Lune

NeurIPS2025Top-tier venue

Image Editing As Programs with Diffusion Models

Yujia Hu, Songhua Liu, Zhenxiong Tan, Xingyi Yang, Xinchao Wang

Abstract

While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle with structurally inconsistent edits that involve substantial layout changes. To mitigate this gap, we introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture. At its core, IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations. Each operation is implemented via a lightweight adapter sharing the same DiT backbone and is specialized for a specific type of edit. Programmed by a vision-language model (VLM)-based agent, these operations collaboratively support arbitrary and structurally inconsistent transformations. By modularizing and sequencing edits in this way, IEAP generalizes robustly across a wide range of editing tasks, from simple adjustments to substantial structural changes. Extensive experiments demonstrate that IEAP significantly outperforms state-of-the-art methods on standard benchmarks across various editing scenarios. In these evaluations, our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions. Codes are available at https://github.com/YujiaHu1109/IEAP.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Meta-CoT: Enhancing Granularity and Generalization in Image Editing cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing cites Emerging Properties in Self-Supervised Vision Transformers
  • InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space cites High-Resolution Image Synthesis with Latent Diffusion Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Meta-CoT: Enhancing Granularity and Generalization in Image EditingShiyi Zhang, Yiji Cheng, Tiankai Hang, Zijin Yin et al.CVPR 2026 · 3 citations
  2. I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image EditingJinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li et al.ACL 2026 · 3 citations
  3. Semantic Granularity Navigation in Image EditingLiangsi Lu, Minzhe Guo, Xuhang Chen, Yang ShiICML 2026 · 1 citation
  4. InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral SpaceJiarui Wu, Yujin Wang, Ruikang Li, Fan Zhang et al.CVPR 2026

Builds on43

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  3. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  4. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  5. Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations

Related papers

  1. RelationAdapter: Learning and Transferring Visual Relation with Diffusion TransformersYan Gong, Yiren Song, Yicheng Li, Chenglin Li et al.NeurIPS 2025 · 30 citations
  2. DiT4Edit: Diffusion Transformer for Image EditingKunyu Feng, Yue Ma, Bingyuan Wang, Chenyang Qi et al.AAAI 2025 · 92 citations
  3. RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic DataDelong Liu, Haotian Hou, Zhaohui Hou, Shihao Han et al.AAAI 2026
  4. MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and EditingXueyun Tian, Wei Li, Bingbing Xu, Yige Yuan et al.ACM MM 2025 · 4 citations
  5. T-Edit: Triple-Branch Diffusion Anchoring for Consistent EditingLinsong Shan, Laurence Yang, Zecan Yang, Shijie Lian et al.ICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines