← Back to Portfolio
🎨

tiny-DDPM

2024.07 - 2024.08

📋 Project Overview

A from-scratch implementation of Denoising Diffusion Probabilistic Models (DDPM) designed for deep understanding of diffusion model mathematics and architecture.

🎯 Problem Definition & Goals

⚙️ Key Features & Contributions

🔧 Technical Challenges & Solutions

📈 Results & Learnings

🛠️ Technologies

Python PyTorch Hugging Face Datasets DDPM DDIM CFG U-Net

🔗 Links