Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Onkarsus13/D2Styler
This is an official implimentation of D2Styler
https://github.com/Onkarsus13/D2Styler
Last synced: about 2 months ago
JSON representation
This is an official implimentation of D2Styler
- Host: GitHub
- URL: https://github.com/Onkarsus13/D2Styler
- Owner: Onkarsus13
- License: apache-2.0
- Created: 2024-07-09T04:58:28.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-08-08T07:38:04.000Z (about 2 months ago)
- Last Synced: 2024-08-08T08:47:31.618Z (about 2 months ago)
- Language: Python
- Size: 5.68 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Citation: CITATION.cff
Awesome Lists containing this project
- awesome-diffusion-categorized - [Code
README
# D2Styler
Welcome to the official implementation of [D2Styler](https://arxiv.org/pdf/2408.03558v1), which has been accepted at the International Conference on Pattern Recognition (ICPR 2024).
## Overview
"D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods" introduces a novel framework for style transfer called D2Styler. Leveraging VQ-GANs and discrete diffusion, this method aims to improve the quality and stability of style transfer, addressing common issues like mode-collapse and over/under-stylization. By using Adaptive Instance Normalization (AdaIN) features, D2Styler facilitates effective style transfer between images. Experimental results show that D2Styler outperforms twelve existing methods on various metrics, producing high-quality, visually appealing images. The method uses images from the WikiArt and COCO datasets.
The model's architecture and its qualitative results are showcased below. The model will be available on HuggingFace 🤗, where you can download it for inference or fine-tuning.
## Model Architecture
## Results
## Installation
To get started with D2Styler, follow the steps below to install the necessary dependencies:
1. Clone the repository:
```bash
git clone https://github.com/yourusername/D2Styler.git
cd D2Styler
```
2. Install the dependencies:
```bash
pip install -e ".[torch]"
pip install -e .[all,dev,notebooks]
```
## Contributing
We welcome contributions to D2Styler! If you have any ideas for improvements or find any issues, please feel free to open an issue or submit a pull request.
For more details, please refer to our [paper](https://arxiv.org/pdf/2408.03558v1) and our repository on [HuggingFace](https://huggingface.co/).