search

X-PLUG / mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
https://www.modelscope.cn/studios/damo/mPLUG-Owl
MIT License
2.25k stars 171 forks source link

about API #96

Closed LinksYuan closed 1 year ago

LinksYuan commented 1 year ago

The API provided gives examples of images, What should I do if I'm using video?

MAGAer13 commented 1 year ago

The API currently only support image only. If you want to treat the video as multiple images, just use multiple <image> as the placeholders for images.

LinksYuan commented 1 year ago

Thanks, Will a video version of the api be provided later？

MAGAer13 commented 1 year ago

You can refer to the image API implementation, the API is just a wrapper of inference procedure.