VIMI: Grounding Video Generation through Multi-modal Instruction

TL;DR

VIMI introduces a multimodal grounded video generation model trained on a large-scale dataset, enabling diverse, coherent, and semantically controlled video synthesis from multi-modal prompts, achieving state-of-the-art results.

Contribution

The paper presents a novel two-stage training framework for grounded video generation using multimodal prompts, addressing the lack of large-scale datasets and improving multimodal understanding.

Findings

VIMI achieves state-of-the-art results on UCF101 benchmark.

The model produces temporally coherent and semantically controlled videos.

VIMI demonstrates strong multimodal understanding and diverse video generation capabilities.

Abstract

Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datasets, resulting in a lack of visual grounding and restricting their versatility and application in multimodal integration. To address this, we construct a large-scale multimodal prompt dataset by employing retrieval methods to pair in-context examples with the given text prompts and then utilize a two-stage training strategy to enable diverse video generation tasks within the same model. In the first stage, we propose a multimodal conditional video generation framework for pretraining on these augmented datasets, establishing a foundational model for grounded video generation. Secondly, we finetune the model from the first stage on three video generation tasks, incorporating multi-modal instructions. This process further refines the model's ability to handle diverse inputs and tasks, ensuring seamless integration of multi-modal information. After this two-stage train-ing process, VIMI demonstrates multimodal understanding capabilities, producing contextually rich and personalized videos grounded in the provided inputs, as shown in Figure 1. Compared to previous visual grounded video generation methods, VIMI can synthesize consistent and temporally coherent videos with large motion while retaining the semantic control. Lastly, VIMI also achieves state-of-the-art text-to-video generation results on UCF101 benchmark.