Score: 0

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

Published: July 13, 2025 | arXiv ID: 2507.09441v1

By: Ankit Sanjyal

Potential Business Impact:

Makes AI pictures look better and more real.

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.

Country of Origin
🇺🇸 United States

Page Count
8 pages

Category
Computer Science:
Graphics