Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| 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 |