Papers
arxiv:2406.04333

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Published on Jun 6
ยท Submitted by akhaliq on Jun 7
#2 Paper of the day
Authors:
,
,
,
,
,

Abstract

Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly large model size. Saving and transferring them is a major bottleneck for various applications, especially those running on resource-constrained devices. In this work, we develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1.5 to 1.99 bits, achieving a model with 7.9X smaller size while exhibiting even better generation quality than the original one. Our approach includes several novel techniques, such as assigning optimal bits to each layer, initializing the quantized model for better performance, and improving the training strategy to dramatically reduce quantization error. Furthermore, we extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.

Community

Plain-english rewrite of the paper is here - feedback welcome! https://www.aimodels.fyi/papers/arxiv/bitsfusion-199-bits-weight-quantization-diffusion-model

ยท

The page looks a bit bugged, as there's a comedic amount of [object Object].

๐Ÿš€ Transforming Diffusion Models with BitsFusion!

Links ๐Ÿ”—:

๐Ÿ‘‰ Subscribe: https://www.youtube.com/@Arxflix
๐Ÿ‘‰ Twitter: https://x.com/arxflix
๐Ÿ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2406.04333 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2406.04333 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2406.04333 in a Space README.md to link it from this page.

Collections including this paper 14