How SADA Boosts Diffusion Model Sampling Speed by Up to 1.8× Without Losing Quality

The paper introduces SADA (Stability‑guided Adaptive Diffusion Acceleration), a novel paradigm that dynamically allocates sparsity per token using a unified stability criterion, enabling efficient ODE‑based sampling for diffusion and flow‑matching models, achieving up to 1.8× speedup with negligible fidelity loss across SD‑2, SDXL, Flux, ControlNet and MusicLDM.

Diffusion ModelsODEgenerative AI

0 likes · 5 min read

How SADA Boosts Diffusion Model Sampling Speed by Up to 1.8× Without Losing Quality

Alimama Tech

Aug 16, 2024 · Artificial Intelligence

SPLAM: Sub‑Path Linear Approximation for Accelerating Diffusion Model Sampling

SPLAM (Sub‑Path Linear Approximation Model) accelerates diffusion‑model image synthesis by linearly approximating short sub‑paths of the probability‑flow ODE, allowing high‑quality generation in as few as four steps, outperforming prior fast‑sampling methods on COCO benchmarks and being deployed in Alibaba Mama’s recommendation system.

AI image generationDiffusion ModelsSPLAM

0 likes · 11 min read

SPLAM: Sub‑Path Linear Approximation for Accelerating Diffusion Model Sampling

Alibaba Cloud Big Data AI Platform

Oct 24, 2023 · Artificial Intelligence

Accelerating Diffusion Model Sampling with OLSS: A Linear Subspace Approach

This article presents the OLSS (Optimal Linear Subspace Search) algorithm, a novel diffusion‑model sampling accelerator that models acceleration as a linear subspace expansion, unifies existing methods, introduces trainable scheduler coefficients solved via least‑squares, and demonstrates significant speed and quality gains on Stable Diffusion benchmarks.

AIDiffusion ModelsImage Generation

0 likes · 8 min read

Accelerating Diffusion Model Sampling with OLSS: A Linear Subspace Approach

Alibaba Cloud Big Data AI Platform

Oct 23, 2023 · Artificial Intelligence

How the New OLSS Algorithm Supercharges Diffusion Model Sampling

The article announces that Alibaba Cloud’s AI platform PAI and ECNU researchers’ paper on the Optimal Linear Subspace Search (OLSS) algorithm was selected for CIKM 2023, explains how OLSS accelerates diffusion‑model sampling by operating in higher‑dimensional linear subspaces, and provides details of the paper and its visual results.

Diffusion ModelsOLSSgenerative AI

0 likes · 5 min read

How the New OLSS Algorithm Supercharges Diffusion Model Sampling