mlsanityData to 7 Oct 2026

Classifier-Free Diffusion Guidance

arXiv 2207.12598 ↗First posted 26 Jul 2022cs.LG cs.AIcited by 5,717

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call classifier-free guidance, we jointly train a conditional and an unconditional diffusion model, and we combine the resulting conditional and unconditional score estimates to attain a trade-off between sample quality and diversity similar to that obtained using classifier guidance.

Key facts. Cited by 5,717 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 17 of its 25 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

17 of 25 references.

Closest ancestors · 7

Same direction, newest first

  1. 2021Variational Diffusion Models1 Jul
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 10

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  10. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 157; 2023: 953; 2024: 1524; 2025: 1694; 2026: 1389.

5,717 papers.

Sort:

By area:

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  6. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  10. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
38 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  2. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  3. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  4. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  5. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  6. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  7. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  8. 2022Human Motion Diffusion Modelcited by 1,062
  9. 2022Diffusion Models in Vision: A Surveycited by 1,008
  10. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  11. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  12. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  13. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  14. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  15. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  16. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  17. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  18. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  19. 2025Large Language Diffusion Modelscited by 872
  20. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  21. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  22. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  23. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  24. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  25. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  26. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  27. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  28. 2023Adversarial Diffusion Distillationcited by 741
  29. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  30. 2022On Distillation of Guided Diffusion Modelscited by 721
  31. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 712
  32. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  33. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  34. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  35. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
  36. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 666
  37. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  38. 2023ModelScope Text-to-Video Technical Reportcited by 651

50 most cited of 5,717 All 5,717 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards a unified framework for guided diffusion models
  2. 2026Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling
  3. 2025Classifier-free Guidance with Adaptive Scaling
  4. 2025Towards Understanding the Mechanisms of Classifier-Free Guidance
  5. 2025Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
  6. 2026MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
  7. 2025How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models