Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

Danil Tokhchukov; Aysel Mirzoeva; Andrey Kuznetsov; Konstantin Sobolev

返回文献探索

Paper · arXiv 2603.24800

Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

Danil Tokhchukov, Aysel Mirzoeva, Andrey Kuznetsov, Konstantin Sobolev

71 upvotesMarch 25, 2026arXiv 预印本

AI 摘要

Diffusion Transformers can be enhanced through a parameter-efficient calibration approach that improves generative quality while reducing inference steps.

Diffusion Transformersdenoising processlearned scaling parameterparameter-efficient approachDiT blocksgenerative qualityblack-box reward optimizationevolutionary algorithm

Abstract

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.