mlsanityData to 14 Oct 2026

Can We Change the Stroke Size for Easier Diffusion?

arXiv 2603.26783 ↗First posted 25 Mar 2026cs.CV cs.AIcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Deep-learning-based image generation is increasingly useful but expensive. Across the different timesteps in the denoising chain, high-noise timesteps present distinct optimization and prediction challenges, which can increase the cost of real-world applications. Inspired by the varying stroke sizes used in human painting, in this work, we ask whether a similar stroke-size variation (i.e., rough stroke applied early) in diffusion can simplify existing image-generation algorithms. We subsequently develop the MultiStroke operator, which linearly interpolates coarse and fine strokes in a coarse-to-fine manner to potentially simplify the prediction target, especially at high-noise timesteps. Across DDPM and flow-matching models trained from scratch, MultiStroke achieves an FID reduction of up to 70.2%. A quick video is at https://wendybaiyunwei.github.io/MultiStroke-Web/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 31 of its 37 references that are in the map. First posted on arXiv 25 Mar 2026.

Builds on

31 of 37 references.

Closest ancestors · 22

Same direction, newest first

  1. 2025Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility24 May
  2. 2024Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment18 Jun
  3. 2024Denoising Task Difficulty-based Curriculum for Training Diffusion Models15 Mar
  4. 2023Diffusion Models With Learned Adaptive Noise20 Dec
  5. 2023FreeU: Free Lunch in Diffusion U-Net20 Sep
  6. 2023Efficient Diffusion Training via Min-SNR Weighting Strategy16 Mar
  7. 2023Diffusion Models are Minimax Optimal Distribution Estimators3 Mar
  8. 2023Consistency Models2 Mar
  9. 2022Soft Diffusion: Score Matching for General Corruptions12 Sep
  10. 2022Classifier-Free Diffusion Guidance26 Jul
  11. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
10 more
  1. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021Variational Diffusion Models1 Jul
  4. 2021Score-based Generative Modeling in Latent Space10 Jun
  5. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  6. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  7. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 9

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2016Improved Techniques for Training GANscited by 2,970
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  6. 2018A Note on the Inception Scorecited by 226
  7. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  8. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 139
  9. 2024Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesiscited by 48

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Improved Noise Schedule for Diffusion Training
  2. 2024Edge-preserving noise for diffusion models
  3. 2026Memorization Control in Diffusion Models from Denoising-centric Perspective
  4. 2026Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
  5. 2025FreSca: Scaling in Frequency Space Enhances Diffusion Models
  6. 2025A Comprehensive Review on Noise Control of Diffusion Model
  7. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed
  8. 2026Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling