SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner
This addresses the need for efficient subject-driven video customization for users in creative or AI applications, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of generating videos for a subject from an input image with text-specified attributes, achieving state-of-the-art results in identity preservation, video dynamics, and video-text alignment without test-time fine-tuning.
We present SUGAR, a zero-shot method for subject-driven video customization. Given an input image, SUGAR is capable of generating videos for the subject contained in the image and aligning the generation with arbitrary visual attributes such as style and motion specified by user-input text. Unlike previous methods, which require test-time fine-tuning or fail to generate text-aligned videos, SUGAR achieves superior results without the need for extra cost at test-time. To enable zero-shot capability, we introduce a scalable pipeline to construct synthetic dataset which is specifically designed for subject-driven customization, leading to 2.5 millions of image-video-text triplets. Additionally, we propose several methods to enhance our model, including special attention designs, improved training strategies, and a refined sampling algorithm. Extensive experiments are conducted. Compared to previous methods, SUGAR achieves state-of-the-art results in identity preservation, video dynamics, and video-text alignment for subject-driven video customization, demonstrating the effectiveness of our proposed method.