English

DiT4Edit: Diffusion Transformer for Image Editing

Computer Vision and Pattern Recognition 2024-11-08 v2

Abstract

Despite recent advances in UNet-based image editing, methods for shape-aware object editing in high-resolution images are still lacking. Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture the long-range dependencies among patches, leading to higher-quality image generation. In this paper, we propose DiT4Edit, the first Diffusion Transformer-based image editing framework. Specifically, DiT4Edit uses the DPM-Solver inversion algorithm to obtain the inverted latents, reducing the number of steps compared to the DDIM inversion algorithm commonly used in UNet-based frameworks. Additionally, we design unified attention control and patches merging, tailored for transformer computation streams. This integration allows our framework to generate higher-quality edited images faster. Our design leverages the advantages of DiT, enabling it to surpass UNet structures in image editing, especially in high-resolution and arbitrary-size images. Extensive experiments demonstrate the strong performance of DiT4Edit across various editing scenarios, highlighting the potential of Diffusion Transformers in supporting image editing.

Keywords

Cite

@article{arxiv.2411.03286,
  title  = {DiT4Edit: Diffusion Transformer for Image Editing},
  author = {Kunyu Feng and Yue Ma and Bingyuan Wang and Chenyang Qi and Haozhe Chen and Qifeng Chen and Zeyu Wang},
  journal= {arXiv preprint arXiv:2411.03286},
  year   = {2024}
}
R2 v1 2026-06-28T19:49:13.868Z