Forward-only Diffusion Probabilistic Models

ICLR 2026 Conference Submission19261 Authors

Keywords: Diffusion models, image generation, image restoration, computer vision application

TL;DR: This paper proposes a simple and effective forward-only diffusion model for image generation.

Abstract: This work presents a forward-only diffusion (FoD) approach for generative modelling. In contrast to traditional diffusion models that rely on a coupled forward-backward diffusion scheme, FoD directly learns data generation through a single forward diffusion process, yielding a simple yet efficient generative framework. The core of FoD is a state-dependent stochastic differential equation that involves a mean-reverting term in both the drift and diffusion functions. This mean-reversion property guarantees the convergence to clean data, naturally simulating a stochastic interpolation between source and target distributions. More importantly, FoD is analytically tractable and is trained using a simple stochastic flow matching objective, enabling a few-step non-Markov chain sampling during inference. The proposed FoD model—despite its simplicity—achieves state-of-the-art performance on various image restoration tasks. Its general applicability on image-conditioned generation is also demonstrated via qualitative results on image-to-image translation.

Primary Area: generative models

Submission Number: 19261