EffiVED:Efficient Video Editing via Text-instruction Diffusion Models
This addresses the problem of limited video editing datasets for researchers and practitioners, offering an incremental improvement by enhancing data collection methods.
The paper tackles the challenge of video editing with text instructions by introducing EffiVED, an efficient diffusion-based model that generates high-quality edited videos rapidly, using workflows to create a dataset from image editing data and open-world videos.
Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of diffusion models or specific inversion optimization to ensure high-fidelity edits. In this paper, we introduce EffiVED, an efficient diffusion-based model that directly supports instruction-guided video editing. To achieve this, we present two efficient workflows to gather video editing pairs, utilizing augmentation and fundamental vision-language techniques. These workflows transform vast image editing datasets and open-world videos into a high-quality dataset for training EffiVED. Experimental results reveal that EffiVED not only generates high-quality editing videos but also executes rapidly. Finally, we demonstrate that our data collection method significantly improves editing performance and can potentially tackle the scarcity of video editing data. Code can be found at https://github.com/alibaba/EffiVED.