MSF factorizes the diffusion denoising target into a low-frequency base and a high-frequency residual, generating them sequentially to improve FID and cut sampling cost by roughly 4x over DiT.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MSF: Efficient Diffusion Model Via Multi-Scale Latent Factorize
MSF factorizes the diffusion denoising target into a low-frequency base and a high-frequency residual, generating them sequentially to improve FID and cut sampling cost by roughly 4x over DiT.