1 dépôt
Awesome GitHub RepositoriesGeneral Purpose Flow Matching
Frameworks that implement flow matching algorithms for a wide variety of data types beyond specific domains like audio or images.
Distinct from Flow-Matching Frameworks: Distinct from Flow-Matching Frameworks in that it provides a general-purpose implementation for continuous and discrete flow matching across multiple modalities, not just image-specific diffusion.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · General Purpose Flow Matching. Refine with filters or upvote what's useful.
Awesome General Purpose Flow Matching GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- facebookresearch/flow_matching
facebookresearch/flow_matching
4,562Voir sur GitHubThis project is a PyTorch-based generative model framework designed to transform noise into complex data distributions by learning vector fields and probability paths. It serves as a multimodal generative toolkit for producing synthetic text and images through learned probability flows. The library distinguishes itself by supporting continuous, discrete, and Riemannian manifold integrations. This allows the framework to handle a variety of data types, including categorical data via discrete-state flow matching and non-Euclidean spaces through Riemannian manifold integration. The toolkit cove
Provides a PyTorch-based library for implementing continuous and discrete flow matching algorithms to train generative models.
Python
