More Research
ShareGPT4V
ShareGPT4Video
MMStar
ShareGPT4Omni:
Towards Building Omni Large Multi-modal Models with Comprehensive Multi-modal Annotations
ShareGPT4V Team
Code
🤗
Dataset
🔥
What's New
[2024.06.07]
ShareGPT4Video
is released, which contains
40K
detailed video
291 hours
captions constructed using GPT4V, and
4.8M
high quality video
3000 hours
captions constructed using ShareCaptioner-Video!
[2023.11.21]
ShareGPT4V
is released, which contains
100K
GPT4-Vision-generated image captions, and
1.2M
high quality captions constructed using ShareCaptioner!
ShareGPT4Omni Dataset
XXXXXX
📃 BibTeX
@article{ }