video language model

Latest news

1. 19 Oct
   TwelveLabs Pegasus 1.5 added to Amazon Bedrock

   TwelveLabs' Pegasus 1.5 video language model is now available through Amazon Bedrock. The model produces structured, timestamped metadata from long-form video and supports new segmentation, multimodal prompting, and up-to-two-hour on-the-fly processing.

   Models · 1 source

   

Articles

No articles about video language model yet.