https://github.com/adonath/jax-diffusion-models-pydata-boston-2025
A Beginner's friendly introduction to Diffusion Models in JAX given at PyData Boston 2025
https://github.com/adonath/jax-diffusion-models-pydata-boston-2025
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
1 of 1 committers (100.0%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.1%) to scientific vocabulary
Repository
A Beginner's friendly introduction to Diffusion Models in JAX given at PyData Boston 2025
Basic Info
- Host: GitHub
- Owner: adonath
- Language: Jupyter Notebook
- Default Branch: main
- Size: 9.84 MB
Statistics
- Stars: 4
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
A Beginner's Friendly Introduction to Diffusion Models in JAX
This repository contains a beginner-friendly introduction to diffusion models in JAX given at the Pydata Boston meeting on June 18th, 2025.
Getting Started
If you would like to run the code yourself, you can clone the repository and install the dependencies. All the examples and notebook should run on a standard laptop.
bash
git clone https://github.com/adonath/jax-diffusion-models-pydata-boston-2025.git
cd jax-diffusion-models-pydata-boston-2025
To setup the environment you can use just a standard Python virtual env:
```bash python -m venv jax-diffusion-pydata-boston ./jax-diffusion-pydata-boston/bin/activate python -m pip install -r requirements.txtx
```
Alternatively you can also use uv:
bash
uv venv
source jax-diffusion-models-pydata-boston-2025/bin/activate
uv pip install -r requirements.txt
Or conda / mamba:
bash
conda env create --name jax-diffusion-pydata-boston --file requirements.txt
conda activate jax-diffusion-pydata-boston
Finally:
bash
jupyter notebook jax-diffusion-models-pydata-boston-2025.ipynb
```
Note on Colab GPU:s If you use Google colab you can experiment with hardware accelerator GPU / TPU. For this you have to change the
runtime environment, using: Runtime -> Change Runtime Type -> T4 GPU -> Save and then reconnect.
JAX will create all the arrays on the default device, which is the GPU when selected. However please do not
expect large speed ups on these toy examples, the overhead might be much larger than the actual computing time.
If you are interested in how to benchmark JAX code, you should definitely read: https://docs.jax.dev/en/latest/faq.html#benchmarking-jax-code
Owner
- Name: Axel Donath
- Login: adonath
- Kind: user
- Location: Cambridge, MA
- Company: Center for Astrophysics | Havard & Smithonian
- Website: https://axeldonath.com
- Repositories: 68
- Profile: https://github.com/adonath
I'm a Postdoc researcher at Center for Astrophysics. I work on statistical methods for analysis of low counts astronomical data.
GitHub Events
Total
- Watch event: 1
- Public event: 1
- Push event: 22
Last Year
- Watch event: 1
- Public event: 1
- Push event: 22
Committers
Last synced: 12 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Axel Donath | a****h@c****u | 33 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 12 months ago
Dependencies
- equinox *
- ffmpeg *
- jax *
- matplotlib *
- notebook *
- numpy *
- optax *
- safetensors *
- scikit-learn *
- tqdm *
- actions/checkout v3 composite
- actions/setup-python v4 composite
- stefanzweifel/git-auto-commit-action v4.16.0 composite