# FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution

arXiv: https://arxiv.org/abs/2410.22655 · HTML: https://mlsanity.com/paper/2410.22655/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (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)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models](https://mlsanity.com/paper/2310.07702/) (2023)
- [FiT: Flexible Vision Transformer for Diffusion Model](https://mlsanity.com/paper/2402.12376/) (2024)

## Built on by (most cited first, 16 of 16)

- [DDT: Decoupled Diffusion Transformer](https://mlsanity.com/paper/2504.05741/) (2025)
- [DiP: Taming Diffusion Models in Pixel Space](https://mlsanity.com/paper/2511.18822/) (2025)
- [Selective Underfitting in Diffusion Models](https://mlsanity.com/paper/2510.01378/) (2025)
- [Native-Resolution Image Synthesis](https://mlsanity.com/paper/2506.03131/) (2025)
- [Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation](https://mlsanity.com/paper/2510.08994/) (2025)
- [B'ezierFlow: Learning B'ezier Stochastic Interpolant Schedulers for Few-Step Generation](https://mlsanity.com/paper/2512.13255/) (2025)
- [DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling](https://mlsanity.com/paper/2505.11196/) (2025)
- [Differentiable Solver Search for Fast Diffusion Sampling](https://mlsanity.com/paper/2505.21114/) (2025)
- [Improved Training Technique for Shortcut Models](https://mlsanity.com/paper/2510.21250/) (2025)
- [UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer](https://mlsanity.com/paper/2606.16255/) (2026)
- [Fast and Accurate Image Restoration and Generation with Rank Enhanced Linear Attention](https://mlsanity.com/paper/2505.16157/) (2025)
- [Adaptive 1D Video Diffusion Autoencoder](https://mlsanity.com/paper/2602.04220/) (2026)
- [Prior-Guided DETR for Ultrasound Nodule Detection](https://mlsanity.com/paper/2601.02212/) (2026)
- [RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations](https://mlsanity.com/paper/2605.15908/) (2026)
- [I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation](https://mlsanity.com/paper/2609.27963/) (2026)
- [Co-Evolving Paths and Flows via Path-Flow Alignment](https://mlsanity.com/paper/2610.08717/) (2026)

## Abstract (arXiv)

Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality. Existing transformer-based diffusion methods suffer from quadratic computation cost and limited resolution extrapolation capabilities, making them less effective for this task. In this paper, we propose FlowDCN, a purely convolution-based generative model with linear time and memory complexity, that can efficiently generate high-quality images at arbitrary resolutions. Equipped with a new design of learnable group-wise deformable convolution block, our FlowDCN yields higher flexibility and capability to handle different resolutions with a single model. FlowDCN achieves the state-of-the-art 4.30 sFID on 256×256 ImageNet Benchmark and comparable resolution extrapolation results, surpassing transformer-based counterparts in terms of convergence speed (only frac15 images), visual quality, parameters (8% reduction) and FLOPs (20% reduction). We believe FlowDCN offers a promising solution to scalable and flexible image synthesis.