mlsanityData to 14 Oct 2026

HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer

arXiv 2505.22705 ↗First posted 28 May 2025cs.CV cs.MMcited by 141

On the map: Diffusion models → Diffusion foundations and sampling

also in 1 more
Abstract (arXiv)

Recent advancements in image generative foundation models have prioritized quality improvements but often at the cost of increased computational complexity and inference latency. To address this critical trade-off, we introduce HiDream-I1, a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds. HiDream-I1 is constructed with a new sparse Diffusion Transformer (DiT) structure. Specifically, it starts with a dual-stream decoupled design of sparse DiT with dynamic Mixture-of-Experts (MoE) architecture, in which two separate encoders are first involved to independently process image and text tokens. Then, a single-stream sparse DiT structure with dynamic MoE architecture is adopted to trigger multi-model interaction for image generation in a cost-efficient manner. To support flexiable accessibility with varied model capabilities, we provide HiDream-I1 in three variants: HiDream-I1-Full, HiDream-I1-Dev, and HiDream-I1-Fast. Furthermore, we go beyond the typical text-to-image generation and remould HiDream-I1 with additional image conditions to perform precise, instruction-based editing on given images, yielding a new instruction-based image editing model namely HiDream-E1. Ultimately, by integrating text-to-image generation and instruction-based image editing, HiDream-I1 evolves to form a comprehensive image agent (HiDream-A1) capable of fully interactive image creation and refinement. To accelerate multi-modal AIGC research, we have open-sourced all the codes and model weights of HiDream-I1-Full, HiDream-I1-Dev, HiDream-I1-Fast, HiDream-E1 through our project websites: https://github.com/HiDream-ai/HiDream-I1 and https://github.com/HiDream-ai/HiDream-E1. All features can be directly experienced via https://vivago.ai/studio.

Key facts. Cited by 141 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 17 of its 22 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

17 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Improved Distribution Matching Distillation for Fast Image Synthesis23 May
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar

Other references · 15

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2020GLU Variants Improve Transformercited by 1,804
  4. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  5. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  6. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  7. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  8. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  9. 2024OmniGen: Unified Image Generationcited by 394
  10. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 324
  11. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 300
  12. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
3 more
  1. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  2. 2023SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Modelscited by 177
  3. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 176

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 61; 2026: 80.

141 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 132
  3. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 112
  4. 2025LongCat-Image Technical Reportcited by 100
  5. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 97
  6. 2025Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learningcited by 92
  7. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 57
  8. 2025EditVerse: Unifying Image and Video Editing and Generation with In-Context Learningcited by 54
  9. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 38
  10. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 34
  11. 2026HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformercited by 32
  12. 2025X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learningcited by 25
38 more
  1. 2025UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generationcited by 25
  2. 2025UniREditBench: A Unified Reasoning-based Image Editing Benchmarkcited by 25
  3. 2025ReasonEdit: Towards Reasoning-Enhanced Image Editing Modelscited by 25
  4. 2025Region-Constraint In-Context Generation for Instructional Video Editingcited by 23
  5. 2025Visual Autoregressive Modeling for Instruction-Guided Image Editingcited by 22
  6. 2025GenExam: A Multidisciplinary Text-to-Image Examcited by 22
  7. 2025When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thoughtcited by 21
  8. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  9. 2026Agent Banana: High-Fidelity Image Editing with Agentic Thinking and Toolingcited by 19
  10. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  11. 2025MIRA: Multimodal Iterative Reasoning Agent for Image Editingcited by 17
  12. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 16
  13. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  14. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  15. 2025Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captionscited by 14
  16. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 14
  17. 2025EasyV2V: A High-quality Instruction-based Video Editing Frameworkcited by 13
  18. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingcited by 12
  19. 2025SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencodercited by 12
  20. 2026PromptRL: Prompt Matters in RL for Flow-Based Image Generationcited by 12
  21. 2026JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generationcited by 12
  22. 2025WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editingcited by 11
  23. 2025TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuningcited by 10
  24. 2025O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editingcited by 10
  25. 2025MIRAGE: Towards AI-Generated Image Detection in the Wildcited by 8
  26. 2025Semantic Visual Anomaly Detection and Reasoning in AI-Generated Imagescited by 8
  27. 2025Group Relative Attention Guidance for Image Editingcited by 8
  28. 2025Ovis-Image Technical Reportcited by 8
  29. 2025EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecturecited by 8
  30. 2025EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editingcited by 8
  31. 2026RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignmentcited by 7
  32. 2026WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editingcited by 7
  33. 2025iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generationcited by 6
  34. 2025Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Modelcited by 6
  35. 2026ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuningcited by 6
  36. 2026CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generationcited by 6
  37. 2026Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modelingcited by 6
  38. 2026Lens: Rethinking Training Efficiency for Foundational Text-to-Image Modelscited by 6

50 most cited of 141 All 141 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generation
  2. 2026HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
  3. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
  4. 2023DiffiT: Diffusion Vision Transformers for Image Generation
  5. 2025Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
  6. 2023DiffI2I: Efficient Diffusion Model for Image-to-Image Translation
  7. 2023CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
  8. 2024SparseDM: Toward Sparse Efficient Diffusion Models