video-generation

Generate videos from structured JSON prompts and reference images via Python scripts.

79.6k|10.9k|Updated May 7, 2025
One-click install
npx skills add https://github.com/bytedance/deer-flow --skill video-generation-bytedance
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-generation
Source: https://github.com/bytedance/deer-flow/tree/main/skills/public/video-generation
Command: npx skills add https://github.com/bytedance/deer-flow --skill video-generation-bytedance

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation of videos, transforming textual descriptions and visual references into dynamic video content, streamlining the video production process.

Core Features & Use Cases

  • Structured Prompt Generation: Creates detailed JSON prompts for AI video generation.
  • Reference Image Integration: Utilizes reference images for guided video creation, acting as inspiration or specific frames.
  • Automated Script Execution: Executes Python scripts to manage the video generation pipeline.
  • Use Case: Generate a short video clip depicting a specific historical event or a scene from a movie, using a detailed prompt and a reference image to guide the AI's output.

Quick Start

Use the video-generation skill to create a video from the prompt file '/mnt/user-data/workspace/my-scene.json' and the reference image '/mnt/user-data/images/scene-ref.jpg', saving the output to '/mnt/user-data/outputs/my-scene.mp4'.

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 video from text prompts and reference images?

To generate AI video, you provide structured JSON prompts detailing scene descriptions and character elements, optionally including reference images. The Skill processes these inputs to automate video synthesis, outputting a dynamic video file.

What is structured JSON prompt engineering for AI video generation?

Structured JSON prompt engineering for AI video involves creating detailed files that specify scene descriptions, camera angles, and audio cues. This structured format guides the AI-driven synthesis process to produce precise multimedia content.

Can I use a Python script to automate video generation from a prompt file?

Yes, you can automate video generation using a Python script that executes the synthesis pipeline. You need to provide the prompt file path, optional reference image path, and output video path for the script to run successfully.

Does AI video synthesis support camera angles and audio cues?

AI video synthesis supports detailed camera angles and audio cues through structured JSON prompts. By defining these elements within the prompt file, the video generation process integrates them into the final multimedia output.

How do I add a reference image to guide AI video creation?

To add a reference image for AI video creation, specify the image file path in the execution command. The image acts as visual inspiration or a specific frame to guide the AI's video synthesis.