Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

• URL: http://arxiv.org/abs/2504.17789v2
• Date: Sun, 27 Apr 2025 23:01:22 GMT
• Title: Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models
• Authors: Xu Ma, Peize Sun, Haoyu Ma, Hao Tang, Chih-Yao Ma, Jialiang Wang, Kunpeng Li, Xiaoliang Dai, Yujun Shi, Xuan Ju, Yushi Hu, Artsiom Sanakoyeu, Felix Juefei-Xu, Ji Hou, Junjiao Tian, Tao Xu, Tingbo Hou, Yen-Cheng Liu, Zecheng He, Zijian He, Matt Feiszli, Peizhao Zhang, Peter Vajda, Sam Tsai, Yun Fu,
• Abstract summary: Token-Shuffle is a novel method that reduces the number of image tokens in Transformer.<n>Our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis.<n>In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15.
• Score: 92.18057318458528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image tokens required for AR models, which constrains both training and inference efficiency, as well as image resolution. To address this, we present Token-Shuffle, a novel yet simple method that reduces the number of image tokens in Transformer. Our key insight is the dimensional redundancy of visual vocabularies in Multimodal Large Language Models (MLLMs), where low-dimensional visual codes from visual encoder are directly mapped to high-dimensional language vocabularies. Leveraging this, we consider two key operations: token-shuffle, which merges spatially local tokens along channel dimension to decrease the input token number, and token-unshuffle, which untangles the inferred tokens after Transformer blocks to restore the spatial arrangement for output. Jointly training with textual prompts, our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis in a unified next-token prediction way while maintaining efficient training and inference. For the first time, we push the boundary of AR text-to-image generation to a resolution of 2048x2048 with gratifying generation performance. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15. Exhaustive large-scale human evaluations also demonstrate our prominent image generation ability in terms of text-alignment, visual flaw, and visual appearance. We hope that Token-Shuffle can serve as a foundational design for efficient high-resolution image generation within MLLMs.

Related papers

• Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens [66.02261367232256]
  Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation.<n>Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order.<n>In this paper, we build a proper visual language by reconstructing diffusion timesteps to learn discrete visual tokens.
  arXiv  Detail & Related papers  (2025-04-20T16:14:28Z)
• Frequency Autoregressive Image Generation with Continuous Tokens [31.833852108014312]
  We introduce the frequency progressive autoregressive (textbfFAR) paradigm and instantiate FAR with the continuous tokenizer.<n>We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset.
  arXiv  Detail & Related papers  (2025-03-07T10:34:04Z)
• FlexTok: Resampling Images into 1D Token Sequences of Flexible Length [16.76602756308683]
  We introduce FlexTok, a tokenizer that projects 2D images into variable-length, ordered 1D token sequences.<n>We evaluate our approach in an autoregressive generation setting using a simple GPT-style Transformer.
  arXiv  Detail & Related papers  (2025-02-19T18:59:44Z)
• Efficient Multi-modal Large Language Models via Visual Token Grouping [55.482198808206284]
  High-resolution images and videos pose a barrier to their broader adoption.<n> compressing vision tokens in MLLMs has emerged as a promising approach to reduce inference costs.<n>We introduce VisToG, a novel grouping mechanism that leverages the capabilities of pre-trained vision encoders to group similar image segments.
  arXiv  Detail & Related papers  (2024-11-26T09:36:02Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.57727062920458]
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.<n>We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers.<n>Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
  We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. Our model is capable of processing images with resolutions up to $1008times 1008$.
  arXiv  Detail & Related papers  (2024-08-30T03:16:49Z)
• Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation [122.63617171522316]
  Large Language Models (LLMs) are the dominant models for generative tasks in language. We introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images.
  arXiv  Detail & Related papers  (2023-10-09T14:10:29Z)
• PuMer: Pruning and Merging Tokens for Efficient Vision Language Models [41.81484883647005]
  PuMer is a framework that uses text-informed Pruning and modality-aware Merging strategies to progressively reduce the tokens of input image and text. PuMer inference increases throughput by up to 2x and reduces memory footprint by over 50% while incurring less than a 1% accuracy drop.
  arXiv  Detail & Related papers  (2023-05-27T17:16:27Z)
• Scaling Autoregressive Models for Content-Rich Text-to-Image Generation [95.02406834386814]
  Parti treats text-to-image generation as a sequence-to-sequence modeling problem. Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens. PartiPrompts (P2) is a new holistic benchmark of over 1600 English prompts.
  arXiv  Detail & Related papers  (2022-06-22T01:11:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.