Latent inter-frame pruning plus attention recovery raises video diffusion throughput 1.44x to 12.44 FPS while keeping quality, by skipping duplicate latent patches.
Token merging for fast stable diffusion.CVPR Workshop on Efficient Deep Learning for Computer Vision, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation
Latent inter-frame pruning plus attention recovery raises video diffusion throughput 1.44x to 12.44 FPS while keeping quality, by skipping duplicate latent patches.