KwaiVGI/VIVID-10M
收藏Hugging Face2025-07-16 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/KwaiVGI/VIVID-10M
下载链接
链接失效反馈官方服务：
资源简介：
VIVID-10M是一个大规模混合图像-视频局部编辑数据集，包含970万个样本，覆盖了多种视频编辑任务。该数据集旨在降低数据构建和模型训练的成本，提供了视频和图像的局部编辑样本，支持更改和移除两种编辑模式。
VIVID-10M is a large-scale hybrid image-video local editing dataset containing 9.7M samples covering a variety of video editing tasks. It is designed to reduce the costs of data construction and model training, providing local editing samples for both video and image with support for change and remove editing modes.
提供机构：
KwaiVGI
