InternVideo
Visit ToolInternVideo is an open-source video foundation model that provides generative and discriminative learning for multimodal understanding. It includes various model series and large-scale video-text datasets.
At a glance
Trending
InternVideo is an open-source video foundation model that provides generative and discriminative learning for multimodal understanding. It includes various model series and large-scale video-text datasets.
Trending
About
InternVideo is an open-source project offering a series of video foundation models and data for multimodal understanding. It encompasses models like InternVideo, InternVideo2, InternVideo2.5, and InternVideo-Next, each designed for specific advancements in video understanding, scaling, long-context modeling, and genuine world understanding. The project also provides large-scale video-text datasets such as InternVid, facilitating research and development in areas like video annotation, video-centric multimodal dialogue systems, and general video foundation models. It supports both generative and discriminative learning approaches, making it a comprehensive resource for AI applications in video analysis.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending