Diff-TONE selects the prompt-swap timestep using a distilled latent instrument classifier, improving content preservation over fixed timestep baselines in text-to-music diffusion editing.
Universal guidance for diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models
Diff-TONE selects the prompt-swap timestep using a distilled latent instrument classifier, improving content preservation over fixed timestep baselines in text-to-music diffusion editing.