mlsanityData to 14 Oct 2026

ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation

arXiv 2311.18822 ↗First posted 30 Nov 2023cs.CVcited by 37

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

Abstract (arXiv)

Diffusion models have revolutionized image generation in recent years, yet they are still limited to a few sizes and aspect ratios. We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image diffusion models to generate images with various sizes. ElasticDiffusion attempts to decouple the generation trajectory of a pretrained model into local and global signals. The local signal controls low-level pixel information and can be estimated on local patches, while the global signal is used to maintain overall structural consistency and is estimated with a reference image. We test our method on CelebA-HQ (faces) and LAION-COCO (objects/indoor/outdoor scenes). Our experiments and qualitative results show superior image coherence quality across aspect ratios compared to MultiDiffusion and the standard decoding strategy of Stable Diffusion. Project page: https://elasticdiffusion.github.io/

Key facts. Cited by 37 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 49 of its 70 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

49 of 70 references.

Closest ancestors · 11

Same direction, newest first

  1. 2023LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis21 Nov
  2. 2023Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer Models15 Sep
  3. 2023Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images31 Aug
  4. 2023Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis14 Jun
  5. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation16 Feb
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
  10. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov
  11. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation6 Oct

Other references · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  11. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
26 more
  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  2. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  3. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  4. 2022Video Diffusion Modelscited by 2,305
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  8. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  9. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  10. 2023Universal Guidance for Diffusion Modelscited by 437
  11. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 388
  12. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  13. 2023Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Modelscited by 324
  14. 2023Pix2Video: Video Editing using Image Diffusioncited by 320
  15. 2022Novel View Synthesis with Diffusion Modelscited by 300
  16. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 294
  17. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  18. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 128
  19. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 107
  20. 2023Inst-Inpaint: Instructing to Remove Objects with Diffusion Modelscited by 66
  21. 2023Mixture of Diffusers for scene composition and high resolution image generationcited by 56
  22. 2023The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusioncited by 41
  23. 2023Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Imagescited by 27
  24. 2023AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generationcited by 22
  25. 2023Dynamic Attention-Guided Diffusion for Image Super-Resolutioncited by 10
  26. 2023VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 17; 2026: 4.

37 papers.

Sort:

By area:

  1. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  2. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 65
  3. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesiscited by 59
  4. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptationcited by 51
  5. 2024LinFusion: 1 GPU, 1 Minute, 16K Imagecited by 43
  6. 2024FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusioncited by 30
  7. 2024Taming Data and Transformers for Audio Generationcited by 28
  8. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuningcited by 25
  9. 2025Lossy Compression with Pretrained Diffusion Modelscited by 25
  10. 2025Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Modelscited by 25
  11. 2024ResAdapter: Domain Consistent Resolution Adapter for Diffusion Modelscited by 23
  12. 2024I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flowcited by 23
25 more
  1. 2024Beyond Deepfake Images: Detecting AI-Generated Videoscited by 22
  2. 2025Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Modelscited by 18
  3. 2024Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Modelscited by 14
  4. 2025DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusioncited by 14
  5. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  6. 2025HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streamingcited by 8
  7. 2024RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generationcited by 6
  8. 2025UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratioscited by 6
  9. 2025Ultra-High-Resolution Image Synthesis: Data, Method and Evaluationcited by 5
  10. 2025Parallel Sequence Modeling via Generalized Spatial Propagation Networkcited by 4
  11. 2025SketchFusion: Learning Universal Sketch Features through Fusing Foundation Modelscited by 4
  12. 2025Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integrationcited by 4
  13. 2024AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolationcited by 3
  14. 2025Creatively Upscaling Images with Global-Regional Priorscited by 2
  15. 2024Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generationcited by 1
  16. 2025RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectificationcited by 1
  17. 2025CineScale: Tuning-Free High-Resolution Video Generationcited by 1
  18. 2025InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Informationcited by 1
  19. 2025Example-Based Feature Painting on Texturescited by 1
  20. 2026TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformerscited by 1
  21. 2025Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr'echet Distancecited by 0
  22. 2025NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generationcited by 0
  23. 2026ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priorscited by 0
  24. 2026ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Modelscited by 0
  25. 2026Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MixDiffusion: Mixing Diffusion-based Uni-condition Text-to-Image Generation Models for Multi-condition Image Synthesis
  2. 2026StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation
  3. 2023SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions
  4. 2026ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
  5. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
  6. 2024SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time
  7. 2023DiffCollage: Parallel Generation of Large Content with Diffusion Models
  8. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion