X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again

TL;DR

X-Omni introduces a reinforcement learning approach to improve discrete autoregressive image generation, achieving state-of-the-art results in image quality and instruction following by integrating language and image generation.

Contribution

The paper presents a novel reinforcement learning framework that enhances discrete autoregressive models for image generation, enabling better quality and instruction adherence.

Findings

Achieves state-of-the-art image generation quality.

Demonstrates strong instruction-following capabilities.

Produces high-aesthetic, detailed images.

Abstract

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through autoregressive modeling with discrete tokens have been plagued by issues such as low visual fidelity, distorted outputs, and failure to adhere to complex instructions when rendering intricate details. These shortcomings are likely attributed to cumulative errors during autoregressive inference or information loss incurred during the discretization process. Probably due to this challenge, recent research has increasingly shifted toward jointly training image generation with diffusion objectives and language generation with autoregressive objectives, moving away from unified modeling approaches. In this work, we demonstrate that reinforcement learning can effectively mitigate artifacts and largely enhance the generation quality of a discrete autoregressive modeling method, thereby enabling seamless integration of image and language generation. Our framework comprises a semantic image tokenizer, a unified autoregressive model for both language and images, and an offline diffusion decoder for image generation, termed X-Omni. X-Omni achieves state-of-the-art performance in image generation tasks using a 7B language model, producing images with high aesthetic quality while exhibiting strong capabilities in following instructions and rendering long texts.