Saved in:
Bibliographic Details
Main Authors: Mo, Sicheng, Nguyen, Thao, Zhang, Richard, Kolkin, Nick, Iyer, Siddharth Srinivasan, Shechtman, Eli, Singh, Krishna Kumar, Lee, Yong Jae, Zhou, Bolei, Li, Yuheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908705992212480
author Mo, Sicheng
Nguyen, Thao
Zhang, Richard
Kolkin, Nick
Iyer, Siddharth Srinivasan
Shechtman, Eli
Singh, Krishna Kumar
Lee, Yong Jae
Zhou, Bolei
Li, Yuheng
author_facet Mo, Sicheng
Nguyen, Thao
Zhang, Richard
Kolkin, Nick
Iyer, Siddharth Srinivasan
Shechtman, Eli
Singh, Krishna Kumar
Lee, Yong Jae
Zhou, Bolei
Li, Yuheng
contents In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask if samples can be generated collaboratively. We propose Group Diffusion, unlocking the attention mechanism to be shared across images, rather than limited to just the patches within an image. This enables images to be jointly denoised at inference time, learning both intra and inter-image correspondence. We observe a clear scaling effect - larger group sizes yield stronger cross-sample attention and better generation quality. Furthermore, we introduce a qualitative measure to capture this behavior and show that its strength closely correlates with FID. Built on standard diffusion transformers, our GroupDiff achieves up to 32.2% FID improvement on ImageNet-256x256. Our work reveals cross-sample inference as an effective, previously unexplored mechanism for generative modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10954
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
Mo, Sicheng
Nguyen, Thao
Zhang, Richard
Kolkin, Nick
Iyer, Siddharth Srinivasan
Shechtman, Eli
Singh, Krishna Kumar
Lee, Yong Jae
Zhou, Bolei
Li, Yuheng
Computer Vision and Pattern Recognition
In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask if samples can be generated collaboratively. We propose Group Diffusion, unlocking the attention mechanism to be shared across images, rather than limited to just the patches within an image. This enables images to be jointly denoised at inference time, learning both intra and inter-image correspondence. We observe a clear scaling effect - larger group sizes yield stronger cross-sample attention and better generation quality. Furthermore, we introduce a qualitative measure to capture this behavior and show that its strength closely correlates with FID. Built on standard diffusion transformers, our GroupDiff achieves up to 32.2% FID improvement on ImageNet-256x256. Our work reveals cross-sample inference as an effective, previously unexplored mechanism for generative modeling.
title Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.10954