skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

wan-2-7

Generate text-to-video clips with Wan 2.7 via the RunComfy Model API.

31|9|Updated Apr 30, 2026
Search Tags:#video generation#text-to-video#ai video#lip sync#motion control#runcomfy#wan 2.7
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill wan-2-7-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wan-2-7
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/wan-2-7
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill wan-2-7-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies the creation of high-quality text-to-video clips with Wan 2.7 on RunComfy, avoiding manual API setup while supporting motion control, custom audio, and flexible output formats.

Core Features & Use Cases

  • Text-to-Video Generation: Create cinematic clips with configurable prompts, duration, resolution, aspect ratio, negative prompts, and seeds.
  • Audio-Driven Lip Sync: Supply a WAV or MP3 track to synchronize generated video with speech, dubbing, or custom voiceovers.
  • Motion and Reference Control: Produce smooth transitions, realistic motion physics, and multi-reference video concepts for ads, social content, product showcases, and spokesperson clips.
  • Model Routing Guidance: Identify when Wan 2.7 is preferable to alternatives such as HappyHorse, Seedance, Kling, or LTX.

Quick Start

Ask the Wan 2.7 skill to generate a video from your prompt, optionally specifying the desired duration, aspect ratio, resolution, negative prompt, or audio track.

Frequently Asked Questions about wan-2-7

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

FAQPage Schema
How do I generate text-to-video clips with Wan 2.7 without manual API setup?▼

Text-to-video generation with Wan 2.7 is simplified by routing prompts through the RunComfy Model API, which requires the RunComfy CLI and authenticated access to produce cinematic clips without manual configuration.

Can I use audio-driven lip sync for spokesperson videos in Wan 2.7?▼

Audio-driven lip sync is supported by supplying a WAV or MP3 track, allowing you to synchronize generated video with custom voiceovers, dubbing, or speech for spokesperson content and social videos.

Do I need the RunComfy CLI to use Wan 2.7 for motion control and video generation?▼

The RunComfy CLI and authenticated RunComfy access are required to execute the Wan 2.7 workflow, handling multi-reference motion control and configurable output directory management for your generated clips.

When should I choose Wan 2.7 over other text-to-video models like Kling or LTX?▼

Wan 2.7 is preferable for cinematic scenes, product showcases, and multi-reference motion control, offering model routing guidance to distinguish it from alternatives like HappyHorse, Seedance, Kling, or LTX.

What are the limitations of generating vertical social videos with Wan 2.7?▼

Limitations include requiring valid prompt and media inputs, supported audio formats like WAV or MP3 for lip sync, and proper output directory handling to successfully generate configurable resolution and aspect ratio clips.

Related Skills

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

wan-2-7

Generate text-to-video clips with optional audio-driven lip-sync via RunComfy.

Official
Intermediate
agentspace-soagentspace-so
31

wan-2-7

Generate lip-synced text-to-video clips via the RunComfy Model API.

Official
Intermediate
agentspace-soagentspace-so
31

image-to-video

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

Official
Intermediate
doany-aidoany-ai
5

ai-avatar-video

Route inputs to avatar-generation models via the RunComfy CLI.

Official
Advanced