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

arXiv: https://arxiv.org/abs/2506.01430 · HTML: https://mlsanity.com/paper/2506.01430/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 26 of 26)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions](https://mlsanity.com/paper/2104.14806/) (2021)
- [FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models](https://mlsanity.com/paper/2412.08629/) (2024)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models](https://mlsanity.com/paper/2305.16807/) (2023)
- [Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations](https://mlsanity.com/paper/2410.10792/) (2024)
- [Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code](https://mlsanity.com/paper/2310.01506/) (2023)
- [FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing](https://mlsanity.com/paper/2412.07517/) (2024)
- [ZONE: Zero-Shot Instruction-Guided Local Editing](https://mlsanity.com/paper/2312.16794/) (2023)
- [KV-Edit: Training-Free Image Editing for Precise Background Preservation](https://mlsanity.com/paper/2502.17363/) (2025)
- [EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing](https://mlsanity.com/paper/2503.10270/) (2025)
- [Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing](https://mlsanity.com/paper/2411.15843/) (2024)
- [Object-aware Inversion and Reassembly for Image Editing](https://mlsanity.com/paper/2310.12149/) (2023)
- [FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models](https://mlsanity.com/paper/2503.13684/) (2025)
- [Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow](https://mlsanity.com/paper/2503.16522/) (2025)

## Built on by (most cited first, 24 of 24)

- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [Delta Rectified Flow Sampling for Text-to-Image Editing](https://mlsanity.com/paper/2509.05342/) (2025)
- [SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing](https://mlsanity.com/paper/2601.19180/) (2026)
- [ConceptWeaver: Weaving Disentangled Concepts with Flow](https://mlsanity.com/paper/2603.28493/) (2026)
- [On Exact Editing of Flow-Based Diffusion Models](https://mlsanity.com/paper/2512.24015/) (2025)
- [BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation](https://mlsanity.com/paper/2603.24942/) (2026)
- [DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing](https://mlsanity.com/paper/2605.02417/) (2026)
- [FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing](https://mlsanity.com/paper/2606.15186/) (2026)
- [Semantic Editing with Coupled Stochastic Differential Equations](https://mlsanity.com/paper/2509.24223/) (2025)
- [Reversible Inversion for Training-Free Exemplar-guided Image Editing](https://mlsanity.com/paper/2512.01382/) (2025)
- [APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping](https://mlsanity.com/paper/2601.15288/) (2026)
- [FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editing](https://mlsanity.com/paper/2602.08725/) (2026)
- [UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs](https://mlsanity.com/paper/2604.15871/) (2026)
- [LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency](https://mlsanity.com/paper/2605.10319/) (2026)
- [Text-Vision Co-Instructed Image Editing](https://mlsanity.com/paper/2606.16767/) (2026)
- [Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing](https://mlsanity.com/paper/2607.02421/) (2026)
- [h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform](https://mlsanity.com/paper/2607.10800/) (2026)
- [Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation](https://mlsanity.com/paper/2607.21628/) (2026)
- [Object-Aware Background-Controlled Editing via Weighted Velocity Guidance](https://mlsanity.com/paper/2609.06288/) (2026)
- [OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization](https://mlsanity.com/paper/2609.29788/) (2026)
- [Constrained Edit Fields for Training-Free Flow Editing](https://mlsanity.com/paper/2609.33735/) (2026)
- [DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling](https://mlsanity.com/paper/2609.34237/) (2026)
- [TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation](https://mlsanity.com/paper/2609.39157/) (2026)
- [OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation](https://mlsanity.com/paper/2610.15414/) (2026)

## Abstract (arXiv)

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. Codes and benchmark will be available at href https://xiechenxi99.github.io/DNAEdit/https://xiechenxi99.github.io/DNAEdit/.