skills.rest
doany-ai
doany-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

image-to-video

Route image-to-video requests to RunComfy models by intent.

5|2|Updated May 18, 2026
Search Tags:#multimodal#prompting#model-routing#image-to-video#lip-sync#cli-integration#runcomfy
One-click install
npx skills add https://github.com/doany-ai/skills --skill image-to-video-doany-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-to-video
Source: https://github.com/doany-ai/skills/tree/main/image-to-video
Command: npx skills add https://github.com/doany-ai/skills --skill image-to-video-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill routes image-to-video requests to the right RunComfy model based on user intent, enabling efficient, model-appropriate animations without manual model selection.

Core Features & Use Cases

  • Intent-driven routing to the right i2v model for given goals (portrait animation with identity preservation, lip-sync with custom audio, or multi-modal composition).
  • Supports multiple models: HappyHorse 1.0 I2V, Wan 2.7 with audio_url, Seedance 2.0 Pro, selecting the best match per call.
  • Provides clear prompting guidance and side-car prerequisites to streamline activation via the RunComfy CLI.

Quick Start

Provide an image URL and your target animation intent to route to the appropriate model and run via the RunComfy CLI.

Frequently Asked Questions about image-to-video

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

FAQPage Schema
How do I convert an image to a video with lip-sync using custom audio?▼

Image-to-video routing selects the appropriate model based on your intent. It analyzes whether you need portrait animation, lip-sync, or multi-modal composition, then automatically routes the request to HappyHorse, Wan 2.7, or Seedance.

How does intent-based routing choose between different image-to-video models?▼

Intent-based routing selects the appropriate model based on your goals. It analyzes whether you need portrait animation, lip-sync, or multi-modal composition, then automatically routes the request to HappyHorse, Wan 2.7, or Seedance.

Can I use the RunComfy CLI for portrait animation while preserving identity?▼

Yes, you can use the RunComfy CLI for portrait animation with identity preservation. Provide an image URL and your animation intent to route the request to the HappyHorse 1.0 I2V model for consistent identity output.

What is the best way to generate multi-modal video clips from a single image?▼

The best way to generate multi-modal video clips is to provide an image URL and specify your multi-modal composition intent. The system routes the request to Seedance 2.0 Pro to create the video via the RunComfy CLI.

Do I need to manually select an i2v model for different animation goals?▼

No, you do not need to manually select an i2v model. The system automatically determines the appropriate RunComfy model based on your stated intent, eliminating manual selection and ensuring model-appropriate animations.

Related Skills

Explore More Software Engineering Skills→
runcomfy-comruncomfy-com
12

image-to-video

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

Official
Intermediate
prime-skillsprime-skills
31

image-to-video

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

Official
Advanced
agentspace-soagentspace-so
31

ai-avatar-video

Create avatar videos from audio or scripts via RunComfy model routing.

Official
Advanced
agentspace-soagentspace-so
31

image-to-video

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

Official
Intermediate