# One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting

arXiv: https://arxiv.org/abs/2510.08273 · HTML: https://mlsanity.com/paper/2510.08273/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 7 of its 49 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 7 of 7)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions](https://mlsanity.com/paper/2104.14806/) (2021)
- [Image Restoration with Mean-Reverting Stochastic Differential Equations](https://mlsanity.com/paper/2301.11699/) (2023)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models](https://mlsanity.com/paper/2312.14091/) (2023)
- [BrushEdit: All-In-One Image Inpainting and Editing](https://mlsanity.com/paper/2412.10316/) (2024)

## Built on by (most cited first, 5 of 5)

- [InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting](https://mlsanity.com/paper/2603.23463/) (2026)
- [Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation](https://mlsanity.com/paper/2605.00548/) (2026)
- [DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes](https://mlsanity.com/paper/2607.16656/) (2026)
- [AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis](https://mlsanity.com/paper/2605.25763/) (2026)
- [STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model](https://mlsanity.com/paper/2606.10653/) (2026)

## Abstract (arXiv)

Text-guided image inpainting aims at reconstructing the masked regions as per text prompts, where the longstanding challenges lie in the preservation for unmasked regions, while achieving the semantics consistency between unmasked and inpainted masked regions. Previous arts failed to address both of them, always with either of them to be remedied. Such facts, as we observed, stem from the entanglement of the hybrid (e.g., mid-and-low) frequency bands that encode varied image properties, which exhibit different robustness to text prompts during the denoising process. In this paper, we propose a null-text-null frequency-aware diffusion models, dubbed NTN-Diff, for text-guided image inpainting, by decomposing the semantics consistency across masked and unmasked regions into the consistencies as per each frequency band, while preserving the unmasked regions, to circumvent two challenges in a row. Based on the diffusion process, we further divide the denoising process into early (high-level noise) and late (low-level noise) stages, where the mid-and-low frequency bands are disentangled during the denoising process. As observed, the stable mid-frequency band is progressively denoised to be semantically aligned during text-guided denoising process, which, meanwhile, serves as the guidance to the null-text denoising process to denoise low-frequency band for the masked regions, followed by a subsequent text-guided denoising process at late stage, to achieve the semantics consistency for mid-and-low frequency bands across masked and unmasked regions, while preserve the unmasked regions. Extensive experiments validate the superiority of NTN-Diff over the state-of-the-art diffusion models to text-guided diffusion models. Our code can be accessed from https://github.com/htyjers/NTN-Diff.