# FiT: Flexible Vision Transformer for Diffusion Model

arXiv: https://arxiv.org/abs/2402.12376 · HTML: https://mlsanity.com/paper/2402.12376/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 38 of its 45 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [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)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [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)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [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)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [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)

## Built on by (most cited first, 30 of 85)

- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining](https://mlsanity.com/paper/2408.02657/) (2024)
- [Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT](https://mlsanity.com/paper/2406.18583/) (2024)
- [DDT: Decoupled Diffusion Transformer](https://mlsanity.com/paper/2504.05741/) (2025)
- [PixNerd: Pixel Neural Field Diffusion](https://mlsanity.com/paper/2507.23268/) (2025)
- [GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control](https://mlsanity.com/paper/2412.11198/) (2024)
- [RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers](https://mlsanity.com/paper/2502.15894/) (2025)
- [FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.12963/) (2024)
- [Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis](https://mlsanity.com/paper/2410.08261/) (2024)
- [U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers](https://mlsanity.com/paper/2405.02730/) (2024)
- [Mitigating Object Hallucination via Concentric Causal Attention](https://mlsanity.com/paper/2410.15926/) (2024)
- [Scaling Laws For Diffusion Transformers](https://mlsanity.com/paper/2410.08184/) (2024)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [A Survey on Long Video Generation: Challenges, Methods, and Prospects](https://mlsanity.com/paper/2403.16407/) (2024)
- [Mind the Time: Temporally-Controlled Multi-Event Video Generation](https://mlsanity.com/paper/2412.05263/) (2024)
- [Walrus: A Cross-Domain Foundation Model for Continuum Dynamics](https://mlsanity.com/paper/2511.15684/) (2025)
- [U-REPA: Aligning Diffusion U-Nets to ViTs](https://mlsanity.com/paper/2503.18414/) (2025)
- [VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks](https://mlsanity.com/paper/2403.00522/) (2024)
- [Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators](https://mlsanity.com/paper/2408.05710/) (2024)
- [I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow](https://mlsanity.com/paper/2410.07536/) (2024)
- [HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving](https://mlsanity.com/paper/2412.01407/) (2024)
- [ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance](https://mlsanity.com/paper/2406.16476/) (2024)
- [Effective Diffusion Transformer Architecture for Image Super-Resolution](https://mlsanity.com/paper/2409.19589/) (2024)
- [FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution](https://mlsanity.com/paper/2410.22655/) (2024)
- [TVG: A Training-free Transition Video Generation Method with Diffusion Models](https://mlsanity.com/paper/2408.13413/) (2024)
- [HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts](https://mlsanity.com/paper/2409.02919/) (2024)

## Abstract (arXiv)

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. This perspective enables a flexible training strategy that effortlessly adapts to diverse aspect ratios during both training and inference phases, thus promoting resolution generalization and eliminating biases induced by image cropping. Enhanced by a meticulously adjusted network structure and the integration of training-free extrapolation techniques, FiT exhibits remarkable flexibility in resolution extrapolation generation. Comprehensive experiments demonstrate the exceptional performance of FiT across a broad range of resolutions, showcasing its effectiveness both within and beyond its training resolution distribution. Repository available at https://github.com/whlzy/FiT.