EUVIMEDEUVIMED entdecken
Crossref

DiT4Edit: Diffusion Transformer for Image Editing

Kunyu Feng, Yue Ma, Bingyuan Wang, Chenyang Qi, Haozhe Chen, Qifeng Chen, Zeyu Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 2969-2977

DOI: 10.1609/aaai.v39i3.32304 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Kunyu Feng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 patch 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 in various editing scenarios, highlighting the potential of diffusion transformers for image editing.

Zitieren

APA

Feng, K., Ma, Y., Wang, B., Qi, C., Chen, H., Chen, Q., & Wang, Z. (2025). DiT4Edit: Diffusion Transformer for Image Editing. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 2969-2977. https://doi.org/10.1609/aaai.v39i3.32304

Vancouver

Feng K, Ma Y, Wang B, Qi C, Chen H, Chen Q, et al. DiT4Edit: Diffusion Transformer for Image Editing. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):2969-2977. doi:10.1609/aaai.v39i3.32304

BibTeX
@article{Feng2025,
  author = {Feng, Kunyu and Ma, Yue and Wang, Bingyuan and Qi, Chenyang and Chen, Haozhe and Chen, Qifeng and Wang, Zeyu},
  title = {DiT4Edit: Diffusion Transformer for Image Editing},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {2969--2977},
  doi = {10.1609/aaai.v39i3.32304}
}
Kostenlos starten →