Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
Pengcheng Xu, Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Charles Ling, Boyu Wang
2025年份
15顶会引用
摘要
Mountain → City Remove moon Gold chain and star Cartoon Figure 1. Our framework reconciles the invariance control for rigid and non-rigid editing, enabling versatile editing via flow transformer.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper15
- DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow EditingChenxi Xie, Minghan Li, Shuai Li, Yuhui Wu 等NeurIPS 2025 · 被引用 27 次
- SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image EditingSung-Hoon Yoon, Minghan Li, Gaspard Beaudouin, Congcong Wen 等NeurIPS 2025 · 被引用 18 次
- FreeViS: Training-free Video Stylization with Inconsistent ReferencesJiacong Xu, Yiqun Mei, Ke Zhang, Vishal M. PatelICLR 2026 · 被引用 7 次
- Free Lunch for Stabilizing Rectified Flow InversionChenru Wang, Beier Zhu, Chi ZhangICLR 2026 · 被引用 6 次
- Training-Free Text-Guided Color Editing with Multi-Modal Diffusion TransformerZixin Yin, Xili Dai, Ling-Hao Chen, Deyu Zhou 等ICLR 2026 · 被引用 6 次
它引用的顶会 Paper38
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 被引用 11,743 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
相关 Paper
- Stable Flow: Vital Layers for Training-Free Image EditingOmri Avrahami, Or Patashnik, Ohad Fried, Egor Nemchinov 等CVPR 2025
- QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video EditingTiancheng Shen, Zilong Huang, Xiangtai Li, Zhijie Lin 等ICCV 2025 · 被引用 2 次
- Cora: Correspondence-aware image editing using few step diffusionAmirhossein Alimohammadi, Aryan Mikaeili, Sauradip Nag, Negar Hassanpour 等SIGGRAPH 2025
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video SynthesisFeng Liang, Bichen Wu, Jialiang Wang, Licheng Yu 等CVPR 2024
- RIGID: Recurrent GAN Inversion and Editing of Real Face VideosYangyang Xu, Shengfeng He, Kwan-Yee K. Wong, Ping LuoICCV 2023 · 被引用 14 次
