mlsanityData to 14 Oct 2026

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

arXiv 2407.02687 ↗First posted 2 Jul 2024cs.LG cs.CVcited by 53

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the training procedure by periodically inserting a null condition. There is also no clear extension of CFG to unconditional models. In this paper, we revisit the core principles of CFG and introduce a new method, independent condition guidance (ICG), which provides the benefits of CFG without the need for any special training procedures. Our approach streamlines the training process of conditional diffusion models and can also be applied during inference on any pre-trained conditional model. Additionally, by leveraging the time-step information encoded in all diffusion networks, we propose an extension of CFG, called time-step guidance (TSG), which can be applied to any diffusion model, including unconditional ones. Our guidance techniques are easy to implement and have the same sampling cost as CFG. Through extensive experiments, we demonstrate that ICG matches the performance of standard CFG across various conditional diffusion models. Moreover, we show that TSG improves generation quality in a manner similar to CFG, without relying on any conditional information.

Key facts. Cited by 53 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 50 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

46 of 50 references.

Closest ancestors · 22

Same direction, newest first

  1. 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance26 Mar
  2. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  3. 2023Manifold Preserving Guided Diffusion28 Nov
  4. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling26 Oct
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  6. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model17 Mar
  7. 2023Universal Guidance for Diffusion Models14 Feb
  8. 2023I2SB: Image-to-Image Schr"odinger Bridge12 Feb
  9. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  10. 2022Scalable Diffusion Models with Transformers19 Dec
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  12. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
10 more
  1. 2022Classifier-Free Diffusion Guidance26 Jul
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  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 · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  11. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
12 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  2. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  3. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  4. 2022Human Motion Diffusion Modelcited by 1,080
  5. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  6. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  8. 2023Photorealistic Video Generation with Diffusion Modelscited by 306
  9. 2022EDGE: Editable Dance Generation From Musiccited by 287
  10. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  11. 2023Noise2Music: Text-conditioned Music Generation with Diffusion Modelscited by 173
  12. 2021Ethics and Creativity in Computer Visioncited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 28; 2026: 19.

53 papers.

Sort:

By area:

  1. 2025Imagine while Reasoning in Space: Multimodal Visualization-of-Thoughtcited by 206
  2. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 114
  3. 2024A Noise is Worth Diffusion Guidancecited by 49
  4. 2024Self-Guidance: Boosting Flow and Diffusion Generation on Their Owncited by 23
  5. 2025TCFG: Tangential Damping Classifier-free Guidancecited by 15
  6. 2025Token Perturbation Guidance for Diffusion Modelscited by 15
  7. 2025SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Scorecited by 14
  8. 2025Learn to Guide Your Diffusion Modelcited by 14
  9. 2025FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Computecited by 12
  10. 2025PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsitycited by 7
  11. 2025Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Modelscited by 7
  12. 2025Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunkingcited by 7
38 more
  1. 2026C2FG: Control Classifier-Free Guidance via Score Discrepancy Analysiscited by 7
  2. 2024Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMscited by 6
  3. 2025Efficient Distillation of Classifier-Free Guidance using Adapterscited by 6
  4. 2025Conditional Diffusion Models with Classifier-Free Gibbs-like Guidancecited by 5
  5. 2025Rethinking Oversaturation in Classifier-Free Guidance via Low Frequencycited by 5
  6. 2025AudioMoG: Guiding Audio Generation with Mixture-of-Guidancecited by 5
  7. 2025Diverse Video Generation with Determinantal Point Process-Guided Policy Optimizationcited by 4
  8. 2025MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matchingcited by 4
  9. 2026ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillationcited by 4
  10. 2025Guidance Free Image Editing via Explicit Conditioningcited by 3
  11. 2025Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attributioncited by 3
  12. 2025HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Modelscited by 3
  13. 2026Guiding a Diffusion Model by Swapping Its Tokenscited by 3
  14. 2024Guiding a diffusion model using sliding windowscited by 2
  15. 2025SPG: Improving Motion Diffusion by Smooth Perturbation Guidancecited by 2
  16. 2025Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generationcited by 2
  17. 2025Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architecturescited by 2
  18. 2026Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measurescited by 2
  19. 2026Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversalcited by 2
  20. 2025Stylized Structural Patterns for Improved Neural Network Pre-trainingcited by 1
  21. 2025Improving Diffusion-Based Image Editing Faithfulness via Guidance and Schedulingcited by 1
  22. 2025Stein Diffusion Guidance: Training-Free Posterior Correction for Sampling Beyond High-Density Regionscited by 1
  23. 2025RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Schedulingcited by 1
  24. 2025Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidancecited by 1
  25. 2026Guiding Token-Sparse Diffusion Modelscited by 1
  26. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidancecited by 1
  27. 2026AMShortcut: An Inference- and Training-Efficient Inverse Design Model for Amorphous Materialscited by 1
  28. 2024Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesiscited by 0
  29. 2025Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variationcited by 0
  30. 2025Guiding Visual Autoregressive Models through Spectrum Weakeningcited by 0
  31. 2026Dynamic Frequency Modulation for Controllable Text-driven Image Generationcited by 0
  32. 2026PureCC: Pure Learning for Text-to-Image Concept Customizationcited by 0
  33. 2026Guiding Diffusion Models with Semantically Degraded Conditionscited by 0
  34. 2026Not all tokens contribute equally to diffusion learningcited by 0
  35. 2026Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learningcited by 0
  36. 2026Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolutioncited by 0
  37. 2026Probability-Conserving Flow Guidancecited by 0
  38. 2026Adversarial Learning of Classifier-Free Guidance Schedulescited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024TFG: Unified Training-Free Guidance for Diffusion Models
  2. 2026Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models
  3. 2025Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
  4. 2025Diffusion Models without Classifier-free Guidance
  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. 2024Rectified Diffusion Guidance for Conditional Generation
  8. 2023Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models