# A Pytorch Reproduction of Masked Generative Image Transformer

arXiv: https://arxiv.org/abs/2310.14400 · HTML: https://mlsanity.com/paper/2310.14400/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 16 references that are in the map.
- First posted on arXiv 22 Oct 2023.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [Improved Masked Image Generation with Token-Critic](https://mlsanity.com/paper/2209.04439/) (2022)
- [Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models](https://mlsanity.com/paper/2304.01515/) (2023)

## Built on by (most cited first, 25 of 25)

- [Discrete Flow Matching](https://mlsanity.com/paper/2407.15595/) (2024)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [MaskBit: Embedding-free Image Generation via Bit Tokens](https://mlsanity.com/paper/2409.16211/) (2024)
- [EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling](https://mlsanity.com/paper/2502.09509/) (2025)
- [Distillation of Discrete Diffusion through Dimensional Correlations](https://mlsanity.com/paper/2410.08709/) (2024)
- [Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms](https://mlsanity.com/paper/2502.00234/) (2025)
- [DINO-Foresight: Looking into the Future with DINO](https://mlsanity.com/paper/2412.11673/) (2024)
- [Halton Scheduler For Masked Generative Image Transformer](https://mlsanity.com/paper/2503.17076/) (2025)
- [Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity](https://mlsanity.com/paper/2407.10387/) (2024)
- [ReDi: Rectified Discrete Flow](https://mlsanity.com/paper/2507.15897/) (2025)
- [[MASK] is All You Need](https://mlsanity.com/paper/2412.06787/) (2024)
- [Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion](https://mlsanity.com/paper/2510.04525/) (2025)
- [Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation](https://mlsanity.com/paper/2507.13032/) (2025)
- [Autoregressive Image Generation with Masked Bit Modeling](https://mlsanity.com/paper/2602.09024/) (2026)
- [Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers](https://mlsanity.com/paper/2501.08303/) (2025)
- [Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings](https://mlsanity.com/paper/2509.22925/) (2025)
- [Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion](https://mlsanity.com/paper/2410.14758/) (2024)
- [Dimathtt[M]O: Distilling Masked Diffusion Models into One-step Generator](https://mlsanity.com/paper/2503.15457/) (2025)
- [Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling](https://mlsanity.com/paper/2607.00773/) (2026)
- [AdaGen: Learning Adaptive Policy for Image Synthesis](https://mlsanity.com/paper/2603.06993/) (2026)
- [Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction](https://mlsanity.com/paper/2604.11707/) (2026)
- [One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration](https://mlsanity.com/paper/2605.21484/) (2026)
- [Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion](https://mlsanity.com/paper/2606.18250/) (2026)
- [BIGFix: Bidirectional Image Generation with Token Fixing](https://mlsanity.com/paper/2510.12231/) (2025)
- [Accelerating Masked Image Generation by Learning Controlled Latent Dynamics](https://mlsanity.com/paper/2602.23996/) (2026)

## Abstract (arXiv)

In this technical report, we present a reproduction of MaskGIT: Masked Generative Image Transformer, using PyTorch. The approach involves leveraging a masked bidirectional transformer architecture, enabling image generation with only few steps (8~16 steps) for 512 x 512 resolution images, i.e., ~64x faster than an auto-regressive approach. Through rigorous experimentation and optimization, we achieved results that closely align with the findings presented in the original paper. We match the reported FID of 7.32 with our replication and obtain 7.59 with similar hyperparameters on ImageNet at resolution 512 x 512. Moreover, we improve over the official implementation with some minor hyperparameter tweaking, achieving FID of 7.26. At the lower resolution of 256 x 256 pixels, our reimplementation scores 6.80, in comparison to the original paper's 6.18. To promote further research on Masked Generative Models and facilitate their reproducibility, we released our code and pre-trained weights openly at https://github.com/valeoai/MaskGIT-pytorch/