# HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

arXiv: https://arxiv.org/abs/2410.10812 · HTML: https://mlsanity.com/paper/2410.10812/

## Key facts

- Cited by 132 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 66 of its 76 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 66)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)

## Built on by (most cited first, 30 of 132)

- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [Taming Rectified Flow for Inversion and Editing](https://mlsanity.com/paper/2411.04746/) (2024)
- [TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation](https://mlsanity.com/paper/2412.03069/) (2024)
- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025)
- [Randomized Autoregressive Visual Generation](https://mlsanity.com/paper/2411.00776/) (2024)
- [Lumina-Image 2.0: A Unified and Efficient Image Generative Framework](https://mlsanity.com/paper/2503.21758/) (2025)
- [DPLM-2: A Multimodal Diffusion Protein Language Model](https://mlsanity.com/paper/2410.13782/) (2024)
- [Fractal Generative Models](https://mlsanity.com/paper/2502.17437/) (2025)
- [Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads](https://mlsanity.com/paper/2412.00127/) (2024)
- [VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model](https://mlsanity.com/paper/2501.12327/) (2025)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [PAN: A World Model for General, Actionable, and Long-Horizon World Simulation](https://mlsanity.com/paper/2511.09057/) (2025)
- [FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning](https://mlsanity.com/paper/2503.23367/) (2025)
- [Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient](https://mlsanity.com/paper/2411.17787/) (2024)
- [Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis](https://mlsanity.com/paper/2412.01819/) (2024)
- [Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning](https://mlsanity.com/paper/2505.07538/) (2025)
- [LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning](https://mlsanity.com/paper/2510.04573/) (2025)
- [Next Patch Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2412.15321/) (2024)
- [LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs](https://mlsanity.com/paper/2504.08358/) (2025)
- [FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction](https://mlsanity.com/paper/2502.20313/) (2025)
- [Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning](https://mlsanity.com/paper/2508.21048/) (2025)
- [Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression](https://mlsanity.com/paper/2505.19602/) (2025)
- [Training-Free Text-Guided Image Editing with Visual Autoregressive Model](https://mlsanity.com/paper/2503.23897/) (2025)
- [VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning](https://mlsanity.com/paper/2504.02949/) (2025)
- [HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation](https://mlsanity.com/paper/2506.04421/) (2025)
- [Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model](https://mlsanity.com/paper/2506.05289/) (2025)
- [Continuous Speculative Decoding for Autoregressive Image Generation](https://mlsanity.com/paper/2411.11925/) (2024)
- [PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models](https://mlsanity.com/paper/2503.10127/) (2025)
- [SCALAR: Scale-wise Controllable Visual Autoregressive Learning](https://mlsanity.com/paper/2507.19946/) (2025)
- [Visual Generation Without Guidance](https://mlsanity.com/paper/2501.15420/) (2025)

## Abstract (arXiv)

We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face limitations due to the poor image reconstruction quality of their discrete tokenizers and the prohibitive training costs associated with generating 1024px images. To address these challenges, we present the hybrid tokenizer, which decomposes the continuous latents from the autoencoder into two components: discrete tokens representing the big picture and continuous tokens representing the residual components that cannot be represented by the discrete tokens. The discrete component is modeled by a scalable-resolution discrete AR model, while the continuous component is learned with a lightweight residual diffusion module with only 37M parameters. Compared with the discrete-only VAR tokenizer, our hybrid approach improves reconstruction FID from 2.11 to 0.30 on MJHQ-30K, leading to a 31% generation FID improvement from 7.85 to 5.38. HART also outperforms state-of-the-art diffusion models in both FID and CLIP score, with 4.5-7.7x higher throughput and 6.9-13.4x lower MACs. Our code is open sourced at https://github.com/mit-han-lab/hart.