mlsanityData to 7 Oct 2026

Seedream 3.0 Technical Report

arXiv 2504.11346 ↗First posted 15 Apr 2025cs.CVcited by 146

Not on the map. Why?

Cited by 46 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts, fine-grained typography generation, suboptimal visual aesthetics and fidelity, and limited image resolutions. Specifically, the advancements of Seedream 3.0 stem from improvements across the entire pipeline, from data construction to model deployment. At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework. Furthermore, we adopt several effective techniques such as mixed-resolution training, cross-modality RoPE, representation alignment loss, and resolution-aware timestep sampling in the pre-training phase. During the post-training stage, we utilize diversified aesthetic captions in SFT, and a VLM-based reward model with scaling, thereby achieving outputs that well align with human preferences. Furthermore, Seedream 3.0 pioneers a novel acceleration paradigm. By employing consistent noise expectation and importance-aware timestep sampling, we achieve a 4 to 8 times speedup while maintaining image quality. Seedream 3.0 demonstrates significant improvements over Seedream 2.0: it enhances overall capabilities, in particular for text-rendering in complicated Chinese characters which is important to professional typography generation. In addition, it provides native high-resolution output (up to 2K), allowing it to generate images with high visual quality.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

19 of 25 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  11. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  12. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
7 more
  1. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  2. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  3. 2024Learning Multi-dimensional Human Preference for Text-to-Image Generationcited by 102
  4. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 59
  5. 2024EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluationcited by 37
  6. 2020Stochastic Stein Discrepanciescited by 30
  7. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 65; 2026: 81.

146 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 973
  2. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  3. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 247
  4. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 233
  5. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  6. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  7. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108
  8. 2025FLARE: Robot Learning with Implicit World Modelingcited by 105
  9. 2025X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Againcited by 105
  10. 2025LongCat-Image Technical Reportcited by 92
  11. 2025Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learningcited by 88
  12. 2025OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generationcited by 81
38 more
  1. 2025PixNerd: Pixel Neural Field Diffusioncited by 75
  2. 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Modelcited by 73
  3. 2025RewardDance: Reward Scaling in Visual Generationcited by 63
  4. 2025EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modelingcited by 61
  5. 2025EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editingcited by 59
  6. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 55
  7. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 55
  8. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 39
  9. 2025PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewritingcited by 38
  10. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 37
  11. 2025CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Designcited by 36
  12. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 33
  13. 2025Transition Models: Rethinking the Generative Learning Objectivecited by 32
  14. 2026LongCat-Next: Lexicalizing Modalities as Discrete Tokenscited by 30
  15. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 29
  16. 2026Qwen-Image-2.0 Technical Reportcited by 28
  17. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  18. 2025EasyText: Controllable Diffusion Transformer for Multilingual Text Renderingcited by 25
  19. 2025UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generationcited by 23
  20. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 23
  21. 2025OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learningcited by 22
  22. 2025DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformerscited by 19
  23. 2025GenExam: A Multidisciplinary Text-to-Image Examcited by 19
  24. 2025Follow-Your-Preference: Towards Preference-Aligned Image Inpaintingcited by 18
  25. 2025CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generationcited by 17
  26. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  27. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 17
  28. 2025DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Designcited by 15
  29. 2025Query-Kontext: An Unified Multimodal Model for Image Generation and Editingcited by 15
  30. 2026TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Renderingcited by 14
  31. 2025Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generationcited by 13
  32. 2026NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generationcited by 13
  33. 2025DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Frameworkcited by 12
  34. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingcited by 12
  35. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Modelcited by 12
  36. 2025Uniform Discrete Diffusion with Metric Path for Video Generationcited by 11
  37. 2026PromptRL: Prompt Matters in RL for Flow-Based Image Generationcited by 11
  38. 2025TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuningcited by 10

50 most cited of 146 All 146 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SeedEdit 3.0: Fast and High-Quality Generative Image Editing
  2. 2026WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization
  3. 2026UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
  4. 2025Test-time Prompt Refinement for Text-to-Image Models
  5. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
  6. 2025LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation
  7. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models
  8. 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation