RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling

TL;DR

This paper introduces energy-aware guidance scheduling for high-resolution diffusion models, improving stability and image quality by analyzing and modulating guidance strength over time.

Contribution

It proposes adaptive guidance schedules based on energy profiling, enhancing stability and visual fidelity in high-resolution image synthesis.

Findings

Energy-aware scheduling improves stability scores to 0.9998

Adaptive guidance reduces artifacts and enhances image sharpness

DPM++ 2M with linear-decreasing CFG achieves optimal results

Abstract

High-resolution image synthesis with diffusion models often suffers from energy instabilities and guidance artifacts that degrade visual quality. We analyze the latent energy landscape during sampling and propose adaptive classifier-free guidance (CFG) schedules that maintain stable energy trajectories. Our approach introduces energy-aware scheduling strategies that modulate guidance strength over time, achieving superior stability scores (0.9998) and consistency metrics (0.9873) compared to fixed-guidance approaches. We demonstrate that DPM++ 2M with linear-decreasing CFG scheduling yields optimal performance, providing sharper, more faithful images while reducing artifacts. Our energy profiling framework serves as a powerful diagnostic tool for understanding and improving diffusion model behavior.