An open API service indexing awesome lists of open source software.

https://github.com/deepmancer/diffusion-gan-vae-pytorch

A PyTorch implementation of various deep generative models, including Diffusion (DDPM), GAN, cGAN, and VAE.
https://github.com/deepmancer/diffusion-gan-vae-pytorch

conditional-diffusion conditional-gan conditional-generation diffusion-models fashion-mnist from-scratch generative-adversarial-network mnist pytorch vae-pytorch

Last synced: 3 months ago
JSON representation

A PyTorch implementation of various deep generative models, including Diffusion (DDPM), GAN, cGAN, and VAE.

Awesome Lists containing this project

README

        

# 🎨 Deep Generative Models in PyTorch


PyTorch
Python
Jupyter Notebook
License

> Master deep generative models in PyTorch with ease!

Welcome to **Diffusion-GAN-VAE-PyTorch**! This repository is your ultimate resource for mastering deep generative models, implemented from scratch in PyTorch. It features **Variational Autoencoders (VAE)**, **Generative Adversarial Networks (GAN)**, **Conditional GANs**, **Diffusion Models**, and **Conditional Diffusion Models**, all crafted with clarity and precision.

---

| **Source Code** | **Website** |
|:-----------------|:------------|
| github.com/deepmancer/diffusion-gan-vae-pytorch | deepmancer.github.io/diffusion-gan-vae-pytorch |

---

## 🌟 Highlights

- 🧩 Modular & Educational
- 🔍 Explore Cutting-Edge Models
- 💡 Beginner-Friendly Yet Research-Ready
- 📕 Fully documented

👉 **[Star this repo](https://github.com/deepmancer/diffusion-gan-vae-pytorch/stargazers)** if you find it helpful, and join our community of AI enthusiasts!

---

## 🌠 Results

### Fashion MNIST


Fashion MNIST Results

### Conditional Diffusion Model


Conditional Diffusion Model Results 1
Conditional Diffusion Model Results 2

### Diffusion Model


Diffusion Model Results 1
Diffusion Model Results 2

### Conditional GAN


Conditional GAN Results

### GAN


GAN Results 1
GAN Results 2

### VAE


VAE Results 1
VAE Results 2

---

## 🛠️ Installation

### Requirements
Ensure the following dependencies are installed:

- **Python 3**: The programming language used.
- **PyTorch**: The deep learning framework for model building and training.
- **NumPy**: For numerical computations.
- **Matplotlib**: For result visualizations.
- **tqdm**: For progress tracking.

Install dependencies with pip:

```bash
pip install torch numpy matplotlib tqdm
```

---

## 🌀 Models Overview

### 🔹 Variational Autoencoder (VAE)
A **VAE** learns a probabilistic latent space, enabling smooth interpolation and robust generation of new data points.

### 🔹 Generative Adversarial Network (GAN)
**GANs** pit a generator against a discriminator in a game-like setup, creating highly realistic samples over time.

### 🔹 Conditional Generative Adversarial Network (cGAN)
**cGANs** incorporate conditional inputs (like class labels) to control data generation, enabling targeted synthesis.

### 🔹 Diffusion Models
**Diffusion Models** simulate a stochastic process to progressively model complex distributions, resulting in high-quality generation.

### 🔹 Conditional Diffusion Models
Building on diffusion models, **Conditional Diffusion Models** allow for guided, condition-driven generation.

---

## 🌟 Getting Started

1. Clone the repository:
```bash
git clone https://github.com/deepmancer/diffusion-gan-vae-pytorch.git
cd diffusion-gan-vae-pytorch
```

2. Install dependencies.

3. Run the notebook!

---

## 📝 License

This project is licensed under the **MIT License**. Feel free to use it in your projects while crediting the repository. See the [LICENSE](LICENSE) file for details.