A co-designed 4-bit quantization and temporal sparsity scheme, with a matching dense-sparse accelerator, speeds up diffusion model inference by 6.91x with 51.5% energy reduction at near-FP32 image quality.
Align your latents: High-resolution video synthesis with latent diffusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity
A co-designed 4-bit quantization and temporal sparsity scheme, with a matching dense-sparse accelerator, speeds up diffusion model inference by 6.91x with 51.5% energy reduction at near-FP32 image quality.