Diffusion models have an SNR-timestep mismatch during inference that the authors mitigate with per-frequency differential correction, raising generation quality across IDDPM, ADM, DDIM and others.
Progressive distillation for fast sampling of diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CR-Diff applies block-wise pruning followed by output amplification to diffusion models, improving consistency and fidelity at unseen resolutions while retaining default-resolution performance.
citing papers explorer
-
Elucidating the SNR-t Bias of Diffusion Probabilistic Models
Diffusion models have an SNR-timestep mismatch during inference that the authors mitigate with per-frequency differential correction, raising generation quality across IDDPM, ADM, DDIM and others.
-
Cross-Resolution Diffusion Models via Network Pruning
CR-Diff applies block-wise pruning followed by output amplification to diffusion models, improving consistency and fidelity at unseen resolutions while retaining default-resolution performance.