# Improving Editability in Image Generation with Layer-wise Memory

arXiv: https://arxiv.org/abs/2505.01079 · HTML: https://mlsanity.com/paper/2505.01079/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 56 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 30 of 46)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Blended Latent Diffusion](https://mlsanity.com/paper/2206.02779/) (2022)
- [Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16322/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting](https://mlsanity.com/paper/2212.06909/) (2022)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting](https://mlsanity.com/paper/2005.09704/) (2020)
- [A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions](https://mlsanity.com/paper/2312.08578/) (2023)
- [Image Generation from Layout](https://mlsanity.com/paper/1811.11389/) (2018)
- [SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing](https://mlsanity.com/paper/2405.04007/) (2024)

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

- [Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2603.05769/) (2026)
- [TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models](https://mlsanity.com/paper/2601.08011/) (2026)
- [Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space](https://mlsanity.com/paper/2605.08250/) (2026)
- [ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation](https://mlsanity.com/paper/2505.20935/) (2025)
- [Making Implicit Preservation Intent Explicit in Conversational Image Editing](https://mlsanity.com/paper/2607.07051/) (2026)

## Abstract (arXiv)

Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining previous edits along with adapting new objects naturally into the existing content. These limitations significantly hinder complex editing scenarios where multiple objects need to be modified while preserving their contextual relationships. We address this fundamental challenge through two key proposals: enabling rough mask inputs that preserve existing content while naturally integrating new elements and supporting consistent editing across multiple modifications. Our framework achieves this through layer-wise memory, which stores latent representations and prompt embeddings from previous edits. We propose Background Consistency Guidance that leverages memorized latents to maintain scene coherence and Multi-Query Disentanglement in cross-attention that ensures natural adaptation to existing content. To evaluate our method, we present a new benchmark dataset incorporating semantic alignment metrics and interactive editing scenarios. Through comprehensive experiments, we demonstrate superior performance in iterative image editing tasks with minimal user effort, requiring only rough masks while maintaining high-quality results throughout multiple editing steps.