Accelerating diffusion models with distillation for fast high-quality image generation

Paper Title:

Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation

Published on:

8 May 2024

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Jonas Kohler,

Albert Pumarola,

Edgar Schönfeld,

Artsiom Sanakoyeu,

Roshan Sumbaly,

Peter Vajda,

Ali Thabet

Bullets

Key Details

•

Proposes distillation framework tailored for extremely low-step diffusion model inference

•

Introduces Backward Distillation concept to calibrate student on its own backward path

•

Presents Shifted Reconstruction Loss to transfer hierarchical knowledge

•

Applies Noise Correction to address singularities in early sampling

•

Achieves teacher-level performance in just 3 steps

Explore the topics in this paper

diffusion models

image generation

knowledge distillation

sample quality

sampling methods

AI generated summary

Accelerating diffusion models with distillation for fast high-quality image generation

This paper proposes a distillation framework to accelerate diffusion models, enabling high-quality and diverse image generation using only 1-3 sampling steps. Key innovations include Backward Distillation to reduce train-test discrepancy, Shifted Reconstruction Loss to transfer both structure and detail knowledge, and Noise Correction to enhance initial sample quality.