paper-with-me

Papers

DiT4Edit: Diffusion Transformer for Image Editing

2024-11-05 · Kunyu Feng, Yue Ma, Bingyuan Wang, Chenyang Qi, Haozhe Chen, Qifeng Chen, Zeyu Wang

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.

📄 PDF Abstract BibTeX arXiv:2411.03286

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SpotEdit: Selective Region Editing in Diffusion Transformers

2025-12-26 · Zhibin Qin, Zhenxiong Tan, Zeqing Wang, Songhua Liu 외 arxiv

Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current …

Image Editing

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

2026-03-16 · Ruonan Yu, Zhenxiong Tan, Zigeng Chen, Songhua Liu 외 arxiv

Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compar…

Video Generation

Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers

2025-11-24 · Yiqing Shi, Yiren Song, Mike Zheng Shou arxiv

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We re…

Image Editing

Masked Generative Transformer Is What You Need for Image Editing

2026-05-11 · Wei Chow, Linfeng Li, Xian Sun, Lingdong Kong 외 arxiv

Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a funda…

Image Editing

Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing

2024-08-23 · Zitao Shuai, Chenwei Wu, Zhengxu Tang, Bowen Song 외

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of genera…

DisentanglementLarge Language Model