UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning

TL;DR

UniGen-1.5 is a multimodal large language model that advances image understanding, generation, and editing by integrating a unified reinforcement learning approach and improved instruction alignment, achieving state-of-the-art results.

Contribution

The paper introduces a unified RL strategy and a light instruction alignment stage that jointly enhance image editing and generation capabilities in a multimodal model.

Findings

Achieves high scores on GenEval and ImgEdit benchmarks.

Outperforms previous models like BAGEL in image understanding and editing.

Demonstrates competitive performance with proprietary models like GPT-Image-1.

Abstract

We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1.