mlsanityData to 14 Oct 2026

Manifold Preserving Guided Diffusion

arXiv 2311.16424 ↗First posted 28 Nov 2023cs.LG cs.AI cs.CVcited by 157

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework that leverages pretrained diffusion models and off-the-shelf neural networks with minimal additional inference cost for a broad range of tasks. Specifically, we leverage the manifold hypothesis to refine the guided diffusion steps and introduce a shortcut algorithm in the process. We then propose two methods for on-manifold training-free guidance using pre-trained autoencoders and demonstrate that our shortcut inherently preserves the manifolds when applied to latent diffusion models. Our experiments show that MPGD is efficient and effective for solving a variety of conditional generation applications in low-compute settings, and can consistently offer up to 3.8x speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.

Key facts. Cited by 157 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 46 of its 55 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

46 of 55 references.

Closest ancestors · 11

Same direction, newest first

  1. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidance23 Mar
  2. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model17 Mar
  3. 2023Universal Guidance for Diffusion Models14 Feb
  4. 2022Your diffusion model secretly knows the dimension of the data manifold23 Dec
  5. 2022Diffusion models as plug-and-play priors17 Jun
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  8. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Implicit Models6 Oct
  11. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 35

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
23 more
  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  4. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  7. 2018Demystifying MMD GANscited by 1,293
  8. 2022Denoising Diffusion Restoration Modelscited by 963
  9. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  10. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  11. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
  12. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 222
  13. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  14. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 182
  15. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 182
  16. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Modelscited by 157
  17. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
  18. 2017The Riemannian Geometry of Deep Generative Modelscited by 82
  19. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 72
  20. 2023Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustnesscited by 20
  21. 2023Lifting Architectural Constraints of Injective Flowscited by 18
  22. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 16
  23. 2023Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Modelscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 38; 2025: 57; 2026: 62.

157 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Inverse Problemscited by 180
  2. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 119
  3. 2024TFG: Unified Training-Free Guidance for Diffusion Modelscited by 107
  4. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 97
  5. 2025Test-time Alignment of Diffusion Models without Reward Over-optimizationcited by 93
  6. 2024Guidance with Spherical Gaussian Constraint for Conditional Diffusioncited by 71
  7. 2024SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generationcited by 68
  8. 2024Gradient Guidance for Diffusion Models: An Optimization Perspectivecited by 61
  9. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 61
  10. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Modelscited by 61
  11. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Modelscited by 53
  12. 2025Inference-time Scaling of Diffusion Models through Classical Searchcited by 49
38 more
  1. 2024Steering Rectified Flow Models in the Vector Field for Controlled Image Generationcited by 39
  2. 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 35
  3. 2025Diffusion Tree Sampling: Scalable inference-time alignment of diffusion modelscited by 34
  4. 2024Understanding and Improving Training-free Loss-based Diffusion Guidancecited by 32
  5. 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Mapscited by 29
  6. 2024PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teachercited by 27
  7. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 24
  8. 2025DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Modelscited by 23
  9. 2025Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posteriorcited by 22
  10. 2025Training-Free Constrained Generation With Stable Diffusion Modelscited by 20
  11. 2025Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approachcited by 18
  12. 2025GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Modelscited by 17
  13. 2024Adding Conditional Control to Diffusion Models with Reinforcement Learningcited by 16
  14. 2025Diffusion models for inverse problemscited by 16
  15. 2024Diffusion State-Guided Projected Gradient for Inverse Problemscited by 14
  16. 2025CoDe: Blockwise Control for Denoising Diffusion Modelscited by 14
  17. 2025SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Scorecited by 14
  18. 2024Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessmentcited by 13
  19. 2024Automated Black-box Prompt Engineering for Personalized Text-to-Image Generationcited by 12
  20. 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidancecited by 11
  21. 2024Decoupling Training-Free Guided Diffusion by ADMMcited by 11
  22. 2025Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Modelscited by 11
  23. 2026Training-Free Adaptation of Diffusion Models via Doob's h-Transformcited by 11
  24. 2024Fast constrained sampling in pre-trained diffusion modelscited by 10
  25. 2024Constrained Diffusion with Trust Samplingcited by 10
  26. 2025ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generationcited by 10
  27. 2024Infusion: Preventing Customized Text-to-Image Diffusion from Overfittingcited by 9
  28. 2024MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Trainingcited by 9
  29. 2025Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planningcited by 9
  30. 2024Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solverscited by 8
  31. 2024Gradient-Free Classifier Guidance for Diffusion Model Samplingcited by 8
  32. 2025Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generationcited by 7
  33. 2025AudioMorphix: Training-free audio editing with diffusion probabilistic modelscited by 7
  34. 2025Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion Modelscited by 7
  35. 2025Product of Experts for Visual Generationcited by 6
  36. 2025FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solverscited by 6
  37. 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimizationcited by 6
  38. 2026How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidancecited by 6

50 most cited of 157 All 157 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
  2. 2025REG: Rectified Gradient Guidance for Conditional Diffusion Models
  3. 2024A Simple Approach to Unifying Diffusion-based Conditional Generation
  4. 2022On Distillation of Guided Diffusion Models
  5. 2023Conditional Image Generation with Pretrained Generative Model
  6. 2023Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
  7. 2024Plug-and-Play Diffusion Distillation
  8. 2023Elucidating The Design Space of Classifier-Guided Diffusion Generation