# lucidrains/denoising-diffusion-pytorch

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/lucidrains-denoising-diffusion-pytorch).**

10,614 stars · 1,286 forks · Python · MIT

## Links

- GitHub: https://github.com/lucidrains/denoising-diffusion-pytorch
- awesome-repositories: https://awesome-repositories.com/repository/lucidrains-denoising-diffusion-pytorch.md

## Topics

`artificial-intelligence` `deep-learning` `generative-model` `score-matching`

## Description

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

## Tags

### Part of an Awesome List

- [Diffusion Models](https://awesome-repositories.com/f/awesome-lists/ai/diffusion-models.md) — Implements the Denoising Diffusion Probabilistic Model for generating images and sequences using a U-Net backbone.
- [Gaussian Noise Diffusion](https://awesome-repositories.com/f/awesome-lists/ai/gaussian-noise-diffusion.md) — Defines a fixed variance schedule that progressively corrupts data from clean to pure noise.
- [Sequence](https://awesome-repositories.com/f/awesome-lists/ai/diffusion-models/sequence.md) — Generates one-dimensional sequences like time series or audio features by applying a learned diffusion process.

### Artificial Intelligence & ML

- [Image Diffusion Models](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/image-diffusion-models.md) — Generates images by iteratively denoising random noise through a learned reverse diffusion process.
- [Diffusion Sampling Methods](https://awesome-repositories.com/f/artificial-intelligence-ml/diffusion-sampling-methods.md) — Generates new data by iteratively applying the learned denoising step from random noise.
- [Diffusion Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/diffusion-models/diffusion-model-training.md) — Trains a denoising diffusion probabilistic model on images or sequences using a U-Net backbone.
- [Automated Folder-Based Training](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/diffusion-models/diffusion-model-training/automated-folder-based-training.md) — Automates the training loop for diffusion models by pointing at a folder of images, handling checkpointing and sample logging. ([source](https://cdn.jsdelivr.net/gh/lucidrains/denoising-diffusion-pytorch@main/README.md))
- [Noise-to-Image Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-image-models/noise-to-image-generation.md) — Trains a diffusion model on images and generates new images by reversing the noise process. ([source](https://cdn.jsdelivr.net/gh/lucidrains/denoising-diffusion-pytorch@main/README.md))
- [U-Net Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-architectures/u-net-architectures.md) — Uses a symmetric encoder-decoder U-Net with skip connections for multi-scale spatial feature processing.
- [Sinusoidal Timestep Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/positional-embedding-techniques/rotary-positional-embeddings/positional-embedding-manipulation/sinusoidal-timestep-embeddings.md) — Encodes the diffusion timestep using sinusoidal embeddings to condition the model on noise level.
- [Sinusoidal Encodings](https://awesome-repositories.com/f/artificial-intelligence-ml/positional-encoding-techniques/sinusoidal-encodings.md) — Injects sinusoidal positional encodings of the diffusion step to condition predictions on noise level.
- [Diffusion Model Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-training-frameworks/diffusion-model-frameworks.md) — Provides a PyTorch-based framework for training and sampling from diffusion models on images and one-dimensional data.
- [Multi-GPU Training Distributions](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/diffusion-models/diffusion-model-training/multi-gpu-training-distributions.md) — Distributes diffusion model training across multiple GPUs using PyTorch's DistributedDataParallel for faster convergence.
- [1D](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation/1d.md) — Generates new one-dimensional sequences like time series or audio features using a learned diffusion process. ([source](https://cdn.jsdelivr.net/gh/lucidrains/denoising-diffusion-pytorch@main/README.md))
- [Diffusion-Based](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation/diffusion-based.md) — Trains a diffusion model on 1D sequence data and samples new sequences by reversing the noise process. ([source](https://cdn.jsdelivr.net/gh/lucidrains/denoising-diffusion-pytorch@main/README.md))

### Graphics & Multimedia

- [Automated Training Pipelines](https://awesome-repositories.com/f/graphics-multimedia/image-file-loading/folder-structured-image-loading/automated-training-pipelines.md) — Automates the training loop for a diffusion model from a folder of images, handling checkpointing and logging. ([source](https://cdn.jsdelivr.net/gh/lucidrains/denoising-diffusion-pytorch@main/README.md))