mlsanityData to 14 Oct 2026

HunyuanImage 3.0 Technical Report

arXiv 2509.23951 ↗First posted 28 Sep 2025cs.CVcited by 149

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training, aggressive model post-training, and an efficient infrastructure that enables large-scale training and inference. With these advancements, we successfully trained a Mixture-of-Experts (MoE) model comprising over 80 billion parameters in total, with 13 billion parameters activated per token during inference, making it the largest and most powerful open-source image generative model to date. We conducted extensive experiments and the results of automatic and human evaluation of text-image alignment and visual quality demonstrate that HunyuanImage 3.0 rivals previous state-of-the-art models. By releasing the code and weights of HunyuanImage 3.0, we aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant multimodal ecosystem. All open source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanImage-3.0

Key facts. Cited by 149 papers in the map (data through 14 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 34 of its 39 references that are in the map. First posted on arXiv 28 Sep 2025.

Builds on

34 of 39 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2023Visual Instruction Tuningcited by 7,869
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2022Flow Matching for Generative Modelingcited by 5,702
  11. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  12. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
22 more
  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  5. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  6. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  7. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  8. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  9. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  10. 2025Mean Flows for One-step Generative Modelingcited by 561
  11. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  12. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 298
  13. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 249
  14. 2025MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEcited by 178
  15. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 163
  16. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  17. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 109
  18. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 60
  19. 2022Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Modelscited by 54
  20. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  21. 2025Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preferencecited by 30
  22. 2023ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectoriescited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 26; 2026: 123.

149 papers.

Sort:

By area:

  1. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  2. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  3. 2025HunyuanVideo 1.5 Technical Reportcited by 160
  4. 2025LongCat-Image Technical Reportcited by 100
  5. 2025Hunyuan-GameCraft-2: Instruction-following Interactive Game World Modelcited by 61
  6. 2026Scaling Text-to-Image Diffusion Transformers with Representation Autoencoderscited by 53
  7. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 37
  8. 2025HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generationcited by 36
  9. 2026Qwen-Image-2.0 Technical Reportcited by 36
  10. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  11. 2026Gen-Searcher: Reinforcing Agentic Search for Image Generationcited by 30
  12. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
38 more
  1. 2025Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervalscited by 24
  2. 2026D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Modelscited by 22
  3. 2026GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillationcited by 19
  4. 2026Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesiscited by 17
  5. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 16
  6. 2026Wan-Image: Pushing the Boundaries of Generative Visual Intelligencecited by 16
  7. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  8. 2025Flow Map Distillation Without Datacited by 14
  9. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  10. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Modelcited by 13
  11. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 12
  12. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 12
  13. 2025HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generationcited by 11
  14. 2025WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editingcited by 11
  15. 2026BizGenEval: A Systematic Benchmark for Commercial Visual Content Generationcited by 11
  16. 2026SpatialEdit: Benchmarking Fine-Grained Image Spatial Editingcited by 10
  17. 2025MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generationcited by 9
  18. 2026Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editingcited by 8
  19. 2026From Scale to Speed: Adaptive Test-Time Scaling for Image Editingcited by 8
  20. 2025Semantic Context Matters: Improving Conditioning for Autoregressive Modelscited by 7
  21. 2025MotionEdit: Benchmarking and Learning Motion-Centric Image Editingcited by 7
  22. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 7
  23. 2026SenseNova-U1.5: Towards Native Unified Visual Intelligencecited by 7
  24. 2026TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Expertscited by 6
  25. 2026AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compressioncited by 6
  26. 2026Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuningcited by 6
  27. 2026Lens: Rethinking Training Efficiency for Foundational Text-to-Image Modelscited by 6
  28. 2026ERNIE-Image Technical Reportcited by 6
  29. 2026Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budgetcited by 6
  30. 2026An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Modelscited by 6
  31. 2025From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detectioncited by 5
  32. 2025ConsistCompose: Unified Multimodal Layout Control for Image Compositioncited by 5
  33. 2025FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoningcited by 5
  34. 2026Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuningcited by 5
  35. 2026Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Trainingcited by 5
  36. 2026Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Itemscited by 5
  37. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  38. 2026Qwen-Image-2.0-RL Technical Reportcited by 5

50 most cited of 149 All 149 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
  2. 2024Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
  3. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
  4. 2024MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective
  5. 2025OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks
  6. 2024ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
  7. 2025Growing Visual Generative Capacity for Pre-Trained MLLMs
  8. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding