FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models

Researchers introduced FLOWBUDGET, a training-free estimator of solver-relative sampling complexity for flow matching models, detailed in arXiv paper 2610.20636v1. FLOWBUDGET normalizes leading one-step discretization error by motion, estimates its coefficient from simulation-free interpolation probes, and maps a numerical tolerance to a step budget using solver order, with derived estimators for Euler and Heun ODE sampling and additive-noise Euler-Maruyama SDE sampling. Experiments on SiT, FlowDCN and Rectified Flow models test whether FLOWBUDGET can estimate the number-of-function-evaluations budget without generating samples at multiple budgets or running an FID-versus-NFE sweep; code is available at https://github.com/Yasaman-dt/FlowBudget.

arXiv:2610.20636v1 Announce Type: new Abstract: Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evaluations NFEs . In practice, the sampling budget is inherited from prior work or selected through expensive FID-versus-NFE sweeps, using FID to assess image-generation quality, requiring sample generation and evaluation at multiple budgets. This makes sampling-budget selection dependent on repeated empirical evaluation. We therefore ask a complementary question to solver design and timestep allocation: for a fixed pretrained model and solver, what numerical resolution is sufficient? We introduce FLOWBUDGET, a training-free estimator of solver-relative sampling complexity. Using simulation-free interpolation probes of the learned dynamics, FLOWBUDGET normalizes the leading one-step discretization error by the motion, estimates its coefficient from interpolation probes, and maps a numerical tolerance to a step budget using the solver order. We derive estimators for numerical solvers in flow~matching sampling, namely Euler and Heun for ODE sampling and additive-noise Euler--Maruyama for SDE sampling, and connect the ODE coefficients to terminal integration error. Experiments on SiT, FlowDCN and Rectified Flow models, spanning flow-model architectures and formulations, test whether FLOWBUDGET can estimate the NFE budget without generating samples at multiple budgets or performing an FID-versus-NFE sweep. The code is available at https://github.com/Yasaman-dt/FlowBudget