SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
This work addresses the problem of limited user instruction response and visual data interaction in multimodal models, offering incremental improvements for AI researchers and practitioners.
The authors tackled the gap between multimodal foundation models' capabilities and real-world applicability by developing SEED-X, which integrates comprehension of arbitrary-sized images and multi-granularity image generation, achieving competitive results on public benchmarks and effectiveness in real-world applications after instruction tuning.
The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the real-world applicability, primarily due to the model's limited capacity to effectively respond to various user instructions and interact with diverse visual data. In this work, we focus on bridging this gap through integrating two enhanced features: (1) comprehending images of arbitrary sizes and ratios, and (2) enabling multi-granularity image generation. We present a unified and versatile foundation model, namely, SEED-X, which is able to model multi-granularity visual semantics for comprehension and generation tasks. Besides the competitive results on public benchmarks, SEED-X demonstrates its effectiveness in handling real-world applications across various domains after instruction tuning. We hope that our work will inspire future research into what can be achieved by versatile multimodal foundation models in real-world applications. The models, codes, and datasets are released in https://github.com/AILab-CVC/SEED-X.