This model learns a velocity field that transports Gaussian noise into 64x64 CelebA face images using flow matching.
1import torch
2from modeling import FlowMatchingModel
3
4model = FlowMatchingModel.from_pretrained(".")
5model.eval()
This project uses a minimal Euler ODE sampler with flow matching and a velocity target:
1x_t = (1 - t) * x0 + t * x1
2target_v = x1 - x0
The checkpoint in this repo is a raw PyTorch state dict generated by the training script.
