References

GenSBI is inspired by and builds upon a broad body of research in simulation-based inference, flow matching, and diffusion models. Below are key libraries and papers that have influenced the development of this project.

If you use GenSBI, please consider citing these works, which provide the theoretical foundations and methodologies implemented in this library.

Libraries and Implementations

• Facebook Flow Matching Library

• EDM: Elucidating the Design Space of Diffusion-Based Generative Models

• Simformer Model

• Flux1 Model from BlackForest Lab

Foundational Papers

• Y. Lipman et al. “Flow Matching for Generative Modeling.” arXiv:2210.02747

• Y. Lipman et al. “Flow Matching Guide and Code.” arXiv:2412.06264

• Y. Song et al. “Score-Based Generative Modeling through Stochastic Differential Equations.” arXiv:2011.13456

• T. Karras et al. “Elucidating the Design Space of Diffusion-Based Generative Models.” arXiv:2206.00364

• M. Gloeckler et al. “All-in-one simulation-based inference.” arXiv:2404.09636

• Black Forest Labs “FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space.” arXiv:2506.15742