Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
TMPDiff: Temporal Mixed-Precision for Diffusion Models
Basile Lewandowski, Simon Kurz, Aditya Shankar +3
Diffusion models are the go-to method for Text-to-Image generation, but their iterative denoising processes has high inference latency. Quantization reduces compute time by using l…
cs.CV2024
MPQ-Diff: Mixed Precision Quantization for Diffusion Models
Rocco Manz Maruzzelli, Basile Lewandowski, Lydia Y. Chen
Diffusion models (DMs) generate remarkable high quality images via the stochastic denoising process, which unfortunately incurs high sampling time. Post-quantizing the trained diff…