A training-free diffusion sampling method exploits an observed linear relation between initial noise perturbations and output changes to control the sample mean and diversity around a target image.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
A training-free diffusion sampling method exploits an observed linear relation between initial noise perturbations and output changes to control the sample mean and diversity around a target image.