video-generation

Generate videos from JSON prompts and reference images via Python script.

5|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/Hadokennn/deer-agents --skill video-generation-hadokennn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-generation
Source: https://github.com/Hadokennn/deer-agents/tree/main/deer-flow/skills/public/video-generation
Command: npx skills add https://github.com/Hadokennn/deer-agents --skill video-generation-hadokennn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for generating high-quality videos based on structured prompts and reference images, offering a solution for users looking to create or imagine videos with specific details and styles.

Core Features & Use Cases

  • Structured Prompt Creation: Generate JSON-formatted prompts to specify content, style, and technical details for AIGC video generation.
  • Reference Image Integration: Use reference images as guidance or as the first/last frame of the video to guide the generation process.
  • Automated Video Generation: Execute video generation through an automated Python script, providing control over output specifications like aspect ratio.

Quick Start

Use the video-generation skill to create a video with the prompt 'The Chronicles of Narnia - Train Station Farewell' and a reference image 'narnia-farewell-scene-01.jpg'.

Frequently Asked Questions about video-generation

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

FAQPage Schema
How do I generate videos using structured prompts and reference images?

To generate videos, you create JSON-formatted structured prompts specifying content, style, and technical details, optionally include reference images for guidance, and execute an automated Python script to produce the final video output.

What is the role of reference images in AIGC video creation?

In AIGC video creation, reference images guide the generation process by serving as visual guidance or acting as the first and last frame of the video to ensure specific subject and style details are maintained.

Can I control aspect ratio and technical specifications during video generation?

Yes, video generation allows you to control output specifications like aspect ratio by defining these technical details within the JSON-formatted structured prompts before executing the automated Python script.

Do I need Python to execute AIGC video generation scripts?

Yes, you need a Python environment to execute the automated video generation script, which requires the requests dependency to handle the API interactions and process your structured JSON prompts.

What's the best way to structure prompts for specific video styles?

The best way to structure prompts for specific video styles is using JSON format to explicitly define content, style, and technical specifications, enabling precise control over the AIGC video generation process.

Are there limitations when using reference images as video frames?

Limitations include relying on Python script execution and the requests dependency, meaning reference images are strictly used as guidance or as the first and last frame rather than for continuous frame-by-frame video editing.