-fishyer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Video Generation
Source: https://github.com/fishyer/skills/tree/main/skills/video-generation
Command: npx skills add https://github.com/fishyer/skills --skill video-generation-fishyer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires z-ai-web-dev-sdk, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides the ability to create high-quality videos programmatically, allowing users to transform text prompts or images into engaging video content quickly and efficiently.

Core Features & Use Cases

  • Text-to-Video: Generate videos from text descriptions with customizable parameters such as resolution, frame rate, and duration.
  • Image-to-Video: Create videos from single or multiple images, with options for keyframe generation and transition effects.
  • Customization: Adjust quality, resolution, frame rate, duration, and more to suit specific video requirements.
  • Use Case: Ideal for creating marketing videos, educational content, or personal projects that require professional-grade video production capabilities.

Quick Start

Generate a video with the prompt 'A cat playing with a ball' and resolution '1920x1080' using the Video Generation skill.

Frequently Asked Questions about Video Generation

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

FAQPage Schema
How do I generate video from text prompts programmatically?

You can generate video from text prompts asynchronously by processing text descriptions through the core task functionality, which outputs customized video content with adjustable resolution, frame rate, and duration settings.

Can I use an image to create video content with transition effects?

Yes, you can use an image to create video content. The image-to-video creation process supports generating videos from single or multiple images, including options for keyframe generation and transition effects.

Do I need the z-ai-web-dev-sdk to process text-to-video conversion?

Yes, you need the z-ai-web-dev-sdk dependency to process text-to-video conversion. The video generation task requires this SDK to handle the asynchronous video processing and parameter customization.

What resolution and frame rate customizations are available for AI video generation?

AI video generation supports custom resolution and frame rate settings. You can adjust these video parameters along with duration to suit specific video requirements for marketing or educational content.

Does asynchronous video generation support batch processing of multiple images?

Asynchronous video generation supports creating videos from multiple images. The image-to-video functionality includes options for keyframe generation and transition effects across the provided image set.