conditional-flow-matching
conditional-flow-matching copied to clipboard
atong01
TorchCFM: a Conditional Flow Matching library
This PR adds support for distributed data parallel (DDP) and replaces `DataParallel` with `DistributedDataParallel` in `train_cifar.py`, which can be used via the flag `parallel`. To achieve this, the code is...
Hello, thanks for the wonderful package. I am trying to do time series anomaly detection using normalizing flows/flow matching. My idea is to use a sliding window to obtain multiple...
I am getting a lot of help from this project. Thank you! I have one question. Is the method for generating samples(ex images) with models trained using the FM framework...
Hi all, huge fan of your work/this library, we've had great success with training latent flow matching models. Our model relies on multiple conditions to generate x1, it looks like...
Been having great success using cfm over diffusion methods for audio tasks so far, kudos for the great library! One thing I'm having trouble wrapping my head around is the...
Hi, I'm working on an ODE-based generative model using conditional flow matching. However, I'm encountering an issue where the computed average probabilities of generated samples are consistently 0. I suspect...
Hi, I have read the paper "Simulation-free Schr\"odinger bridges via score and flow matching", interesting work and very nice presentation! After read through it, I have some questions. According to...
Hi, very interesting work and nice presentation in paper. I'm interested in applying conditional flow matching to the tasks without paired training data. For example, many image restoration tasks do...
Dear experts, Thank you very much for this nice package! I am trying to use your batch OT version of flow matching to perform the matching between two distributions, but...
