Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

TL;DR

This paper introduces Janus-Pro-R1, a multimodal large language model that integrates visual comprehension and generation through reinforcement learning, enabling iterative, introspective image creation and improved semantic understanding.

Contribution

It presents a novel two-stage training method combining supervised fine-tuning and reinforcement learning to unify visual comprehension and generation in MLLMs.

Findings

Outperforms existing models in text-to-image generation and editing

Functions as a superior image semantic evaluator

Enables iterative, introspective image generation

Abstract

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation. However, these two capabilities remain largely independent, as if they are two separate functions encapsulated within the same model. Consequently, visual comprehension does not enhance visual generation, and the reasoning mechanisms of LLMs have not been fully integrated to revolutionize image generation. In this paper, we propose to enable the collaborative co-evolution of visual comprehension and generation, advancing image generation into an iterative introspective process. We introduce a two-stage training approach: supervised fine-tuning teaches the MLLM with the foundational ability to generate genuine CoT for visual generation, while reinforcement learning activates its full potential via an exploration-exploitation trade-off. Ultimately, we unlock the Aha moment in visual generation, advancing MLLMs from text-to-image tasks to unified image generation. Extensive experiments demonstrate that our model not only excels in text-to-image generation and image editing, but also functions as a superior image semantic evaluator with enhanced visual comprehension capabilities. Project Page: https://janus-pro-r1.github.io.