mlsanityData to 7 Oct 2026

Diffusion Models without Classifier-free Guidance

arXiv 2502.12154 ↗First posted 17 Feb 2025cs.CV cs.AI cs.LGcited by 28

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data distribution to incorporating the posterior probability of conditions. The proposed technique originates from the idea of CFG and is easy yet effective, making it a plug-and-play module for existing models. Our method significantly accelerates the training process, doubles the inference speed, and achieve exceptional quality that parallel and even surpass concurrent diffusion models with CFG. Extensive experiments demonstrate the effectiveness, efficiency, scalability on different models and datasets. Finally, we establish state-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34. Our code is available at https://github.com/tzco/Diffusion-wo-CFG.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 47 of its 54 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

47 of 54 references.

Closest ancestors · 23

Same direction, newest first

  1. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models2 Jan
  2. 2024One Step Diffusion via Shortcut Models16 Oct
  3. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think9 Oct
  4. 2024Guiding a Diffusion Model with a Bad Version of Itself4 Jun
  5. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
  6. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation18 Mar
  7. 2023Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale11 Dec
  8. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  10. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer25 Mar
  11. 2023Consistency Models2 Mar
  12. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
11 more
  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2022On Distillation of Guided Diffusion Models6 Oct
  3. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
  4. 2022Classifier-Free Diffusion Guidance26 Jul
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  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 · 24

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2016Improved Techniques for Training GANscited by 2,938
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2022Video Diffusion Modelscited by 2,280
12 more
  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  2. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  3. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  4. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  6. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  7. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  8. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  9. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  10. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  11. 2021Generating Images with Sparse Representationscited by 262
  12. 2024Randomized Autoregressive Visual Generationcited by 125

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 11.

28 papers.

Sort:

By area:

  1. 2025Improved Mean Flows: On the Challenges of Fastforward Generative Modelscited by 102
  2. 2025Transition Models: Rethinking the Generative Learning Objectivecited by 32
  3. 2026Meta Flow Maps enable scalable reward alignmentcited by 32
  4. 2026ELF: Embedded Language Flowscited by 27
  5. 2026Discrete Flow Mapscited by 23
  6. 2025Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecastingcited by 19
  7. 2025Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Samplingcited by 19
  8. 2025Learn to Guide Your Diffusion Modelcited by 12
  9. 2025Guiding a Diffusion Transformer with the Internal Dynamics of Itselfcited by 12
  10. 2025Bidirectional Normalizing Flow: From Data to Noise and Backcited by 7
  11. 2026Variational Flow Maps: Make Some Noise for One-Step Conditional Generationcited by 5
  12. 2025DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Modelscited by 4
16 more
  1. 2025Selective Classifier-free Guidance for Zero-shot Text-to-speechcited by 4
  2. 2025Guided Diffusion for the Discovery of New Superconductorscited by 4
  3. 2025MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matchingcited by 4
  4. 2025Exploring the flavor structure of leptons via diffusion modelscited by 3
  5. 2025A Minimalist Method for Fine-tuning Text-to-Image Diffusion Modelscited by 3
  6. 2026CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalizationcited by 3
  7. 2025Towards Flow-Matching-based TTS without Classifier-Free Guidancecited by 2
  8. 2025SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Modelcited by 2
  9. 2026A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformerscited by 2
  10. 2026DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolutioncited by 1
  11. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidancecited by 1
  12. 2025TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidancecited by 0
  13. 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generationcited by 0
  14. 2026Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesiscited by 0
  15. 2026Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolutioncited by 0
  16. 2026Continuous Adversarial MeanFlow Transfercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
  2. 2026Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models
  3. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
  4. 2025Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
  5. 2025Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
  6. 2023Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
  7. 2025Feedback Guidance of Diffusion Models
  8. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models