DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing

NeurIPSSpotlight2025

Authors
Chenxi Xie, Minghan Li, Shuai Li, Yuhui Wu, Qiaosi Yi, Lei Zhang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

text-to-image alignment rag

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive