atong01/conditional-flow-matching
A PyTorch library implementing conditional flow matching for training generative flow-based models.
Not currently ranked — collecting fresh signals.
star history
TorchCFM is a conditional flow matching library built on PyTorch and Lightning. It provides implementations of flow matching techniques that use optimal transport theory to construct continuous paths between probability distributions for generative modeling. The library supports training and evaluation workflows for flow-based models.
Frequently asked
- What is atong01/conditional-flow-matching?
- A PyTorch library implementing conditional flow matching for training generative flow-based models.
- Is conditional-flow-matching open source?
- Yes — atong01/conditional-flow-matching is open source, released under the MIT license.
- What language is conditional-flow-matching written in?
- atong01/conditional-flow-matching is primarily written in Python.
- How popular is conditional-flow-matching?
- atong01/conditional-flow-matching has 2.5k stars on GitHub.
- Where can I find conditional-flow-matching?
- atong01/conditional-flow-matching is on GitHub at https://github.com/atong01/conditional-flow-matching.