Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
This addresses the problem of efficient video generation for AI and creative applications, though it is incremental as it builds on existing text-to-image models.
The paper tackles the computational expense of training text-to-video generators by proposing Tune-A-Video, a method that tunes pre-trained text-to-image diffusion models using only one text-video pair, achieving promising results in generating consistent and motion-aware videos.
To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting$\unicode{x2014}$One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.