mlsanityData to 14 Oct 2026

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models

arXiv 2605.31162 ↗First posted 29 May 2026cs.CV cs.LGcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free diffusion editing, systematically fails for global, low-level transformations required for aesthetic and perceptual refinement. We introduce a novel, generalized framework for image-editing in unconditional diffusion models without explicit training. This inference-time mechanism operates on low-level features by extracting degradation concept vectors and combining bottleneck patching with classifier-free guidance to guide sampling away from the degraded manifold, producing consistently improved images without any model retraining.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 16 of its 20 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

16 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models20 Nov

Other references · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2022Diffusion Models already have a Semantic Latent Spacecited by 328
  8. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidancecited by 154
  9. 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidancecited by 113
  10. 2023Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Modelscited by 60
  11. 2024Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidancecited by 59
  12. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attentioncited by 59
3 more
  1. 2020GAN "Steerability" without optimizationcited by 48
  2. 2023Unsupervised Discovery of Semantic Latent Directions in Diffusion Modelscited by 28
  3. 2025LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learningcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
  2. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs
  3. 2024Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing
  4. 2026Language-Free Generative Editing from One Visual Example
  5. 2023Perceptual Similarity guidance and text guidance optimization for Editing Real Images using Guided Diffusion Models
  6. 2023Cross-domain Compositing with Pretrained Diffusion Models
  7. 2023Training-free Content Injection using h-space in Diffusion Models
  8. 2024Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models