Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

Researchers have developed Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework that propagates reward-tilted clean-image distributions across all noise levels to improve one-step text-to-image generation. The method addresses a mismatch between terminal reward optimization and generative dynamics that previously caused image fidelity loss. DIDR consistently outperforms existing one-step SDXL baselines and, when applied to a 6B DiT backbone, surpasses its 50-step teacher in preference alignment using only a single generation step.

arXiv:2605.24001v1 Announce Type: new Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward DIDR , a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score DRS , which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy DRP , an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone Z-Image , DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.