Sparse VideoGen accelerates video diffusion transformers by about 2.3x with only small quality loss by classifying attention heads into spatial and temporal sparse patterns and using hardware-friendly layouts.
Condition-aware neural network for controlled image generation
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
-
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Sparse VideoGen accelerates video diffusion transformers by about 2.3x with only small quality loss by classifying attention heads into spatial and temporal sparse patterns and using hardware-friendly layouts.