3 papers
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.LG2025
Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion Models
Basile Lewandowski, Robert Birke, Lydia Y. Chen
Text-to-image (T2I) models based on diffusion and transformer architectures advance rapidly. They are often pretrained on large corpora, and openly shared on a model platform, such…
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…