ai-video-generation

Route text and image prompts to the right AI video model via RunComfy's CLI. The skill handles model selection across HappyHorse, Kling, Seedance, Veo, Wan, and others—each optimized for different outputs like in-pass audio, multi-shot character consistency, or physics-accurate motion. Get the exact `runcomfy run` command and prompt patterns for your use case.

AI Video Generation routes your text or image prompts to the best RunComfy video model for your needs.

AI-generated summary based on this skill's SKILL.md

★ 31 ⁮ 9 MIT updated 2026-05-15 by prime-skills

Install

prime-skills/runcomfy-agent-skills/ai-video-generation

Manual (git clone) CLI (skillfed)coming soon

git clone https://github.com/prime-skills/runcomfy-agent-skills
cp -r runcomfy-agent-skills/ai-video-generation ~/.claude/skills/ai-video-generation

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate video from text with ai-video-generation?

ai-video-generation routes your text prompt to the right AI video model via RunComfy's CLI. Depending on your needs—whether you want fast generation, cinematic quality, or specific motion physics—the skill selects from models like HappyHorse, Kling, Seedance, Veo, and Wan. You receive the exact `runcomfy run` command and optimized prompt patterns for your use case.

Can ai-video-generation animate a still image to video?

Yes. ai-video-generation supports image-to-video (i2v) animation, letting you add motion to a static image with optional audio narration. The skill routes your image and motion description to the appropriate model—each optimized for different animation styles, from subtle motion to dynamic character movement with consistent identity across frames.

What models does ai-video-generation support?

ai-video-generation integrates HappyHorse, Kling, Seedance, Veo, Wan, and others. Each model is optimized for different outputs: in-pass audio, multi-shot character consistency, physics-accurate motion, or cinematic quality tiers. The skill automatically selects the best model based on your prompt and desired output characteristics.

Can I extend or continue an existing video with ai-video-generation?

Yes. ai-video-generation can extend or continue an existing video while maintaining consistent motion and character identity. This is handled by models like Veo, which preserve visual continuity across generated segments, letting you build longer sequences from shorter clips.

Does ai-video-generation support creating talking head videos?

Yes. ai-video-generation supports dialog and lip-sync video generation with audio-driven mouth synchronization. The skill routes your audio and character reference to models equipped for this, ensuring the generated video's mouth movements align precisely with your narration or dialog track.

What license does ai-video-generation use?

ai-video-generation is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim