skills.rest
jjyaoao
jjyaoaoCOMMUNITY
Explore all skills by this author →
GitHub

Video Generation

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

2.7k|627|Updated Sep 11, 2025
Search Tags:#polling#video-generation#text-to-video#ai-video#z-ai-web-dev-sdk#image-to-video#asynchronous-task
One-click install
npx skills add https://github.com/jjyaoao/HelloAgents --skill video-generation-jjyaoao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Video Generation
Source: https://github.com/jjyaoao/HelloAgents/tree/main/skills/video-generation
Command: npx skills add https://github.com/jjyaoao/HelloAgents --skill video-generation-jjyaoao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate AI-powered videos from text prompts or images, enabling rapid content creation and prototyping with asynchronous task handling and result retrieval.

Core Features & Use Cases

  • Text-to-video: produce videos from descriptive prompts with configurable size, fps, duration, and optional audio.
  • Image-to-video: convert single or multiple images into video sequences, accepting base64 data or URLs.
  • Keyframes and transitions: support for start/end frames and smooth transitions using SDK functionality.
  • Asynchronous results: create tasks and poll for final video URLs, suitable for batch workflows.
  • Use Cases: marketing clips, tutorials, social media assets, and rapid concept visualization.

Quick Start

Provide a prompt or image data to start a video generation task, then poll for the final video URL.

Frequently Asked Questions about Video Generation

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

FAQPage Schema
How do I generate AI videos from text prompts asynchronously?▼

To generate AI videos from text prompts asynchronously, provide a descriptive prompt to create a video generation task, then poll the asynchronous result API for the final video URL. You can configure size, fps, duration, and optional audio.

Can I convert images into video sequences using base64 data or URLs?▼

Yes, you can convert images into video sequences using base64 data or URLs. The image-to-video process supports single or multiple images, including start and end frames for smooth keyframe transitions.

Do I need the z-ai-web-dev-sdk to handle asynchronous video generation tasks?▼

Yes, you need the z-ai-web-dev-sdk installed to handle asynchronous video generation tasks. It manages the task lifecycle, including polling for PROCESSING, SUCCESS, and FAIL statuses to retrieve the final video URL.

What is the best way to manage video processing status when creating marketing clips?▼

The best way to manage video processing status when creating marketing clips is using asynchronous polling. Create a generation task, then continuously poll the async result API until the status changes from PROCESSING to SUCCESS or FAIL.

Why does my asynchronous task return a FAIL status during text-to-video generation?▼

An asynchronous task returns a FAIL status during text-to-video generation when the underlying processing encounters an error. The z-ai-web-dev-sdk handles these statuses, allowing you to check the result API and retry the task if it fails.

Related Skills

Explore More Design & Creative Skills→
Merit-SystemsMerit-Systems
3

media-generation

Generate images and videos from prompts via x402-protected StableStudio models.

Official
Intermediate
zakarooozakarooo

Video Generation

Create video generation tasks from text or images and poll for results.

Community
Intermediate
TietveTietve
1

ai-multimodal

Process audio, video, images, and documents via Google Gemini's multimodal API.

Community
Advanced
nidhalboumaiza-0nidhalboumaiza-0

Video Generation

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

Community
Intermediate