Search papers, labs, and topics across Lattice.
The paper introduces VINO, a unified visual generator for image and video creation and editing, built upon a shared diffusion backbone conditioned on text, images, and videos. VINO couples a vision-language model (VLM) with a Multimodal Diffusion Transformer (MMDiT), encoding multimodal inputs as interleaved conditioning tokens to guide the diffusion process. VINO achieves strong visual quality, faithful instruction following, and improved reference/attribute preservation across diverse generation and editing benchmarks, demonstrating a path towards scalable unified visual generation.
Forget separate image and video models: VINO's single diffusion backbone handles both, opening the door to truly unified visual creation and editing.
We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a shared diffusion backbone that conditions on text, images and videos, enabling a broad range of visual creation and editing tasks under one model. Specifically, VINO couples a vision-language model (VLM) with a Multimodal Diffusion Transformer (MMDiT), where multimodal inputs are encoded as interleaved conditioning tokens, and then used to guide the diffusion process. This design supports multi-reference grounding, long-form instruction following, and coherent identity preservation across static and dynamic content, while avoiding modality-specific architectural components. To train such a unified system, we introduce a multi-stage training pipeline that progressively expands a video generation base model into a unified, multi-task generator capable of both image and video input and output. Across diverse generation and editing benchmarks, VINO demonstrates strong visual quality, faithful instruction following, improved reference and attribute preservation, and more controllable multi-identity edits. Our results highlight a practical path toward scalable unified visual generation, and the promise of interleaved, in-context computation as a foundation for general-purpose visual creation.
