search

mbzuai-oryx / Video-ChatGPT

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
https://mbzuai-oryx.github.io/Video-ChatGPT
Creative Commons Attribution 4.0 International
1.23k stars 108 forks source link

model inference #53

Closed Xiuyuan-Chen closed 10 months ago

Xiuyuan-Chen commented 1 year ago

Could you please post a code reasoning script that doesn't use gradio, thank you very much!

ee2110 commented 1 year ago

Hi, thank you for the great work! I am also keen to know how can we make inferences without using the interface. For example, I have a list of videos, and I would like to make this model to iterate over the video list and generate output for each video.

mmaaz60 commented 1 year ago

Hi @khhuiyh, @ee2110,

Please have a look at #59, thanks