mlsanityData to 14 Oct 2026

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

arXiv 2507.21033 ↗First posted 28 Jul 2025cs.CVcited by 70

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

Abstract (arXiv)

Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these models and their training data creates a significant barrier for open-source research. To bridge this gap, we introduce GPT-IMAGE-EDIT-1.5M, a publicly available, large-scale image-editing corpus containing more than 1.5 million high-quality triplets (instruction, source image, edited image). We systematically construct this dataset by leveraging the versatile capabilities of GPT-4o to unify and refine three popular image-editing datasets: OmniEdit, HQ-Edit, and UltraEdit. Specifically, our methodology involves 1) regenerating output images to enhance visual quality and instruction alignment, and 2) selectively rewriting prompts to improve semantic clarity. To validate the efficacy of our dataset, we fine-tune advanced open-source models on GPT-IMAGE-EDIT-1.5M. The empirical results are exciting, e.g., the fine-tuned FluxKontext achieves highly competitive performance across a comprehensive suite of benchmarks, including 7.24 on GEdit-EN, 3.80 on ImgEdit-Full, and 8.78 on Complex-Edit, showing stronger instruction following and higher perceptual quality while maintaining identity. These scores markedly exceed all previously published open-source methods and substantially narrow the gap to leading proprietary models. We hope the full release of GPT-IMAGE-EDIT-1.5M can help to catalyze further open research in instruction-guided image editing.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 24 of its 27 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

24 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025ImgEdit: A Unified Image Editing Dataset and Benchmark26 May

Other references · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2025Qwen2.5-VL Technical Reportcited by 5,587
  8. 2024GPT-4o System Cardcited by 4,588
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  10. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
11 more
  1. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  2. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  3. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  4. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  5. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 253
  6. 2024HQ-Edit: A High-Quality Dataset for Instruction-based Image Editingcited by 193
  7. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervisioncited by 145
  8. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 97
  9. 2024SeedEdit: Align Image Re-Generation to Image Editingcited by 61
  10. 2025SeedEdit 3.0: Fast and High-Quality Generative Image Editingcited by 53
  11. 2025textttComplex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmarkcited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 32; 2026: 38.

70 papers.

Sort:

By area:

  1. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 132
  2. 2025Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generationcited by 100
  3. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 62
  4. 2025Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editingcited by 61
  5. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57
  6. 2025EditVerse: Unifying Image and Video Editing and Generation with In-Context Learningcited by 54
  7. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 53
  8. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 49
  9. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 41
  10. 2026Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidancecited by 36
  11. 2025InstructX: Towards Unified Visual Editing with MLLM Guidancecited by 32
  12. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
38 more
  1. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  2. 2025VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimizationcited by 16
  3. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generationcited by 15
  4. 2025SliderEdit: Continuous Image Editing with Fine-Grained Instruction Controlcited by 14
  5. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  6. 2025EasyV2V: A High-quality Instruction-based Video Editing Frameworkcited by 13
  7. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 13
  8. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingcited by 12
  9. 2026Quantifying the Gap between Understanding and Generation within Unified Multimodal Modelscited by 12
  10. 2026JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generationcited by 12
  11. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 12
  12. 2025TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuningcited by 10
  13. 2025UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Editscited by 10
  14. 2025SuperFlow: Training Flow Matching Models with RL on the Flycited by 10
  15. 2026SpatialEdit: Benchmarking Fine-Grained Image Spatial Editingcited by 10
  16. 2025LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generationcited by 9
  17. 2025MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generationcited by 9
  18. 2026Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generationcited by 9
  19. 2025UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learningcited by 8
  20. 2025EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecturecited by 8
  21. 2025EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editingcited by 8
  22. 2026SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editingcited by 8
  23. 2026LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Modelscited by 7
  24. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 7
  25. 2025Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Modelscited by 6
  26. 2026LoomVideo: Unifying Multimodal Inputs into Video Generation and Editingcited by 6
  27. 2025ConsistCompose: Unified Multimodal Layout Control for Image Compositioncited by 5
  28. 2026I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editingcited by 5
  29. 2026ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Frameworkcited by 5
  30. 2026RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Detailscited by 5
  31. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  32. 2025Growing Visual Generative Capacity for Pre-Trained MLLMscited by 4
  33. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  34. 2025Exploring MLLM-Diffusion Information Transfer with MetaCanvascited by 4
  35. 2026MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Datacited by 4
  36. 2026DuoGen: Towards General Purpose Interleaved Multimodal Generationcited by 3
  37. 2026MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonalitycited by 3
  38. 2025MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Taskscited by 2

50 most cited of 70 All 70 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
  2. 2024SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing
  3. 2024InsightEdit: Towards Better Instruction Following for Image Editing
  4. 2025ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation
  5. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
  6. 2024Multi-Reward as Condition for Instruction-based Image Editing
  7. 2023EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
  8. 2025X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning