Video-LLaVA
Video-LLaVA copied to clipboard
Can the model be used with 2 images as an input
Or a video with less than 8 frames?
Officially do not support, but you can modify it by yourself. https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/videollava/model/multimodal_encoder/languagebind/video/processing_video.py#L72