Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
This addresses the need for efficient and unified multi-modal AI models, though it appears incremental as it builds on prior diffusion and unified model approaches.
The paper tackles the problem of multi-modal generation and understanding by introducing Lumina-DiMOO, an open-source foundational model that uses fully discrete diffusion modeling to handle various modalities, achieving state-of-the-art performance on multiple benchmarks.
We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs and outputs across various modalities. This innovative approach allows Lumina-DiMOO to achieve higher sampling efficiency compared to previous autoregressive (AR) or hybrid AR-Diffusion paradigms and adeptly support a broad spectrum of multi-modal tasks, including text-to-image generation, image-to-image generation (e.g., image editing, subject-driven generation, and image inpainting, etc.), as well as image understanding. Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models. To foster further advancements in multi-modal and discrete diffusion model research, we release our code and checkpoints to the community. Project Page: https://synbol.github.io/Lumina-DiMOO.