Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.24800 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911545096667136 |
|---|---|
| author | Tokhchukov, Danil Mirzoeva, Aysel Kuznetsov, Andrey Sobolev, Konstantin |
| author_facet | Tokhchukov, Danil Mirzoeva, Aysel Kuznetsov, Andrey Sobolev, Konstantin |
| contents | In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24800 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration Tokhchukov, Danil Mirzoeva, Aysel Kuznetsov, Andrey Sobolev, Konstantin Computer Vision and Pattern Recognition In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analysis of the denoising process, we demonstrate that introducing a single learned scaling parameter can significantly improve the performance of DiT blocks. Building on this insight, we propose Calibri, a parameter-efficient approach that optimally calibrates DiT components to elevate generative quality. Calibri frames DiT calibration as a black-box reward optimization problem, which is efficiently solved using an evolutionary algorithm and modifies just ~100 parameters. Experimental results reveal that despite its lightweight design, Calibri consistently improves performance across various text-to-image models. Notably, Calibri also reduces the inference steps required for image generation, all while maintaining high-quality outputs. |
| title | Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.24800 |