Noise Consistency Training adds new controls to pre-trained one-step generators by training a lightweight adapter with a noise-space consistency loss, matching conditional generation quality at a fraction of the compute.
Diff- instruct: A universal approach for transferring knowledge from pre-trained diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
Noise Consistency Training adds new controls to pre-trained one-step generators by training a lightweight adapter with a noise-space consistency loss, matching conditional generation quality at a fraction of the compute.