ai-video-generation

What problem does it solve?

This Skill simplifies the creation of diverse AI-generated videos, from text or image inputs, by providing access to a wide array of advanced models and tools.

Core Features & Use Cases

• Text-to-Video Generation: Create videos from textual descriptions using models like Veo, Grok, and WAN.
• Image-to-Video Animation: Animate static images into dynamic video content with models like Wan and Seedance.
• AI Avatars & Lipsync: Generate talking head videos or animate faces with audio using OmniHuman and Fabric.
• Video Enhancement: Upscale video quality or add sound effects with specialized tools.
• Use Case: Quickly produce social media clips, marketing content, or explainer videos by leveraging various AI models through a unified CLI.

Quick Start

Generate a video with Veo by running the command infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'.