skills.rest
happycapy-ai
happycapy-aiCOMMUNITY
Explore all skills by this author →
Website𝕏@happycapyaiGitHub

ai-video-generation

Generate videos from text or images using Veo, Seedance, Wan, and Grok via inference.sh CLI.

137|29|Updated Feb 4, 2026
Search Tags:#video generation#text-to-video#image-to-video#ai video#avatar animation#lipsync
One-click install
npx skills add https://github.com/happycapy-ai/Happycapy-skills --skill ai-video-generation-happycapy-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-video-generation
Source: https://github.com/happycapy-ai/Happycapy-skills/tree/main/skills/ai-video-generation
Command: npx skills add https://github.com/happycapy-ai/Happycapy-skills --skill ai-video-generation-happycapy-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables the creation of diverse AI-generated videos, from text or images, with advanced features like lip-sync and avatar animation, streamlining content production.

Core Features & Use Cases

  • Text-to-Video: Generate videos from textual descriptions using models like Veo and Grok.
  • Image-to-Video: Animate static images into dynamic video clips.
  • Avatar & Lipsync: Create talking avatars from images and audio.
  • Video Enhancement: Upscale video quality and add sound effects.
  • Use Case: A social media manager needs to create a short promotional video for a new product. They can use a text prompt to generate a video or animate a product image, then add a voiceover.

Quick Start

Use the ai-video-generation skill to create a video from the prompt 'a drone shot flying over a forest'.

Frequently Asked Questions about ai-video-generation

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

FAQPage Schema
How do I generate AI video from text or images?▼

To generate AI video from text or images, you execute the inference.sh CLI with specified app IDs and input parameters. This supports text-to-video and image-to-video generation using models like Veo, Seedance, Wan, and Grok.

Can I create talking avatars with lip-sync using AI video generation?▼

Yes, you can create talking avatars with lip-sync using AI video generation. By providing a static image and an audio track, the Skill animates the avatar and syncs the mouth movements to the audio input.

Does this AI video generation Skill support adding sound effects?▼

Yes, this AI video generation Skill supports adding sound effects. It includes a foley sound generation feature to produce audio for your video clips alongside its video upscaling capabilities.

What is the best way to create social media marketing videos with AI?▼

The best way to create social media marketing videos with AI is using text prompts or animating product images. This Skill streamlines content production for marketing materials, explainer videos, and product demos.

Do I need Bash to run the AI video generation models?▼

Yes, you need Bash to run the AI video generation models. The Skill requires Bash execution of the inference.sh CLI to invoke the 40+ available models like Veo, Seedance, Wan, and Grok.

Related Skills

Explore More Design & Creative Skills→
s1366560s1366560
5

speech-to-text

Transcribe audio files to text using Whisper models via the inference.sh CLI.

Community
Intermediate
breakingcircuits1337breakingcircuits1337

ai-video-generation

Generate videos from text and images using AI models like Google Veo.

Community
Advanced
agentspace-soagentspace-so
31

ai-avatar-video

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

Official
Advanced
TeamDay-AITeamDay-AI
2

animate-avatar

Animate avatar images into looping MP4 videos using Kling V2.6 Pro, LTX, or Veo models.

Official
Advanced