mlsanityData to 7 Oct 2026

UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

arXiv 2407.02158 ↗First posted 2 Jul 2024cs.CVcited by 64

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (textite.g., 1K to 6K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images, significantly reducing complexity. Furthermore, we introduce implicit neural representations for continuous upsampling and scale-aware normalization layers adaptable to various resolutions. Notably, both low- and high-resolution processes are performed in the most compact space, sharing the majority of parameters with less than 3% additional parameters for high-resolution outputs, largely enhancing training and inference efficiency. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images and demonstrating state-of-the-art performance in extensive experiments.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 43 of its 53 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

43 of 53 references.

References · 43

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2023Segment Anythingcited by 8,158
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
31 more
  1. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  7. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  8. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  9. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  10. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  11. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  12. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  13. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  14. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  15. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  16. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  17. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  18. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  19. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
  20. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  21. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 127
  22. 2023SyncDiffusion: Coherent Montage via Synchronized Joint Diffusionscited by 108
  23. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 105
  24. 2021Shunted Self-Attention via Multi-Scale Token Aggregationcited by 90
  25. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  26. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesiscited by 58
  27. 2023Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesiscited by 55
  28. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  29. 2023TinyMIM: An Empirical Study of Distilling MIM Pre-trained Modelscited by 24
  30. 2024ResAdapter: Domain Consistent Resolution Adapter for Diffusion Modelscited by 23
  31. 2023Rejuvenating image-GPT as Strong Visual Representation Learnerscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 36; 2026: 19.

64 papers.

Sort:

By area:

  1. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  2. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
  3. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 148
  4. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 85
  5. 2025Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generationcited by 71
  6. 2025POSTA: A Go-to Framework for Customized Artistic Poster Generationcited by 36
  7. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  8. 2024FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusioncited by 29
  9. 2025Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Modelscited by 24
  10. 2024I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flowcited by 21
  11. 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidancecited by 21
  12. 2025Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Modelscited by 18
38 more
  1. 2025UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Datasetcited by 16
  2. 2024FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Samplingcited by 15
  3. 2025Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesiscited by 13
  4. 2025RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditionscited by 13
  5. 2025DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusioncited by 13
  6. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 13
  7. 2024Diffusion Models Need Visual Priors for Image Generationcited by 12
  8. 2025Ultra-Resolution Adaptation with Easecited by 12
  9. 2025UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformerscited by 10
  10. 2026JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generationcited by 10
  11. 2024DreamRelation: Bridging Customization and Relation Generationcited by 9
  12. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  13. 2025HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streamingcited by 8
  14. 2025Semantic Context Matters: Improving Conditioning for Autoregressive Modelscited by 7
  15. 2026Fast Image Super-Resolution via Consistency Rectified Flowcited by 7
  16. 2024Timeline and Boundary Guided Diffusion Network for Video Shadow Detectioncited by 6
  17. 2025Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesiscited by 6
  18. 2026Frequency-Aware Flow Matching for High-Quality Image Generationcited by 6
  19. 2025ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restorationcited by 5
  20. 2025ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusioncited by 5
  21. 2026Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separationcited by 5
  22. 2025Progressive Growing of Video Tokenizers for Temporally Compact Latent Spacescited by 4
  23. 2025Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignmentcited by 4
  24. 2025InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesiscited by 4
  25. 2025Stable Score Distillationcited by 3
  26. 2025Creatively Upscaling Images with Global-Regional Priorscited by 2
  27. 2025SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolutioncited by 2
  28. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  29. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarkingcited by 2
  30. 2025RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectificationcited by 1
  31. 2025Cross-Subject Mind Decoding from Inaccurate Representationscited by 1
  32. 2025InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Informationcited by 1
  33. 2025UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attentioncited by 1
  34. 2025ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformerscited by 1
  35. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  36. 2026PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Datasetcited by 1
  37. 2026Spatial Gram Alignment for Ultra-High-Resolution Image Synthesiscited by 1
  38. 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutionscited by 1

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Model
  2. 2025Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
  3. 2026DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer
  4. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  5. 2025Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
  6. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
  7. 2026TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution
  8. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation