mlsanityData to 7 Oct 2026

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling

arXiv 2310.17347 ↗First posted 26 Oct 2023cs.CVcited by 124

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optimal image quality or when trained on small datasets. We attribute this problem to the role of the conditioning signal in inference and offer an improved sampling strategy for diffusion models that can increase generation diversity, especially at high guidance scales, with minimal loss of sample quality. Our sampling strategy anneals the conditioning signal by adding scheduled, monotonically decreasing Gaussian noise to the conditioning vector during inference to balance diversity and condition alignment. Our Condition-Annealed Diffusion Sampler (CADS) can be used with any pretrained model and sampling algorithm, and we show that it boosts the diversity of diffusion models in various conditional generation tasks. Further, using an existing pretrained diffusion model, CADS achieves a new state-of-the-art FID of 1.70 and 2.31 for class-conditional ImageNet generation at 256×256 and 512×512 respectively.

Key facts. Cited by 124 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 48 of its 52 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

48 of 52 references.

Closest ancestors · 23

Same direction, newest first

  1. 2023Understanding and Mitigating Copying in Diffusion Models31 May
  2. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer25 Mar
  3. 2023I2SB: Image-to-Image Schr"odinger Bridge12 Feb
  4. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
  5. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  6. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  7. 2022Scalable Diffusion Models with Transformers19 Dec
  8. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models28 Nov
  9. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  10. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications2 Sep
  12. 2022Classifier-Free Diffusion Guidance26 Jul
11 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  3. 2022Generating High Fidelity Data from Low-density Regions using Diffusion Models31 Mar
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Implicit Models6 Oct
  11. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 25

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
13 more
  1. 2022Human Motion Diffusion Modelcited by 1,062
  2. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  3. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  4. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  5. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  6. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  7. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 299
  8. 2022EDGE: Editable Dance Generation From Musiccited by 284
  9. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  10. 2023Noise2Music: Text-conditioned Music Generation with Diffusion Modelscited by 173
  11. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143
  12. 2023Controllable Inversion of Black-Box Face Recognition Models via Diffusioncited by 22
  13. 2021Ethics and Creativity in Computer Visioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 30; 2025: 55; 2026: 39.

124 papers.

Sort:

By area:

  1. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  2. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 240
  3. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 107
  4. 2024Faster Diffusion via Temporal Attention Decompositioncited by 54
  5. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Modelscited by 52
  6. 2024A Noise is Worth Diffusion Guidancecited by 48
  7. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 35
  8. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  9. 2025Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewardscited by 29
  10. 2024LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Modelscited by 22
  11. 2024Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusioncited by 22
  12. 2024Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellencycited by 21
38 more
  1. 2024Self-Guided Generation of Minority Samples Using Diffusion Modelscited by 19
  2. 2025Training-Free Safe Denoisers for Safe Use of Diffusion Modelscited by 19
  3. 2024Minority-Focused Text-to-Image Generation via Prompt Optimizationcited by 18
  4. 2024Heavy-Tailed Diffusion with Denoising L'evy Probabilistic Modelscited by 16
  5. 2025Feedback Guidance of Diffusion Modelscited by 16
  6. 2024Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Stepscited by 14
  7. 2025CoDe: Blockwise Control for Denoising Diffusion Modelscited by 14
  8. 2025Token Perturbation Guidance for Diffusion Modelscited by 14
  9. 2025SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Scorecited by 14
  10. 2025Rectified-CFG++ for Flow Based Modelscited by 14
  11. 2024Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modelingcited by 13
  12. 2025Effective and Efficient Masked Image Generation Modelscited by 13
  13. 2025Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scalescited by 13
  14. 2024A Diffusion-Based Generative Equalizer for Music Restorationcited by 12
  15. 2024ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generationcited by 12
  16. 2025Provable Maximum Entropy Manifold Exploration via Diffusion Modelscited by 12
  17. 2025Learn to Guide Your Diffusion Modelcited by 12
  18. 2025Guiding a Diffusion Transformer with the Internal Dynamics of Itselfcited by 12
  19. 2024Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modelingcited by 11
  20. 2025Entropy Rectifying Guidance for Diffusion and Flow Modelscited by 11
  21. 2025Navigating with Annealing Guidance Scale in Diffusion Spacecited by 11
  22. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedbackcited by 11
  23. 2025Diverse Text-to-Image Generation via Contrastive Noise Optimizationcited by 10
  24. 2024TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Modelscited by 9
  25. 2025It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Modelscited by 9
  26. 2024Robust Guided Diffusion for Offline Black-Box Optimizationcited by 8
  27. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  28. 2024Few-Shot Image Generation by Conditional Relaxing Diffusion Inversioncited by 7
  29. 2025Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinementcited by 7
  30. 2024Diffusion Bridge AutoEncoders for Unsupervised Representation Learningcited by 6
  31. 2024GeoGuide: Geometric guidance of diffusion modelscited by 6
  32. 2025DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Imagecited by 6
  33. 2025SIME: Enhancing Policy Self-Improvement with Modal-level Explorationcited by 6
  34. 2025Increasing the Utility of Synthetic Images through Chamfer Guidancecited by 6
  35. 2025The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Modelscited by 6
  36. 2025FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Modelscited by 6
  37. 2026Verifier-Constrained Flow Expansion for Discovery Beyond the Datacited by 6
  38. 2024Rethinking cluster-conditioned diffusion models for label-free image synthesiscited by 5

50 most cited of 124 All 124 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024A Simple Approach to Unifying Diffusion-based Conditional Generation
  2. 2024Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
  3. 2026A Plug-in Interpretation of Conditioning in Score-Based Diffusion Models
  4. 2026Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling
  5. 2023Conditional Generation from Unconditional Diffusion Models using Denoiser Representations
  6. 2022On Distillation of Guided Diffusion Models
  7. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
  8. 2022On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models