Diff-VF extends short-video diffusion models to longer videos at inference time by combining noise mixing, weighted window fusion, and temporally dilated sampling, with no retraining.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diff-VF: Training-free High-quality Long Video Generation via Diffusion Model
Diff-VF extends short-video diffusion models to longer videos at inference time by combining noise mixing, weighted window fusion, and temporally dilated sampling, with no retraining.