Metadata-Version: 2.4
Name: openvto
Version: 0.0.1
Summary: Open-source toolkit for building studio-quality virtual try-ons with generative AI
Project-URL: Homepage, https://openvto.com
Project-URL: Repository, https://github.com/Prompt-Haus/OpenVTO
Project-URL: Issues, https://github.com/Prompt-Haus/OpenVTO/issues
Author: OpenVTO Contributors
License-Expression: MIT
License-File: LICENSE
Keywords: fashion,generative-ai,image-generation,video-generation,virtual-try-on
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.9
Provides-Extra: dev
Requires-Dist: pytest-cov>=4.0; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: ruff>=0.1.0; extra == 'dev'
Description-Content-Type: text/markdown

# OpenVTO

**OpenVTO** is an open-source toolkit for building studio-quality virtual try-ons with generative AI, both as high-end still photos and short animated loops.

It provides a stable and consistent workflow for generating clean "studio avatar" images, swapping outfits from product images, and optionally turning the result into a 4-8s motion clip using image-to-video models.

OpenVTO is designed for **speed**, **consistency**, and **aesthetics**: uniform lighting, controlled backgrounds, repeatable outputs that feel like a premium fashion app.

---

## What OpenVTO Includes

| Feature | Description |
|---------|-------------|
| **Avatar Base Layer** | Generate studio-quality avatars from 1–2 photos with controlled lighting and backgrounds |
| **Outfit Compositing** | Garment swap from catalog images — single items or complete bundles |
| **Still → Video Pipeline** | Animated try-ons as loop-friendly 4–8s clips using image-to-video models |
| **Prompt Templates & Guardrails** | Keep identity, body shape, and style consistent across generations |
| **Reference Implementations** | Python library with reproducible examples to get you started fast |

---

## Goal

OpenVTO's goal is simple: **make it easy for teams to ship virtual try-ons that look good enough to market, not just "tech demos."**

---

## Installation

```bash
pip install openvto
```

## Quick Start

```python
from openvto import OpenVTO

vto = OpenVTO()
print(vto.hello())  # Hello from OpenVTO!
```

---

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

---

## License

This project is open source. See the [LICENSE](LICENSE) file for details.
