Concept
Consistency function
A consistency function is the core object of consistency models: a learned map f(x_t, t) that takes a noisy sample x_t at any diffusion timestep t and returns the clean endpoint of that sample's probability-flow ODE trajectory. Think of it like a diffusion sampler,…
The rest of “Consistency function” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→