Search papers, labs, and topics across Lattice.
FlowInOne unifies multimodal generation tasks by converting all inputs, including text, layouts, and instructions, into visual prompts for an image-in, image-out flow matching model. This approach eliminates cross-modal alignment issues and task-specific architectures, enabling a single model to handle text-to-image generation, layout-guided editing, and visual instruction following. Experiments on the newly introduced VisPrompt-5M dataset and VP-Bench benchmark demonstrate state-of-the-art performance across these tasks, outperforming existing open-source and commercial systems.
Forget text-centric pipelines: FlowInOne achieves SOTA multimodal generation by unifying text, layouts, and instructions into a single visual flow, outperforming both open-source and commercial systems.
Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts, and editing instructions, can be unified into a single visual representation. We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. To support this, we introduce VisPrompt-5M, a large-scale dataset of 5 million visual prompt pairs spanning diverse tasks including physics-aware force dynamics and trajectory prediction, alongside VP-Bench, a rigorously curated benchmark assessing instruction faithfulness, spatial precision, visual realism, and content consistency. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance across all unified generation tasks, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.
NUS