mlsanityData to 14 Oct 2026

OmniGen2: Towards Instruction-Aligned Multimodal Generation

arXiv 2506.18871 ↗First posted 23 Jun 2025cs.CV cs.AI cs.CLcited by 253

Not on the map. Why?

Cited by 44 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2

Key facts. Cited by 253 papers in the map (data through 14 Oct 2026). Builds on 83 of its 103 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

83 of 103 references.

References · 83

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  9. 2022Flow Matching for Generative Modelingcited by 5,702
  10. 2025Qwen2.5-VL Technical Reportcited by 5,587
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  12. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
38 more
  1. 2024GPT-4o System Cardcited by 4,588
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  6. 2023Let's Verify Step by Stepcited by 3,789
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  11. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  13. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  14. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  15. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  16. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  17. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  18. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  19. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  20. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  21. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  22. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  23. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  24. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  25. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  26. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  27. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  28. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  29. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  30. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  31. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 450
  32. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  33. 2025Step1X-Edit: A Practical Framework for General Image Editingcited by 429
  34. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 413
  35. 2024OmniGen: Unified Image Generationcited by 394
  36. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 376
  37. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  38. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 324

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 123; 2026: 130.

253 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  3. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 132
  4. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 112
  5. 2025Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generationcited by 100
  6. 2025LongCat-Image Technical Reportcited by 100
  7. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 88
  8. 2025Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedbackcited by 79
  9. 2025GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Datasetcited by 70
  10. 2025Ovis-U1 Technical Reportcited by 67
  11. 2025EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modelingcited by 64
  12. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 62
38 more
  1. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 60
  2. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57
  3. 2025BLIP3o-NEXT: Next Frontier of Native Image Generationcited by 54
  4. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  5. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 44
  6. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  7. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 41
  8. 2025Interleaving Reasoning for Better Text-to-Image Generationcited by 41
  9. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 38
  10. 2025DreamOmni2: Multimodal Instruction-based Editing and Generationcited by 38
  11. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 36
  12. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 34
  13. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 34
  14. 2025InstructX: Towards Unified Visual Editing with MLLM Guidancecited by 32
  15. 2025ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulationcited by 29
  16. 2025Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizercited by 28
  17. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  18. 2025USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learningcited by 27
  19. 2025EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewardscited by 27
  20. 2026VINO: A Unified Visual Generator with Interleaved OmniModal Contextcited by 26
  21. 2025UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generationcited by 25
  22. 2025UniREditBench: A Unified Reasoning-based Image Editing Benchmarkcited by 25
  23. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Modelscited by 25
  24. 2025EditThinker: Unlocking Iterative Reasoning for Any Image Editorcited by 25
  25. 2026Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generationcited by 23
  26. 2025Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Datacited by 21
  27. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  28. 2025UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Rewardcited by 19
  29. 2026Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Toolingcited by 19
  30. 2025Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Modelscited by 18
  31. 2025Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editingcited by 18
  32. 2025ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generationcited by 18
  33. 2025From Pixels to Words -- Towards Native Vision-Language Primitives at Scalecited by 18
  34. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  35. 2025WithAnyone: Towards Controllable and ID Consistent Image Generationcited by 17
  36. 2025MIRA: Multimodal Iterative Reasoning Agent for Image Editingcited by 17
  37. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  38. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 16

50 most cited of 253 All 253 (JSON)