Ovis-U1 Technical Report

TL;DR

Ovis-U1 is a large, unified multimodal model that integrates understanding, generation, and editing, achieving state-of-the-art performance across multiple benchmarks by combining these capabilities in a single system.

Contribution

It introduces a novel unified training approach for multimodal tasks, combining understanding and generation to improve overall performance in a single model.

Findings

Achieves 69.6 on OpenCompass benchmark, surpassing recent models.

Scores 83.72 on DPG-Bench for text-to-image generation.

Attains 6.42 on GEdit-Bench for image editing.

Abstract

In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.