mlsanityData to 14 Oct 2026

ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

arXiv 2506.18095 ↗First posted 22 Jun 2025cs.CV cs.AI cs.LGcited by 97

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent advances in multimodal generative models have unlocked photorealistic, instruction-aligned image generation, yet leading systems like GPT-4o-Image remain proprietary and inaccessible. To democratize these capabilities, we present ShareGPT-4o-Image, the first dataset comprising 45K text-to-image and 46K text-and-image-to-image data, all synthesized using GPT-4o's image generation capabilities for distilling its advanced image generation abilities. Leveraging this dataset, we develop Janus-4o, a multimodal large language model capable of both text-to-image and text-and-image-to-image generation. Janus-4o not only significantly improves text-to-image generation over its predecessor, Janus-Pro, but also newly supports text-and-image-to-image generation. Notably, it achieves impressive performance in text-and-image-to-image generation from scratch, using only 91K synthetic samples and 6 hours of training on an 8 A800-GPU machine. We hope the release of ShareGPT-4o-Image and Janus-4o will foster open research in photorealistic, instruction-aligned image generation.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 22 Jun 2025.

Builds on

53 of 66 references.

References · 53

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2025Qwen2.5-VL Technical Reportcited by 5,587
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
38 more
  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  6. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  7. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  8. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  9. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  10. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  11. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  12. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  13. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  14. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  15. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  16. 2020Scaling Laws for Autoregressive Generative Modelingcited by 522
  17. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  18. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  19. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  20. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  21. 2020TextCaps: a Dataset for Image Captioning with Reading Comprehensioncited by 400
  22. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 376
  23. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331
  24. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  25. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  26. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  27. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 241
  28. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 231
  29. 2023TextDiffuser: Diffusion Models as Text Painterscited by 229
  30. 2024AnyGPT: Unified Multimodal LLM with Discrete Sequence Modelingcited by 217
  31. 2024ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Modelscited by 205
  32. 2024HQ-Edit: A High-Quality Dataset for Instruction-based Image Editingcited by 193
  33. 2023AnyText: Multilingual Visual Text Generation And Editingcited by 170
  34. 2025HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformercited by 141
  35. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 132
  36. 2024SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editingcited by 97
  37. 2025GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generationcited by 58
  38. 2024Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editingcited by 49

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 39; 2026: 58.

97 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. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 88
  4. 2025UniVideo: Unified Understanding, Generation, and Editing for Videoscited by 87
  5. 2025GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Datasetcited by 70
  6. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 62
  7. 2025Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Visioncited by 56
  8. 2025EditVerse: Unifying Image and Video Editing and Generation with In-Context Learningcited by 54
  9. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 53
  10. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  11. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 50
  12. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 49
38 more
  1. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 44
  2. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 41
  3. 2025Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmarkcited by 29
  4. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  5. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 23
  6. 2025NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matchingcited by 21
  7. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  8. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  9. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  10. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generationcited by 15
  11. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  12. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 14
  13. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  14. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 13
  15. 2026UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editingcited by 12
  16. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 12
  17. 2025WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editingcited by 11
  18. 2025TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuningcited by 10
  19. 2026LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Modelcited by 10
  20. 2025OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilitiescited by 9
  21. 2026Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generationcited by 9
  22. 2026Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteriacited by 9
  23. 2025MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generationcited by 8
  24. 2025UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learningcited by 8
  25. 2026Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editingcited by 8
  26. 2026Elastic Diffusion Transformercited by 8
  27. 2026Reinforcing Few-step Generators via Reward-Tilted Distribution Matchingcited by 8
  28. 2025PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modelingcited by 7
  29. 2026LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Modelscited by 7
  30. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 7
  31. 2025Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Modelscited by 6
  32. 2026LoomVideo: Unifying Multimodal Inputs into Video Generation and Editingcited by 6
  33. 2026An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Modelscited by 6
  34. 2026ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Frameworkcited by 5
  35. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  36. 2025VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flipcited by 4
  37. 2025Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editingcited by 4
  38. 2025Growing Visual Generative Capacity for Pre-Trained MLLMscited by 4

50 most cited of 97 All 97 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generation
  2. 2025Preliminary Explorations with GPT-4o(mni) Native Image Generation
  3. 2023Controllable Text-to-Image Generation with GPT-4
  4. 2026Unified Text-Image Generation with Weakness-Targeted Post-Training
  5. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
  6. 2025Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
  7. 2023MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens
  8. 2025Why Settle for One? Text-to-ImageSet Generation and Evaluation