Video Generation

Name: Video Generation
Availability: InStock
Author: chancoute

Submit text-to-video or image-to-video tasks and return final video URLs.

Updated Jan 8, 2026

Search Tags:#AI #asynchronous #polling #video generation #text-to-video #image-to-video

Ready to run

npx skills add https://github.com/chancoute/sgin --skill video-generation-chancoute

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Video Generation
Source: https://github.com/chancoute/sgin/tree/main/skills/video-generation
Command: npx skills add https://github.com/chancoute/sgin --skill video-generation-chancoute

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables developers to generate AI-driven videos from text prompts or input images, automating content creation and reducing manual video production time.

Core Features & Use Cases

Text-to-video: generate videos from descriptive prompts for marketing, education, or entertainment.
Image-to-video: animate static visuals using input images or sequences.
Asynchronous workflow: task creation with polling to retrieve results; supports audio options, multiple frames, and custom resolutions.

Quick Start

Use the skill to create and poll a video generation task from a prompt like 'A cat playing with a ball' and fetch the resulting 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 video from text prompts or images asynchronously?▼

To generate video from text or images asynchronously, you submit a text-to-video or image-to-video task and use polling to retrieve the final video URL. This workflow supports custom resolution, frame rate, and audio options.

How does polling work for retrieving AI video generation results?▼

Polling for AI video generation works by repeatedly checking the task status after submission until the asynchronous processing completes, allowing you to retrieve the final video URL without blocking your application's execution.

Can I customize resolution, frame rate, and duration for text-to-video tasks?▼

Yes, you can customize resolution, frame rate, and duration for text-to-video tasks by passing specific parameters like size, fps, and duration, alongside optional audio settings, to control the final media output.

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

Yes, you need the z-ai-web-dev-sdk library to run image-to-video generation tasks. This dependency provides the necessary asynchronous task submission and polling controls required for real-world media production.

What is the difference between text-to-video and image-to-video generation?▼

The difference between text-to-video and image-to-video generation is the input source: text-to-video creates media from descriptive prompts, while image-to-video animates static visuals using input image URLs or sequences.

Can I add audio to AI generated videos?▼

Yes, you can add audio to AI generated videos by using the with_audio parameter during task submission, allowing you to produce complete multimedia content directly through the asynchronous polling workflow.