mlsanityData to 14 Oct 2026

PixelFlow: Pixel-Space Generative Models with Flow

arXiv 2504.07963 ↗First posted 10 Apr 2025cs.CVcited by 97

Not on the map. Why?

Cited by 68 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256×256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow.

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). Builds on 59 of its 70 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

59 of 70 references.

References · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2022Flow Matching for Generative Modelingcited by 5,702
  11. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
38 more
  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  2. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  3. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  8. 2016Improved Techniques for Training GANscited by 2,970
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  12. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  13. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  14. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  15. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  16. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  17. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  18. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  19. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  20. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  21. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  22. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  23. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  24. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422
  25. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  26. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 304
  27. 2021Generating Images with Sparse Representationscited by 266
  28. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 254
  29. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  30. 2022Scalable Adaptive Computation for Iterative Generationcited by 195
  31. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 194
  32. 2024Fast Timing-Conditioned Latent Audio Diffusioncited by 181
  33. 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Acceleratorcited by 97
  34. 2024Normalizing Flows are Capable Generative Modelscited by 91
  35. 2023GenTron: Diffusion Transformers for Image and Video Generationcited by 82
  36. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesiscited by 79
  37. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusioncited by 75
  38. 2023Matryoshka Diffusion Modelscited by 72

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 19; 2026: 78.

97 papers.

Sort:

By area:

  1. 2025Diffusion Transformers with Representation Autoencoderscited by 295
  2. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 84
  3. 2025PixelDiT: Pixel Diffusion Transformers for Image Generationcited by 83
  4. 2025PixNerd: Pixel Neural Field Diffusioncited by 82
  5. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 60
  6. 2026One-step Latent-free Image Generation with Pixel Mean Flowscited by 53
  7. 2025DiP: Taming Diffusion Models in Pixel Spacecited by 48
  8. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  9. 2025There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-trainingcited by 24
  10. 2025FARMER: Flow AutoRegressive Transformer over Pixelscited by 18
  11. 2025Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusioncited by 18
  12. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 18
38 more
  1. 2025Guiding a Diffusion Transformer with the Internal Dynamics of Itselfcited by 16
  2. 2026PixelGen: Improving Pixel Diffusion with Perceptual Supervisioncited by 14
  3. 2026Representation Alignment for Just Image Transformers is not Easier than You Thinkcited by 14
  4. 2026Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoderscited by 13
  5. 2026Improving Reconstruction of Representation Autoencodercited by 9
  6. 2026L2P: Unlocking Latent Potential for Pixel Generationcited by 9
  7. 2026HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusioncited by 9
  8. 2026Asymmetric Flow Modelscited by 8
  9. 2026PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusioncited by 8
  10. 2025Stochastic Interpolants via Conditional Dependent Couplingcited by 7
  11. 2025SimFlow: Simplified and End-to-End Training of Latent Normalizing Flowscited by 7
  12. 2026Revisiting Diffusion Model Predictions Through Dimensionalitycited by 7
  13. 2026Laminating Representation Autoencoders for Efficient Diffusioncited by 7
  14. 2026SenseNova-U1.5: Towards Native Unified Visual Intelligencecited by 7
  15. 2025Trainable Log-linear Sparse Attention for Efficient Diffusion Transformerscited by 6
  16. 2026End-to-End Training for Unified Tokenization and Latent Denoisingcited by 6
  17. 2026An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Modelscited by 6
  18. 2026Spectrally-Guided Diffusion Noise Schedulescited by 5
  19. 2026Continuous Adversarial Flow Modelscited by 5
  20. 2025Pyramidal Patchification Flow for Visual Generationcited by 4
  21. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulationcited by 4
  22. 2025RecTok: Reconstruction Distillation along Rectified Flowcited by 4
  23. 2026DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformerscited by 4
  24. 2026Scale Space Diffusioncited by 4
  25. 2026MotionHiFlow: Text-to-motion via hierarchical flow matchingcited by 4
  26. 2026FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusioncited by 4
  27. 2026Representation Forcing for Bottleneck-Free Unified Multimodal Modelscited by 4
  28. 2026UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformercited by 4
  29. 2026PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Spacecited by 4
  30. 2026FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generationcited by 3
  31. 2026WaiT for the Signal: Simple Frequency-Aware Flow-Matchingcited by 3
  32. 2026Eliminating VAE for Fast and High-Resolution Generative Detail Restorationcited by 2
  33. 2026Geometric Autoencoder for Diffusion Modelscited by 2
  34. 2026V-Co: A Closer Look at Visual Representation Alignment via Co-Denoisingcited by 2
  35. 2026Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstructioncited by 2
  36. 2026Registers Matter for Pixel-Space Diffusion Transformerscited by 2
  37. 2026WavFlow: Audio Generation in Waveform Spacecited by 2
  38. 2026RiT: Vanilla Diffusion Transformers Suffice in Representation Spacecited by 2

50 most cited of 97 All 97 (JSON)