https://github.com/qiauil/distrans
A PyTorch Library for Distribution Transformation in Generative Modeling
https://github.com/qiauil/distrans
diffusion-models flowmatching generative-model
Last synced: about 1 year ago
JSON representation
A PyTorch Library for Distribution Transformation in Generative Modeling
- Host: GitHub
- URL: https://github.com/qiauil/distrans
- Owner: qiauil
- License: mit
- Created: 2024-08-29T13:14:13.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-11-07T15:58:43.000Z (over 1 year ago)
- Last Synced: 2025-06-10T00:05:32.194Z (about 1 year ago)
- Topics: diffusion-models, flowmatching, generative-model
- Language: Jupyter Notebook
- Homepage:
- Size: 1.88 MB
- Stars: 3
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
distrans
A PyTorch Library for Distribution Transformation in Generative Modeling
## Installation
* Install the latest version through pip: `pip install git+https://github.com/qiauil/distrans`
* Install locally: Download the repository and run `./install.sh` or `pip install .`
## Playground
* Distribution transformation from Gaussian: [gaussian.ipynb](https://github.com/qiauil/distrans/blob/main/gaussian.ipynb)
* Transform moons distribution to swiss distribution: [moons2swiss.ipynb](https://github.com/qiauil/distrans/blob/main/moons2swiss.ipynb)
## Additional Info
This work is part of our physics-based deep learning research, please visit [the website of our research group at TUM](https://ge.in.tum.de/publications/) for more information.
## Useful reference
### Diffusion
* [***Denoising Diffusion Probabilistic Models***, Jonathan Ho, Ajay Jain and Pieter Abbeel, NeurIPS, 2020](https://arxiv.org/abs/2006.11239)
* [***Diffusion Models Beat GANs on Image Synthesis***, Prafulla Dhariwal and Alex Nichol, NeurIPS, 2021](https://arxiv.org/abs/2105.05233)
### Flow Matching
* [***Flow Matching for Generative Modeling***, Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, and Matthew Le, ICLR, 2023](https://arxiv.org/abs/2210.02747)
* [***Improving and generalizing flow-based generative models with minibatch optimal transport***, Alexander Tong, Kilian Fatras, Nikolay Malkin, Guillaume Huguet, Yanlei Zhang, Jarrid Rector-Brooks, Guy Wolf and Yoshua Bengio, TMLR, 2024](https://arxiv.org/abs/2302.00482)
* [***An introduction to Flow Matching***, Fjelde, Tor and Mathieu, Emile and Dutordoir, Vincent, 2024](https://mlg.eng.cam.ac.uk/blog/2024/01/20/flow-matching.html)