Multi-image inference

[g-h-chen]

Thanks for your great work! LLaMA-VID supports single-image input and video input, but does it support multi-image input? What's the quickest way to adapt to this input?

Thanks in advance!

[yanwei-li]

In current version, we do not support multi-image input. But you can support it by using multi-image instruction data like MIMIC-IT for instruction tuning.