image-to-video

Name: image-to-video
Availability: InStock
Author: prime-skills

Routes still-image animation requests to the appropriate RunComfy video generation model.

31|9|Updated Apr 30, 2026

Search Tags:#animation #video generation #image-to-video #lip-sync #runcomfy #multimodal video

Ready to run

npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill image-to-video-prime-skills

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-to-video
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/image-to-video
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill image-to-video-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork from animating still images by routing each request to the RunComfy video model best suited to the user's creative intent.

Core Features & Use Cases

Intent-Based Model Routing: Selects HappyHorse 1.0 I2V for general animation, portraits, product motion, and native audio.
Custom Voiceover Lip-Sync: Uses Wan 2.7 with an audio track for talking-head videos, custom voiceovers, and multilingual dubbing.
Multi-Modal Animation: Uses Seedance 2.0 Pro to combine subject images with reference video and audio for brand-consistent narrative clips.
Prompt and Input Guidance: Provides model-specific schemas, prompting patterns, media requirements, reproducibility options, and CLI error handling.
Use Case: Animate a product portrait with a gentle camera orbit, or combine a character image, café reference video, and voice sample into one narrated scene.

Quick Start

Ask the image-to-video skill to animate the attached still image with a gentle camera push-in and identity-stable facial motion.

Frequently Asked Questions about image-to-video

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

FAQPage Schema

How do I turn a still image into a video with custom voiceover and lip-sync?▼

To turn a still image into a video with custom voiceover lip-sync, this Skill routes your request to the Wan 2.7 model, applying an audio track to generate talking-head videos and multilingual dubbing.

What is the best way to animate a product portrait with a gentle camera orbit?▼

The best way to animate a product portrait with a gentle camera orbit is using intent-based routing to the HappyHorse 1.0 I2V model, which handles general animation, product motion, and native audio.

Can I combine a character image with reference video and audio for multimodal video generation?▼

Yes, you can combine a character image with reference video and audio for multimodal video generation by routing the request to Seedance 2.0 Pro, which creates brand-consistent narrative clips.

Do I need a RunComfy token to generate video from an image?▼

Yes, you need a RunComfy token to generate video from an image, as this Skill requires the RunComfy CLI, an authenticated account or RUNCOMFY_TOKEN, valid media URLs, and model-specific schemas.

Why does image-to-video generation fail when using model-specific input schemas?▼

Image-to-video generation fails when model-specific input schemas are invalid because this Skill requires specific prompting patterns, media requirements, and proper output directory handling to execute CLI calls without errors.