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

Chenxi Xie1,2*, Minghan Li3,*, Shuai Li2, Yuhui Wu1,2, Qiaosi Yi1,2, Lei Zhang1,2,♢
1 Hong Kong Polytecnic University, 2 OPPO Research Institute, 3 Harvard University
*Indicates Equal Contribution, Indicates Corresponding Author
MY ALT TEXT

Illustration of (a) DNA and (b) MVG, which collectively build our DNAEdit algorithm.

Abstract

Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional diffusion-based methods, as well as recent rectified flow (RF)-based methods, typically reverse synthesis trajectories by gradually adding noise to clean images, during which the noisy latent at the current timestep is used to approximate that at the next timesteps, introducing accumulated drift and degrading reconstruction accuracy. Considering the fact that in RF the noisy latent is estimated through direct interpolation between Gaussian noises and clean images at each timestep, we propose Direct Noise Alignment (DNA), which directly refines the desired Gaussian noise in the noise domain, significantly reducing the error accumulation in previous methods. Specifically, DNA estimates the velocity field of the interpolated noised latent at each timestep and adjusts the Gaussian noise by computing the difference between the predicted and expected velocity field. We validate the effectiveness of DNA and reveal its relationship with existing RF-based inversion methods. Additionally, we introduce a Mobile Velocity Guidance (MVG) to control the target prompt-guided generation process, balancing image background preservation and target object editability. DNA and MVG collectively constitute our proposed method, namely DNAEdit. Finally, we introduce DNA-Bench, a long-prompt benchmark, to evaluate the performance of advanced image editing models. Experimental results demonstrate that our DNAEdit achieves superior performance to state-of-the-art text-guided editing methods.

Results of Real Image Editing

Visual comparison on PIE-Bench

Results of Video Editing

BibTeX

@article{xie2025dnaedit,
        title={DNAEdit: Direct Noise Alignment for Text- Guided Rectified Flow Editing},
        author={Xie, Chenxi and Li, Minghan and Li, Shuai and Wu, Yuhui and Yi, Qiaosi and Zhang, Lei},
        year={2025}
      }