# DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

arXiv: https://arxiv.org/abs/2511.19365 · HTML: https://mlsanity.com/paper/2511.19365/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 69 of its 81 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 69)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)

## Built on by (most cited first, 30 of 60)

- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [One-step Latent-free Image Generation with Pixel Mean Flows](https://mlsanity.com/paper/2601.22158/) (2026)
- [PixelGen: Improving Pixel Diffusion with Perceptual Supervision](https://mlsanity.com/paper/2602.02493/) (2026)
- [L2P: Unlocking Latent Potential for Pixel Generation](https://mlsanity.com/paper/2605.12013/) (2026)
- [HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion](https://mlsanity.com/paper/2605.15741/) (2026)
- [EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture](https://mlsanity.com/paper/2512.04810/) (2025)
- [Asymmetric Flow Models](https://mlsanity.com/paper/2605.12964/) (2026)
- [PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion](https://mlsanity.com/paper/2606.27760/) (2026)
- [CoD-Lite: Real-Time Diffusion-Based Generative Image Compression](https://mlsanity.com/paper/2604.12525/) (2026)
- [An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models](https://mlsanity.com/paper/2608.16887/) (2026)
- [FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion](https://mlsanity.com/paper/2605.17759/) (2026)
- [PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space](https://mlsanity.com/paper/2607.05373/) (2026)
- [FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation](https://mlsanity.com/paper/2605.06421/) (2026)
- [Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space](https://mlsanity.com/paper/2605.08250/) (2026)
- [V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising](https://mlsanity.com/paper/2603.16792/) (2026)
- [Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories](https://mlsanity.com/paper/2606.22527/) (2026)
- [PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation](https://mlsanity.com/paper/2607.01803/) (2026)
- [SPEED: One-Step Pixel Diffusion for High-quality Video Frame Interpolation](https://mlsanity.com/paper/2607.15585/) (2026)
- [A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples](https://mlsanity.com/paper/2607.29122/) (2026)
- [GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling](https://mlsanity.com/paper/2608.29335/) (2026)
- [Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion](https://mlsanity.com/paper/2609.36014/) (2026)
- [RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model](https://mlsanity.com/paper/2512.12083/) (2025)
- [WiT: Waypoint Diffusion Transformers for Alleviating Trajectory Conflict in Pixel-Space Image Generation](https://mlsanity.com/paper/2603.15132/) (2026)
- [SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotyping](https://mlsanity.com/paper/2603.27519/) (2026)
- [PixIE: Prompted Pixel-Space Low-Light Image Enhancement](https://mlsanity.com/paper/2605.23531/) (2026)
- [WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling](https://mlsanity.com/paper/2606.03455/) (2026)
- [BareWave: Waveform-Native Flow-Matching Text-to-Speech](https://mlsanity.com/paper/2606.09048/) (2026)
- [Pixel-Space Diffusion Transformers](https://mlsanity.com/paper/2607.17585/) (2026)
- [DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer](https://mlsanity.com/paper/2607.18510/) (2026)
- [Generative Video Compression with Adaptive Score Distillation](https://mlsanity.com/paper/2607.22772/) (2026)

## Abstract (arXiv)

Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both high-frequency signals and low-frequency semantics within a single diffusion transformer (DiT). To pursue a more efficient pixel diffusion paradigm, we propose the frequency-DeCoupled pixel diffusion framework. With the intuition to decouple the generation of high and low frequency components, we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance from the DiT. This thus frees the DiT to specialize in modeling low-frequency semantics. In addition, we introduce a frequency-aware flow-matching loss that emphasizes visually salient frequencies while suppressing insignificant ones. Extensive experiments show that DeCo achieves superior performance among pixel diffusion models, attaining FID of 1.62 (256x256) and 2.22 (512x512) on ImageNet, closing the gap with latent diffusion methods. Furthermore, our pretrained text-to-image model achieves a leading overall score of 0.86 on GenEval in system-level comparison. Codes are publicly available at https://github.com/Zehong-Ma/DeCo.