cambrian-mllm / cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
https://cambrian-mllm.github.io/
Apache License 2.0
1.4k stars 88 forks source link

Can it accept a video as input? #9

Closed LinaZhangCoding closed 6 days ago

ellisbrown commented 6 days ago

Hi, thanks for your interest! Unfortunately no. Cambrian-1 only supports single-image inputs.

We are interested in video and may explore this direction in the future though!