https://github.com/louis-alexandre-laguet/diffusion_model
This repository contains multiple implementations of Diffusion Models, starting from the Denoising Diffusion Probabilistic Model (DDPM) and progressing to its conditional version (CDM). The project explores image generation by reversing the diffusion and denoising processes.
https://github.com/louis-alexandre-laguet/diffusion_model
ai cdm ddpm deep-learning diffusion-models generative-models image-generation
Last synced: about 1 year ago
JSON representation
This repository contains multiple implementations of Diffusion Models, starting from the Denoising Diffusion Probabilistic Model (DDPM) and progressing to its conditional version (CDM). The project explores image generation by reversing the diffusion and denoising processes.
- Host: GitHub
- URL: https://github.com/louis-alexandre-laguet/diffusion_model
- Owner: louis-alexandre-laguet
- Created: 2025-03-22T09:20:49.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-22T10:27:47.000Z (about 1 year ago)
- Last Synced: 2025-03-22T11:26:48.166Z (about 1 year ago)
- Topics: ai, cdm, ddpm, deep-learning, diffusion-models, generative-models, image-generation
- Language: Jupyter Notebook
- Homepage:
- Size: 18.5 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Diffusion Models Implementation (DDPM & CDM)
This repository contains several implementations of diffusion models, starting with a Denoising Diffusion Probabilistic Model (DDPM) and progressing to a conditional version (CDM). These exercises allow exploring image generation using a diffusion and denoising process.
## Repository Content
### 1. DDPM Implementation and Sampling Process
**Objective:**
- Understand how probabilistic diffusion models (DDPM) work.
- Learn how images are generated by reversing a noise diffusion process.
- Implement the sampling process to progressively denoise an image from pure noise.
### 2. DDPM Implementation and Training Process
**Objective:**
- Train a DDPM model on image data.
- Implement the loss function and train the denoising network.
- Observe the improvement in image quality as the model progresses.
### 3. Training a Conditional Diffusion Model (CDM)
**Objective:**
- Extend the DDPM approach to allow for conditional image generation.
- Condition the model on additional information (e.g., class labels, textual descriptions, structured attributes).
- Experiment with a Conditional Denoising Diffusion Model (CDDM) for more precise control over generated images.
Trained models are saved in the `models` directory.