mlsanityData to 7 Oct 2026

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

arXiv 2503.18352 ↗First posted 24 Mar 2025cs.CVcited by 61

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper, we present Diffusion-4K, a novel framework for direct ultra-high-resolution image synthesis using text-to-image diffusion models. The core advancements include: (1) Aesthetic-4K Benchmark: addressing the absence of a publicly available 4K image synthesis dataset, we construct Aesthetic-4K, a comprehensive benchmark for ultra-high-resolution image generation. We curated a high-quality 4K dataset with carefully selected images and captions generated by GPT-4o. Additionally, we introduce GLCM Score and Compression Ratio metrics to evaluate fine details, combined with holistic measures such as FID, Aesthetics and CLIPScore for a comprehensive assessment of ultra-high-resolution images. (2) Wavelet-based Fine-tuning: we propose a wavelet-based fine-tuning approach for direct training with photorealistic 4K images, applicable to various latent diffusion models, demonstrating its effectiveness in synthesizing highly detailed 4K images. Consequently, Diffusion-4K achieves impressive performance in high-quality image synthesis and text prompt adherence, especially when powered by modern large-scale diffusion models (e.g., SD3-2B and Flux-12B). Extensive experimental results from our benchmark demonstrate the superiority of Diffusion-4K in ultra-high-resolution image synthesis.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 38 of its 49 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

38 of 49 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models14 Oct
  2. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers14 Oct
  3. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation18 Mar
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers16 Jan
  6. 2023Adversarial Diffusion Distillation28 Nov
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  8. 2022Scalable Diffusion Models with Transformers19 Dec
  9. 2022Wavelet Diffusion Models are fast and scalable Image Generators29 Nov
  10. 2022Wavelet Score-Based Generative Modeling9 Aug
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
3 more
  1. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  3. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2024GPT-4o System Cardcited by 4,467
  8. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  10. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
11 more
  1. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  2. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  3. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  4. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  5. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  6. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  7. 2021ZeRO-Offload: Democratizing Billion-Scale Model Trainingcited by 339
  8. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
  9. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 113
  10. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 105
  11. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 25; 2026: 36.

61 papers.

Sort:

By area:

  1. 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidancecited by 21
  2. 2025UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Datasetcited by 16
  3. 2025Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Modelscited by 13
  4. 2025DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusioncited by 13
  5. 2025UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformerscited by 10
  6. 2026SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformercited by 10
  7. 2025Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioningcited by 7
  8. 2025Decoupling High and Low Frequencies for Faithful Image Generation with Fine Detailscited by 7
  9. 2025DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Spacecited by 7
  10. 2025Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspectivecited by 7
  11. 2025AutoMV: An Automatic Multi-Agent System for Music Video Generationcited by 7
  12. 2026L2P: Unlocking Latent Potential for Pixel Generationcited by 7
38 more
  1. 2025Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesiscited by 6
  2. 2025UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratioscited by 6
  3. 2025Jodi: Unification of Visual Generation and Understanding via Joint Modelingcited by 5
  4. 2025Ultra-High-Resolution Image Synthesis: Data, Method and Evaluationcited by 5
  5. 2026FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matchingcited by 5
  6. 2026Nucleus-Image: Sparse MoE for Image Generationcited by 5
  7. 2025RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectorscited by 4
  8. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  9. 2026DA-VAE: Plug-in Latent Compression for Diffusion via Detail Alignmentcited by 4
  10. 2025Asymmetric VAE for One-Step Video Super-Resolution Accelerationcited by 3
  11. 2025Transform Trained Transformer for Accelerating Native 4K Video Generationcited by 3
  12. 2026Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothingcited by 3
  13. 2026Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generationcited by 2
  14. 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformerscited by 2
  15. 2025Underwater Diffusion Attention Network with Contrastive Language-Image Joint Learning for Underwater Image Enhancementcited by 1
  16. 2025UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attentioncited by 1
  17. 2025Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformercited by 1
  18. 2025Low-Resolution Editing is All You Need for High-Resolution Editingcited by 1
  19. 2025FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformerscited by 1
  20. 2026PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusioncited by 1
  21. 2026BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Modelscited by 1
  22. 2026Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolutioncited by 1
  23. 2026TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformerscited by 1
  24. 2026EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesiscited by 1
  25. 2026PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Datasetcited by 1
  26. 2026Spatial Gram Alignment for Ultra-High-Resolution Image Synthesiscited by 1
  27. 2026Where the Score Lives: A Wavelet View of Diffusioncited by 1
  28. 2025LVLM-Composer's Explicit Planning for Image Generationcited by 0
  29. 2025HiMat: DiT-based Ultra-High Resolution SVBRDF Generationcited by 0
  30. 2025ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-Oncited by 0
  31. 2026InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMscited by 0
  32. 2026mmWave-Diffusion:A Novel Framework for Respiration Sensing Using Observation-Anchored Conditional Diffusion Modelcited by 0
  33. 2026CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibrationcited by 0
  34. 2026ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priorscited by 0
  35. 2026Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Modelscited by 0
  36. 2026ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Modelscited by 0
  37. 2026QDSB: Quantized Diffusion Schr"odinger Bridgescited by 0
  38. 2026OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppressioncited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  2. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
  3. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
  4. 2023Boosting Latent Diffusion with Flow Matching
  5. 2024Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Model
  6. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
  7. 2025ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
  8. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models