mlsanityData to 14 Oct 2026

InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis

arXiv 2509.10441 ↗First posted 12 Sep 2025cs.CVcited by 4

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Arbitrary resolution image generation provides a consistent visual experience across devices, having extensive applications for producers and consumers. Current diffusion models increase computational demand quadratically with resolution, causing 4K image generation delays over 100 seconds. To solve this, we explore the second generation upon the latent diffusion models, where the fixed latent generated by diffusion models is regarded as the content representation and we propose to decode arbitrary resolution images with a compact generated latent using a one-step generator. Thus, we present the InfGen, replacing the VAE decoder with the new generator, for generating images at any resolution from a fixed-size latent without retraining the diffusion models, which simplifies the process, reducing computational complexity and can be applied to any model using the same latent space. Experiments show InfGen is capable of improving many models into the arbitrary high-resolution era while cutting 4K image generation time to under 10 seconds.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 39 of its 45 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

39 of 45 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Exploring Representation-Aligned Latent Space for Better Generation1 Feb
  2. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis19 Mar
  3. 2024FiT: Flexible Vision Transformer for Diffusion Model19 Feb
  4. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers16 Jan
  5. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models11 Oct
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  7. 2023Fast Training of Diffusion Models with Masked Transformers15 Jun
  8. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer25 Mar
  9. 2022Scalable Diffusion Models with Transformers19 Dec
  10. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  11. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  12. 2020Denoising Diffusion Implicit Models6 Oct
1 more
  1. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 26

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2017Neural Discrete Representation Learningcited by 4,712
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
14 more
  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  2. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  3. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  4. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  5. 2021Transformers in Vision: A Surveycited by 1,013
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  7. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  8. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  9. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  10. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  11. 2021Generating Images with Sparse Representationscited by 266
  12. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 65
  13. 2023Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesiscited by 56
  14. 2024Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformercited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Generative Scenario Rollouts for End-to-End Autonomous Drivingcited by 6
  2. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  3. 2026RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representationscited by 0
  4. 2026MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DemoFusion: Democratising High-Resolution Image Generation With No
  2. 2023Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
  3. 2025Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation
  4. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  5. 2024Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder
  6. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
  7. 2024FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
  8. 2025One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models