video-generation

Generates videos from text or images and analyzes scenes with object detection.

1|Updated Feb 8, 2026

Search Tags:#multimodal #video generation #video analysis #AI video #scene detection

Ready to run

npx skills add https://github.com/framerslab/agentos-skills --skill video-generation-framerslab

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-generation
Source: https://github.com/framerslab/agentos-skills/tree/main/registry/curated/video-generation
Command: npx skills add https://github.com/framerslab/agentos-skills --skill video-generation-framerslab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires runway, replicate, fal, ffmpeg, openai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive solution for creating AI-generated videos, analyzing existing video content, and detecting visual changes, addressing needs in media production, content moderation, and surveillance.

Core Features & Use Cases

Video Generation: Generate videos from text prompts or images.
Video Analysis: Extract structured scene descriptions, detected objects, and on-screen text from videos.
Scene Detection: Detect visual changes in live or recorded frame streams.
Use Case: Use this Skill to create a promotional video from a text description, analyze a product demonstration video for scene descriptions, or detect motion in a security camera feed.

Quick Start

Use the video-generation skill to generate a video from the text prompt 'A drone flying over a misty forest at sunrise, cinematic 4K'.

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 or images?▼

AI video generation transforms text prompts or static images into dynamic video content. This Skill supports text-to-video and image-to-video workflows by routing requests through integrated video providers like Runway, Replicate, or Fal.

Can I extract scene descriptions and object detection from video?▼

Video analysis extracts structured scene descriptions, detected objects, and on-screen text from video files. This Skill processes existing video content to provide structured metadata for media production and content moderation workflows.

What providers do I need for text-to-video generation?▼

Text-to-video generation requires an external video provider such as Runway, Replicate, or Fal. Optionally, a vision-capable LLM and Speech-to-Text (STT) provider are needed for structured scene analysis and transcription features.

How do I detect visual changes in a frame stream?▼

Scene detection identifies visual changes within live or recorded frame streams. This Skill analyzes sequential frames to detect motion or visual shifts, suitable for surveillance feeds or real-time monitoring applications.

Does this Skill work with FFmpeg and OpenAI?▼

Yes, the Skill integrates with FFmpeg for video processing and OpenAI for vision-capable LLM tasks. These dependencies function together to enable structured scene analysis, transcription, and video generation pipelines.