mlsanityData to 14 Oct 2026

Creatively Upscaling Images with Global-Regional Priors

arXiv 2505.16976 ↗First posted 22 May 2025cs.CV cs.MMcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Contemporary diffusion models show remarkable capability in text-to-image generation, while still being limited to restricted resolutions (e.g., 1,024 X 1,024). Recent advances enable tuning-free higher-resolution image generation by recycling pre-trained diffusion models and extending them via regional denoising or dilated sampling/convolutions. However, these models struggle to simultaneously preserve global semantic structure and produce creative regional details in higher-resolution images. To address this, we present C-Upscale, a new recipe of tuning-free image upscaling that pivots on global-regional priors derived from given global prompt and estimated regional prompts via Multimodal LLM. Technically, the low-frequency component of low-resolution image is recognized as global structure prior to encourage global semantic consistency in high-resolution generation. Next, we perform regional attention control to screen cross-attention between global prompt and each region during regional denoising, leading to regional attention prior that alleviates object repetition issue. The estimated regional prompts containing rich descriptive details further act as regional semantic prior to fuel the creativity of regional detail generation. Both quantitative and qualitative evaluations demonstrate that our C-Upscale manages to generate ultra-high-resolution images (e.g., 4,096 X 4,096 and 8,192 X 8,192) with higher visual fidelity and more creative regional details.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 48 of its 59 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

48 of 59 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance26 Jun
  2. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis21 Apr
  3. 2024Boosting Diffusion Models with Moving Average Sampling in Frequency Domain26 Mar
  4. 2024SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer25 Mar
  5. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis19 Mar
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  7. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation16 Feb
  8. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models11 Oct
  9. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  10. 2023FreeU: Free Lunch in Diffusion U-Net20 Sep
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
4 more
  1. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2020Denoising Diffusion Implicit Models6 Oct
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  9. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  10. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  11. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  12. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
20 more
  1. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  2. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  3. 2021Multi-Stage Progressive Image Restorationcited by 816
  4. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  5. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  6. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  7. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  8. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 279
  9. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 238
  10. 2024Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMscited by 224
  11. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
  12. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 107
  13. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 65
  14. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  15. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40
  16. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  17. 2023Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Imagescited by 36
  18. 2024AccDiffusion: An Accurate Method for Higher-Resolution Image Generationcited by 33
  19. 2024Improving Virtual Try-On with Garment-focused Diffusion Modelscited by 15
  20. 2024Improving Text-guided Object Inpainting with Semantic Pre-inpaintingcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Visual Autoregressive Modeling for Instruction-Guided Image Editingcited by 22
  2. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
  2. 2025RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution
  3. 2024HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts
  4. 2025The Power of Context: How Multimodality Improves Image Super-Resolution
  5. 2023Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
  6. 2025Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
  7. 2024GLoD: Composing Global Contexts and Local Details in Image Generation
  8. 2026Disentangled Textual Priors for Diffusion-based Image Super-Resolution