AI Media Production Toolkit

## Overview

A complete AI media production pipeline — generate images with 50+ models (FLUX, Gemini, Grok), create videos from text/images/audio using 40+ models (Veo, Wan, OmniHuman), and handle text-to-speech and speech-to-text via fal.ai audio models.

## Quick Start

1. Install: `npx skillstore add @ai-media-production-toolkit`
2. Generate an image: use the **ai-image-generation** skill with inference.sh CLI to create images from text prompts using FLUX, Gemini 3 Pro Image, Grok Imagine, or other models
3. Create a video: use the **ai-video-generation** skill to generate videos from text, images, or audio with Veo 3.1, Grok Video, Wan 2.5, and more
4. Convert audio: use the **fal-audio** skill for text-to-speech or speech-to-text via fal.ai

## Key Commands

- **ai-image-generation**: Text-to-image, image-to-image, inpainting, LoRA, upscaling — supports FLUX Dev LoRA, Seedream 4.5, Reve, ImagineArt and 50+ models
- **ai-video-generation**: Text-to-video, image-to-video, audio-driven generation — supports Veo 3.1, Grok Video, Wan 2.5, OmniHuman and 40+ models
- **fal-audio**: Text-to-speech and speech-to-text using fal.ai audio models

## Tips

- Chain skills: generate an image with ai-image-generation, then animate it into a video with ai-video-generation
- Add voiceover with fal-audio TTS and combine with your generated video
- Great for social media content, product mockups, marketing visuals, and AI art workflows