mlsanityData to 7 Oct 2026

Resolution Chromatography of Diffusion Models

arXiv 2401.10247 ↗First posted 7 Dec 2023cs.CV cs.LGcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models generate high-resolution images through iterative stochastic processes. In particular, the denoising method is one of the most popular approaches that predicts the noise in samples and denoises it at each time step. It has been commonly observed that the resolution of generated samples changes over time, starting off blurry and coarse, and becoming sharper and finer. In this paper, we introduce "resolution chromatography" that indicates the signal generation rate of each resolution, which is very helpful concept to mathematically explain this coarse-to-fine behavior in generation process, to understand the role of noise schedule, and to design time-dependent modulation. Using resolution chromatography, we determine which resolution level becomes dominant at a specific time step, and experimentally verify our theory with text-to-image diffusion models. We also propose some direct applications utilizing the concept: upscaling pre-trained models to higher resolutions and time-dependent prompt composing. Our theory not only enables a better understanding of numerous pre-existing techniques for manipulating image generation, but also suggests the potential for designing better noise schedules.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 23 of its 27 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

23 of 27 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry24 Jul
  2. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  3. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  4. 2022Diffusion Models already have a Semantic Latent Space20 Oct
  5. 2022Classifier-Free Diffusion Guidance26 Jul
  6. 2022Perception Prioritized Training of Diffusion Models1 Apr
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  11. 2020Denoising Diffusion Implicit Models6 Oct
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 11

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  7. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  8. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  9. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  11. 2022Multiresolution Textual Inversioncited by 33

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Upsample Guidance: Scale Up Diffusion Models without Trainingcited by 19
  2. 2025NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Denoising diffusion models for high-resolution microscopy image restoration
  2. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  3. 2024Diffusion Models to Enhance the Resolution of Microscopy Images: A Tutorial
  4. 2025Training-free Diffusion Acceleration with Bottleneck Sampling
  5. 2025LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition
  6. 2024Enhancing Sample Generation of Diffusion Models using Noise Level Correction
  7. 2024Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
  8. 2023Compensation Sampling for Improved Convergence in Diffusion Models