Metadata-Version: 2.4
Name: vintagify
Version: 0.1.2
Summary: A simple CycleGAN-based image translation package (modern <-> vintage)
Author: Yusong Zhao, Fangyi Wang
Author-email: yusongzhao@link.cuhk.edu.cn, fangyiwang@link.cuhk.edu.cn
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: Pillow
Requires-Dist: matplotlib
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: license
Dynamic: license-file
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# vintagify

A simple Python package for image-to-image translation using  CycleGAN model.  
Easily convert modern photos into vintage-style images with just one function call.

---

## ✨ Features

- 🎨 Translate modern images to vintage style using pretrained model.
- 🔁 Based on CycleGAN with unpaired training capability.
- 📦 Packaged with built-in pretrained model – no extra downloads required.
- 🔧 Simple API, minimal setup.

---

## 📦 Installation

Install via pip:

```bash
pip install vintagify
```
---

## 🚀 Quick Start

```python
from vintagify import translate_image

translate_image("photo.jpg", "photo_vintage.jpg")
```

---

## 📐 Input Requirements

- Input image should be at least **500×500** pixels.
- The image will be automatically center-cropped and resized to 512×512.

---

## 📝 License

MIT License © 2025 beingbetter11643



