zi
menglan
·
AI & ML interests
None yet
Recent Activity
new activity
6 days ago
AIDC-AI/Ovis2-34B:How to only use the text and visual embedding?
Organizations
None yet
menglan's activity
what about the image/video captioning ability compared to other methods, like internvl-2.5, sharegpt4v and so on?
#3 opened 6 days ago
by
menglan
How to only use the text and visual embedding?
1
#2 opened 9 days ago
by
Labmem009
TypeError: chat() got an unexpected keyword argument 'video_path'
10
#2 opened about 1 month ago
by
skyernest
something wrong in caling ffmpeg to extract frames
#4 opened 24 days ago
by
menglan
Error on get_vision_tower
2
#3 opened about 1 month ago
by
Clip-AI
find a bug in load_images func
#3 opened 26 days ago
by
menglan
does it support multi-images and chinese prompt as input
#2 opened about 1 month ago
by
menglan