skills.rest
agentspace-so
agentspace-soOFFICIAL
Explore all skills by this author →
GitHub

wan-2-7

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

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you generate high-quality text-to-video outputs—especially lip-synced clips—without manually dealing with complex model setup or routing.

Core Features & Use Cases

  • Text-to-video on RunComfy: Generate video from a prompt using the RunComfy Model API via the local RunComfy CLI.
  • Audio-driven lip-sync: Provide an audio_url so the model synchronizes motion to your supplied audio track.
  • Prompt control and reliability: Support aspect ratio, resolution, duration, negative_prompt, optional prompt expansion, and repeatable seeds for consistent variants.
  • Model routing guidance: Use Wan 2.7 for the “Wan / Wan 2.7 / wan-ai” use case, with documented alternatives for other needs (e.g., HappyHorse, Seedance, Kling, LTX).

Quick Start

Use wan-2-7 to generate a 9:16 lip-synced vertical video by providing your prompt and an audio_url to the RunComfy CLI output directory.

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 lip-sync video from text using an audio URL?▼

To generate lip-sync video, you provide a text prompt and an audio_url in a JSON input to the RunComfy Model API, which synchronizes the generated character motion to your supplied audio track.

Can I control aspect ratio and resolution for text-to-video generation?▼

Yes, text-to-video generation supports optional aspect_ratio and resolution parameters in the JSON input, allowing you to format outputs for specific use cases like 9:16 vertical videos.

How do I get consistent variants when generating text-to-video clips?▼

You can generate consistent variants of text-to-video clips by setting a specific seed value in your JSON input, ensuring repeatable results across multiple generation runs.

Does prompt expansion work with negative prompts for text-to-video?▼

Yes, you can use both negative_prompt to exclude unwanted elements and enable_prompt_expansion to enhance your input, giving you precise control over the final text-to-video output.

What is the best way to create spokesperson videos with Wan 2.7?▼

The best way to create spokesperson videos is using Wan 2.7 via the RunComfy Model API, passing your descriptive prompt and an audio_url to generate realistic, audio-synchronized character motion.

Can I set a specific duration for text-to-video clips?▼

Yes, you can set a specific duration for your text-to-video clips by including the optional duration parameter in your JSON input sent to the RunComfy Model API.

Related Skills

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

ai-video-generation

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

Official
Intermediate
prime-skillsprime-skills
31

wan-2-7

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

Official
Intermediate
MCKRUZMCKRUZ
86

comfyui-voice-pipeline

Automate character voice creation and lip-sync for video production.

Community
Advanced
TakMczkTakMczk
1

fal-ai-media

Generates images, videos, and audio via fal.ai's MCP.

Community
Intermediate