RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling
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.
Similar Papers
Dynamic Classifier-Free Diffusion Guidance via Online Feedback
Machine Learning (CS)
Makes AI pictures match words better.
Energy Scaling Laws for Diffusion Models: Quantifying Compute and Carbon Emissions in Image Generation
Machine Learning (CS)
Predicts computer power use for making pictures.
Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Quantum Physics
Makes AI art look better by adjusting its settings.