Open lucasjinreal opened 4 months ago
Hello,
Thanks for your interest in our work!
Hi The meta is needed to prepare training images?
The meta data is included in the vcr_images directory. Therefore, do not worry. The metadata is there.
I wanna using official llava base. I just need to add a vipProceessor to process image right?
Correct. Visual prompt blending is all you need.
So that it can not be easily missleading model using llava original dataset.
Meanwhile, it looks like the images are missing..