# Masked Generative Transformer Is What You Need for Image Editing

arXiv: https://arxiv.org/abs/2605.10859 · HTML: https://mlsanity.com/paper/2605.10859/

## Key facts

- Cited by 3 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 20 of its 23 references that are in the map.
- First posted on arXiv 11 May 2026.

## 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, 20 of 20)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024)
- [GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing](https://mlsanity.com/paper/2503.10639/) (2025)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [EditAR: Unified Conditional Generation with Autoregressive Models](https://mlsanity.com/paper/2501.04699/) (2025)
- [PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions](https://mlsanity.com/paper/2409.15278/) (2024)
- [Visual Autoregressive Modeling for Instruction-Guided Image Editing](https://mlsanity.com/paper/2508.15772/) (2025)
- [EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing](https://mlsanity.com/paper/2512.11715/) (2025)
- [NEP: Autoregressive Image Editing via Next Editing Token Prediction](https://mlsanity.com/paper/2508.06044/) (2025)

## Built on by (most cited first, 3 of 3)

- [DanceOPD: On-Policy Generative Field Distillation](https://mlsanity.com/paper/2606.27377/) (2026)
- [Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI](https://mlsanity.com/paper/2608.28787/) (2026)
- [MARS: Multi-Agent Re-ranking for Repeat-Order Food Delivery Recommendation](https://mlsanity.com/paper/2607.25420/) (2026)

## Abstract (arXiv)

Diffusion models dominate image editing, yet their global denoising mechanism entangles edited regions with surrounding context, causing modifications to propagate into areas that should remain intact. We propose a fundamentally different approach by leveraging Masked Generative Transformers (MGTs), whose localized token-prediction paradigm naturally confines changes to intended regions. We present EditMGT, an MGT-based editing framework that is the first of its kind. Our approach employs multi-layer attention consolidation to aggregate cross-attention maps into precise edit localization signals, and region-hold sampling to explicitly prevent token flipping in non-target areas. To support training, we construct CrispEdit-2M, a 2M-sample high-resolution (>1024) editing dataset spanning seven categories. With only 960M parameters, EditMGT achieves state-of-the-art image similarity on multiple benchmarks while delivering 6x faster editing, demonstrating that MGTs offer a compelling alternative to diffusion-based editing.