skills.rest
runcomfy-com
runcomfy-comOFFICIAL
Explore all skills by this author →
Website𝕏@runcomfyaiGitHub

ai-video-generation

Route text-to-video, image-to-video, and video-extend requests to RunComfy model endpoints.

12|2|Updated May 18, 2026
Search Tags:#text-to-video#image-to-video#ai video#lip sync#runcomfy cli#video extend#cinematic models
One-click install
npx skills add https://github.com/runcomfy-com/skills --skill ai-video-generation-runcomfy-com
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-video-generation
Source: https://github.com/runcomfy-com/skills/tree/main/ai-video-generation
Command: npx skills add https://github.com/runcomfy-com/skills --skill ai-video-generation-runcomfy-com

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of manually selecting and invoking different video models by providing a single router-like workflow that generates videos from prompts, animates still images, or extends existing clips.

Core Features & Use Cases

  • Unified video generation routing: Classifies requests into text-to-video, image-to-video, or video-extend and selects the best RunComfy model for the intent (e.g., quality, speed, multi-shot consistency, in-pass audio, character identity).
  • Prompt + schema-driven invocation: Ships model-specific documented prompting patterns and calls the exact runcomfy run <model>/<endpoint> command with the correct JSON input shape.
  • Audio and extend support: Supports audio-driven lip-sync via Wan 2-7 using audio_url, and extends Veo clips with the dedicated extend-video endpoints.
  • Use cases: Create marketing/social video clips, animate product spins from a still, generate cinematic multi-shot character narratives, and extend short clips beyond per-call duration limits.

Quick Start

Use the ai-video-generation skill to create a text-to-video clip by asking for a specific scene and including optional duration, aspect ratio, and resolution.

Frequently Asked Questions about ai-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 using the RunComfy CLI?▼

To generate AI video from text prompts, use the RunComfy CLI to route your request to the appropriate text-to-video model endpoint. You send a JSON payload containing your prompt, duration, aspect ratio, and resolution to execute the generation.

Can I animate a still image into a video clip?▼

Yes, you can animate a still image by using the image-to-video workflow. You provide an image_url in your JSON payload and route the request through the RunComfy CLI to generate an animated video clip from your static image.

How do I add lip sync audio to an AI video generation workflow?▼

To add lip sync audio to an AI video, use the Wan 2-7 model and include an audio_url in your JSON payload. The workflow routes through the RunComfy CLI to generate audio-driven lip-sync dialog scenes.

What is the best way to extend an existing Veo video clip?▼

The best way to extend a Veo video clip is to use the dedicated extend-video endpoints via the RunComfy CLI. This allows you to bypass per-call duration limits by continuing existing footage with the correct JSON payload fields.

Does AI video generation support cinematic multi-shot character narratives?▼

Yes, AI video generation supports cinematic multi-shot character narratives. The workflow classifies your request intent and selects the appropriate RunComfy model to ensure multi-shot consistency and character identity across generated clips.

Do I need the runcomfy CLI to generate videos from prompts?▼

Yes, you need the runcomfy CLI with allowed Bash(runcomfy *) tooling to generate videos from prompts. The workflow depends on routing specific model IDs and JSON payloads through this command-line interface to execute properly.

Related Skills

Explore More Design & Creative Skills→
runcomfy-comruncomfy-com
12

image-to-video

Route still images to RunComfy image-to-video models for animated video output.

Official
Intermediate
vm0-aivm0-ai
76

runway

Generate AI videos from images, text, or existing videos via the Runway API.

Official
Advanced
agentspace-soagentspace-so
31

image-to-video

Route still images to RunComfy image-to-video models by intent.

Official
Intermediate
runcomfy-comruncomfy-com
12

face-swap

Route face swaps in images and videos to RunComfy model endpoints.

Official
Advanced