mlsanityData to 7 Oct 2026

ImgEdit: A Unified Image Editing Dataset and Benchmark

arXiv 2505.20275 ↗First posted 26 May 2025cs.CVcited by 225

On the map: Multimodal LLMs / vision-language models → Image editing and quality assessment

Abstract (arXiv)

Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce ImgEdit, a large-scale, high-quality image-editing dataset comprising 1.2 million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks. To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict post-processing. ImgEdit surpasses existing datasets in both task novelty and data quality. Using ImgEdit, we train ImgEdit-E1, an editing model using Vision Language Model to process the reference image and editing prompt, which outperforms existing open-source models on multiple tasks, highlighting the value of ImgEdit and model design. For comprehensive evaluation, we introduce ImgEdit-Bench, a benchmark designed to evaluate image editing performance in terms of instruction adherence, editing quality, and detail preservation. It includes a basic testsuite, a challenging single-turn suite, and a dedicated multi-turn suite. We evaluate both open-source and proprietary models, as well as ImgEdit-E1, providing deep analysis and actionable insights into the current behavior of image-editing models. The source data are publicly available on https://github.com/PKU-YuanGroup/ImgEdit.

Key facts. Cited by 225 papers in the map (data through 7 Oct 2026). Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 78 of its 84 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

78 of 84 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models11 Dec

Other references · 77

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2024The Llama 3 Herd of Modelscited by 14,192
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  8. 2023Segment Anythingcited by 8,158
  9. 2023Visual Instruction Tuningcited by 7,792
  10. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  11. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  12. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
38 more
  1. 2025Qwen2.5-VL Technical Reportcited by 5,418
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  7. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  10. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,385
  11. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  12. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  13. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  14. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  15. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  16. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  17. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  18. 2018nocaps: novel object captioning at scalecited by 444
  19. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 417
  20. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
  21. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  22. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
  23. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 297
  24. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  25. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 266
  26. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 235
  27. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 229
  28. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
  29. 2023VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluationcited by 196
  30. 2024HQ-Edit: A High-Quality Dataset for Instruction-based Image Editingcited by 191
  31. 2023HIVE: Harnessing Human Feedback for Instructional Visual Editingcited by 172
  32. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
  33. 2023InstructDiffusion: A Generalist Modeling Interface for Vision Taskscited by 162
  34. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  35. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervisioncited by 145
  36. 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editingcited by 132
  37. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 129
  38. 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Modelscited by 111

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 76; 2026: 149.

225 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 973
  2. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  3. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  4. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  5. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 94
  6. 2025LongCat-Image Technical Reportcited by 92
  7. 2025UniVideo: Unified Understanding, Generation, and Editing for Videoscited by 85
  8. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  9. 2025Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedbackcited by 78
  10. 2025GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Datasetcited by 68
  11. 2025Ovis-U1 Technical Reportcited by 65
  12. 2025UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generationcited by 64
38 more
  1. 2025EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modelingcited by 61
  2. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 55
  3. 2025EditVerse: Unifying Image and Video Editing and Generation with In-Context Learningcited by 53
  4. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  5. 2025BLIP3o-NEXT: Next Frontier of Native Image Generationcited by 50
  6. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 50
  7. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 48
  8. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 43
  9. 2026Image Generators are Generalist Vision Learnerscited by 40
  10. 2025Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Playcited by 37
  11. 2025TUNA: Taming Unified Visual Representations for Native Unified Multimodal Modelscited by 34
  12. 2025NoHumansRequired: Autonomous High-Quality Image Editing Triplet Miningcited by 33
  13. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 33
  14. 2025InstructX: Towards Unified Visual Editing with MLLM Guidancecited by 31
  15. 2026FireRed-Image-Edit-1.0 Technical Reportcited by 31
  16. 2026HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformercited by 29
  17. 2025ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulationcited by 28
  18. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  19. 2026VINO: A Unified Visual Generator with Interleaved OmniModal Contextcited by 26
  20. 2025X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learningcited by 24
  21. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Modelscited by 24
  22. 2025UniREditBench: A Unified Reasoning-based Image Editing Benchmarkcited by 23
  23. 2025EditThinker: Unlocking Iterative Reasoning for Any Image Editorcited by 23
  24. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 23
  25. 2025Visual Autoregressive Modeling for Instruction-Guided Image Editingcited by 21
  26. 2026Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generationcited by 18
  27. 2026Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Toolingcited by 17
  28. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 17
  29. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 16
  30. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  31. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  32. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generationcited by 14
  33. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 14
  34. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  35. 2025Learning an Image Editing Model without Image Editing Pairscited by 13
  36. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 13
  37. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 13
  38. 2025Reinforcement Learning with Inverse Rewards for World Model Post-trainingcited by 12

50 most cited of 225 All 225 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
  2. 2025I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models
  3. 2025ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies
  4. 2025Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
  5. 2026EPEdit: Redefining Image Editing with Generative AI and User-Centric Design
  6. 2024InsightEdit: Towards Better Instruction Following for Image Editing
  7. 2024ParallelEdits: Efficient Multi-object Image Editing
  8. 2025FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model