mlsanityData to 7 Oct 2026

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

arXiv 2303.09833 ↗First posted 17 Mar 2023cs.CVcited by 290

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required. They need to train a time-dependent classifier or a condition-dependent score estimator, which increases the cost of constructing conditional diffusion models and is inconvenient to transfer across different conditions. Some current works aim to overcome this limitation by proposing training-free solutions, but most can only be applied to a specific category of tasks and not to more general conditions. In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions. Specifically, we leverage off-the-shelf pre-trained networks, such as a face detection model, to construct time-independent energy functions, which guide the generation process without requiring training. Furthermore, because the construction of the energy function is very flexible and adaptable to various conditions, our proposed FreeDoM has a broader range of applications than existing training-free methods. FreeDoM is advantageous in its simplicity, effectiveness, and low cost. Experiments demonstrate that FreeDoM is effective for various conditions and suitable for diffusion models of diverse data domains, including image and latent code domains.

Key facts. Cited by 290 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 46 of its 54 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

46 of 54 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Universal Guidance for Diffusion Models14 Feb
  2. 2022Classifier-Free Diffusion Guidance26 Jul
  3. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations14 Jul
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  5. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  6. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
24 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  4. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  6. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  7. 2022Denoising Diffusion Restoration Modelscited by 951
  8. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  9. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  10. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  11. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  12. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  13. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  14. 2023Zero-shot Image-to-Image Translationcited by 503
  15. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  16. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 386
  17. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  18. 2021Deblurring via Stochastic Refinementcited by 248
  19. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  20. 2022KNN-Diffusion: Image Generation via Large-Scale Retrievalcited by 135
  21. 2021AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generationcited by 25
  22. 2021Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesiscited by 24
  23. 2023Unlimited-Size Diffusion Restorationcited by 15
  24. 2022Combating Mode Collapse in GANs via Manifold Entropy Estimationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 29; 2024: 81; 2025: 109; 2026: 71.

290 papers.

Sort:

By area:

  1. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 293
  2. 2025Improving Video Generation with Human Feedbackcited by 267
  3. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 193
  4. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  5. 2023Manifold Preserving Guided Diffusioncited by 153
  6. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Codecited by 145
  7. 2024Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingcited by 127
  8. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
  9. 2024TFG: Unified Training-Free Guidance for Diffusion Modelscited by 103
  10. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  11. 2025Test-time Alignment of Diffusion Models without Reward Over-optimizationcited by 89
  12. 2024DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editingcited by 88
38 more
  1. 2024Controllable Generation with Text-to-Image Diffusion Models: A Surveycited by 82
  2. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  3. 2024Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Modelcited by 73
  4. 2024Guidance with Spherical Gaussian Constraint for Conditional Diffusioncited by 69
  5. 2024Gradient Guidance for Diffusion Models: An Optimization Perspectivecited by 59
  6. 2024Magic-Me: Identity-Specific Video Customized Diffusioncited by 58
  7. 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Modelcited by 56
  8. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  9. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Modelscited by 52
  10. 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganographycited by 50
  11. 2025Inference-time Scaling of Diffusion Models through Classical Searchcited by 48
  12. 2024Distillation of Discrete Diffusion through Dimensional Correlationscited by 46
  13. 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
  14. 2024ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preservingcited by 42
  15. 2024Diffusion Facial Forgery Detectioncited by 41
  16. 2023ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptationcited by 39
  17. 2024Steering Rectified Flow Models in the Vector Field for Controlled Image Generationcited by 38
  18. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  19. 2024SMooDi: Stylized Motion Diffusion Modelcited by 37
  20. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcingcited by 37
  21. 2025Dynamic Search for Inference-Time Alignment in Diffusion Modelscited by 36
  22. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidancecited by 33
  23. 2023An Image is Worth Multiple Words: Multi-attribute Inversion for Constrained Text-to-Image Synthesiscited by 31
  24. 2024Understanding and Improving Training-free Loss-based Diffusion Guidancecited by 31
  25. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  26. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputscited by 29
  27. 2024Dynamic Negative Guidance of Diffusion Modelscited by 28
  28. 2024DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Schedulingcited by 27
  29. 2023Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scalecited by 26
  30. 2024DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generationcited by 26
  31. 2024Generative Diffusion Models for High Dimensional Channel Estimationcited by 26
  32. 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Mapscited by 26
  33. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  34. 2024Noise Map Guidance: Inversion with Spatial Context for Real Image Editingcited by 25
  35. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 23
  36. 2024Group Diffusion Transformers are Unsupervised Multitask Learnerscited by 22
  37. 2025Variational Control for Guidance in Diffusion Modelscited by 22
  38. 2024Distribution-Aware Data Expansion with Diffusion Modelscited by 20

50 most cited of 290 All 290 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
  2. 2025Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based Perspective
  3. 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression
  4. 2023Conditional Generation from Unconditional Diffusion Models using Denoiser Representations
  5. 2023Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance
  6. 2025Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
  7. 2026Simulation-free and finite-time diffusion model
  8. 2025Capturing Conditional Dependence via Auto-regressive Diffusion Models