DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
This addresses the challenge of zero-shot video generation for AI-generated content applications, though it is incremental as it builds on existing text-to-image models.
The paper tackles the problem of maintaining consistent narratives and scene composition in zero-shot text-to-video generation by introducing DirecT2V, a framework that uses large language models as frame-level directors to generate time-dependent prompts, resulting in visually coherent and storyful videos from abstract user prompts.
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling shifts in scene composition or object placement from a single abstract user prompt. Exploring the ability of large language models (LLMs) to generate time-dependent, frame-by-frame prompts, this paper introduces a new framework, dubbed DirecT2V. DirecT2V leverages instruction-tuned LLMs as directors, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent mapping the value to a different object, we equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos from abstract user prompts, successfully addressing the challenges of zero-shot video generation.