Bridging Your Imagination with Audio-Video Generation via a Unified Director

Existing AI-driven video creation systems typically treat script drafting and key-shot design as two disjoint tasks: the former relies on large language models, while the latter depends on image generation models. We argue that these two tasks should be unified within a single framework, as logical reasoning and imaginative thinking are both fundamental qualities of a film director. In this work, we propose UniMAGE, a unified director model that bridges user prompts with well-structured scripts, thereby empowering non-experts to produce long-context, multi-shot films by leveraging existing audio–video generation models. To achieve this, we employ the Mixture-of-Transformers architecture that unifies text and image generation. To further enhance narrative logic and keyframe consistency, we introduce a ``first interleaving, then disentangling" training paradigm. Specifically, we first perform Interleaved Concept Learning, which utilizes interleaved text–image data to foster the model’s deeper understanding and imaginative interpretation of scripts. We then conduct Disentangled Expert Learning, which decouples script writing from keyframe generation, enabling greater flexibility and creativity in storytelling. Extensive experiments demonstrate that UniMAGE achieves state-of-the-art performance among open-source models, generating logically coherent scripts and visually consistent keyframe images.

Creating a long video with AI is challenging because the story, characters, and visuals must remain consistent across many shots. In this paper, we introduce UniMAGE, an AI system that works like a virtual director: given a simple idea, it can write a structured story, describe characters and scenes, and generate key images for important moments. Unlike existing methods that usually separate story writing from image generation, UniMAGE handles both together, helping it produce more coherent stories and more stable character appearances. Experiments show that UniMAGE performs better than existing open-source systems in long-form storytelling and visual consistency, making AI-assisted video creation more accessible for non-expert users.