mlsanityData to 14 Oct 2026

Guiding a diffusion model using sliding windows

arXiv 2411.10257 ↗First posted 15 Nov 2024cs.CV cs.AI cs.LGcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Guidance is a widely used technique for diffusion models to enhance sample quality. Technically, guidance is realised by using an auxiliary model that generalises more broadly than the primary model. Using a 2D toy example, we first show that it is highly beneficial when the auxiliary model exhibits similar but stronger generalisation errors than the primary model. Based on this insight, we introduce masked sliding window guidance (M-SWG), a novel, training-free method. M-SWG upweights long-range spatial dependencies by guiding the primary model with itself by selectively restricting its receptive field. M-SWG requires neither access to model weights from previous iterations, additional training, nor class conditioning. M-SWG achieves a superior Inception score (IS) compared to previous state-of-the-art training-free approaches, without introducing sample oversaturation. In conjunction with existing guidance methods, M-SWG reaches state-of-the-art Frechet DINOv2 distance on ImageNet using EDM2-XXL and DiT-XL. The code is available at https://github.com/HHU-MMBS/swgbmvc2025official.

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 36 of its 49 references that are in the map. First posted on arXiv 15 Nov 2024.

Builds on

36 of 49 references.

Closest ancestors · 21

Same direction, newest first

  1. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models3 Oct
  2. 2024Self-Improving Diffusion Models with Synthetic Data29 Aug
  3. 2024Classifier-Free Guidance is a Predictor-Corrector16 Aug
  4. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention1 Aug
  5. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models2 Jul
  6. 2024A Comprehensive Survey on Diffusion Models and Their Applications1 Jul
  7. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models12 Jun
  8. 2024Guiding a Diffusion Model with a Bad Version of Itself4 Jun
  9. 2024Analysis of Classifier-Free Guidance Weight Schedulers19 Apr
  10. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
  11. 2024Rethinking cluster-conditioned diffusion models for label-free image synthesis1 Mar
  12. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
9 more
  1. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling26 Oct
  2. 2022Scalable Diffusion Models with Transformers19 Dec
  3. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  4. 2022Classifier-Free Diffusion Guidance26 Jul
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 15

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  5. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  6. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  7. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  8. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  9. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 310
  10. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  11. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  12. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 165
3 more
  1. 2024Rolling Diffusion Modelscited by 104
  2. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  3. 2024DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalizationcited by 60

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025Learn to Guide Your Diffusion Modelcited by 14
  2. 2026Diffusion Models Memorize in Training -- and Generalize in Inferencecited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion Models without Classifier-free Guidance
  2. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
  3. 2026Learned End-to-End Guidance Schedules for Diffusion Models
  4. 2025Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
  5. 2025Variational Control for Guidance in Diffusion Models
  6. 2026On the Robustness of Distribution Support under Diffusion Guidance
  7. 2025In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models
  8. 2023Guided Diffusion from Self-Supervised Diffusion Features