mlsanityData to 14 Oct 2026

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale

arXiv 2312.07586 ↗First posted 11 Dec 2023cs.CV cs.AI cs.LGcited by 26

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 23 of its 32 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

23 of 32 references.

Closest ancestors · 20

Same direction, newest first

  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  2. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model17 Mar
  3. 2023Universal Guidance for Diffusion Models14 Feb
  4. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
  5. 2023ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories5 Feb
  6. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models28 Nov
  7. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  8. 2022FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation9 Oct
  9. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  10. 2022On Investigating the Conservative Property of Score-Based Generative Models26 Sep
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications2 Sep
  12. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
8 more
  1. 2022Classifier-Free Diffusion Guidance26 Jul
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  3. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  5. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 3

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2016Improved Techniques for Training GANscited by 2,970

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 9.

26 papers.

Sort:

By area:

  1. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 299
  2. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 114
  3. 2025CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Modelscited by 52
  4. 2025Diffusion Models without Classifier-free Guidancecited by 33
  5. 2025Rectified-CFG++ for Flow Based Modelscited by 17
  6. 2025Learn to Guide Your Diffusion Modelcited by 14
  7. 2025Flow Map Distillation Without Datacited by 14
  8. 2025Normalized Attention Guidance: Universal Negative Guidance for Diffusion Modelscited by 13
  9. 2025REG: Rectified Gradient Guidance for Conditional Diffusion Modelscited by 8
  10. 2026CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidancecited by 8
  11. 2025Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterationscited by 6
  12. 2025Dichotomous Diffusion Policy Optimizationcited by 6
14 more
  1. 2025DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Modelscited by 4
  2. 2026Improving Classifier-Free Guidance of Flow Matching via Manifold Projectioncited by 3
  3. 2025DICE: Distilling Classifier-Free Guidance into Text Embeddingscited by 2
  4. 2025Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generationcited by 2
  5. 2025On the Separability of Information in Diffusion Modelscited by 2
  6. 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scalescited by 2
  7. 2025RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformerscited by 1
  8. 2026Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidancecited by 1
  9. 2026ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-Oncited by 1
  10. 2025TAG: Tangential Amplifying Guidance for Hallucination-Resistant Samplingcited by 0
  11. 2026Commitment Before Realization: When Classifier-Free Guidance Becomes Unnecessary in Masked Diffusion Language Modelscited by 0
  12. 2026Backward SDEs-based Diffusion for Physics-Constrained Generationcited by 0
  13. 2026SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Modelscited by 0
  14. 2026Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strengthcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026On the Robustness of Distribution Support under Diffusion Guidance
  2. 2025Feedback Guidance of Diffusion Models
  3. 2024Classifier-Free Guidance is a Predictor-Corrector
  4. 2025Navigating with Annealing Guidance Scale in Diffusion Space
  5. 2023Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance
  6. 2025In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models
  7. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance
  8. 2024Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models