We introduce ``InteractiveVideo'', a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing users to instruct the generative model through various intuitive mechanisms during the whole generation process,
e.g. text and image prompts, human painting, drag-and-drop, etc.
We propose a Synergistic Multimodal Instruction mechanism, designed to seamlessly integrate user's multimodal instructions into generative models, thus facilitating a cooperative and responsive interaction between user inputs and the generative process.
This approach enables iterative and fine-grained refinement of the generation result through precise and effective user instructions.
With InteractiveVideo, users have the flexibility to meticulously tailor key aspects of a video until their requirements are fully satisfied, by instructing image generation, painting the image, editing image semantics, and adjusting video motions.
As a result, our framework can generate videos of high visual quality.
