Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

TL;DR

This paper introduces Ctrl-Z Sampling, a scalable method for improving diffusion model sampling by detecting quality plateaus and exploring alternative denoising paths to enhance generated sample quality.

Contribution

We propose Ctrl-Z Sampling, a novel scalable sampling strategy that detects quality plateaus and adaptively explores alternative trajectories to escape local optima in diffusion models.

Findings

Consistently improves generation quality over existing samplers.

Effective across different NFE budgets and diffusion frameworks.

Offers a scalable compute-quality trade-off.

Abstract

Diffusion models generate conditional samples by progressively denoising Gaussian noise, yet the denoising trajectory can stall at visually plausible but low-quality outcomes with conditional misalignment or structural artifacts. We interpret this behavior as local optima in a surrogate quality landscape: Once early denoising commits to a suboptimal global structure, later steps mainly sharpen details and seldom correct the underlying mistake. While existing inference-time approaches explore alternative diffusion states via re-noising with fixed strength or direction, they exhibit limited capacity to escape steep quality plateaus. We propose Controlled Random Zigzag Sampling (Ctrl-Z Sampling),a scalable sampling strategy that detects plateaus in quality landscape via a surrogate score, and allocates exploration only when a plateau is detected. Upon detection, Ctrl-Z Sampling rolls back to noisier states, samples a set of alternative continuations, and updates the trajectory when a candidate improves the score, otherwise escalating the exploration depth to escape the current plateau. The proposed method is model-agnostic and broadly compatible with existing diffusion frameworks. Experiments show that Ctrl-Z Sampling consistently improves generation quality over other inference-time scaling samplers across different NFE budgets, offering a scalable compute-quality trade-off.