mlsanityData to 14 Oct 2026

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

arXiv 2405.08748 ↗First posted 14 May 2024cs.CVcited by 298

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT

Key facts. Cited by 298 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 35 of its 41 references that are in the map. First posted on arXiv 14 May 2024.

Builds on

35 of 41 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation27 Feb
  2. 2024Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs22 Jan
  3. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs14 Nov
  4. 2023PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud11 Sep
  5. 2023AltDiffusion: A Multilingual Text-to-Image Diffusion Model19 Aug
  6. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  7. 2022Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation18 Oct
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May

Other references · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
15 more
  1. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  2. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  3. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  5. 2023Adversarial Diffusion Distillationcited by 759
  6. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  7. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  8. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  9. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  10. 2020Query-Key Normalization for Transformerscited by 280
  11. 2023Making LLaMA SEE and Draw with SEED Tokenizercited by 185
  12. 2023CapsFusion: Rethinking Image-Text Data at Scalecited by 90
  13. 2023Matryoshka Diffusion Modelscited by 72
  14. 2024DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generationcited by 26
  15. 2024Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Supportcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 47; 2025: 170; 2026: 81.

298 papers.

Sort:

By area:

  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  2. 2025Qwen-Image Technical Reportcited by 1,044
  3. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  4. 2025VACE: All-in-One Video Creation and Editingcited by 479
  5. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  6. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  7. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  8. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  9. 2025Show-o2: Improved Native Unified Multimodal Modelscited by 250
  10. 2025HPSv3: Towards Wide-Spectrum Human Preference Scorecited by 211
  11. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  12. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
38 more
  1. 2025SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformercited by 165
  2. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
  3. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 163
  4. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 150
  5. 2025HunyuanImage 3.0 Technical Reportcited by 149
  6. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 136
  7. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 116
  8. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 109
  9. 2024CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Modelscited by 102
  10. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 101
  11. 2025Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generationcited by 100
  12. 2025LongCat-Image Technical Reportcited by 100
  13. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 97
  14. 2025Lumina-Image 2.0: A Unified and Efficient Image Generative Frameworkcited by 96
  15. 2025ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Fillingcited by 95
  16. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
  17. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 92
  18. 2025Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learningcited by 92
  19. 2025WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generationcited by 90
  20. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 87
  21. 2025PixelDiT: Pixel Diffusion Transformers for Image Generationcited by 83
  22. 2024GenAI Arena: An Open Evaluation Platform for Generative Modelscited by 82
  23. 2025Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedbackcited by 79
  24. 2025Harmonizing Visual Representations for Unified Multimodal Understanding and Generationcited by 74
  25. 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesiscited by 72
  26. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 69
  27. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  28. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 62
  29. 2025Hunyuan-GameCraft-2: Instruction-following Interactive Game World Modelcited by 61
  30. 2024CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generationcited by 60
  31. 2024ACE: All-round Creator and Editor Following Instructions via Diffusion Transformercited by 56
  32. 2024xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismcited by 56
  33. 2025From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuningcited by 56
  34. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  35. 2025T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generationcited by 48
  36. 2025Rope to Nope and Back Again: A New Hybrid Attention Strategycited by 47
  37. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocitiescited by 46
  38. 2025OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generationcited by 46

50 most cited of 298 All 298 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
  2. 2023Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots
  3. 2024UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion
  4. 2024Dual Diffusion for Unified Image Generation and Understanding
  5. 2025Decoder-Only LLMs are Better Controllers for Diffusion Models
  6. 2026TextLDM: Language Modeling with Continuous Latent Diffusion
  7. 2025CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities
  8. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts