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

Inference Code and Possible Utilization of Prompts #117

Open lucasxu777 opened 4 months ago

lucasxu777 commented 4 months ago

Hi, thanks so much for the model here! I followed the steps in the offline_demo.md (assume this is something similar to inference code for testings, correct?), but it does not seem to provide place for self-made prompts. Is there any other file that I should look at?

mmaaz60 commented 4 months ago

Hi @lucasxu777,

Thank you for your interest in our work. The inference code at single_video_inferece.py would be helpful. Good Luck!