X-PLUG / mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
https://www.modelscope.cn/studios/damo/mPLUG-Owl
MIT License
2.33k stars 176 forks source link

The video is not supported? #169

Closed Shame-fight closed 1 year ago

Shame-fight commented 1 year ago

Thank you for your work. I have not found any support for video prediction. May I ask if video prediction is no longer supported?

MAGAer13 commented 1 year ago

We do not train extra video version of mPLUG-Owl2. You can treat video as multiple images for inference.