AI RESEARCH
Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing
arXiv CS.CV
•
ArXi:2602.08820v2 Announce Type: replace We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the understanding and reasoning capabilities of MLLMs to produce explicit target captions to interpret user instructions. In this way, the rich contextual representations from the understanding model are directly used to guide the generative process, thereby improving performance on complex and compositional editing.