Related papers: Infinity: Scaling Bitwise AutoRegressive Modeling …

We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete…

Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form text in images, such as paragraphs in slides or documents,…

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes reconstruction and generation, enabling direct supervision…

Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency -…

Adapting pretrained diffusion-based generative models for text-driven image editing with negligible tuning overhead has demonstrated remarkable potential. A classical adaptation paradigm, as followed by these methods, first infers the…

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…

Visual Autoregressive(VAR) models enhance generation quality but face a critical efficiency bottleneck in later stages. In this paper, we present a novel optimization framework for VAR models that fundamentally differs from prior approaches…

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether…

State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size.…

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are…

Autoregressive models have shown remarkable success in image generation by adapting sequential prediction techniques from language modeling. However, applying these approaches to images requires discretizing continuous pixel data through…

We present Infinite-Story, a training-free framework for consistent text-to-image (T2I) generation tailored for multi-prompt storytelling scenarios. Built upon a scale-wise autoregressive model, our method addresses two key challenges in…

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard…

Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…

Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…

This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts…