tipi2v/TIP-I2V

TIP-I2V是一个大规模的图像到视频生成数据集，包含超过170万个唯一的用户提供的文本和图像提示，以及五种最先进的图像到视频模型生成的视频。数据集旨在促进更优和更安全的图像到视频模型的发展。TIP-I2V is a large-scale image-to-video generation dataset containing over 1.70 million unique user-provided text and image prompts, as well as videos generated by five state-of-the-art image-to-video models. The dataset aims to contribute to the development of better and safer image-to-video models.