COMPUTER VISION

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

June 05, 2024

Abstract

Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-to-image network has to be applied many times to iteratively refine an image from random noise. While many recent works propose techniques to reduce the number of required steps, they generally treat the underlying denoising network as a black box. In this work, we investigate the behavior of the layers within the network and find that 1) the layers' output changes smoothly over time, 2) the layers show distinct patterns of change, and 3) the change from step to step is often very small. We hypothesize that many layer computations in the denoising network are redundant. Leveraging this, we introduce block caching, in which we reuse outputs from layer blocks of previous steps to speed up inference. Furthermore, we propose a technique to automatically determine caching schedules based on each block's changes over timesteps. In our experiments, we show through FID, human evaluation and qualitative analysis that Block Caching allows to generate images with higher visual quality at the same computational cost. We demonstrate this for different state-of-the-art models (LDM and EMU) and solvers (DDIM and DPM).

Download the Paper

AUTHORS

Written by

Felix Wimbauer

Bichen Wu

Edgar Schoenfeld

Ji Hou

Zijian He

Artsiom Sanakoyeu

Peizhao Zhang

Sam Tsai

Jonas Kohler

Christian Rupprecht

Daniel Cramers

Peter Vajda

Jialiang Wang

Publisher

CVPR

Research Topics

Computer Vision

Related Publications

July 02, 2024

GRAPHICS

COMPUTER VISION

Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials

Yawar Siddiqui, Tom Monnier, Filippos Kokkinos, Mahendra Kariya, Yanir Kleiman, Emilien Garreau, Oran Gafni, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotny

July 02, 2024

July 02, 2024

GRAPHICS

COMPUTER VISION

Meta 3D Gen

Raphael Bensadoun, Tom Monnier, Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Emilien Garreau, Animesh Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny, Oran Gafni, Natalia Neverova, Andrea Vedaldi

July 02, 2024

July 02, 2024

GRAPHICS

COMPUTER VISION

Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects

Raphael Bensadoun, Yanir Kleiman, Idan Azuri, Omri Harosh, Andrea Vedaldi, Natalia Neverova, Oran Gafni

July 02, 2024

June 20, 2024

COMPUTER VISION

ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization

Weiyao Wang, Pierre Gleize, Hao Tang, Xingyu Chen, Kevin Liang, Matt Feiszli

June 20, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.