🎬 Comic Video Studio

A Python-based application that converts comic images into narrated videos with cinematic zoom effects, transitions, and AI-generated voice.

---

🚀 Features (MVP)

• Upload multiple comic images
• Convert script into voice narration (TTS)
• Sync images with narration
• Apply zoom (Ken Burns effect)
• Export final video (MP4)

---

🧠 Future Features

• AI script generation (OpenAI / local models)
• Panel/region-based cropping
• Subtitles
• Background music
• Advanced transitions
• Desktop app UI

---

⚙️ Tech Stack

• Python
• MoviePy (video processing)
• FFmpeg (rendering backend)
• OpenCV & Pillow (image processing)
• Coqui TTS (free voice generation)
• ElevenLabs (optional premium voice)
• Streamlit (UI - upcoming)

---

📂 Project Structure (Planned)

comic-video-studio/
│
├── main.py
├── modules/
│   ├── image_processor.py
│   ├── tts_engine.py
│   ├── video_engine.py
│   ├── script_engine.py
│
├── images/
├── audio/
├── output/
├── requirements.txt
└── README.md

---

🛠️ Setup

1. Clone Repo

git clone https://github.com/yourusername/comic-video-studio.git
cd comic-video-studio

2. Create Virtual Environment

python -m venv venv

Activate:

venv\Scripts\activate

3. Install Dependencies

pip install -r requirements.txt

4. Install FFmpeg

Make sure FFmpeg is installed and added to PATH.

---

▶️ Run

python main.py

---

⚠️ Notes

• This project is in early development (MVP stage)
• Designed for learning + content automation workflows
• Ensure proper usage of copyrighted content

---

📌 Status

🚧 In Development – Version 0.1 (Core Pipeline)

---

🤝 Contributions

Open for improvements and feature ideas.